Merge tag 'net-6.6-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Current release - regressions:

   - bpf: adjust size_index according to the value of KMALLOC_MIN_SIZE

   - netfilter: fix entries val in rule reset audit log

   - eth: stmmac: fix incorrect rxq|txq_stats reference

  Previous releases - regressions:

   - ipv4: fix null-deref in ipv4_link_failure

   - netfilter:
      - fix several GC related issues
      - fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP

   - eth: team: fix null-ptr-deref when team device type is changed

   - eth: i40e: fix VF VLAN offloading when port VLAN is configured

   - eth: ionic: fix 16bit math issue when PAGE_SIZE >= 64KB

  Previous releases - always broken:

   - core: fix ETH_P_1588 flow dissector

   - mptcp: fix several connection hang-up conditions

   - bpf:
      - avoid deadlock when using queue and stack maps from NMI
      - add override check to kprobe multi link attach

   - hsr: properly parse HSRv1 supervisor frames.

   - eth: igc: fix infinite initialization loop with early XDP redirect

   - eth: octeon_ep: fix tx dma unmap len values in SG

   - eth: hns3: fix GRE checksum offload issue"

* tag 'net-6.6-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits)
  sfc: handle error pointers returned by rhashtable_lookup_get_insert_fast()
  igc: Expose tx-usecs coalesce setting to user
  octeontx2-pf: Do xdp_do_flush() after redirects.
  bnxt_en: Flush XDP for bnxt_poll_nitroa0()'s NAPI
  net: ena: Flush XDP packets on error.
  net/handshake: Fix memory leak in __sock_create() and sock_alloc_file()
  net: hinic: Fix warning-hinic_set_vlan_fliter() warn: variable dereferenced before check 'hwdev'
  netfilter: ipset: Fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP
  netfilter: nf_tables: fix memleak when more than 255 elements expired
  netfilter: nf_tables: disable toggling dormant table state more than once
  vxlan: Add missing entries to vxlan_get_size()
  net: rds: Fix possible NULL-pointer dereference
  team: fix null-ptr-deref when team device type is changed
  net: bridge: use DEV_STATS_INC()
  net: hns3: add 5ms delay before clear firmware reset irq source
  net: hns3: fix fail to delete tc flower rules during reset issue
  net: hns3: only enable unicast promisc when mac table full
  net: hns3: fix GRE checksum offload issue
  net: hns3: add cmdq check for vf periodic service task
  net: stmmac: fix incorrect rxq|txq_stats reference
  ...

Documentation/networking/ax25.rst

@@ -7,9 +7,9 @@ AX.25
 To use the amateur radio protocols within Linux you will need to get a
 suitable copy of the AX.25 Utilities. More detailed information about
 AX.25, NET/ROM and ROSE, associated programs and utilities can be
-found on http://www.linux-ax25.org.
+found on https://linux-ax25.in-berlin.de.
 
-There is an active mailing list for discussing Linux amateur radio matters
+There is a mailing list for discussing Linux amateur radio matters
 called linux-hams@vger.kernel.org. To subscribe to it, send a message to
 majordomo@vger.kernel.org with the words "subscribe linux-hams" in the body
 of the message, the subject field is ignored.  You don't need to be

MAINTAINERS

@@ -3344,7 +3344,7 @@ AX.25 NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/ax25.h
 F:	include/uapi/linux/ax25.h
 F:	net/ax25/
@@ -14756,7 +14756,7 @@ NETROM NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/netrom.h
 F:	include/uapi/linux/netrom.h
 F:	net/netrom/
@@ -18607,7 +18607,7 @@ ROSE NETWORK LAYER
 M:	Ralf Baechle <ralf@linux-mips.org>
 L:	linux-hams@vger.kernel.org
 S:	Maintained
-W:	http://www.linux-ax25.org/
+W:	https://linux-ax25.in-berlin.de
 F:	include/net/rose.h
 F:	include/uapi/linux/rose.h
 F:	net/rose/

drivers/net/ethernet/amazon/ena/ena_netdev.c

@@ -1833,6 +1833,9 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi,
 	return work_done;
 
 error:
+	if (xdp_flags & ENA_XDP_REDIRECT)
+		xdp_do_flush();
+
 	adapter = netdev_priv(rx_ring->netdev);
 
 	if (rc == -ENOSPC) {

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

@@ -2614,6 +2614,7 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 	struct rx_cmp_ext *rxcmp1;
 	u32 cp_cons, tmp_raw_cons;
 	u32 raw_cons = cpr->cp_raw_cons;
+	bool flush_xdp = false;
 	u32 rx_pkts = 0;
 	u8 event = 0;
 
@@ -2648,6 +2649,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 				rx_pkts++;
 			else if (rc == -EBUSY)	/* partial completion */
 				break;
+			if (event & BNXT_REDIRECT_EVENT)
+				flush_xdp = true;
 		} else if (unlikely(TX_CMP_TYPE(txcmp) ==
 				    CMPL_BASE_TYPE_HWRM_DONE)) {
 			bnxt_hwrm_handler(bp, txcmp);
@@ -2667,6 +2670,8 @@ static int bnxt_poll_nitroa0(struct napi_struct *napi, int budget)
 
 	if (event & BNXT_AGG_EVENT)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
+	if (flush_xdp)
+		xdp_do_flush();
 
 	if (!bnxt_has_work(bp, cpr) && rx_pkts < budget) {
 		napi_complete_done(napi, rx_pkts);

drivers/net/ethernet/engleder/tsnep_ethtool.c

@@ -300,10 +300,8 @@ static void tsnep_ethtool_get_channels(struct net_device *netdev,
 {
 	struct tsnep_adapter *adapter = netdev_priv(netdev);
 
-	ch->max_rx = adapter->num_rx_queues;
-	ch->max_tx = adapter->num_tx_queues;
-	ch->rx_count = adapter->num_rx_queues;
-	ch->tx_count = adapter->num_tx_queues;
+	ch->max_combined = adapter->num_queues;
+	ch->combined_count = adapter->num_queues;
 }
 
 static int tsnep_ethtool_get_ts_info(struct net_device *netdev,

drivers/net/ethernet/engleder/tsnep_main.c

@@ -87,8 +87,11 @@ static irqreturn_t tsnep_irq(int irq, void *arg)
 
 	/* handle TX/RX queue 0 interrupt */
 	if ((active & adapter->queue[0].irq_mask) != 0) {
-		tsnep_disable_irq(adapter, adapter->queue[0].irq_mask);
-		napi_schedule(&adapter->queue[0].napi);
+		if (napi_schedule_prep(&adapter->queue[0].napi)) {
+			tsnep_disable_irq(adapter, adapter->queue[0].irq_mask);
+			/* schedule after masking to avoid races */
+			__napi_schedule(&adapter->queue[0].napi);
+		}
 	}
 
 	return IRQ_HANDLED;
@@ -99,8 +102,11 @@ static irqreturn_t tsnep_irq_txrx(int irq, void *arg)
 	struct tsnep_queue *queue = arg;
 
 	/* handle TX/RX queue interrupt */
-	tsnep_disable_irq(queue->adapter, queue->irq_mask);
-	napi_schedule(&queue->napi);
+	if (napi_schedule_prep(&queue->napi)) {
+		tsnep_disable_irq(queue->adapter, queue->irq_mask);
+		/* schedule after masking to avoid races */
+		__napi_schedule(&queue->napi);
+	}
 
 	return IRQ_HANDLED;
 }
@@ -1728,6 +1734,10 @@ static int tsnep_poll(struct napi_struct *napi, int budget)
 	if (queue->tx)
 		complete = tsnep_tx_poll(queue->tx, budget);
 
+	/* handle case where we are called by netpoll with a budget of 0 */
+	if (unlikely(budget <= 0))
+		return budget;
+
 	if (queue->rx) {
 		done = queue->rx->xsk_pool ?
 		       tsnep_rx_poll_zc(queue->rx, napi, budget) :

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -3353,6 +3353,15 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		  NETIF_F_HW_TC);
 
 	netdev->hw_enc_features |= netdev->vlan_features | NETIF_F_TSO_MANGLEID;
+
+	/* The device_version V3 hardware can't offload the checksum for IP in
+	 * GRE packets, but can do it for NvGRE. So default to disable the
+	 * checksum and GSO offload for GRE.
+	 */
+	if (ae_dev->dev_version > HNAE3_DEVICE_VERSION_V2) {
+		netdev->features &= ~NETIF_F_GSO_GRE;
+		netdev->features &= ~NETIF_F_GSO_GRE_CSUM;
+	}
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c

@@ -3564,9 +3564,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type,
 				    u32 regclr)
 {
+#define HCLGE_IMP_RESET_DELAY		5
+
 	switch (event_type) {
 	case HCLGE_VECTOR0_EVENT_PTP:
 	case HCLGE_VECTOR0_EVENT_RST:
+		if (regclr == BIT(HCLGE_VECTOR0_IMPRESET_INT_B))
+			mdelay(HCLGE_IMP_RESET_DELAY);
+
 		hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr);
 		break;
 	case HCLGE_VECTOR0_EVENT_MBX:
@@ -7348,6 +7353,12 @@ static int hclge_del_cls_flower(struct hnae3_handle *handle,
 	ret = hclge_fd_tcam_config(hdev, HCLGE_FD_STAGE_1, true, rule->location,
 				   NULL, false);
 	if (ret) {
+		/* if tcam config fail, set rule state to TO_DEL,
+		 * so the rule will be deleted when periodic
+		 * task being scheduled.
+		 */
+		hclge_update_fd_list(hdev, HCLGE_FD_TO_DEL, rule->location, NULL);
+		set_bit(HCLGE_STATE_FD_TBL_CHANGED, &hdev->state);
 		spin_unlock_bh(&hdev->fd_rule_lock);
 		return ret;
 	}
@@ -8824,7 +8835,7 @@ static void hclge_update_overflow_flags(struct hclge_vport *vport,
 	if (mac_type == HCLGE_MAC_ADDR_UC) {
 		if (is_all_added)
 			vport->overflow_promisc_flags &= ~HNAE3_OVERFLOW_UPE;
-		else
+		else if (hclge_is_umv_space_full(vport, true))
 			vport->overflow_promisc_flags |= HNAE3_OVERFLOW_UPE;
 	} else {
 		if (is_all_added)

drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c

@@ -1855,7 +1855,8 @@ static void hclgevf_periodic_service_task(struct hclgevf_dev *hdev)
 	unsigned long delta = round_jiffies_relative(HZ);
 	struct hnae3_handle *handle = &hdev->nic;
 
-	if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state))
+	if (test_bit(HCLGEVF_STATE_RST_FAIL, &hdev->state) ||
+	    test_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state))
 		return;
 
 	if (time_is_after_jiffies(hdev->last_serv_processed + HZ)) {

drivers/net/ethernet/huawei/hinic/hinic_port.c

@@ -456,9 +456,6 @@ int hinic_set_vlan_fliter(struct hinic_dev *nic_dev, u32 en)
 	u16 out_size = sizeof(vlan_filter);
 	int err;
 
-	if (!hwdev)
-		return -EINVAL;
-
 	vlan_filter.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	vlan_filter.enable = en;
 

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -4475,9 +4475,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 		goto error_pvid;
 
 	i40e_vlan_stripping_enable(vsi);
-	i40e_vc_reset_vf(vf, true);
-	/* During reset the VF got a new VSI, so refresh a pointer. */
-	vsi = pf->vsi[vf->lan_vsi_idx];
+
 	/* Locked once because multiple functions below iterate list */
 	spin_lock_bh(&vsi->mac_filter_hash_lock);
 
@@ -4563,6 +4561,10 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id,
 	 */
 	vf->port_vlan_id = le16_to_cpu(vsi->info.pvid);
 
+	i40e_vc_reset_vf(vf, true);
+	/* During reset the VF got a new VSI, so refresh a pointer. */
+	vsi = pf->vsi[vf->lan_vsi_idx];
+
 	ret = i40e_config_vf_promiscuous_mode(vf, vsi->id, allmulti, alluni);
 	if (ret) {
 		dev_err(&pf->pdev->dev, "Unable to config vf promiscuous mode\n");

drivers/net/ethernet/intel/iavf/iavf.h

@@ -521,7 +521,7 @@ void iavf_down(struct iavf_adapter *adapter);
 int iavf_process_config(struct iavf_adapter *adapter);
 int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter);
 void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags);
-void iavf_schedule_request_stats(struct iavf_adapter *adapter);
+void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags);
 void iavf_schedule_finish_config(struct iavf_adapter *adapter);
 void iavf_reset(struct iavf_adapter *adapter);
 void iavf_set_ethtool_ops(struct net_device *netdev);

drivers/net/ethernet/intel/iavf/iavf_ethtool.c

@@ -362,7 +362,7 @@ static void iavf_get_ethtool_stats(struct net_device *netdev,
 	unsigned int i;
 
 	/* Explicitly request stats refresh */
-	iavf_schedule_request_stats(adapter);
+	iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_REQUEST_STATS);
 
 	iavf_add_ethtool_stats(&data, adapter, iavf_gstrings_stats);
 

drivers/net/ethernet/intel/iavf/iavf_main.c

@@ -314,15 +314,13 @@ void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags)
 }
 
 /**
- * iavf_schedule_request_stats - Set the flags and schedule statistics request
+ * iavf_schedule_aq_request - Set the flags and schedule aq request
  * @adapter: board private structure
- *
- * Sets IAVF_FLAG_AQ_REQUEST_STATS flag so iavf_watchdog_task() will explicitly
- * request and refresh ethtool stats
+ * @flags: requested aq flags
  **/
-void iavf_schedule_request_stats(struct iavf_adapter *adapter)
+void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags)
 {
-	adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_STATS;
+	adapter->aq_required |= flags;
 	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
 }
 
@@ -823,7 +821,7 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter,
 		list_add_tail(&f->list, &adapter->vlan_filter_list);
 		f->state = IAVF_VLAN_ADD;
 		adapter->num_vlan_filters++;
-		adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER;
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER);
 	}
 
 clearout:
@@ -845,7 +843,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan)
 	f = iavf_find_vlan(adapter, vlan);
 	if (f) {
 		f->state = IAVF_VLAN_REMOVE;
-		adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER;
+		iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER);
 	}
 
 	spin_unlock_bh(&adapter->mac_vlan_list_lock);
@@ -1421,7 +1419,8 @@ void iavf_down(struct iavf_adapter *adapter)
 	iavf_clear_fdir_filters(adapter);
 	iavf_clear_adv_rss_conf(adapter);
 
-	if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED)) {
+	if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) &&
+	    !(test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))) {
 		/* cancel any current operation */
 		adapter->current_op = VIRTCHNL_OP_UNKNOWN;
 		/* Schedule operations to close down the HW. Don't wait

drivers/net/ethernet/intel/igc/igc_ethtool.c

@@ -868,6 +868,18 @@ static void igc_ethtool_get_stats(struct net_device *netdev,
 	spin_unlock(&adapter->stats64_lock);
 }
 
+static int igc_ethtool_get_previous_rx_coalesce(struct igc_adapter *adapter)
+{
+	return (adapter->rx_itr_setting <= 3) ?
+		adapter->rx_itr_setting : adapter->rx_itr_setting >> 2;
+}
+
+static int igc_ethtool_get_previous_tx_coalesce(struct igc_adapter *adapter)
+{
+	return (adapter->tx_itr_setting <= 3) ?
+		adapter->tx_itr_setting : adapter->tx_itr_setting >> 2;
+}
+
 static int igc_ethtool_get_coalesce(struct net_device *netdev,
 				    struct ethtool_coalesce *ec,
 				    struct kernel_ethtool_coalesce *kernel_coal,
@@ -875,17 +887,8 @@ static int igc_ethtool_get_coalesce(struct net_device *netdev,
 {
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
-	if (adapter->rx_itr_setting <= 3)
-		ec->rx_coalesce_usecs = adapter->rx_itr_setting;
-	else
-		ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2;
-
-	if (!(adapter->flags & IGC_FLAG_QUEUE_PAIRS)) {
-		if (adapter->tx_itr_setting <= 3)
-			ec->tx_coalesce_usecs = adapter->tx_itr_setting;
-		else
-			ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2;
-	}
+	ec->rx_coalesce_usecs = igc_ethtool_get_previous_rx_coalesce(adapter);
+	ec->tx_coalesce_usecs = igc_ethtool_get_previous_tx_coalesce(adapter);
 
 	return 0;
 }
@@ -910,8 +913,12 @@ static int igc_ethtool_set_coalesce(struct net_device *netdev,
 	    ec->tx_coalesce_usecs == 2)
 		return -EINVAL;
 
-	if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) && ec->tx_coalesce_usecs)
+	if ((adapter->flags & IGC_FLAG_QUEUE_PAIRS) &&
+	    ec->tx_coalesce_usecs != igc_ethtool_get_previous_tx_coalesce(adapter)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Queue Pair mode enabled, both Rx and Tx coalescing controlled by rx-usecs");
 		return -EINVAL;
+	}
 
 	/* If ITR is disabled, disable DMAC */
 	if (ec->rx_coalesce_usecs == 0) {

drivers/net/ethernet/intel/igc/igc_main.c

@@ -6491,7 +6491,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames,
 	struct igc_ring *ring;
 	int i, drops;
 
-	if (unlikely(test_bit(__IGC_DOWN, &adapter->state)))
+	if (unlikely(!netif_carrier_ok(dev)))
 		return -ENETDOWN;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))

drivers/net/ethernet/marvell/octeon_ep/octep_main.c

@@ -734,13 +734,13 @@ static netdev_tx_t octep_start_xmit(struct sk_buff *skb,
 dma_map_sg_err:
 	if (si > 0) {
 		dma_unmap_single(iq->dev, sglist[0].dma_ptr[0],
-				 sglist[0].len[0], DMA_TO_DEVICE);
-		sglist[0].len[0] = 0;
+				 sglist[0].len[3], DMA_TO_DEVICE);
+		sglist[0].len[3] = 0;
 	}
 	while (si > 1) {
 		dma_unmap_page(iq->dev, sglist[si >> 2].dma_ptr[si & 3],
-			       sglist[si >> 2].len[si & 3], DMA_TO_DEVICE);
-		sglist[si >> 2].len[si & 3] = 0;
+			       sglist[si >> 2].len[3 - (si & 3)], DMA_TO_DEVICE);
+		sglist[si >> 2].len[3 - (si & 3)] = 0;
 		si--;
 	}
 	tx_buffer->gather = 0;

drivers/net/ethernet/marvell/octeon_ep/octep_tx.c

@@ -69,12 +69,12 @@ int octep_iq_process_completions(struct octep_iq *iq, u16 budget)
 		compl_sg++;
 
 		dma_unmap_single(iq->dev, tx_buffer->sglist[0].dma_ptr[0],
-				 tx_buffer->sglist[0].len[0], DMA_TO_DEVICE);
+				 tx_buffer->sglist[0].len[3], DMA_TO_DEVICE);
 
 		i = 1; /* entry 0 is main skb, unmapped above */
 		while (frags--) {
 			dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3],
-				       tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE);
+				       tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE);
 			i++;
 		}
 
@@ -131,13 +131,13 @@ static void octep_iq_free_pending(struct octep_iq *iq)
 
 		dma_unmap_single(iq->dev,
 				 tx_buffer->sglist[0].dma_ptr[0],
-				 tx_buffer->sglist[0].len[0],
+				 tx_buffer->sglist[0].len[3],
 				 DMA_TO_DEVICE);
 
 		i = 1; /* entry 0 is main skb, unmapped above */
 		while (frags--) {
 			dma_unmap_page(iq->dev, tx_buffer->sglist[i >> 2].dma_ptr[i & 3],
-				       tx_buffer->sglist[i >> 2].len[i & 3], DMA_TO_DEVICE);
+				       tx_buffer->sglist[i >> 2].len[3 - (i & 3)], DMA_TO_DEVICE);
 			i++;
 		}
 

drivers/net/ethernet/marvell/octeon_ep/octep_tx.h

@@ -17,7 +17,21 @@
 #define TX_BUFTYPE_NET_SG        2
 #define NUM_TX_BUFTYPES          3
 
-/* Hardware format for Scatter/Gather list */
+/* Hardware format for Scatter/Gather list
+ *
+ * 63      48|47     32|31     16|15       0
+ * -----------------------------------------
+ * |  Len 0  |  Len 1  |  Len 2  |  Len 3  |
+ * -----------------------------------------
+ * |                Ptr 0                  |
+ * -----------------------------------------
+ * |                Ptr 1                  |
+ * -----------------------------------------
+ * |                Ptr 2                  |
+ * -----------------------------------------
+ * |                Ptr 3                  |
+ * -----------------------------------------
+ */
 struct octep_tx_sglist_desc {
 	u16 len[4];
 	dma_addr_t dma_ptr[4];

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c

@@ -29,7 +29,8 @@
 static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
-				     struct otx2_cq_queue *cq);
+				     struct otx2_cq_queue *cq,
+				     bool *need_xdp_flush);
 
 static int otx2_nix_cq_op_status(struct otx2_nic *pfvf,
 				 struct otx2_cq_queue *cq)
@@ -337,7 +338,7 @@ static bool otx2_check_rcv_errors(struct otx2_nic *pfvf,
 static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 				 struct napi_struct *napi,
 				 struct otx2_cq_queue *cq,
-				 struct nix_cqe_rx_s *cqe)
+				 struct nix_cqe_rx_s *cqe, bool *need_xdp_flush)
 {
 	struct nix_rx_parse_s *parse = &cqe->parse;
 	struct nix_rx_sg_s *sg = &cqe->sg;
@@ -353,7 +354,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	}
 
 	if (pfvf->xdp_prog)
-		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq))
+		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush))
 			return;
 
 	skb = napi_get_frags(napi);
@@ -388,6 +389,7 @@ static int otx2_rx_napi_handler(struct otx2_nic *pfvf,
 				struct napi_struct *napi,
 				struct otx2_cq_queue *cq, int budget)
 {
+	bool need_xdp_flush = false;
 	struct nix_cqe_rx_s *cqe;
 	int processed_cqe = 0;
 
@@ -409,13 +411,15 @@ process_cqe:
 		cq->cq_head++;
 		cq->cq_head &= (cq->cqe_cnt - 1);
 
-		otx2_rcv_pkt_handler(pfvf, napi, cq, cqe);
+		otx2_rcv_pkt_handler(pfvf, napi, cq, cqe, &need_xdp_flush);
 
 		cqe->hdr.cqe_type = NIX_XQE_TYPE_INVALID;
 		cqe->sg.seg_addr = 0x00;
 		processed_cqe++;
 		cq->pend_cqe--;
 	}
+	if (need_xdp_flush)
+		xdp_do_flush();
 
 	/* Free CQEs to HW */
 	otx2_write64(pfvf, NIX_LF_CQ_OP_DOOR,
@@ -1354,7 +1358,8 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
 static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
-				     struct otx2_cq_queue *cq)
+				     struct otx2_cq_queue *cq,
+				     bool *need_xdp_flush)
 {
 	unsigned char *hard_start, *data;
 	int qidx = cq->cq_idx;
@@ -1391,8 +1396,10 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
 				    DMA_FROM_DEVICE);
-		if (!err)
+		if (!err) {
+			*need_xdp_flush = true;
 			return true;
+		}
 		put_page(page);
 		break;
 	default: