Merge tag 'net-7.3-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/netHEADmaster

Pull networking fixes from Jakub Kicinski:
 "Including fixes from wireless, wireguard, CAN and Bluetooth.
  We have one known regression to wrap up in VLAN handling.

  Current release - regressions:

   - Bluetooth: RFCOMM: fix deadlock on rfcomm_mutex

  Previous releases - regressions:

   - can: fix regression in handling RPS after migrating metadata to skb_ext

   - eth:
      - iavf: fix regressions in reconfig impacting bonding
      - mana: fix packet forwarding performance regression
      - stmmac: remove buggy VLAN acceleration support

  Previous releases - always broken:

   - a few high prio fixes for tun, and af_packet

   - amt: fix a UaF on tunnel teardown

   - eth:
      - bnxt: fix PCIe AER recovery and FLR handling issues
      - macb: don't modify Tx skbs before taking ownership
      - axienet: don't leak Tx skbs on interface stop

   - wifi:
      - nxpwifi: number of LLM-ish fixes
      - assorted mt76 fixes"

* tag 'net-7.3-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (128 commits)
  net: macb: copy shared skbs before appending the FCS
  net: macb: check TX ring before modifying skb
  vsock: Fix memory leak in vmci_transport_recv_dgram_cb()
  wireguard: noise: reject response consumption after intermediate initiation
  wireguard: queueing: preserve tstamp_type when encapsulating packet
  net: openvswitch: validate transport header presence in set_ipv6_addr
  net/smc: protect clcsock lifetime in smc_getname
  ipv6: do not warn on route notification size race
  ipv4: do not warn on route notification size race
  ipv4: validate checksum_start before completing checksum
  ptp: ocp: fix PCIe delay estimation calculation
  xen/netfront: don't leak the skb when xennet_fill_frags() fails
  net/packet: call packet_parse_headers after virtio_net_hdr_to_skb
  xen/netfront: drop RX packets with a short Ethernet header
  net: skbuff: don't leave stale bytes in skb_copy_and_csum_bits()
  net: sparx5: free the matchall entry on destroy
  selftests: mlxsw: Test port range occupancy on template create
  mlxsw: spectrum_flower: Fix port range register leak in tmplt_create()
  net: dsa: microchip: fix KSZ8765 fiber detection
  net/mlx5e: Order ICOSQ cc update after CQ doorbell
  ...

2 files changed, 47 insertions, 11 deletions

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index fcd3aaef27fc..c63d99686d0b 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -523,8 +523,9 @@ struct skbuf_dma_descriptor {
  * @stats_work: Work for reading the hardware statistics counters often enough
  *              to catch overflows.
  * @dma_err_task: Work structure to process Axi DMA errors
- * @stopping:   Set when @dma_err_task shouldn't do anything because we are
- *              about to stop the device.
+ * @stopping:   Set when we are about to stop the device: makes @dma_err_task
+ *              a no-op (legacy DMA path) and fences RX descriptor
+ *              resubmission in axienet_dma_rx_cb() (dmaengine path).
  * @tx_irq:	Axidma TX IRQ number
  * @rx_irq:	Axidma RX IRQ number
  * @eth_irq:	Ethernet core IRQ number
@@ -545,6 +546,7 @@ struct skbuf_dma_descriptor {
  * @tx_ring_tail: TX skb ring buffer tail index.
  * @rx_ring_head: RX skb ring buffer head index.
  * @rx_ring_tail: RX skb ring buffer tail index.
+ * @rx_submit_lock: Protects RX ring resubmission vs teardown in dmaengine path.
  */
 struct axienet_local {
 	struct net_device *ndev;
@@ -626,6 +628,7 @@ struct axienet_local {
 	int tx_ring_tail;
 	int rx_ring_head;
 	int rx_ring_tail;
+	spinlock_t rx_submit_lock;
 };
 
 /**
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 1722b7038f34..09443623a3e2 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -881,6 +881,7 @@ static void axienet_dma_tx_cb(void *data, const struct dmaengine_result *result)
 	u64_stats_update_end(&lp->tx_stat_sync);
 	dma_unmap_sg(lp->dev, skbuf_dma->sgl, skbuf_dma->sg_len, DMA_TO_DEVICE);
 	dev_consume_skb_any(skbuf_dma->skb);
+	skbuf_dma->skb = NULL;
 	netif_txq_completed_wake(txq, 1, len,
 				 CIRC_SPACE(lp->tx_ring_head, lp->tx_ring_tail, TX_BD_NUM_MAX),
 				 2);
@@ -1171,6 +1172,7 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 						       &meta_max_len);
 	dma_unmap_single(lp->dev, skbuf_dma->dma_address, lp->max_frm_size,
 			 DMA_FROM_DEVICE);
+	skbuf_dma->skb = NULL;
 
 	if (IS_ERR(app_metadata)) {
 		if (net_ratelimit())
@@ -1193,10 +1195,17 @@ static void axienet_dma_rx_cb(void *data, const struct dmaengine_result *result)
 	u64_stats_update_end(&lp->rx_stat_sync);
 
 rx_submit:
+	spin_lock(&lp->rx_submit_lock);
+	if (lp->stopping) {
+		spin_unlock(&lp->rx_submit_lock);
+		return;
+	}
+
 	for (i = 0; i < CIRC_SPACE(lp->rx_ring_head, lp->rx_ring_tail,
 				   RX_BUF_NUM_DEFAULT); i++)
 		axienet_rx_submit_desc(lp->ndev);
 	dma_async_issue_pending(lp->rx_chan);
+	spin_unlock(&lp->rx_submit_lock);
 }
 
 /**
@@ -1541,6 +1550,7 @@ static int axienet_init_dmaengine(struct net_device *ndev)
 	lp->tx_ring_head = 0;
 	lp->rx_ring_tail = 0;
 	lp->rx_ring_head = 0;
+	lp->stopping = false;
 	lp->tx_skb_ring = kzalloc_objs(*lp->tx_skb_ring, TX_BD_NUM_MAX);
 	if (!lp->tx_skb_ring) {
 		ret = -ENOMEM;
@@ -1752,20 +1762,42 @@ static int axienet_stop(struct net_device *ndev)
 		free_irq(lp->rx_irq, ndev);
 		axienet_dma_bd_release(ndev);
 	} else {
+		struct skbuf_dma_descriptor *skbuf_dma;
+
+		spin_lock_bh(&lp->rx_submit_lock);
+		lp->stopping = true;
+		spin_unlock_bh(&lp->rx_submit_lock);
+
 		dmaengine_terminate_sync(lp->tx_chan);
-		dmaengine_synchronize(lp->tx_chan);
 		dmaengine_terminate_sync(lp->rx_chan);
-		dmaengine_synchronize(lp->rx_chan);
-
-		for (i = 0; i < TX_BD_NUM_MAX; i++)
-			kfree(lp->tx_skb_ring[i]);
-		kfree(lp->tx_skb_ring);
-		for (i = 0; i < RX_BUF_NUM_DEFAULT; i++)
-			kfree(lp->rx_skb_ring[i]);
-		kfree(lp->rx_skb_ring);
 
 		dma_release_channel(lp->rx_chan);
 		dma_release_channel(lp->tx_chan);
+
+		/* Unmap and free any buffer the terminate did not reclaim, so it
+		 * is not leaked; a non-NULL skb marks such a slot.
+		 */
+		for (i = 0; i < TX_BD_NUM_MAX; i++) {
+			skbuf_dma = lp->tx_skb_ring[i];
+			if (skbuf_dma && skbuf_dma->skb) {
+				dma_unmap_sg(lp->dev, skbuf_dma->sgl,
+					     skbuf_dma->sg_len, DMA_TO_DEVICE);
+				dev_kfree_skb_any(skbuf_dma->skb);
+			}
+			kfree(skbuf_dma);
+		}
+		kfree(lp->tx_skb_ring);
+
+		for (i = 0; i < RX_BUF_NUM_DEFAULT; i++) {
+			skbuf_dma = lp->rx_skb_ring[i];
+			if (skbuf_dma && skbuf_dma->skb) {
+				dma_unmap_single(lp->dev, skbuf_dma->dma_address,
+						 lp->max_frm_size, DMA_FROM_DEVICE);
+				dev_kfree_skb_any(skbuf_dma->skb);
+			}
+			kfree(skbuf_dma);
+		}
+		kfree(lp->rx_skb_ring);
 	}
 
 	netdev_reset_queue(ndev);
@@ -3065,6 +3097,7 @@ static int axienet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&lp->rx_cr_lock);
 	spin_lock_init(&lp->tx_cr_lock);
+	spin_lock_init(&lp->rx_submit_lock);
 	INIT_WORK(&lp->rx_dim.work, axienet_rx_dim_work);
 	lp->rx_dim_enabled = true;
 	lp->rx_dim.profile_ix = 1;