Merge tag 'net-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski: "Including fixes from Netfilter. Current release - new code bugs: - net: fix backlog_unlock_irq_restore() vs CONFIG_PREEMPT_RT - eth: mlx5e: XSK, Fix unintended ICOSQ change - phy_port: correctly recompute the port's linkmodes - vsock: prevent child netns mode switch from local to global - couple of kconfig fixes for new symbols Previous releases - regressions: - nfc: nci: fix false-positive parameter validation for packet data - net: do not delay zero-copy skbs in skb_attempt_defer_free() Previous releases - always broken: - mctp: ensure our nlmsg responses to user space are zero-initialised - ipv6: ioam: fix heap buffer overflow in __ioam6_fill_trace_data() - fixes for ICMP rate limiting Misc: - intel: fix PCI device ID conflict between i40e and ipw2200" * tag 'net-7.0-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (85 commits) net: nfc: nci: Fix parameter validation for packet data net/mlx5e: Use unsigned for mlx5e_get_max_num_channels net/mlx5e: Fix deadlocks between devlink and netdev instance locks net/mlx5e: MACsec, add ASO poll loop in macsec_aso_set_arm_event net/mlx5: Fix misidentification of write combining CQE during poll loop net/mlx5e: Fix misidentification of ASO CQE during poll loop net/mlx5: Fix multiport device check over light SFs bonding: alb: fix UAF in rlb_arp_recv during bond up/down bnge: fix reserving resources from FW eth: fbnic: Advertise supported XDP features. rds: tcp: fix uninit-value in __inet_bind net/rds: Fix NULL pointer dereference in rds_tcp_accept_one octeontx2-af: Fix default entries mcam entry action net/mlx5e: XSK, Fix unintended ICOSQ change ipv6: icmp: icmpv6_xrlim_allow() optimization if net.ipv6.icmp.ratelimit is zero ipv4: icmp: icmpv4_xrlim_allow() optimization if net.ipv4.icmp_ratelimit is zero ipv6: icmp: remove obsolete code in icmpv6_xrlim_allow() inet: move icmp_global_{credit,stamp} to a separate cache line icmp: prevent possible overflow in icmp_global_allow() selftests/net: packetdrill: add ipv4-mapped-ipv6 tests ...
2026-08-13 14:19:53 -07:00 · 2026-02-19 10:39:08 -08:00
parent 4f13d0dabc 571dcbeb8e
commit 8bf22c33e7
103 changed files with 1140 additions and 694 deletions
@@ -40,8 +40,8 @@ Table : Subdirectories in /proc/sys/net
 bridge    Bridging              rose       X.25 PLP layer
 core      General parameter     tipc       TIPC
 ethernet  Ethernet protocol     unix       Unix domain sockets
- ipv4      IP version 4          x25        X.25 protocol
- ipv6      IP version 6
+ ipv4      IP version 4          vsock      VSOCK sockets
+ ipv6      IP version 6          x25        X.25 protocol
 ========= =================== = ========== ===================

 1. /proc/sys/net/core - Network core options
@@ -551,3 +551,51 @@ originally may have been issued in the correct sequential order.
 If named_timeout is nonzero, failed topology updates will be placed on a defer
 queue until another event arrives that clears the error, or until the timeout
 expires. Value is in milliseconds.
+
+6. /proc/sys/net/vsock - VSOCK sockets
+--------------------------------------
+
+VSOCK sockets (AF_VSOCK) provide communication between virtual machines and
+their hosts. The behavior of VSOCK sockets in a network namespace is determined
+by the namespace's mode (``global`` or ``local``), which controls how CIDs
+(Context IDs) are allocated and how sockets interact across namespaces.
+
+ns_mode
+-------
+
+Read-only. Reports the current namespace's mode, set at namespace creation
+and immutable thereafter.
+
+Values:
+
+	- ``global`` - the namespace shares system-wide CID allocation and
+	  its sockets can reach any VM or socket in any global namespace.
+	  Sockets in this namespace cannot reach sockets in local
+	  namespaces.
+	- ``local`` - the namespace has private CID allocation and its
+	  sockets can only connect to VMs or sockets within the same
+	  namespace.
+
+The init_net mode is always ``global``.
+
+child_ns_mode
+-------------
+
+Controls what mode newly created child namespaces will inherit. At namespace
+creation, ``ns_mode`` is inherited from the parent's ``child_ns_mode``. The
+initial value matches the namespace's own ``ns_mode``.
+
+Values:
+
+	- ``global`` - child namespaces will share system-wide CID allocation
+	  and their sockets will be able to reach any VM or socket in any
+	  global namespace.
+	- ``local`` - child namespaces will have private CID allocation and
+	  their sockets will only be able to connect within their own
+	  namespace.
+
+Changing ``child_ns_mode`` only affects namespaces created after the change;
+it does not modify the current namespace or any existing children.
+
+A namespace with ``ns_mode`` set to ``local`` cannot change
+``child_ns_mode`` to ``global`` (returns ``-EPERM``).
@@ -3234,12 +3234,13 @@ enhanced_dad - BOOLEAN
 ===========

 ratelimit - INTEGER
-	Limit the maximal rates for sending ICMPv6 messages.
+	Limit the maximal rates for sending ICMPv6 messages to a particular
+	peer.

 	0 to disable any limiting,
-	otherwise the minimal space between responses in milliseconds.
+	otherwise the space between responses in milliseconds.

-	Default: 1000
+	Default: 100

 ratemask - list of comma separated ranges
 	For ICMPv6 message types matching the ranges in the ratemask, limit
@@ -373,6 +373,10 @@ fore200e_shutdown(struct fore200e* fore200e)
 	fallthrough;
    case FORE200E_STATE_IRQ:
 	free_irq(fore200e->irq, fore200e->atm_dev);
+#ifdef FORE200E_USE_TASKLET
+	tasklet_kill(&fore200e->tx_tasklet);
+	tasklet_kill(&fore200e->rx_tasklet);
+#endif

 	fallthrough;
    case FORE200E_STATE_ALLOC_BUF:
@@ -91,6 +91,8 @@ zl3073x_ref_freq_set(struct zl3073x_ref *ref, u32 freq)

 	ref->freq_base = base;
 	ref->freq_mult = mult;
+	ref->freq_ratio_m = 1;
+	ref->freq_ratio_n = 1;

 	return 0;
 }
@@ -333,6 +333,7 @@ config MACSEC

 config NETCONSOLE
 	tristate "Network console logging support"
+	depends on PRINTK
 	help
 	  If you want to log kernel messages over the network, enable this.
 	  See <file:Documentation/networking/netconsole.rst> for details.
@@ -115,6 +115,8 @@ static const struct attribute_group com20020_state_group = {
 	.attrs = com20020_state_attrs,
 };

+static struct com20020_pci_card_info card_info_2p5mbit;
+
 static void com20020pci_remove(struct pci_dev *pdev);

 static int com20020pci_probe(struct pci_dev *pdev,
@@ -140,7 +142,7 @@ static int com20020pci_probe(struct pci_dev *pdev,

 	ci = (struct com20020_pci_card_info *)id->driver_data;
 	if (!ci)
-		return -EINVAL;
+		ci = &card_info_2p5mbit;

 	priv->ci = ci;
 	mm = &ci->misc_map;
@@ -347,6 +349,18 @@ static struct com20020_pci_card_info card_info_5mbit = {
 	.flags = ARC_IS_5MBIT,
 };

+static struct com20020_pci_card_info card_info_2p5mbit = {
+	.name = "ARC-PCI",
+	.devcount = 1,
+	.chan_map_tbl = {
+		{
+			.bar = 2,
+			.offset = 0x00,
+			.size = 0x08,
+		},
+	},
+};
+
 static struct com20020_pci_card_info card_info_sohard = {
 	.name = "SOHARD SH ARC-PCI",
 	.devcount = 1,
@@ -4343,9 +4343,13 @@ static int bond_close(struct net_device *bond_dev)

 	bond_work_cancel_all(bond);
 	bond->send_peer_notif = 0;
+	WRITE_ONCE(bond->recv_probe, NULL);
+
+	/* Wait for any in-flight RX handlers */
+	synchronize_net();
+
 	if (bond_is_lb(bond))
 		bond_alb_deinitialize(bond);
-	bond->recv_probe = NULL;

 	if (BOND_MODE(bond) == BOND_MODE_8023AD &&
 	    bond->params.broadcast_neighbor)
@@ -2,7 +2,6 @@
 config NET_DSA_MXL862
 	tristate "MaxLinear MxL862xx"
 	depends on NET_DSA
-	select MAXLINEAR_GPHY
 	select NET_DSA_TAG_MXL_862XX
 	help
 	  This enables support for the MaxLinear MxL862xx switch family.
@@ -442,7 +442,7 @@ __bnge_hwrm_reserve_pf_rings(struct bnge_dev *bd, struct bnge_hw_rings *hwr)
 	struct hwrm_func_cfg_input *req;
 	u32 enables = 0;

-	if (bnge_hwrm_req_init(bd, req, HWRM_FUNC_QCFG))
+	if (bnge_hwrm_req_init(bd, req, HWRM_FUNC_CFG))
 		return NULL;

 	req->fid = cpu_to_le16(0xffff);
@@ -16,7 +16,6 @@
 #include <linux/etherdevice.h>
 #include <linux/if.h>
 #include <net/ip.h>
-#include <net/netdev_queues.h>
 #include <linux/skbuff.h>
 #include <net/page_pool/helpers.h>

@@ -423,7 +423,7 @@ static int ec_bhf_open(struct net_device *net_dev)

 error_rx_free:
 	dma_free_coherent(dev, priv->rx_buf.alloc_len, priv->rx_buf.alloc,
-			  priv->rx_buf.alloc_len);
+			  priv->rx_buf.alloc_phys);
 out:
 	return err;
 }
@@ -75,7 +75,13 @@ static const struct pci_device_id i40e_pci_tbl[] = {
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0},
-	{PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0},
+	/*
+	 * This ID conflicts with ipw2200, but the devices can be differentiated
+	 * because i40e devices use PCI_CLASS_NETWORK_ETHERNET and ipw2200
+	 * devices use PCI_CLASS_NETWORK_OTHER.
+	 */
+	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, I40E_DEV_ID_10G_B),
+		PCI_CLASS_NETWORK_ETHERNET << 8, 0xffff00, 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_X722), 0},
 	{PCI_VDEVICE(INTEL, I40E_DEV_ID_SFP_X722), 0},
@@ -1042,32 +1042,35 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf,
 	rvu_write64(rvu, blkaddr,
 		    NPC_AF_MCAMEX_BANKX_ACTION(index, bank), *(u64 *)&action);

-	/* update the VF flow rule action with the VF default entry action */
-	if (mcam_index < 0)
-		npc_update_vf_flow_entry(rvu, mcam, blkaddr, pcifunc,
-					 *(u64 *)&action);
-
 	/* update the action change in default rule */
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 	if (pfvf->def_ucast_rule)
 		pfvf->def_ucast_rule->rx_action = action;

-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_PROMISC_ENTRY);
+	if (mcam_index < 0) {
+		/* update the VF flow rule action with the VF default
+		 * entry action
+		 */
+		npc_update_vf_flow_entry(rvu, mcam, blkaddr, pcifunc,
+					 *(u64 *)&action);

-	/* If PF's promiscuous entry is enabled,
-	 * Set RSS action for that entry as well
-	 */
-	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
-					  alg_idx);
+		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+						 nixlf, NIXLF_PROMISC_ENTRY);

-	index = npc_get_nixlf_mcam_index(mcam, pcifunc,
-					 nixlf, NIXLF_ALLMULTI_ENTRY);
-	/* If PF's allmulti  entry is enabled,
-	 * Set RSS action for that entry as well
-	 */
-	npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index, blkaddr,
-					  alg_idx);
+		/* If PF's promiscuous  entry is enabled,
+		 * Set RSS action for that entry as well
+		 */
+		npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index,
+						  blkaddr, alg_idx);
+
+		index = npc_get_nixlf_mcam_index(mcam, pcifunc,
+						 nixlf, NIXLF_ALLMULTI_ENTRY);
+		/* If PF's allmulti  entry is enabled,
+		 * Set RSS action for that entry as well
+		 */
+		npc_update_rx_action_with_alg_idx(rvu, action, pfvf, index,
+						  blkaddr, alg_idx);
+	}
 }

 void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc,
@@ -180,7 +180,8 @@ static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size)
 }

 /* Use this function to get max num channels (rxqs/txqs) only to create netdev */
-static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
+static inline unsigned int
+mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 {
 	return is_kdump_kernel() ?
 		MLX5E_MIN_NUM_CHANNELS :
@@ -1103,6 +1104,7 @@ int mlx5e_open_locked(struct net_device *netdev);
 int mlx5e_close_locked(struct net_device *netdev);

 void mlx5e_trigger_napi_icosq(struct mlx5e_channel *c);
+void mlx5e_trigger_napi_async_icosq(struct mlx5e_channel *c);
 void mlx5e_trigger_napi_sched(struct napi_struct *napi);

 int mlx5e_open_channels(struct mlx5e_priv *priv,
@@ -457,22 +457,8 @@ static void mlx5e_ptpsq_unhealthy_work(struct work_struct *work)
 {
 	struct mlx5e_ptpsq *ptpsq =
 		container_of(work, struct mlx5e_ptpsq, report_unhealthy_work);
-	struct mlx5e_txqsq *sq = &ptpsq->txqsq;
-
-	/* Recovering the PTP SQ means re-enabling NAPI, which requires the
-	 * netdev instance lock. However, SQ closing has to wait for this work
-	 * task to finish while also holding the same lock. So either get the
-	 * lock or find that the SQ is no longer enabled and thus this work is
-	 * not relevant anymore.
-	 */
-	while (!netdev_trylock(sq->netdev)) {
-		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
-			return;
-		msleep(20);
-	}

 	mlx5e_reporter_tx_ptpsq_unhealthy(ptpsq);
-	netdev_unlock(sq->netdev);
 }

 static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
@@ -1,6 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2019 Mellanox Technologies.

+#include <net/netdev_lock.h>
+
 #include "health.h"
 #include "params.h"
 #include "txrx.h"
@@ -177,6 +179,16 @@ static int mlx5e_rx_reporter_timeout_recover(void *ctx)
 	rq = ctx;
 	priv = rq->priv;

+	/* Acquire netdev instance lock to synchronize with channel close and
+	 * reopen flows. Either successfully obtain the lock, or detect that
+	 * channels are closing for another reason, making this work no longer
+	 * necessary.
+	 */
+	while (!netdev_trylock(rq->netdev)) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &rq->priv->state))
+			return 0;
+		msleep(20);
+	}
 	mutex_lock(&priv->state_lock);

 	eq = rq->cq.mcq.eq;
@@ -186,6 +198,7 @@ static int mlx5e_rx_reporter_timeout_recover(void *ctx)
 		clear_bit(MLX5E_SQ_STATE_ENABLED, &rq->icosq->state);

 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(rq->netdev);

 	return err;
 }
@@ -1,6 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (c) 2019 Mellanox Technologies. */

+#include <net/netdev_lock.h>
+
 #include "health.h"
 #include "en/ptp.h"
 #include "en/devlink.h"
@@ -79,6 +81,18 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state))
 		return 0;

+	/* Recovering queues means re-enabling NAPI, which requires the netdev
+	 * instance lock. However, SQ closing flows have to wait for work tasks
+	 * to finish while also holding the netdev instance lock. So either get
+	 * the lock or find that the SQ is no longer enabled and thus this work
+	 * is not relevant anymore.
+	 */
+	while (!netdev_trylock(dev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state))
+			return 0;
+		msleep(20);
+	}
+
 	err = mlx5_core_query_sq_state(mdev, sq->sqn, &state);
 	if (err) {
 		netdev_err(dev, "Failed to query SQ 0x%x state. err = %d\n",
@@ -114,9 +128,11 @@ static int mlx5e_tx_reporter_err_cqe_recover(void *ctx)
 	else
 		mlx5e_trigger_napi_sched(sq->cq.napi);

+	netdev_unlock(dev);
 	return 0;
 out:
 	clear_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state);
+	netdev_unlock(dev);
 	return err;
 }

@@ -137,10 +153,24 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 	sq = to_ctx->sq;
 	eq = sq->cq.mcq.eq;
 	priv = sq->priv;
+
+	/* Recovering the TX queues implies re-enabling NAPI, which requires
+	 * the netdev instance lock.
+	 * However, channel closing flows have to wait for this work to finish
+	 * while holding the same lock. So either get the lock or find that
+	 * channels are being closed for other reason and this work is not
+	 * relevant anymore.
+	 */
+	while (!netdev_trylock(sq->netdev)) {
+		if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state))
+			return 0;
+		msleep(20);
+	}
+
 	err = mlx5e_health_channel_eq_recover(sq->netdev, eq, sq->cq.ch_stats);
 	if (!err) {
 		to_ctx->status = 0; /* this sq recovered */
-		return err;
+		goto out;
 	}

 	mutex_lock(&priv->state_lock);
@@ -148,7 +178,7 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 	mutex_unlock(&priv->state_lock);
 	if (!err) {
 		to_ctx->status = 1; /* all channels recovered */
-		return err;
+		goto out;
 	}

 	to_ctx->status = err;
@@ -156,7 +186,8 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
 	netdev_err(priv->netdev,
 		   "mlx5e_safe_reopen_channels failed recovering from a tx_timeout, err(%d).\n",
 		   err);
-
+out:
+	netdev_unlock(sq->netdev);
 	return err;
 }

@@ -173,10 +204,22 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 		return 0;

 	priv = ptpsq->txqsq.priv;
+	netdev = priv->netdev;
+
+	/* Recovering the PTP SQ means re-enabling NAPI, which requires the
+	 * netdev instance lock. However, SQ closing has to wait for this work
+	 * task to finish while also holding the same lock. So either get the
+	 * lock or find that the SQ is no longer enabled and thus this work is
+	 * not relevant anymore.
+	 */
+	while (!netdev_trylock(netdev)) {
+		if (!test_bit(MLX5E_SQ_STATE_ENABLED, &ptpsq->txqsq.state))
+			return 0;
+		msleep(20);
+	}

 	mutex_lock(&priv->state_lock);
 	chs = &priv->channels;
-	netdev = priv->netdev;

 	carrier_ok = netif_carrier_ok(netdev);
 	netif_carrier_off(netdev);
@@ -193,6 +236,7 @@ static int mlx5e_tx_reporter_ptpsq_unhealthy_recover(void *ctx)
 		netif_carrier_on(netdev);

 	mutex_unlock(&priv->state_lock);
+	netdev_unlock(netdev);

 	return err;
 }
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved.

+#include <linux/iopoll.h>
 #include <linux/math64.h>
 #include "lib/aso.h"
 #include "en/tc/post_act.h"
@@ -115,7 +116,6 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev,
 	struct mlx5e_flow_meters *flow_meters;
 	u8 cir_man, cir_exp, cbs_man, cbs_exp;
 	struct mlx5_aso_wqe *aso_wqe;
-	unsigned long expires;
 	struct mlx5_aso *aso;
 	u64 rate, burst;
 	u8 ds_cnt;
@@ -187,12 +187,8 @@ mlx5e_tc_meter_modify(struct mlx5_core_dev *mdev,
 	mlx5_aso_post_wqe(aso, true, &aso_wqe->ctrl);

 	/* With newer FW, the wait for the first ASO WQE is more than 2us, put the wait 10ms. */
-	expires = jiffies + msecs_to_jiffies(10);
-	do {
-		err = mlx5_aso_poll_cq(aso, true);
-		if (err)
-			usleep_range(2, 10);
-	} while (err && time_is_after_jiffies(expires));
+	read_poll_timeout(mlx5_aso_poll_cq, err, !err, 10, 10 * USEC_PER_MSEC,
+			  false, aso, true);
 	mutex_unlock(&flow_meters->aso_lock);

 	return err;
@@ -127,7 +127,7 @@ static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv,
 		goto err_remove_pool;

 	mlx5e_activate_xsk(c);
-	mlx5e_trigger_napi_icosq(c);
+	mlx5e_trigger_napi_async_icosq(c);

 	/* Don't wait for WQEs, because the newer xdpsock sample doesn't provide
 	 * any Fill Ring entries at the setup stage.
@@ -179,7 +179,7 @@ static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix)
 	c = priv->channels.c[ix];

 	mlx5e_activate_rq(&c->rq);
-	mlx5e_trigger_napi_icosq(c);
+	mlx5e_trigger_napi_async_icosq(c);
 	mlx5e_wait_for_min_rx_wqes(&c->rq, MLX5E_RQ_WQES_TIMEOUT);

 	mlx5e_rx_res_xsk_update(priv->rx_res, &priv->channels, ix, false);
@@ -34,7 +34,7 @@ int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags)
 				     &c->async_icosq->state))
 			return 0;

-		mlx5e_trigger_napi_icosq(c);
+		mlx5e_trigger_napi_async_icosq(c);
 	}

 	return 0;
--- a/Show More
+++ b/Show More