Merge tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

183d46ff · Linus Torvalds <[email protected]> · 2024-08-01 09:42:09 -07:00

Pull networking fixes from Paolo Abeni:
 "Including fixes from wireless, bleutooth, BPF and netfilter.

  Current release - regressions:

   - core: drop bad gso csum_start and offset in virtio_net_hdr

   - wifi: mt76: fix null pointer access in mt792x_mac_link_bss_remove

   - eth: tun: add missing bpf_net_ctx_clear() in do_xdp_generic()

   - phy: aquantia: only poll GLOBAL_CFG regs on aqr113, aqr113c and
     aqr115c

  Current release - new code bugs:

   - smc: prevent UAF in inet_create()

   - bluetooth: btmtk: fix kernel crash when entering btmtk_usb_suspend

   - eth: bnxt: reject unsupported hash functions

  Previous releases - regressions:

   - sched: act_ct: take care of padding in struct zones_ht_key

   - netfilter: fix null-ptr-deref in iptable_nat_table_init().

   - tcp: adjust clamping window for applications specifying SO_RCVBUF

  Previous releases - always broken:

   - ethtool: rss: small fixes to spec and GET

   - mptcp:
      - fix signal endpoint re-add
      - pm: fix backup support in signal endpoints

   - wifi: ath12k: fix soft lockup on suspend

   - eth: bnxt_en: fix RSS logic in __bnxt_reserve_rings()

   - eth: ice: fix AF_XDP ZC timeout and concurrency issues

   - eth: mlx5:
      - fix missing lock on sync reset reload
      - fix error handling in irq_pool_request_irq"

* tag 'net-6.11-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (76 commits)
  mptcp: fix duplicate data handling
  mptcp: fix bad RCVPRUNED mib accounting
  ipv6: fix ndisc_is_useropt() handling for PIO
  igc: Fix double reset adapter triggered from a single taprio cmd
  net: MAINTAINERS: Demote Qualcomm IPA to "maintained"
  net: wan: fsl_qmc_hdlc: Discard received CRC
  net: wan: fsl_qmc_hdlc: Convert carrier_lock spinlock to a mutex
  net/mlx5e: Add a check for the return value from mlx5_port_set_eth_ptys
  net/mlx5e: Fix CT entry update leaks of modify header context
  net/mlx5e: Require mlx5 tc classifier action support for IPsec prio capability
  net/mlx5: Fix missing lock on sync reset reload
  net/mlx5: Lag, don't use the hardcoded value of the first port
  net/mlx5: DR, Fix 'stack guard page was hit' error in dr_rule
  net/mlx5: Fix error handling in irq_pool_request_irq
  net/mlx5: Always drain health in shutdown callback
  net: Add skbuff.h to MAINTAINERS
  r8169: don't increment tx_dropped in case of NETDEV_TX_BUSY
  netfilter: iptables: Fix potential null-ptr-deref in ip6table_nat_table_init().
  netfilter: iptables: Fix null-ptr-deref in iptable_nat_table_init().
  net: drop bad gso csum_start and offset in virtio_net_hdr
  ...

Commit: 183d46ff422ef9f3d755b6808ef3faa6d009ba3a
Parents: 21b136cc · 25010bfd

Merge commit. Changes below are compared with the first parent: 21b136cc.

Changes

73 files changed · +694 −303

File	Status	Add	Del	Content
Documentation/netlink/specs/ethtool.yaml	modified	+1	−1	View file
Documentation/networking/ethtool-netlink.rst	modified	+1	−0	View file
MAINTAINERS	modified	+2	−1	View file
drivers/bluetooth/Kconfig	modified	+2	−0	View file
drivers/bluetooth/btintel.c	modified	+3	−0	View file
drivers/bluetooth/btmtk.c	modified	+4	−1	View file
drivers/net/ethernet/broadcom/bnxt/bnxt.c	modified	+4	−2	View file
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c	modified	+12	−2	View file
drivers/net/ethernet/intel/ice/ice.h	modified	+5	−6	View file
drivers/net/ethernet/intel/ice/ice_base.c	modified	+2	−2	View file
drivers/net/ethernet/intel/ice/ice_main.c	modified	+1	−1	View file
drivers/net/ethernet/intel/ice/ice_txrx.c	modified	+6	−4	View file
drivers/net/ethernet/intel/ice/ice_xsk.c	modified	+111	−73	View file
drivers/net/ethernet/intel/ice/ice_xsk.h	modified	+10	−4	View file
drivers/net/ethernet/intel/igc/igc_main.c	modified	+17	−16	View file
drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c	modified	+3	−3	View file
drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c	modified	+1	−0	View file
drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c	modified	+4	−3	View file
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c	modified	+6	−1	View file
drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c	modified	+4	−1	View file
drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c	modified	+7	−3	View file
drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c	modified	+1	−1	View file
drivers/net/ethernet/mellanox/mlx5/core/main.c	modified	+1	−1	View file
drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c	modified	+1	−0	View file
drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c	modified	+1	−1	View file
drivers/net/ethernet/meta/Kconfig	modified	+1	−1	View file
drivers/net/ethernet/realtek/r8169_main.c	modified	+2	−6	View file
drivers/net/ethernet/xilinx/xilinx_axienet_main.c	modified	+1	−1	View file
drivers/net/phy/aquantia/aquantia_main.c	modified	+21	−8	View file
drivers/net/phy/micrel.c	modified	+19	−15	View file
drivers/net/phy/realtek.c	modified	+7	−0	View file
drivers/net/usb/sr9700.c	modified	+9	−2	View file
drivers/net/wan/fsl_qmc_hdlc.c	modified	+22	−9	View file
drivers/net/wireless/ath/ath12k/pci.c	modified	+2	−1	View file
drivers/net/wireless/ath/ath12k/wow.c	modified	+4	−4	View file
drivers/net/wireless/mediatek/mt76/mt7921/main.c	modified	+1	−0	View file
include/linux/virtio_net.h	modified	+5	−11	View file
include/trace/events/mptcp.h	modified	+1	−1	View file
net/bluetooth/hci_core.c	modified	+0	−7	View file
net/bluetooth/hci_event.c	modified	+3	−2	View file
net/bluetooth/hci_sync.c	modified	+21	−0	View file
net/core/dev.c	modified	+1	−0	View file
net/core/rtnetlink.c	modified	+1	−1	View file
net/ethtool/ioctl.c	modified	+33	−10	View file
net/ethtool/rss.c	modified	+7	−1	View file
net/ipv4/netfilter/iptable_nat.c	modified	+10	−8	View file
net/ipv4/tcp_input.c	modified	+16	−7	View file
net/ipv4/tcp_offload.c	modified	+3	−0	View file
net/ipv4/udp_offload.c	modified	+4	−0	View file
net/ipv6/ndisc.c	modified	+18	−16	View file
net/ipv6/netfilter/ip6table_nat.c	modified	+9	−5	View file
net/iucv/af_iucv.c	modified	+2	−2	View file
net/mac80211/cfg.c	modified	+5	−2	View file
net/mac80211/tx.c	modified	+3	−2	View file
net/mac80211/util.c	modified	+1	−1	View file
net/mptcp/mib.c	modified	+2	−0	View file
net/mptcp/mib.h	modified	+2	−0	View file
net/mptcp/options.c	modified	+1	−1	View file
net/mptcp/pm.c	modified	+12	−0	View file
net/mptcp/pm_netlink.c	modified	+37	−9	View file
net/mptcp/pm_userspace.c	modified	+18	−0	View file
net/mptcp/protocol.c	modified	+10	−8	View file
net/mptcp/protocol.h	modified	+4	−0	View file
net/mptcp/subflow.c	modified	+22	−4	View file
net/sched/act_ct.c	modified	+3	−1	View file
net/smc/af_smc.c	modified	+4	−3	View file
net/wireless/scan.c	modified	+8	−3	View file
net/wireless/sme.c	modified	+1	−0	View file
tools/testing/selftests/bpf/Makefile	modified	+1	−1	View file
tools/testing/selftests/bpf/prog_tests/uprobe_syscall.c	modified	+1	−1	View file
tools/testing/selftests/drivers/net/hw/rss_ctx.py	modified	+34	−3	View file
tools/testing/selftests/net/mptcp/mptcp_connect.c	modified	+4	−4	View file
tools/testing/selftests/net/mptcp/mptcp_join.sh	modified	+88	−15	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/netlink/specs/ethtool.yaml

View file

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 495e35f..ea21fe1 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1753,6 +1753,7 @@ operations:
         request:
           attributes:
             - header
+            - context
         reply:
           attributes:
             - header
@@ -1761,7 +1762,6 @@ operations:
             - indir
             - hkey
             - input_xfrm
-      dump: *rss-get-op
     -
       name: plca-get-cfg
       doc: Get PLCA params.

Documentation/networking/ethtool-netlink.rst

View file

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 3ab423b..d5f246a 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1875,6 +1875,7 @@ Kernel response contents:
 
 =====================================  ======  ==========================
   ``ETHTOOL_A_RSS_HEADER``             nested  reply header
+  ``ETHTOOL_A_RSS_CONTEXT``            u32     context number
   ``ETHTOOL_A_RSS_HFUNC``              u32     RSS hash func
   ``ETHTOOL_A_RSS_INDIR``              binary  Indir table bytes
   ``ETHTOOL_A_RSS_HKEY``               binary  Hash key bytes

MAINTAINERS

View file

diff --git a/MAINTAINERS b/MAINTAINERS
index 42decde..8766f3e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15936,6 +15936,7 @@ F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
 F:	include/linux/netdevice.h
+F:	include/linux/skbuff.h
 F:	include/net/
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
@@ -18556,7 +18557,7 @@ F:	drivers/usb/misc/qcom_eud.c
 QCOM IPA DRIVER
 M:	Alex Elder <[email protected]>
 L:	[email protected]
-S:	Supported
+S:	Maintained
 F:	drivers/net/ipa/
 
 QEMU MACHINE EMULATOR AND VIRTUALIZER SUPPORT

drivers/bluetooth/Kconfig

View file

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 90a94a1..769fa28 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -413,6 +413,7 @@ config BT_ATH3K
 config BT_MTKSDIO
 	tristate "MediaTek HCI SDIO driver"
 	depends on MMC
+	depends on USB || !BT_HCIBTUSB_MTK
 	select BT_MTK
 	help
 	  MediaTek Bluetooth HCI SDIO driver.
@@ -425,6 +426,7 @@ config BT_MTKSDIO
 config BT_MTKUART
 	tristate "MediaTek HCI UART driver"
 	depends on SERIAL_DEV_BUS
+	depends on USB || !BT_HCIBTUSB_MTK
 	select BT_MTK
 	help
 	  MediaTek Bluetooth HCI UART driver.

drivers/bluetooth/btintel.c

View file

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index e7a6125..2ebc970 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -3085,6 +3085,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		btintel_set_dsm_reset_method(hdev, &ver_tlv);
 
 		err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
+		if (err)
+			goto exit_error;
+
 		btintel_register_devcoredump_support(hdev);
 		btintel_print_fseq_info(hdev);
 		break;

drivers/bluetooth/btmtk.c

View file

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index b7c3486..2b7c800 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -437,6 +437,7 @@ int btmtk_process_coredump(struct hci_dev *hdev, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(btmtk_process_coredump);
 
+#if IS_ENABLED(CONFIG_BT_HCIBTUSB_MTK)
 static void btmtk_usb_wmt_recv(struct urb *urb)
 {
 	struct hci_dev *hdev = urb->context;
@@ -1262,7 +1263,8 @@ int btmtk_usb_suspend(struct hci_dev *hdev)
 	struct btmtk_data *btmtk_data = hci_get_priv(hdev);
 
 	/* Stop urb anchor for iso data transmission */
-	usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
+	if (test_bit(BTMTK_ISOPKT_RUNNING, &btmtk_data->flags))
+		usb_kill_anchored_urbs(&btmtk_data->isopkt_anchor);
 
 	return 0;
 }
@@ -1487,6 +1489,7 @@ int btmtk_usb_shutdown(struct hci_dev *hdev)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(btmtk_usb_shutdown);
+#endif
 
 MODULE_AUTHOR("Sean Wang <[email protected]>");
 MODULE_AUTHOR("Mark Chen <[email protected]>");

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

View file

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ffa74c2..23f74c6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7649,8 +7649,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num);
 static int __bnxt_reserve_rings(struct bnxt *bp)
 {
 	struct bnxt_hw_rings hwr = {0};
+	int rx_rings, old_rx_rings, rc;
 	int cp = bp->cp_nr_rings;
-	int rx_rings, rc;
 	int ulp_msix = 0;
 	bool sh = false;
 	int tx_cp;
@@ -7684,6 +7684,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	hwr.grp = bp->rx_nr_rings;
 	hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
 	hwr.stat = bnxt_get_func_stat_ctxs(bp);
+	old_rx_rings = bp->hw_resc.resv_rx_rings;
 
 	rc = bnxt_hwrm_reserve_rings(bp, &hwr);
 	if (rc)
@@ -7738,7 +7739,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 	if (!bnxt_rings_ok(bp, &hwr))
 		return -ENOMEM;
 
-	if (!netif_is_rxfh_configured(bp->dev))
+	if (old_rx_rings != bp->hw_resc.resv_rx_rings &&
+	    !netif_is_rxfh_configured(bp->dev))
 		bnxt_set_dflt_rss_indir_tbl(bp, NULL);
 
 	if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {

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

View file

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index d00ef00..ab8e3f1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -1863,8 +1863,14 @@ static void bnxt_modify_rss(struct bnxt *bp, struct ethtool_rxfh_context *ctx,
 }
 
 static int bnxt_rxfh_context_check(struct bnxt *bp,
+				   const struct ethtool_rxfh_param *rxfh,
 				   struct netlink_ext_ack *extack)
 {
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+
 	if (!BNXT_SUPPORTS_MULTI_RSS_CTX(bp)) {
 		NL_SET_ERR_MSG_MOD(extack, "RSS contexts not supported");
 		return -EOPNOTSUPP;
@@ -1888,7 +1894,7 @@ static int bnxt_create_rxfh_context(struct net_device *dev,
 	struct bnxt_vnic_info *vnic;
 	int rc;
 
-	rc = bnxt_rxfh_context_check(bp, extack);
+	rc = bnxt_rxfh_context_check(bp, rxfh, extack);
 	if (rc)
 		return rc;
 
@@ -1915,8 +1921,12 @@ static int bnxt_create_rxfh_context(struct net_device *dev,
 	if (rc)
 		goto out;
 
+	/* Populate defaults in the context */
 	bnxt_set_dflt_rss_indir_tbl(bp, ctx);
+	ctx->hfunc = ETH_RSS_HASH_TOP;
 	memcpy(vnic->rss_hash_key, bp->rss_hash_key, HW_HASH_KEY_SIZE);
+	memcpy(ethtool_rxfh_context_key(ctx),
+	       bp->rss_hash_key, HW_HASH_KEY_SIZE);
 
 	rc = bnxt_hwrm_vnic_alloc(bp, vnic, 0, bp->rx_nr_rings);
 	if (rc) {
@@ -1953,7 +1963,7 @@ static int bnxt_modify_rxfh_context(struct net_device *dev,
 	struct bnxt_rss_ctx *rss_ctx;
 	int rc;
 
-	rc = bnxt_rxfh_context_check(bp, extack);
+	rc = bnxt_rxfh_context_check(bp, rxfh, extack);
 	if (rc)
 		return rc;
 

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

View file

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 99a75a5..caaa101 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
 }
 
 /**
- * ice_xsk_pool - get XSK buffer pool bound to a ring
+ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
  * @ring: Rx ring to use
  *
- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
- * present, NULL otherwise.
+ * Sets XSK buff pool pointer on Rx ring.
  */
-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
+static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
 {
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	return ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**
@@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
+	WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
 }
 
 /**

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

View file

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 5d396c1..1facf17 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 				return err;
 		}
 
-		ring->xsk_pool = ice_xsk_pool(ring);
+		ice_rx_xsk_pool(ring);
 		if (ring->xsk_pool) {
 			xdp_rxq_info_unreg(&ring->xdp_rxq);
 
@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 			return 0;
 		}
 
-		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
+		ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
 		if (!ok) {
 			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
 

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

View file

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index ec636be..3de0200 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2948,7 +2948,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
 	ice_for_each_rxq(vsi, i) {
 		struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
 
-		if (rx_ring->xsk_pool)
+		if (READ_ONCE(rx_ring->xsk_pool))
 			napi_schedule(&rx_ring->q_vector->napi);
 	}
 }

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

View file

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8bb743f..8d25b69 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
 	if (rx_ring->vsi->type == ICE_VSI_PF)
 		if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
 			xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	rx_ring->xdp_prog = NULL;
+	WRITE_ONCE(rx_ring->xdp_prog, NULL);
 	if (rx_ring->xsk_pool) {
 		kfree(rx_ring->xdp_buf);
 		rx_ring->xdp_buf = NULL;
@@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 	 * budget and be more aggressive about cleaning up the Tx descriptors.
 	 */
 	ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
 		bool wd;
 
-		if (tx_ring->xsk_pool)
-			wd = ice_xmit_zc(tx_ring);
+		if (xsk_pool)
+			wd = ice_xmit_zc(tx_ring, xsk_pool);
 		else if (ice_ring_is_xdp(tx_ring))
 			wd = true;
 		else
@@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		budget_per_ring = budget;
 
 	ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+		struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
 		int cleaned;
 
 		/* A dedicated path for zero-copy allows making a single
@@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
 		 * ice_clean_rx_irq function and makes the codebase cleaner.
 		 */
 		cleaned = rx_ring->xsk_pool ?
-			  ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
+			  ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
 			  ice_clean_rx_irq(rx_ring, budget_per_ring);
 		work_done += cleaned;
 		/* if we clean as many as budgeted, we must not be done */

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

View file

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index a65955e..240a7be 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
 static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
 {
 	ice_clean_tx_ring(vsi->tx_rings[q_idx]);
-	if (ice_is_xdp_ena_vsi(vsi)) {
-		synchronize_rcu();
+	if (ice_is_xdp_ena_vsi(vsi))
 		ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
-	}
 	ice_clean_rx_ring(vsi->rx_rings[q_idx]);
 }
 
@@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
  * ice_qvec_cfg_msix - Enable IRQ for given queue vector
  * @vsi: the VSI that contains queue vector
  * @q_vector: queue vector
+ * @qid: queue index
  */
 static void
-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
+ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
 {
 	u16 reg_idx = q_vector->reg_idx;
 	struct ice_pf *pf = vsi->back;
 	struct ice_hw *hw = &pf->hw;
-	struct ice_tx_ring *tx_ring;
-	struct ice_rx_ring *rx_ring;
+	int q, _qid = qid;
 
 	ice_cfg_itr(hw, q_vector);
 
-	ice_for_each_tx_ring(tx_ring, q_vector->tx)
-		ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
-				      q_vector->tx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_tx; q++) {
+		ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
+		_qid++;
+	}
+
+	_qid = qid;
 
-	ice_for_each_rx_ring(rx_ring, q_vector->rx)
-		ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
-				      q_vector->rx.itr_idx);
+	for (q = 0; q < q_vector->num_ring_rx; q++) {
+		ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
+		_qid++;
+	}
 
 	ice_flush(hw);
 }
@@ -164,6 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 	struct ice_tx_ring *tx_ring;
 	struct ice_rx_ring *rx_ring;
 	int timeout = 50;
+	int fail = 0;
 	int err;
 
 	if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
@@ -180,15 +183,17 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		usleep_range(1000, 2000);
 	}
 
+	synchronize_net();
+	netif_carrier_off(vsi->netdev);
+	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+
 	ice_qvec_dis_irq(vsi, rx_ring, q_vector);
 	ice_qvec_toggle_napi(vsi, q_vector, false);
 
-	netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
-
 	ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
 	err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
@@ -196,17 +201,15 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 		ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
 		err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
 					   &txq_meta);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 	}
-	err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
-	if (err)
-		return err;
 
+	ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
 	ice_qp_clean_rings(vsi, q_idx);
 	ice_qp_reset_stats(vsi, q_idx);
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -219,40 +222,48 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
 static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 {
 	struct ice_q_vector *q_vector;
+	int fail = 0;
+	bool link_up;
 	int err;
 
 	err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	if (ice_is_xdp_ena_vsi(vsi)) {
 		struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
 
 		err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
-		if (err)
-			return err;
+		if (!fail)
+			fail = err;
 		ice_set_ring_xdp(xdp_ring);
 		ice_tx_xsk_pool(vsi, q_idx);
 	}
 
 	err = ice_vsi_cfg_single_rxq(vsi, q_idx);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	q_vector = vsi->rx_rings[q_idx]->q_vector;
-	ice_qvec_cfg_msix(vsi, q_vector);
+	ice_qvec_cfg_msix(vsi, q_vector, q_idx);
 
 	err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
-	if (err)
-		return err;
+	if (!fail)
+		fail = err;
 
 	ice_qvec_toggle_napi(vsi, q_vector, true);
 	ice_qvec_ena_irq(vsi, q_vector);
 
-	netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+	/* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
+	synchronize_net();
+	ice_get_link_status(vsi->port_info, &link_up);
+	if (link_up) {
+		netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+		netif_carrier_on(vsi->netdev);
+	}
 	clear_bit(ICE_CFG_BUSY, vsi->state);
 
-	return 0;
+	return fail;
 }
 
 /**
@@ -459,6 +470,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
 /**
  * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Place the @count of descriptors onto Rx ring. Handle the ring wrap
@@ -467,7 +479,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
  *
  * Returns true if all allocations were successful, false if any fail.
  */
-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+				   struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u32 nb_buffs_extra = 0, nb_buffs = 0;
 	union ice_32b_rx_flex_desc *rx_desc;
@@ -479,8 +492,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	xdp = ice_xdp_buf(rx_ring, ntu);
 
 	if (ntu + count >= rx_ring->count) {
-		nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
-						   rx_desc,
+		nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
 						   rx_ring->count - ntu);
 		if (nb_buffs_extra != rx_ring->count - ntu) {
 			ntu += nb_buffs_extra;
@@ -493,7 +505,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 		ice_release_rx_desc(rx_ring, 0);
 	}
 
-	nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
+	nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
 
 	ntu += nb_buffs;
 	if (ntu == rx_ring->count)
@@ -509,6 +521,7 @@ exit:
 /**
  * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
  * @rx_ring: Rx ring
+ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
  * @count: The number of buffers to allocate
  *
  * Wrapper for internal allocation routine; figure out how many tail
@@ -516,7 +529,8 @@ exit:
  *
  * Returns true if all calls to internal alloc routine succeeded
  */
-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
+			  struct xsk_buff_pool *xsk_pool, u16 count)
 {
 	u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
 	u16 leftover, i, tail_bumps;
@@ -525,9 +539,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
 	leftover = count - (tail_bumps * rx_thresh);
 
 	for (i = 0; i < tail_bumps; i++)
-		if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
+		if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
 			return false;
-	return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
+	return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
 }
 
 /**
@@ -596,8 +610,10 @@ out:
 /**
  * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
  * @xdp_ring: XDP Tx ring
+ * @xsk_pool: AF_XDP buffer pool pointer
  */
-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
+				struct xsk_buff_pool *xsk_pool)
 {
 	u16 ntc = xdp_ring->next_to_clean;
 	struct ice_tx_desc *tx_desc;
@@ -648,7 +664,7 @@ skip:
 	if (xdp_ring->next_to_clean >= cnt)
 		xdp_ring->next_to_clean -= cnt;
 	if (xsk_frames)
-		xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
+		xsk_tx_completed(xsk_pool, xsk_frames);
 
 	return completed_frames;
 }
@@ -657,6 +673,7 @@ skip:
  * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
  * @xdp: XDP buffer to xmit
  * @xdp_ring: XDP ring to produce descriptor onto
+ * @xsk_pool: AF_XDP buffer pool pointer
  *
  * note that this function works directly on xdp_buff, no need to convert
  * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
@@ -666,7 +683,8 @@ skip:
  * was not enough space on XDP ring
  */
 static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
-			      struct ice_tx_ring *xdp_ring)
+			      struct ice_tx_ring *xdp_ring,
+			      struct xsk_buff_pool *xsk_pool)
 {
 	struct skb_shared_info *sinfo = NULL;
 	u32 size = xdp->data_end - xdp->data;
@@ -680,7 +698,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 
 	free_space = ICE_DESC_UNUSED(xdp_ring);
 	if (free_space < ICE_RING_QUARTER(xdp_ring))
-		free_space += ice_clean_xdp_irq_zc(xdp_ring);
+		free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
 
 	if (unlikely(!free_space))
 		goto busy;
@@ -700,7 +718,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
 		dma_addr_t dma;
 
 		dma = xsk_buff_xdp_get_dma(xdp);