Merge tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

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

  Quite a handful of old regression fixes but most of those are
  pre-5.16.

  Current release - regressions:

   - fix memory leaks in the skb free deferral scheme if upper layer
     protocols are used, i.e. in-kernel TCP readers like TLS

  Current release - new code bugs:

   - nf_tables: fix NULL check typo in _clone() functions

   - change the default to y for Vertexcom vendor Kconfig

   - a couple of fixes to incorrect uses of ref tracking

   - two fixes for constifying netdev->dev_addr

  Previous releases - regressions:

   - bpf:
      - various verifier fixes mainly around register offset handling
        when passed to helper functions
      - fix mount source displayed for bpffs (none -> bpffs)

   - bonding:
      - fix extraction of ports for connection hash calculation
      - fix bond_xmit_broadcast return value when some devices are down

   - phy: marvell: add Marvell specific PHY loopback

   - sch_api: don't skip qdisc attach on ingress, prevent ref leak

   - htb: restore minimal packet size handling in rate control

   - sfp: fix high power modules without diagnostic monitoring

   - mscc: ocelot:
      - don't let phylink re-enable TX PAUSE on the NPI port
      - don't dereference NULL pointers with shared tc filters

   - smsc95xx: correct reset handling for LAN9514

   - cpsw: avoid alignment faults by taking NET_IP_ALIGN into account

   - phy: micrel: use kszphy_suspend/_resume for irq aware devices,
     avoid races with the interrupt

  Previous releases - always broken:

   - xdp: check prog type before updating BPF link

   - smc: resolve various races around abnormal connection termination

   - sit: allow encapsulated IPv6 traffic to be delivered locally

   - axienet: fix init/reset handling, add missing barriers, read the
     right status words, stop queues correctly

   - add missing dev_put() in sock_timestamping_bind_phc()

  Misc:

   - ipv4: prevent accidentally passing RTO_ONLINK to
     ip_route_output_key_hash() by sanitizing flags

   - ipv4: avoid quadratic behavior in netns dismantle

   - stmmac: dwmac-oxnas: add support for OX810SE

   - fsl: xgmac_mdio: add workaround for erratum A-009885"

* tag 'net-5.17-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (92 commits)
  ipv4: add net_hash_mix() dispersion to fib_info_laddrhash keys
  ipv4: avoid quadratic behavior in netns dismantle
  net/fsl: xgmac_mdio: Fix incorrect iounmap when removing module
  powerpc/fsl/dts: Enable WA for erratum A-009885 on fman3l MDIO buses
  dt-bindings: net: Document fsl,erratum-a009885
  net/fsl: xgmac_mdio: Add workaround for erratum A-009885
  net: mscc: ocelot: fix using match before it is set
  net: phy: micrel: use kszphy_suspend()/kszphy_resume for irq aware devices
  net: cpsw: avoid alignment faults by taking NET_IP_ALIGN into account
  nfc: llcp: fix NULL error pointer dereference on sendmsg() after failed bind()
  net: axienet: increase default TX ring size to 128
  net: axienet: fix for TX busy handling
  net: axienet: fix number of TX ring slots for available check
  net: axienet: Fix TX ring slot available check
  net: axienet: limit minimum TX ring size
  net: axienet: add missing memory barriers
  net: axienet: reset core on initialization prior to MDIO access
  net: axienet: Wait for PhyRstCmplt after core reset
  net: axienet: increase reset timeout
  bpf, selftests: Add ringbuf memory type confusion test
  ...

1 files changed, 84 insertions, 51 deletions

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 23ac353b35fe..377c94ec2486 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -41,8 +41,9 @@
 #include "xilinx_axienet.h"
 
 /* Descriptors defines for Tx and Rx DMA */
-#define TX_BD_NUM_DEFAULT		64
+#define TX_BD_NUM_DEFAULT		128
 #define RX_BD_NUM_DEFAULT		1024
+#define TX_BD_NUM_MIN			(MAX_SKB_FRAGS + 1)
 #define TX_BD_NUM_MAX			4096
 #define RX_BD_NUM_MAX			4096
 
@@ -496,7 +497,8 @@ static void axienet_setoptions(struct net_device *ndev, u32 options)
 
 static int __axienet_device_reset(struct axienet_local *lp)
 {
-	u32 timeout;
+	u32 value;
+	int ret;
 
 	/* Reset Axi DMA. This would reset Axi Ethernet core as well. The reset
 	 * process of Axi DMA takes a while to complete as all pending
@@ -506,15 +508,23 @@ static int __axienet_device_reset(struct axienet_local *lp)
 	 * they both reset the entire DMA core, so only one needs to be used.
 	 */
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, XAXIDMA_CR_RESET_MASK);
-	timeout = DELAY_OF_ONE_MILLISEC;
-	while (axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET) &
-				XAXIDMA_CR_RESET_MASK) {
-		udelay(1);
-		if (--timeout == 0) {
-			netdev_err(lp->ndev, "%s: DMA reset timeout!\n",
-				   __func__);
-			return -ETIMEDOUT;
-		}
+	ret = read_poll_timeout(axienet_dma_in32, value,
+				!(value & XAXIDMA_CR_RESET_MASK),
+				DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+				XAXIDMA_TX_CR_OFFSET);
+	if (ret) {
+		dev_err(lp->dev, "%s: DMA reset timeout!\n", __func__);
+		return ret;
+	}
+
+	/* Wait for PhyRstCmplt bit to be set, indicating the PHY reset has finished */
+	ret = read_poll_timeout(axienet_ior, value,
+				value & XAE_INT_PHYRSTCMPLT_MASK,
+				DELAY_OF_ONE_MILLISEC, 50000, false, lp,
+				XAE_IS_OFFSET);
+	if (ret) {
+		dev_err(lp->dev, "%s: timeout waiting for PhyRstCmplt\n", __func__);
+		return ret;
 	}
 
 	return 0;
@@ -623,6 +633,8 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
 		if (nr_bds == -1 && !(status & XAXIDMA_BD_STS_COMPLETE_MASK))
 			break;
 
+		/* Ensure we see complete descriptor update */
+		dma_rmb();
 		phys = desc_get_phys_addr(lp, cur_p);
 		dma_unmap_single(ndev->dev.parent, phys,
 				 (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
@@ -631,13 +643,15 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
 		if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
 			dev_consume_skb_irq(cur_p->skb);
 
-		cur_p->cntrl = 0;
 		cur_p->app0 = 0;
 		cur_p->app1 = 0;
 		cur_p->app2 = 0;
 		cur_p->app4 = 0;
-		cur_p->status = 0;
 		cur_p->skb = NULL;
+		/* ensure our transmit path and device don't prematurely see status cleared */
+		wmb();
+		cur_p->cntrl = 0;
+		cur_p->status = 0;
 
 		if (sizep)
 			*sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
@@ -647,6 +661,32 @@ static int axienet_free_tx_chain(struct net_device *ndev, u32 first_bd,
 }
 
 /**
+ * axienet_check_tx_bd_space - Checks if a BD/group of BDs are currently busy
+ * @lp:		Pointer to the axienet_local structure
+ * @num_frag:	The number of BDs to check for
+ *
+ * Return: 0, on success
+ *	    NETDEV_TX_BUSY, if any of the descriptors are not free
+ *
+ * This function is invoked before BDs are allocated and transmission starts.
+ * This function returns 0 if a BD or group of BDs can be allocated for
+ * transmission. If the BD or any of the BDs are not free the function
+ * returns a busy status. This is invoked from axienet_start_xmit.
+ */
+static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
+					    int num_frag)
+{
+	struct axidma_bd *cur_p;
+
+	/* Ensure we see all descriptor updates from device or TX IRQ path */
+	rmb();
+	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
+	if (cur_p->cntrl)
+		return NETDEV_TX_BUSY;
+	return 0;
+}
+
+/**
  * axienet_start_xmit_done - Invoked once a transmit is completed by the
  * Axi DMA Tx channel.
  * @ndev:	Pointer to the net_device structure
@@ -675,30 +715,8 @@ static void axienet_start_xmit_done(struct net_device *ndev)
 	/* Matches barrier in axienet_start_xmit */
 	smp_mb();
 
-	netif_wake_queue(ndev);
-}
-
-/**
- * axienet_check_tx_bd_space - Checks if a BD/group of BDs are currently busy
- * @lp:		Pointer to the axienet_local structure
- * @num_frag:	The number of BDs to check for
- *
- * Return: 0, on success
- *	    NETDEV_TX_BUSY, if any of the descriptors are not free
- *
- * This function is invoked before BDs are allocated and transmission starts.
- * This function returns 0 if a BD or group of BDs can be allocated for
- * transmission. If the BD or any of the BDs are not free the function
- * returns a busy status. This is invoked from axienet_start_xmit.
- */
-static inline int axienet_check_tx_bd_space(struct axienet_local *lp,
-					    int num_frag)
-{
-	struct axidma_bd *cur_p;
-	cur_p = &lp->tx_bd_v[(lp->tx_bd_tail + num_frag) % lp->tx_bd_num];
-	if (cur_p->status & XAXIDMA_BD_STS_ALL_MASK)
-		return NETDEV_TX_BUSY;
-	return 0;
+	if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+		netif_wake_queue(ndev);
 }
 
 /**
@@ -730,20 +748,15 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	num_frag = skb_shinfo(skb)->nr_frags;
 	cur_p = &lp->tx_bd_v[lp->tx_bd_tail];
 
-	if (axienet_check_tx_bd_space(lp, num_frag)) {
-		if (netif_queue_stopped(ndev))
-			return NETDEV_TX_BUSY;
-
+	if (axienet_check_tx_bd_space(lp, num_frag + 1)) {
+		/* Should not happen as last start_xmit call should have
+		 * checked for sufficient space and queue should only be
+		 * woken when sufficient space is available.
+		 */
 		netif_stop_queue(ndev);
-
-		/* Matches barrier in axienet_start_xmit_done */
-		smp_mb();
-
-		/* Space might have just been freed - check again */
-		if (axienet_check_tx_bd_space(lp, num_frag))
-			return NETDEV_TX_BUSY;
-
-		netif_wake_queue(ndev);
+		if (net_ratelimit())
+			netdev_warn(ndev, "TX ring unexpectedly full\n");
+		return NETDEV_TX_BUSY;
 	}
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -804,6 +817,18 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (++lp->tx_bd_tail >= lp->tx_bd_num)
 		lp->tx_bd_tail = 0;
 
+	/* Stop queue if next transmit may not have space */
+	if (axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1)) {
+		netif_stop_queue(ndev);
+
+		/* Matches barrier in axienet_start_xmit_done */
+		smp_mb();
+
+		/* Space might have just been freed - check again */
+		if (!axienet_check_tx_bd_space(lp, MAX_SKB_FRAGS + 1))
+			netif_wake_queue(ndev);
+	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -834,6 +859,8 @@ static void axienet_recv(struct net_device *ndev)
 
 		tail_p = lp->rx_bd_p + sizeof(*lp->rx_bd_v) * lp->rx_bd_ci;
 
+		/* Ensure we see complete descriptor update */
+		dma_rmb();
 		phys = desc_get_phys_addr(lp, cur_p);
 		dma_unmap_single(ndev->dev.parent, phys, lp->max_frm_size,
 				 DMA_FROM_DEVICE);
@@ -1352,7 +1379,8 @@ axienet_ethtools_set_ringparam(struct net_device *ndev,
 	if (ering->rx_pending > RX_BD_NUM_MAX ||
 	    ering->rx_mini_pending ||
 	    ering->rx_jumbo_pending ||
-	    ering->rx_pending > TX_BD_NUM_MAX)
+	    ering->tx_pending < TX_BD_NUM_MIN ||
+	    ering->tx_pending > TX_BD_NUM_MAX)
 		return -EINVAL;
 
 	if (netif_running(ndev))
@@ -2027,6 +2055,11 @@ static int axienet_probe(struct platform_device *pdev)
 	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 
+	/* Reset core now that clocks are enabled, prior to accessing MDIO */
+	ret = __axienet_device_reset(lp);
+	if (ret)
+		goto cleanup_clk;
+
 	lp->phy_node = of_parse_phandle(pdev->dev.of_node, "phy-handle", 0);
 	if (lp->phy_node) {
 		ret = axienet_mdio_setup(lp);