Merge branch 'intel-wired-lan-driver-updates-2025-01-06-igb-igc-ixgbe-ixgbevf-i40e-fm10k'

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2025-01-06 (igb, igc, ixgbe, ixgbevf, i40e, fm10k)

For igb:

Sriram Yagnaraman and Kurt Kanzenbach add support for AF_XDP
zero-copy.

Original cover letter:
The first couple of patches adds helper functions to prepare for AF_XDP
zero-copy support which comes in the last couple of patches, one each
for Rx and TX paths.

As mentioned in v1 patchset [0], I don't have access to an actual IGB
device to provide correct performance numbers. I have used Intel 82576EB
emulator in QEMU [1] to test the changes to IGB driver.

The tests use one isolated vCPU for RX/TX and one isolated vCPU for the
xdp-sock application [2]. Hope these measurements provide at the least
some indication on the increase in performance when using ZC, especially
in the TX path. It would be awesome if someone with a real IGB NIC can
test the patch.

AF_XDP performance using 64 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		220		235		350
txpush		1.000		1.000		410
l2fwd 		1.000		1.000		200

AF_XDP performance using 1500 byte packets in Kpps.
Benchmark:	XDP-SKB		XDP-DRV		XDP-DRV(ZC)
rxdrop		200		210		310
txpush		1.000		1.000		410
l2fwd 		0.900		1.000		160

[0]: https://lore.kernel.org/intel-wired-lan/20230704095915.9750-1-sriram.yagnaraman@est.tech/
[1]: https://www.qemu.org/docs/master/system/devices/igb.html
[2]: https://github.com/xdp-project/bpf-examples/tree/master/AF_XDP-example

Subsequent changes and information can be found here:
https://lore.kernel.org/intel-wired-lan/20241018-b4-igb_zero_copy-v9-0-da139d78d796@linutronix.de/

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For igc:

Song Yoong Siang allows for the XDP program to be hot-swapped.

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

Joe Damato adds sets IRQ and queues to NAPI instances to allow for
reporting via netdev-genl API.

For ixgbe:

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For ixgbevf:

Yue Haibing converts use of ERR_PTR return to traditional error code
which resolves a smatch warning.

For i40e:

Alex implements "mdd-auto-reset-vf" private flag to automatically reset
VFs when encountering an MDD event.

For fm10k:

Dr. David Alan Gilbert removes an unused function.
====================

Link: https://patch.msgid.link/20250106221929.956999-1-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 57 insertions, 22 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index f58cd6940434..56a35d58e7a6 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2123,10 +2123,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring,
 				union igc_adv_rx_desc *rx_desc,
 				struct sk_buff *skb)
 {
-	/* XDP packets use error pointer so abort at this point */
-	if (IS_ERR(skb))
-		return true;
-
 	if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) {
 		struct net_device *netdev = rx_ring->netdev;
 
@@ -2515,8 +2511,7 @@ out_failure:
 	}
 }
 
-static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
-					struct xdp_buff *xdp)
+static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp)
 {
 	struct bpf_prog *prog;
 	int res;
@@ -2530,7 +2525,7 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter,
 	res = __igc_xdp_run_prog(adapter, prog, xdp);
 
 out:
-	return ERR_PTR(-res);
+	return res;
 }
 
 /* This function assumes __netif_tx_lock is held by the caller. */
@@ -2585,6 +2580,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = igc_desc_unused(rx_ring);
 	int xdp_status = 0, rx_buffer_pgcnt;
+	int xdp_res = 0;
 
 	while (likely(total_packets < budget)) {
 		struct igc_xdp_buff ctx = { .rx_ts = NULL };
@@ -2630,12 +2626,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			xdp_buff_clear_frags_flag(&ctx.xdp);
 			ctx.rx_desc = rx_desc;
 
-			skb = igc_xdp_run_prog(adapter, &ctx.xdp);
+			xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp);
 		}
 
-		if (IS_ERR(skb)) {
-			unsigned int xdp_res = -PTR_ERR(skb);
-
+		if (xdp_res) {
 			switch (xdp_res) {
 			case IGC_XDP_CONSUMED:
 				rx_buffer->pagecnt_bias++;
@@ -2657,7 +2651,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			skb = igc_construct_skb(rx_ring, rx_buffer, &ctx);
 
 		/* exit if we failed to retrieve a buffer */
-		if (!skb) {
+		if (!xdp_res && !skb) {
 			rx_ring->rx_stats.alloc_failed++;
 			rx_buffer->pagecnt_bias++;
 			set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags);
@@ -2672,7 +2666,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget)
 			continue;
 
 		/* verify the packet layout is correct */
-		if (igc_cleanup_headers(rx_ring, rx_desc, skb)) {
+		if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) {
 			skb = NULL;
 			continue;
 		}
@@ -4948,6 +4942,22 @@ static int igc_sw_init(struct igc_adapter *adapter)
 	return 0;
 }
 
+void igc_set_queue_napi(struct igc_adapter *adapter, int vector,
+			struct napi_struct *napi)
+{
+	struct igc_q_vector *q_vector = adapter->q_vector[vector];
+
+	if (q_vector->rx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->rx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_RX, napi);
+
+	if (q_vector->tx.ring)
+		netif_queue_set_napi(adapter->netdev,
+				     q_vector->tx.ring->queue_index,
+				     NETDEV_QUEUE_TYPE_TX, napi);
+}
+
 /**
  * igc_up - Open the interface and prepare it to handle traffic
  * @adapter: board private structure
@@ -4955,6 +4965,7 @@ static int igc_sw_init(struct igc_adapter *adapter)
 void igc_up(struct igc_adapter *adapter)
 {
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int i = 0;
 
 	/* hardware has been reset, we need to reload some things */
@@ -4962,8 +4973,11 @@ void igc_up(struct igc_adapter *adapter)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	if (adapter->msix_entries)
 		igc_configure_msix(adapter);
@@ -5192,6 +5206,7 @@ void igc_down(struct igc_adapter *adapter)
 	for (i = 0; i < adapter->num_q_vectors; i++) {
 		if (adapter->q_vector[i]) {
 			napi_synchronize(&adapter->q_vector[i]->napi);
+			igc_set_queue_napi(adapter, i, NULL);
 			napi_disable(&adapter->q_vector[i]->napi);
 		}
 	}
@@ -5576,6 +5591,9 @@ static int igc_request_msix(struct igc_adapter *adapter)
 				  q_vector);
 		if (err)
 			goto err_free;
+
+		netif_napi_set_irq(&q_vector->napi,
+				   adapter->msix_entries[vector].vector);
 	}
 
 	igc_configure_msix(adapter);
@@ -6018,6 +6036,7 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 	struct igc_adapter *adapter = netdev_priv(netdev);
 	struct pci_dev *pdev = adapter->pdev;
 	struct igc_hw *hw = &adapter->hw;
+	struct napi_struct *napi;
 	int err = 0;
 	int i = 0;
 
@@ -6053,8 +6072,11 @@ static int __igc_open(struct net_device *netdev, bool resuming)
 
 	clear_bit(__IGC_DOWN, &adapter->state);
 
-	for (i = 0; i < adapter->num_q_vectors; i++)
-		napi_enable(&adapter->q_vector[i]->napi);
+	for (i = 0; i < adapter->num_q_vectors; i++) {
+		napi = &adapter->q_vector[i]->napi;
+		napi_enable(napi);
+		igc_set_queue_napi(adapter, i, napi);
+	}
 
 	/* Clear any pending interrupts. */
 	rd32(IGC_ICR);
@@ -7299,7 +7321,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev)
 	netif_rx(skb);
 }
 
-static int igc_resume(struct device *dev)
+static int __igc_resume(struct device *dev, bool rpm)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -7342,7 +7364,11 @@ static int igc_resume(struct device *dev)
 	wr32(IGC_WUS, ~0);
 
 	if (netif_running(netdev)) {
+		if (!rpm)
+			rtnl_lock();
 		err = __igc_open(netdev, true);
+		if (!rpm)
+			rtnl_unlock();
 		if (!err)
 			netif_device_attach(netdev);
 	}
@@ -7350,9 +7376,14 @@ static int igc_resume(struct device *dev)
 	return err;
 }
 
+static int igc_resume(struct device *dev)
+{
+	return __igc_resume(dev, false);
+}
+
 static int igc_runtime_resume(struct device *dev)
 {
-	return igc_resume(dev);
+	return __igc_resume(dev, true);
 }
 
 static int igc_suspend(struct device *dev)
@@ -7397,14 +7428,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev,
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igc_adapter *adapter = netdev_priv(netdev);
 
+	rtnl_lock();
 	netif_device_detach(netdev);
 
-	if (state == pci_channel_io_perm_failure)
+	if (state == pci_channel_io_perm_failure) {
+		rtnl_unlock();
 		return PCI_ERS_RESULT_DISCONNECT;
+	}
 
 	if (netif_running(netdev))
 		igc_down(adapter);
 	pci_disable_device(pdev);
+	rtnl_unlock();
 
 	/* Request a slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -7415,7 +7450,7 @@ static pci_ers_result_t igc_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 igc_resume routine.
+ *  resembles the first-half of the __igc_resume routine.
  **/
 static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev)
 {
@@ -7454,7 +7489,7 @@ static pci_ers_result_t igc_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 igc_resume routine.
+ *  second-half of the __igc_resume routine.
  */
 static void igc_io_resume(struct pci_dev *pdev)
 {