diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-19 21:39:08 +0300 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-02-19 21:39:08 +0300 |
| commit | 8bf22c33e7a172fbc72464f4cc484d23a6b412ba (patch) | |
| tree | 7034d84f09ee8c239574adec764ddae7594775f0 /drivers | |
| parent | 4f13d0dabc87fb585b96d90cc4b29f67a2995405 (diff) | |
| parent | 571dcbeb8e635182bb825ae758399831805693c2 (diff) | |
| download | linux-8bf22c33e7a172fbc72464f4cc484d23a6b412ba.tar.xz | |
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
...
Diffstat (limited to 'drivers')
43 files changed, 432 insertions, 239 deletions
diff --git a/drivers/atm/fore200e.c b/drivers/atm/fore200e.c index f62e38571440..fec081db36dc 100644 --- a/drivers/atm/fore200e.c +++ b/drivers/atm/fore200e.c @@ -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: diff --git a/drivers/dpll/zl3073x/ref.h b/drivers/dpll/zl3073x/ref.h index efc7f59cd9f9..0d8618f5ce8d 100644 --- a/drivers/dpll/zl3073x/ref.h +++ b/drivers/dpll/zl3073x/ref.h @@ -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; } diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 7e9becad91df..17108c359216 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -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. diff --git a/drivers/net/arcnet/com20020-pci.c b/drivers/net/arcnet/com20020-pci.c index 19e411b2e3a7..dbadda08dce2 100644 --- a/drivers/net/arcnet/com20020-pci.c +++ b/drivers/net/arcnet/com20020-pci.c @@ -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, diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 78cff904cdc3..55a960da42b5 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -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) diff --git a/drivers/net/dsa/mxl862xx/Kconfig b/drivers/net/dsa/mxl862xx/Kconfig index 4db7bab21a71..3e772298cc89 100644 --- a/drivers/net/dsa/mxl862xx/Kconfig +++ b/drivers/net/dsa/mxl862xx/Kconfig @@ -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. diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c index 84c90a957719..91a4ef9e3150 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c @@ -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); diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c index 6ab317f1c16e..b8e258842c61 100644 --- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c +++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.c @@ -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> diff --git a/drivers/net/ethernet/ec_bhf.c b/drivers/net/ethernet/ec_bhf.c index 67275aa4f65b..0c86cbb0313c 100644 --- a/drivers/net/ethernet/ec_bhf.c +++ b/drivers/net/ethernet/ec_bhf.c @@ -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; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index d3bc3207054f..02de186dcc8f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -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}, diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index c7c70429eb6c..8658cb2143df 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -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, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index a7de3a3efc49..ea2cd1f5d1d0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -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, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 424f8a2728a3..74660e7fe674 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -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, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index 0686fbdd5a05..6efb626b5506 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -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; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index 4adc1adf9897..60ba840e00fa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -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; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c index 7819fb297280..d5d9146efca6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c @@ -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; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c index db776e515b6a..5c5360a25c64 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/pool.c @@ -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); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 9e33156fac8a..8aeab4b21035 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -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; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c index 528b04d4de41..90b3bc5f9166 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/macsec.c @@ -5,6 +5,7 @@ #include <linux/mlx5/mlx5_ifc.h> #include <linux/xarray.h> #include <linux/if_vlan.h> +#include <linux/iopoll.h> #include "en.h" #include "lib/aso.h" @@ -1385,7 +1386,8 @@ static int macsec_aso_set_arm_event(struct mlx5_core_dev *mdev, struct mlx5e_mac MLX5_ACCESS_ASO_OPC_MOD_MACSEC); macsec_aso_build_ctrl(aso, &aso_wqe->aso_ctrl, in); mlx5_aso_post_wqe(maso, false, &aso_wqe->ctrl); - err = mlx5_aso_poll_cq(maso, false); + read_poll_timeout(mlx5_aso_poll_cq, err, !err, 10, 10 * USEC_PER_MSEC, + false, maso, false); mutex_unlock(&aso->aso_lock); return err; @@ -1397,7 +1399,6 @@ static int macsec_aso_query(struct mlx5_core_dev *mdev, struct mlx5e_macsec *mac struct mlx5e_macsec_aso *aso; struct mlx5_aso_wqe *aso_wqe; struct mlx5_aso *maso; - unsigned long expires; int err; aso = &macsec->aso; @@ -1411,12 +1412,8 @@ static int macsec_aso_query(struct mlx5_core_dev *mdev, struct mlx5e_macsec *mac macsec_aso_build_wqe_ctrl_seg(aso, &aso_wqe->aso_ctrl, NULL); mlx5_aso_post_wqe(maso, false, &aso_wqe->ctrl); - expires = jiffies + msecs_to_jiffies(10); - do { - err = mlx5_aso_poll_cq(maso, false); - 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, maso, false); if (err) goto err_out; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 4b8084420816..7eb691c2a1bd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -631,19 +631,7 @@ static void mlx5e_rq_timeout_work(struct work_struct *timeout_work) struct mlx5e_rq, rx_timeout_work); - /* 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; - msleep(20); - } - mlx5e_reporter_rx_timeout(rq); - netdev_unlock(rq->netdev); } static int mlx5e_alloc_mpwqe_rq_drop_page(struct mlx5e_rq *rq) @@ -1952,20 +1940,7 @@ void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, recover_work); - /* 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(sq->netdev)) { - if (!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)) - return; - msleep(20); - } - mlx5e_reporter_tx_err_cqe(sq); - netdev_unlock(sq->netdev); } static struct dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) @@ -2744,16 +2719,26 @@ static int mlx5e_channel_stats_alloc(struct mlx5e_priv *priv, int ix, int cpu) void mlx5e_trigger_napi_icosq(struct mlx5e_channel *c) { + struct mlx5e_icosq *sq = &c->icosq; bool locked; - if (!test_and_set_bit(MLX5E_SQ_STATE_LOCK_NEEDED, &c->icosq.state)) - synchronize_net(); + set_bit(MLX5E_SQ_STATE_LOCK_NEEDED, &sq->state); + synchronize_net(); + + locked = mlx5e_icosq_sync_lock(sq); + mlx5e_trigger_irq(sq); + mlx5e_icosq_sync_unlock(sq, locked); - locked = mlx5e_icosq_sync_lock(&c->icosq); - mlx5e_trigger_irq(&c->icosq); - mlx5e_icosq_sync_unlock(&c->icosq, locked); + clear_bit(MLX5E_SQ_STATE_LOCK_NEEDED, &sq->state); +} + +void mlx5e_trigger_napi_async_icosq(struct mlx5e_channel *c) +{ + struct mlx5e_icosq *sq = c->async_icosq; - clear_bit(MLX5E_SQ_STATE_LOCK_NEEDED, &c->icosq.state); + spin_lock_bh(&sq->lock); + mlx5e_trigger_irq(sq); + spin_unlock_bh(&sq->lock); } void mlx5e_trigger_napi_sched(struct napi_struct *napi) @@ -2836,7 +2821,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix); netif_napi_set_irq_locked(&c->napi, irq); - async_icosq_needed = !!xsk_pool || priv->ktls_rx_was_enabled; + async_icosq_needed = !!params->xdp_prog || priv->ktls_rx_was_enabled; err = mlx5e_open_queues(c, params, cparam, async_icosq_needed); if (unlikely(err)) goto err_napi_del; @@ -5105,19 +5090,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) struct net_device *netdev = priv->netdev; int i; - /* 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(netdev)) { - if (!test_bit(MLX5E_STATE_CHANNELS_ACTIVE, &priv->state)) - return; - msleep(20); - } - for (i = 0; i < netdev->real_num_tx_queues; i++) { struct netdev_queue *dev_queue = netdev_get_tx_queue(netdev, i); @@ -5130,8 +5102,6 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) /* break if tried to reopened channels */ break; } - - netdev_unlock(netdev); } static void mlx5e_tx_timeout(struct net_device *dev, unsigned int txqueue) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wc.c b/drivers/net/ethernet/mellanox/mlx5/core/wc.c index 815a7c97d6b0..04d03be1bb77 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wc.c @@ -2,6 +2,7 @@ // Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved. #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/mlx5/transobj.h> #include "lib/clock.h" #include "mlx5_core.h" @@ -15,7 +16,7 @@ #define TEST_WC_NUM_WQES 255 #define TEST_WC_LOG_CQ_SZ (order_base_2(TEST_WC_NUM_WQES)) #define TEST_WC_SQ_LOG_WQ_SZ TEST_WC_LOG_CQ_SZ -#define TEST_WC_POLLING_MAX_TIME_JIFFIES msecs_to_jiffies(100) +#define TEST_WC_POLLING_MAX_TIME_USEC (100 * USEC_PER_MSEC) struct mlx5_wc_cq { /* data path - accessed per cqe */ @@ -359,7 +360,6 @@ static int mlx5_wc_poll_cq(struct mlx5_wc_sq *sq) static void mlx5_core_test_wc(struct mlx5_core_dev *mdev) { unsigned int offset = 0; - unsigned long expires; struct mlx5_wc_sq *sq; int i, err; @@ -389,13 +389,9 @@ static void mlx5_core_test_wc(struct mlx5_core_dev *mdev) mlx5_wc_post_nop(sq, &offset, true); - expires = jiffies + TEST_WC_POLLING_MAX_TIME_JIFFIES; - do { - err = mlx5_wc_poll_cq(sq); - if (err) - usleep_range(2, 10); - } while (mdev->wc_state == MLX5_WC_STATE_UNINITIALIZED && - time_is_after_jiffies(expires)); + poll_timeout_us(mlx5_wc_poll_cq(sq), + mdev->wc_state != MLX5_WC_STATE_UNINITIALIZED, 10, + TEST_WC_POLLING_MAX_TIME_USEC, false); mlx5_wc_destroy_sq(sq); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c index 11745a2d8a44..401c2196b9ff 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c @@ -1145,6 +1145,9 @@ ipv6_flow: return -EINVAL; } + dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, + FBNIC_RCD_HDR_AL_DMA_HINT_L4); + /* Write action table values */ act_tcam->dest = dest; act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c index 85a883dba385..d8a9a7d7c237 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw_log.c @@ -51,8 +51,6 @@ int fbnic_fw_log_init(struct fbnic_dev *fbd) log->data_start = data; log->data_end = data + FBNIC_FW_LOG_SIZE; - fbnic_fw_log_enable(fbd, true); - return 0; } @@ -63,7 +61,6 @@ void fbnic_fw_log_free(struct fbnic_dev *fbd) if (!fbnic_fw_log_ready(fbd)) return; - fbnic_fw_log_disable(fbd); INIT_LIST_HEAD(&log->entries); log->size = 0; vfree(log->data_start); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c index 81c9d5c9a4b2..b4b396ca9bce 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c @@ -262,6 +262,23 @@ static int fbnic_set_mac(struct net_device *netdev, void *p) return 0; } +static int fbnic_change_mtu(struct net_device *dev, int new_mtu) +{ + struct fbnic_net *fbn = netdev_priv(dev); + + if (fbnic_check_split_frames(fbn->xdp_prog, new_mtu, fbn->hds_thresh)) { + dev_err(&dev->dev, + "MTU %d is larger than HDS threshold %d in XDP mode\n", + new_mtu, fbn->hds_thresh); + + return -EINVAL; + } + + WRITE_ONCE(dev->mtu, new_mtu); + + return 0; +} + void fbnic_clear_rx_mode(struct fbnic_dev *fbd) { struct net_device *netdev = fbd->netdev; @@ -533,6 +550,7 @@ static const struct net_device_ops fbnic_netdev_ops = { .ndo_start_xmit = fbnic_xmit_frame, .ndo_features_check = fbnic_features_check, .ndo_set_mac_address = fbnic_set_mac, + .ndo_change_mtu = fbnic_change_mtu, .ndo_set_rx_mode = fbnic_set_rx_mode, .ndo_get_stats64 = fbnic_get_stats64, .ndo_bpf = fbnic_bpf, @@ -787,6 +805,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd) netdev->hw_enc_features |= netdev->features; netdev->features |= NETIF_F_NTUPLE; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_RX_SG; + netdev->min_mtu = IPV6_MIN_MTU; netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN; diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c index 6f9389748a7d..3fa9d1910daa 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c @@ -311,11 +311,17 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto free_irqs; } + err = fbnic_fw_log_init(fbd); + if (err) + dev_warn(fbd->dev, + "Unable to initialize firmware log buffer: %d\n", + err); + err = fbnic_fw_request_mbx(fbd); if (err) { dev_err(&pdev->dev, "Firmware mailbox initialization failure\n"); - goto free_irqs; + goto free_fw_log; } /* Send the request to enable the FW logging to host. Note if this @@ -323,11 +329,7 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) * possible the FW is just too old to support the logging and needs * to be updated. */ - err = fbnic_fw_log_init(fbd); - if (err) - dev_warn(fbd->dev, - "Unable to initialize firmware log buffer: %d\n", - err); + fbnic_fw_log_enable(fbd, true); fbnic_devlink_register(fbd); fbnic_devlink_otp_check(fbd, "error detected during probe"); @@ -374,6 +376,8 @@ init_failure_mode: * firmware updates for fixes. */ return 0; +free_fw_log: + fbnic_fw_log_free(fbd); free_irqs: fbnic_free_irqs(fbd); err_destroy_health: @@ -408,8 +412,9 @@ static void fbnic_remove(struct pci_dev *pdev) fbnic_hwmon_unregister(fbd); fbnic_dbg_fbd_exit(fbd); fbnic_devlink_unregister(fbd); - fbnic_fw_log_free(fbd); + fbnic_fw_log_disable(fbd); fbnic_fw_free_mbx(fbd); + fbnic_fw_log_free(fbd); fbnic_free_irqs(fbd); fbnic_devlink_health_destroy(fbd); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c index 7f31e890031c..42a186db43ea 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c @@ -338,9 +338,8 @@ void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn) else if (tstamp_mask & (1u << flow_type)) dest |= FBNIC_RPC_ACT_TBL0_TS_ENA; - if (act1_value[flow_type] & FBNIC_RPC_TCAM_ACT1_L4_VALID) - dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, - FBNIC_RCD_HDR_AL_DMA_HINT_L4); + dest |= FIELD_PREP(FBNIC_RPC_ACT_TBL0_DMA_HINT, + FBNIC_RCD_HDR_AL_DMA_HINT_L4); rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, flow_type); diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c index e29959241ff3..4aaa928bf8ab 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c @@ -2591,7 +2591,8 @@ write_ctl: } static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, - struct fbnic_ring *rcq, bool tx_pause) + struct fbnic_ring *rcq, bool tx_pause, + bool hdr_split) { struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 drop_mode, rcq_ctl; @@ -2604,22 +2605,26 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv, /* Specify packet layout */ rcq_ctl = FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_DROP_MODE_MASK, drop_mode) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_HROOM_MASK, FBNIC_RX_HROOM) | - FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_TROOM_MASK, FBNIC_RX_TROOM); + FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_MIN_TROOM_MASK, FBNIC_RX_TROOM) | + FIELD_PREP(FBNIC_QUEUE_RDE_CTL0_EN_HDR_SPLIT, hdr_split); fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl); } -void fbnic_config_drop_mode(struct fbnic_net *fbn, bool tx_pause) +void fbnic_config_drop_mode(struct fbnic_net *fbn, bool txp) { + bool hds; int i, t; + hds = fbn->hds_thresh < FBNIC_HDR_BYTES_MIN; + for (i = 0; i < fbn->num_napi; i++) { struct fbnic_napi_vector *nv = fbn->napi[i]; for (t = 0; t < nv->rxt_count; t++) { struct fbnic_q_triad *qt = &nv->qt[nv->txt_count + t]; - fbnic_config_drop_mode_rcq(nv, &qt->cmpl, tx_pause); + fbnic_config_drop_mode_rcq(nv, &qt->cmpl, txp, hds); } } } @@ -2670,20 +2675,18 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv, { struct fbnic_net *fbn = netdev_priv(nv->napi.dev); u32 log_size = fls(rcq->size_mask); - u32 hds_thresh = fbn->hds_thresh; u32 rcq_ctl = 0; - - fbnic_config_drop_mode_rcq(nv, rcq, fbn->tx_pause); + bool hdr_split; + u32 hds_thresh; /* Force lower bound on MAX_HEADER_BYTES. Below this, all frames should * be split at L4. It would also result in the frames being split at * L2/L3 depending on the frame size. */ - if (fbn->hds_thresh < FBNIC_HDR_BYTES_MIN) { - rcq_ctl = FBNIC_QUEUE_RDE_CTL0_EN_HDR_SPLIT; - hds_thresh = FBNIC_HDR_BYTES_MIN; - } + hdr_split = fbn->hds_thresh < FBNIC_HDR_BYTES_MIN; + fbnic_config_drop_mode_rcq(nv, rcq, fbn->tx_pause, hdr_split); + hds_thresh = max(fbn->hds_thresh, FBNIC_HDR_BYTES_MIN); rcq_ctl |= FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_PADLEN_MASK, FBNIC_RX_PAD) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_MAX_HDR_MASK, hds_thresh) | FIELD_PREP(FBNIC_QUEUE_RDE_CTL1_PAYLD_OFF_MASK, diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h index b9560103ab86..980965274079 100644 --- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h +++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h @@ -66,7 +66,7 @@ struct fbnic_net; (4096 - FBNIC_RX_HROOM - FBNIC_RX_TROOM - FBNIC_RX_PAD) #define FBNIC_HDS_THRESH_DEFAULT \ (1536 - FBNIC_RX_PAD) -#define FBNIC_HDR_BYTES_MIN 128 +#define FBNIC_HDR_BYTES_MIN 256 struct fbnic_pkt_buff { struct xdp_buff buff; diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c index 2f168700f63c..8b2e07821a95 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_ptp.c @@ -576,7 +576,7 @@ static int sparx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) static struct ptp_clock_info sparx5_ptp_clock_info = { .owner = THIS_MODULE, .name = "sparx5 ptp", - .max_adj = 200000, + .max_adj = 10000000, .gettime64 = sparx5_ptp_gettime64, .settime64 = sparx5_ptp_settime64, .adjtime = sparx5_ptp_adjtime, diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h index 1231a80335d7..04f76f1e23f6 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_qos.h @@ -35,7 +35,7 @@ #define SPX5_SE_BURST_UNIT 4096 /* Dwrr */ -#define SPX5_DWRR_COST_MAX 63 +#define SPX5_DWRR_COST_MAX 31 struct sparx5_shaper { u32 mode; diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index 469784d3a1a6..1b8269320464 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -551,44 +551,81 @@ static int ocelot_port_stop(struct net_device *dev) return 0; } -static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) +static bool ocelot_xmit_timestamp(struct ocelot *ocelot, int port, + struct sk_buff *skb, u32 *rew_op) { - struct ocelot_port_private *priv = netdev_priv(dev); - struct ocelot_port *ocelot_port = &priv->port; - struct ocelot *ocelot = ocelot_port->ocelot; - int port = priv->port.index; - u32 rew_op = 0; - - if (!static_branch_unlikely(&ocelot_fdma_enabled) && - !ocelot_can_inject(ocelot, 0)) - return NETDEV_TX_BUSY; - - /* Check if timestamping is needed */ if (ocelot->ptp && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { struct sk_buff *clone = NULL; if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) { kfree_skb(skb); - return NETDEV_TX_OK; + return false; } if (clone) OCELOT_SKB_CB(skb)->clone = clone; - rew_op = ocelot_ptp_rew_op(skb); + *rew_op = ocelot_ptp_rew_op(skb); } - if (static_branch_unlikely(&ocelot_fdma_enabled)) { - ocelot_fdma_inject_frame(ocelot, port, rew_op, skb, dev); - } else { - ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + return true; +} + +static netdev_tx_t ocelot_port_xmit_fdma(struct sk_buff *skb, + struct net_device *dev) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->port.index; + u32 rew_op = 0; + + if (!ocelot_xmit_timestamp(ocelot, port, skb, &rew_op)) + return NETDEV_TX_OK; + + ocelot_fdma_inject_frame(ocelot, port, rew_op, skb, dev); + + return NETDEV_TX_OK; +} - consume_skb(skb); +static netdev_tx_t ocelot_port_xmit_inj(struct sk_buff *skb, + struct net_device *dev) +{ + struct ocelot_port_private *priv = netdev_priv(dev); + struct ocelot_port *ocelot_port = &priv->port; + struct ocelot *ocelot = ocelot_port->ocelot; + int port = priv->port.index; + u32 rew_op = 0; + + ocelot_lock_inj_grp(ocelot, 0); + + if (!ocelot_can_inject(ocelot, 0)) { + ocelot_unlock_inj_grp(ocelot, 0); + return NETDEV_TX_BUSY; } + if (!ocelot_xmit_timestamp(ocelot, port, skb, &rew_op)) { + ocelot_unlock_inj_grp(ocelot, 0); + return NETDEV_TX_OK; + } + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + ocelot_unlock_inj_grp(ocelot, 0); + + consume_skb(skb); + return NETDEV_TX_OK; } +static netdev_tx_t ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) +{ + if (static_branch_unlikely(&ocelot_fdma_enabled)) + return ocelot_port_xmit_fdma(skb, dev); + + return ocelot_port_xmit_inj(skb, dev); +} + enum ocelot_action_type { OCELOT_MACT_LEARN, OCELOT_MACT_FORGET, diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 2f0cdbd4e2ac..d9b5d7999370 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -688,9 +688,9 @@ static int myri10ge_get_firmware_capabilities(struct myri10ge_priv *mgp) /* probe for IPv6 TSO support */ mgp->features = NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_TSO; - cmd.data0 = 0, - cmd.data1 = 0, - cmd.data2 = 0, + cmd.data0 = 0; + cmd.data1 = 0; + cmd.data2 = 0; status = myri10ge_send_cmd(mgp, MXGEFW_CMD_GET_MAX_TSO6_HDR_SIZE, &cmd, 0); if (status == 0) { @@ -821,9 +821,9 @@ static int myri10ge_change_pause(struct myri10ge_priv *mgp, int pause) int status, ctl; ctl = pause ? MXGEFW_ENABLE_FLOW_CONTROL : MXGEFW_DISABLE_FLOW_CONTROL; - cmd.data0 = 0, - cmd.data1 = 0, - cmd.data2 = 0, + cmd.data0 = 0; + cmd.data1 = 0; + cmd.data2 = 0; status = myri10ge_send_cmd(mgp, ctl, &cmd, 0); if (status) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index c63099a77cc0..82375d34ad57 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -5040,13 +5040,27 @@ static unsigned int stmmac_rx_buf2_len(struct stmmac_priv *priv, if (!priv->sph_active) return 0; - /* Not last descriptor */ - if (status & rx_not_ls) + /* For GMAC4, when split header is enabled, in some rare cases, the + * hardware does not fill buf2 of the first descriptor with payload. + * Thus we cannot assume buf2 is always fully filled if it is not + * the last descriptor. Otherwise, the length of buf2 of the second + * descriptor will be calculated wrong and cause an oops. + * + * If this is the last descriptor, 'plen' is the length of the + * received packet that was transferred to system memory. + * Otherwise, it is the accumulated number of bytes that have been + * transferred for the current packet. + * + * Thus 'plen - len' always gives the correct length of buf2. + */ + + /* Not GMAC4 and not last descriptor */ + if (priv->plat->core_type != DWMAC_CORE_GMAC4 && (status & rx_not_ls)) return priv->dma_conf.dma_buf_sz; + /* GMAC4 or last descriptor */ plen = stmmac_get_rx_frame_len(priv, p, coe); - /* Last descriptor */ return plen - len; } diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index c509228be84d..4433b8e95b6a 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1572,6 +1572,11 @@ destroy_macvlan_port: if (create) macvlan_port_destroy(port->dev); } + /* @dev might have been made visible before an error was detected. + * Make sure to observe an RCU grace period before our caller + * (rtnl_newlink()) frees it. + */ + synchronize_net(); return err; } EXPORT_SYMBOL_GPL(macvlan_common_newlink); diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c index 3e9e7f8444b3..955c9a37e1f8 100644 --- a/drivers/net/ovpn/io.c +++ b/drivers/net/ovpn/io.c @@ -355,6 +355,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) struct ovpn_priv *ovpn = netdev_priv(dev); struct sk_buff *segments, *curr, *next; struct sk_buff_head skb_list; + unsigned int tx_bytes = 0; struct ovpn_peer *peer; __be16 proto; int ret; @@ -365,7 +366,27 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) /* verify IP header size in network packet */ proto = ovpn_ip_check_protocol(skb); if (unlikely(!proto || skb->protocol != proto)) - goto drop; + goto drop_no_peer; + + /* retrieve peer serving the destination IP of this packet */ + peer = ovpn_peer_get_by_dst(ovpn, skb); + if (unlikely(!peer)) { + switch (skb->protocol) { + case htons(ETH_P_IP): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n", + netdev_name(ovpn->dev), + &ip_hdr(skb)->daddr); + break; + case htons(ETH_P_IPV6): + net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n", + netdev_name(ovpn->dev), + &ipv6_hdr(skb)->daddr); + break; + } + goto drop_no_peer; + } + /* dst was needed for peer selection - it can now be dropped */ + skb_dst_drop(skb); if (skb_is_gso(skb)) { segments = skb_gso_segment(skb, 0); @@ -394,36 +415,28 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev) continue; } + /* only count what we actually send */ + tx_bytes += curr->len; __skb_queue_tail(&skb_list, curr); } - skb_list.prev->next = NULL; - /* retrieve peer serving the destination IP of this packet */ - peer = ovpn_peer_get_by_dst(ovpn, skb); - if (unlikely(!peer)) { - switch (skb->protocol) { - case htons(ETH_P_IP): - net_dbg_ratelimited("%s: no peer to send data to dst=%pI4\n", - netdev_name(ovpn->dev), - &ip_hdr(skb)->daddr); - break; - case htons(ETH_P_IPV6): - net_dbg_ratelimited("%s: no peer to send data to dst=%pI6c\n", - netdev_name(ovpn->dev), - &ipv6_hdr(skb)->daddr); - break; - } - goto drop; + /* no segments survived: don't jump to 'drop' because we already + * incremented the counter for each failure in the loop + */ + if (unlikely(skb_queue_empty(&skb_list))) { + ovpn_peer_put(peer); + return NETDEV_TX_OK; } - /* dst was needed for peer selection - it can now be dropped */ - skb_dst_drop(skb); + skb_list.prev->next = NULL; - ovpn_peer_stats_increment_tx(&peer->vpn_stats, skb->len); + ovpn_peer_stats_increment_tx(&peer->vpn_stats, tx_bytes); ovpn_send(ovpn, skb_list.next, peer); return NETDEV_TX_OK; drop: + ovpn_peer_put(peer); +drop_no_peer: dev_dstats_tx_dropped(ovpn->dev); skb_tx_error(skb); kfree_skb_list(skb); diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c index 9750871ab65c..448cee3b3f9f 100644 --- a/drivers/net/ovpn/socket.c +++ b/drivers/net/ovpn/socket.c @@ -200,6 +200,22 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) ovpn_sock->sk = sk; kref_init(&ovpn_sock->refcount); + /* TCP sockets are per-peer, therefore they are linked to their unique + * peer + */ + if (sk->sk_protocol == IPPROTO_TCP) { + INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work); + ovpn_sock->peer = peer; + ovpn_peer_hold(peer); + } else if (sk->sk_protocol == IPPROTO_UDP) { + /* in UDP we only link the ovpn instance since the socket is + * shared among multiple peers + */ + ovpn_sock->ovpn = peer->ovpn; + netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker, + GFP_KERNEL); + } + /* the newly created ovpn_socket is holding reference to sk, * therefore we increase its refcounter. * @@ -212,29 +228,16 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer) ret = ovpn_socket_attach(ovpn_sock, sock, peer); if (ret < 0) { + if (sk->sk_protocol == IPPROTO_TCP) + ovpn_peer_put(peer); + else if (sk->sk_protocol == IPPROTO_UDP) + netdev_put(peer->ovpn->dev, &ovpn_sock->dev_tracker); + sock_put(sk); kfree(ovpn_sock); ovpn_sock = ERR_PTR(ret); - goto sock_release; - } - - /* TCP sockets are per-peer, therefore they are linked to their unique - * peer - */ - if (sk->sk_protocol == IPPROTO_TCP) { - INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work); - ovpn_sock->peer = peer; - ovpn_peer_hold(peer); - } else if (sk->sk_protocol == IPPROTO_UDP) { - /* in UDP we only link the ovpn instance since the socket is - * shared among multiple peers - */ - ovpn_sock->ovpn = peer->ovpn; - netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker, - GFP_KERNEL); } - rcu_assign_sk_user_data(sk, ovpn_sock); sock_release: release_sock(sk); return ovpn_sock; diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c index 0d7f30360d87..ec2bbc28c196 100644 --- a/drivers/net/ovpn/tcp.c +++ b/drivers/net/ovpn/tcp.c @@ -199,7 +199,19 @@ void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock) sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready; sk->sk_write_space = peer->tcp.sk_cb.sk_write_space; sk->sk_prot = peer->tcp.sk_cb.prot; - sk->sk_socket->ops = peer->tcp.sk_cb.ops; + + /* tcp_close() may race this function and could set + * sk->sk_socket to NULL. It does so by invoking + * sock_orphan(), which holds sk_callback_lock before + * doing the assignment. + * + * For this reason we acquire the same lock to avoid + * sk_socket to disappear under our feet + */ + write_lock_bh(&sk->sk_callback_lock); + if (sk->sk_socket) + sk->sk_socket->ops = peer->tcp.sk_cb.ops; + write_unlock_bh(&sk->sk_callback_lock); rcu_assign_sk_user_data(sk, NULL); } @@ -487,6 +499,7 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, /* make sure no pre-existing encapsulation handler exists */ if (ovpn_sock->sk->sk_user_data) return -EBUSY; + rcu_assign_sk_user_data(ovpn_sock->sk, ovpn_sock); /* only a fully connected socket is expected. Connection should be * handled in userspace @@ -495,13 +508,14 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n", netdev_name(peer->ovpn->dev), ovpn_sock->sk->sk_state); - return -EINVAL; + ret = -EINVAL; + goto err; } ret = strp_init(&peer->tcp.strp, ovpn_sock->sk, &cb); if (ret < 0) { DEBUG_NET_WARN_ON_ONCE(1); - return ret; + goto err; } INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work); @@ -536,6 +550,9 @@ int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock, strp_check_rcv(&peer->tcp.strp); return 0; +err: + rcu_assign_sk_user_data(ovpn_sock->sk, NULL); + return ret; } static void ovpn_tcp_close(struct sock *sk, long timeout) diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c index d6a0f7a0b75d..272b535ecaad 100644 --- a/drivers/net/ovpn/udp.c +++ b/drivers/net/ovpn/udp.c @@ -386,6 +386,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock, struct socket *sock, struct ovpn_priv *ovpn) { struct udp_tunnel_sock_cfg cfg = { + .sk_user_data = ovpn_sock, .encap_type = UDP_ENCAP_OVPNINUDP, .encap_rcv = ovpn_udp_encap_recv, .encap_destroy = ovpn_udp_encap_destroy, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8a3eb1839a3d..9b8eaac63b90 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3499,6 +3499,9 @@ static int of_phy_ports(struct phy_device *phydev) port->parent_type = PHY_PORT_PHY; port->phy = phydev; + + linkmode_copy(port->supported, phydev->supported); + err = phy_add_port(phydev, port); if (err) { phy_port_destroy(port); diff --git a/drivers/net/phy/phy_port.c b/drivers/net/phy/phy_port.c index ec93c8ca051e..63d1bb154dc7 100644 --- a/drivers/net/phy/phy_port.c +++ b/drivers/net/phy/phy_port.c @@ -53,7 +53,7 @@ struct phy_port *phy_of_parse_port(struct device_node *dn) enum ethtool_link_medium medium; struct phy_port *port; const char *med_str; - u32 pairs = 0, mediums = 0; + u32 pairs = 0; int ret; ret = fwnode_property_read_string(fwnode, "media", &med_str); @@ -85,17 +85,12 @@ struct phy_port *phy_of_parse_port(struct device_node *dn) return ERR_PTR(-EINVAL); } - mediums |= BIT(medium); - - if (!mediums) - return ERR_PTR(-EINVAL); - port = phy_port_alloc(); if (!port) return ERR_PTR(-ENOMEM); port->pairs = pairs; - port->mediums = mediums; + port->mediums = BIT(medium); return port; } @@ -113,16 +108,10 @@ EXPORT_SYMBOL_GPL(phy_of_parse_port); */ void phy_port_update_supported(struct phy_port *port) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = { 0 }; + __ETHTOOL_DECLARE_LINK_MODE_MASK(supported) = {0}; unsigned long mode; int i; - for_each_set_bit(i, &port->mediums, __ETHTOOL_LINK_MEDIUM_LAST) { - linkmode_zero(supported); - phy_caps_medium_get_supported(supported, i, port->pairs); - linkmode_or(port->supported, port->supported, supported); - } - /* If there's no pairs specified, we grab the default number of * pairs as the max of the default pairs for each linkmode */ @@ -132,6 +121,22 @@ void phy_port_update_supported(struct phy_port *port) port->pairs = max_t(int, port->pairs, ethtool_linkmode_n_pairs(mode)); + for_each_set_bit(i, &port->mediums, __ETHTOOL_LINK_MEDIUM_LAST) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(med_supported) = {0}; + + phy_caps_medium_get_supported(med_supported, i, port->pairs); + linkmode_or(supported, supported, med_supported); + } + + /* If port->supported is already populated, filter it out with the + * medium/pair support. Otherwise, let's just use this medium-based + * support as the port's supported list. + */ + if (linkmode_empty(port->supported)) + linkmode_copy(port->supported, supported); + else + linkmode_and(port->supported, supported, port->supported); + /* Serdes ports supported through SFP may not have any medium set, * as they will output PHY_INTERFACE_MODE_XXX modes. In that case, derive * the supported list based on these interfaces diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c index 5c7f19cbacf6..96e82f94edcf 100644 --- a/drivers/net/usb/catc.c +++ b/drivers/net/usb/catc.c @@ -59,6 +59,16 @@ static const char driver_name[] = "catc"; #define RX_PKT_SZ 1600 /* Max size of receive packet for F5U011 */ /* + * USB endpoints. + */ + +enum catc_usb_ep { + CATC_USB_EP_CONTROL = 0, + CATC_USB_EP_BULK = 1, + CATC_USB_EP_INT_IN = 2, +}; + +/* * Control requests. */ @@ -765,6 +775,13 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id u8 broadcast[ETH_ALEN]; u8 *macbuf; int pktsz, ret = -ENOMEM; + static const u8 bulk_ep_addr[] = { + CATC_USB_EP_BULK | USB_DIR_OUT, + CATC_USB_EP_BULK | USB_DIR_IN, + 0}; + static const u8 int_ep_addr[] = { + CATC_USB_EP_INT_IN | USB_DIR_IN, + 0}; macbuf = kmalloc(ETH_ALEN, GFP_KERNEL); if (!macbuf) @@ -777,6 +794,14 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id goto fail_mem; } + /* Verify that all required endpoints are present */ + if (!usb_check_bulk_endpoints(intf, bulk_ep_addr) || + !usb_check_int_endpoints(intf, int_ep_addr)) { + dev_err(dev, "Missing or invalid endpoints\n"); + ret = -ENODEV; + goto fail_mem; + } + netdev = alloc_etherdev(sizeof(struct catc)); if (!netdev) goto fail_mem; @@ -821,14 +846,14 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id usb_fill_control_urb(catc->ctrl_urb, usbdev, usb_sndctrlpipe(usbdev, 0), NULL, NULL, 0, catc_ctrl_done, catc); - usb_fill_bulk_urb(catc->tx_urb, usbdev, usb_sndbulkpipe(usbdev, 1), - NULL, 0, catc_tx_done, catc); + usb_fill_bulk_urb(catc->tx_urb, usbdev, usb_sndbulkpipe(usbdev, CATC_USB_EP_BULK), + NULL, 0, catc_tx_done, catc); - usb_fill_bulk_urb(catc->rx_urb, usbdev, usb_rcvbulkpipe(usbdev, 1), - catc->rx_buf, pktsz, catc_rx_done, catc); + usb_fill_bulk_urb(catc->rx_urb, usbdev, usb_rcvbulkpipe(usbdev, CATC_USB_EP_BULK), + catc->rx_buf, pktsz, catc_rx_done, catc); - usb_fill_int_urb(catc->irq_urb, usbdev, usb_rcvintpipe(usbdev, 2), - catc->irq_buf, 2, catc_irq_done, catc, 1); + usb_fill_int_urb(catc->irq_urb, usbdev, usb_rcvintpipe(usbdev, CATC_USB_EP_INT_IN), + catc->irq_buf, 2, catc_irq_done, catc, 1); if (!catc->is_f5u011) { u32 *buf; diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c index 09035a77e775..b0e769da9415 100644 --- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c +++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c @@ -11387,7 +11387,13 @@ static const struct pci_device_id card_ids[] = { {PCI_VENDOR_ID_INTEL, 0x1043, 0x8086, 0x2754, 0, 0, 0}, {PCI_VENDOR_ID_INTEL, 0x1043, 0x8086, 0x2761, 0, 0, 0}, {PCI_VENDOR_ID_INTEL, 0x1043, 0x8086, 0x2762, 0, 0, 0}, - {PCI_VDEVICE(INTEL, 0x104f), 0}, + /* + * This ID conflicts with i40e, 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, 0x104f), + PCI_CLASS_NETWORK_OTHER << 8, 0xffff00, 0}, {PCI_VDEVICE(INTEL, 0x4220), 0}, /* BG */ {PCI_VDEVICE(INTEL, 0x4221), 0}, /* BG */ {PCI_VDEVICE(INTEL, 0x4223), 0}, /* ABG */ diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index a78a25b87240..61b547aab286 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -735,10 +735,11 @@ static void connect(struct backend_info *be) */ requested_num_queues = xenbus_read_unsigned(dev->otherend, "multi-queue-num-queues", 1); - if (requested_num_queues > xenvif_max_queues) { + if (requested_num_queues > xenvif_max_queues || + requested_num_queues == 0) { /* buggy or malicious guest */ xenbus_dev_fatal(dev, -EINVAL, - "guest requested %u queues, exceeding the maximum of %u.", + "guest requested %u queues, but valid range is 1 - %u.", requested_num_queues, xenvif_max_queues); return; } |
