Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue

Tony Nguyen says:

====================
Intel Wired LAN Driver Updates 2025-09-16 (ice, i40e, ixgbe, igc)

For ice:
Jake resolves leaking pages with multi-buffer frames when a 0-sized
descriptor is encountered.

For i40e:
Maciej removes a redundant, and incorrect, memory barrier.

For ixgbe:
Jedrzej adjusts lifespan of ACI lock to ensure uses are while it is
valid.

For igc:
Kohei Enju does not fail probe on LED setup failure which resolves a
kernel panic in the cleanup path, if we were to fail.

* '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/net-queue:
  igc: don't fail igc_probe() on LED setup error
  ixgbe: destroy aci.lock later within ixgbe_remove path
  ixgbe: initialize aci.lock before it's used
  i40e: remove redundant memory barrier when cleaning Tx descs
  ice: fix Rx page leak on multi-buffer frames
====================

Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -948,9 +948,6 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 		if (!eop_desc)
 			break;
 
-		/* prevent any other reads prior to eop_desc */
-		smp_rmb();
-
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */
 		if (tx_head == tx_desc)

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

@@ -894,10 +894,6 @@ ice_add_xdp_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
 	__skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buf->page,
 				   rx_buf->page_offset, size);
 	sinfo->xdp_frags_size += size;
-	/* remember frag count before XDP prog execution; bpf_xdp_adjust_tail()
-	 * can pop off frags but driver has to handle it on its own
-	 */
-	rx_ring->nr_frags = sinfo->nr_frags;
 
 	if (page_is_pfmemalloc(rx_buf->page))
 		xdp_buff_set_frag_pfmemalloc(xdp);
@@ -968,20 +964,20 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 /**
  * ice_get_pgcnts - grab page_count() for gathered fragments
  * @rx_ring: Rx descriptor ring to store the page counts on
+ * @ntc: the next to clean element (not included in this frame!)
  *
  * This function is intended to be called right before running XDP
  * program so that the page recycling mechanism will be able to take
  * a correct decision regarding underlying pages; this is done in such
  * way as XDP program can change the refcount of page
  */
-static void ice_get_pgcnts(struct ice_rx_ring *rx_ring)
+static void ice_get_pgcnts(struct ice_rx_ring *rx_ring, unsigned int ntc)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	struct ice_rx_buf *rx_buf;
 	u32 cnt = rx_ring->count;
 
-	for (int i = 0; i < nr_frags; i++) {
+	while (idx != ntc) {
 		rx_buf = &rx_ring->rx_buf[idx];
 		rx_buf->pgcnt = page_count(rx_buf->page);
 
@@ -1154,62 +1150,51 @@ ice_put_rx_buf(struct ice_rx_ring *rx_ring, struct ice_rx_buf *rx_buf)
 }
 
 /**
- * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all frame frags
+ * ice_put_rx_mbuf - ice_put_rx_buf() caller, for all buffers in frame
  * @rx_ring: Rx ring with all the auxiliary data
  * @xdp: XDP buffer carrying linear + frags part
- * @xdp_xmit: XDP_TX/XDP_REDIRECT verdict storage
- * @ntc: a current next_to_clean value to be stored at rx_ring
+ * @ntc: the next to clean element (not included in this frame!)
  * @verdict: return code from XDP program execution
  *
- * Walk through gathered fragments and satisfy internal page
- * recycle mechanism; we take here an action related to verdict
- * returned by XDP program;
+ * Called after XDP program is completed, or on error with verdict set to
+ * ICE_XDP_CONSUMED.
+ *
+ * Walk through buffers from first_desc to the end of the frame, releasing
+ * buffers and satisfying internal page recycle mechanism. The action depends
+ * on verdict from XDP program.
  */
 static void ice_put_rx_mbuf(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
-			    u32 *xdp_xmit, u32 ntc, u32 verdict)
+			    u32 ntc, u32 verdict)
 {
-	u32 nr_frags = rx_ring->nr_frags + 1;
 	u32 idx = rx_ring->first_desc;
 	u32 cnt = rx_ring->count;
-	u32 post_xdp_frags = 1;
 	struct ice_rx_buf *buf;
-	int i;
+	u32 xdp_frags = 0;
+	int i = 0;
 
 	if (unlikely(xdp_buff_has_frags(xdp)))
-		post_xdp_frags += xdp_get_shared_info_from_buff(xdp)->nr_frags;
+		xdp_frags = xdp_get_shared_info_from_buff(xdp)->nr_frags;
 
-	for (i = 0; i < post_xdp_frags; i++) {
+	while (idx != ntc) {
 		buf = &rx_ring->rx_buf[idx];
+		if (++idx == cnt)
+			idx = 0;
 
-		if (verdict & (ICE_XDP_TX | ICE_XDP_REDIR)) {
+		/* An XDP program could release fragments from the end of the
+		 * buffer. For these, we need to keep the pagecnt_bias as-is.
+		 * To do this, only adjust pagecnt_bias for fragments up to
+		 * the total remaining after the XDP program has run.
+		 */
+		if (verdict != ICE_XDP_CONSUMED)
 			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-			*xdp_xmit |= verdict;
-		} else if (verdict & ICE_XDP_CONSUMED) {
+		else if (i++ <= xdp_frags)
 			buf->pagecnt_bias++;
-		} else if (verdict == ICE_XDP_PASS) {
-			ice_rx_buf_adjust_pg_offset(buf, xdp->frame_sz);
-		}
 
 		ice_put_rx_buf(rx_ring, buf);
-
-		if (++idx == cnt)
-			idx = 0;
-	}
-	/* handle buffers that represented frags released by XDP prog;
-	 * for these we keep pagecnt_bias as-is; refcount from struct page
-	 * has been decremented within XDP prog and we do not have to increase
-	 * the biased refcnt
-	 */
-	for (; i < nr_frags; i++) {
-		buf = &rx_ring->rx_buf[idx];
-		ice_put_rx_buf(rx_ring, buf);
-		if (++idx == cnt)
-			idx = 0;
 	}
 
 	xdp->data = NULL;
 	rx_ring->first_desc = ntc;
-	rx_ring->nr_frags = 0;
 }
 
 /**
@@ -1317,6 +1302,10 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 		/* retrieve a buffer from the ring */
 		rx_buf = ice_get_rx_buf(rx_ring, size, ntc);
 
+		/* Increment ntc before calls to ice_put_rx_mbuf() */
+		if (++ntc == cnt)
+			ntc = 0;
+
 		if (!xdp->data) {
 			void *hard_start;
 
@@ -1325,24 +1314,23 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
-			ice_put_rx_mbuf(rx_ring, xdp, NULL, ntc, ICE_XDP_CONSUMED);
+			ice_put_rx_mbuf(rx_ring, xdp, ntc, ICE_XDP_CONSUMED);
 			break;
 		}
-		if (++ntc == cnt)
-			ntc = 0;
 
 		/* skip if it is NOP desc */
 		if (ice_is_non_eop(rx_ring, rx_desc))
 			continue;
 
-		ice_get_pgcnts(rx_ring);
+		ice_get_pgcnts(rx_ring, ntc);
 		xdp_verdict = ice_run_xdp(rx_ring, xdp, xdp_prog, xdp_ring, rx_desc);
 		if (xdp_verdict == ICE_XDP_PASS)
 			goto construct_skb;
 		total_rx_bytes += xdp_get_buff_len(xdp);
 		total_rx_pkts++;
 
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
+		xdp_xmit |= xdp_verdict & (ICE_XDP_TX | ICE_XDP_REDIR);
 
 		continue;
 construct_skb:
@@ -1355,7 +1343,7 @@ static int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			rx_ring->ring_stats->rx_stats.alloc_buf_failed++;
 			xdp_verdict = ICE_XDP_CONSUMED;
 		}
-		ice_put_rx_mbuf(rx_ring, xdp, &xdp_xmit, ntc, xdp_verdict);
+		ice_put_rx_mbuf(rx_ring, xdp, ntc, xdp_verdict);
 
 		if (!skb)
 			break;

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

@@ -358,7 +358,6 @@ struct ice_rx_ring {
 	struct ice_tx_ring *xdp_ring;
 	struct ice_rx_ring *next;	/* pointer to next ring in q_vector */
 	struct xsk_buff_pool *xsk_pool;
-	u32 nr_frags;
 	u16 max_frame;
 	u16 rx_buf_len;
 	dma_addr_t dma;			/* physical address of ring */

drivers/net/ethernet/intel/igc/igc.h

@@ -345,6 +345,7 @@ struct igc_adapter {
 	/* LEDs */
 	struct mutex led_mutex;
 	struct igc_led_classdev *leds;
+	bool leds_available;
 };
 
 void igc_up(struct igc_adapter *adapter);

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

@@ -7335,8 +7335,14 @@ static int igc_probe(struct pci_dev *pdev,
 
 	if (IS_ENABLED(CONFIG_IGC_LEDS)) {
 		err = igc_led_setup(adapter);
-		if (err)
-			goto err_register;
+		if (err) {
+			netdev_warn_once(netdev,
+					 "LED init failed (%d); continuing without LED support\n",
+					 err);
+			adapter->leds_available = false;
+		} else {
+			adapter->leds_available = true;
+		}
 	}
 
 	return 0;
@@ -7392,7 +7398,7 @@ static void igc_remove(struct pci_dev *pdev)
 	cancel_work_sync(&adapter->watchdog_task);
 	hrtimer_cancel(&adapter->hrtimer);
 
-	if (IS_ENABLED(CONFIG_IGC_LEDS))
+	if (IS_ENABLED(CONFIG_IGC_LEDS) && adapter->leds_available)
 		igc_led_free(adapter);
 
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -6973,6 +6973,13 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter,
 		break;
 	}
 
+	/* Make sure the SWFW semaphore is in a valid state */
+	if (hw->mac.ops.init_swfw_sync)
+		hw->mac.ops.init_swfw_sync(hw);
+
+	if (hw->mac.type == ixgbe_mac_e610)
+		mutex_init(&hw->aci.lock);
+
 #ifdef IXGBE_FCOE
 	/* FCoE support exists, always init the FCoE lock */
 	spin_lock_init(&adapter->fcoe.lock);
@@ -11643,10 +11650,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_sw_init;
 
-	/* Make sure the SWFW semaphore is in a valid state */
-	if (hw->mac.ops.init_swfw_sync)
-		hw->mac.ops.init_swfw_sync(hw);
-
 	if (ixgbe_check_fw_error(adapter))
 		return ixgbe_recovery_probe(adapter);
 
@@ -11850,8 +11853,6 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ether_addr_copy(hw->mac.addr, hw->mac.perm_addr);
 	ixgbe_mac_set_default_filter(adapter);
 
-	if (hw->mac.type == ixgbe_mac_e610)
-		mutex_init(&hw->aci.lock);
 	timer_setup(&adapter->service_timer, ixgbe_service_timer, 0);
 
 	if (ixgbe_removed(hw->hw_addr)) {
@@ -12007,9 +12008,9 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	devl_unlock(adapter->devlink);
 	ixgbe_release_hw_control(adapter);
 	ixgbe_clear_interrupt_scheme(adapter);
+err_sw_init:
 	if (hw->mac.type == ixgbe_mac_e610)
 		mutex_destroy(&adapter->hw.aci.lock);
-err_sw_init:
 	ixgbe_disable_sriov(adapter);
 	adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP;
 	iounmap(adapter->io_addr);
@@ -12060,10 +12061,8 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	set_bit(__IXGBE_REMOVING, &adapter->state);
 	cancel_work_sync(&adapter->service_task);
 
-	if (adapter->hw.mac.type == ixgbe_mac_e610) {
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
 		ixgbe_disable_link_status_events(adapter);
-		mutex_destroy(&adapter->hw.aci.lock);
-	}
 
 	if (adapter->mii_bus)
 		mdiobus_unregister(adapter->mii_bus);
@@ -12123,6 +12122,9 @@ static void ixgbe_remove(struct pci_dev *pdev)
 	disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state);
 	free_netdev(netdev);
 
+	if (adapter->hw.mac.type == ixgbe_mac_e610)
+		mutex_destroy(&adapter->hw.aci.lock);
+
 	if (disable_dev)
 		pci_disable_device(pdev);
 }