diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-02-21 20:59:51 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-02-21 20:59:51 +0100 |
| commit | 3dc55dba67231fc22352483f5ca737df96cdc1e6 (patch) | |
| tree | 5eec1f5ce42822cb744313ec394b761fab0f7ed6 | |
| parent | Merge branch 'akpm' (patches from Andrew) (diff) | |
| parent | Merge branch 'bnxt_en-shutdown-and-kexec-kdump-related-fixes' (diff) | |
| download | linux-3dc55dba67231fc22352483f5ca737df96cdc1e6.tar.xz linux-3dc55dba67231fc22352483f5ca737df96cdc1e6.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from David Miller:
1) Limit xt_hashlimit hash table size to avoid OOM or hung tasks, from
Cong Wang.
2) Fix deadlock in xsk by publishing global consumer pointers when NAPI
is finished, from Magnus Karlsson.
3) Set table field properly to RT_TABLE_COMPAT when necessary, from
Jethro Beekman.
4) NLA_STRING attributes are not necessary NULL terminated, deal wiht
that in IFLA_ALT_IFNAME. From Eric Dumazet.
5) Fix checksum handling in atlantic driver, from Dmitry Bezrukov.
6) Handle mtu==0 devices properly in wireguard, from Jason A.
Donenfeld.
7) Fix several lockdep warnings in bonding, from Taehee Yoo.
8) Fix cls_flower port blocking, from Jason Baron.
9) Sanitize internal map names in libbpf, from Toke Høiland-Jørgensen.
10) Fix RDMA race in qede driver, from Michal Kalderon.
11) Fix several false lockdep warnings by adding conditions to
list_for_each_entry_rcu(), from Madhuparna Bhowmik.
12) Fix sleep in atomic in mlx5 driver, from Huy Nguyen.
13) Fix potential deadlock in bpf_map_do_batch(), from Yonghong Song.
14) Hey, variables declared in switch statement before any case
statements are not initialized. I learn something every day. Get
rids of this stuff in several parts of the networking, from Kees
Cook.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (99 commits)
bnxt_en: Issue PCIe FLR in kdump kernel to cleanup pending DMAs.
bnxt_en: Improve device shutdown method.
net: netlink: cap max groups which will be considered in netlink_bind()
net: thunderx: workaround BGX TX Underflow issue
ionic: fix fw_status read
net: disable BRIDGE_NETFILTER by default
net: macb: Properly handle phylink on at91rm9200
s390/qeth: fix off-by-one in RX copybreak check
s390/qeth: don't warn for napi with 0 budget
s390/qeth: vnicc Fix EOPNOTSUPP precedence
openvswitch: Distribute switch variables for initialization
net: ip6_gre: Distribute switch variables for initialization
net: core: Distribute switch variables for initialization
udp: rehash on disconnect
net/tls: Fix to avoid gettig invalid tls record
bpf: Fix a potential deadlock with bpf_map_do_batch
bpf: Do not grab the bucket spinlock by default on htab batch ops
ice: Wait for VF to be reset/ready before configuration
ice: Don't tell the OS that link is going down
ice: Don't reject odd values of usecs set by user
...
104 files changed, 1132 insertions, 506 deletions
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 48d5ec770b94..d10805e5e623 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3526,6 +3526,47 @@ static void bond_fold_stats(struct rtnl_link_stats64 *_res, } } +#ifdef CONFIG_LOCKDEP +static int bond_get_lowest_level_rcu(struct net_device *dev) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int cur = 0, max = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + if (max <= cur) + max = cur; + break; + } + + if (!next) { + if (!cur) + return max; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return max; +} +#endif + static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 *stats) { @@ -3533,11 +3574,17 @@ static void bond_get_stats(struct net_device *bond_dev, struct rtnl_link_stats64 temp; struct list_head *iter; struct slave *slave; + int nest_level = 0; - spin_lock(&bond->stats_lock); - memcpy(stats, &bond->bond_stats, sizeof(*stats)); rcu_read_lock(); +#ifdef CONFIG_LOCKDEP + nest_level = bond_get_lowest_level_rcu(bond_dev); +#endif + + spin_lock_nested(&bond->stats_lock, nest_level); + memcpy(stats, &bond->bond_stats, sizeof(*stats)); + bond_for_each_slave_rcu(bond, slave, iter) { const struct rtnl_link_stats64 *new = dev_get_stats(slave->dev, &temp); @@ -3547,10 +3594,10 @@ static void bond_get_stats(struct net_device *bond_dev, /* save off the slave stats for the next run */ memcpy(&slave->slave_stats, new, sizeof(*new)); } - rcu_read_unlock(); memcpy(&bond->bond_stats, stats, sizeof(*stats)); spin_unlock(&bond->stats_lock); + rcu_read_unlock(); } static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd) @@ -3640,6 +3687,8 @@ static int bond_do_ioctl(struct net_device *bond_dev, struct ifreq *ifr, int cmd case BOND_RELEASE_OLD: case SIOCBONDRELEASE: res = bond_release(bond_dev, slave_dev); + if (!res) + netdev_update_lockdep_key(slave_dev); break; case BOND_SETHWADDR_OLD: case SIOCBONDSETHWADDR: diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index ddb3916d3506..215c10923289 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -1398,6 +1398,8 @@ static int bond_option_slaves_set(struct bonding *bond, case '-': slave_dbg(bond->dev, dev, "Releasing interface\n"); ret = bond_release(bond->dev, dev); + if (!ret) + netdev_update_lockdep_key(dev); break; default: diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 449a22172e07..1a69286daa8d 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -1366,6 +1366,9 @@ void b53_vlan_add(struct dsa_switch *ds, int port, b53_get_vlan_entry(dev, vid, vl); + if (vid == 0 && vid == b53_default_pvid(dev)) + untagged = true; + vl->members |= BIT(port); if (untagged && !dsa_is_cpu_port(ds, port)) vl->untag |= BIT(port); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c index a1f99bef4a68..7b55633d2cb9 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c @@ -722,6 +722,11 @@ static int aq_ethtool_set_priv_flags(struct net_device *ndev, u32 flags) if (flags & ~AQ_PRIV_FLAGS_MASK) return -EOPNOTSUPP; + if (hweight32((flags | priv_flags) & AQ_HW_LOOPBACK_MASK) > 1) { + netdev_info(ndev, "Can't enable more than one loopback simultaneously\n"); + return -EINVAL; + } + cfg->priv_flags = flags; if ((priv_flags ^ flags) & BIT(AQ_HW_LOOPBACK_DMA_NET)) { diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c index 6102251bb909..03ff92bc4a7f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_filters.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_filters.c @@ -163,7 +163,7 @@ aq_check_approve_fvlan(struct aq_nic_s *aq_nic, } if ((aq_nic->ndev->features & NETIF_F_HW_VLAN_CTAG_FILTER) && - (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci), + (!test_bit(be16_to_cpu(fsp->h_ext.vlan_tci) & VLAN_VID_MASK, aq_nic->active_vlans))) { netdev_err(aq_nic->ndev, "ethtool: unknown vlan-id specified"); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h index cc70c606b6ef..251767c31f7e 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h @@ -337,6 +337,8 @@ struct aq_fw_ops { void (*enable_ptp)(struct aq_hw_s *self, int enable); + void (*adjust_ptp)(struct aq_hw_s *self, uint64_t adj); + int (*set_eee_rate)(struct aq_hw_s *self, u32 speed); int (*get_eee_rate)(struct aq_hw_s *self, u32 *rate, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c index c85e3e29012c..e95f6a6bef73 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c @@ -533,8 +533,10 @@ unsigned int aq_nic_map_skb(struct aq_nic_s *self, struct sk_buff *skb, dx_buff->len, DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) + if (unlikely(dma_mapping_error(aq_nic_get_dev(self), dx_buff->pa))) { + ret = 0; goto exit; + } first = dx_buff; dx_buff->len_pkt = skb->len; @@ -655,10 +657,6 @@ int aq_nic_xmit(struct aq_nic_s *self, struct sk_buff *skb) if (likely(frags)) { err = self->aq_hw_ops->hw_ring_tx_xmit(self->aq_hw, ring, frags); - if (err >= 0) { - ++ring->stats.tx.packets; - ring->stats.tx.bytes += skb->len; - } } else { err = NETDEV_TX_BUSY; } diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c index 6b27af0db499..78b6f3248756 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_pci_func.c @@ -359,7 +359,8 @@ static int aq_suspend_common(struct device *dev, bool deep) netif_device_detach(nic->ndev); netif_tx_stop_all_queues(nic->ndev); - aq_nic_stop(nic); + if (netif_running(nic->ndev)) + aq_nic_stop(nic); if (deep) { aq_nic_deinit(nic, !nic->aq_hw->aq_nic_cfg->wol); @@ -375,7 +376,7 @@ static int atl_resume_common(struct device *dev, bool deep) { struct pci_dev *pdev = to_pci_dev(dev); struct aq_nic_s *nic; - int ret; + int ret = 0; nic = pci_get_drvdata(pdev); @@ -390,9 +391,11 @@ static int atl_resume_common(struct device *dev, bool deep) goto err_exit; } - ret = aq_nic_start(nic); - if (ret) - goto err_exit; + if (netif_running(nic->ndev)) { + ret = aq_nic_start(nic); + if (ret) + goto err_exit; + } netif_device_attach(nic->ndev); netif_tx_start_all_queues(nic->ndev); diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c index 951d86f8b66e..bae95a618560 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.c +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.c @@ -272,9 +272,12 @@ bool aq_ring_tx_clean(struct aq_ring_s *self) } } - if (unlikely(buff->is_eop)) - dev_kfree_skb_any(buff->skb); + if (unlikely(buff->is_eop)) { + ++self->stats.rx.packets; + self->stats.tx.bytes += buff->skb->len; + dev_kfree_skb_any(buff->skb); + } buff->pa = 0U; buff->eop_index = 0xffffU; self->sw_head = aq_ring_next_dx(self, self->sw_head); @@ -351,7 +354,8 @@ int aq_ring_rx_clean(struct aq_ring_s *self, err = 0; goto err_exit; } - if (buff->is_error || buff->is_cso_err) { + if (buff->is_error || + (buff->is_lro && buff->is_cso_err)) { buff_ = buff; do { next_ = buff_->next, diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h index 991e4d31b094..2c96f20f6289 100644 --- a/drivers/net/ethernet/aquantia/atlantic/aq_ring.h +++ b/drivers/net/ethernet/aquantia/atlantic/aq_ring.h @@ -78,7 +78,8 @@ struct __packed aq_ring_buff_s { u32 is_cleaned:1; u32 is_error:1; u32 is_vlan:1; - u32 rsvd3:4; + u32 is_lro:1; + u32 rsvd3:3; u16 eop_index; u16 rsvd4; }; diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c index ec041f78d063..d20d91cdece8 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c @@ -823,6 +823,8 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, } } + buff->is_lro = !!(HW_ATL_B0_RXD_WB_STAT2_RSCCNT & + rxd_wb->status); if (HW_ATL_B0_RXD_WB_STAT2_EOP & rxd_wb->status) { buff->len = rxd_wb->pkt_len % AQ_CFG_RX_FRAME_MAX; @@ -835,8 +837,7 @@ static int hw_atl_b0_hw_ring_rx_receive(struct aq_hw_s *self, rxd_wb->pkt_len > AQ_CFG_RX_FRAME_MAX ? AQ_CFG_RX_FRAME_MAX : rxd_wb->pkt_len; - if (HW_ATL_B0_RXD_WB_STAT2_RSCCNT & - rxd_wb->status) { + if (buff->is_lro) { /* LRO */ buff->next = rxd_wb->next_desc_ptr; ++ring->stats.rx.lro_packets; @@ -884,13 +885,16 @@ static int hw_atl_b0_hw_packet_filter_set(struct aq_hw_s *self, { struct aq_nic_cfg_s *cfg = self->aq_nic_cfg; unsigned int i = 0U; + u32 vlan_promisc; + u32 l2_promisc; - hw_atl_rpfl2promiscuous_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC)); + l2_promisc = IS_FILTER_ENABLED(IFF_PROMISC) || + !!(cfg->priv_flags & BIT(AQ_HW_LOOPBACK_DMA_NET)); + vlan_promisc = l2_promisc || cfg->is_vlan_force_promisc; - hw_atl_rpf_vlan_prom_mode_en_set(self, - IS_FILTER_ENABLED(IFF_PROMISC) || - cfg->is_vlan_force_promisc); + hw_atl_rpfl2promiscuous_mode_en_set(self, l2_promisc); + + hw_atl_rpf_vlan_prom_mode_en_set(self, vlan_promisc); hw_atl_rpfl2multicast_flr_en_set(self, IS_FILTER_ENABLED(IFF_ALLMULTI) && @@ -1161,6 +1165,8 @@ static int hw_atl_b0_adj_sys_clock(struct aq_hw_s *self, s64 delta) { self->ptp_clk_offset += delta; + self->aq_fw_ops->adjust_ptp(self, self->ptp_clk_offset); + return 0; } @@ -1211,7 +1217,7 @@ static int hw_atl_b0_gpio_pulse(struct aq_hw_s *self, u32 index, fwreq.ptp_gpio_ctrl.index = index; fwreq.ptp_gpio_ctrl.period = period; /* Apply time offset */ - fwreq.ptp_gpio_ctrl.start = start - self->ptp_clk_offset; + fwreq.ptp_gpio_ctrl.start = start; size = sizeof(fwreq.msg_id) + sizeof(fwreq.ptp_gpio_ctrl); return self->aq_fw_ops->send_fw_request(self, &fwreq, size); diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c index f547baa6c954..354705f9bc49 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c @@ -22,6 +22,7 @@ #define HW_ATL_MIF_ADDR 0x0208U #define HW_ATL_MIF_VAL 0x020CU +#define HW_ATL_MPI_RPC_ADDR 0x0334U #define HW_ATL_RPC_CONTROL_ADR 0x0338U #define HW_ATL_RPC_STATE_ADR 0x033CU @@ -53,15 +54,14 @@ enum mcp_area { }; static int hw_atl_utils_ver_match(u32 ver_expected, u32 ver_actual); - static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state); - static u32 hw_atl_utils_get_mpi_mbox_tid(struct aq_hw_s *self); static u32 hw_atl_utils_mpi_get_state(struct aq_hw_s *self); static u32 hw_atl_utils_mif_cmd_get(struct aq_hw_s *self); static u32 hw_atl_utils_mif_addr_get(struct aq_hw_s *self); static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self); +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self); int hw_atl_utils_initfw(struct aq_hw_s *self, const struct aq_fw_ops **fw_ops) { @@ -476,6 +476,10 @@ static int hw_atl_utils_init_ucp(struct aq_hw_s *self, self, self->mbox_addr, self->mbox_addr != 0U, 1000U, 10000U); + err = readx_poll_timeout_atomic(aq_fw1x_rpc_get, self, + self->rpc_addr, + self->rpc_addr != 0U, + 1000U, 100000U); return err; } @@ -531,6 +535,12 @@ int hw_atl_utils_fw_rpc_wait(struct aq_hw_s *self, self, fw.val, sw.tid == fw.tid, 1000U, 100000U); + if (err < 0) + goto err_exit; + + err = aq_hw_err_from_flags(self); + if (err < 0) + goto err_exit; if (fw.len == 0xFFFFU) { err = hw_atl_utils_fw_rpc_call(self, sw.len); @@ -1025,6 +1035,11 @@ static u32 hw_atl_utils_rpc_state_get(struct aq_hw_s *self) return aq_hw_read_reg(self, HW_ATL_RPC_STATE_ADR); } +static u32 aq_fw1x_rpc_get(struct aq_hw_s *self) +{ + return aq_hw_read_reg(self, HW_ATL_MPI_RPC_ADDR); +} + const struct aq_fw_ops aq_fw_1x_ops = { .init = hw_atl_utils_mpi_create, .deinit = hw_atl_fw1x_deinit, diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c index 97ebf849695f..77a4ed64830f 100644 --- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c +++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c @@ -30,6 +30,9 @@ #define HW_ATL_FW3X_EXT_CONTROL_ADDR 0x378 #define HW_ATL_FW3X_EXT_STATE_ADDR 0x37c +#define HW_ATL_FW3X_PTP_ADJ_LSW_ADDR 0x50a0 +#define HW_ATL_FW3X_PTP_ADJ_MSW_ADDR 0x50a4 + #define HW_ATL_FW2X_CAP_PAUSE BIT(CAPS_HI_PAUSE) #define HW_ATL_FW2X_CAP_ASYM_PAUSE BIT(CAPS_HI_ASYMMETRIC_PAUSE) #define HW_ATL_FW2X_CAP_SLEEP_PROXY BIT(CAPS_HI_SLEEP_PROXY) @@ -475,6 +478,14 @@ static void aq_fw3x_enable_ptp(struct aq_hw_s *self, int enable) aq_hw_write_reg(self, HW_ATL_FW3X_EXT_CONTROL_ADDR, ptp_opts); } +static void aq_fw3x_adjust_ptp(struct aq_hw_s *self, uint64_t adj) +{ + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_LSW_ADDR, + (adj >> 0) & 0xffffffff); + aq_hw_write_reg(self, HW_ATL_FW3X_PTP_ADJ_MSW_ADDR, + (adj >> 32) & 0xffffffff); +} + static int aq_fw2x_led_control(struct aq_hw_s *self, u32 mode) { if (self->fw_ver_actual < HW_ATL_FW_VER_LED) @@ -633,4 +644,5 @@ const struct aq_fw_ops aq_fw_2x_ops = { .enable_ptp = aq_fw3x_enable_ptp, .led_control = aq_fw2x_led_control, .set_phyloopback = aq_fw2x_set_phyloopback, + .adjust_ptp = aq_fw3x_adjust_ptp, }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 597e6fd5bfea..fd6e0e48cd51 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -11786,6 +11786,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (version_printed++ == 0) pr_info("%s", version); + /* Clear any pending DMA transactions from crash kernel + * while loading driver in capture kernel. + */ + if (is_kdump_kernel()) { + pci_clear_master(pdev); + pcie_flr(pdev); + } + max_irqs = bnxt_get_max_irq(pdev); dev = alloc_etherdev_mq(sizeof(*bp), max_irqs); if (!dev) @@ -11983,10 +11991,10 @@ static void bnxt_shutdown(struct pci_dev *pdev) dev_close(dev); bnxt_ulp_shutdown(bp); + bnxt_clear_int_mode(bp); + pci_disable_device(pdev); if (system_state == SYSTEM_POWER_OFF) { - bnxt_clear_int_mode(bp); - pci_disable_device(pdev); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); } diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index b38499774071..99e2c6d4d8c3 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -543,13 +543,13 @@ struct l4_kwq_update_pg { #define L4_KWQ_UPDATE_PG_RESERVERD2_SHIFT 2 #endif #if defined(__BIG_ENDIAN) - u16 reserverd3; + u16 reserved3; u8 da0; u8 da1; #elif defined(__LITTLE_ENDIAN) u8 da1; u8 da0; - u16 reserverd3; + u16 reserved3; #endif #if defined(__BIG_ENDIAN) u8 da2; diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index dbf7070fcdba..a3f0f27fc79a 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -652,6 +652,7 @@ #define MACB_CAPS_GEM_HAS_PTP 0x00000040 #define MACB_CAPS_BD_RD_PREFETCH 0x00000080 #define MACB_CAPS_NEEDS_RSTONUBR 0x00000100 +#define MACB_CAPS_MACB_IS_EMAC 0x08000000 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 4508f0d150da..2c28da1737fe 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -572,8 +572,21 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, old_ctrl = ctrl = macb_or_gem_readl(bp, NCFGR); /* Clear all the bits we might set later */ - ctrl &= ~(GEM_BIT(GBE) | MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE) | - GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + ctrl &= ~(MACB_BIT(SPD) | MACB_BIT(FD) | MACB_BIT(PAE)); + + if (bp->caps & MACB_CAPS_MACB_IS_EMAC) { + if (state->interface == PHY_INTERFACE_MODE_RMII) + ctrl |= MACB_BIT(RM9200_RMII); + } else { + ctrl &= ~(GEM_BIT(GBE) | GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL)); + + /* We do not support MLO_PAUSE_RX yet */ + if (state->pause & MLO_PAUSE_TX) + ctrl |= MACB_BIT(PAE); + + if (state->interface == PHY_INTERFACE_MODE_SGMII) + ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); + } if (state->speed == SPEED_1000) ctrl |= GEM_BIT(GBE); @@ -583,13 +596,6 @@ static void macb_mac_config(struct phylink_config *config, unsigned int mode, if (state->duplex) ctrl |= MACB_BIT(FD); - /* We do not support MLO_PAUSE_RX yet */ - if (state->pause & MLO_PAUSE_TX) - ctrl |= MACB_BIT(PAE); - - if (state->interface == PHY_INTERFACE_MODE_SGMII) - ctrl |= GEM_BIT(SGMIIEN) | GEM_BIT(PCSSEL); - /* Apply the new configuration, if any */ if (old_ctrl ^ ctrl) macb_or_gem_writel(bp, NCFGR, ctrl); @@ -608,9 +614,10 @@ static void macb_mac_link_down(struct phylink_config *config, unsigned int mode, unsigned int q; u32 ctrl; - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IDR, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IDR, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); /* Disable Rx and Tx */ ctrl = macb_readl(bp, NCR) & ~(MACB_BIT(RE) | MACB_BIT(TE)); @@ -627,17 +634,19 @@ static void macb_mac_link_up(struct phylink_config *config, unsigned int mode, struct macb_queue *queue; unsigned int q; - macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); + if (!(bp->caps & MACB_CAPS_MACB_IS_EMAC)) { + macb_set_tx_clk(bp->tx_clk, bp->speed, ndev); - /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down - * cleared the pipeline and control registers. - */ - bp->macbgem_ops.mog_init_rings(bp); - macb_init_buffers(bp); + /* Initialize rings & buffers as clearing MACB_BIT(TE) in link down + * cleared the pipeline and control registers. + */ + bp->macbgem_ops.mog_init_rings(bp); + macb_init_buffers(bp); - for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) - queue_writel(queue, IER, - bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) + queue_writel(queue, IER, + bp->rx_intr_mask | MACB_TX_INT_FLAGS | MACB_BIT(HRESP)); + } /* Enable Rx and Tx */ macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(RE) | MACB_BIT(TE)); @@ -3790,6 +3799,10 @@ static int at91ether_open(struct net_device *dev) u32 ctl; int ret; + ret = pm_runtime_get_sync(&lp->pdev->dev); + if (ret < 0) + return ret; + /* Clear internal statistics */ ctl = macb_readl(lp, NCR); macb_writel(lp, NCR, ctl | MACB_BIT(CLRSTAT)); @@ -3854,7 +3867,7 @@ static int at91ether_close(struct net_device *dev) q->rx_buffers, q->rx_buffers_dma); q->rx_buffers = NULL; - return 0; + return pm_runtime_put(&lp->pdev->dev); } /* Transmit packet */ @@ -4037,7 +4050,6 @@ static int at91ether_init(struct platform_device *pdev) struct net_device *dev = platform_get_drvdata(pdev); struct macb *bp = netdev_priv(dev); int err; - u32 reg; bp->queues[0].bp = bp; @@ -4051,11 +4063,7 @@ static int at91ether_init(struct platform_device *pdev) macb_writel(bp, NCR, 0); - reg = MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG); - if (bp->phy_interface == PHY_INTERFACE_MODE_RMII) - reg |= MACB_BIT(RM9200_RMII); - - macb_writel(bp, NCFGR, reg); + macb_writel(bp, NCFGR, MACB_BF(CLK, MACB_CLK_DIV32) | MACB_BIT(BIG)); return 0; } @@ -4214,7 +4222,7 @@ static const struct macb_config sama5d4_config = { }; static const struct macb_config emac_config = { - .caps = MACB_CAPS_NEEDS_RSTONUBR, + .caps = MACB_CAPS_NEEDS_RSTONUBR | MACB_CAPS_MACB_IS_EMAC, .clk_init = at91ether_clk_init, .init = at91ether_init, }; diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c index 17a4110c2e49..8ff28ed04b7f 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c @@ -410,10 +410,19 @@ void bgx_lmac_rx_tx_enable(int node, int bgx_idx, int lmacid, bool enable) lmac = &bgx->lmac[lmacid]; cfg = bgx_reg_read(bgx, lmacid, BGX_CMRX_CFG); - if (enable) + if (enable) { cfg |= CMR_PKT_RX_EN | CMR_PKT_TX_EN; - else + + /* enable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1S, + GMI_TXX_INT_UNDFLW); + } else { cfg &= ~(CMR_PKT_RX_EN | CMR_PKT_TX_EN); + + /* Disable TX FIFO Underflow interrupt */ + bgx_reg_modify(bgx, lmacid, BGX_GMP_GMI_TXX_INT_ENA_W1C, + GMI_TXX_INT_UNDFLW); + } bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cfg); if (bgx->is_rgx) @@ -1535,6 +1544,48 @@ static int bgx_init_phy(struct bgx *bgx) return bgx_init_of_phy(bgx); } +static irqreturn_t bgx_intr_handler(int irq, void *data) +{ + struct bgx *bgx = (struct bgx *)data; + u64 status, val; + int lmac; + + for (lmac = 0; lmac < bgx->lmac_count; lmac++) { + status = bgx_reg_read(bgx, lmac, BGX_GMP_GMI_TXX_INT); + if (status & GMI_TXX_INT_UNDFLW) { + pci_err(bgx->pdev, "BGX%d lmac%d UNDFLW\n", + bgx->bgx_id, lmac); + val = bgx_reg_read(bgx, lmac, BGX_CMRX_CFG); + val &= ~CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + val |= CMR_EN; + bgx_reg_write(bgx, lmac, BGX_CMRX_CFG, val); + } + /* clear interrupts */ + bgx_reg_write(bgx, lmac, BGX_GMP_GMI_TXX_INT, status); + } + + return IRQ_HANDLED; +} + +static void bgx_register_intr(struct pci_dev *pdev) +{ + struct bgx *bgx = pci_get_drvdata(pdev); + int ret; + + ret = pci_alloc_irq_vectors(pdev, BGX_LMAC_VEC_OFFSET, + BGX_LMAC_VEC_OFFSET, PCI_IRQ_ALL_TYPES); + if (ret < 0) { + pci_err(pdev, "Req for #%d msix vectors failed\n", + BGX_LMAC_VEC_OFFSET); + return; + } + ret = pci_request_irq(pdev, GMPX_GMI_TX_INT, bgx_intr_handler, NULL, + bgx, "BGX%d", bgx->bgx_id); + if (ret) + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); +} + static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { int err; @@ -1550,7 +1601,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_drvdata(pdev, bgx); - err = pci_enable_device(pdev); + err = pcim_enable_device(pdev); if (err) { dev_err(dev, "Failed to enable PCI device\n"); pci_set_drvdata(pdev, NULL); @@ -1604,6 +1655,8 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) bgx_init_hw(bgx); + bgx_register_intr(pdev); + /* Enable all LMACs */ for (lmac = 0; lmac < bgx->lmac_count; lmac++) { err = bgx_lmac_enable(bgx, lmac); @@ -1620,6 +1673,7 @@ static int bgx_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err_enable: bgx_vnic[bgx->bgx_id] = NULL; + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); err_release_regions: pci_release_regions(pdev); err_disable_device: @@ -1637,6 +1691,8 @@ static void bgx_remove(struct pci_dev *pdev) for (lmac = 0; lmac < bgx->lmac_count; lmac++) bgx_lmac_disable(bgx, lmac); + pci_free_irq(pdev, GMPX_GMI_TX_INT, bgx); + bgx_vnic[bgx->bgx_id] = NULL; pci_release_regions(pdev); pci_disable_device(pdev); diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h index 25888706bdcd..cdea49392185 100644 --- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.h +++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.h @@ -180,6 +180,15 @@ #define BGX_GMP_GMI_TXX_BURST 0x38228 #define BGX_GMP_GMI_TXX_MIN_PKT 0x38240 #define BGX_GMP_GMI_TXX_SGMII_CTL 0x38300 +#define BGX_GMP_GMI_TXX_INT 0x38500 +#define BGX_GMP_GMI_TXX_INT_W1S 0x38508 +#define BGX_GMP_GMI_TXX_INT_ENA_W1C 0x38510 +#define BGX_GMP_GMI_TXX_INT_ENA_W1S 0x38518 +#define GMI_TXX_INT_PTP_LOST BIT_ULL(4) +#define GMI_TXX_INT_LATE_COL BIT_ULL(3) +#define GMI_TXX_INT_XSDEF BIT_ULL(2) +#define GMI_TXX_INT_XSCOL BIT_ULL(1) +#define GMI_TXX_INT_UNDFLW BIT_ULL(0) #define BGX_MSIX_VEC_0_29_ADDR 0x400000 /* +(0..29) << 4 */ #define BGX_MSIX_VEC_0_29_CTL 0x400008 diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 1ea3372775e6..e94ae9b94dbf 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1405,6 +1405,8 @@ static struct dm9000_plat_data *dm9000_parse_dt(struct device *dev) mac_addr = of_get_mac_address(np); if (!IS_ERR(mac_addr)) ether_addr_copy(pdata->dev_addr, mac_addr); + else if (PTR_ERR(mac_addr) == -EPROBE_DEFER) + return ERR_CAST(mac_addr); return pdata; } diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index b002ab4e5838..77c412a7e7a4 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2936,13 +2936,6 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) else return -EINVAL; - /* Tell the OS link is going down, the link will go back up when fw - * says it is ready asynchronously - */ - ice_print_link_msg(vsi, false); - netif_carrier_off(netdev); - netif_tx_stop_all_queues(netdev); - /* Set the FC mode and only restart AN if link is up */ status = ice_set_fc(pi, &aq_failures, link_up); @@ -3489,21 +3482,13 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, return -EINVAL; } - /* hardware only supports an ITR granularity of 2us */ - if (coalesce_usecs % 2 != 0) { - netdev_info(vsi->netdev, "Invalid value, %s-usecs must be even\n", - c_type_str); - return -EINVAL; - } - if (use_adaptive_coalesce) { rc->itr_setting |= ICE_ITR_DYNAMIC; } else { - /* store user facing value how it was set */ + /* save the user set usecs */ rc->itr_setting = coalesce_usecs; - /* set to static and convert to value HW understands */ - rc->target_itr = - ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting)); + /* device ITR granularity is in 2 usec increments */ + rc->target_itr = ITR_REG_ALIGN(rc->itr_setting); } return 0; @@ -3597,6 +3582,30 @@ ice_is_coalesce_param_invalid(struct net_device *netdev, } /** + * ice_print_if_odd_usecs - print message if user tries to set odd [tx|rx]-usecs + * @netdev: netdev used for print + * @itr_setting: previous user setting + * @use_adaptive_coalesce: if adaptive coalesce is enabled or being enabled + * @coalesce_usecs: requested value of [tx|rx]-usecs + * @c_type_str: either "rx" or "tx" to match user set field of [tx|rx]-usecs + */ +static void +ice_print_if_odd_usecs(struct net_device *netdev, u16 itr_setting, + u32 use_adaptive_coalesce, u32 coalesce_usecs, + const char *c_type_str) +{ + if (use_adaptive_coalesce) + return; + + itr_setting = ITR_TO_REG(itr_setting); + + if (itr_setting != coalesce_usecs && (coalesce_usecs % 2)) + netdev_info(netdev, "User set %s-usecs to %d, device only supports even values. Rounding down and attempting to set %s-usecs to %d\n", + c_type_str, coalesce_usecs, c_type_str, + ITR_REG_ALIGN(coalesce_usecs)); +} + +/** * __ice_set_coalesce - set ITR/INTRL values for the device * @netdev: pointer to the netdev associated with this query * @ec: ethtool structure to fill with driver's coalesce settings @@ -3616,8 +3625,19 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, return -EINVAL; if (q_num < 0) { + struct ice_q_vector *q_vector = vsi->q_vectors[0]; int v_idx; + if (q_vector) { + ice_print_if_odd_usecs(netdev, q_vector->rx.itr_setting, + ec->use_adaptive_rx_coalesce, + ec->rx_coalesce_usecs, "rx"); + + ice_print_if_odd_usecs(netdev, q_vector->tx.itr_setting, + ec->use_adaptive_tx_coalesce, + ec->tx_coalesce_usecs, "tx"); + } + ice_for_each_q_vector(vsi, v_idx) { /* In some cases if DCB is configured the num_[rx|tx]q * can be less than vsi->num_q_vectors. This check diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 14a1bf445889..7ee00a128663 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -222,7 +222,7 @@ enum ice_rx_dtype { #define ICE_ITR_GRAN_S 1 /* ITR granularity is always 2us */ #define ICE_ITR_GRAN_US BIT(ICE_ITR_GRAN_S) #define ICE_ITR_MASK 0x1FFE /* ITR register value alignment mask */ -#define ITR_REG_ALIGN(setting) __ALIGN_MASK(setting, ~ICE_ITR_MASK) +#define ITR_REG_ALIGN(setting) ((setting) & ICE_ITR_MASK) #define ICE_ITR_ADAPTIVE_MIN_INC 0x0002 #define ICE_ITR_ADAPTIVE_MIN_USECS 0x0002 diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 262714d5f54a..75c70d432c72 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -1874,6 +1874,48 @@ error_param: } /** + * ice_wait_on_vf_reset - poll to make sure a given VF is ready after reset + * @vf: The VF being resseting + * + * The max poll time is about ~800ms, which is about the maximum time it takes + * for a VF to be reset and/or a VF driver to be removed. + */ +static void ice_wait_on_vf_reset(struct ice_vf *vf) +{ + int i; + + for (i = 0; i < ICE_MAX_VF_RESET_TRIES; i++) { + if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) + break; + msleep(ICE_MAX_VF_RESET_SLEEP_MS); + } +} + +/** + * ice_check_vf_ready_for_cfg - check if VF is ready to be configured/queried + * @vf: VF to check if it's ready to be configured/queried + * + * The purpose of this function is to make sure the VF is not in reset, not + * disabled, and initialized so it can be configured and/or queried by a host + * administrator. + */ +static int ice_check_vf_ready_for_cfg(struct ice_vf *vf) +{ + struct ice_pf *pf; + + ice_wait_on_vf_reset(vf); + + if (ice_is_vf_disabled(vf)) + return -EINVAL; + + pf = vf->pf; + if (ice_check_vf_init(pf, vf)) + return -EBUSY; + + return 0; +} + +/** * ice_set_vf_spoofchk * @netdev: network interface device structure * @vf_id: VF identifier @@ -1890,16 +1932,16 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) enum ice_status status; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vf_vsi = pf->vsi[vf->lan_vsi_idx]; if (!vf_vsi) { @@ -2696,7 +2738,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, struct ice_vsi *vsi; struct device *dev; struct ice_vf *vf; - int ret = 0; + int ret; dev = ice_pf_to_dev(pf); if (ice_validate_vf_id(pf, vf_id)) @@ -2714,13 +2756,15 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, vf = &pf->vf[vf_id]; vsi = pf->vsi[vf->lan_vsi_idx]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; if (le16_to_cpu(vsi->info.pvid) == vlanprio) { /* duplicate request, so just return success */ dev_dbg(dev, "Duplicate pvid %d request\n", vlanprio); - return ret; + return 0; } /* If PVID, then remove all filters on the old VLAN */ @@ -2731,7 +2775,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (vlan_id || qos) { ret = ice_vsi_manage_pvid(vsi, vlanprio, true); if (ret) - goto error_set_pvid; + return ret; } else { ice_vsi_manage_pvid(vsi, 0, false); vsi->info.pvid = 0; @@ -2744,7 +2788,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, /* add new VLAN filter for each MAC */ ret = ice_vsi_add_vlan(vsi, vlan_id); if (ret) - goto error_set_pvid; + return ret; } /* The Port VLAN needs to be saved across resets the same as the @@ -2752,8 +2796,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, */ vf->port_vlan_id = le16_to_cpu(vsi->info.pvid); -error_set_pvid: - return ret; + return 0; } /** @@ -3237,23 +3280,6 @@ ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi) } /** - * ice_wait_on_vf_reset - * @vf: The VF being resseting - * - * Poll to make sure a given VF is ready after reset - */ -static void ice_wait_on_vf_reset(struct ice_vf *vf) -{ - int i; - - for (i = 0; i < ICE_MAX_VF_RESET_WAIT; i++) { - if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) - break; - msleep(20); - } -} - -/** * ice_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -3265,29 +3291,21 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; - int ret = 0; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; - vf = &pf->vf[vf_id]; - /* Don't set MAC on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; - if (is_zero_ether_addr(mac) || is_multicast_ether_addr(mac)) { netdev_err(netdev, "%pM not a valid unicast address\n", mac); return -EINVAL; } + vf = &pf->vf[vf_id]; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; + /* copy MAC into dflt_lan_addr and trigger a VF reset. The reset * flow will use the updated dflt_lan_addr and add a MAC filter * using ice_add_mac. Also set pf_set_mac to indicate that the PF has @@ -3299,7 +3317,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) vf_id, mac); ice_vc_reset_vf(vf); - return ret; + return 0; } /** @@ -3314,22 +3332,15 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - /* Don't set Trusted Mode on disabled VF */ - if (ice_is_vf_disabled(vf)) - return -EINVAL; - - /* In case VF is in reset mode, wait until it is completed. Depending - * on factors like queue disabling routine, this could take ~250ms - */ - ice_wait_on_vf_reset(vf); - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; /* Check if already trusted */ if (trusted == vf->trusted) @@ -3355,13 +3366,15 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state) { struct ice_pf *pf = ice_netdev_to_pf(netdev); struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; switch (link_state) { case IFLA_VF_LINK_STATE_AUTO: @@ -3397,14 +3410,15 @@ int ice_get_vf_stats(struct net_device *netdev, int vf_id, struct ice_eth_stats *stats; struct ice_vsi *vsi; struct ice_vf *vf; + int ret; if (ice_validate_vf_id(pf, vf_id)) return -EINVAL; vf = &pf->vf[vf_id]; - - if (ice_check_vf_init(pf, vf)) - return -EBUSY; + ret = ice_check_vf_ready_for_cfg(vf); + if (ret) + return ret; vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 4647d636ed36..ac67982751df 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -38,7 +38,8 @@ #define ICE_MAX_POLICY_INTR_PER_VF 33 #define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) #define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) -#define ICE_MAX_VF_RESET_WAIT 15 +#define ICE_MAX_VF_RESET_TRIES 40 +#define ICE_MAX_VF_RESET_SLEEP_MS 20 #define ice_for_each_vf(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vfs; (i)++) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c index 3a975641f902..20b907dc1e29 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -200,7 +200,7 @@ int mlx5e_health_report(struct mlx5e_priv *priv, netdev_err(priv->netdev, err_str); if (!reporter) - return err_ctx->recover(&err_ctx->ctx); + return err_ctx->recover(err_ctx->ctx); return devlink_health_report(reporter, err_str, err_ctx); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index 7c8796d9743f..a226277b0980 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -179,6 +179,14 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) } } +static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq) +{ + if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + mlx5_wq_ll_reset(&rq->mpwqe.wq); + else + mlx5_wq_cyc_reset(&rq->wqe.wq); +} + /* SW parser related functions */ struct mlx5e_swp_spec { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 454d3459bd8b..966983674663 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -712,6 +712,9 @@ int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state) if (!in) return -ENOMEM; + if (curr_state == MLX5_RQC_STATE_RST && next_state == MLX5_RQC_STATE_RDY) + mlx5e_rqwq_reset(rq); + rqc = MLX5_ADDR_OF(modify_rq_in, in, ctx); MLX5_SET(modify_rq_in, in, rq_state, curr_state); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 5acf60b1bbfe..e49acd0c5da5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -459,12 +459,16 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) static int esw_legacy_enable(struct mlx5_eswitch *esw) { - int ret; + struct mlx5_vport *vport; + int ret, i; ret = esw_create_legacy_table(esw); if (ret) return ret; + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO; + ret = mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); if (ret) esw_destroy_legacy_table(esw); @@ -2452,25 +2456,17 @@ out: int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting) { - int err = 0; - if (!esw) return -EOPNOTSUPP; if (!ESW_ALLOWED(esw)) return -EPERM; - mutex_lock(&esw->state_lock); - if (esw->mode != MLX5_ESWITCH_LEGACY) { - err = -EOPNOTSUPP; - goto out; - } + if (esw->mode != MLX5_ESWITCH_LEGACY) + return -EOPNOTSUPP; *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0; - -out: - mutex_unlock(&esw->state_lock); - return err; + return 0; } int mlx5_eswitch_set_vport_trust(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 979f13bdc203..1a57b2bd74b8 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -1172,7 +1172,7 @@ static int esw_offloads_start(struct mlx5_eswitch *esw, return -EINVAL; } - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); mlx5_eswitch_update_num_of_vfs(esw, esw->dev->priv.sriov.num_vfs); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_OFFLOADS); if (err) { @@ -2065,7 +2065,7 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, { int err, err1; - mlx5_eswitch_disable(esw, true); + mlx5_eswitch_disable(esw, false); err = mlx5_eswitch_enable(esw, MLX5_ESWITCH_LEGACY); if (err) { NL_SET_ERR_MSG_MOD(extack, "Failed setting eswitch to legacy"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c index c5a446e295aa..4276194b633f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads_chains.c @@ -35,7 +35,7 @@ static const unsigned int ESW_POOLS[] = { 4 * 1024 * 1024, 1 * 1024 * 1024, 64 * 1024, - 4 * 1024, }; + 128 }; struct mlx5_esw_chains_priv { struct rhashtable chains_ht; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c index c6c7d1defbd7..aade62a9ee5c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -2307,7 +2307,9 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, struct mlx5dr_cmd_vport_cap *vport_cap; struct mlx5dr_domain *dmn = sb->dmn; struct mlx5dr_cmd_caps *caps; + u8 *bit_mask = sb->bit_mask; u8 *tag = hw_ste->tag; + bool source_gvmi_set; DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); @@ -2328,7 +2330,8 @@ static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, if (!vport_cap) return -EINVAL; - if (vport_cap->vport_gvmi) + source_gvmi_set = MLX5_GET(ste_src_gvmi_qp, bit_mask, source_gvmi); + if (vport_cap->vport_gvmi && source_gvmi_set) MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi); misc->source_eswitch_owner_vhca_id = 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c index 3abfc8125926..c2027192e21e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -66,15 +66,20 @@ static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *next_ft) { struct mlx5dr_table *tbl; + u32 flags; int err; if (mlx5_dr_is_fw_table(ft->flags)) return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, log_size, next_ft); + flags = ft->flags; + /* turn off encap/decap if not supported for sw-str by fw */ + if (!MLX5_CAP_FLOWTABLE(ns->dev, sw_owner_reformat_supported)) + flags = ft->flags & ~(MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT | + MLX5_FLOW_TABLE_TUNNEL_EN_DECAP); - tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, - ft->level, ft->flags); + tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, ft->level, flags); if (!tbl) { mlx5_core_err(ns->dev, "Failed creating dr flow_table\n"); return -EINVAL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 02f7e4a39578..01f075fac276 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -94,6 +94,13 @@ void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides) print_hex_dump(KERN_WARNING, "", DUMP_PREFIX_OFFSET, 16, 1, wqe, len, false); } +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq) +{ + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_cyc_update_db_record(wq); +} + int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -192,6 +199,19 @@ err_db_free: return err; } +static void mlx5_wq_ll_init_list(struct mlx5_wq_ll *wq) +{ + struct mlx5_wqe_srq_next_seg *next_seg; + int i; + + for (i = 0; i < wq->fbc.sz_m1; i++) { + next_seg = mlx5_wq_ll_get_wqe(wq, i); + next_seg->next_wqe_index = cpu_to_be16(i + 1); + } + next_seg = mlx5_wq_ll_get_wqe(wq, i); + wq->tail_next = &next_seg->next_wqe_index; +} + int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl) @@ -199,9 +219,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, u8 log_wq_stride = MLX5_GET(wq, wqc, log_wq_stride); u8 log_wq_sz = MLX5_GET(wq, wqc, log_wq_sz); struct mlx5_frag_buf_ctrl *fbc = &wq->fbc; - struct mlx5_wqe_srq_next_seg *next_seg; int err; - int i; err = mlx5_db_alloc_node(mdev, &wq_ctrl->db, param->db_numa_node); if (err) { @@ -220,13 +238,7 @@ int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, mlx5_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc); - for (i = 0; i < fbc->sz_m1; i++) { - next_seg = mlx5_wq_ll_get_wqe(wq, i); - next_seg->next_wqe_index = cpu_to_be16(i + 1); - } - next_seg = mlx5_wq_ll_get_wqe(wq, i); - wq->tail_next = &next_seg->next_wqe_index; - + mlx5_wq_ll_init_list(wq); wq_ctrl->mdev = mdev; return 0; @@ -237,6 +249,15 @@ err_db_free: return err; } +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq) +{ + wq->head = 0; + wq->wqe_ctr = 0; + wq->cur_sz = 0; + mlx5_wq_ll_init_list(wq); + mlx5_wq_ll_update_db_record(wq); +} + void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl) { mlx5_frag_buf_free(wq_ctrl->mdev, &wq_ctrl->buf); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index d9a94bc223c0..4cadc336593f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -80,6 +80,7 @@ int mlx5_wq_cyc_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_cyc *wq, struct mlx5_wq_ctrl *wq_ctrl); void mlx5_wq_cyc_wqe_dump(struct mlx5_wq_cyc *wq, u16 ix, u8 nstrides); +void mlx5_wq_cyc_reset(struct mlx5_wq_cyc *wq); int mlx5_wq_qp_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *qpc, struct mlx5_wq_qp *wq, @@ -92,6 +93,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, struct mlx5_wq_ctrl *wq_ctrl); +void mlx5_wq_ll_reset(struct mlx5_wq_ll *wq); void mlx5_wq_destroy(struct mlx5_wq_ctrl *wq_ctrl); diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index a41a90c589db..1c9e70c8cc30 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -157,24 +157,6 @@ static int msg_enable; */ /** - * ks_rdreg8 - read 8 bit register from device - * @ks : The chip information - * @offset: The register address - * - * Read a 8bit register from the chip, returning the result - */ -static u8 ks_rdreg8(struct ks_net *ks, int offset) -{ - u16 data; - u8 shift_bit = offset & 0x03; - u8 shift_data = (offset & 1) << 3; - ks->cmd_reg_cache = (u16) offset | (u16)(BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - data = ioread16(ks->hw_addr); - return (u8)(data >> shift_data); -} - -/** * ks_rdreg16 - read 16 bit register from device * @ks : The chip information * @offset: The register address @@ -184,28 +166,12 @@ static u8 ks_rdreg8(struct ks_net *ks, int offset) static u16 ks_rdreg16(struct ks_net *ks, int offset) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); return ioread16(ks->hw_addr); } /** - * ks_wrreg8 - write 8bit register value to chip - * @ks: The chip information - * @offset: The register address - * @value: The value to write - * - */ -static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) -{ - u8 shift_bit = (offset & 0x03); - u16 value_write = (u16)(value << ((offset & 1) << 3)); - ks->cmd_reg_cache = (u16)offset | (BE0 << shift_bit); - iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); - iowrite16(value_write, ks->hw_addr); -} - -/** * ks_wrreg16 - write 16bit register value to chip * @ks: The chip information * @offset: The register address @@ -215,7 +181,7 @@ static void ks_wrreg8(struct ks_net *ks, int offset, u8 value) static void ks_wrreg16(struct ks_net *ks, int offset, u16 value) { - ks->cmd_reg_cache = (u16)offset | ((BE1 | BE0) << (offset & 0x02)); + ks->cmd_reg_cache = (u16)offset | ((BE3 | BE2) >> (offset & 0x02)); iowrite16(ks->cmd_reg_cache, ks->hw_addr_cmd); iowrite16(value, ks->hw_addr); } @@ -231,7 +197,7 @@ static inline void ks_inblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - *wptr++ = (u16)ioread16(ks->hw_addr); + *wptr++ = be16_to_cpu(ioread16(ks->hw_addr)); } /** @@ -245,7 +211,7 @@ static inline void ks_outblk(struct ks_net *ks, u16 *wptr, u32 len) { len >>= 1; while (len--) - iowrite16(*wptr++, ks->hw_addr); + iowrite16(cpu_to_be16(*wptr++), ks->hw_addr); } static void ks_disable_int(struct ks_net *ks) @@ -324,8 +290,7 @@ static void ks_read_config(struct ks_net *ks) u16 reg_data = 0; /* Regardless of bus width, 8 bit read should always work.*/ - reg_data = ks_rdreg8(ks, KS_CCR) & 0x00FF; - reg_data |= ks_rdreg8(ks, KS_CCR+1) << 8; + reg_data = ks_rdreg16(ks, KS_CCR); /* addr/data bus are multiplexed */ ks->sharedbus = (reg_data & CCR_SHARED) == CCR_SHARED; @@ -429,7 +394,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) /* 1. set sudo DMA mode */ ks_wrreg16(ks, KS_RXFDPR, RXFDPR_RXFPAI); - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. read prepend data */ /** @@ -446,7 +411,7 @@ static inline void ks_read_qmu(struct ks_net *ks, u16 *buf, u32 len) ks_inblk(ks, buf, ALIGN(len, 4)); /* 4. reset sudo DMA Mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); } /** @@ -679,13 +644,13 @@ static void ks_write_qmu(struct ks_net *ks, u8 *pdata, u16 len) ks->txh.txw[1] = cpu_to_le16(len); /* 1. set sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, (ks->rc_rxqcr | RXQCR_SDA) & 0xff); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA); /* 2. write status/lenth info */ ks_outblk(ks, ks->txh.txw, 4); /* 3. write pkt data */ ks_outblk(ks, (u16 *)pdata, ALIGN(len, 4)); /* 4. reset sudo-DMA mode */ - ks_wrreg8(ks, KS_RXQCR, ks->rc_rxqcr); + ks_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); /* 5. Enqueue Tx(move the pkt from TX buffer into TXQ) */ ks_wrreg16(ks, KS_TXQCR, TXQCR_METFE); /* 6. wait until TXQCR_METFE is auto-cleared */ diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index b38820849faa..1135a18019c7 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -114,6 +114,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) if (err != 4) break; + /* At this point the IFH was read correctly, so it is safe to + * presume that there is no error. The err needs to be reset + * otherwise a frame could come in CPU queue between the while + * condition and the check for error later on. And in that case + * the new frame is just removed and not processed. + */ + err = 0; + ocelot_parse_ifh(ifh, &info); ocelot_port = ocelot->ports[info.port]; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c index 87f82f36812f..46107de5e6c3 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_dev.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -103,7 +103,7 @@ int ionic_heartbeat_check(struct ionic *ionic) { struct ionic_dev *idev = &ionic->idev; unsigned long hb_time; - u32 fw_status; + u8 fw_status; u32 hb; /* wait a little more than one second before testing again */ @@ -111,9 +111,12 @@ int ionic_heartbeat_check(struct ionic *ionic) if (time_before(hb_time, (idev->last_hb_time + ionic->watchdog_period))) return 0; - /* firmware is useful only if fw_status is non-zero */ - fw_status = ioread32(&idev->dev_info_regs->fw_status); - if (!fw_status) + /* firmware is useful only if the running bit is set and + * fw_status != 0xff (bad PCI read) + */ + fw_status = ioread8(&idev->dev_info_regs->fw_status); + if (fw_status == 0xff || + !(fw_status & IONIC_FW_STS_F_RUNNING)) return -ENXIO; /* early FW has no heartbeat, else FW will return non-zero */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h index ce07c2931a72..54547d53b0f2 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_if.h +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -2445,6 +2445,7 @@ union ionic_dev_info_regs { u8 version; u8 asic_type; u8 asic_rev; +#define IONIC_FW_STS_F_RUNNING 0x1 u8 fw_status; u32 fw_heartbeat; char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index e8a1b27db84d..234c6f30effb 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -163,6 +163,8 @@ struct qede_rdma_dev { struct list_head entry; struct list_head rdma_event_list; struct workqueue_struct *rdma_wq; + struct kref refcnt; + struct completion event_comp; bool exp_recovery; }; diff --git a/drivers/net/ethernet/qlogic/qede/qede_rdma.c b/drivers/net/ethernet/qlogic/qede/qede_rdma.c index ffabc2d2f082..2d873ae8a234 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_rdma.c +++ b/drivers/net/ethernet/qlogic/qede/qede_rdma.c @@ -59,6 +59,9 @@ static void _qede_rdma_dev_add(struct qede_dev *edev) static int qede_rdma_create_wq(struct qede_dev *edev) { INIT_LIST_HEAD(&edev->rdma_info.rdma_event_list); + kref_init(&edev->rdma_info.refcnt); + init_completion(&edev->rdma_info.event_comp); + edev->rdma_info.rdma_wq = create_singlethread_workqueue("rdma_wq"); if (!edev->rdma_info.rdma_wq) { DP_NOTICE(edev, "qedr: Could not create workqueue\n"); @@ -83,8 +86,23 @@ static void qede_rdma_cleanup_event(struct qede_dev *edev) } } +static void qede_rdma_complete_event(struct kref *ref) +{ + struct qede_rdma_dev *rdma_dev = + container_of(ref, struct qede_rdma_dev, refcnt); + + /* no more events will be added after this */ + complete(&rdma_dev->event_comp); +} + static void qede_rdma_destroy_wq(struct qede_dev *edev) { + /* Avoid race with add_event flow, make sure it finishes before + * we start accessing the list and cleaning up the work + */ + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); + wait_for_completion(&edev->rdma_info.event_comp); + qede_rdma_cleanup_event(edev); destroy_workqueue(edev->rdma_info.rdma_wq); } @@ -310,15 +328,24 @@ static void qede_rdma_add_event(struct qede_dev *edev, if (!edev->rdma_info.qedr_dev) return; + /* We don't want the cleanup flow to start while we're allocating and + * scheduling the work + */ + if (!kref_get_unless_zero(&edev->rdma_info.refcnt)) + return; /* already being destroyed */ + event_node = qede_rdma_get_free_event_node(edev); if (!event_node) - return; + goto out; event_node->event = event; event_node->ptr = edev; INIT_WORK(&event_node->work, qede_rdma_handle_event); queue_work(edev->rdma_info.rdma_wq, &event_node->work); + +out: + kref_put(&edev->rdma_info.refcnt, qede_rdma_complete_event); } void qede_rdma_dev_event_open(struct qede_dev *edev) diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c index 7d68b28bb893..a62229a8b1a4 100644 --- a/drivers/net/phy/broadcom.c +++ b/drivers/net/phy/broadcom.c @@ -410,7 +410,7 @@ static int bcm5481_config_aneg(struct phy_device *phydev) struct device_node *np = phydev->mdio.dev.of_node; int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ ret = genphy_config_aneg(phydev); /* Then we can set up the delay. */ @@ -463,7 +463,7 @@ static int bcm54616s_config_aneg(struct phy_device *phydev) { int ret; - /* Aneg firsly. */ + /* Aneg firstly. */ if (phydev->dev_flags & PHY_BCM_FLAGS_MODE_1000BX) ret = genphy_c37_config_aneg(phydev); else diff --git a/drivers/net/phy/mdio-bcm-iproc.c b/drivers/net/phy/mdio-bcm-iproc.c index 7e9975d25066..f1ded03f0229 100644 --- a/drivers/net/phy/mdio-bcm-iproc.c +++ b/drivers/net/phy/mdio-bcm-iproc.c @@ -178,6 +178,23 @@ static int iproc_mdio_remove(struct platform_device *pdev) return 0; } +#ifdef CONFIG_PM_SLEEP +int iproc_mdio_resume(struct device *dev) +{ + struct platform_device *pdev = to_platform_device(dev); + struct iproc_mdio_priv *priv = platform_get_drvdata(pdev); + + /* restore the mii clock configuration */ + iproc_mdio_config_clk(priv->base); + + return 0; +} + +static const struct dev_pm_ops iproc_mdio_pm_ops = { + .resume = iproc_mdio_resume +}; +#endif /* CONFIG_PM_SLEEP */ + static const struct of_device_id iproc_mdio_of_match[] = { { .compatible = "brcm,iproc-mdio", }, { /* sentinel */ }, @@ -188,6 +205,9 @@ static struct platform_driver iproc_mdio_driver = { .driver = { .name = "iproc-mdio", .of_match_table = iproc_mdio_of_match, +#ifdef CONFIG_PM_SLEEP + .pm = &iproc_mdio_pm_ops, +#endif }, .probe = iproc_mdio_probe, .remove = iproc_mdio_remove, diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c index 43db442b1373..cdc96968b0f4 100644 --- a/drivers/net/wireguard/device.c +++ b/drivers/net/wireguard/device.c @@ -258,6 +258,8 @@ static void wg_setup(struct net_device *dev) enum { WG_NETDEV_FEATURES = NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA }; + const int overhead = MESSAGE_MINIMUM_LENGTH + sizeof(struct udphdr) + + max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); dev->netdev_ops = &netdev_ops; dev->hard_header_len = 0; @@ -271,9 +273,8 @@ static void wg_setup(struct net_device *dev) dev->features |= WG_NETDEV_FEATURES; dev->hw_features |= WG_NETDEV_FEATURES; dev->hw_enc_features |= WG_NETDEV_FEATURES; - dev->mtu = ETH_DATA_LEN - MESSAGE_MINIMUM_LENGTH - - sizeof(struct udphdr) - - max(sizeof(struct ipv6hdr), sizeof(struct iphdr)); + dev->mtu = ETH_DATA_LEN - overhead; + dev->max_mtu = round_down(INT_MAX, MESSAGE_PADDING_MULTIPLE) - overhead; SET_NETDEV_DEVTYPE(dev, &device_type); diff --git a/drivers/net/wireguard/receive.c b/drivers/net/wireguard/receive.c index 9c6bab9c981f..4a153894cee2 100644 --- a/drivers/net/wireguard/receive.c +++ b/drivers/net/wireguard/receive.c @@ -118,10 +118,13 @@ static void wg_receive_handshake_packet(struct wg_device *wg, under_load = skb_queue_len(&wg->incoming_handshakes) >= MAX_QUEUED_INCOMING_HANDSHAKES / 8; - if (under_load) + if (under_load) { last_under_load = ktime_get_coarse_boottime_ns(); - else if (last_under_load) + } else if (last_under_load) { under_load = !wg_birthdate_has_expired(last_under_load, 1); + if (!under_load) + last_under_load = 0; + } mac_state = wg_cookie_validate_packet(&wg->cookie_checker, skb, under_load); if ((under_load && mac_state == VALID_MAC_WITH_COOKIE) || diff --git a/drivers/net/wireguard/send.c b/drivers/net/wireguard/send.c index c13260563446..7348c10cbae3 100644 --- a/drivers/net/wireguard/send.c +++ b/drivers/net/wireguard/send.c @@ -143,16 +143,22 @@ static void keep_key_fresh(struct wg_peer *peer) static unsigned int calculate_skb_padding(struct sk_buff *skb) { + unsigned int padded_size, last_unit = skb->len; + + if (unlikely(!PACKET_CB(skb)->mtu)) + return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; + /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the - * padded_size being clamped. + * padded_size being clamped. Fortunately, that's very rarely the case, + * so we optimize for that not happening. */ - unsigned int last_unit = skb->len % PACKET_CB(skb)->mtu; - unsigned int padded_size = ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE); + if (unlikely(last_unit > PACKET_CB(skb)->mtu)) + last_unit %= PACKET_CB(skb)->mtu; - if (padded_size > PACKET_CB(skb)->mtu) - padded_size = PACKET_CB(skb)->mtu; + padded_size = min(PACKET_CB(skb)->mtu, + ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } diff --git a/drivers/net/wireguard/socket.c b/drivers/net/wireguard/socket.c index 262f3b5c819d..b0d6541582d3 100644 --- a/drivers/net/wireguard/socket.c +++ b/drivers/net/wireguard/socket.c @@ -432,7 +432,6 @@ void wg_socket_reinit(struct wg_device *wg, struct sock *new4, wg->incoming_port = ntohs(inet_sk(new4)->inet_sport); mutex_unlock(&wg->socket_update_lock); synchronize_rcu(); - synchronize_net(); sock_free(old4); sock_free(old6); } diff --git a/drivers/nfc/pn544/i2c.c b/drivers/nfc/pn544/i2c.c index 720c89d6066e..4ac8cb262559 100644 --- a/drivers/nfc/pn544/i2c.c +++ b/drivers/nfc/pn544/i2c.c @@ -225,6 +225,7 @@ static void pn544_hci_i2c_platform_init(struct pn544_i2c_phy *phy) out: gpiod_set_value_cansleep(phy->gpiod_en, !phy->en_polarity); + usleep_range(10000, 15000); } static void pn544_hci_i2c_enable_mode(struct pn544_i2c_phy *phy, int run_mode) diff --git a/drivers/nfc/pn544/pn544.c b/drivers/nfc/pn544/pn544.c index 2b83156efe3f..b788870473e8 100644 --- a/drivers/nfc/pn544/pn544.c +++ b/drivers/nfc/pn544/pn544.c @@ -682,7 +682,7 @@ static int pn544_hci_tm_send(struct nfc_hci_dev *hdev, struct sk_buff *skb) static int pn544_hci_check_presence(struct nfc_hci_dev *hdev, struct nfc_target *target) { - pr_debug("supported protocol %d\b", target->supported_protocols); + pr_debug("supported protocol %d\n", target->supported_protocols); if (target->supported_protocols & (NFC_PROTO_ISO14443_MASK | NFC_PROTO_ISO14443_B_MASK)) { return nfc_hci_send_cmd(hdev, target->hci_reader_gate, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index 9639938581f5..5efcaa43615b 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -5344,7 +5344,7 @@ next_packet: } use_rx_sg = (card->options.cq == QETH_CQ_ENABLED) || - ((skb_len >= card->options.rx_sg_cb) && + (skb_len > card->options.rx_sg_cb && !atomic_read(&card->force_alloc_skb) && !IS_OSN(card)); @@ -5447,7 +5447,6 @@ static int qeth_extract_skbs(struct qeth_card *card, int budget, { int work_done = 0; - WARN_ON_ONCE(!budget); *done = false; while (budget) { diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index 692bd2623401..9972d96820f3 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -1707,15 +1707,14 @@ int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state) QETH_CARD_TEXT(card, 2, "vniccsch"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and enable/disable are supported */ if (!(card->options.vnicc.sup_chars & vnicc) || !(card->options.vnicc.set_char_sup & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* set enable/disable command and store wanted characteristic */ if (state) { cmd = IPA_VNICC_ENABLE; @@ -1761,14 +1760,13 @@ int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state) QETH_CARD_TEXT(card, 2, "vniccgch"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic is supported */ if (!(card->options.vnicc.sup_chars & vnicc)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, query current VNICC state */ if (qeth_card_hw_is_reachable(card)) rc = qeth_l2_vnicc_query_chars(card); @@ -1786,15 +1784,14 @@ int qeth_l2_vnicc_set_timeout(struct qeth_card *card, u32 timeout) QETH_CARD_TEXT(card, 2, "vniccsto"); - /* do not change anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and set_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* do we need to do anything? */ if (card->options.vnicc.learning_timeout == timeout) return rc; @@ -1823,14 +1820,14 @@ int qeth_l2_vnicc_get_timeout(struct qeth_card *card, u32 *timeout) QETH_CARD_TEXT(card, 2, "vniccgto"); - /* do not get anything if BridgePort is enabled */ - if (qeth_bridgeport_is_in_use(card)) - return -EBUSY; - /* check if characteristic and get_timeout are supported */ if (!(card->options.vnicc.sup_chars & QETH_VNICC_LEARNING) || !(card->options.vnicc.getset_timeout_sup & QETH_VNICC_LEARNING)) return -EOPNOTSUPP; + + if (qeth_bridgeport_is_in_use(card)) + return -EBUSY; + /* if card is ready, get timeout. Otherwise, just return stored value */ *timeout = card->options.vnicc.learning_timeout; if (qeth_card_hw_is_reachable(card)) diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ff8c9d527bb4..bfdf41537cf1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -688,7 +688,10 @@ struct mlx5_ifc_flow_table_nic_cap_bits { u8 nic_rx_multi_path_tirs[0x1]; u8 nic_rx_multi_path_tirs_fts[0x1]; u8 allow_sniffer_and_nic_rx_shared_tir[0x1]; - u8 reserved_at_3[0x1d]; + u8 reserved_at_3[0x4]; + u8 sw_owner_reformat_supported[0x1]; + u8 reserved_at_8[0x18]; + u8 encap_general_header[0x1]; u8 reserved_at_21[0xa]; u8 log_max_packet_reformat_context[0x5]; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9f1f633235f6..6c3f7032e8d9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -72,6 +72,8 @@ void netdev_set_default_ethtool_ops(struct net_device *dev, #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +#define MAX_NEST_DEV 8 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -4389,11 +4391,8 @@ void *netdev_lower_get_next(struct net_device *dev, ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) -struct net_device *netdev_all_lower_get_next(struct net_device *dev, +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); -struct net_device *netdev_all_lower_get_next_rcu(struct net_device *dev, - struct list_head **iter); - int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, void *data), diff --git a/include/linux/rculist_nulls.h b/include/linux/rculist_nulls.h index e5b752027a03..9670b54b484a 100644 --- a/include/linux/rculist_nulls.h +++ b/include/linux/rculist_nulls.h @@ -145,6 +145,13 @@ static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n, } } +/* after that hlist_nulls_del will work */ +static inline void hlist_nulls_add_fake(struct hlist_nulls_node *n) +{ + n->pprev = &n->next; + n->next = (struct hlist_nulls_node *)NULLS_MARKER(NULL); +} + /** * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type * @tpos: the type * to use as a loop cursor. diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ca8806b69388..5b50278c4bc8 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -611,9 +611,15 @@ typedef unsigned char *sk_buff_data_t; * @next: Next buffer in list * @prev: Previous buffer in list * @tstamp: Time we arrived/left + * @skb_mstamp_ns: (aka @tstamp) earliest departure time; start point + * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp + * @list: queue head * @sk: Socket we are owned by + * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in + * fragmentation management * @dev: Device we arrived on/are leaving by + * @dev_scratch: (aka @dev) alternate use of @dev when @dev would be %NULL * @cb: Control buffer. Free for use by every layer. Put private vars here * @_skb_refdst: destination entry (with norefcount bit) * @sp: the security path, used for xfrm @@ -632,6 +638,9 @@ typedef unsigned char *sk_buff_data_t; * @pkt_type: Packet class * @fclone: skbuff clone status * @ipvs_property: skbuff is owned by ipvs + * @inner_protocol_type: whether the inner protocol is + * ENCAP_TYPE_ETHER or ENCAP_TYPE_IPPROTO + * @remcsum_offload: remote checksum offload is enabled * @offload_fwd_mark: Packet was L2-forwarded in hardware * @offload_l3_fwd_mark: Packet was L3-forwarded in hardware * @tc_skip_classify: do not classify packet. set by IFB device @@ -650,6 +659,8 @@ typedef unsigned char *sk_buff_data_t; * @tc_index: Traffic control index * @hash: the packet hash * @queue_mapping: Queue mapping for multiqueue devices + * @head_frag: skb was allocated from page fragments, + * not allocated by kmalloc() or vmalloc(). * @pfmemalloc: skbuff was allocated from PFMEMALLOC reserves * @active_extensions: active extensions (skb_ext_id types) * @ndisc_nodetype: router type (from link layer) @@ -660,15 +671,28 @@ typedef unsigned char *sk_buff_data_t; * @wifi_acked_valid: wifi_acked was set * @wifi_acked: whether frame was acked on wifi or not * @no_fcs: Request NIC to treat last 4 bytes as Ethernet FCS + * @encapsulation: indicates the inner headers in the skbuff are valid + * @encap_hdr_csum: software checksum is needed + * @csum_valid: checksum is already valid * @csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL + * @csum_complete_sw: checksum was completed by software + * @csum_level: indicates the number of consecutive checksums found in + * the packet minus one that have been verified as + * CHECKSUM_UNNECESSARY (max 3) * @dst_pending_confirm: need to confirm neighbour * @decrypted: Decrypted SKB * @napi_id: id of the NAPI struct this skb came from + * @sender_cpu: (aka @napi_id) source CPU in XPS * @secmark: security marking * @mark: Generic packet mark + * @reserved_tailroom: (aka @mark) number of bytes of free space available + * at the tail of an sk_buff + * @vlan_present: VLAN tag is present * @vlan_proto: vlan encapsulation protocol * @vlan_tci: vlan tag control information * @inner_protocol: Protocol (encapsulation) + * @inner_ipproto: (aka @inner_protocol) stores ipproto when + * skb->inner_protocol_type == ENCAP_TYPE_IPPROTO; * @inner_transport_header: Inner transport layer header (encapsulation) * @inner_network_header: Network layer header (encapsulation) * @inner_mac_header: Link layer header (encapsulation) @@ -750,7 +774,9 @@ struct sk_buff { #endif #define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) + /* private: */ __u8 __cloned_offset[0]; + /* public: */ __u8 cloned:1, nohdr:1, fclone:2, @@ -775,7 +801,9 @@ struct sk_buff { #endif #define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + /* private: */ __u8 __pkt_type_offset[0]; + /* public: */ __u8 pkt_type:3; __u8 ignore_df:1; __u8 nf_trace:1; @@ -798,7 +826,9 @@ struct sk_buff { #define PKT_VLAN_PRESENT_BIT 0 #endif #define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) + /* private: */ __u8 __pkt_vlan_present_offset[0]; + /* public: */ __u8 vlan_present:1; __u8 csum_complete_sw:1; __u8 csum_level:2; diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index e9391e877f9a..628383915827 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -5,6 +5,7 @@ #include <linux/types.h> #include <linux/in6.h> #include <linux/siphash.h> +#include <linux/string.h> #include <uapi/linux/if_ether.h> struct sk_buff; @@ -348,4 +349,12 @@ struct bpf_flow_dissector { void *data_end; }; +static inline void +flow_dissector_init_keys(struct flow_dissector_key_control *key_control, + struct flow_dissector_key_basic *key_basic) +{ + memset(key_control, 0, sizeof(*key_control)); + memset(key_basic, 0, sizeof(*key_basic)); +} + #endif diff --git a/include/net/sock.h b/include/net/sock.h index 02162b0378f7..328564525526 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -117,19 +117,26 @@ typedef __u64 __bitwise __addrpair; * struct sock_common - minimal network layer representation of sockets * @skc_daddr: Foreign IPv4 addr * @skc_rcv_saddr: Bound local IPv4 addr + * @skc_addrpair: 8-byte-aligned __u64 union of @skc_daddr & @skc_rcv_saddr * @skc_hash: hash value used with various protocol lookup tables * @skc_u16hashes: two u16 hash values used by UDP lookup tables * @skc_dport: placeholder for inet_dport/tw_dport * @skc_num: placeholder for inet_num/tw_num + * @skc_portpair: __u32 union of @skc_dport & @skc_num * @skc_family: network address family * @skc_state: Connection state * @skc_reuse: %SO_REUSEADDR setting * @skc_reuseport: %SO_REUSEPORT setting + * @skc_ipv6only: socket is IPV6 only + * @skc_net_refcnt: socket is using net ref counting * @skc_bound_dev_if: bound device index if != 0 * @skc_bind_node: bind hash linkage for various protocol lookup tables * @skc_portaddr_node: second hash linkage for UDP/UDP-Lite protocol * @skc_prot: protocol handlers inside a network family * @skc_net: reference to the network namespace of this socket + * @skc_v6_daddr: IPV6 destination address + * @skc_v6_rcv_saddr: IPV6 source address + * @skc_cookie: socket's cookie value * @skc_node: main hash linkage for various protocol lookup tables * @skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol * @skc_tx_queue_mapping: tx queue number for this connection @@ -137,7 +144,15 @@ typedef __u64 __bitwise __addrpair; * @skc_flags: place holder for sk_flags * %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, * %SO_OOBINLINE settings, %SO_TIMESTAMPING settings + * @skc_listener: connection request listener socket (aka rsk_listener) + * [union with @skc_flags] + * @skc_tw_dr: (aka tw_dr) ptr to &struct inet_timewait_death_row + * [union with @skc_flags] * @skc_incoming_cpu: record/match cpu processing incoming packets + * @skc_rcv_wnd: (aka rsk_rcv_wnd) TCP receive window size (possibly scaled) + * [union with @skc_incoming_cpu] + * @skc_tw_rcv_nxt: (aka tw_rcv_nxt) TCP window next expected seq number + * [union with @skc_incoming_cpu] * @skc_refcnt: reference count * * This is the minimal network layer representation of sockets, the header @@ -245,6 +260,7 @@ struct bpf_sk_storage; * @sk_dst_cache: destination cache * @sk_dst_pending_confirm: need to confirm neighbour * @sk_policy: flow policy + * @sk_rx_skb_cache: cache copy of recently accessed RX skb * @sk_receive_queue: incoming packets * @sk_wmem_alloc: transmit queue bytes committed * @sk_tsq_flags: TCP Small Queues flags @@ -265,6 +281,8 @@ struct bpf_sk_storage; * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) + * @sk_route_forced_caps: static, forced route capabilities + * (set in tcp_init_sock()) * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments @@ -303,6 +321,8 @@ struct bpf_sk_storage; * @sk_frag: cached page frag * @sk_peek_off: current peek_offset value * @sk_send_head: front of stuff to transmit + * @tcp_rtx_queue: TCP re-transmit queue [union with @sk_send_head] + * @sk_tx_skb_cache: cache copy of recently accessed TX skb * @sk_security: used by security modules * @sk_mark: generic packet mark * @sk_cgrp_data: cgroup data for this cgroup @@ -313,11 +333,14 @@ struct bpf_sk_storage; * @sk_write_space: callback to indicate there is bf sending space available * @sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE) * @sk_backlog_rcv: callback to process the backlog + * @sk_validate_xmit_skb: ptr to an optional validate function * @sk_destruct: called at sock freeing time, i.e. when all refcnt == 0 * @sk_reuseport_cb: reuseport group container + * @sk_bpf_storage: ptr to cache and control for bpf_sk_storage * @sk_rcu: used during RCU grace period * @sk_clockid: clockid used by time-based scheduling (SO_TXTIME) * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME + * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags */ struct sock { @@ -393,7 +416,9 @@ struct sock { struct sk_filter __rcu *sk_filter; union { struct socket_wq __rcu *sk_wq; + /* private: */ struct socket_wq *sk_wq_raw; + /* public: */ }; #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; @@ -2017,7 +2042,7 @@ static inline int skb_copy_to_page_nocache(struct sock *sk, struct iov_iter *fro * sk_wmem_alloc_get - returns write allocations * @sk: socket * - * Returns sk_wmem_alloc minus initial offset of one + * Return: sk_wmem_alloc minus initial offset of one */ static inline int sk_wmem_alloc_get(const struct sock *sk) { @@ -2028,7 +2053,7 @@ static inline int sk_wmem_alloc_get(const struct sock *sk) * sk_rmem_alloc_get - returns read allocations * @sk: socket * - * Returns sk_rmem_alloc + * Return: sk_rmem_alloc */ static inline int sk_rmem_alloc_get(const struct sock *sk) { @@ -2039,7 +2064,7 @@ static inline int sk_rmem_alloc_get(const struct sock *sk) * sk_has_allocations - check if allocations are outstanding * @sk: socket * - * Returns true if socket has write or read allocations + * Return: true if socket has write or read allocations */ static inline bool sk_has_allocations(const struct sock *sk) { @@ -2050,7 +2075,7 @@ static inline bool sk_has_allocations(const struct sock *sk) * skwq_has_sleeper - check if there are any waiting processes * @wq: struct socket_wq * - * Returns true if socket_wq has waiting processes + * Return: true if socket_wq has waiting processes * * The purpose of the skwq_has_sleeper and sock_poll_wait is to wrap the memory * barrier call. They were added due to the race found within the tcp code. @@ -2238,6 +2263,9 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest * inside other socket operations and end up recursing into sk_page_frag() * while it's already in use. + * + * Return: a per task page_frag if context allows that, + * otherwise a per socket one. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { @@ -2432,6 +2460,7 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from @@ -2440,7 +2469,6 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. */ -DECLARE_STATIC_KEY_FALSE(tcp_rx_skb_cache_key); static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb) { __skb_unlink(skb, &sk->sk_receive_queue); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f1d74a2bd234..22f235260a3a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/include/uapi/linux/netfilter/nf_conntrack_common.h b/include/uapi/linux/netfilter/nf_conntrack_common.h index 336014bf8868..b6f0bb1dc799 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_common.h +++ b/include/uapi/linux/netfilter/nf_conntrack_common.h @@ -97,6 +97,15 @@ enum ip_conntrack_status { IPS_UNTRACKED_BIT = 12, IPS_UNTRACKED = (1 << IPS_UNTRACKED_BIT), +#ifdef __KERNEL__ + /* Re-purposed for in-kernel use: + * Tags a conntrack entry that clashed with an existing entry + * on insert. + */ + IPS_NAT_CLASH_BIT = IPS_UNTRACKED_BIT, + IPS_NAT_CLASH = IPS_UNTRACKED, +#endif + /* Conntrack got a helper explicitly attached via CT target. */ IPS_HELPER_BIT = 13, IPS_HELPER = (1 << IPS_HELPER_BIT), @@ -110,7 +119,8 @@ enum ip_conntrack_status { */ IPS_UNCHANGEABLE_MASK = (IPS_NAT_DONE_MASK | IPS_NAT_MASK | IPS_EXPECTED | IPS_CONFIRMED | IPS_DYING | - IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_OFFLOAD), + IPS_SEQ_ADJUST | IPS_TEMPLATE | IPS_UNTRACKED | + IPS_OFFLOAD), __IPS_MAX_BIT = 15, }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 805c43b083e9..787140095e58 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -4142,9 +4142,9 @@ int btf_distill_func_proto(struct bpf_verifier_log *log, * EFAULT - verifier bug * 0 - 99% match. The last 1% is validated by the verifier. */ -int btf_check_func_type_match(struct bpf_verifier_log *log, - struct btf *btf1, const struct btf_type *t1, - struct btf *btf2, const struct btf_type *t2) +static int btf_check_func_type_match(struct bpf_verifier_log *log, + struct btf *btf1, const struct btf_type *t1, + struct btf *btf2, const struct btf_type *t2) { const struct btf_param *args1, *args2; const char *fn1, *fn2, *s1, *s2; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 2d182c4ee9d9..a1468e3f5af2 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -56,6 +56,7 @@ struct htab_elem { union { struct bpf_htab *htab; struct pcpu_freelist_node fnode; + struct htab_elem *batch_flink; }; }; }; @@ -126,6 +127,17 @@ free_elems: bpf_map_area_free(htab->elems); } +/* The LRU list has a lock (lru_lock). Each htab bucket has a lock + * (bucket_lock). If both locks need to be acquired together, the lock + * order is always lru_lock -> bucket_lock and this only happens in + * bpf_lru_list.c logic. For example, certain code path of + * bpf_lru_pop_free(), which is called by function prealloc_lru_pop(), + * will acquire lru_lock first followed by acquiring bucket_lock. + * + * In hashtab.c, to avoid deadlock, lock acquisition of + * bucket_lock followed by lru_lock is not allowed. In such cases, + * bucket_lock needs to be released first before acquiring lru_lock. + */ static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, u32 hash) { @@ -1256,10 +1268,12 @@ __htab_map_lookup_and_delete_batch(struct bpf_map *map, void __user *ukeys = u64_to_user_ptr(attr->batch.keys); void *ubatch = u64_to_user_ptr(attr->batch.in_batch); u32 batch, max_count, size, bucket_size; + struct htab_elem *node_to_free = NULL; u64 elem_map_flags, map_flags; struct hlist_nulls_head *head; struct hlist_nulls_node *n; - unsigned long flags; + unsigned long flags = 0; + bool locked = false; struct htab_elem *l; struct bucket *b; int ret = 0; @@ -1319,15 +1333,25 @@ again_nocopy: dst_val = values; b = &htab->buckets[batch]; head = &b->head; - raw_spin_lock_irqsave(&b->lock, flags); + /* do not grab the lock unless need it (bucket_cnt > 0). */ + if (locked) + raw_spin_lock_irqsave(&b->lock, flags); bucket_cnt = 0; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) bucket_cnt++; + if (bucket_cnt && !locked) { + locked = true; + goto again_nocopy; + } + if (bucket_cnt > (max_count - total)) { if (total == 0) ret = -ENOSPC; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1337,6 +1361,9 @@ again_nocopy: if (bucket_cnt > bucket_size) { bucket_size = bucket_cnt; + /* Note that since bucket_cnt > 0 here, it is implicit + * that the locked was grabbed, so release it. + */ raw_spin_unlock_irqrestore(&b->lock, flags); rcu_read_unlock(); this_cpu_dec(bpf_prog_active); @@ -1346,6 +1373,10 @@ again_nocopy: goto alloc; } + /* Next block is only safe to run if you have grabbed the lock */ + if (!locked) + goto next_batch; + hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { memcpy(dst_key, l->key, key_size); @@ -1370,16 +1401,33 @@ again_nocopy: } if (do_delete) { hlist_nulls_del_rcu(&l->hash_node); - if (is_lru_map) - bpf_lru_push_free(&htab->lru, &l->lru_node); - else + + /* bpf_lru_push_free() will acquire lru_lock, which + * may cause deadlock. See comments in function + * prealloc_lru_pop(). Let us do bpf_lru_push_free() + * after releasing the bucket lock. + */ + if (is_lru_map) { + l->batch_flink = node_to_free; + node_to_free = l; + } else { free_htab_elem(htab, l); + } } dst_key += key_size; dst_val += value_size; } raw_spin_unlock_irqrestore(&b->lock, flags); + locked = false; + + while (node_to_free) { + l = node_to_free; + node_to_free = node_to_free->batch_flink; + bpf_lru_push_free(&htab->lru, &l->lru_node); + } + +next_batch: /* If we are not copying data, we can go to next bucket and avoid * unlocking the rcu. */ diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index 2c5dc6541ece..bd09290e3648 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -321,7 +321,7 @@ int bpf_prog_offload_info_fill(struct bpf_prog_info *info, ulen = info->jited_prog_len; info->jited_prog_len = aux->offload->jited_len; - if (info->jited_prog_len & ulen) { + if (info->jited_prog_len && ulen) { uinsns = u64_to_user_ptr(info->jited_prog_insns); ulen = min_t(u32, info->jited_prog_len, ulen); if (copy_to_user(uinsns, aux->offload->jited_image, ulen)) { diff --git a/net/Kconfig b/net/Kconfig index b0937a700f01..2eeb0e55f7c9 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -189,7 +189,6 @@ config BRIDGE_NETFILTER depends on NETFILTER_ADVANCED select NETFILTER_FAMILY_BRIDGE select SKB_EXTENSIONS - default m ---help--- Enabling this option will let arptables resp. iptables see bridged ARP resp. IP traffic. If you want a bridging firewall, you probably diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 6856a6d9282b..1f14b8455345 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -63,7 +63,8 @@ struct net_bridge_port *br_get_port(struct net_bridge *br, u16 port_no) { struct net_bridge_port *p; - list_for_each_entry_rcu(p, &br->port_list, list) { + list_for_each_entry_rcu(p, &br->port_list, list, + lockdep_is_held(&br->lock)) { if (p->port_no == port_no) return p; } diff --git a/net/core/dev.c b/net/core/dev.c index a6316b336128..e10bd680dc03 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -146,7 +146,6 @@ #include "net-sysfs.h" #define MAX_GRO_SKBS 8 -#define MAX_NEST_DEV 8 /* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@ -331,6 +330,12 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) name_node = netdev_name_node_lookup(net, name); if (!name_node) return -ENOENT; + /* lookup might have found our primary name or a name belonging + * to another device. + */ + if (name_node == dev->name_node || name_node->dev != dev) + return -EINVAL; + __netdev_name_node_alt_destroy(name_node); return 0; @@ -3657,26 +3662,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && READ_ONCE(q->empty) && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -7201,8 +7188,8 @@ static int __netdev_walk_all_lower_dev(struct net_device *dev, return 0; } -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -7214,6 +7201,7 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); static u8 __netdev_upper_depth(struct net_device *dev) { diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 3e7e15278c46..bd7eba9066f8 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -974,7 +974,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 09c44bf2e1d2..e1152f4ffe33 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3504,27 +3504,25 @@ static int rtnl_alt_ifname(int cmd, struct net_device *dev, struct nlattr *attr, if (err) return err; - alt_ifname = nla_data(attr); + alt_ifname = nla_strdup(attr, GFP_KERNEL); + if (!alt_ifname) + return -ENOMEM; + if (cmd == RTM_NEWLINKPROP) { - alt_ifname = kstrdup(alt_ifname, GFP_KERNEL); - if (!alt_ifname) - return -ENOMEM; err = netdev_name_node_alt_create(dev, alt_ifname); - if (err) { - kfree(alt_ifname); - return err; - } + if (!err) + alt_ifname = NULL; } else if (cmd == RTM_DELLINKPROP) { err = netdev_name_node_alt_destroy(dev, alt_ifname); - if (err) - return err; } else { - WARN_ON(1); - return 0; + WARN_ON_ONCE(1); + err = -EINVAL; } - *changed = true; - return 0; + kfree(alt_ifname); + if (!err) + *changed = true; + return err; } static int rtnl_linkprop(int cmd, struct sk_buff *skb, struct nlmsghdr *nlh, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 864cb9e9622f..e1101a4f90a6 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -467,7 +467,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -527,7 +526,6 @@ struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, return NULL; } - /* use OR instead of assignment to avoid clearing of bits in mask */ if (nc->page.pfmemalloc) skb->pfmemalloc = 1; skb->head_frag = 1; @@ -4805,9 +4803,9 @@ static __sum16 *skb_checksum_setup_ip(struct sk_buff *skb, typeof(IPPROTO_IP) proto, unsigned int off) { - switch (proto) { - int err; + int err; + switch (proto) { case IPPROTO_TCP: err = skb_maybe_pull_tail(skb, off + sizeof(struct tcphdr), off + MAX_TCP_HDR_LEN); diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index fce45dac4205..8977fe1f3946 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -447,7 +447,10 @@ ethnl_update_bitset32_verbose(u32 *bitmap, unsigned int nbits, "mask only allowed in compact bitset"); return -EINVAL; } + no_mask = tb[ETHTOOL_A_BITSET_NOMASK]; + if (no_mask) + ethnl_bitmap32_clear(bitmap, 0, nbits, mod); nla_for_each_nested(bit_attr, tb[ETHTOOL_A_BITSET_BITS], rem) { bool old_val, new_val; diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 364ea2cc028e..3ba7f61be107 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -155,7 +155,8 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, new_node->seq_out[i] = seq_out; spin_lock_bh(&hsr->list_lock); - list_for_each_entry_rcu(node, node_db, mac_list) { + list_for_each_entry_rcu(node, node_db, mac_list, + lockdep_is_held(&hsr->list_lock)) { if (ether_addr_equal(node->macaddress_A, addr)) goto out; if (ether_addr_equal(node->macaddress_B, addr)) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db76b9609299..08a41f1e1cd2 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1857,8 +1857,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 58fbde244381..72abf892302f 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1102,8 +1102,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1146,7 +1145,9 @@ next_iter: } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 55bfc5149d0c..781ca8c07a0d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -437,8 +437,6 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, return -ENOENT; switch (type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -452,7 +450,10 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, break; } return 0; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if (code == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -468,6 +469,7 @@ static int ip6gre_err(struct sk_buff *skb, struct inet6_skb_parm *opt, t->parms.name); } return 0; + } case ICMPV6_PKT_TOOBIG: ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); return 0; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 5d65436ad5ad..4703b09808d0 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -517,8 +517,6 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, err = 0; switch (*type) { - struct ipv6_tlv_tnl_enc_lim *tel; - __u32 mtu, teli; case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); @@ -531,7 +529,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; - case ICMPV6_PARAMPROB: + case ICMPV6_PARAMPROB: { + struct ipv6_tlv_tnl_enc_lim *tel; + __u32 teli; + teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); @@ -548,7 +549,10 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, t->parms.name); } break; - case ICMPV6_PKT_TOOBIG: + } + case ICMPV6_PKT_TOOBIG: { + __u32 mtu; + ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; @@ -562,6 +566,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, rel_msg = 1; } break; + } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 4fbdc60b4e07..2931224b674e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5198,6 +5198,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/mptcp/Kconfig b/net/mptcp/Kconfig index 49f6054e7f4e..a9ed3bf1d93f 100644 --- a/net/mptcp/Kconfig +++ b/net/mptcp/Kconfig @@ -4,6 +4,7 @@ config MPTCP depends on INET select SKB_EXTENSIONS select CRYPTO_LIB_SHA256 + select CRYPTO help Multipath TCP (MPTCP) connections send and receive data over multiple subflows in order to utilize multiple network paths. Each subflow diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 030dee668e0a..e9aa6807b5be 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -755,60 +755,50 @@ static int mptcp_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); /* @@ the meaning of setsockopt() when the socket is connected and - * there are multiple subflows is not defined. + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when TCP socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_setsockopt(ssock->sk, level, optname, optval, + optlen); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_setsockopt(ssk, level, optname, optval, optlen); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { struct mptcp_sock *msk = mptcp_sk(sk); - int ret = -EOPNOTSUPP; struct socket *ssock; - struct sock *ssk; pr_debug("msk=%p", msk); - /* @@ the meaning of getsockopt() when the socket is connected and - * there are multiple subflows is not defined. + /* @@ the meaning of setsockopt() when the socket is connected and + * there are multiple subflows is not yet defined. It is up to the + * MPTCP-level socket to configure the subflows until the subflow + * is in TCP fallback, when socket options are passed through + * to the one remaining subflow. */ lock_sock(sk); - ssock = __mptcp_socket_create(msk, MPTCP_SAME_STATE); - if (IS_ERR(ssock)) { - release_sock(sk); - return ret; - } + ssock = __mptcp_tcp_fallback(msk); + if (ssock) + return tcp_getsockopt(ssock->sk, level, optname, optval, + option); - ssk = ssock->sk; - sock_hold(ssk); release_sock(sk); - ret = tcp_getsockopt(ssk, level, optname, optval, option); - sock_put(ssk); - - return ret; + return -EOPNOTSUPP; } static int mptcp_get_port(struct sock *sk, unsigned short snum) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8a99a2930284..9f8663b30456 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -56,8 +56,8 @@ #define MPTCP_DSS_FLAG_MASK (0x1F) /* MPTCP socket flags */ -#define MPTCP_DATA_READY BIT(0) -#define MPTCP_SEND_SPACE BIT(1) +#define MPTCP_DATA_READY 0 +#define MPTCP_SEND_SPACE 1 /* MPTCP connection sock */ struct mptcp_sock { diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index d1305423640f..1927fc296f95 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -894,32 +894,175 @@ static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } } -/* Resolve race on insertion if this protocol allows this. */ +static void __nf_conntrack_insert_prepare(struct nf_conn *ct) +{ + struct nf_conn_tstamp *tstamp; + + atomic_inc(&ct->ct_general.use); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_get_real_ns(); +} + +static int __nf_ct_resolve_clash(struct sk_buff *skb, + struct nf_conntrack_tuple_hash *h) +{ + /* This is the conntrack entry already in hashes that won race. */ + struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + + loser_ct = nf_ct_get(skb, &ctinfo); + + if (nf_ct_is_dying(ct)) + return NF_DROP; + + if (!atomic_inc_not_zero(&ct->ct_general.use)) + return NF_DROP; + + if (((ct->status & IPS_NAT_DONE_MASK) == 0) || + nf_ct_match(ct, loser_ct)) { + struct net *net = nf_ct_net(ct); + + nf_ct_acct_merge(ct, ctinfo, loser_ct); + nf_ct_add_to_dying_list(loser_ct); + nf_conntrack_put(&loser_ct->ct_general); + nf_ct_set(skb, ct, ctinfo); + + NF_CT_STAT_INC(net, insert_failed); + return NF_ACCEPT; + } + + nf_ct_put(ct); + return NF_DROP; +} + +/** + * nf_ct_resolve_clash_harder - attempt to insert clashing conntrack entry + * + * @skb: skb that causes the collision + * @repl_idx: hash slot for reply direction + * + * Called when origin or reply direction had a clash. + * The skb can be handled without packet drop provided the reply direction + * is unique or there the existing entry has the identical tuple in both + * directions. + * + * Caller must hold conntrack table locks to prevent concurrent updates. + * + * Returns NF_DROP if the clash could not be handled. + */ +static int nf_ct_resolve_clash_harder(struct sk_buff *skb, u32 repl_idx) +{ + struct nf_conn *loser_ct = (struct nf_conn *)skb_nfct(skb); + const struct nf_conntrack_zone *zone; + struct nf_conntrack_tuple_hash *h; + struct hlist_nulls_node *n; + struct net *net; + + zone = nf_ct_zone(loser_ct); + net = nf_ct_net(loser_ct); + + /* Reply direction must never result in a clash, unless both origin + * and reply tuples are identical. + */ + hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[repl_idx], hnnode) { + if (nf_ct_key_equal(h, + &loser_ct->tuplehash[IP_CT_DIR_REPLY].tuple, + zone, net)) + return __nf_ct_resolve_clash(skb, h); + } + + /* We want the clashing entry to go away real soon: 1 second timeout. */ + loser_ct->timeout = nfct_time_stamp + HZ; + + /* IPS_NAT_CLASH removes the entry automatically on the first + * reply. Also prevents UDP tracker from moving the entry to + * ASSURED state, i.e. the entry can always be evicted under + * pressure. + */ + loser_ct->status |= IPS_FIXED_TIMEOUT | IPS_NAT_CLASH; + + __nf_conntrack_insert_prepare(loser_ct); + + /* fake add for ORIGINAL dir: we want lookups to only find the entry + * already in the table. This also hides the clashing entry from + * ctnetlink iteration, i.e. conntrack -L won't show them. + */ + hlist_nulls_add_fake(&loser_ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode); + + hlist_nulls_add_head_rcu(&loser_ct->tuplehash[IP_CT_DIR_REPLY].hnnode, + &nf_conntrack_hash[repl_idx]); + return NF_ACCEPT; +} + +/** + * nf_ct_resolve_clash - attempt to handle clash without packet drop + * + * @skb: skb that causes the clash + * @h: tuplehash of the clashing entry already in table + * @hash_reply: hash slot for reply direction + * + * A conntrack entry can be inserted to the connection tracking table + * if there is no existing entry with an identical tuple. + * + * If there is one, @skb (and the assocated, unconfirmed conntrack) has + * to be dropped. In case @skb is retransmitted, next conntrack lookup + * will find the already-existing entry. + * + * The major problem with such packet drop is the extra delay added by + * the packet loss -- it will take some time for a retransmit to occur + * (or the sender to time out when waiting for a reply). + * + * This function attempts to handle the situation without packet drop. + * + * If @skb has no NAT transformation or if the colliding entries are + * exactly the same, only the to-be-confirmed conntrack entry is discarded + * and @skb is associated with the conntrack entry already in the table. + * + * Failing that, the new, unconfirmed conntrack is still added to the table + * provided that the collision only occurs in the ORIGINAL direction. + * The new entry will be added after the existing one in the hash list, + * so packets in the ORIGINAL direction will continue to match the existing + * entry. The new entry will also have a fixed timeout so it expires -- + * due to the collision, it will not see bidirectional traffic. + * + * Returns NF_DROP if the clash could not be resolved. + */ static __cold noinline int -nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, - enum ip_conntrack_info ctinfo, - struct nf_conntrack_tuple_hash *h) +nf_ct_resolve_clash(struct sk_buff *skb, struct nf_conntrack_tuple_hash *h, + u32 reply_hash) { /* This is the conntrack entry already in hashes that won race. */ struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); const struct nf_conntrack_l4proto *l4proto; - enum ip_conntrack_info oldinfo; - struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); + enum ip_conntrack_info ctinfo; + struct nf_conn *loser_ct; + struct net *net; + int ret; + + loser_ct = nf_ct_get(skb, &ctinfo); + net = nf_ct_net(loser_ct); l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->allow_clash && - !nf_ct_is_dying(ct) && - atomic_inc_not_zero(&ct->ct_general.use)) { - if (((ct->status & IPS_NAT_DONE_MASK) == 0) || - nf_ct_match(ct, loser_ct)) { - nf_ct_acct_merge(ct, ctinfo, loser_ct); - nf_conntrack_put(&loser_ct->ct_general); - nf_ct_set(skb, ct, oldinfo); - return NF_ACCEPT; - } - nf_ct_put(ct); - } + if (!l4proto->allow_clash) + goto drop; + + ret = __nf_ct_resolve_clash(skb, h); + if (ret == NF_ACCEPT) + return ret; + + ret = nf_ct_resolve_clash_harder(skb, reply_hash); + if (ret == NF_ACCEPT) + return ret; + +drop: + nf_ct_add_to_dying_list(loser_ct); NF_CT_STAT_INC(net, drop); + NF_CT_STAT_INC(net, insert_failed); return NF_DROP; } @@ -932,7 +1075,6 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; - struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -989,6 +1131,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) if (unlikely(nf_ct_is_dying(ct))) { nf_ct_add_to_dying_list(ct); + NF_CT_STAT_INC(net, insert_failed); goto dying; } @@ -1009,13 +1152,8 @@ __nf_conntrack_confirm(struct sk_buff *skb) setting time, otherwise we'd get timer wrap in weird delay cases. */ ct->timeout += nfct_time_stamp; - atomic_inc(&ct->ct_general.use); - ct->status |= IPS_CONFIRMED; - /* set conntrack timestamp, if enabled. */ - tstamp = nf_conn_tstamp_find(ct); - if (tstamp) - tstamp->start = ktime_get_real_ns(); + __nf_conntrack_insert_prepare(ct); /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers @@ -1035,11 +1173,9 @@ __nf_conntrack_confirm(struct sk_buff *skb) return NF_ACCEPT; out: - nf_ct_add_to_dying_list(ct); - ret = nf_ct_resolve_clash(net, skb, ctinfo, h); + ret = nf_ct_resolve_clash(skb, h, reply_hash); dying: nf_conntrack_double_unlock(hash, reply_hash); - NF_CT_STAT_INC(net, insert_failed); local_bh_enable(); return ret; } diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 7365b43f8f98..760ca2422816 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -81,6 +81,18 @@ static bool udp_error(struct sk_buff *skb, return false; } +static void nf_conntrack_udp_refresh_unreplied(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + u32 extra_jiffies) +{ + if (unlikely(ctinfo == IP_CT_ESTABLISHED_REPLY && + ct->status & IPS_NAT_CLASH)) + nf_ct_kill(ct); + else + nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies); +} + /* Returns verdict for packet, and may modify conntracktype */ int nf_conntrack_udp_packet(struct nf_conn *ct, struct sk_buff *skb, @@ -116,8 +128,8 @@ int nf_conntrack_udp_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } @@ -198,8 +210,8 @@ int nf_conntrack_udplite_packet(struct nf_conn *ct, if (!test_and_set_bit(IPS_ASSURED_BIT, &ct->status)) nf_conntrack_event_cache(IPCT_ASSURED, ct); } else { - nf_ct_refresh_acct(ct, ctinfo, skb, - timeouts[UDP_CT_UNREPLIED]); + nf_conntrack_udp_refresh_unreplied(ct, skb, ctinfo, + timeouts[UDP_CT_UNREPLIED]); } return NF_ACCEPT; } diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 83e1db37c3b0..06f00cdc3891 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -847,9 +847,6 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, { int err; - if (!nf_flowtable_hw_offload(flowtable)) - return 0; - if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; @@ -876,6 +873,9 @@ int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, struct flow_block_offload bo; int err; + if (!nf_flowtable_hw_offload(flowtable)) + return 0; + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index f0cb1e13af50..feac8553f6d9 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -203,7 +203,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * * Matching @@ -298,7 +298,7 @@ * :: * * rule indices in last field: 0 1 - * map to elements: 0x42 0x66 + * map to elements: 0x66 0x42 * * the matching element is at 0x42. * @@ -503,7 +503,7 @@ static int pipapo_refill(unsigned long *map, int len, int rules, return -1; } - if (unlikely(match_only)) { + if (match_only) { bitmap_clear(map, i, 1); return i; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index bccd47cd7190..7a2c4b8408c4 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/mutex.h> #include <linux/kernel.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/xt_hashlimit.h> #define XT_HASHLIMIT_ALL (XT_HASHLIMIT_HASH_DIP | XT_HASHLIMIT_HASH_DPT | \ @@ -114,7 +115,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -315,7 +316,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -420,7 +421,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -429,12 +430,11 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); + mutex_unlock(&hashlimit_mutex); htable_destroy(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -837,6 +837,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } +#define HASHLIMIT_MAX_SIZE 1048576 + static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, @@ -847,6 +849,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; + if (cfg->size > HASHLIMIT_MAX_SIZE) { + cfg->size = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); + } + if (cfg->max > HASHLIMIT_MAX_SIZE) { + cfg->max = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); + } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index f5d34da0646e..a1f2320ecc16 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -143,7 +143,8 @@ static struct netlbl_dom_map *netlbl_domhsh_search(const char *domain, if (domain != NULL) { bkt = netlbl_domhsh_hash(domain); bkt_list = &netlbl_domhsh_rcu_deref(netlbl_domhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_domhsh_lock)) if (iter->valid && netlbl_family_match(iter->family, family) && strcmp(iter->domain, domain) == 0) diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index d2e4ab8d1cb1..77bb1bb22c3b 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -207,7 +207,8 @@ static struct netlbl_unlhsh_iface *netlbl_unlhsh_search_iface(int ifindex) bkt = netlbl_unlhsh_hash(ifindex); bkt_list = &netlbl_unlhsh_rcu_deref(netlbl_unlhsh)->tbl[bkt]; - list_for_each_entry_rcu(iter, bkt_list, list) + list_for_each_entry_rcu(iter, bkt_list, list, + lockdep_is_held(&netlbl_unlhsh_lock)) if (iter->valid && iter->ifindex == ifindex) return iter; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 4e31721e7293..edf3e285e242 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1014,7 +1014,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1033,7 +1034,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 659c2a790fe7..c047afd12116 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -179,7 +179,8 @@ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) struct hlist_head *head; head = vport_hash_bucket(dp, port_no); - hlist_for_each_entry_rcu(vport, head, dp_hash_node) { + hlist_for_each_entry_rcu(vport, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (vport->port_no == port_no) return vport; } @@ -2042,7 +2043,8 @@ static unsigned int ovs_get_max_headroom(struct datapath *dp) int i; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) { - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) { + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) { dev = vport->dev; dev_headroom = netdev_get_fwd_headroom(dev); if (dev_headroom > max_headroom) @@ -2061,7 +2063,8 @@ static void ovs_update_headroom(struct datapath *dp, unsigned int new_headroom) dp->max_headroom = new_headroom; for (i = 0; i < DP_VPORT_HASH_BUCKETS; i++) - hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node) + hlist_for_each_entry_rcu(vport, &dp->ports[i], dp_hash_node, + lockdep_ovsl_is_held()) netdev_set_rx_headroom(vport->dev, new_headroom); } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 7da4230627f5..288122eec7c8 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2708,10 +2708,6 @@ static int validate_set(const struct nlattr *a, return -EINVAL; switch (key_type) { - const struct ovs_key_ipv4 *ipv4_key; - const struct ovs_key_ipv6 *ipv6_key; - int err; - case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: @@ -2723,7 +2719,9 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - case OVS_KEY_ATTR_TUNNEL: + case OVS_KEY_ATTR_TUNNEL: { + int err; + if (masked) return -EINVAL; /* Masked tunnel set not supported. */ @@ -2732,8 +2730,10 @@ static int validate_set(const struct nlattr *a, if (err) return err; break; + } + case OVS_KEY_ATTR_IPV4: { + const struct ovs_key_ipv4 *ipv4_key; - case OVS_KEY_ATTR_IPV4: if (eth_type != htons(ETH_P_IP)) return -EINVAL; @@ -2753,8 +2753,10 @@ static int validate_set(const struct nlattr *a, return -EINVAL; } break; + } + case OVS_KEY_ATTR_IPV6: { + const struct ovs_key_ipv6 *ipv6_key; - case OVS_KEY_ATTR_IPV6: if (eth_type != htons(ETH_P_IPV6)) return -EINVAL; @@ -2781,7 +2783,7 @@ static int validate_set(const struct nlattr *a, return -EINVAL; break; - + } case OVS_KEY_ATTR_TCP: if ((eth_type != htons(ETH_P_IP) && eth_type != htons(ETH_P_IPV6)) || diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index 5904e93e5765..fd8a01ca7a2d 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -585,7 +585,8 @@ static struct sw_flow *masked_flow_lookup(struct table_instance *ti, head = find_bucket(ti, hash); (*n_mask_hit)++; - hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, flow_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->mask == mask && flow->flow_table.hash == hash && flow_cmp_masked_key(flow, &masked_key, &mask->range)) return flow; @@ -769,7 +770,8 @@ struct sw_flow *ovs_flow_tbl_lookup_ufid(struct flow_table *tbl, hash = ufid_hash(ufid); head = find_bucket(ti, hash); - hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver]) { + hlist_for_each_entry_rcu(flow, head, ufid_table.node[ti->node_ver], + lockdep_ovsl_is_held()) { if (flow->ufid_table.hash == hash && ovs_flow_cmp_ufid(flow, ufid)) return flow; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 3323b79ff548..5010d1ddd4bd 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -61,7 +61,8 @@ static struct dp_meter *lookup_meter(const struct datapath *dp, struct hlist_head *head; head = meter_hash_bucket(dp, meter_id); - hlist_for_each_entry_rcu(meter, head, dp_hash_node) { + hlist_for_each_entry_rcu(meter, head, dp_hash_node, + lockdep_ovsl_is_held()) { if (meter->id == meter_id) return meter; } diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 5da9392b03d6..47febb4504f0 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -96,7 +96,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name) struct hlist_head *bucket = hash_bucket(net, name); struct vport *vport; - hlist_for_each_entry_rcu(vport, bucket, hash_node) + hlist_for_each_entry_rcu(vport, bucket, hash_node, + lockdep_ovsl_is_held()) if (!strcmp(name, ovs_vport_name(vport)) && net_eq(ovs_dp_get_net(vport->dp), net)) return vport; diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 3341eee87bf9..585e6b3b69ce 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -162,10 +162,9 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, if (write) gup_flags |= FOLL_WRITE; - ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); + ret = pin_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { - while (ret--) - put_page(pages[ret]); + unpin_user_pages(pages, ret); ret = -EFAULT; } @@ -300,8 +299,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * to release anything. */ if (!need_odp) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); + unpin_user_pages(pages, nr_pages); kfree(sg); } ret = PTR_ERR(trans_private); @@ -325,7 +323,12 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, if (cookie_ret) *cookie_ret = cookie; - if (args->cookie_addr && put_user(cookie, (u64 __user *)(unsigned long) args->cookie_addr)) { + if (args->cookie_addr && + put_user(cookie, (u64 __user *)(unsigned long)args->cookie_addr)) { + if (!need_odp) { + unpin_user_pages(pages, nr_pages); + kfree(sg); + } ret = -EFAULT; goto out; } @@ -496,9 +499,7 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) * is the case for a RDMA_READ which copies from remote * to local memory */ - if (!ro->op_write) - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, !ro->op_write); } } @@ -515,8 +516,7 @@ void rds_atomic_free_op(struct rm_atomic_op *ao) /* Mark page dirty if it was possibly modified, which * is the case for a RDMA_READ which copies from remote * to local memory */ - set_page_dirty(page); - put_page(page); + unpin_user_pages_dirty_lock(&page, 1, true); kfree(ao->op_notifier); ao->op_notifier = NULL; @@ -944,7 +944,7 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, return ret; err: if (page) - put_page(page); + unpin_user_page(page); rm->atomic.op_active = 0; kfree(rm->atomic.op_notifier); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 7e54d2ab5254..d32d4233d337 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -305,6 +305,7 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct cls_fl_filter *f; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 748e3b19ec1d..6a16af4b1ef6 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -2255,6 +2265,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2298,6 +2311,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2565,6 +2581,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2582,16 +2601,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 1ba5a92832bb..1c5574e2e058 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -593,7 +593,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -605,6 +605,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, struct tls_record_info, list); if (!info) return NULL; + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index df600487a68d..356f90e4522b 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -217,6 +217,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) static void xsk_flush(struct xdp_sock *xs) { xskq_prod_submit(xs->rx); + __xskq_cons_release(xs->umem->fq); sock_def_readable(&xs->sk); } @@ -304,6 +305,7 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem) rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { + __xskq_cons_release(xs->tx); xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index bec2af11853a..89a01ac4e079 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -271,7 +271,8 @@ static inline void xskq_cons_release(struct xsk_queue *q) { /* To improve performance, only update local state here. * Reflect this to global state when we get new entries - * from the ring in xskq_cons_get_entries(). + * from the ring in xskq_cons_get_entries() and whenever + * Rx or Tx processing are completed in the NAPI loop. */ q->cached_cons++; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f1d74a2bd234..22f235260a3a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1045,9 +1045,9 @@ union bpf_attr { * supports redirection to the egress interface, and accepts no * flag at all. * - * The same effect can be attained with the more generic - * **bpf_redirect_map**\ (), which requires specific maps to be - * used but offers better performance. + * The same effect can also be attained with the more generic + * **bpf_redirect_map**\ (), which uses a BPF map to store the + * redirect target instead of providing it directly to the helper. * Return * For XDP, the helper returns **XDP_REDIRECT** on success or * **XDP_ABORTED** on error. For other program types, the values @@ -1611,13 +1611,11 @@ union bpf_attr { * the caller. Any higher bits in the *flags* argument must be * unset. * - * When used to redirect packets to net devices, this helper - * provides a high performance increase over **bpf_redirect**\ (). - * This is due to various implementation details of the underlying - * mechanisms, one of which is the fact that **bpf_redirect_map**\ - * () tries to send packet as a "bulk" to the device. + * See also bpf_redirect(), which only supports redirecting to an + * ifindex, but doesn't require a map to do so. * Return - * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * **XDP_REDIRECT** on success, or the value of the two lower bits + * of the **flags* argument on error. * * int bpf_sk_redirect_map(struct sk_buff *skb, struct bpf_map *map, u32 key, u64 flags) * Description diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 514b1a524abb..7469c7dcc15e 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -24,6 +24,7 @@ #include <endian.h> #include <fcntl.h> #include <errno.h> +#include <ctype.h> #include <asm/unistd.h> #include <linux/err.h> #include <linux/kernel.h> @@ -1283,7 +1284,7 @@ static size_t bpf_map_mmap_sz(const struct bpf_map *map) static char *internal_map_name(struct bpf_object *obj, enum libbpf_map_type type) { - char map_name[BPF_OBJ_NAME_LEN]; + char map_name[BPF_OBJ_NAME_LEN], *p; const char *sfx = libbpf_type_to_btf_name[type]; int sfx_len = max((size_t)7, strlen(sfx)); int pfx_len = min((size_t)BPF_OBJ_NAME_LEN - sfx_len - 1, @@ -1292,6 +1293,11 @@ static char *internal_map_name(struct bpf_object *obj, snprintf(map_name, sizeof(map_name), "%.*s%.*s", pfx_len, obj->name, sfx_len, libbpf_type_to_btf_name[type]); + /* sanitise map name to characters allowed by kernel */ + for (p = map_name; *p && p < map_name + sizeof(map_name); p++) + if (!isalnum(*p) && *p != '_' && *p != '.') + *p = '_'; + return strdup(map_name); } diff --git a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c index 098bcae5f827..0800036ed654 100644 --- a/tools/testing/selftests/bpf/prog_tests/select_reuseport.c +++ b/tools/testing/selftests/bpf/prog_tests/select_reuseport.c @@ -506,8 +506,10 @@ static void test_syncookie(int type, sa_family_t family) .pass_on_failure = 0, }; - if (type != SOCK_STREAM) + if (type != SOCK_STREAM) { + test__skip(); return; + } /* * +1 for TCP-SYN and @@ -822,8 +824,10 @@ void test_select_reuseport(void) goto out; saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL); + if (saved_tcp_fo < 0) + goto out; saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL); - if (saved_tcp_syncookie < 0 || saved_tcp_syncookie < 0) + if (saved_tcp_syncookie < 0) goto out; if (enable_fastopen()) diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index 07f5b462c2ef..aa43e0bd210c 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -3,6 +3,11 @@ #include "test_progs.h" +#define TCP_REPAIR 19 /* TCP sock is under repair right now */ + +#define TCP_REPAIR_ON 1 +#define TCP_REPAIR_OFF_NO_WP -1 /* Turn off without window probes */ + static int connected_socket_v4(void) { struct sockaddr_in addr = { diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh index 6dd403103800..60273f1bc7d9 100755 --- a/tools/testing/selftests/net/fib_tests.sh +++ b/tools/testing/selftests/net/fib_tests.sh @@ -910,6 +910,12 @@ ipv6_rt_replace_mpath() check_route6 "2001:db8:104::/64 via 2001:db8:101::3 dev veth1 metric 1024" log_test $? 0 "Multipath with single path via multipath attribute" + # multipath with dev-only + add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" + run_cmd "$IP -6 ro replace 2001:db8:104::/64 dev veth1" + check_route6 "2001:db8:104::/64 dev veth1 metric 1024" + log_test $? 0 "Multipath with dev-only" + # route replace fails - invalid nexthop 1 add_initial_route6 "nexthop via 2001:db8:101::2 nexthop via 2001:db8:103::2" run_cmd "$IP -6 ro replace 2001:db8:104::/64 nexthop via 2001:db8:111::3 nexthop via 2001:db8:103::3" diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh index e6fd7a18c655..0266443601bc 100755 --- a/tools/testing/selftests/net/forwarding/mirror_gre.sh +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -63,22 +63,23 @@ test_span_gre_mac() { local tundev=$1; shift local direction=$1; shift - local prot=$1; shift local what=$1; shift - local swp3mac=$(mac_get $swp3) - local h3mac=$(mac_get $h3) + case "$direction" in + ingress) local src_mac=$(mac_get $h1); local dst_mac=$(mac_get $h2) + ;; + egress) local src_mac=$(mac_get $h2); local dst_mac=$(mac_get $h1) + ;; + esac RET=0 mirror_install $swp1 $direction $tundev "matchall $tcflags" - tc filter add dev $h3 ingress pref 77 prot $prot \ - flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ - action pass + icmp_capture_install h3-${tundev} "src_mac $src_mac dst_mac $dst_mac" - mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + mirror_test v$h1 192.0.2.1 192.0.2.2 h3-${tundev} 100 10 - tc filter del dev $h3 ingress pref 77 + icmp_capture_uninstall h3-${tundev} mirror_uninstall $swp1 $direction log_test "$direction $what: envelope MAC ($tcflags)" @@ -120,14 +121,14 @@ test_ip6gretap() test_gretap_mac() { - test_span_gre_mac gt4 ingress ip "mirror to gretap" - test_span_gre_mac gt4 egress ip "mirror to gretap" + test_span_gre_mac gt4 ingress "mirror to gretap" + test_span_gre_mac gt4 egress "mirror to gretap" } test_ip6gretap_mac() { - test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" - test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 ingress "mirror to ip6gretap" + test_span_gre_mac gt6 egress "mirror to ip6gretap" } test_all() diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh index bb10e33690b2..ce6bea9675c0 100755 --- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh +++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh @@ -516,9 +516,9 @@ test_tos() RET=0 tc filter add dev v1 egress pref 77 prot ip \ - flower ip_tos 0x40 action pass - vxlan_ping_test $h1 192.0.2.3 "-Q 0x40" v1 egress 77 10 - vxlan_ping_test $h1 192.0.2.3 "-Q 0x30" v1 egress 77 0 + flower ip_tos 0x14 action pass + vxlan_ping_test $h1 192.0.2.3 "-Q 0x14" v1 egress 77 10 + vxlan_ping_test $h1 192.0.2.3 "-Q 0x18" v1 egress 77 0 tc filter del dev v1 egress pref 77 prot ip log_test "VXLAN: envelope TOS inheritance" diff --git a/tools/testing/selftests/wireguard/qemu/Makefile b/tools/testing/selftests/wireguard/qemu/Makefile index f10aa3590adc..28d477683e8a 100644 --- a/tools/testing/selftests/wireguard/qemu/Makefile +++ b/tools/testing/selftests/wireguard/qemu/Makefile @@ -38,19 +38,17 @@ endef define file_download = $(DISTFILES_PATH)/$(1): mkdir -p $(DISTFILES_PATH) - flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp' - if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi + flock -x $$@.lock -c '[ -f $$@ ] && exit 0; wget -O $$@.tmp $(MIRROR)$(1) || wget -O $$@.tmp $(2)$(1) || rm -f $$@.tmp; [ -f $$@.tmp ] || exit 1; if echo "$(3) $$@.tmp" | sha256sum -c -; then mv $$@.tmp $$@; else rm -f $$@.tmp; exit 71; fi' endef $(eval $(call tar_download,MUSL,musl,1.1.24,.tar.gz,https://www.musl-libc.org/releases/,1370c9a812b2cf2a7d92802510cca0058cc37e66a7bedd70051f0a34015022a3)) -$(eval $(call tar_download,LIBMNL,libmnl,1.0.4,.tar.bz2,https://www.netfilter.org/projects/libmnl/files/,171f89699f286a5854b72b91d06e8f8e3683064c5901fb09d954a9ab6f551f81)) $(eval $(call tar_download,IPERF,iperf,3.7,.tar.gz,https://downloads.es.net/pub/iperf/,d846040224317caf2f75c843d309a950a7db23f9b44b94688ccbe557d6d1710c)) $(eval $(call tar_download,BASH,bash,5.0,.tar.gz,https://ftp.gnu.org/gnu/bash/,b4a80f2ac66170b2913efbfb9f2594f1f76c7b1afd11f799e22035d63077fb4d)) $(eval $(call tar_download,IPROUTE2,iproute2,5.4.0,.tar.xz,https://www.kernel.org/pub/linux/utils/net/iproute2/,fe97aa60a0d4c5ac830be18937e18dc3400ca713a33a89ad896ff1e3d46086ae)) $(eval $(call tar_download,IPTABLES,iptables,1.8.4,.tar.bz2,https://www.netfilter.org/projects/iptables/files/,993a3a5490a544c2cbf2ef15cf7e7ed21af1845baf228318d5c36ef8827e157c)) $(eval $(call tar_download,NMAP,nmap,7.80,.tar.bz2,https://nmap.org/dist/,fcfa5a0e42099e12e4bf7a68ebe6fde05553383a682e816a7ec9256ab4773faa)) $(eval $(call tar_download,IPUTILS,iputils,s20190709,.tar.gz,https://github.com/iputils/iputils/archive/s20190709.tar.gz/#,a15720dd741d7538dd2645f9f516d193636ae4300ff7dbc8bfca757bf166490a)) -$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20191226,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,aa8af0fdc9872d369d8c890a84dbc2a2466b55795dccd5b47721b2d97644b04f)) +$(eval $(call tar_download,WIREGUARD_TOOLS,wireguard-tools,1.0.20200206,.tar.xz,https://git.zx2c4.com/wireguard-tools/snapshot/,f5207248c6a3c3e3bfc9ab30b91c1897b00802ed861e1f9faaed873366078c64)) KERNEL_BUILD_PATH := $(BUILD_PATH)/kernel$(if $(findstring yes,$(DEBUG_KERNEL)),-debug) rwildcard=$(foreach d,$(wildcard $1*),$(call rwildcard,$d/,$2) $(filter $(subst *,%,$2),$d)) @@ -295,21 +293,13 @@ $(IPERF_PATH)/src/iperf3: | $(IPERF_PATH)/.installed $(USERSPACE_DEPS) $(MAKE) -C $(IPERF_PATH) $(STRIP) -s $@ -$(LIBMNL_PATH)/.installed: $(LIBMNL_TAR) - flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - touch $@ - -$(LIBMNL_PATH)/src/.libs/libmnl.a: | $(LIBMNL_PATH)/.installed $(USERSPACE_DEPS) - cd $(LIBMNL_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared - $(MAKE) -C $(LIBMNL_PATH) - sed -i 's:prefix=.*:prefix=$(LIBMNL_PATH):' $(LIBMNL_PATH)/libmnl.pc - $(WIREGUARD_TOOLS_PATH)/.installed: $(WIREGUARD_TOOLS_TAR) + mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< touch $@ -$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src LIBMNL_CFLAGS="-I$(LIBMNL_PATH)/include" LIBMNL_LDLIBS="-lmnl" wg +$(WIREGUARD_TOOLS_PATH)/src/wg: | $(WIREGUARD_TOOLS_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(WIREGUARD_TOOLS_PATH)/src wg $(STRIP) -s $@ $(BUILD_PATH)/init: init.c | $(USERSPACE_DEPS) @@ -340,17 +330,17 @@ $(BASH_PATH)/bash: | $(BASH_PATH)/.installed $(USERSPACE_DEPS) $(IPROUTE2_PATH)/.installed: $(IPROUTE2_TAR) mkdir -p $(BUILD_PATH) flock -s $<.lock tar -C $(BUILD_PATH) -xf $< - printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=y\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS -DHAVE_LIBMNL -I$(LIBMNL_PATH)/include\nLDLIBS+=-lmnl' > $(IPROUTE2_PATH)/config.mk + printf 'CC:=$(CC)\nPKG_CONFIG:=pkg-config\nTC_CONFIG_XT:=n\nTC_CONFIG_ATM:=n\nTC_CONFIG_IPSET:=n\nIP_CONFIG_SETNS:=y\nHAVE_ELF:=n\nHAVE_MNL:=n\nHAVE_BERKELEY_DB:=n\nHAVE_LATEX:=n\nHAVE_PDFLATEX:=n\nCFLAGS+=-DHAVE_SETNS\n' > $(IPROUTE2_PATH)/config.mk printf 'lib: snapshot\n\t$$(MAKE) -C lib\nip/ip: lib\n\t$$(MAKE) -C ip ip\nmisc/ss: lib\n\t$$(MAKE) -C misc ss\n' >> $(IPROUTE2_PATH)/Makefile touch $@ -$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip - $(STRIP) -s $(IPROUTE2_PATH)/ip/ip +$(IPROUTE2_PATH)/ip/ip: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ ip/ip + $(STRIP) -s $@ -$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - LDFLAGS="$(LDFLAGS) -L$(LIBMNL_PATH)/src/.libs" PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss - $(STRIP) -s $(IPROUTE2_PATH)/misc/ss +$(IPROUTE2_PATH)/misc/ss: | $(IPROUTE2_PATH)/.installed $(USERSPACE_DEPS) + $(MAKE) -C $(IPROUTE2_PATH) PREFIX=/ misc/ss + $(STRIP) -s $@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) mkdir -p $(BUILD_PATH) @@ -358,8 +348,8 @@ $(IPTABLES_PATH)/.installed: $(IPTABLES_TAR) sed -i -e "/nfnetlink=[01]/s:=[01]:=0:" -e "/nfconntrack=[01]/s:=[01]:=0:" $(IPTABLES_PATH)/configure touch $@ -$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(LIBMNL_PATH)/src/.libs/libmnl.a $(USERSPACE_DEPS) - cd $(IPTABLES_PATH) && PKG_CONFIG_LIBDIR="$(LIBMNL_PATH)" ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --with-kernel=$(BUILD_PATH)/include +$(IPTABLES_PATH)/iptables/xtables-legacy-multi: | $(IPTABLES_PATH)/.installed $(USERSPACE_DEPS) + cd $(IPTABLES_PATH) && ./configure --prefix=/ $(CROSS_COMPILE_FLAG) --enable-static --disable-shared --disable-nftables --disable-bpf-compiler --disable-nfsynproxy --disable-libipq --disable-connlabel --with-kernel=$(BUILD_PATH)/include $(MAKE) -C $(IPTABLES_PATH) $(STRIP) -s $@ |