diff options
37 files changed, 266 insertions, 149 deletions
@@ -265,6 +265,7 @@ Vinod Koul <vkoul@kernel.org> <vkoul@infradead.org> Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com> Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com> Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com> +Vivien Didelot <vivien.didelot@gmail.com> <vivien.didelot@savoirfairelinux.com> Vlad Dogaru <ddvlad@gmail.com> <vlad.dogaru@intel.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@virtuozzo.com> Vladimir Davydov <vdavydov.dev@gmail.com> <vdavydov@parallels.com> diff --git a/MAINTAINERS b/MAINTAINERS index b908e56639e3..e34488f7baae 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -13709,6 +13709,15 @@ L: linux-arm-msm@vger.kernel.org S: Maintained F: drivers/iommu/qcom_iommu.c +QUALCOMM RMNET DRIVER +M: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org> +M: Sean Tranchetti <stranche@codeaurora.org> +L: netdev@vger.kernel.org +S: Maintained +F: drivers/net/ethernet/qualcomm/rmnet/ +F: Documentation/networking/device_drivers/qualcomm/rmnet.txt +F: include/linux/if_rmnet.h + QUALCOMM TSENS THERMAL DRIVER M: Amit Kucheria <amit.kucheria@linaro.org> L: linux-pm@vger.kernel.org diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 041aa9649dfc..48d5ec770b94 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2272,9 +2272,6 @@ static void bond_miimon_commit(struct bonding *bond) } else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { /* make it immediately active */ bond_set_active_slave(slave); - } else if (slave != primary) { - /* prevent it from being the active one */ - bond_set_backup_slave(slave); } slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 36828f210030..edacacfc9365 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -347,7 +347,7 @@ static void b53_set_forwarding(struct b53_device *dev, int enable) * frames should be flooded or not. */ b53_read8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, &mgmt); - mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN; + mgmt |= B53_UC_FWD_EN | B53_MC_FWD_EN | B53_IPMC_FWD_EN; b53_write8(dev, B53_CTRL_PAGE, B53_IP_MULTICAST_CTRL, mgmt); } @@ -526,6 +526,8 @@ int b53_enable_port(struct dsa_switch *ds, int port, struct phy_device *phy) cpu_port = dsa_to_port(ds, port)->cpu_dp->index; + b53_br_egress_floods(ds, port, true, true); + if (dev->ops->irq_enable) ret = dev->ops->irq_enable(dev, port); if (ret) @@ -641,6 +643,8 @@ static void b53_enable_cpu_port(struct b53_device *dev, int port) b53_write8(dev, B53_CTRL_PAGE, B53_PORT_CTRL(port), port_ctrl); b53_brcm_hdr_setup(dev->ds, port); + + b53_br_egress_floods(dev->ds, port, true, true); } static void b53_enable_mib(struct b53_device *dev) @@ -1821,19 +1825,26 @@ int b53_br_egress_floods(struct dsa_switch *ds, int port, struct b53_device *dev = ds->priv; u16 uc, mc; - b53_read16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, &uc); + b53_read16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, &uc); if (unicast) uc |= BIT(port); else uc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_UC_FWD_EN, uc); + b53_write16(dev, B53_CTRL_PAGE, B53_UC_FLOOD_MASK, uc); + + b53_read16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, &mc); + if (multicast) + mc |= BIT(port); + else + mc &= ~BIT(port); + b53_write16(dev, B53_CTRL_PAGE, B53_MC_FLOOD_MASK, mc); - b53_read16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, &mc); + b53_read16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, &mc); if (multicast) mc |= BIT(port); else mc &= ~BIT(port); - b53_write16(dev, B53_CTRL_PAGE, B53_MC_FWD_EN, mc); + b53_write16(dev, B53_CTRL_PAGE, B53_IPMC_FLOOD_MASK, mc); return 0; diff --git a/drivers/net/dsa/ocelot/Kconfig b/drivers/net/dsa/ocelot/Kconfig index 0031ca814346..6f9804093150 100644 --- a/drivers/net/dsa/ocelot/Kconfig +++ b/drivers/net/dsa/ocelot/Kconfig @@ -2,6 +2,7 @@ config NET_DSA_MSCC_FELIX tristate "Ocelot / Felix Ethernet switch support" depends on NET_DSA && PCI + depends on NET_VENDOR_MICROSEMI select MSCC_OCELOT_SWITCH select NET_DSA_TAG_OCELOT help diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index 8b08cb18e363..3f63ffd7561b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -1109,7 +1109,7 @@ static inline u8 bnx2x_get_path_func_num(struct bnx2x *bp) for (i = 0; i < E1H_FUNC_MAX / 2; i++) { u32 func_config = MF_CFG_RD(bp, - func_mf_config[BP_PORT(bp) + 2 * i]. + func_mf_config[BP_PATH(bp) + 2 * i]. config); func_num += ((func_config & FUNC_MF_CFG_FUNC_HIDE) ? 0 : 1); diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index 192ff8d5da32..cff64e43bdd8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9976,10 +9976,18 @@ static void bnx2x_recovery_failed(struct bnx2x *bp) */ static void bnx2x_parity_recover(struct bnx2x *bp) { - bool global = false; u32 error_recovered, error_unrecovered; - bool is_parity; + bool is_parity, global = false; +#ifdef CONFIG_BNX2X_SRIOV + int vf_idx; + + for (vf_idx = 0; vf_idx < bp->requested_nr_virtfn; vf_idx++) { + struct bnx2x_virtf *vf = BP_VF(bp, vf_idx); + if (vf) + vf->state = VF_LOST; + } +#endif DP(NETIF_MSG_HW, "Handling parity\n"); while (1) { switch (bp->recovery_state) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h index b6ebd92ec565..3a716c015415 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.h @@ -139,6 +139,7 @@ struct bnx2x_virtf { #define VF_ACQUIRED 1 /* VF acquired, but not initialized */ #define VF_ENABLED 2 /* VF Enabled */ #define VF_RESET 3 /* VF FLR'd, pending cleanup */ +#define VF_LOST 4 /* Recovery while VFs are loaded */ bool flr_clnup_stage; /* true during flr cleanup */ bool malicious; /* true if FW indicated so, until FLR */ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c index 0752b7fa4d9c..ea0e9394f898 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c @@ -2107,6 +2107,18 @@ static void bnx2x_vf_mbx_request(struct bnx2x *bp, struct bnx2x_virtf *vf, { int i; + if (vf->state == VF_LOST) { + /* Just ack the FW and return if VFs are lost + * in case of parity error. VFs are supposed to be timedout + * on waiting for PF response. + */ + DP(BNX2X_MSG_IOV, + "VF 0x%x lost, not handling the request\n", vf->abs_vfid); + + storm_memset_vf_mbx_ack(bp, vf->abs_vfid); + return; + } + /* check if tlv type is known */ if (bnx2x_tlv_supported(mbx->first_tlv.tl.type)) { /* Lock the per vf op mutex and note the locker's identity. diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index a754903b27ee..c779f9cf8822 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -6190,7 +6190,7 @@ static void bnxt_hwrm_set_coal_params(struct bnxt *bp, tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks_irq); val = clamp_t(u16, tmr, 1, coal_cap->cmpl_aggr_dma_tmr_during_int_max); - req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr); + req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(val); req->enables |= cpu_to_le16(BNXT_COAL_CMPL_AGGR_TMR_DURING_INT_ENABLE); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index 93868dca186a..aca9f7a20a2a 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3048,6 +3048,9 @@ static int sge_queue_entries(const struct adapter *adap) int tot_uld_entries = 0; int i; + if (!is_uld(adap)) + goto lld_only; + mutex_lock(&uld_mutex); for (i = 0; i < CXGB4_TX_MAX; i++) tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i); @@ -3058,6 +3061,7 @@ static int sge_queue_entries(const struct adapter *adap) } mutex_unlock(&uld_mutex); +lld_only: return DIV_ROUND_UP(adap->sge.ethqsets, 4) + (adap->sge.eohw_txq ? DIV_ROUND_UP(adap->sge.eoqsets, 4) : 0) + tot_uld_entries + diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index a8f4c69252ff..2814b96751b4 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -576,6 +576,8 @@ static int gmac_setup_txqs(struct net_device *netdev) if (port->txq_dma_base & ~DMA_Q_BASE_MASK) { dev_warn(geth->dev, "TX queue base is not aligned\n"); + dma_free_coherent(geth->dev, len * sizeof(*desc_ring), + desc_ring, port->txq_dma_base); kfree(skb_tab); return -ENOMEM; } diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index c90080781924..830791ab4619 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -184,7 +184,7 @@ static int ibmvnic_wait_for_completion(struct ibmvnic_adapter *adapter, netdev_err(netdev, "Device down!\n"); return -ENODEV; } - if (retry--) + if (!retry--) break; if (wait_for_completion_timeout(comp_done, div_timeout)) return 0; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 62dc2f362a16..14e372cda7f4 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -3680,7 +3680,7 @@ static int mvpp2_open(struct net_device *dev) valid = true; } - if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) { + if (priv->hw_version == MVPP22 && port->link_irq) { err = request_irq(port->link_irq, mvpp2_link_status_isr, 0, dev->name, port); if (err) { diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index a46f4189fde3..bf98e0fa7d8b 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -63,6 +63,7 @@ config TI_CPSW_SWITCHDEV tristate "TI CPSW Switch Support with switchdev" depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST depends on NET_SWITCHDEV + select PAGE_POOL select TI_DAVINCI_MDIO select MFD_SYSCON select REGMAP diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index d34df8e5cf94..ecf776ad8689 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -5,6 +5,7 @@ obj-$(CONFIG_TI_CPSW) += cpsw-common.o obj-$(CONFIG_TI_DAVINCI_EMAC) += cpsw-common.o +obj-$(CONFIG_TI_CPSW_SWITCHDEV) += cpsw-common.o obj-$(CONFIG_TLAN) += tlan.o obj-$(CONFIG_CPMAC) += cpmac.o diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index ecfe26215935..e5b7d6d2286e 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -38,7 +38,6 @@ struct pdp_ctx { struct hlist_node hlist_addr; union { - u64 tid; struct { u64 tid; u16 flow; @@ -641,9 +640,16 @@ static void gtp_link_setup(struct net_device *dev) } static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize); -static void gtp_hashtable_free(struct gtp_dev *gtp); static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]); +static void gtp_destructor(struct net_device *dev) +{ + struct gtp_dev *gtp = netdev_priv(dev); + + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); +} + static int gtp_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -661,10 +667,13 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, if (err < 0) return err; - if (!data[IFLA_GTP_PDP_HASHSIZE]) + if (!data[IFLA_GTP_PDP_HASHSIZE]) { hashsize = 1024; - else + } else { hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]); + if (!hashsize) + hashsize = 1024; + } err = gtp_hashtable_new(gtp, hashsize); if (err < 0) @@ -678,13 +687,15 @@ static int gtp_newlink(struct net *src_net, struct net_device *dev, gn = net_generic(dev_net(dev), gtp_net_id); list_add_rcu(>p->list, &gn->gtp_dev_list); + dev->priv_destructor = gtp_destructor; netdev_dbg(dev, "registered new GTP interface\n"); return 0; out_hashtable: - gtp_hashtable_free(gtp); + kfree(gtp->addr_hash); + kfree(gtp->tid_hash); out_encap: gtp_encap_disable(gtp); return err; @@ -693,8 +704,13 @@ out_encap: static void gtp_dellink(struct net_device *dev, struct list_head *head) { struct gtp_dev *gtp = netdev_priv(dev); + struct pdp_ctx *pctx; + int i; + + for (i = 0; i < gtp->hash_size; i++) + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) + pdp_context_delete(pctx); - gtp_hashtable_free(gtp); list_del_rcu(>p->list); unregister_netdevice_queue(dev, head); } @@ -772,20 +788,6 @@ err1: return -ENOMEM; } -static void gtp_hashtable_free(struct gtp_dev *gtp) -{ - struct pdp_ctx *pctx; - int i; - - for (i = 0; i < gtp->hash_size; i++) - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) - pdp_context_delete(pctx); - - synchronize_rcu(); - kfree(gtp->addr_hash); - kfree(gtp->tid_hash); -} - static struct sock *gtp_encap_enable_socket(int fd, int type, struct gtp_dev *gtp) { @@ -926,24 +928,31 @@ static void ipv4_pdp_fill(struct pdp_ctx *pctx, struct genl_info *info) } } -static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, - struct genl_info *info) +static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk, + struct genl_info *info) { + struct pdp_ctx *pctx, *pctx_tid = NULL; struct net_device *dev = gtp->dev; u32 hash_ms, hash_tid = 0; - struct pdp_ctx *pctx; + unsigned int version; bool found = false; __be32 ms_addr; ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]); hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size; + version = nla_get_u32(info->attrs[GTPA_VERSION]); - hlist_for_each_entry_rcu(pctx, >p->addr_hash[hash_ms], hlist_addr) { - if (pctx->ms_addr_ip4.s_addr == ms_addr) { - found = true; - break; - } - } + pctx = ipv4_pdp_find(gtp, ms_addr); + if (pctx) + found = true; + if (version == GTP_V0) + pctx_tid = gtp0_pdp_find(gtp, + nla_get_u64(info->attrs[GTPA_TID])); + else if (version == GTP_V1) + pctx_tid = gtp1_pdp_find(gtp, + nla_get_u32(info->attrs[GTPA_I_TEI])); + if (pctx_tid) + found = true; if (found) { if (info->nlhdr->nlmsg_flags & NLM_F_EXCL) @@ -951,6 +960,11 @@ static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk, if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + if (pctx && pctx_tid) + return -EEXIST; + if (!pctx) + pctx = pctx_tid; + ipv4_pdp_fill(pctx, info); if (pctx->gtp_version == GTP_V0) @@ -1074,7 +1088,7 @@ static int gtp_genl_new_pdp(struct sk_buff *skb, struct genl_info *info) goto out_unlock; } - err = ipv4_pdp_add(gtp, sk, info); + err = gtp_pdp_add(gtp, sk, info); out_unlock: rcu_read_unlock(); @@ -1232,43 +1246,46 @@ static int gtp_genl_dump_pdp(struct sk_buff *skb, struct netlink_callback *cb) { struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp; + int i, j, bucket = cb->args[0], skip = cb->args[1]; struct net *net = sock_net(skb->sk); - struct gtp_net *gn = net_generic(net, gtp_net_id); - unsigned long tid = cb->args[1]; - int i, k = cb->args[0], ret; struct pdp_ctx *pctx; + struct gtp_net *gn; + + gn = net_generic(net, gtp_net_id); if (cb->args[4]) return 0; + rcu_read_lock(); list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) { if (last_gtp && last_gtp != gtp) continue; else last_gtp = NULL; - for (i = k; i < gtp->hash_size; i++) { - hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], hlist_tid) { - if (tid && tid != pctx->u.tid) - continue; - else - tid = 0; - - ret = gtp_genl_fill_info(skb, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - cb->nlh->nlmsg_type, pctx); - if (ret < 0) { + for (i = bucket; i < gtp->hash_size; i++) { + j = 0; + hlist_for_each_entry_rcu(pctx, >p->tid_hash[i], + hlist_tid) { + if (j >= skip && + gtp_genl_fill_info(skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + cb->nlh->nlmsg_type, pctx)) { cb->args[0] = i; - cb->args[1] = pctx->u.tid; + cb->args[1] = j; cb->args[2] = (unsigned long)gtp; goto out; } + j++; } + skip = 0; } + bucket = 0; } cb->args[4] = 1; out: + rcu_read_unlock(); return skb->len; } diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c index 23281aeeb222..71d6629e65c9 100644 --- a/drivers/net/hamradio/6pack.c +++ b/drivers/net/hamradio/6pack.c @@ -654,10 +654,10 @@ static void sixpack_close(struct tty_struct *tty) { struct sixpack *sp; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); sp = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!sp) return; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index c5bfa19ddb93..deef14215110 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -773,10 +773,10 @@ static void mkiss_close(struct tty_struct *tty) { struct mkiss *ax; - write_lock_bh(&disc_data_lock); + write_lock_irq(&disc_data_lock); ax = tty->disc_data; tty->disc_data = NULL; - write_unlock_bh(&disc_data_lock); + write_unlock_irq(&disc_data_lock); if (!ax) return; diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index 206b4e77eaf0..05bc5ec8bb1f 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -1171,6 +1171,9 @@ int rndis_set_subchannel(struct net_device *ndev, wait_event(nvdev->subchan_open, atomic_read(&nvdev->open_chn) == nvdev->num_chn); + for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) + ndev_ctx->tx_table[i] = i % nvdev->num_chn; + /* ignore failures from setting rss parameters, still have channels */ if (dev_info) rndis_filter_set_rss_param(rdev, dev_info->rss_key); @@ -1180,9 +1183,6 @@ int rndis_set_subchannel(struct net_device *ndev, netif_set_real_num_tx_queues(ndev, nvdev->num_chn); netif_set_real_num_rx_queues(ndev, nvdev->num_chn); - for (i = 0; i < VRSS_SEND_TAB_SIZE; i++) - ndev_ctx->tx_table[i] = i % nvdev->num_chn; - return 0; } diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 9a616d6bc4eb..1585eebb73fe 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -442,8 +442,7 @@ static void phylink_mac_link_up(struct phylink *pl, pl->cur_interface = link_state.interface; pl->ops->mac_link_up(pl->config, pl->link_an_mode, - pl->phy_state.interface, - pl->phydev); + pl->cur_interface, pl->phydev); if (ndev) netif_carrier_on(ndev); diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index d7bf1918ca62..f940dc6485e5 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -511,7 +511,7 @@ static int lan78xx_read_stats(struct lan78xx_net *dev, } } else { netdev_warn(dev->net, - "Failed to read stat ret = 0x%x", ret); + "Failed to read stat ret = %d", ret); } kfree(stats); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 68dd7bb07ca6..f15ba3de6195 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -628,18 +628,6 @@ err: static void xenvif_disconnect_queue(struct xenvif_queue *queue) { - if (queue->tx_irq) { - unbind_from_irqhandler(queue->tx_irq, queue); - if (queue->tx_irq == queue->rx_irq) - queue->rx_irq = 0; - queue->tx_irq = 0; - } - - if (queue->rx_irq) { - unbind_from_irqhandler(queue->rx_irq, queue); - queue->rx_irq = 0; - } - if (queue->task) { kthread_stop(queue->task); queue->task = NULL; @@ -655,6 +643,18 @@ static void xenvif_disconnect_queue(struct xenvif_queue *queue) queue->napi.poll = NULL; } + if (queue->tx_irq) { + unbind_from_irqhandler(queue->tx_irq, queue); + if (queue->tx_irq == queue->rx_irq) + queue->rx_irq = 0; + queue->tx_irq = 0; + } + + if (queue->rx_irq) { + unbind_from_irqhandler(queue->rx_irq, queue); + queue->rx_irq = 0; + } + xenvif_unmap_frontend_data_rings(queue); } diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig index b45d2b86d8ca..b0d1b8d264fa 100644 --- a/drivers/ptp/Kconfig +++ b/drivers/ptp/Kconfig @@ -121,7 +121,7 @@ config PTP_1588_CLOCK_KVM config PTP_1588_CLOCK_IDTCM tristate "IDT CLOCKMATRIX as PTP clock" - depends on PTP_1588_CLOCK + depends on PTP_1588_CLOCK && I2C default n help This driver adds support for using IDT CLOCKMATRIX(TM) as a PTP diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index bc8206a8f30e..61974c4c566b 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -101,6 +101,43 @@ static inline void hlist_nulls_add_head_rcu(struct hlist_nulls_node *n, } /** + * hlist_nulls_add_tail_rcu + * @n: the element to add to the hash list. + * @h: the list to add to. + * + * Description: + * Adds the specified element to the specified hlist_nulls, + * while permitting racing traversals. + * + * The caller must take whatever precautions are necessary + * (such as holding appropriate locks) to avoid racing + * with another list-mutation primitive, such as hlist_nulls_add_head_rcu() + * or hlist_nulls_del_rcu(), running on this same list. + * However, it is perfectly legal to run concurrently with + * the _rcu list-traversal primitives, such as + * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency + * problems on Alpha CPUs. Regardless of the type of CPU, the + * list-traversal primitive must be guarded by rcu_read_lock(). + */ +static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, + struct hlist_nulls_head *h) +{ + struct hlist_nulls_node *i, *last = NULL; + + /* Note: write side code, so rcu accessors are not needed. */ + for (i = h->first; !is_a_nulls(i); i = i->next) + last = i; + + if (last) { + n->next = last->next; + n->pprev = &last->next; + rcu_assign_pointer(hlist_next_rcu(last), n); + } else { + hlist_nulls_add_head_rcu(n, h); + } +} + +/** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_nulls_node to use as a loop cursor. diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index af2b4c065a04..d0019d3395cf 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -103,13 +103,19 @@ struct inet_bind_hashbucket { struct hlist_head chain; }; -/* - * Sockets can be hashed in established or listening table +/* Sockets can be hashed in established or listening table. + * We must use different 'nulls' end-of-chain value for all hash buckets : + * A socket might transition from ESTABLISH to LISTEN state without + * RCU grace period. A lookup in ehash table needs to handle this case. */ +#define LISTENING_NULLS_BASE (1U << 29) struct inet_listen_hashbucket { spinlock_t lock; unsigned int count; - struct hlist_head head; + union { + struct hlist_head head; + struct hlist_nulls_head nulls_head; + }; }; /* This is for listening sockets, thus all sockets which possess wildcards. */ diff --git a/include/net/sock.h b/include/net/sock.h index 87d54ef57f00..04c274a20620 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -722,6 +722,11 @@ static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_h hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list); } +static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list) +{ + hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list); +} + static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list) { sock_hold(sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 86b9a8766648..e460ea7f767b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1766,9 +1766,18 @@ static inline bool tcp_skb_is_last(const struct sock *sk, return skb_queue_is_last(&sk->sk_write_queue, skb); } +/** + * tcp_write_queue_empty - test if any payload (or FIN) is available in write queue + * @sk: socket + * + * Since the write queue can have a temporary empty skb in it, + * we must not use "return skb_queue_empty(&sk->sk_write_queue)" + */ static inline bool tcp_write_queue_empty(const struct sock *sk) { - return skb_queue_empty(&sk->sk_write_queue); + const struct tcp_sock *tp = tcp_sk(sk); + + return tp->write_seq == tp->snd_nxt; } static inline bool tcp_rtx_queue_empty(const struct sock *sk) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index af154977904c..f11e997e517b 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -911,11 +911,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 83fb00153018..2bbaaf0c7176 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 8a39ee794891..716938313a32 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1087,8 +1087,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1419,8 +1418,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 92282f98dc82..1c7326e04f9b 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2147,13 +2147,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2161,9 +2162,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b184f03d7437..36902d08473e 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2438,6 +2438,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -3121,7 +3129,7 @@ void sk_forced_mem_schedule(struct sock *sk, int size) */ void tcp_send_fin(struct sock *sk) { - struct sk_buff *skb, *tskb = tcp_write_queue_tail(sk); + struct sk_buff *skb, *tskb, *tail = tcp_write_queue_tail(sk); struct tcp_sock *tp = tcp_sk(sk); /* Optimization, tack on the FIN if we have one skb in write queue and @@ -3129,6 +3137,7 @@ void tcp_send_fin(struct sock *sk) * Note: in the latter case, FIN packet will be sent after a timeout, * as TCP stack thinks it has already been transmitted. */ + tskb = tail; if (!tskb && tcp_under_memory_pressure(sk)) tskb = skb_rb_last(&sk->tcp_rtx_queue); @@ -3136,7 +3145,7 @@ void tcp_send_fin(struct sock *sk) TCP_SKB_CB(tskb)->tcp_flags |= TCPHDR_FIN; TCP_SKB_CB(tskb)->end_seq++; tp->write_seq++; - if (tcp_write_queue_empty(sk)) { + if (!tail) { /* This means tskb was already sent. * Pretend we included the FIN on previous transmit. * We need to set tp->snd_nxt to the value it would have diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 98d82305d6de..39d861d00377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b997072c72e5..cee5bf4a9bb9 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -857,6 +857,8 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out; sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1721,8 +1723,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1730,6 +1730,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1741,15 +1743,14 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1758,7 +1759,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1769,6 +1770,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index e5ea29c6bca7..6abec3fc81d1 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -34,6 +34,9 @@ virtio_transport_get_ops(struct vsock_sock *vsk) { const struct vsock_transport *t = vsock_core_get_transport(vsk); + if (WARN_ON(!t)) + return NULL; + return container_of(t, struct virtio_transport, transport); } @@ -161,15 +164,25 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +/* This function can only be used on connecting/connected sockets, + * since a socket assigned to a transport is required. + * + * Do not use on listener sockets! + */ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt_info *info) { u32 src_cid, src_port, dst_cid, dst_port; + const struct virtio_transport *t_ops; struct virtio_vsock_sock *vvs; struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; - src_cid = virtio_transport_get_ops(vsk)->transport.get_local_cid(); + t_ops = virtio_transport_get_ops(vsk); + if (unlikely(!t_ops)) + return -EFAULT; + + src_cid = t_ops->transport.get_local_cid(); src_port = vsk->local_addr.svm_port; if (!info->remote_cid) { dst_cid = vsk->remote_addr.svm_cid; @@ -202,7 +215,7 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, virtio_transport_inc_tx_pkt(vvs, pkt); - return virtio_transport_get_ops(vsk)->send_pkt(pkt); + return t_ops->send_pkt(pkt); } static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs, @@ -1021,18 +1034,18 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, int ret; if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -EINVAL; } if (sk_acceptq_is_full(sk)) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } child = vsock_create_connected(sk); if (!child) { - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); return -ENOMEM; } @@ -1054,7 +1067,7 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, */ if (ret || vchild->transport != &t->transport) { release_sock(child); - virtio_transport_reset(vsk, pkt); + virtio_transport_reset_no_sock(t, pkt); sock_put(child); return ret; } diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 13e5ef615026..0ea44d975b6c 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -722,34 +722,6 @@ TEST_F(tls, recv_lowat) EXPECT_EQ(memcmp(send_mem, recv_mem + 10, 5), 0); } -TEST_F(tls, recv_rcvbuf) -{ - char send_mem[4096]; - char recv_mem[4096]; - int rcv_buf = 1024; - - memset(send_mem, 0x1c, sizeof(send_mem)); - - EXPECT_EQ(setsockopt(self->cfd, SOL_SOCKET, SO_RCVBUF, - &rcv_buf, sizeof(rcv_buf)), 0); - - EXPECT_EQ(send(self->fd, send_mem, 512, 0), 512); - memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), 512); - EXPECT_EQ(memcmp(send_mem, recv_mem, 512), 0); - - if (self->notls) - return; - - EXPECT_EQ(send(self->fd, send_mem, 4096, 0), 4096); - memset(recv_mem, 0, sizeof(recv_mem)); - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1); - EXPECT_EQ(errno, EMSGSIZE); - - EXPECT_EQ(recv(self->cfd, recv_mem, sizeof(recv_mem), 0), -1); - EXPECT_EQ(errno, EMSGSIZE); -} - TEST_F(tls, bidir) { char const *test_str = "test_read"; |