Merge tag 'net-6.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from Netfilter and IPsec.

  Current release - regressions:

   - netfilter: nft_set_pipapo:
      - don't return bogus extension pointer
      - fix null deref for empty set

  Current release - new code bugs:

   - core: prevent deadlocks when enabling NAPIs with mixed kthread
     config

   - eth: netdevsim: Fix wild pointer access in nsim_queue_free().

  Previous releases - regressions:

   - page_pool: allow enabling recycling late, fix false positive
     warning

   - sched: ets: use old 'nbands' while purging unused classes

   - xfrm:
      - restore GSO for SW crypto
      - bring back device check in validate_xmit_xfrm

   - tls: handle data disappearing from under the TLS ULP

   - ptp: prevent possible ABBA deadlock in ptp_clock_freerun()

   - eth:
      - bnxt: fill data page pool with frags if PAGE_SIZE > BNXT_RX_PAGE_SIZE
      - hv_netvsc: fix panic during namespace deletion with VF

  Previous releases - always broken:

   - netfilter: fix refcount leak on table dump

   - vsock: do not allow binding to VMADDR_PORT_ANY

   - sctp: linearize cloned gso packets in sctp_rcv

   - eth:
      - hibmcge: fix the division by zero issue
      - microchip: fix KSZ8863 reset problem"

* tag 'net-6.17-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (54 commits)
  net: usb: asix_devices: add phy_mask for ax88772 mdio bus
  net: kcm: Fix race condition in kcm_unattach()
  selftests: net/forwarding: test purge of active DWRR classes
  net/sched: ets: use old 'nbands' while purging unused classes
  bnxt: fill data page pool with frags if PAGE_SIZE > BNXT_RX_PAGE_SIZE
  netdevsim: Fix wild pointer access in nsim_queue_free().
  net: mctp: Fix bad kfree_skb in bind lookup test
  netfilter: nf_tables: reject duplicate device on updates
  ipvs: Fix estimator kthreads preferred affinity
  netfilter: nft_set_pipapo: fix null deref for empty set
  selftests: tls: test TCP stealing data from under the TLS socket
  tls: handle data disappearing from under the TLS ULP
  ptp: prevent possible ABBA deadlock in ptp_clock_freerun()
  ixgbe: prevent from unwanted interface name changes
  devlink: let driver opt out of automatic phys_port_name generation
  net: prevent deadlocks when enabling NAPIs with mixed kthread config
  net: update NAPI threaded config even for disabled NAPIs
  selftests: drv-net: don't assume device has only 2 queues
  docs: Fix name for net.ipv4.udp_child_hash_entries
  riscv: dts: thead: Add APB clocks for TH1520 GMACs
  ...

Author: torvalds

Documentation/devicetree/bindings/net/thead,th1520-gmac.yaml

@@ -62,11 +62,13 @@ properties:
     items:
       - description: GMAC main clock
       - description: Peripheral registers interface clock
+      - description: APB glue registers interface clock
 
   clock-names:
     items:
       - const: stmmaceth
       - const: pclk
+      - const: apb
 
   interrupts:
     items:
@@ -88,8 +90,8 @@ examples:
         compatible = "thead,th1520-gmac", "snps,dwmac-3.70a";
         reg = <0xe7070000 0x2000>, <0xec003000 0x1000>;
         reg-names = "dwmac", "apb";
-        clocks = <&clk 1>, <&clk 2>;
-        clock-names = "stmmaceth", "pclk";
+        clocks = <&clk 1>, <&clk 2>, <&clk 3>;
+        clock-names = "stmmaceth", "pclk", "apb";
         interrupts = <66>;
         interrupt-names = "macirq";
         phy-mode = "rgmii-id";

Documentation/networking/ip-sysctl.rst

@@ -1420,7 +1420,7 @@ udp_hash_entries - INTEGER
 	A negative value means the networking namespace does not own its
 	hash buckets and shares the initial networking namespace's one.
 
-udp_child_ehash_entries - INTEGER
+udp_child_hash_entries - INTEGER
 	Control the number of hash buckets for UDP sockets in the child
 	networking namespace, which must be set before clone() or unshare().
 

MAINTAINERS

@@ -12584,10 +12584,9 @@ S:	Supported
 F:	drivers/cpufreq/intel_pstate.c
 
 INTEL PTP DFL ToD DRIVER
-M:	Tianfei Zhang <[email protected]>
 L:	[email protected]
 L:	[email protected]
-S:	Maintained
+S:	Orphan
 F:	drivers/ptp/ptp_dfl_tod.c
 
 INTEL QUADRATURE ENCODER PERIPHERAL DRIVER
@@ -12725,9 +12724,8 @@ S:	Maintained
 F:	drivers/platform/x86/intel/wmi/thunderbolt.c
 
 INTEL WWAN IOSM DRIVER
-M:	M Chetan Kumar <[email protected]>
 L:	[email protected]
-S:	Maintained
+S:	Orphan
 F:	drivers/net/wwan/iosm/
 
 INTEL(R) FLEXIBLE RETURN AND EVENT DELIVERY
@@ -15674,7 +15672,6 @@ MEDIATEK T7XX 5G WWAN MODEM DRIVER
 M:	Chandrashekar Devegowda <[email protected]>
 R:	Chiranjeevi Rapolu <[email protected]>
 R:	Liu Haijun <[email protected]>
-R:	M Chetan Kumar <[email protected]>
 R:	Ricardo Martinez <[email protected]>
 L:	[email protected]
 S:	Supported
@@ -17451,6 +17448,7 @@ F:	drivers/net/ethernet/neterion/
 NETFILTER
 M:	Pablo Neira Ayuso <[email protected]>
 M:	Jozsef Kadlecsik <[email protected]>
+M:	Florian Westphal <[email protected]>
 L:	[email protected]
 L:	[email protected]
 S:	Maintained

arch/riscv/boot/dts/thead/th1520.dtsi

@@ -297,8 +297,9 @@
 			reg-names = "dwmac", "apb";
 			interrupts = <67 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "macirq";
-			clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>;
-			clock-names = "stmmaceth", "pclk";
+			clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC1>,
+				 <&clk CLK_PERISYS_APB4_HCLK>;
+			clock-names = "stmmaceth", "pclk", "apb";
 			snps,pbl = <32>;
 			snps,fixed-burst;
 			snps,multicast-filter-bins = <64>;
@@ -319,8 +320,9 @@
 			reg-names = "dwmac", "apb";
 			interrupts = <66 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "macirq";
-			clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>;
-			clock-names = "stmmaceth", "pclk";
+			clocks = <&clk CLK_GMAC_AXI>, <&clk CLK_GMAC0>,
+				 <&clk CLK_PERISYS_APB4_HCLK>;
+			clock-names = "stmmaceth", "pclk", "apb";
 			snps,pbl = <32>;
 			snps,fixed-burst;
 			snps,multicast-filter-bins = <64>;

drivers/net/dsa/microchip/ksz8.c

@@ -36,15 +36,14 @@
 
 static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
 {
-	regmap_update_bits(ksz_regmap_8(dev), addr, bits, set ? bits : 0);
+	ksz_rmw8(dev, addr, bits, set ? bits : 0);
 }
 
 static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
 			 bool set)
 {
-	regmap_update_bits(ksz_regmap_8(dev),
-			   dev->dev_ops->get_port_addr(port, offset),
-			   bits, set ? bits : 0);
+	ksz_rmw8(dev, dev->dev_ops->get_port_addr(port, offset), bits,
+		 set ? bits : 0);
 }
 
 /**
@@ -1955,16 +1954,19 @@ int ksz8_setup(struct dsa_switch *ds)
 	ksz_cfg(dev, S_LINK_AGING_CTRL, SW_LINK_AUTO_AGING, true);
 
 	/* Enable aggressive back off algorithm in half duplex mode. */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_1,
-			   SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
+	ret = ksz_rmw8(dev, REG_SW_CTRL_1, SW_AGGR_BACKOFF, SW_AGGR_BACKOFF);
+	if (ret)
+		return ret;
 
 	/*
 	 * Make sure unicast VLAN boundary is set as default and
 	 * enable no excessive collision drop.
 	 */
-	regmap_update_bits(ksz_regmap_8(dev), REG_SW_CTRL_2,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
-			   UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
+	ret = ksz_rmw8(dev, REG_SW_CTRL_2,
+		       UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP,
+		       UNICAST_VLAN_BOUNDARY | NO_EXC_COLLISION_DROP);
+	if (ret)
+		return ret;
 
 	ksz_cfg(dev, S_REPLACE_VID_CTRL, SW_REPLACE_VID, false);
 

drivers/net/dsa/microchip/ksz_common.c

@@ -1447,6 +1447,7 @@ static const struct regmap_range ksz8873_valid_regs[] = {
 	regmap_reg_range(0x3f, 0x3f),
 
 	/* advanced control registers */
+	regmap_reg_range(0x43, 0x43),
 	regmap_reg_range(0x60, 0x6f),
 	regmap_reg_range(0x70, 0x75),
 	regmap_reg_range(0x76, 0x78),

drivers/net/ethernet/broadcom/bnxt/bnxt.c

@@ -926,15 +926,21 @@ static struct page *__bnxt_alloc_rx_page(struct bnxt *bp, dma_addr_t *mapping,
 
 static netmem_ref __bnxt_alloc_rx_netmem(struct bnxt *bp, dma_addr_t *mapping,
 					 struct bnxt_rx_ring_info *rxr,
+					 unsigned int *offset,
 					 gfp_t gfp)
 {
 	netmem_ref netmem;
 
-	netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+	if (PAGE_SIZE > BNXT_RX_PAGE_SIZE) {
+		netmem = page_pool_alloc_frag_netmem(rxr->page_pool, offset, BNXT_RX_PAGE_SIZE, gfp);
+	} else {
+		netmem = page_pool_alloc_netmems(rxr->page_pool, gfp);
+		*offset = 0;
+	}
 	if (!netmem)
 		return 0;
 
-	*mapping = page_pool_get_dma_addr_netmem(netmem);
+	*mapping = page_pool_get_dma_addr_netmem(netmem) + *offset;
 	return netmem;
 }
 
@@ -1029,7 +1035,7 @@ static int bnxt_alloc_rx_netmem(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 	dma_addr_t mapping;
 	netmem_ref netmem;
 
-	netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, gfp);
+	netmem = __bnxt_alloc_rx_netmem(bp, &mapping, rxr, &offset, gfp);
 	if (!netmem)
 		return -ENOMEM;
 
@@ -3819,7 +3825,6 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	if (BNXT_RX_PAGE_MODE(bp))
 		pp.pool_size += bp->rx_ring_size / rx_size_fac;
 	pp.nid = numa_node;
-	pp.napi = &rxr->bnapi->napi;
 	pp.netdev = bp->dev;
 	pp.dev = &bp->pdev->dev;
 	pp.dma_dir = bp->rx_dir;
@@ -3851,6 +3856,12 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp,
 	return PTR_ERR(pool);
 }
 
+static void bnxt_enable_rx_page_pool(struct bnxt_rx_ring_info *rxr)
+{
+	page_pool_enable_direct_recycling(rxr->head_pool, &rxr->bnapi->napi);
+	page_pool_enable_direct_recycling(rxr->page_pool, &rxr->bnapi->napi);
+}
+
 static int bnxt_alloc_rx_agg_bmap(struct bnxt *bp, struct bnxt_rx_ring_info *rxr)
 {
 	u16 mem_size;
@@ -3889,6 +3900,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp)
 		rc = bnxt_alloc_rx_page_pool(bp, rxr, cpu_node);
 		if (rc)
 			return rc;
+		bnxt_enable_rx_page_pool(rxr);
 
 		rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0);
 		if (rc < 0)
@@ -16031,6 +16043,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 			goto err_reset;
 	}
 
+	bnxt_enable_rx_page_pool(rxr);
 	napi_enable_locked(&bnapi->napi);
 	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
 

drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c

@@ -53,9 +53,11 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
 {
 	int ret;
 
-	ASSERT_RTNL();
+	if (test_and_set_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return -EBUSY;
 
 	if (netif_running(priv->netdev)) {
+		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 		dev_warn(&priv->pdev->dev,
 			 "failed to reset because port is up\n");
 		return -EBUSY;
@@ -64,7 +66,6 @@ static int hbg_reset_prepare(struct hbg_priv *priv, enum hbg_reset_type type)
 	netif_device_detach(priv->netdev);
 
 	priv->reset_type = type;
-	set_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	clear_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
 	ret = hbg_hw_event_notify(priv, HBG_HW_EVENT_RESET);
 	if (ret) {
@@ -84,29 +85,26 @@ static int hbg_reset_done(struct hbg_priv *priv, enum hbg_reset_type type)
 	    type != priv->reset_type)
 		return 0;
 
-	ASSERT_RTNL();
-
-	clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 	ret = hbg_rebuild(priv);
 	if (ret) {
 		priv->stats.reset_fail_cnt++;
 		set_bit(HBG_NIC_STATE_RESET_FAIL, &priv->state);
+		clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 		dev_err(&priv->pdev->dev, "failed to rebuild after reset\n");
 		return ret;
 	}
 
 	netif_device_attach(priv->netdev);
+	clear_bit(HBG_NIC_STATE_RESETTING, &priv->state);
 
 	dev_info(&priv->pdev->dev, "reset done\n");
 	return ret;
 }
 
-/* must be protected by rtnl lock */
 int hbg_reset(struct hbg_priv *priv)
 {
 	int ret;
 
-	ASSERT_RTNL();
 	ret = hbg_reset_prepare(priv, HBG_RESET_TYPE_FUNCTION);
 	if (ret)
 		return ret;
@@ -171,7 +169,6 @@ static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct hbg_priv *priv = netdev_priv(netdev);
 
-	rtnl_lock();
 	hbg_reset_prepare(priv, HBG_RESET_TYPE_FLR);
 }
 
@@ -181,7 +178,6 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
 	struct hbg_priv *priv = netdev_priv(netdev);
 
 	hbg_reset_done(priv, HBG_RESET_TYPE_FLR);
-	rtnl_unlock();
 }
 
 static const struct pci_error_handlers hbg_pci_err_handler = {

drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c

@@ -12,6 +12,8 @@
 
 #define HBG_HW_EVENT_WAIT_TIMEOUT_US	(2 * 1000 * 1000)
 #define HBG_HW_EVENT_WAIT_INTERVAL_US	(10 * 1000)
+#define HBG_MAC_LINK_WAIT_TIMEOUT_US	(500 * 1000)
+#define HBG_MAC_LINK_WAIT_INTERVAL_US	(5 * 1000)
 /* little endian or big endian.
  * ctrl means packet description, data means skb packet data
  */
@@ -228,6 +230,9 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr)
 
 void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex)
 {
+	u32 link_status;
+	int ret;
+
 	hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE);
 
 	hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR,
@@ -239,8 +244,14 @@ void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex)
 
 	hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE);
 
-	if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
-				HBG_REG_AN_NEG_STATE_NP_LINK_OK_B))
+	/* wait MAC link up */
+	ret = readl_poll_timeout(priv->io_base + HBG_REG_AN_NEG_STATE_ADDR,
+				 link_status,
+				 FIELD_GET(HBG_REG_AN_NEG_STATE_NP_LINK_OK_B,
+					   link_status),
+				 HBG_MAC_LINK_WAIT_INTERVAL_US,
+				 HBG_MAC_LINK_WAIT_TIMEOUT_US);
+	if (ret)
 		hbg_np_link_fail_task_schedule(priv);
 }
 

drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.h

@@ -29,7 +29,12 @@ static inline bool hbg_fifo_is_full(struct hbg_priv *priv, enum hbg_dir dir)
 
 static inline u32 hbg_get_queue_used_num(struct hbg_ring *ring)
 {
-	return (ring->ntu + ring->len - ring->ntc) % ring->len;
+	u32 len = READ_ONCE(ring->len);
+
+	if (!len)
+		return 0;
+
+	return (READ_ONCE(ring->ntu) + len - READ_ONCE(ring->ntc)) % len;
 }
 
 netdev_tx_t hbg_net_start_xmit(struct sk_buff *skb, struct net_device *netdev);