Merge tag 'net-5.16-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter.

  Current release - regressions:

   - revert "tipc: use consistent GFP flags"

  Previous releases - regressions:

   - igb: fix deadlock caused by taking RTNL in runtime resume path

   - accept UFOv6 packages in virtio_net_hdr_to_skb

   - netfilter: fix regression in looped (broad|multi)cast's MAC
     handling

   - bridge: fix ioctl old_deviceless bridge argument

   - ice: xsk: do not clear status_error0 for ntu + nb_buffs descriptor,
     avoid stalls when multiple sockets use an interface

  Previous releases - always broken:

   - inet: fully convert sk->sk_rx_dst to RCU rules

   - veth: ensure skb entering GRO are not cloned

   - sched: fix zone matching for invalid conntrack state

   - bonding: fix ad_actor_system option setting to default

   - nf_tables: fix use-after-free in nft_set_catchall_destroy()

   - lantiq_xrx200: increase buffer reservation to avoid mem corruption

   - ice: xsk: avoid leaking app buffers during clean up

   - tun: avoid double free in tun_free_netdev"

* tag 'net-5.16-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (45 commits)
  net: stmmac: dwmac-visconti: Fix value of ETHER_CLK_SEL_FREQ_SEL_2P5M
  r8152: sync ocp base
  r8152: fix the force speed doesn't work for RTL8156
  net: bridge: fix ioctl old_deviceless bridge argument
  net: stmmac: ptp: fix potentially overflowing expression
  net: dsa: tag_ocelot: use traffic class to map priority on injected header
  veth: ensure skb entering GRO are not cloned.
  asix: fix wrong return value in asix_check_host_enable()
  asix: fix uninit-value in asix_mdio_read()
  sfc: falcon: Check null pointer of rx_queue->page_ring
  sfc: Check null pointer of rx_queue->page_ring
  net: ks8851: Check for error irq
  drivers: net: smc911x: Check for error irq
  fjes: Check for error irq
  bonding: fix ad_actor_system option setting to default
  igb: fix deadlock caused by taking RTNL in RPM resume path
  gve: Correct order of processing device options
  net: skip virtio_net_hdr_set_proto if protocol already set
  net: accept UFOv6 packages in virtio_net_hdr_to_skb
  docs: networking: replace skb_hwtstamp_tx with skb_tstamp_tx
  ...

Author: torvalds

Documentation/networking/bonding.rst

@@ -196,11 +196,12 @@ ad_actor_sys_prio
 ad_actor_system
 
 	In an AD system, this specifies the mac-address for the actor in
-	protocol packet exchanges (LACPDUs). The value cannot be NULL or
-	multicast. It is preferred to have the local-admin bit set for this
-	mac but driver does not enforce it. If the value is not given then
-	system defaults to using the masters' mac address as actors' system
-	address.
+	protocol packet exchanges (LACPDUs). The value cannot be a multicast
+	address. If the all-zeroes MAC is specified, bonding will internally
+	use the MAC of the bond itself. It is preferred to have the
+	local-admin bit set for this mac but driver does not enforce it. If
+	the value is not given then system defaults to using the masters'
+	mac address as actors' system address.
 
 	This parameter has effect only in 802.3ad mode and is available through
 	SysFs interface.

Documentation/networking/device_drivers/ethernet/freescale/dpaa2/overview.rst

@@ -183,6 +183,7 @@ PHY and allows physical transmission and reception of Ethernet frames.
   IRQ config, enable, reset
 
 DPNI (Datapath Network Interface)
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 Contains TX/RX queues, network interface configuration, and RX buffer pool
 configuration mechanisms.  The TX/RX queues are in memory and are identified
 by queue number.

Documentation/networking/timestamping.rst

@@ -582,8 +582,8 @@ Time stamps for outgoing packets are to be generated as follows:
   and hardware timestamping is not possible (SKBTX_IN_PROGRESS not set).
 - As soon as the driver has sent the packet and/or obtained a
   hardware time stamp for it, it passes the time stamp back by
-  calling skb_hwtstamp_tx() with the original skb, the raw
-  hardware time stamp. skb_hwtstamp_tx() clones the original skb and
+  calling skb_tstamp_tx() with the original skb, the raw
+  hardware time stamp. skb_tstamp_tx() clones the original skb and
   adds the timestamps, therefore the original skb has to be freed now.
   If obtaining the hardware time stamp somehow fails, then the driver
   should not fall back to software time stamping. The rationale is that

drivers/net/bonding/bond_options.c

@@ -1526,7 +1526,7 @@ static int bond_option_ad_actor_system_set(struct bonding *bond,
 		mac = (u8 *)&newval->value;
 	}
 
-	if (!is_valid_ether_addr(mac))
+	if (is_multicast_ether_addr(mac))
 		goto err;
 
 	netdev_dbg(bond->dev, "Setting ad_actor_system to %pM\n", mac);

drivers/net/ethernet/google/gve/gve_adminq.c

@@ -738,10 +738,7 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	 * is not set to GqiRda, choose the queue format in a priority order:
 	 * DqoRda, GqiRda, GqiQpl. Use GqiQpl as default.
 	 */
-	if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
-		dev_info(&priv->pdev->dev,
-			 "Driver is running with GQI RDA queue format.\n");
-	} else if (dev_op_dqo_rda) {
+	if (dev_op_dqo_rda) {
 		priv->queue_format = GVE_DQO_RDA_FORMAT;
 		dev_info(&priv->pdev->dev,
 			 "Driver is running with DQO RDA queue format.\n");
@@ -753,6 +750,9 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 			 "Driver is running with GQI RDA queue format.\n");
 		supported_features_mask =
 			be32_to_cpu(dev_op_gqi_rda->supported_features_mask);
+	} else if (priv->queue_format == GVE_GQI_RDA_FORMAT) {
+		dev_info(&priv->pdev->dev,
+			 "Driver is running with GQI RDA queue format.\n");
 	} else {
 		priv->queue_format = GVE_GQI_QPL_FORMAT;
 		if (dev_op_gqi_qpl)

drivers/net/ethernet/intel/ice/ice_base.c

@@ -6,6 +6,18 @@
 #include "ice_lib.h"
 #include "ice_dcb_lib.h"
 
+static bool ice_alloc_rx_buf_zc(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->xdp_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->xdp_buf), GFP_KERNEL);
+	return !!rx_ring->xdp_buf;
+}
+
+static bool ice_alloc_rx_buf(struct ice_rx_ring *rx_ring)
+{
+	rx_ring->rx_buf = kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
+	return !!rx_ring->rx_buf;
+}
+
 /**
  * __ice_vsi_get_qs_contig - Assign a contiguous chunk of queues to VSI
  * @qs_cfg: gathered variables needed for PF->VSI queues assignment
@@ -492,8 +504,11 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
 					 ring->q_index, ring->q_vector->napi.napi_id);
 
+		kfree(ring->rx_buf);
 		ring->xsk_pool = ice_xsk_pool(ring);
 		if (ring->xsk_pool) {
+			if (!ice_alloc_rx_buf_zc(ring))
+				return -ENOMEM;
 			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
 
 			ring->rx_buf_len =
@@ -508,6 +523,8 @@ int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
 				 ring->q_index);
 		} else {
+			if (!ice_alloc_rx_buf(ring))
+				return -ENOMEM;
 			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
 				/* coverity[check_return] */
 				xdp_rxq_info_reg(&ring->xdp_rxq,

drivers/net/ethernet/intel/ice/ice_txrx.c

@@ -419,7 +419,10 @@ void ice_clean_rx_ring(struct ice_rx_ring *rx_ring)
 	}
 
 rx_skip_free:
-	memset(rx_ring->rx_buf, 0, sizeof(*rx_ring->rx_buf) * rx_ring->count);
+	if (rx_ring->xsk_pool)
+		memset(rx_ring->xdp_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->xdp_buf)));
+	else
+		memset(rx_ring->rx_buf, 0, array_size(rx_ring->count, sizeof(*rx_ring->rx_buf)));
 
 	/* Zero out the descriptor ring */
 	size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -446,8 +449,13 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
 	rx_ring->xdp_prog = NULL;
-	devm_kfree(rx_ring->dev, rx_ring->rx_buf);
-	rx_ring->rx_buf = NULL;
+	if (rx_ring->xsk_pool) {
+		kfree(rx_ring->xdp_buf);
+		rx_ring->xdp_buf = NULL;
+	} else {
+		kfree(rx_ring->rx_buf);
+		rx_ring->rx_buf = NULL;
+	}
 
 	if (rx_ring->desc) {
 		size = ALIGN(rx_ring->count * sizeof(union ice_32byte_rx_desc),
@@ -475,8 +483,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	/* warn if we are about to overwrite the pointer */
 	WARN_ON(rx_ring->rx_buf);
 	rx_ring->rx_buf =
-		devm_kcalloc(dev, sizeof(*rx_ring->rx_buf), rx_ring->count,
-			     GFP_KERNEL);
+		kcalloc(rx_ring->count, sizeof(*rx_ring->rx_buf), GFP_KERNEL);
 	if (!rx_ring->rx_buf)
 		return -ENOMEM;
 
@@ -505,7 +512,7 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	return 0;
 
 err:
-	devm_kfree(dev, rx_ring->rx_buf);
+	kfree(rx_ring->rx_buf);
 	rx_ring->rx_buf = NULL;
 	return -ENOMEM;
 }

drivers/net/ethernet/intel/ice/ice_txrx.h

@@ -24,7 +24,6 @@
 #define ICE_MAX_DATA_PER_TXD_ALIGNED \
 	(~(ICE_MAX_READ_REQ_SIZE - 1) & ICE_MAX_DATA_PER_TXD)
 
-#define ICE_RX_BUF_WRITE	16	/* Must be power of 2 */
 #define ICE_MAX_TXQ_PER_TXQG	128
 
 /* Attempt to maximize the headroom available for incoming frames. We use a 2K

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -12,6 +12,11 @@
 #include "ice_txrx_lib.h"
 #include "ice_lib.h"
 
+static struct xdp_buff **ice_xdp_buf(struct ice_rx_ring *rx_ring, u32 idx)
+{
+	return &rx_ring->xdp_buf[idx];
+}
+
 /**
  * ice_qp_reset_stats - Resets all stats for rings of given index
  * @vsi: VSI that contains rings of interest
@@ -372,7 +377,7 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	dma_addr_t dma;
 
 	rx_desc = ICE_RX_DESC(rx_ring, ntu);
-	xdp = &rx_ring->xdp_buf[ntu];
+	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	nb_buffs = min_t(u16, count, rx_ring->count - ntu);
 	nb_buffs = xsk_buff_alloc_batch(rx_ring->xsk_pool, xdp, nb_buffs);
@@ -390,14 +395,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	}
 
 	ntu += nb_buffs;
-	if (ntu == rx_ring->count) {
-		rx_desc = ICE_RX_DESC(rx_ring, 0);
-		xdp = rx_ring->xdp_buf;
+	if (ntu == rx_ring->count)
 		ntu = 0;
-	}
 
-	/* clear the status bits for the next_to_use descriptor */
-	rx_desc->wb.status_error0 = 0;
 	ice_release_rx_desc(rx_ring, ntu);
 
 	return count == nb_buffs;
@@ -419,19 +419,18 @@ static void ice_bump_ntc(struct ice_rx_ring *rx_ring)
 /**
  * ice_construct_skb_zc - Create an sk_buff from zero-copy buffer
  * @rx_ring: Rx ring
- * @xdp_arr: Pointer to the SW ring of xdp_buff pointers
+ * @xdp: Pointer to XDP buffer
  *
  * This function allocates a new skb from a zero-copy Rx buffer.
  *
  * Returns the skb on success, NULL on failure.
  */
 static struct sk_buff *
-ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
+ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
 {
-	struct xdp_buff *xdp = *xdp_arr;
+	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	unsigned int metasize = xdp->data - xdp->data_meta;
 	unsigned int datasize = xdp->data_end - xdp->data;
-	unsigned int datasize_hard = xdp->data_end - xdp->data_hard_start;
 	struct sk_buff *skb;
 
 	skb = __napi_alloc_skb(&rx_ring->q_vector->napi, datasize_hard,
@@ -445,7 +444,6 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff **xdp_arr)
 		skb_metadata_set(skb, metasize);
 
 	xsk_buff_free(xdp);
-	*xdp_arr = NULL;
 	return skb;
 }
 
@@ -507,7 +505,6 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 {
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
-	u16 cleaned_count = ICE_DESC_UNUSED(rx_ring);
 	struct ice_tx_ring *xdp_ring;
 	unsigned int xdp_xmit = 0;
 	struct bpf_prog *xdp_prog;
@@ -522,7 +519,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		union ice_32b_rx_flex_desc *rx_desc;
 		unsigned int size, xdp_res = 0;
-		struct xdp_buff **xdp;
+		struct xdp_buff *xdp;
 		struct sk_buff *skb;
 		u16 stat_err_bits;
 		u16 vlan_tag = 0;
@@ -540,39 +537,42 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
+		xdp = *ice_xdp_buf(rx_ring, rx_ring->next_to_clean);
+
 		size = le16_to_cpu(rx_desc->wb.pkt_len) &
 				   ICE_RX_FLX_DESC_PKT_LEN_M;
-		if (!size)
-			break;
+		if (!size) {
+			xdp->data = NULL;
+			xdp->data_end = NULL;
+			xdp->data_hard_start = NULL;
+			xdp->data_meta = NULL;
+			goto construct_skb;
+		}
 
-		xdp = &rx_ring->xdp_buf[rx_ring->next_to_clean];
-		xsk_buff_set_size(*xdp, size);
-		xsk_buff_dma_sync_for_cpu(*xdp, rx_ring->xsk_pool);
+		xsk_buff_set_size(xdp, size);
+		xsk_buff_dma_sync_for_cpu(xdp, rx_ring->xsk_pool);
 
-		xdp_res = ice_run_xdp_zc(rx_ring, *xdp, xdp_prog, xdp_ring);
+		xdp_res = ice_run_xdp_zc(rx_ring, xdp, xdp_prog, xdp_ring);
 		if (xdp_res) {
 			if (xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))
 				xdp_xmit |= xdp_res;
 			else
-				xsk_buff_free(*xdp);
+				xsk_buff_free(xdp);
 
-			*xdp = NULL;
 			total_rx_bytes += size;
 			total_rx_packets++;
-			cleaned_count++;
 
 			ice_bump_ntc(rx_ring);
 			continue;
 		}
-
+construct_skb:
 		/* XDP_PASS path */
 		skb = ice_construct_skb_zc(rx_ring, xdp);
 		if (!skb) {
 			rx_ring->rx_stats.alloc_buf_failed++;
 			break;
 		}
 
-		cleaned_count++;
 		ice_bump_ntc(rx_ring);
 
 		if (eth_skb_pad(skb)) {
@@ -594,8 +594,7 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
 		ice_receive_skb(rx_ring, skb, vlan_tag);
 	}
 
-	if (cleaned_count >= ICE_RX_BUF_WRITE)
-		failure = !ice_alloc_rx_bufs_zc(rx_ring, cleaned_count);
+	failure = !ice_alloc_rx_bufs_zc(rx_ring, ICE_DESC_UNUSED(rx_ring));
 
 	ice_finalize_xdp_rx(xdp_ring, xdp_xmit);
 	ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
@@ -811,15 +810,14 @@ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi)
  */
 void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring)
 {
-	u16 i;
-
-	for (i = 0; i < rx_ring->count; i++) {
-		struct xdp_buff **xdp = &rx_ring->xdp_buf[i];
+	u16 count_mask = rx_ring->count - 1;
+	u16 ntc = rx_ring->next_to_clean;
+	u16 ntu = rx_ring->next_to_use;
 
-		if (!xdp)
-			continue;
+	for ( ; ntc != ntu; ntc = (ntc + 1) & count_mask) {
+		struct xdp_buff *xdp = *ice_xdp_buf(rx_ring, ntc);
 
-		*xdp = NULL;
+		xsk_buff_free(xdp);
 	}
 }
 

drivers/net/ethernet/intel/igb/igb_main.c

@@ -9254,7 +9254,7 @@ static int __maybe_unused igb_suspend(struct device *dev)
 	return __igb_shutdown(to_pci_dev(dev), NULL, 0);
 }
 
-static int __maybe_unused igb_resume(struct device *dev)
+static int __maybe_unused __igb_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -9297,17 +9297,24 @@ static int __maybe_unused igb_resume(struct device *dev)
 
 	wr32(E1000_WUS, ~0);
 
-	rtnl_lock();
+	if (!rpm)
+		rtnl_lock();
 	if (!err && netif_running(netdev))
 		err = __igb_open(netdev, true);
 
 	if (!err)
 		netif_device_attach(netdev);
-	rtnl_unlock();
+	if (!rpm)
+		rtnl_unlock();
 
 	return err;
 }
 
+static int __maybe_unused igb_resume(struct device *dev)
+{
+	return __igb_resume(dev, false);
+}
+
 static int __maybe_unused igb_runtime_idle(struct device *dev)
 {
 	struct net_device *netdev = dev_get_drvdata(dev);
@@ -9326,7 +9333,7 @@ static int __maybe_unused igb_runtime_suspend(struct device *dev)
 
 static int __maybe_unused igb_runtime_resume(struct device *dev)
 {
-	return igb_resume(dev);
+	return __igb_resume(dev, true);
 }
 
 static void igb_shutdown(struct pci_dev *pdev)
@@ -9442,7 +9449,7 @@ static pci_ers_result_t igb_io_error_detected(struct pci_dev *pdev,
  *  @pdev: Pointer to PCI device
  *
  *  Restart the card from scratch, as if from a cold-boot. Implementation
- *  resembles the first-half of the igb_resume routine.
+ *  resembles the first-half of the __igb_resume routine.
  **/
 static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
 {
@@ -9482,7 +9489,7 @@ static pci_ers_result_t igb_io_slot_reset(struct pci_dev *pdev)
  *
  *  This callback is called when the error recovery driver tells us that
  *  its OK to resume normal operation. Implementation resembles the
- *  second-half of the igb_resume routine.
+ *  second-half of the __igb_resume routine.
  */
 static void igb_io_resume(struct pci_dev *pdev)
 {