diff options
72 files changed, 546 insertions, 318 deletions
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml index b4dcdae54ffd..cffef09729f1 100644 --- a/Documentation/netlink/specs/netdev.yaml +++ b/Documentation/netlink/specs/netdev.yaml @@ -28,7 +28,7 @@ definitions: - name: hw-offload doc: - This feature informs if netdev supports XDP hw oflloading. + This feature informs if netdev supports XDP hw offloading. - name: rx-sg doc: diff --git a/Documentation/networking/msg_zerocopy.rst b/Documentation/networking/msg_zerocopy.rst index 15920db8d35d..b3ea96af9b49 100644 --- a/Documentation/networking/msg_zerocopy.rst +++ b/Documentation/networking/msg_zerocopy.rst @@ -15,7 +15,7 @@ Opportunity and Caveats Copying large buffers between user process and kernel can be expensive. Linux supports various interfaces that eschew copying, -such as sendpage and splice. The MSG_ZEROCOPY flag extends the +such as sendfile and splice. The MSG_ZEROCOPY flag extends the underlying copy avoidance mechanism to common socket send calls. Copy avoidance is not a free lunch. As implemented, with page pinning, @@ -83,8 +83,8 @@ Pass the new flag. ret = send(fd, buf, sizeof(buf), MSG_ZEROCOPY); A zerocopy failure will return -1 with errno ENOBUFS. This happens if -the socket option was not set, the socket exceeds its optmem limit or -the user exceeds its ulimit on locked pages. +the socket exceeds its optmem limit or the user exceeds their ulimit on +locked pages. Mixing copy avoidance and copying diff --git a/drivers/mfd/ocelot-core.c b/drivers/mfd/ocelot-core.c index b0ff05c1759f..e1772ff00cad 100644 --- a/drivers/mfd/ocelot-core.c +++ b/drivers/mfd/ocelot-core.c @@ -177,7 +177,7 @@ static const struct mfd_cell vsc7512_devs[] = { .num_resources = ARRAY_SIZE(vsc7512_miim1_resources), .resources = vsc7512_miim1_resources, }, { - .name = "ocelot-switch", + .name = "ocelot-ext-switch", .of_compatible = "mscc,vsc7512-switch", .num_resources = ARRAY_SIZE(vsc7512_switch_resources), .resources = vsc7512_switch_resources, diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 354aa3dbfde7..dddb28984bdf 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -554,7 +554,7 @@ static const char * const vsc9959_resource_names[TARGET_MAX] = { * SGMII/QSGMII MAC PCS can be found. */ static const struct resource vsc9959_imdio_res = - DEFINE_RES_MEM_NAMED(0x8030, 0x8040, "imdio"); + DEFINE_RES_MEM_NAMED(0x8030, 0x10, "imdio"); static const struct reg_field vsc9959_regfields[REGFIELD_MAX] = { [ANA_ADVLEARN_VLAN_CHK] = REG_FIELD(ANA_ADVLEARN, 6, 6), diff --git a/drivers/net/dsa/ocelot/ocelot_ext.c b/drivers/net/dsa/ocelot/ocelot_ext.c index 14efa6387bd7..063150659816 100644 --- a/drivers/net/dsa/ocelot/ocelot_ext.c +++ b/drivers/net/dsa/ocelot/ocelot_ext.c @@ -4,7 +4,6 @@ */ #include <linux/mfd/ocelot.h> -#include <linux/phylink.h> #include <linux/platform_device.h> #include <linux/regmap.h> #include <soc/mscc/ocelot.h> @@ -149,7 +148,7 @@ MODULE_DEVICE_TABLE(of, ocelot_ext_switch_of_match); static struct platform_driver ocelot_ext_switch_driver = { .driver = { - .name = "ocelot-switch", + .name = "ocelot-ext-switch", .of_match_table = of_match_ptr(ocelot_ext_switch_of_match), }, .probe = ocelot_ext_probe, diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index 287b64b788db..563ad338da25 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -893,8 +893,8 @@ static int vsc9953_mdio_bus_alloc(struct ocelot *ocelot) rc = mscc_miim_setup(dev, &bus, "VSC9953 internal MDIO bus", ocelot->targets[GCB], - ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK]); - + ocelot->map[GCB][GCB_MIIM_MII_STATUS & REG_MASK], + true); if (rc) { dev_err(dev, "failed to setup MDIO bus\n"); return rc; diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 146ca1d8031b..c63d3ec9d328 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -296,10 +296,10 @@ static void ibmvnic_set_affinity(struct ibmvnic_adapter *adapter) rc = __netif_set_xps_queue(adapter->netdev, cpumask_bits(queue->affinity_mask), - i, XPS_CPUS); + i_txqs - 1, XPS_CPUS); if (rc) netdev_warn(adapter->netdev, "%s: Set XPS on queue %d failed, rc = %d.\n", - __func__, i, rc); + __func__, i_txqs - 1, rc); } out: diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index a3c84bf05e44..c18c3b373846 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -296,6 +296,7 @@ config ICE default n depends on PCI_MSI depends on PTP_1588_CLOCK_OPTIONAL + depends on GNSS || GNSS = n select AUXILIARY_BUS select DIMLIB select NET_DEVLINK @@ -337,9 +338,6 @@ config ICE_HWTS the PTP clock driver precise cross-timestamp ioctl (PTP_SYS_OFFSET_PRECISE). -config ICE_GNSS - def_bool GNSS = y || GNSS = ICE - config FM10K tristate "Intel(R) FM10000 Ethernet Switch Host Interface Support" default n diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index f269952d207d..5d89392f969b 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -47,4 +47,4 @@ ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o ice-$(CONFIG_RFS_ACCEL) += ice_arfs.o ice-$(CONFIG_XDP_SOCKETS) += ice_xsk.o ice-$(CONFIG_ICE_SWITCHDEV) += ice_eswitch.o -ice-$(CONFIG_ICE_GNSS) += ice_gnss.o +ice-$(CONFIG_GNSS) += ice_gnss.o diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 31db0701d13f..4d49e5b0b4b8 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -45,7 +45,7 @@ struct gnss_serial { struct list_head queue; }; -#if IS_ENABLED(CONFIG_ICE_GNSS) +#if IS_ENABLED(CONFIG_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); bool ice_gnss_is_gps_present(struct ice_hw *hw); @@ -56,5 +56,5 @@ static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) { return false; } -#endif /* IS_ENABLED(CONFIG_ICE_GNSS) */ +#endif /* IS_ENABLED(CONFIG_GNSS) */ #endif /* _ICE_GNSS_H_ */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c index 684cb8ec9f21..10e11262d48a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_flows.c @@ -793,7 +793,7 @@ static int otx2_prepare_ipv6_flow(struct ethtool_rx_flow_spec *fsp, /* NPC profile doesn't extract AH/ESP header fields */ if ((ah_esp_mask->spi & ah_esp_hdr->spi) || - (ah_esp_mask->tclass & ah_esp_mask->tclass)) + (ah_esp_mask->tclass & ah_esp_hdr->tclass)) return -EOPNOTSUPP; if (flow_type == AH_V6_FLOW) diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c index ef10aef3cda0..7045fedfd73a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c @@ -10,6 +10,7 @@ #include <net/tso.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <net/ip6_checksum.h> #include "otx2_reg.h" #include "otx2_common.h" @@ -699,7 +700,7 @@ static void otx2_sqe_add_ext(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, static void otx2_sqe_add_mem(struct otx2_snd_queue *sq, int *offset, int alg, u64 iova, int ptp_offset, - u64 base_ns, int udp_csum) + u64 base_ns, bool udp_csum_crt) { struct nix_sqe_mem_s *mem; @@ -711,7 +712,7 @@ static void otx2_sqe_add_mem(struct otx2_snd_queue *sq, int *offset, if (ptp_offset) { mem->start_offset = ptp_offset; - mem->udp_csum_crt = udp_csum; + mem->udp_csum_crt = !!udp_csum_crt; mem->base_ns = base_ns; mem->step_type = 1; } @@ -986,10 +987,11 @@ static bool otx2_validate_network_transport(struct sk_buff *skb) return false; } -static bool otx2_ptp_is_sync(struct sk_buff *skb, int *offset, int *udp_csum) +static bool otx2_ptp_is_sync(struct sk_buff *skb, int *offset, bool *udp_csum_crt) { struct ethhdr *eth = (struct ethhdr *)(skb->data); u16 nix_offload_hlen = 0, inner_vhlen = 0; + bool udp_hdr_present = false, is_sync; u8 *data = skb->data, *msgtype; __be16 proto = eth->h_proto; int network_depth = 0; @@ -1029,45 +1031,81 @@ static bool otx2_ptp_is_sync(struct sk_buff *skb, int *offset, int *udp_csum) if (!otx2_validate_network_transport(skb)) return false; - *udp_csum = 1; *offset = nix_offload_hlen + skb_transport_offset(skb) + sizeof(struct udphdr); + udp_hdr_present = true; + } msgtype = data + *offset; - /* Check PTP messageId is SYNC or not */ - return (*msgtype & 0xf) == 0; + is_sync = !(*msgtype & 0xf); + if (is_sync) + *udp_csum_crt = udp_hdr_present; + else + *offset = 0; + + return is_sync; } static void otx2_set_txtstamp(struct otx2_nic *pfvf, struct sk_buff *skb, struct otx2_snd_queue *sq, int *offset) { + struct ethhdr *eth = (struct ethhdr *)(skb->data); struct ptpv2_tstamp *origin_tstamp; - int ptp_offset = 0, udp_csum = 0; + bool udp_csum_crt = false; + unsigned int udphoff; struct timespec64 ts; + int ptp_offset = 0; + __wsum skb_csum; u64 iova; if (unlikely(!skb_shinfo(skb)->gso_size && (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))) { - if (unlikely(pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC)) { - if (otx2_ptp_is_sync(skb, &ptp_offset, &udp_csum)) { - origin_tstamp = (struct ptpv2_tstamp *) - ((u8 *)skb->data + ptp_offset + - PTP_SYNC_SEC_OFFSET); - ts = ns_to_timespec64(pfvf->ptp->tstamp); - origin_tstamp->seconds_msb = htons((ts.tv_sec >> 32) & 0xffff); - origin_tstamp->seconds_lsb = htonl(ts.tv_sec & 0xffffffff); - origin_tstamp->nanoseconds = htonl(ts.tv_nsec); - /* Point to correction field in PTP packet */ - ptp_offset += 8; + if (unlikely(pfvf->flags & OTX2_FLAG_PTP_ONESTEP_SYNC && + otx2_ptp_is_sync(skb, &ptp_offset, &udp_csum_crt))) { + origin_tstamp = (struct ptpv2_tstamp *) + ((u8 *)skb->data + ptp_offset + + PTP_SYNC_SEC_OFFSET); + ts = ns_to_timespec64(pfvf->ptp->tstamp); + origin_tstamp->seconds_msb = htons((ts.tv_sec >> 32) & 0xffff); + origin_tstamp->seconds_lsb = htonl(ts.tv_sec & 0xffffffff); + origin_tstamp->nanoseconds = htonl(ts.tv_nsec); + /* Point to correction field in PTP packet */ + ptp_offset += 8; + + /* When user disables hw checksum, stack calculates the csum, + * but it does not cover ptp timestamp which is added later. + * Recalculate the checksum manually considering the timestamp. + */ + if (udp_csum_crt) { + struct udphdr *uh = udp_hdr(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL && uh->check != 0) { + udphoff = skb_transport_offset(skb); + uh->check = 0; + skb_csum = skb_checksum(skb, udphoff, skb->len - udphoff, + 0); + if (ntohs(eth->h_proto) == ETH_P_IPV6) + uh->check = csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + skb->len - udphoff, + ipv6_hdr(skb)->nexthdr, + skb_csum); + else + uh->check = csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + skb->len - udphoff, + IPPROTO_UDP, + skb_csum); + } } } else { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; } iova = sq->timestamps->iova + (sq->head * sizeof(u64)); otx2_sqe_add_mem(sq, offset, NIX_SENDMEMALG_E_SETTSTMP, iova, - ptp_offset, pfvf->ptp->base_ns, udp_csum); + ptp_offset, pfvf->ptp->base_ns, udp_csum_crt); } else { skb_tx_timestamp(skb); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c index 9a3878f9e582..7c9c4e40c019 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ecpf.c @@ -98,4 +98,8 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev) err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_HOST_PF]); if (err) mlx5_core_warn(dev, "Timeout reclaiming external host PF pages err(%d)\n", err); + + err = mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF]); + if (err) + mlx5_core_warn(dev, "Timeout reclaiming external host VFs pages err(%d)\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c index 9a1bc93b7dc6..eb5aeba3addf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c @@ -86,7 +86,19 @@ static bool mlx5e_ptp_ts_cqe_drop(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb return (ptpsq->ts_cqe_ctr_mask && (skb_cc != skb_id)); } -static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, u16 skb_id) +static bool mlx5e_ptp_ts_cqe_ooo(struct mlx5e_ptpsq *ptpsq, u16 skb_id) +{ + u16 skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); + u16 skb_pc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_pc); + + if (PTP_WQE_CTR2IDX(skb_id - skb_cc) >= PTP_WQE_CTR2IDX(skb_pc - skb_cc)) + return true; + + return false; +} + +static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_cc, + u16 skb_id, int budget) { struct skb_shared_hwtstamps hwts = {}; struct sk_buff *skb; @@ -98,6 +110,7 @@ static void mlx5e_ptp_skb_fifo_ts_cqe_resync(struct mlx5e_ptpsq *ptpsq, u16 skb_ hwts.hwtstamp = mlx5e_skb_cb_get_hwts(skb)->cqe_hwtstamp; skb_tstamp_tx(skb, &hwts); ptpsq->cq_stats->resync_cqe++; + napi_consume_skb(skb, budget); skb_cc = PTP_WQE_CTR2IDX(ptpsq->skb_fifo_cc); } } @@ -118,8 +131,14 @@ static void mlx5e_ptp_handle_ts_cqe(struct mlx5e_ptpsq *ptpsq, goto out; } - if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) - mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id); + if (mlx5e_ptp_ts_cqe_drop(ptpsq, skb_cc, skb_id)) { + if (mlx5e_ptp_ts_cqe_ooo(ptpsq, skb_id)) { + /* already handled by a previous resync */ + ptpsq->cq_stats->ooo_cqe_drop++; + return; + } + mlx5e_ptp_skb_fifo_ts_cqe_resync(ptpsq, skb_cc, skb_id, budget); + } skb = mlx5e_skb_fifo_pop(&ptpsq->skb_fifo); hwtstamp = mlx5e_cqe_ts_to_ns(sq->ptp_cyc2time, sq->clock, get_cqe_ts(cqe)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c index e24b46953542..8f7452dc00ee 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c @@ -710,8 +710,7 @@ forward: else napi_gro_receive(rq->cq.napi, skb); - if (tc_priv.fwd_dev) - dev_put(tc_priv.fwd_dev); + dev_put(tc_priv.fwd_dev); return; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c index f71766dca660..626cb7470fa5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act_stats.c @@ -37,7 +37,7 @@ mlx5e_tc_act_stats_create(void) int err; handle = kvzalloc(sizeof(*handle), GFP_KERNEL); - if (IS_ERR(handle)) + if (!handle) return ERR_PTR(-ENOMEM); err = rhashtable_init(&handle->ht, &act_counters_ht_params); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index c067d2efab51..b9c2f67d3794 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -86,7 +86,7 @@ void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); static inline bool mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo) { - return (*fifo->pc - *fifo->cc) < fifo->mask; + return (u16)(*fifo->pc - *fifo->cc) < fifo->mask; } static inline bool @@ -302,6 +302,8 @@ void mlx5e_skb_fifo_push(struct mlx5e_skb_fifo *fifo, struct sk_buff *skb) static inline struct sk_buff *mlx5e_skb_fifo_pop(struct mlx5e_skb_fifo *fifo) { + WARN_ON_ONCE(*fifo->pc == *fifo->cc); + return *mlx5e_skb_fifo_get(fifo, (*fifo->cc)++); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 6687b8136e44..4478223c1720 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -2138,6 +2138,7 @@ static const struct counter_desc ptp_cq_stats_desc[] = { { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, abort_abs_diff_ns) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_cqe) }, { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, resync_event) }, + { MLX5E_DECLARE_PTP_CQ_STAT(struct mlx5e_ptp_cq_stats, ooo_cqe_drop) }, }; static const struct counter_desc ptp_rq_stats_desc[] = { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 375752d6546d..b77100b60b50 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -461,6 +461,7 @@ struct mlx5e_ptp_cq_stats { u64 abort_abs_diff_ns; u64 resync_cqe; u64 resync_event; + u64 ooo_cqe_drop; }; struct mlx5e_rep_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index e34d9b5fb504..70b8d2dfa751 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -1048,61 +1048,6 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, return 0; } -static int debugfs_hairpin_queues_set(void *data, u64 val) -{ - struct mlx5e_hairpin_params *hp = data; - - if (!val) { - mlx5_core_err(hp->mdev, - "Number of hairpin queues must be > 0\n"); - return -EINVAL; - } - - hp->num_queues = val; - - return 0; -} - -static int debugfs_hairpin_queues_get(void *data, u64 *val) -{ - struct mlx5e_hairpin_params *hp = data; - - *val = hp->num_queues; - - return 0; -} -DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queues, debugfs_hairpin_queues_get, - debugfs_hairpin_queues_set, "%llu\n"); - -static int debugfs_hairpin_queue_size_set(void *data, u64 val) -{ - struct mlx5e_hairpin_params *hp = data; - - if (val > BIT(MLX5_CAP_GEN(hp->mdev, log_max_hairpin_num_packets))) { - mlx5_core_err(hp->mdev, - "Invalid hairpin queue size, must be <= %lu\n", - BIT(MLX5_CAP_GEN(hp->mdev, - log_max_hairpin_num_packets))); - return -EINVAL; - } - - hp->queue_size = roundup_pow_of_two(val); - - return 0; -} - -static int debugfs_hairpin_queue_size_get(void *data, u64 *val) -{ - struct mlx5e_hairpin_params *hp = data; - - *val = hp->queue_size; - - return 0; -} -DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queue_size, - debugfs_hairpin_queue_size_get, - debugfs_hairpin_queue_size_set, "%llu\n"); - static int debugfs_hairpin_num_active_get(void *data, u64 *val) { struct mlx5e_tc_table *tc = data; @@ -1148,10 +1093,6 @@ static void mlx5e_tc_debugfs_init(struct mlx5e_tc_table *tc, tc->dfs_root = debugfs_create_dir("tc", dfs_root); - debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root, - &tc->hairpin_params, &fops_hairpin_queues); - debugfs_create_file("hairpin_queue_size", 0644, tc->dfs_root, - &tc->hairpin_params, &fops_hairpin_queue_size); debugfs_create_file("hairpin_num_active", 0444, tc->dfs_root, tc, &fops_hairpin_num_active); debugfs_create_file("hairpin_table_dump", 0444, tc->dfs_root, tc, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 2a98375a0abf..d766a64b1823 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -869,7 +869,8 @@ mlx5_eswitch_add_send_to_vport_rule(struct mlx5_eswitch *on_esw, dest.vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; - if (rep->vport == MLX5_VPORT_UPLINK) + if (MLX5_CAP_ESW_FLOWTABLE(on_esw->dev, flow_source) && + rep->vport == MLX5_VPORT_UPLINK) spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_LOCAL_VPORT; flow_rule = mlx5_add_flow_rules(mlx5_eswitch_get_slow_fdb(on_esw), diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c index 23361a9ae4fa..6dc83e871cd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/geneve.c @@ -105,6 +105,7 @@ int mlx5_geneve_tlv_option_add(struct mlx5_geneve *geneve, struct geneve_opt *op geneve->opt_type = opt->type; geneve->obj_id = res; geneve->refcount++; + res = 0; } unlock: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c index 2c53589b765d..6e3f178d6f84 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c @@ -162,7 +162,7 @@ int mlx5_ipsec_fs_roce_tx_create(struct mlx5_core_dev *mdev, if (IS_ERR(ft)) { err = PTR_ERR(ft); mlx5_core_err(mdev, "Fail to create RoCE IPsec tx ft err=%d\n", err); - return err; + goto free_in; } roce->ft = ft; @@ -174,22 +174,25 @@ int mlx5_ipsec_fs_roce_tx_create(struct mlx5_core_dev *mdev, if (IS_ERR(g)) { err = PTR_ERR(g); mlx5_core_err(mdev, "Fail to create RoCE IPsec tx group err=%d\n", err); - goto fail; + goto destroy_table; } roce->g = g; err = ipsec_fs_roce_tx_rule_setup(mdev, roce, pol_ft); if (err) { mlx5_core_err(mdev, "Fail to create RoCE IPsec tx rules err=%d\n", err); - goto rule_fail; + goto destroy_group; } + kvfree(in); return 0; -rule_fail: +destroy_group: mlx5_destroy_flow_group(roce->g); -fail: +destroy_table: mlx5_destroy_flow_table(ft); +free_in: + kvfree(in); return err; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c index 3008e9ce2bbf..20d7662c10fb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/sriov.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/sriov.c @@ -147,6 +147,10 @@ mlx5_device_disable_sriov(struct mlx5_core_dev *dev, int num_vfs, bool clear_vf) mlx5_eswitch_disable_sriov(dev->priv.eswitch, clear_vf); + /* For ECPFs, skip waiting for host VF pages until ECPF is destroyed */ + if (mlx5_core_is_ecpf(dev)) + return; + if (mlx5_wait_for_pages(dev, &dev->priv.page_counters[MLX5_VF])) mlx5_core_warn(dev, "timeout reclaiming VFs pages\n"); } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 4a3c3b5fb4a1..261f982ca40d 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -963,7 +963,6 @@ static int qede_alloc_fp_array(struct qede_dev *edev) { u8 fp_combined, fp_rx = edev->fp_num_rx; struct qede_fastpath *fp; - void *mem; int i; edev->fp_array = kcalloc(QEDE_QUEUE_CNT(edev), @@ -974,20 +973,14 @@ static int qede_alloc_fp_array(struct qede_dev *edev) } if (!edev->coal_entry) { - mem = kcalloc(QEDE_MAX_RSS_CNT(edev), - sizeof(*edev->coal_entry), GFP_KERNEL); - } else { - mem = krealloc(edev->coal_entry, - QEDE_QUEUE_CNT(edev) * sizeof(*edev->coal_entry), - GFP_KERNEL); - } - - if (!mem) { - DP_ERR(edev, "coalesce entry allocation failed\n"); - kfree(edev->coal_entry); - goto err; + edev->coal_entry = kcalloc(QEDE_MAX_RSS_CNT(edev), + sizeof(*edev->coal_entry), + GFP_KERNEL); + if (!edev->coal_entry) { + DP_ERR(edev, "coalesce entry allocation failed\n"); + goto err; + } } - edev->coal_entry = mem; fp_combined = QEDE_QUEUE_CNT(edev) - fp_rx - edev->fp_num_tx; diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c index 1c16548415cd..b0c7ab74a82e 100644 --- a/drivers/net/ethernet/sun/sunhme.c +++ b/drivers/net/ethernet/sun/sunhme.c @@ -2894,8 +2894,10 @@ static int happy_meal_pci_probe(struct pci_dev *pdev, goto err_out_clear_quattro; } - hpreg_res = devm_request_region(&pdev->dev, pci_resource_start(pdev, 0), - pci_resource_len(pdev, 0), DRV_NAME); + hpreg_res = devm_request_mem_region(&pdev->dev, + pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0), + DRV_NAME); if (!hpreg_res) { err = -EBUSY; dev_err(&pdev->dev, "Cannot obtain PCI resources, aborting.\n"); diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index c87e991d1a17..1a1b95ae95fa 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -52,6 +52,7 @@ struct mscc_miim_info { struct mscc_miim_dev { struct regmap *regs; int mii_status_offset; + bool ignore_read_errors; struct regmap *phy_regs; const struct mscc_miim_info *info; struct clk *clk; @@ -135,7 +136,7 @@ static int mscc_miim_read(struct mii_bus *bus, int mii_id, int regnum) goto out; } - if (val & MSCC_MIIM_DATA_ERROR) { + if (!miim->ignore_read_errors && !!(val & MSCC_MIIM_DATA_ERROR)) { ret = -EIO; goto out; } @@ -212,7 +213,8 @@ static const struct regmap_config mscc_miim_phy_regmap_config = { }; int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, - struct regmap *mii_regmap, int status_offset) + struct regmap *mii_regmap, int status_offset, + bool ignore_read_errors) { struct mscc_miim_dev *miim; struct mii_bus *bus; @@ -234,6 +236,7 @@ int mscc_miim_setup(struct device *dev, struct mii_bus **pbus, const char *name, miim->regs = mii_regmap; miim->mii_status_offset = status_offset; + miim->ignore_read_errors = ignore_read_errors; *pbus = bus; @@ -285,7 +288,7 @@ static int mscc_miim_probe(struct platform_device *pdev) return dev_err_probe(dev, PTR_ERR(phy_regmap), "Unable to create phy register regmap\n"); - ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0); + ret = mscc_miim_setup(dev, &bus, "mscc_miim", mii_regmap, 0, false); if (ret < 0) { dev_err(dev, "Unable to setup the MDIO bus\n"); return ret; diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c index f9b128cecc3f..fee514b96ab1 100644 --- a/drivers/net/phy/phy-c45.c +++ b/drivers/net/phy/phy-c45.c @@ -262,7 +262,7 @@ int genphy_c45_an_config_aneg(struct phy_device *phydev) linkmode_and(phydev->advertising, phydev->advertising, phydev->supported); - ret = genphy_c45_write_eee_adv(phydev, phydev->supported_eee); + ret = genphy_c45_an_config_eee_aneg(phydev); if (ret < 0) return ret; else if (ret) @@ -672,9 +672,9 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_mdix); */ int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) { - int val, changed; + int val, changed = 0; - if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) { val = linkmode_to_mii_eee_cap1_t(adv); /* In eee_broken_modes are stored MDIO_AN_EEE_ADV specific raw @@ -721,12 +721,11 @@ int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv) * @phydev: target phy_device struct * @adv: the linkmode advertisement status */ -static int genphy_c45_read_eee_adv(struct phy_device *phydev, - unsigned long *adv) +int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv) { int val; - if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) { /* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1 * (Register 7.60) */ @@ -762,7 +761,7 @@ static int genphy_c45_read_eee_lpa(struct phy_device *phydev, { int val; - if (linkmode_intersects(phydev->supported, PHY_EEE_CAP1_FEATURES)) { + if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) { /* IEEE 802.3-2018 45.2.7.14 EEE link partner ability 1 * (Register 7.61) */ @@ -859,6 +858,21 @@ int genphy_c45_read_eee_abilities(struct phy_device *phydev) EXPORT_SYMBOL_GPL(genphy_c45_read_eee_abilities); /** + * genphy_c45_an_config_eee_aneg - configure EEE advertisement + * @phydev: target phy_device struct + */ +int genphy_c45_an_config_eee_aneg(struct phy_device *phydev) +{ + if (!phydev->eee_enabled) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; + + return genphy_c45_write_eee_adv(phydev, adv); + } + + return genphy_c45_write_eee_adv(phydev, phydev->advertising_eee); +} + +/** * genphy_c45_pma_read_abilities - read supported link modes from PMA * @phydev: target phy_device struct * @@ -1421,17 +1435,33 @@ EXPORT_SYMBOL(genphy_c45_ethtool_get_eee); int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data) { - __ETHTOOL_DECLARE_LINK_MODE_MASK(adv) = {}; int ret; if (data->eee_enabled) { - if (data->advertised) - adv[0] = data->advertised; - else - linkmode_copy(adv, phydev->supported_eee); + if (data->advertised) { + __ETHTOOL_DECLARE_LINK_MODE_MASK(adv); + + ethtool_convert_legacy_u32_to_link_mode(adv, + data->advertised); + linkmode_andnot(adv, adv, phydev->supported_eee); + if (!linkmode_empty(adv)) { + phydev_warn(phydev, "At least some EEE link modes are not supported.\n"); + return -EINVAL; + } + + ethtool_convert_legacy_u32_to_link_mode(phydev->advertising_eee, + data->advertised); + } else { + linkmode_copy(phydev->advertising_eee, + phydev->supported_eee); + } + + phydev->eee_enabled = true; + } else { + phydev->eee_enabled = false; } - ret = genphy_c45_write_eee_adv(phydev, adv); + ret = genphy_c45_an_config_eee_aneg(phydev); if (ret < 0) return ret; if (ret > 0) diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 71becceb8764..3f8a64fb9d71 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -2231,7 +2231,7 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed) { int err; - err = genphy_c45_write_eee_adv(phydev, phydev->supported_eee); + err = genphy_c45_an_config_eee_aneg(phydev); if (err < 0) return err; else if (err) @@ -3141,6 +3141,25 @@ static int phy_probe(struct device *dev) of_set_phy_supported(phydev); phy_advertise_supported(phydev); + /* Get PHY default EEE advertising modes and handle them as potentially + * safe initial configuration. + */ + err = genphy_c45_read_eee_adv(phydev, phydev->advertising_eee); + if (err) + return err; + + /* There is no "enabled" flag. If PHY is advertising, assume it is + * kind of enabled. + */ + phydev->eee_enabled = !linkmode_empty(phydev->advertising_eee); + + /* Some PHYs may advertise, by default, not support EEE modes. So, + * we need to clean them. + */ + if (phydev->eee_enabled) + linkmode_and(phydev->advertising_eee, phydev->supported_eee, + phydev->advertising_eee); + /* Get the EEE modes we want to prohibit. We will ask * the PHY stop advertising these mode later on */ diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c index 776362d151cb..0aeef2948ff5 100644 --- a/drivers/net/wireless/ath/ath11k/pci.c +++ b/drivers/net/wireless/ath/ath11k/pci.c @@ -981,7 +981,7 @@ static __maybe_unused int ath11k_pci_pm_suspend(struct device *dev) if (ret) ath11k_warn(ab, "failed to suspend core: %d\n", ret); - return ret; + return 0; } static __maybe_unused int ath11k_pci_pm_resume(struct device *dev) diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c index b88959ef38aa..5e5c7bf51174 100644 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@ -706,6 +706,7 @@ mt76u_free_rx_queue(struct mt76_dev *dev, struct mt76_queue *q) q->entry[i].urb = NULL; } page_pool_destroy(q->page_pool); + q->page_pool = NULL; } static void mt76u_free_rx(struct mt76_dev *dev) diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index bf627af723bf..1b42676ca141 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -883,11 +883,9 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, struct xen_netif_tx_request txfrags[XEN_NETBK_LEGACY_SLOTS_MAX]; struct xen_netif_extra_info extras[XEN_NETIF_EXTRA_TYPE_MAX-1]; unsigned int extra_count; - u16 pending_idx; RING_IDX idx; int work_to_do; unsigned int data_len; - pending_ring_idx_t index; if (queue->tx.sring->req_prod - queue->tx.req_cons > XEN_NETIF_TX_RING_SIZE) { @@ -983,9 +981,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, break; } - index = pending_index(queue->pending_cons); - pending_idx = queue->pending_ring[index]; - if (ret >= XEN_NETBK_LEGACY_SLOTS_MAX - 1 && data_len < txreq.size) data_len = txreq.size; diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index ec87dd21e054..b2f1ced8e6dd 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -672,6 +672,12 @@ int st_nci_se_io(struct nci_dev *ndev, u32 se_idx, ST_NCI_EVT_TRANSMIT_DATA, apdu, apdu_length); default: + /* Need to free cb_context here as at the moment we can't + * clearly indicate to the caller if the callback function + * would be called (and free it) or not. In both cases a + * negative value may be returned to the caller. + */ + kfree(cb_context); return -ENODEV; } } diff --git a/drivers/nfc/st21nfca/se.c b/drivers/nfc/st21nfca/se.c index df8d27cf2956..dae288bebcb5 100644 --- a/drivers/nfc/st21nfca/se.c +++ b/drivers/nfc/st21nfca/se.c @@ -236,6 +236,12 @@ int st21nfca_hci_se_io(struct nfc_hci_dev *hdev, u32 se_idx, ST21NFCA_EVT_TRANSMIT_DATA, apdu, apdu_length); default: + /* Need to free cb_context here as at the moment we can't + * clearly indicate to the caller if the callback function + * would be called (and free it) or not. In both cases a + * negative value may be returned to the caller. + */ + kfree(cb_context); return -ENODEV; } } diff --git a/drivers/ptp/ptp_private.h b/drivers/ptp/ptp_private.h index 77918a2c6701..75f58fc468a7 100644 --- a/drivers/ptp/ptp_private.h +++ b/drivers/ptp/ptp_private.h @@ -66,7 +66,7 @@ struct ptp_vclock { struct hlist_node vclock_hash_node; struct cyclecounter cc; struct timecounter tc; - spinlock_t lock; /* protects tc/cc */ + struct mutex lock; /* protects tc/cc */ }; /* diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c index 1c0ed4805c0a..dcf752c9e045 100644 --- a/drivers/ptp/ptp_vclock.c +++ b/drivers/ptp/ptp_vclock.c @@ -43,16 +43,16 @@ static void ptp_vclock_hash_del(struct ptp_vclock *vclock) static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) { struct ptp_vclock *vclock = info_to_vclock(ptp); - unsigned long flags; s64 adj; adj = (s64)scaled_ppm << PTP_VCLOCK_FADJ_SHIFT; adj = div_s64(adj, PTP_VCLOCK_FADJ_DENOMINATOR); - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; timecounter_read(&vclock->tc); vclock->cc.mult = PTP_VCLOCK_CC_MULT + adj; - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); return 0; } @@ -60,11 +60,11 @@ static int ptp_vclock_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) static int ptp_vclock_adjtime(struct ptp_clock_info *ptp, s64 delta) { struct ptp_vclock *vclock = info_to_vclock(ptp); - unsigned long flags; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; timecounter_adjtime(&vclock->tc, delta); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); return 0; } @@ -73,12 +73,12 @@ static int ptp_vclock_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { struct ptp_vclock *vclock = info_to_vclock(ptp); - unsigned long flags; u64 ns; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; ns = timecounter_read(&vclock->tc); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); *ts = ns_to_timespec64(ns); return 0; @@ -91,7 +91,6 @@ static int ptp_vclock_gettimex(struct ptp_clock_info *ptp, struct ptp_vclock *vclock = info_to_vclock(ptp); struct ptp_clock *pptp = vclock->pclock; struct timespec64 pts; - unsigned long flags; int err; u64 ns; @@ -99,9 +98,10 @@ static int ptp_vclock_gettimex(struct ptp_clock_info *ptp, if (err) return err; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; ns = timecounter_cyc2time(&vclock->tc, timespec64_to_ns(&pts)); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); *ts = ns_to_timespec64(ns); @@ -113,11 +113,11 @@ static int ptp_vclock_settime(struct ptp_clock_info *ptp, { struct ptp_vclock *vclock = info_to_vclock(ptp); u64 ns = timespec64_to_ns(ts); - unsigned long flags; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; timecounter_init(&vclock->tc, &vclock->cc, ns); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); return 0; } @@ -127,7 +127,6 @@ static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp, { struct ptp_vclock *vclock = info_to_vclock(ptp); struct ptp_clock *pptp = vclock->pclock; - unsigned long flags; int err; u64 ns; @@ -135,9 +134,10 @@ static int ptp_vclock_getcrosststamp(struct ptp_clock_info *ptp, if (err) return err; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + return -EINTR; ns = timecounter_cyc2time(&vclock->tc, ktime_to_ns(xtstamp->device)); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); xtstamp->device = ns_to_ktime(ns); @@ -205,7 +205,7 @@ struct ptp_vclock *ptp_vclock_register(struct ptp_clock *pclock) INIT_HLIST_NODE(&vclock->vclock_hash_node); - spin_lock_init(&vclock->lock); + mutex_init(&vclock->lock); vclock->clock = ptp_clock_register(&vclock->info, &pclock->dev); if (IS_ERR_OR_NULL(vclock->clock)) { @@ -269,7 +269,6 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) { unsigned int hash = vclock_index % HASH_SIZE(vclock_hash); struct ptp_vclock *vclock; - unsigned long flags; u64 ns; u64 vclock_ns = 0; @@ -281,9 +280,10 @@ ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp, int vclock_index) if (vclock->clock->index != vclock_index) continue; - spin_lock_irqsave(&vclock->lock, flags); + if (mutex_lock_interruptible(&vclock->lock)) + break; vclock_ns = timecounter_cyc2time(&vclock->tc, ns); - spin_unlock_irqrestore(&vclock->lock, flags); + mutex_unlock(&vclock->lock); break; } diff --git a/include/linux/mdio/mdio-mscc-miim.h b/include/linux/mdio/mdio-mscc-miim.h index 5b4ed2c3cbb9..1ce699740af6 100644 --- a/include/linux/mdio/mdio-mscc-miim.h +++ b/include/linux/mdio/mdio-mscc-miim.h @@ -14,6 +14,6 @@ int mscc_miim_setup(struct device *device, struct mii_bus **bus, const char *name, struct regmap *mii_regmap, - int status_offset); + int status_offset, bool ignore_read_errors); #endif diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 6863e271a9de..c8e03bcaecaa 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -491,4 +491,9 @@ extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; */ DECLARE_PER_CPU(bool, nf_skb_duplicated); +/** + * Contains bitmask of ctnetlink event subscribers, if any. + * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag. + */ +extern u8 nf_ctnetlink_has_listener; #endif /*__LINUX_NETFILTER_H*/ diff --git a/include/linux/phy.h b/include/linux/phy.h index 727bff531a14..36bf0bbc8efa 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -575,6 +575,8 @@ struct macsec_ops; * @advertising: Currently advertised linkmodes * @adv_old: Saved advertised while power saving for WoL * @supported_eee: supported PHY EEE linkmodes + * @advertising_eee: Currently advertised EEE linkmodes + * @eee_enabled: Flag indicating whether the EEE feature is enabled * @lp_advertising: Current link partner advertised linkmodes * @host_interfaces: PHY interface modes supported by host * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited @@ -681,6 +683,8 @@ struct phy_device { __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* used for eee validation */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee); + __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee); + bool eee_enabled; /* Host supported PHY interface types. Should be ignored if empty. */ DECLARE_PHY_INTERFACE_MASK(host_interfaces); @@ -1765,6 +1769,8 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev, int genphy_c45_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int genphy_c45_write_eee_adv(struct phy_device *phydev, unsigned long *adv); +int genphy_c45_an_config_eee_aneg(struct phy_device *phydev); +int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv); /* Generic C45 PHY driver */ extern struct phy_driver genphy_c45_driver; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index e1290c159184..1f463b3957c7 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -95,7 +95,6 @@ struct nf_ip_net { struct netns_ct { #ifdef CONFIG_NF_CONNTRACK_EVENTS - u8 ctnetlink_has_listener; bool ecache_dwork_pending; #endif u8 sysctl_log_invalid; /* Log invalid packets */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index afa3781e3ca2..e1f6e7fc2b11 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1412,6 +1412,7 @@ struct sctp_stream_priorities { /* The next stream in line */ struct sctp_stream_out_ext *next; __u16 prio; + __u16 users; }; struct sctp_stream_out_ext { diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h index 9ee459872600..588391447bfb 100644 --- a/include/uapi/linux/netdev.h +++ b/include/uapi/linux/netdev.h @@ -19,7 +19,7 @@ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP * in zero copy mode. * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw - * oflloading. + * offloading. * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear * XDP buffer support in the driver napi callback. * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index ce5dfa3babd2..757ec46fc45a 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1090,7 +1090,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, audit_log_nfcfg(repl->name, AF_BRIDGE, repl->nentries, AUDIT_XT_OP_REPLACE, GFP_KERNEL); - return ret; + return 0; free_unlock: mutex_unlock(&ebt_mutex); diff --git a/net/core/dev.c b/net/core/dev.c index 18dc8d75ead9..253584777101 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3134,8 +3134,10 @@ void __dev_kfree_skb_any(struct sk_buff *skb, enum skb_free_reason reason) { if (in_hardirq() || irqs_disabled()) __dev_kfree_skb_irq(skb, reason); + else if (unlikely(reason == SKB_REASON_DROPPED)) + kfree_skb(skb); else - dev_kfree_skb(skb); + consume_skb(skb); } EXPORT_SYMBOL(__dev_kfree_skb_any); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index ffc0cab7cf18..2407066b0fec 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1525,6 +1525,10 @@ int arpt_register_table(struct net *net, new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { + struct arpt_entry *iter; + + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 2ed7c58b471a..da5998011ab9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1045,7 +1045,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_counters *counters; struct ipt_entry *iter; - ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; @@ -1091,7 +1090,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, net_warn_ratelimited("iptables: counters copy to user failed while replacing table\n"); } vfree(counters); - return ret; + return 0; put_module: module_put(t->me); @@ -1742,6 +1741,10 @@ int ipt_register_table(struct net *net, const struct xt_table *table, new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { + struct ipt_entry *iter; + + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e002f2e1d4f2..9a7ef7732c24 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -597,6 +597,9 @@ EXPORT_SYMBOL(tcp_create_openreq_child); * validation and inside tcp_v4_reqsk_send_ack(). Can we do better? * * We don't need to initialize tmp_opt.sack_ok as we don't use the results + * + * Note: If @fastopen is true, this can be called from process context. + * Otherwise, this is from BH context. */ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, @@ -748,7 +751,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, &tcp_rsk(req)->last_oow_ack_time)) req->rsk_ops->send_ack(sk, skb, req); if (paws_reject) - __NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); + NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED); return NULL; } @@ -767,7 +770,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, * "fourth, check the SYN bit" */ if (flg & (TCP_FLAG_RST|TCP_FLAG_SYN)) { - __TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); + TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); goto embryonic_reset; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 2d816277f2c5..0ce0ed17c758 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1062,7 +1062,6 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, struct xt_counters *counters; struct ip6t_entry *iter; - ret = 0; counters = xt_counters_alloc(num_counters); if (!counters) { ret = -ENOMEM; @@ -1108,7 +1107,7 @@ __do_replace(struct net *net, const char *name, unsigned int valid_hooks, net_warn_ratelimited("ip6tables: counters copy to user failed while replacing table\n"); } vfree(counters); - return ret; + return 0; put_module: module_put(t->me); @@ -1751,6 +1750,10 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, new_table = xt_register_table(net, table, &bootstrap, newinfo); if (IS_ERR(new_table)) { + struct ip6t_entry *iter; + + xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) + cleanup_entry(iter, net); xt_free_table_info(newinfo); return PTR_ERR(new_table); } diff --git a/net/ipv6/netfilter/ip6t_rpfilter.c b/net/ipv6/netfilter/ip6t_rpfilter.c index a01d9b842bd0..67c87a88cde4 100644 --- a/net/ipv6/netfilter/ip6t_rpfilter.c +++ b/net/ipv6/netfilter/ip6t_rpfilter.c @@ -72,7 +72,9 @@ static bool rpfilter_lookup_reverse6(struct net *net, const struct sk_buff *skb, goto out; } - if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE)) + if (rt->rt6i_idev->dev == dev || + l3mdev_master_ifindex_rcu(rt->rt6i_idev->dev) == dev->ifindex || + (flags & XT_RPFILTER_LOOSE)) ret = true; out: ip6_rt_put(rt); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index c180c2ef17c5..0fdb03df2287 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5533,16 +5533,17 @@ static size_t rt6_nlmsg_size(struct fib6_info *f6i) nexthop_for_each_fib6_nh(f6i->nh, rt6_nh_nlmsg_size, &nexthop_len); } else { + struct fib6_info *sibling, *next_sibling; struct fib6_nh *nh = f6i->fib6_nh; nexthop_len = 0; if (f6i->fib6_nsiblings) { - nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ - + NLA_ALIGN(sizeof(struct rtnexthop)) - + nla_total_size(16) /* RTA_GATEWAY */ - + lwtunnel_get_encap_size(nh->fib_nh_lws); + rt6_nh_nlmsg_size(nh, &nexthop_len); - nexthop_len *= f6i->fib6_nsiblings; + list_for_each_entry_safe(sibling, next_sibling, + &f6i->fib6_siblings, fib6_siblings) { + rt6_nh_nlmsg_size(sibling->fib6_nh, &nexthop_len); + } } nexthop_len += lwtunnel_get_encap_size(nh->fib_nh_lws); } diff --git a/net/netfilter/core.c b/net/netfilter/core.c index b2fdbbed2b4b..358220b58521 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -669,6 +669,9 @@ const struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) +u8 nf_ctnetlink_has_listener; +EXPORT_SYMBOL_GPL(nf_ctnetlink_has_listener); + const struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); diff --git a/net/netfilter/nf_conntrack_bpf.c b/net/netfilter/nf_conntrack_bpf.c index 34913521c385..cd99e6dc1f35 100644 --- a/net/netfilter/nf_conntrack_bpf.c +++ b/net/netfilter/nf_conntrack_bpf.c @@ -381,7 +381,6 @@ __bpf_kfunc struct nf_conn *bpf_ct_insert_entry(struct nf_conn___init *nfct_i) struct nf_conn *nfct = (struct nf_conn *)nfct_i; int err; - nfct->status |= IPS_CONFIRMED; err = nf_conntrack_hash_check_insert(nfct); if (err < 0) { nf_conntrack_free(nfct); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 70c4f892174e..7250082e7de5 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -884,10 +884,8 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) zone = nf_ct_zone(ct); - if (!nf_ct_ext_valid_pre(ct->ext)) { - NF_CT_STAT_INC_ATOMIC(net, insert_failed); - return -ETIMEDOUT; - } + if (!nf_ct_ext_valid_pre(ct->ext)) + return -EAGAIN; local_bh_disable(); do { @@ -922,6 +920,19 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) goto chaintoolong; } + /* If genid has changed, we can't insert anymore because ct + * extensions could have stale pointers and nf_ct_iterate_destroy + * might have completed its table scan already. + * + * Increment of the ext genid right after this check is fine: + * nf_ct_iterate_destroy blocks until locks are released. + */ + if (!nf_ct_ext_valid_post(ct->ext)) { + err = -EAGAIN; + goto out; + } + + ct->status |= IPS_CONFIRMED; smp_wmb(); /* The caller holds a reference to this object */ refcount_set(&ct->ct_general.use, 2); @@ -930,12 +941,6 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct) NF_CT_STAT_INC(net, insert); local_bh_enable(); - if (!nf_ct_ext_valid_post(ct->ext)) { - nf_ct_kill(ct); - NF_CT_STAT_INC_ATOMIC(net, drop); - return -ETIMEDOUT; - } - return 0; chaintoolong: NF_CT_STAT_INC(net, chaintoolong); diff --git a/net/netfilter/nf_conntrack_ecache.c b/net/netfilter/nf_conntrack_ecache.c index 8698b3424646..69948e1d6974 100644 --- a/net/netfilter/nf_conntrack_ecache.c +++ b/net/netfilter/nf_conntrack_ecache.c @@ -309,7 +309,7 @@ bool nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp break; return true; case 2: /* autodetect: no event listener, don't allocate extension. */ - if (!READ_ONCE(net->ct.ctnetlink_has_listener)) + if (!READ_ONCE(nf_ctnetlink_has_listener)) return true; fallthrough; case 1: diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 308fc0023c7e..c11dff91d52d 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2316,9 +2316,6 @@ ctnetlink_create_conntrack(struct net *net, nfct_seqadj_ext_add(ct); nfct_synproxy_ext_add(ct); - /* we must add conntrack extensions before confirmation. */ - ct->status |= IPS_CONFIRMED; - if (cda[CTA_STATUS]) { err = ctnetlink_change_status(ct, cda); if (err < 0) @@ -2375,12 +2372,15 @@ ctnetlink_create_conntrack(struct net *net, err = nf_conntrack_hash_check_insert(ct); if (err < 0) - goto err2; + goto err3; rcu_read_unlock(); return ct; +err3: + if (ct->master) + nf_ct_put(ct->master); err2: rcu_read_unlock(); err1: diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d73edbd4eec4..6004d4b24451 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5507,7 +5507,7 @@ static int nf_tables_getsetelem(struct sk_buff *skb, int rem, err = 0; table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, - genmask, NETLINK_CB(skb).portid); + genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 6d18fb346868..81c7737c803a 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -29,6 +29,7 @@ #include <net/netlink.h> #include <net/netns/generic.h> +#include <linux/netfilter.h> #include <linux/netfilter/nfnetlink.h> MODULE_LICENSE("GPL"); @@ -685,12 +686,12 @@ static void nfnetlink_bind_event(struct net *net, unsigned int group) group_bit = (1 << group); spin_lock(&nfnl_grp_active_lock); - v = READ_ONCE(net->ct.ctnetlink_has_listener); + v = READ_ONCE(nf_ctnetlink_has_listener); if ((v & group_bit) == 0) { v |= group_bit; /* read concurrently without nfnl_grp_active_lock held. */ - WRITE_ONCE(net->ct.ctnetlink_has_listener, v); + WRITE_ONCE(nf_ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); @@ -744,12 +745,12 @@ static void nfnetlink_unbind(struct net *net, int group) spin_lock(&nfnl_grp_active_lock); if (!nfnetlink_has_listeners(net, group)) { - u8 v = READ_ONCE(net->ct.ctnetlink_has_listener); + u8 v = READ_ONCE(nf_ctnetlink_has_listener); v &= ~group_bit; /* read concurrently without nfnl_grp_active_lock held. */ - WRITE_ONCE(net->ct.ctnetlink_has_listener, v); + WRITE_ONCE(nf_ctnetlink_has_listener, v); } spin_unlock(&nfnl_grp_active_lock); #endif diff --git a/net/netfilter/xt_length.c b/net/netfilter/xt_length.c index b3d623a52885..ca730cedb5d4 100644 --- a/net/netfilter/xt_length.c +++ b/net/netfilter/xt_length.c @@ -30,8 +30,7 @@ static bool length_mt6(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_length_info *info = par->matchinfo; - const u_int16_t pktlen = ntohs(ipv6_hdr(skb)->payload_len) + - sizeof(struct ipv6hdr); + u32 pktlen = skb->len; return (pktlen >= info->min && pktlen <= info->max) ^ info->invert; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 1fc339084d89..348bf561bc9f 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1442,7 +1442,11 @@ static int nfc_se_io(struct nfc_dev *dev, u32 se_idx, rc = dev->ops->se_io(dev, se_idx, apdu, apdu_length, cb, cb_context); + device_unlock(&dev->dev); + return rc; + error: + kfree(cb_context); device_unlock(&dev->dev); return rc; } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index fce522886099..34c508675041 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -1596,12 +1596,12 @@ static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[], if (tcf_action_dump(skb, actions, bind, ref, false) < 0) goto out_nlmsg_trim; - nla_nest_end(skb, nest); - if (extack && extack->_msg && nla_put_string(skb, TCA_EXT_WARN_MSG, extack->_msg)) goto out_nlmsg_trim; + nla_nest_end(skb, nest); + nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; diff --git a/net/sched/act_mpls.c b/net/sched/act_mpls.c index 6b26bdb999d7..809f7928a1be 100644 --- a/net/sched/act_mpls.c +++ b/net/sched/act_mpls.c @@ -190,40 +190,67 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, parm = nla_data(tb[TCA_MPLS_PARMS]); index = parm->index; + err = tcf_idr_check_alloc(tn, &index, a, bind); + if (err < 0) + return err; + exists = err; + if (exists && bind) + return 0; + + if (!exists) { + ret = tcf_idr_create(tn, index, est, a, &act_mpls_ops, bind, + true, flags); + if (ret) { + tcf_idr_cleanup(tn, index); + return ret; + } + + ret = ACT_P_CREATED; + } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { + tcf_idr_release(*a, bind); + return -EEXIST; + } + /* Verify parameters against action type. */ switch (parm->m_action) { case TCA_MPLS_ACT_POP: if (!tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be set for MPLS pop"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } if (!eth_proto_is_802_3(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Invalid protocol type for MPLS pop"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } if (tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC or BOS cannot be used with MPLS pop"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } break; case TCA_MPLS_ACT_DEC_TTL: if (tb[TCA_MPLS_PROTO] || tb[TCA_MPLS_LABEL] || tb[TCA_MPLS_TTL] || tb[TCA_MPLS_TC] || tb[TCA_MPLS_BOS]) { NL_SET_ERR_MSG_MOD(extack, "Label, TTL, TC, BOS or protocol cannot be used with MPLS dec_ttl"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } break; case TCA_MPLS_ACT_PUSH: case TCA_MPLS_ACT_MAC_PUSH: if (!tb[TCA_MPLS_LABEL]) { NL_SET_ERR_MSG_MOD(extack, "Label is required for MPLS push"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } if (tb[TCA_MPLS_PROTO] && !eth_p_mpls(nla_get_be16(tb[TCA_MPLS_PROTO]))) { NL_SET_ERR_MSG_MOD(extack, "Protocol must be an MPLS type for MPLS push"); - return -EPROTONOSUPPORT; + err = -EPROTONOSUPPORT; + goto release_idr; } /* Push needs a TTL - if not specified, set a default value. */ if (!tb[TCA_MPLS_TTL]) { @@ -238,33 +265,14 @@ static int tcf_mpls_init(struct net *net, struct nlattr *nla, case TCA_MPLS_ACT_MODIFY: if (tb[TCA_MPLS_PROTO]) { NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be used with MPLS modify"); - return -EINVAL; + err = -EINVAL; + goto release_idr; } break; default: NL_SET_ERR_MSG_MOD(extack, "Unknown MPLS action"); - return -EINVAL; - } - - err = tcf_idr_check_alloc(tn, &index, a, bind); - if (err < 0) - return err; - exists = err; - if (exists && bind) - return 0; - - if (!exists) { - ret = tcf_idr_create(tn, index, est, a, - &act_mpls_ops, bind, true, flags); - if (ret) { - tcf_idr_cleanup(tn, index); - return ret; - } - - ret = ACT_P_CREATED; - } else if (!(flags & TCA_ACT_FLAGS_REPLACE)) { - tcf_idr_release(*a, bind); - return -EEXIST; + err = -EINVAL; + goto release_idr; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 77d288d384ae..4559a1507ea5 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -181,26 +181,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); - if (!parm->nkeys) { - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - return -EINVAL; - } - ksize = parm->nkeys * sizeof(struct tc_pedit_key); - if (nla_len(pattr) < sizeof(*parm) + ksize) { - NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); - return -EINVAL; - } - - nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); - if (!nparms) - return -ENOMEM; - - nparms->tcfp_keys_ex = - tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); - if (IS_ERR(nparms->tcfp_keys_ex)) { - ret = PTR_ERR(nparms->tcfp_keys_ex); - goto out_free; - } index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); @@ -209,25 +189,49 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, &act_pedit_ops, bind, flags); if (ret) { tcf_idr_cleanup(tn, index); - goto out_free_ex; + return ret; } ret = ACT_P_CREATED; } else if (err > 0) { if (bind) - goto out_free; + return 0; if (!(flags & TCA_ACT_FLAGS_REPLACE)) { ret = -EEXIST; goto out_release; } } else { - ret = err; - goto out_free_ex; + return err; + } + + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + ret = -EINVAL; + goto out_release; + } + ksize = parm->nkeys * sizeof(struct tc_pedit_key); + if (nla_len(pattr) < sizeof(*parm) + ksize) { + NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); + ret = -EINVAL; + goto out_release; + } + + nparms = kzalloc(sizeof(*nparms), GFP_KERNEL); + if (!nparms) { + ret = -ENOMEM; + goto out_release; + } + + nparms->tcfp_keys_ex = + tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys); + if (IS_ERR(nparms->tcfp_keys_ex)) { + ret = PTR_ERR(nparms->tcfp_keys_ex); + goto out_free; } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) { ret = err; - goto out_release; + goto out_free_ex; } nparms->tcfp_off_max_hint = 0; @@ -278,12 +282,12 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); -out_release: - tcf_idr_release(*a, bind); out_free_ex: kfree(nparms->tcfp_keys_ex); out_free: kfree(nparms); +out_release: + tcf_idr_release(*a, bind); return ret; } diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index f7416b5598e0..4c670e7568dc 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -55,8 +55,8 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, sample_policy, NULL); if (ret < 0) return ret; - if (!tb[TCA_SAMPLE_PARMS] || !tb[TCA_SAMPLE_RATE] || - !tb[TCA_SAMPLE_PSAMPLE_GROUP]) + + if (!tb[TCA_SAMPLE_PARMS]) return -EINVAL; parm = nla_data(tb[TCA_SAMPLE_PARMS]); @@ -80,6 +80,13 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla, tcf_idr_release(*a, bind); return -EEXIST; } + + if (!tb[TCA_SAMPLE_RATE] || !tb[TCA_SAMPLE_PSAMPLE_GROUP]) { + NL_SET_ERR_MSG(extack, "sample rate and group are required"); + err = -EINVAL; + goto release_idr; + } + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 3569e2c3660c..2a6b6be0811b 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3241,9 +3241,9 @@ EXPORT_SYMBOL(tcf_exts_init_ex); void tcf_exts_destroy(struct tcf_exts *exts) { -#ifdef CONFIG_NET_CLS_ACT tcf_exts_miss_cookie_base_destroy(exts); +#ifdef CONFIG_NET_CLS_ACT if (exts->actions) { tcf_action_destroy(exts->actions, TCA_ACT_UNBIND); kfree(exts->actions); diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c index 42d4800f263d..4d4d9da331f4 100644 --- a/net/sctp/stream_sched_prio.c +++ b/net/sctp/stream_sched_prio.c @@ -25,6 +25,18 @@ static void sctp_sched_prio_unsched_all(struct sctp_stream *stream); +static struct sctp_stream_priorities *sctp_sched_prio_head_get(struct sctp_stream_priorities *p) +{ + p->users++; + return p; +} + +static void sctp_sched_prio_head_put(struct sctp_stream_priorities *p) +{ + if (p && --p->users == 0) + kfree(p); +} + static struct sctp_stream_priorities *sctp_sched_prio_new_head( struct sctp_stream *stream, int prio, gfp_t gfp) { @@ -38,6 +50,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_new_head( INIT_LIST_HEAD(&p->active); p->next = NULL; p->prio = prio; + p->users = 1; return p; } @@ -53,7 +66,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ list_for_each_entry(p, &stream->prio_list, prio_sched) { if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); if (p->prio > prio) break; } @@ -70,7 +83,7 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head( */ break; if (p->prio == prio) - return p; + return sctp_sched_prio_head_get(p); } /* If not even there, allocate a new one. */ @@ -154,32 +167,21 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid, struct sctp_stream_out_ext *soute = sout->ext; struct sctp_stream_priorities *prio_head, *old; bool reschedule = false; - int i; + + old = soute->prio_head; + if (old && old->prio == prio) + return 0; prio_head = sctp_sched_prio_get_head(stream, prio, gfp); if (!prio_head) return -ENOMEM; reschedule = sctp_sched_prio_unsched(soute); - old = soute->prio_head; soute->prio_head = prio_head; if (reschedule) sctp_sched_prio_sched(stream, soute); - if (!old) - /* Happens when we set the priority for the first time */ - return 0; - - for (i = 0; i < stream->outcnt; i++) { - soute = SCTP_SO(stream, i)->ext; - if (soute && soute->prio_head == old) - /* It's still in use, nothing else to do here. */ - return 0; - } - - /* No hits, we are good to free it. */ - kfree(old); - + sctp_sched_prio_head_put(old); return 0; } @@ -206,20 +208,8 @@ static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid, static void sctp_sched_prio_free_sid(struct sctp_stream *stream, __u16 sid) { - struct sctp_stream_priorities *prio = SCTP_SO(stream, sid)->ext->prio_head; - int i; - - if (!prio) - return; - + sctp_sched_prio_head_put(SCTP_SO(stream, sid)->ext->prio_head); SCTP_SO(stream, sid)->ext->prio_head = NULL; - for (i = 0; i < stream->outcnt; i++) { - if (SCTP_SO(stream, i)->ext && - SCTP_SO(stream, i)->ext->prio_head == prio) - return; - } - - kfree(prio); } static void sctp_sched_prio_enqueue(struct sctp_outq *q, diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 13a72b17248e..a125fd1fa134 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -641,8 +641,8 @@ static void wireless_warn_cfg80211_wext(void) { char name[sizeof(current->comm)]; - pr_warn_ratelimited("warning: `%s' uses wireless extensions that are deprecated for modern drivers; use nl80211\n", - get_task_comm(name, current)); + pr_warn_once("warning: `%s' uses wireless extensions which will stop working for Wi-Fi 7 hardware; use nl80211\n", + get_task_comm(name, current)); } #endif diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h index 9ee459872600..588391447bfb 100644 --- a/tools/include/uapi/linux/netdev.h +++ b/tools/include/uapi/linux/netdev.h @@ -19,7 +19,7 @@ * @NETDEV_XDP_ACT_XSK_ZEROCOPY: This feature informs if netdev supports AF_XDP * in zero copy mode. * @NETDEV_XDP_ACT_HW_OFFLOAD: This feature informs if netdev supports XDP hw - * oflloading. + * offloading. * @NETDEV_XDP_ACT_RX_SG: This feature informs if netdev implements non-linear * XDP buffer support in the driver napi callback. * @NETDEV_XDP_ACT_NDO_XMIT_SG: This feature informs if netdev implements diff --git a/tools/net/ynl/lib/.gitignore b/tools/net/ynl/lib/.gitignore new file mode 100644 index 000000000000..c18dd8d83cee --- /dev/null +++ b/tools/net/ynl/lib/.gitignore @@ -0,0 +1 @@ +__pycache__/ diff --git a/tools/net/ynl/lib/nlspec.py b/tools/net/ynl/lib/nlspec.py index e204679ad8b7..71da568e2c28 100644 --- a/tools/net/ynl/lib/nlspec.py +++ b/tools/net/ynl/lib/nlspec.py @@ -3,7 +3,6 @@ import collections import importlib import os -import traceback import yaml @@ -234,8 +233,7 @@ class SpecFamily(SpecElement): resolved.append(elem) if len(resolved) == 0: - traceback.print_exception(last_exception) - raise Exception("Could not resolve any spec element, infinite loop?") + raise last_exception def new_attr_set(self, elem): return SpecAttrSet(self, elem) diff --git a/tools/net/ynl/ynl-gen-c.py b/tools/net/ynl/ynl-gen-c.py index 3942f24b9163..274e9c566f61 100755 --- a/tools/net/ynl/ynl-gen-c.py +++ b/tools/net/ynl/ynl-gen-c.py @@ -546,7 +546,7 @@ class Struct: max_val = 0 self.attr_max_val = None for name, attr in self.attr_list: - if attr.value > max_val: + if attr.value >= max_val: max_val = attr.value self.attr_max_val = attr self.attrs[name] = attr diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 70ea8798b1f6..7da8ec838c63 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -9,7 +9,7 @@ ret=0 ksft_skip=4 # all tests in this script. Can be overridden with -t option -TESTS="unregister down carrier nexthop suppress ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" +TESTS="unregister down carrier nexthop suppress ipv6_notify ipv4_notify ipv6_rt ipv4_rt ipv6_addr_metric ipv4_addr_metric ipv6_route_metrics ipv4_route_metrics ipv4_route_v6_gw rp_filter ipv4_del_addr ipv4_mangle ipv6_mangle ipv4_bcast_neigh" VERBOSE=0 PAUSE_ON_FAIL=no @@ -655,6 +655,98 @@ fib_nexthop_test() cleanup } +fib6_notify_test() +{ + setup + + echo + echo "Fib6 info length calculation in route notify test" + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP -6 address add 2001:$i::1/64 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP -6 route add 2001::/64 \ + nexthop via 2001:10::2 dev dummy_10 \ + nexthop encap ip6 dst 2002::20 via 2001:20::2 dev dummy_20 \ + nexthop encap ip6 dst 2002::30 via 2001:30::2 dev dummy_30 \ + nexthop encap ip6 dst 2002::40 via 2001:40::2 dev dummy_40 \ + nexthop encap ip6 dst 2002::50 via 2001:50::2 dev dummy_50 \ + nexthop encap ip6 dst 2002::60 via 2001:60::2 dev dummy_60 \ + nexthop encap ip6 dst 2002::70 via 2001:70::2 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv6 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + #rm errors.txt + + cleanup &> /dev/null +} + + +fib_notify_test() +{ + setup + + echo + echo "Fib4 info length calculation in route notify test" + + set -e + + for i in 10 20 30 40 50 60 70; + do + $IP link add dummy_$i type dummy + $IP link set dev dummy_$i up + $IP address add 20.20.$i.2/24 dev dummy_$i + done + + $NS_EXEC ip monitor route &> errors.txt & + sleep 2 + + $IP route add 10.0.0.0/24 \ + nexthop via 20.20.10.1 dev dummy_10 \ + nexthop encap ip dst 192.168.10.20 via 20.20.20.1 dev dummy_20 \ + nexthop encap ip dst 192.168.10.30 via 20.20.30.1 dev dummy_30 \ + nexthop encap ip dst 192.168.10.40 via 20.20.40.1 dev dummy_40 \ + nexthop encap ip dst 192.168.10.50 via 20.20.50.1 dev dummy_50 \ + nexthop encap ip dst 192.168.10.60 via 20.20.60.1 dev dummy_60 \ + nexthop encap ip dst 192.168.10.70 via 20.20.70.1 dev dummy_70 + + set +e + + err=`cat errors.txt |grep "Message too long"` + if [ -z "$err" ];then + ret=0 + else + ret=1 + fi + + log_test $ret 0 "ipv4 route add notify" + + { kill %% && wait %%; } 2>/dev/null + + rm errors.txt + + cleanup &> /dev/null +} + fib_suppress_test() { echo @@ -2111,6 +2203,8 @@ do fib_carrier_test|carrier) fib_carrier_test;; fib_rp_filter_test|rp_filter) fib_rp_filter_test;; fib_nexthop_test|nexthop) fib_nexthop_test;; + fib_notify_test|ipv4_notify) fib_notify_test;; + fib6_notify_test|ipv6_notify) fib6_notify_test;; fib_suppress_test|suppress) fib_suppress_test;; ipv6_route_test|ipv6_rt) ipv6_route_test;; ipv4_route_test|ipv4_rt) ipv4_route_test;; diff --git a/tools/testing/selftests/netfilter/rpath.sh b/tools/testing/selftests/netfilter/rpath.sh index f7311e66d219..5289c8447a41 100755 --- a/tools/testing/selftests/netfilter/rpath.sh +++ b/tools/testing/selftests/netfilter/rpath.sh @@ -62,10 +62,16 @@ ip -net "$ns1" a a fec0:42::2/64 dev v0 nodad ip -net "$ns2" a a fec0:42::1/64 dev d0 nodad # firewall matches to test -[ -n "$iptables" ] && ip netns exec "$ns2" \ - "$iptables" -t raw -A PREROUTING -s 192.168.0.0/16 -m rpfilter -[ -n "$ip6tables" ] && ip netns exec "$ns2" \ - "$ip6tables" -t raw -A PREROUTING -s fec0::/16 -m rpfilter +[ -n "$iptables" ] && { + common='-t raw -A PREROUTING -s 192.168.0.0/16' + ip netns exec "$ns2" "$iptables" $common -m rpfilter + ip netns exec "$ns2" "$iptables" $common -m rpfilter --invert +} +[ -n "$ip6tables" ] && { + common='-t raw -A PREROUTING -s fec0::/16' + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter + ip netns exec "$ns2" "$ip6tables" $common -m rpfilter --invert +} [ -n "$nft" ] && ip netns exec "$ns2" $nft -f - <<EOF table inet t { chain c { @@ -89,6 +95,11 @@ ipt_zero_rule() { # (command) [ -n "$1" ] || return 0 ip netns exec "$ns2" "$1" -t raw -vS | grep -q -- "-m rpfilter -c 0 0" } +ipt_zero_reverse_rule() { # (command) + [ -n "$1" ] || return 0 + ip netns exec "$ns2" "$1" -t raw -vS | \ + grep -q -- "-m rpfilter --invert -c 0 0" +} nft_zero_rule() { # (family) [ -n "$nft" ] || return 0 ip netns exec "$ns2" "$nft" list chain inet t c | \ @@ -101,8 +112,7 @@ netns_ping() { # (netns, args...) ip netns exec "$netns" ping -q -c 1 -W 1 "$@" >/dev/null } -testrun() { - # clear counters first +clear_counters() { [ -n "$iptables" ] && ip netns exec "$ns2" "$iptables" -t raw -Z [ -n "$ip6tables" ] && ip netns exec "$ns2" "$ip6tables" -t raw -Z if [ -n "$nft" ]; then @@ -111,6 +121,10 @@ testrun() { ip netns exec "$ns2" $nft -s list table inet t; ) | ip netns exec "$ns2" $nft -f - fi +} + +testrun() { + clear_counters # test 1: martian traffic should fail rpfilter matches netns_ping "$ns1" -I v0 192.168.42.1 && \ @@ -120,9 +134,13 @@ testrun() { ipt_zero_rule "$iptables" || die "iptables matched martian" ipt_zero_rule "$ip6tables" || die "ip6tables matched martian" + ipt_zero_reverse_rule "$iptables" && die "iptables not matched martian" + ipt_zero_reverse_rule "$ip6tables" && die "ip6tables not matched martian" nft_zero_rule ip || die "nft IPv4 matched martian" nft_zero_rule ip6 || die "nft IPv6 matched martian" + clear_counters + # test 2: rpfilter match should pass for regular traffic netns_ping "$ns1" 192.168.23.1 || \ die "regular ping 192.168.23.1 failed" @@ -131,6 +149,8 @@ testrun() { ipt_zero_rule "$iptables" && die "iptables match not effective" ipt_zero_rule "$ip6tables" && die "ip6tables match not effective" + ipt_zero_reverse_rule "$iptables" || die "iptables match over-effective" + ipt_zero_reverse_rule "$ip6tables" || die "ip6tables match over-effective" nft_zero_rule ip && die "nft IPv4 match not effective" nft_zero_rule ip6 && die "nft IPv6 match not effective" |