Merge tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from BPF and netfilter.

  Current release - regressions:

   - core: fix undefined behavior in netdev name allocation

   - bpf: do not allocate percpu memory at init stage

   - netfilter: nf_tables: split async and sync catchall in two
     functions

   - mptcp: fix possible NULL pointer dereference on close

  Current release - new code bugs:

   - eth: ice: dpll: fix initial lock status of dpll

  Previous releases - regressions:

   - bpf: fix precision backtracking instruction iteration

   - af_unix: fix use-after-free in unix_stream_read_actor()

   - tipc: fix kernel-infoleak due to uninitialized TLV value

   - eth: bonding: stop the device in bond_setup_by_slave()

   - eth: mlx5:
      - fix double free of encap_header
      - avoid referencing skb after free-ing in drop path

   - eth: hns3: fix VF reset

   - eth: mvneta: fix calls to page_pool_get_stats

  Previous releases - always broken:

   - core: set SOCK_RCU_FREE before inserting socket into hashtable

   - bpf: fix control-flow graph checking in privileged mode

   - eth: ppp: limit MRU to 64K

   - eth: stmmac: avoid rx queue overrun

   - eth: icssg-prueth: fix error cleanup on failing initialization

   - eth: hns3: fix out-of-bounds access may occur when coalesce info is
     read via debugfs

   - eth: cortina: handle large frames

  Misc:

   - selftests: gso: support CONFIG_MAX_SKB_FRAGS up to 45"

* tag 'net-6.7-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (78 commits)
  macvlan: Don't propagate promisc change to lower dev in passthru
  net: sched: do not offload flows with a helper in act_ct
  net/mlx5e: Check return value of snprintf writing to fw_version buffer for representors
  net/mlx5e: Check return value of snprintf writing to fw_version buffer
  net/mlx5e: Reduce the size of icosq_str
  net/mlx5: Increase size of irq name buffer
  net/mlx5e: Update doorbell for port timestamping CQ before the software counter
  net/mlx5e: Track xmit submission to PTP WQ after populating metadata map
  net/mlx5e: Avoid referencing skb after free-ing in drop path of mlx5e_sq_xmit_wqe
  net/mlx5e: Don't modify the peer sent-to-vport rules for IPSec offload
  net/mlx5e: Fix pedit endianness
  net/mlx5e: fix double free of encap_header in update funcs
  net/mlx5e: fix double free of encap_header
  net/mlx5: Decouple PHC .adjtime and .adjphase implementations
  net/mlx5: DR, Allow old devices to use multi destination FTE
  net/mlx5: Free used cpus mask when an IRQ is released
  Revert "net/mlx5: DR, Supporting inline WQE when possible"
  bpf: Do not allocate percpu memory at init stage
  net: Fix undefined behavior in netdev name allocation
  dt-bindings: net: ethernet-controller: Fix formatting error
  ...

Author: torvalds

Documentation/devicetree/bindings/net/ethernet-controller.yaml

@@ -275,12 +275,12 @@ allOf:
       properties:
         rx-internal-delay-ps:
           description:
-            RGMII Receive Clock Delay defined in pico seconds.This is used for
+            RGMII Receive Clock Delay defined in pico seconds. This is used for
             controllers that have configurable RX internal delays. If this
             property is present then the MAC applies the RX delay.
         tx-internal-delay-ps:
           description:
-            RGMII Transmit Clock Delay defined in pico seconds.This is used for
+            RGMII Transmit Clock Delay defined in pico seconds. This is used for
             controllers that have configurable TX internal delays. If this
             property is present then the MAC applies the TX delay.
 

MAINTAINERS

@@ -21768,7 +21768,9 @@ F:	Documentation/devicetree/bindings/counter/ti-eqep.yaml
 F:	drivers/counter/ti-eqep.c
 
 TI ETHERNET SWITCH DRIVER (CPSW)
-R:	Grygorii Strashko <grygorii.strashko@ti.com>
+R:	Siddharth Vadapalli <s-vadapalli@ti.com>
+R:	Ravi Gunasekaran <r-gunasekaran@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
 L:	linux-omap@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Maintained
@@ -21792,6 +21794,15 @@ F:	Documentation/devicetree/bindings/media/i2c/ti,ds90*
 F:	drivers/media/i2c/ds90*
 F:	include/media/i2c/ds90*
 
+TI ICSSG ETHERNET DRIVER (ICSSG)
+R:	MD Danish Anwar <danishanwar@ti.com>
+R:	Roger Quadros <rogerq@kernel.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/ti,icss*.yaml
+F:	drivers/net/ethernet/ti/icssg/*
+
 TI J721E CSI2RX DRIVER
 M:	Jai Luthra <j-luthra@ti.com>
 L:	linux-media@vger.kernel.org

drivers/net/bonding/bond_main.c

@@ -1500,6 +1500,10 @@ static void bond_compute_features(struct bonding *bond)
 static void bond_setup_by_slave(struct net_device *bond_dev,
 				struct net_device *slave_dev)
 {
+	bool was_up = !!(bond_dev->flags & IFF_UP);
+
+	dev_close(bond_dev);
+
 	bond_dev->header_ops	    = slave_dev->header_ops;
 
 	bond_dev->type		    = slave_dev->type;
@@ -1514,6 +1518,8 @@ static void bond_setup_by_slave(struct net_device *bond_dev,
 		bond_dev->flags &= ~(IFF_BROADCAST | IFF_MULTICAST);
 		bond_dev->flags |= (IFF_POINTOPOINT | IFF_NOARP);
 	}
+	if (was_up)
+		dev_open(bond_dev, NULL);
 }
 
 /* On bonding slaves other than the currently active slave, suppress

drivers/net/ethernet/amd/pds_core/adminq.c

@@ -146,7 +146,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 	}
 
 	queue_work(pdsc->wq, &qcq->work);
-	pds_core_intr_mask(&pdsc->intr_ctrl[irq], PDS_CORE_INTR_MASK_CLEAR);
+	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
 
 	return IRQ_HANDLED;
 }

drivers/net/ethernet/amd/pds_core/core.h

@@ -15,7 +15,7 @@
 #define PDSC_DRV_DESCRIPTION	"AMD/Pensando Core Driver"
 
 #define PDSC_WATCHDOG_SECS	5
-#define PDSC_QUEUE_NAME_MAX_SZ  32
+#define PDSC_QUEUE_NAME_MAX_SZ  16
 #define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false

drivers/net/ethernet/amd/pds_core/dev.c

@@ -261,10 +261,14 @@ static int pdsc_identify(struct pdsc *pdsc)
 	struct pds_core_drv_identity drv = {};
 	size_t sz;
 	int err;
+	int n;
 
 	drv.drv_type = cpu_to_le32(PDS_DRIVER_LINUX);
-	snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
-		 "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	/* Catching the return quiets a Wformat-truncation complaint */
+	n = snprintf(drv.driver_ver_str, sizeof(drv.driver_ver_str),
+		     "%s %s", PDS_CORE_DRV_NAME, utsname()->release);
+	if (n > sizeof(drv.driver_ver_str))
+		dev_dbg(pdsc->dev, "release name truncated, don't care\n");
 
 	/* Next let's get some info about the device
 	 * We use the devcmd_lock at this level in order to

drivers/net/ethernet/amd/pds_core/devlink.c

@@ -104,7 +104,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	struct pds_core_fw_list_info fw_list;
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
-	char buf[16];
+	char buf[32];
 	int listlen;
 	int err;
 	int i;

drivers/net/ethernet/broadcom/tg3.c

@@ -6889,7 +6889,7 @@ static int tg3_rx(struct tg3_napi *tnapi, int budget)
 				       desc_idx, *post_ptr);
 		drop_it_no_recycle:
 			/* Other statistics kept track of by card. */
-			tp->rx_dropped++;
+			tnapi->rx_dropped++;
 			goto next_pkt;
 		}
 
@@ -7918,8 +7918,10 @@ static int tg3_tso_bug(struct tg3 *tp, struct tg3_napi *tnapi,
 
 	segs = skb_gso_segment(skb, tp->dev->features &
 				    ~(NETIF_F_TSO | NETIF_F_TSO6));
-	if (IS_ERR(segs) || !segs)
+	if (IS_ERR(segs) || !segs) {
+		tnapi->tx_dropped++;
 		goto tg3_tso_bug_end;
+	}
 
 	skb_list_walk_safe(segs, seg, next) {
 		skb_mark_not_on_list(seg);
@@ -8190,7 +8192,7 @@ static netdev_tx_t __tg3_start_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 	dev_kfree_skb_any(skb);
 drop_nofree:
-	tp->tx_dropped++;
+	tnapi->tx_dropped++;
 	return NETDEV_TX_OK;
 }
 
@@ -9405,7 +9407,7 @@ static void __tg3_set_rx_mode(struct net_device *);
 /* tp->lock is held. */
 static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 {
-	int err;
+	int err, i;
 
 	tg3_stop_fw(tp);
 
@@ -9426,6 +9428,13 @@ static int tg3_halt(struct tg3 *tp, int kind, bool silent)
 
 		/* And make sure the next sample is new data */
 		memset(tp->hw_stats, 0, sizeof(struct tg3_hw_stats));
+
+		for (i = 0; i < TG3_IRQ_MAX_VECS; ++i) {
+			struct tg3_napi *tnapi = &tp->napi[i];
+
+			tnapi->rx_dropped = 0;
+			tnapi->tx_dropped = 0;
+		}
 	}
 
 	return err;
@@ -11975,6 +11984,9 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 {
 	struct rtnl_link_stats64 *old_stats = &tp->net_stats_prev;
 	struct tg3_hw_stats *hw_stats = tp->hw_stats;
+	unsigned long rx_dropped;
+	unsigned long tx_dropped;
+	int i;
 
 	stats->rx_packets = old_stats->rx_packets +
 		get_stat64(&hw_stats->rx_ucast_packets) +
@@ -12021,8 +12033,26 @@ static void tg3_get_nstats(struct tg3 *tp, struct rtnl_link_stats64 *stats)
 	stats->rx_missed_errors = old_stats->rx_missed_errors +
 		get_stat64(&hw_stats->rx_discards);
 
-	stats->rx_dropped = tp->rx_dropped;
-	stats->tx_dropped = tp->tx_dropped;
+	/* Aggregate per-queue counters. The per-queue counters are updated
+	 * by a single writer, race-free. The result computed by this loop
+	 * might not be 100% accurate (counters can be updated in the middle of
+	 * the loop) but the next tg3_get_nstats() will recompute the current
+	 * value so it is acceptable.
+	 *
+	 * Note that these counters wrap around at 4G on 32bit machines.
+	 */
+	rx_dropped = (unsigned long)(old_stats->rx_dropped);
+	tx_dropped = (unsigned long)(old_stats->tx_dropped);
+
+	for (i = 0; i < tp->irq_cnt; i++) {
+		struct tg3_napi *tnapi = &tp->napi[i];
+
+		rx_dropped += tnapi->rx_dropped;
+		tx_dropped += tnapi->tx_dropped;
+	}
+
+	stats->rx_dropped = rx_dropped;
+	stats->tx_dropped = tx_dropped;
 }
 
 static int tg3_get_regs_len(struct net_device *dev)

drivers/net/ethernet/broadcom/tg3.h

@@ -3018,6 +3018,7 @@ struct tg3_napi {
 	u16				*rx_rcb_prod_idx;
 	struct tg3_rx_prodring_set	prodring;
 	struct tg3_rx_buffer_desc	*rx_rcb;
+	unsigned long			rx_dropped;
 
 	u32				tx_prod	____cacheline_aligned;
 	u32				tx_cons;
@@ -3026,6 +3027,7 @@ struct tg3_napi {
 	u32				prodmbox;
 	struct tg3_tx_buffer_desc	*tx_ring;
 	struct tg3_tx_ring_info		*tx_buffers;
+	unsigned long			tx_dropped;
 
 	dma_addr_t			status_mapping;
 	dma_addr_t			rx_rcb_mapping;
@@ -3220,8 +3222,6 @@ struct tg3 {
 
 
 	/* begin "everything else" cacheline(s) section */
-	unsigned long			rx_dropped;
-	unsigned long			tx_dropped;
 	struct rtnl_link_stats64	net_stats_prev;
 	struct tg3_ethtool_stats	estats_prev;
 

drivers/net/ethernet/cortina/gemini.c

@@ -432,8 +432,8 @@ static const struct gmac_max_framelen gmac_maxlens[] = {
 		.val = CONFIG0_MAXLEN_1536,
 	},
 	{
-		.max_l3_len = 1542,
-		.val = CONFIG0_MAXLEN_1542,
+		.max_l3_len = 1548,
+		.val = CONFIG0_MAXLEN_1548,
 	},
 	{
 		.max_l3_len = 9212,
@@ -1145,6 +1145,7 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 	dma_addr_t mapping;
 	unsigned short mtu;
 	void *buffer;
+	int ret;
 
 	mtu  = ETH_HLEN;
 	mtu += netdev->mtu;
@@ -1159,9 +1160,30 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
 		word3 |= mtu;
 	}
 
-	if (skb->ip_summed != CHECKSUM_NONE) {
+	if (skb->len >= ETH_FRAME_LEN) {
+		/* Hardware offloaded checksumming isn't working on frames
+		 * bigger than 1514 bytes. A hypothesis about this is that the
+		 * checksum buffer is only 1518 bytes, so when the frames get
+		 * bigger they get truncated, or the last few bytes get
+		 * overwritten by the FCS.
+		 *
+		 * Just use software checksumming and bypass on bigger frames.
+		 */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			ret = skb_checksum_help(skb);
+			if (ret)
+				return ret;
+		}
+		word1 |= TSS_BYPASS_BIT;
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		int tcp = 0;
 
+		/* We do not switch off the checksumming on non TCP/UDP
+		 * frames: as is shown from tests, the checksumming engine
+		 * is smart enough to see that a frame is not actually TCP
+		 * or UDP and then just pass it through without any changes
+		 * to the frame.
+		 */
 		if (skb->protocol == htons(ETH_P_IP)) {
 			word1 |= TSS_IP_CHKSUM_BIT;
 			tcp = ip_hdr(skb)->protocol == IPPROTO_TCP;
@@ -1978,15 +2000,6 @@ static int gmac_change_mtu(struct net_device *netdev, int new_mtu)
 	return 0;
 }
 
-static netdev_features_t gmac_fix_features(struct net_device *netdev,
-					   netdev_features_t features)
-{
-	if (netdev->mtu + ETH_HLEN + VLAN_HLEN > MTU_SIZE_BIT_MASK)
-		features &= ~GMAC_OFFLOAD_FEATURES;
-
-	return features;
-}
-
 static int gmac_set_features(struct net_device *netdev,
 			     netdev_features_t features)
 {
@@ -2212,7 +2225,6 @@ static const struct net_device_ops gmac_351x_ops = {
 	.ndo_set_mac_address	= gmac_set_mac_address,
 	.ndo_get_stats64	= gmac_get_stats64,
 	.ndo_change_mtu		= gmac_change_mtu,
-	.ndo_fix_features	= gmac_fix_features,
 	.ndo_set_features	= gmac_set_features,
 };
 
@@ -2464,11 +2476,12 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
 	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
-	/* We can handle jumbo frames up to 10236 bytes so, let's accept
-	 * payloads of 10236 bytes minus VLAN and ethernet header
+	/* We can receive jumbo frames up to 10236 bytes but only
+	 * transmit 2047 bytes so, let's accept payloads of 2047
+	 * bytes minus VLAN and ethernet header
 	 */
 	netdev->min_mtu = ETH_MIN_MTU;
-	netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
+	netdev->max_mtu = MTU_SIZE_BIT_MASK - VLAN_ETH_HLEN;
 
 	port->freeq_refill = 0;
 	netif_napi_add(netdev, &port->napi, gmac_napi_poll);