diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-13 15:33:04 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-04-13 15:33:04 -0700 |
| commit | 829cca4d1783088e43bace57a555044cc937c554 (patch) | |
| tree | 78a99d818c13e7a7601297ce59fd103918458010 | |
| parent | 4413ad01e27eb989f4b19bb5b038328c220a383d (diff) | |
| parent | d0f89c4c1d4e7614581d4fe7caebb3ce6bceafe6 (diff) | |
Merge tag 'net-6.3-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from bpf, and bluetooth.
Not all that quiet given spring celebrations, but "current" fixes are
thinning out, which is encouraging. One outstanding regression in the
mlx5 driver when using old FW, not blocking but we're pushing for a
fix.
Current release - new code bugs:
- eth: enetc: workaround for unresponsive pMAC after receiving
express traffic
Previous releases - regressions:
- rtnetlink: restore RTM_NEW/DELLINK notification behavior, keep the
pid/seq fields 0 for backward compatibility
Previous releases - always broken:
- sctp: fix a potential overflow in sctp_ifwdtsn_skip
- mptcp:
- use mptcp_schedule_work instead of open-coding it and make the
worker check stricter, to avoid scheduling work on closed
sockets
- fix NULL pointer dereference on fastopen early fallback
- skbuff: fix memory corruption due to a race between skb coalescing
and releasing clones confusing page_pool reference counting
- bonding: fix neighbor solicitation validation on backup slaves
- bpf: tcp: use sock_gen_put instead of sock_put in bpf_iter_tcp
- bpf: arm64: fixed a BTI error on returning to patched function
- openvswitch: fix race on port output leading to inf loop
- sfp: initialize sfp->i2c_block_size at sfp allocation to avoid
returning a different errno than expected
- phy: nxp-c45-tja11xx: unregister PTP, purge queues on remove
- Bluetooth: fix printing errors if LE Connection times out
- Bluetooth: assorted UaF, deadlock and data race fixes
- eth: macb: fix memory corruption in extended buffer descriptor mode
Misc:
- adjust the XDP Rx flow hash API to also include the protocol layers
over which the hash was computed"
* tag 'net-6.3-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (50 commits)
selftests/bpf: Adjust bpf_xdp_metadata_rx_hash for new arg
mlx4: bpf_xdp_metadata_rx_hash add xdp rss hash type
veth: bpf_xdp_metadata_rx_hash add xdp rss hash type
mlx5: bpf_xdp_metadata_rx_hash add xdp rss hash type
xdp: rss hash types representation
selftests/bpf: xdp_hw_metadata remove bpf_printk and add counters
skbuff: Fix a race between coalescing and releasing SKBs
net: macb: fix a memory corruption in extended buffer descriptor mode
selftests: add the missing CONFIG_IP_SCTP in net config
udp6: fix potential access to stale information
selftests: openvswitch: adjust datapath NL message declaration
selftests: mptcp: userspace pm: uniform verify events
mptcp: fix NULL pointer dereference on fastopen early fallback
mptcp: stricter state check in mptcp_worker
mptcp: use mptcp_schedule_work instead of open-coding it
net: enetc: workaround for unresponsive pMAC after receiving express traffic
sctp: fix a potential overflow in sctp_ifwdtsn_skip
net: qrtr: Fix an uninit variable access bug in qrtr_tx_resume()
rtnetlink: Restore RTM_NEW/DELLINK notification behavior
net: ti/cpsw: Add explicit platform_device.h and of_platform.h includes
...
65 files changed, 990 insertions, 517 deletions
diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 87dd1c5283e6..58a78a316697 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -340,6 +340,8 @@ tcp_app_win - INTEGER Reserve max(window/2^tcp_app_win, mss) of window for application buffer. Value 0 is special, it means that nothing is reserved. + Possible values are [0, 31], inclusive. + Default: 31 tcp_autocorking - BOOLEAN diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h index a6acb94ea3d6..c2edadb8ec6a 100644 --- a/arch/arm64/net/bpf_jit.h +++ b/arch/arm64/net/bpf_jit.h @@ -281,4 +281,8 @@ /* DMB */ #define A64_DMB_ISH aarch64_insn_gen_dmb(AARCH64_INSN_MB_ISH) +/* ADR */ +#define A64_ADR(Rd, offset) \ + aarch64_insn_gen_adr(0, offset, Rd, AARCH64_INSN_ADR_TYPE_ADR) + #endif /* _BPF_JIT_H */ diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 62f805f427b7..b26da8efa616 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -1900,7 +1900,8 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im, restore_args(ctx, args_off, nargs); /* call original func */ emit(A64_LDR64I(A64_R(10), A64_SP, retaddr_off), ctx); - emit(A64_BLR(A64_R(10)), ctx); + emit(A64_ADR(A64_LR, AARCH64_INSN_SIZE * 2), ctx); + emit(A64_RET(A64_R(10)), ctx); /* store return value */ emit(A64_STR64I(A64_R(0), A64_SP, retval_off), ctx); /* reserve a nop for bpf_tramp_image_put */ diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c index 288003a9f0ca..d586df48ecc6 100644 --- a/arch/loongarch/net/bpf_jit.c +++ b/arch/loongarch/net/bpf_jit.c @@ -1022,6 +1022,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext emit_atomic(insn, ctx); break; + /* Speculation barrier */ + case BPF_ST | BPF_NOSPEC: + break; + default: pr_err("bpf_jit: unknown opcode %02x\n", code); return -EINVAL; diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c index 3006e2a0f37e..43e98a598bd9 100644 --- a/drivers/bluetooth/btbcm.c +++ b/drivers/bluetooth/btbcm.c @@ -511,7 +511,7 @@ static const char *btbcm_get_board_name(struct device *dev) len = strlen(tmp) + 1; board_type = devm_kzalloc(dev, len, GFP_KERNEL); strscpy(board_type, tmp, len); - for (i = 0; i < board_type[i]; i++) { + for (i = 0; i < len; i++) { if (board_type[i] == '/') board_type[i] = '-'; } diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 02893600db39..51000320e1ea 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -358,6 +358,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 236e5219c811..8cc9a74789b7 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3269,7 +3269,8 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, combined = skb_header_pointer(skb, 0, sizeof(_combined), &_combined); if (!combined || combined->ip6.nexthdr != NEXTHDR_ICMP || - combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT) + (combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_SOLICITATION && + combined->icmp6.icmp6_type != NDISC_NEIGHBOUR_ADVERTISEMENT)) goto out; saddr = &combined->ip6.saddr; @@ -3291,7 +3292,7 @@ static int bond_na_rcv(const struct sk_buff *skb, struct bonding *bond, else if (curr_active_slave && time_after(slave_last_rx(bond, curr_active_slave), curr_active_slave->last_link_up)) - bond_validate_na(bond, slave, saddr, daddr); + bond_validate_na(bond, slave, daddr, saddr); else if (curr_arp_slave && bond_time_in_interval(bond, slave_last_tx(curr_arp_slave), 1)) bond_validate_na(bond, slave, saddr, daddr); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 66e30561569e..e43d99ec50ba 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -1064,6 +1064,10 @@ static dma_addr_t macb_get_addr(struct macb *bp, struct macb_dma_desc *desc) } #endif addr |= MACB_BF(RX_WADDR, MACB_BFEXT(RX_WADDR, desc->addr)); +#ifdef CONFIG_MACB_USE_HWSTAMP + if (bp->hw_dma_cap & HW_DMA_CAP_PTP) + addr &= ~GEM_BIT(DMA_RXVALID); +#endif return addr; } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c index da9d4b310fcd..838750a03cf6 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c @@ -989,6 +989,20 @@ static int enetc_get_mm(struct net_device *ndev, struct ethtool_mm_state *state) return 0; } +/* FIXME: Workaround for the link partner's verification failing if ENETC + * priorly received too much express traffic. The documentation doesn't + * suggest this is needed. + */ +static void enetc_restart_emac_rx(struct enetc_si *si) +{ + u32 val = enetc_port_rd(&si->hw, ENETC_PM0_CMD_CFG); + + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val & ~ENETC_PM0_RX_EN); + + if (val & ENETC_PM0_RX_EN) + enetc_port_wr(&si->hw, ENETC_PM0_CMD_CFG, val); +} + static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, struct netlink_ext_ack *extack) { @@ -1040,6 +1054,8 @@ static int enetc_set_mm(struct net_device *ndev, struct ethtool_mm_cfg *cfg, enetc_port_wr(hw, ENETC_MMCSR, val); + enetc_restart_emac_rx(priv->si); + mutex_unlock(&priv->mm_lock); return 0; diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 232bc61d9eee..746ff76f2fb1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -59,8 +59,6 @@ enum iavf_vsi_state_t { struct iavf_vsi { struct iavf_adapter *back; struct net_device *netdev; - unsigned long active_cvlans[BITS_TO_LONGS(VLAN_N_VID)]; - unsigned long active_svlans[BITS_TO_LONGS(VLAN_N_VID)]; u16 seid; u16 id; DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); @@ -158,15 +156,20 @@ struct iavf_vlan { u16 tpid; }; +enum iavf_vlan_state_t { + IAVF_VLAN_INVALID, + IAVF_VLAN_ADD, /* filter needs to be added */ + IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ + IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ + IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ + IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ +}; + struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - struct { - u8 is_new_vlan:1; /* filter is new, wait for PF answer */ - u8 remove:1; /* filter needs to be removed */ - u8 add:1; /* filter needs to be added */ - u8 padding:5; - }; + enum iavf_vlan_state_t state; }; #define IAVF_MAX_TRAFFIC_CLASS 4 @@ -258,6 +261,7 @@ struct iavf_adapter { wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; + int num_vlan_filters; struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 095201e83c9d..2de4baff4c20 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -791,7 +791,8 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->vlan = vlan; list_add_tail(&f->list, &adapter->vlan_filter_list); - f->add = true; + f->state = IAVF_VLAN_ADD; + adapter->num_vlan_filters++; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -813,7 +814,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; + f->state = IAVF_VLAN_REMOVE; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } @@ -828,14 +829,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - u16 vid; + struct iavf_vlan_filter *f; /* re-add all VLAN filters */ - for_each_set_bit(vid, adapter->vsi.active_cvlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021Q)); + spin_lock_bh(&adapter->mac_vlan_list_lock); - for_each_set_bit(vid, adapter->vsi.active_svlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021AD)); + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_INACTIVE) + f->state = IAVF_VLAN_ADD; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } /** @@ -844,8 +849,7 @@ static void iavf_restore_filters(struct iavf_adapter *adapter) */ u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) { - return bitmap_weight(adapter->vsi.active_cvlans, VLAN_N_VID) + - bitmap_weight(adapter->vsi.active_svlans, VLAN_N_VID); + return adapter->num_vlan_filters; } /** @@ -928,11 +932,6 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, return 0; iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); - if (proto == cpu_to_be16(ETH_P_8021Q)) - clear_bit(vid, adapter->vsi.active_cvlans); - else - clear_bit(vid, adapter->vsi.active_svlans); - return 0; } @@ -1293,16 +1292,11 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* remove all VLAN filters */ + /* disable all VLAN filters */ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) { - if (vlf->add) { - list_del(&vlf->list); - kfree(vlf); - } else { - vlf->remove = true; - } - } + list) + vlf->state = IAVF_VLAN_DISABLE; + spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -2914,6 +2908,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) list_del(&fv->list); kfree(fv); } + adapter->num_vlan_filters = 0; spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -3131,9 +3126,6 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); - bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); - bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 4e17d006c52d..9afbbdac3590 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -642,16 +642,10 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - if (f->vlan.tpid == ETH_P_8021Q) - clear_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - clear_bit(f->vlan.vid, - adapter->vsi.active_svlans); - + if (f->state == IAVF_VLAN_IS_NEW) { list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -679,7 +673,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) + if (f->state == IAVF_VLAN_ADD) count++; } if (!count || !VLAN_FILTERING_ALLOWED(adapter)) { @@ -710,11 +704,10 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; if (i == count) break; } @@ -760,7 +753,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -778,8 +771,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; } } @@ -822,10 +814,16 @@ void iavf_del_vlans(struct iavf_adapter *adapter) * filters marked for removal to enable bailing out before * sending a virtchnl message */ - if (f->remove && !VLAN_FILTERING_ALLOWED(adapter)) { + if (f->state == IAVF_VLAN_REMOVE && + !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); - } else if (f->remove) { + adapter->num_vlan_filters--; + } else if (f->state == IAVF_VLAN_DISABLE && + !VLAN_FILTERING_ALLOWED(adapter)) { + f->state = IAVF_VLAN_INACTIVE; + } else if (f->state == IAVF_VLAN_REMOVE || + f->state == IAVF_VLAN_DISABLE) { count++; } } @@ -857,11 +855,18 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE) { vvfl->vlan_id[i] = f->vlan.vid; + f->state = IAVF_VLAN_INACTIVE; i++; + if (i == count) + break; + } else if (f->state == IAVF_VLAN_REMOVE) { + vvfl->vlan_id[i] = f->vlan.vid; list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; + i++; if (i == count) break; } @@ -901,7 +906,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE || + f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -915,8 +921,13 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - list_del(&f->list); - kfree(f); + if (f->state == IAVF_VLAN_DISABLE) { + f->state = IAVF_VLAN_INACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } i++; if (i == count) break; @@ -2192,7 +2203,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; @@ -2260,7 +2271,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -2444,15 +2455,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - f->is_new_vlan = false; - if (f->vlan.tpid == ETH_P_8021Q) - set_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - set_bit(f->vlan.vid, - adapter->vsi.active_svlans); - } + if (f->state == IAVF_VLAN_IS_NEW) + f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 4b5e459b6d49..332472fe4990 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -681,14 +681,32 @@ int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct mlx4_en_xdp_buff *_ctx = (void *)ctx; + struct mlx4_cqe *cqe = _ctx->cqe; + enum xdp_rss_hash_type xht = 0; + __be16 status; if (unlikely(!(_ctx->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->immed_rss_invalid); + *hash = be32_to_cpu(cqe->immed_rss_invalid); + status = cqe->status; + if (status & cpu_to_be16(MLX4_CQE_STATUS_TCP)) + xht = XDP_RSS_L4_TCP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_UDP)) + xht = XDP_RSS_L4_UDP; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV4 | MLX4_CQE_STATUS_IPV4F)) + xht |= XDP_RSS_L3_IPV4; + if (status & cpu_to_be16(MLX4_CQE_STATUS_IPV6)) { + xht |= XDP_RSS_L3_IPV6; + if (cqe->ipv6_ext_mask) + xht |= XDP_RSS_L3_DYNHDR; + } + *rss_type = xht; + return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 544e09b97483..4ac4d883047b 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -798,7 +798,8 @@ int mlx4_en_netdev_event(struct notifier_block *this, struct xdp_md; int mlx4_en_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp); -int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash); +int mlx4_en_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); /* * Functions for time stamping diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index c5dae48b7932..d9d3b9e1f15a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -34,6 +34,7 @@ #include <net/xdp_sock_drv.h> #include "en/xdp.h" #include "en/params.h" +#include <linux/bitfield.h> int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { @@ -169,14 +170,72 @@ static int mlx5e_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +/* Mapping HW RSS Type bits CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 into 4-bits*/ +#define RSS_TYPE_MAX_TABLE 16 /* 4-bits max 16 entries */ +#define RSS_L4 GENMASK(1, 0) +#define RSS_L3 GENMASK(3, 2) /* Same as CQE_RSS_HTYPE_IP */ + +/* Valid combinations of CQE_RSS_HTYPE_IP + CQE_RSS_HTYPE_L4 sorted numerical */ +enum mlx5_rss_hash_type { + RSS_TYPE_NO_HASH = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IP_NONE) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L3_IPV4 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV4_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV4_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV4_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV4) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), + RSS_TYPE_L3_IPV6 = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_NONE)), + RSS_TYPE_L4_IPV6_TCP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_TCP)), + RSS_TYPE_L4_IPV6_UDP = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_UDP)), + RSS_TYPE_L4_IPV6_IPSEC = (FIELD_PREP_CONST(RSS_L3, CQE_RSS_IPV6) | + FIELD_PREP_CONST(RSS_L4, CQE_RSS_L4_IPSEC)), +}; + +/* Invalid combinations will simply return zero, allows no boundary checks */ +static const enum xdp_rss_hash_type mlx5_xdp_rss_type[RSS_TYPE_MAX_TABLE] = { + [RSS_TYPE_NO_HASH] = XDP_RSS_TYPE_NONE, + [1] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [2] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [3] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [RSS_TYPE_L3_IPV4] = XDP_RSS_TYPE_L3_IPV4, + [RSS_TYPE_L4_IPV4_TCP] = XDP_RSS_TYPE_L4_IPV4_TCP, + [RSS_TYPE_L4_IPV4_UDP] = XDP_RSS_TYPE_L4_IPV4_UDP, + [RSS_TYPE_L4_IPV4_IPSEC] = XDP_RSS_TYPE_L4_IPV4_IPSEC, + [RSS_TYPE_L3_IPV6] = XDP_RSS_TYPE_L3_IPV6, + [RSS_TYPE_L4_IPV6_TCP] = XDP_RSS_TYPE_L4_IPV6_TCP, + [RSS_TYPE_L4_IPV6_UDP] = XDP_RSS_TYPE_L4_IPV6_UDP, + [RSS_TYPE_L4_IPV6_IPSEC] = XDP_RSS_TYPE_L4_IPV6_IPSEC, + [12] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [13] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [14] = XDP_RSS_TYPE_NONE, /* Implicit zero */ + [15] = XDP_RSS_TYPE_NONE, /* Implicit zero */ +}; + +static int mlx5e_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { const struct mlx5e_xdp_buff *_ctx = (void *)ctx; + const struct mlx5_cqe64 *cqe = _ctx->cqe; + u32 hash_type, l4_type, ip_type, lookup; if (unlikely(!(_ctx->xdp.rxq->dev->features & NETIF_F_RXHASH))) return -ENODATA; - *hash = be32_to_cpu(_ctx->cqe->rss_hash_result); + *hash = be32_to_cpu(cqe->rss_hash_result); + + hash_type = cqe->rss_hash_type; + BUILD_BUG_ON(CQE_RSS_HTYPE_IP != RSS_L3); /* same mask */ + ip_type = hash_type & CQE_RSS_HTYPE_IP; + l4_type = FIELD_GET(CQE_RSS_HTYPE_L4, hash_type); + lookup = ip_type | l4_type; + *rss_type = mlx5_xdp_rss_type[lookup]; + return 0; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c index 87f76bac2e46..eb827b86ecae 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ctx.c @@ -628,7 +628,13 @@ int qlcnic_fw_create_ctx(struct qlcnic_adapter *dev) int i, err, ring; if (dev->flags & QLCNIC_NEED_FLR) { - pci_reset_function(dev->pdev); + err = pci_reset_function(dev->pdev); + if (err) { + dev_err(&dev->pdev->dev, + "Adapter reset failed (%d). Please reboot\n", + err); + return err; + } dev->flags &= ~QLCNIC_NEED_FLR; } diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index ab8b09a9ef61..7a2e76776297 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -4522,7 +4522,7 @@ static int niu_alloc_channels(struct niu *np) err = niu_rbr_fill(np, rp, GFP_KERNEL); if (err) - return err; + goto out_err; } tx_rings = kcalloc(num_tx_rings, sizeof(struct tx_ring_info), diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 37f0b62ec5d6..f9cd566d1c9b 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -27,7 +27,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_device.h> +#include <linux/of_platform.h> #include <linux/if_vlan.h> #include <linux/kmemleak.h> #include <linux/sys_soc.h> diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 35128dd45ffc..c61e4e44a78f 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -7,6 +7,7 @@ #include <linux/io.h> #include <linux/clk.h> +#include <linux/platform_device.h> #include <linux/timer.h> #include <linux/module.h> #include <linux/irqreturn.h> @@ -23,7 +24,7 @@ #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/of_net.h> -#include <linux/of_device.h> +#include <linux/of_platform.h> #include <linux/if_vlan.h> #include <linux/kmemleak.h> #include <linux/sys_soc.h> diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c index 5813b07242ce..029875a59ff8 100644 --- a/drivers/net/phy/nxp-c45-tja11xx.c +++ b/drivers/net/phy/nxp-c45-tja11xx.c @@ -191,7 +191,7 @@ #define MAX_ID_PS 2260U #define DEFAULT_ID_PS 2000U -#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK(31, 0) * (ppb) * \ +#define PPM_TO_SUBNS_INC(ppb) div_u64(GENMASK_ULL(31, 0) * (ppb) * \ PTP_CLK_PERIOD_100BT1, NSEC_PER_SEC) #define NXP_C45_SKB_CB(skb) ((struct nxp_c45_skb_cb *)(skb)->cb) @@ -1337,6 +1337,17 @@ no_ptp_support: return ret; } +static void nxp_c45_remove(struct phy_device *phydev) +{ + struct nxp_c45_phy *priv = phydev->priv; + + if (priv->ptp_clock) + ptp_clock_unregister(priv->ptp_clock); + + skb_queue_purge(&priv->tx_queue); + skb_queue_purge(&priv->rx_queue); +} + static struct phy_driver nxp_c45_driver[] = { { PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103), @@ -1359,6 +1370,7 @@ static struct phy_driver nxp_c45_driver[] = { .set_loopback = genphy_c45_loopback, .get_sqi = nxp_c45_get_sqi, .get_sqi_max = nxp_c45_get_sqi_max, + .remove = nxp_c45_remove, }, }; diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c index 8af10bb53e57..bf345032d450 100644 --- a/drivers/net/phy/sfp.c +++ b/drivers/net/phy/sfp.c @@ -210,6 +210,12 @@ static const enum gpiod_flags gpio_flags[] = { #define SFP_PHY_ADDR 22 #define SFP_PHY_ADDR_ROLLBALL 17 +/* SFP_EEPROM_BLOCK_SIZE is the size of data chunk to read the EEPROM + * at a time. Some SFP modules and also some Linux I2C drivers do not like + * reads longer than 16 bytes. + */ +#define SFP_EEPROM_BLOCK_SIZE 16 + struct sff_data { unsigned int gpios; bool (*module_supported)(const struct sfp_eeprom_id *id); @@ -1929,11 +1935,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report) u8 check; int ret; - /* Some SFP modules and also some Linux I2C drivers do not like reads - * longer than 16 bytes, so read the EEPROM in chunks of 16 bytes at - * a time. - */ - sfp->i2c_block_size = 16; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base)); if (ret < 0) { @@ -2485,6 +2487,9 @@ static int sfp_module_eeprom(struct sfp *sfp, struct ethtool_eeprom *ee, unsigned int first, last, len; int ret; + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (ee->len == 0) return -EINVAL; @@ -2517,6 +2522,9 @@ static int sfp_module_eeprom_by_page(struct sfp *sfp, const struct ethtool_module_eeprom *page, struct netlink_ext_ack *extack) { + if (!(sfp->state & SFP_F_PRESENT)) + return -ENODEV; + if (page->bank) { NL_SET_ERR_MSG(extack, "Banks not supported"); return -EOPNOTSUPP; @@ -2621,6 +2629,7 @@ static struct sfp *sfp_alloc(struct device *dev) return ERR_PTR(-ENOMEM); sfp->dev = dev; + sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE; mutex_init(&sfp->sm_mutex); mutex_init(&sfp->st_mutex); diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index decb5ba56a25..0fc4b959edc1 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1943,7 +1943,7 @@ static struct rx_agg *alloc_rx_agg(struct r8152 *tp, gfp_t mflags) if (!rx_agg) return NULL; - rx_agg->page = alloc_pages(mflags | __GFP_COMP, order); + rx_agg->page = alloc_pages(mflags | __GFP_COMP | __GFP_NOWARN, order); if (!rx_agg->page) goto free_rx; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index c1178915496d..e1b38fbf1dd9 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -1648,14 +1648,18 @@ static int veth_xdp_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp) return 0; } -static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash) +static int veth_xdp_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { struct veth_xdp_buff *_ctx = (void *)ctx; + struct sk_buff *skb = _ctx->skb; - if (!_ctx->skb) + if (!skb) return -ENODATA; - *hash = skb_get_hash(_ctx->skb); + *hash = skb_get_hash(skb); + *rss_type = skb->l4_hash ? XDP_RSS_TYPE_L4_ANY : XDP_RSS_TYPE_NONE; + return 0; } diff --git a/drivers/net/wwan/iosm/iosm_ipc_pcie.c b/drivers/net/wwan/iosm/iosm_ipc_pcie.c index 5bf5a93937c9..04517bd3325a 100644 --- a/drivers/net/wwan/iosm/iosm_ipc_pcie.c +++ b/drivers/net/wwan/iosm/iosm_ipc_pcie.c @@ -295,7 +295,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, ret = dma_set_mask(ipc_pcie->dev, DMA_BIT_MASK(64)); if (ret) { dev_err(ipc_pcie->dev, "Could not set PCI DMA mask: %d", ret); - return ret; + goto set_mask_fail; } ipc_pcie_config_aspm(ipc_pcie); @@ -323,6 +323,7 @@ static int ipc_pcie_probe(struct pci_dev *pci, imem_init_fail: ipc_pcie_resources_release(ipc_pcie); resources_req_fail: +set_mask_fail: pci_disable_device(pci); pci_enable_fail: kfree(ipc_pcie); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 71b06ebad402..1db19a9d26e3 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -36,6 +36,7 @@ #include <linux/types.h> #include <rdma/ib_verbs.h> #include <linux/mlx5/mlx5_ifc.h> +#include <linux/bitfield.h> #if defined(__LITTLE_ENDIAN) #define MLX5_SET_HOST_ENDIANNESS 0 @@ -980,14 +981,23 @@ enum { }; enum { - CQE_RSS_HTYPE_IP = 0x3 << 2, + CQE_RSS_HTYPE_IP = GENMASK(3, 2), /* cqe->rss_hash_type[3:2] - IP destination selected for hash * (00 = none, 01 = IPv4, 10 = IPv6, 11 = Reserved) */ - CQE_RSS_HTYPE_L4 = 0x3 << 6, + CQE_RSS_IP_NONE = 0x0, + CQE_RSS_IPV4 = 0x1, + CQE_RSS_IPV6 = 0x2, + CQE_RSS_RESERVED = 0x3, + + CQE_RSS_HTYPE_L4 = GENMASK(7, 6), /* cqe->rss_hash_type[7:6] - L4 destination selected for hash * (00 = none, 01 = TCP. 10 = UDP, 11 = IPSEC.SPI */ + CQE_RSS_L4_NONE = 0x0, + CQE_RSS_L4_TCP = 0x1, + CQE_RSS_L4_UDP = 0x2, + CQE_RSS_L4_IPSEC = 0x3, }; enum { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 470085b121d3..c35f04f636f1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1624,7 +1624,8 @@ struct net_device_ops { struct xdp_metadata_ops { int (*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp); - int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash); + int (*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type); }; /** diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 92ad75549e9c..b6e6378dcbbd 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -25,7 +25,8 @@ void rtmsg_ifinfo_newnet(int type, struct net_device *dev, unsigned int change, struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq); + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh); void rtmsg_ifinfo_send(struct sk_buff *skb, struct net_device *dev, gfp_t flags, u32 portid, const struct nlmsghdr *nlh); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 6ed9b4d546a7..d5311ceb21c6 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -954,6 +954,7 @@ enum { HCI_CONN_STK_ENCRYPT, HCI_CONN_AUTH_INITIATOR, HCI_CONN_DROP, + HCI_CONN_CANCEL, HCI_CONN_PARAM_REMOVAL_PEND, HCI_CONN_NEW_LINK_KEY, HCI_CONN_SCANNING, diff --git a/include/net/bonding.h b/include/net/bonding.h index ea36ab7f9e72..c3843239517d 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -761,13 +761,17 @@ static inline int bond_get_targets_ip(__be32 *targets, __be32 ip) #if IS_ENABLED(CONFIG_IPV6) static inline int bond_get_targets_ip6(struct in6_addr *targets, struct in6_addr *ip) { + struct in6_addr mcaddr; int i; - for (i = 0; i < BOND_MAX_NS_TARGETS; i++) - if (ipv6_addr_equal(&targets[i], ip)) + for (i = 0; i < BOND_MAX_NS_TARGETS; i++) { + addrconf_addr_solict_mult(&targets[i], &mcaddr); + if ((ipv6_addr_equal(&targets[i], ip)) || + (ipv6_addr_equal(&mcaddr, ip))) return i; else if (ipv6_addr_any(&targets[i])) break; + } return -1; } diff --git a/include/net/xdp.h b/include/net/xdp.h index 41c57b8b1671..76aa748e7923 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -8,6 +8,7 @@ #include <linux/skbuff.h> /* skb_shared_info */ #include <uapi/linux/netdev.h> +#include <linux/bitfield.h> /** * DOC: XDP RX-queue information @@ -425,6 +426,52 @@ XDP_METADATA_KFUNC_xxx MAX_XDP_METADATA_KFUNC, }; +enum xdp_rss_hash_type { + /* First part: Individual bits for L3/L4 types */ + XDP_RSS_L3_IPV4 = BIT(0), + XDP_RSS_L3_IPV6 = BIT(1), + + /* The fixed (L3) IPv4 and IPv6 headers can both be followed by + * variable/dynamic headers, IPv4 called Options and IPv6 called + * Extension Headers. HW RSS type can contain this info. + */ + XDP_RSS_L3_DYNHDR = BIT(2), + + /* When RSS hash covers L4 then drivers MUST set XDP_RSS_L4 bit in + * addition to the protocol specific bit. This ease interaction with + * SKBs and avoids reserving a fixed mask for future L4 protocol bits. + */ + XDP_RSS_L4 = BIT(3), /* L4 based hash, proto can be unknown */ + XDP_RSS_L4_TCP = BIT(4), + XDP_RSS_L4_UDP = BIT(5), + XDP_RSS_L4_SCTP = BIT(6), + XDP_RSS_L4_IPSEC = BIT(7), /* L4 based hash include IPSEC SPI */ + + /* Second part: RSS hash type combinations used for driver HW mapping */ + XDP_RSS_TYPE_NONE = 0, + XDP_RSS_TYPE_L2 = XDP_RSS_TYPE_NONE, + + XDP_RSS_TYPE_L3_IPV4 = XDP_RSS_L3_IPV4, + XDP_RSS_TYPE_L3_IPV6 = XDP_RSS_L3_IPV6, + XDP_RSS_TYPE_L3_IPV4_OPT = XDP_RSS_L3_IPV4 | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L3_IPV6_EX = XDP_RSS_L3_IPV6 | XDP_RSS_L3_DYNHDR, + + XDP_RSS_TYPE_L4_ANY = XDP_RSS_L4, + XDP_RSS_TYPE_L4_IPV4_TCP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV4_UDP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV4_SCTP = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV4_IPSEC = XDP_RSS_L3_IPV4 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_TCP, + XDP_RSS_TYPE_L4_IPV6_UDP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_UDP, + XDP_RSS_TYPE_L4_IPV6_SCTP = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_SCTP, + XDP_RSS_TYPE_L4_IPV6_IPSEC = XDP_RSS_L3_IPV6 | XDP_RSS_L4 | XDP_RSS_L4_IPSEC, + + XDP_RSS_TYPE_L4_IPV6_TCP_EX = XDP_RSS_TYPE_L4_IPV6_TCP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_UDP_EX = XDP_RSS_TYPE_L4_IPV6_UDP | XDP_RSS_L3_DYNHDR, + XDP_RSS_TYPE_L4_IPV6_SCTP_EX = XDP_RSS_TYPE_L4_IPV6_SCTP | XDP_RSS_L3_DYNHDR, +}; + #ifdef CONFIG_NET u32 bpf_xdp_metadata_kfunc_id(int id); bool bpf_dev_bound_kfunc_id(u32 btf_id); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 17b946f9ba31..8455ba141ee6 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -68,7 +68,7 @@ static const struct sco_param esco_param_msbc[] = { }; /* This function requires the caller holds hdev->lock */ -static void hci_connect_le_scan_cleanup(struct hci_conn *conn) +static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) { struct hci_conn_params *params; struct hci_dev *hdev = conn->hdev; @@ -88,9 +88,28 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn) params = hci_pend_le_action_lookup(&hdev->pend_le_conns, bdaddr, bdaddr_type); - if (!params || !params->explicit_connect) + if (!params) return; + if (params->conn) { + hci_conn_drop(params->conn); + hci_conn_put(params->conn); + params->conn = NULL; + } + + if (!params->explicit_connect) + return; + + /* If the status indicates successful cancellation of + * the attempt (i.e. Unknown Connection Id) there's no point of + * notifying failure since we'll go back to keep trying to + * connect. The only exception is explicit connect requests + * where a timeout + cancel does indicate an actual failure. + */ + if (status && status != HCI_ERROR_UNKNOWN_CONN_ID) + mgmt_connect_failed(hdev, &conn->dst, conn->type, + conn->dst_type, status); + /* The connection attempt was doing scan for new RPA, and is * in scan phase. If params are not associated with any other * autoconnect action, remove them completely. If they are, just unmark @@ -178,7 +197,7 @@ static void le_scan_cleanup(struct work_struct *work) rcu_read_unlock(); if (c == conn) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); hci_conn_cleanup(conn); } @@ -1049,6 +1068,17 @@ struct hci_conn *hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t *dst, return conn; } +static bool hci_conn_unlink(struct hci_conn *conn) +{ + if (!conn->link) + return false; + + conn->link->link = NULL; + conn->link = NULL; + + return true; +} + int hci_conn_del(struct hci_conn *conn) { struct hci_dev *hdev = conn->hdev; @@ -1060,15 +1090,16 @@ int hci_conn_del(struct hci_conn *conn) cancel_delayed_work_sync(&conn->idle_work); if (conn->type == ACL_LINK) { - struct hci_conn *sco = conn->link; - if (sco) { - sco->link = NULL; + struct hci_conn *link = conn->link; + + if (link) { + hci_conn_unlink(conn); /* Due to race, SCO connection might be not established * yet at this point. Delete it now, otherwise it is * possible for it to be stuck and can't be deleted. */ - if (sco->handle == HCI_CONN_HANDLE_UNSET) - hci_conn_del(sco); + if (link->handle == HCI_CONN_HANDLE_UNSET) + hci_conn_del(link); } /* Unacked frames */ @@ -1084,7 +1115,7 @@ int hci_conn_del(struct hci_conn *conn) struct hci_conn *acl = conn->link; if (acl) { - acl->link = NULL; + hci_conn_unlink(conn); hci_conn_drop(acl); } @@ -1179,31 +1210,8 @@ EXPORT_SYMBOL(hci_get_route); static void hci_le_conn_failed(struct hci_conn *conn, u8 status) { struct hci_dev *hdev = conn->hdev; - struct hci_conn_params *params; - params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, - conn->dst_type); - if (params && params->conn) { - hci_conn_drop(params->conn); - hci_conn_put(params->conn); - params->conn = NULL; - } - - /* If the status indicates successful cancellation of - * the attempt (i.e. Unknown Connection Id) there's no point of - * notifying failure since we'll go back to keep trying to - * connect. The only exception is explicit connect requests - * where a timeout + cancel does indicate an actual failure. - */ - if (status != HCI_ERROR_UNKNOWN_CONN_ID || - (params && params->explicit_connect)) - mgmt_connect_failed(hdev, &conn->dst, conn->type, - conn->dst_type, status); - - /* Since we may have temporarily stopped the background scanning in - * favor of connection establishment, we should restart it. - */ - hci_update_passive_scan(hdev); + hci_connect_le_scan_cleanup(conn, status); /* Enable advertising in case this was a failed connection * attempt as a peripheral. @@ -1237,15 +1245,15 @@ static void create_le_conn_complete(struct hci_dev *hdev, void *data, int err) { struct hci_conn *conn = data; + bt_dev_dbg(hdev, "err %d", err); + hci_dev_lock(hdev); if (!err) { - hci_connect_le_scan_cleanup(conn); + hci_connect_le_scan_cleanup(conn, 0x00); goto done; } - bt_dev_err(hdev, "request failed to create LE connection: err %d", err); - /* Check if connection is still pending */ if (conn != hci_lookup_le_connect(hdev)) goto done; @@ -2438,6 +2446,12 @@ void hci_conn_hash_flush(struct hci_dev *hdev) c->state = BT_CLOSED; hci_disconn_cfm(c, HCI_ERROR_LOCAL_HOST_TERM); + + /* Unlink before deleting otherwise it is possible that + * hci_conn_del removes the link which may cause the list to + * contain items already freed. + */ + hci_conn_unlink(c); hci_conn_del(c); } } @@ -2775,6 +2789,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason) { int r = 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + switch (conn->state) { case BT_CONNECTED: case BT_CONFIG: diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ad92a4be5851..e87c928c9e17 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2881,16 +2881,6 @@ static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr, conn->resp_addr_type = peer_addr_type; bacpy(&conn->resp_addr, peer_addr); - - /* We don't want the connection attempt to stick around - * indefinitely since LE doesn't have a page timeout concept - * like BR/EDR. Set a timer for any connection that doesn't use - * the accept list for connecting. - */ - if (filter_policy == HCI_LE_USE_PEER_ADDR) - queue_delayed_work(conn->hdev->workqueue, - &conn->le_conn_timeout, - conn->conn_timeout); } static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status) @@ -5902,6 +5892,12 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, if (status) goto unlock; + /* Drop the connection if it has been aborted */ + if (test_bit(HCI_CONN_CANCEL, &conn->flags)) { + hci_conn_drop(conn); + goto unlock; + } + if (conn->dst_type == ADDR_LE_DEV_PUBLIC) addr_type = BDADDR_LE_PUBLIC; else @@ -6995,7 +6991,7 @@ static void hci_le_big_sync_established_evt(struct hci_dev *hdev, void *data, bis->iso_qos.in.latency = le16_to_cpu(ev->interval) * 125 / 100; bis->iso_qos.in.sdu = le16_to_cpu(ev->max_pdu); - hci_connect_cfm(bis, ev->status); + hci_iso_setup_path(bis); } hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 5a6aa1627791..632be1267288 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -246,8 +246,9 @@ int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, skb = __hci_cmd_sync_sk(hdev, opcode, plen, param, event, timeout, sk); if (IS_ERR(skb)) { - bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, - PTR_ERR(skb)); + if (!event) + bt_dev_err(hdev, "Opcode 0x%4x failed: %ld", opcode, + PTR_ERR(skb)); return PTR_ERR(skb); } @@ -5126,8 +5127,11 @@ static int hci_le_connect_cancel_sync(struct hci_dev *hdev, if (test_bit(HCI_CONN_SCANNING, &conn->flags)) return 0; + if (test_and_set_bit(HCI_CONN_CANCEL, &conn->flags)) + return 0; + return __hci_cmd_sync_status(hdev, HCI_OP_LE_CREATE_CONN_CANCEL, - 6, &conn->dst, HCI_CMD_TIMEOUT); + 0, NULL, HCI_CMD_TIMEOUT); } static int hci_connect_cancel_sync(struct hci_dev *hdev, struct hci_conn *conn) @@ -6102,6 +6106,9 @@ int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn) conn->conn_timeout, NULL); done: + if (err == -ETIMEDOUT) + hci_le_connect_cancel_sync(hdev, conn); + /* Re-enable advertising after the connection attempt is finished. */ hci_resume_advertising_sync(hdev); return err; diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index bed1a7b9205c..707f229f896a 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -433,7 +433,7 @@ static void hidp_set_timer(struct hidp_session *session) static void hidp_del_timer(struct hidp_session *session) { if (session->idle_to > 0) - del_timer(&session->timer); + del_timer_sync(&session->timer); } static void hidp_process_report(struct hidp_session *session, int type, diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 49926f59cc12..55a7226233f9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4652,33 +4652,27 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, BT_DBG("scid 0x%4.4x dcid 0x%4.4x", scid, dcid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, dcid); + chan = l2cap_get_chan_by_scid(conn, dcid); if (!chan) { - mutex_unlock(&conn->chan_lock); cmd_reject_invalid_cid(conn, cmd->ident, dcid, scid); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - rsp.dcid = cpu_to_le16(chan->scid); rsp.scid = cpu_to_le16(chan->dcid); l2cap_send_cmd(conn, cmd->ident, L2CAP_DISCONN_RSP, sizeof(rsp), &rsp); chan->ops->set_shutdown(chan); + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, ECONNRESET); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } @@ -4698,33 +4692,27 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, BT_DBG("dcid 0x%4.4x scid 0x%4.4x", dcid, scid); - mutex_lock(&conn->chan_lock); - - chan = __l2cap_get_chan_by_scid(conn, scid); + chan = l2cap_get_chan_by_scid(conn, scid); if (!chan) { mutex_unlock(&conn->chan_lock); return 0; } - l2cap_chan_hold(chan); - l2cap_chan_lock(chan); - if (chan->state != BT_DISCONN) { l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); return 0; } + mutex_lock(&conn->chan_lock); l2cap_chan_del(chan, 0); + mutex_unlock(&conn->chan_lock); chan->ops->close(chan); l2cap_chan_unlock(chan); l2cap_chan_put(chan); - mutex_unlock(&conn->chan_lock); - return 0; } diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 1111da4e2f2b..cd1a27ac555d 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -235,27 +235,41 @@ static int sco_chan_add(struct sco_conn *conn, struct sock *sk, return err; } -static int sco_connect(struct hci_dev *hdev, struct sock *sk) +static int sco_connect(struct sock *sk) { struct sco_conn *conn; struct hci_conn *hcon; + struct hci_dev *hdev; int err, type; BT_DBG("%pMR -> %pMR", &sco_pi(sk)->src, &sco_pi(sk)->dst); + hdev = hci_get_route(&sco_pi(sk)->dst, &sco_pi(sk)->src, BDADDR_BREDR); + if (!hdev) + return -EHOSTUNREACH; + + hci_dev_lock(hdev); + if (lmp_esco_capable(hdev) && !disable_esco) type = ESCO_LINK; else type = SCO_LINK; if (sco_pi(sk)->setting == BT_VOICE_TRANSPARENT && - (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) - return -EOPNOTSUPP; + (!lmp_transp_capable(hdev) || !lmp_esco_capable(hdev))) { + err = -EOPNOTSUPP; + goto unlock; + } hcon = hci_connect_sco(hdev, type, &sco_pi(sk)->dst, sco_pi(sk)->setting, &sco_pi(sk)->codec); - if (IS_ERR(hcon)) - return PTR_ERR(hcon); + if (IS_ERR(hcon)) { + err = PTR_ERR(hcon); + goto unlock; + } + + hci_dev_unlock(hdev); + hci_dev_put(hdev); conn = sco_conn_add(hcon); if (!conn) { @@ -263,13 +277,15 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) return -ENOMEM; } - /* Update source addr of the socket */ - bacpy(&sco_pi(sk)->src, &hcon->src); - err = sco_chan_add(conn, sk, NULL); if (err) return err; + lock_sock(sk); + + /* Update source addr of the socket */ + bacpy(&sco_pi(sk)->src, &hcon->src); + if (hcon->state == BT_CONNECTED) { sco_sock_clear_timer(sk); sk->sk_state = BT_CONNECTED; @@ -278,6 +294,13 @@ static int sco_connect(struct hci_dev *hdev, struct sock *sk) sco_sock_set_timer(sk, sk->sk_sndtimeo); } + release_sock(sk); + + return err; + +unlock: + hci_dev_unlock(hdev); + hci_dev_put(hdev); return err; } @@ -565,7 +588,6 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen { struct sockaddr_sco *sa = (struct sockaddr_sco *) addr; struct sock *sk = sock->sk; - struct hci_dev *hdev; int err; BT_DBG("sk %p", sk); @@ -574,37 +596,26 @@ static int sco_sock_connect(struct socket *sock, struct sockaddr *addr, int alen addr->sa_family != AF_BLUETOOTH) return -EINVAL; - lock_sock(sk); - if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) { - err = -EBADFD; - goto done; - } + if (sk->sk_state != BT_OPEN && sk->sk_state != BT_BOUND) + return -EBADFD; - if (sk->sk_type != SOCK_SEQPACKET) { + if (sk->sk_type != SOCK_SEQPACKET) err = -EINVAL; - goto done; - } - - hdev = hci_get_route(&sa->sco_bdaddr, &sco_pi(sk)->src, BDADDR_BREDR); - if (!hdev) { - err = -EHOSTUNREACH; - goto done; - } - hci_dev_lock(hdev); + lock_sock(sk); /* Set destination address and psm */ bacpy(&sco_pi(sk)->dst, &sa->sco_bdaddr); + release_sock(sk); - err = sco_connect(hdev, sk); - hci_dev_unlock(hdev); - hci_dev_put(hdev); + err = sco_connect(sk); if (err) - goto done; + return err; + + lock_sock(sk); err = bt_sock_wait_state(sk, BT_CONNECTED, sock_sndtimeo(sk, flags & O_NONBLOCK)); -done: release_sock(sk); return err; } @@ -1129,6 +1140,8 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, break; } + release_sock(sk); + /* find total buffer size required to copy codec + caps */ hci_dev_lock(hdev); list_for_each_entry(c, &hdev->local_codecs, list) { @@ -1146,15 +1159,13 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, buf_len += sizeof(struct bt_codecs); if (buf_len > len) { hci_dev_put(hdev); - err = -ENOBUFS; - break; + return -ENOBUFS; } ptr = optval; if (put_user(num_codecs, ptr)) { hci_dev_put(hdev); - err = -EFAULT; - break; + return -EFAULT; } ptr += sizeof(num_codecs); @@ -1194,12 +1205,14 @@ static int sco_sock_getsockopt(struct socket *sock, int level, int optname, ptr += len; } - if (!err && put_user(buf_len, optlen)) - err = -EFAULT; - hci_dev_unlock(hdev); hci_dev_put(hdev); + lock_sock(sk); + + if (!err && put_user(buf_len, optlen)) + err = -EFAULT; + break; default: diff --git a/net/core/dev.c b/net/core/dev.c index 253584777101..1488f700bf81 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3199,6 +3199,7 @@ static u16 skb_tx_hash(const struct net_device *dev, } if (skb_rx_queue_recorded(skb)) { + DEBUG_NET_WARN_ON_ONCE(qcount == 0); hash = skb_get_rx_queue(skb); if (hash >= qoffset) hash -= qoffset; @@ -10846,7 +10847,7 @@ void unregister_netdevice_many_notify(struct list_head *head, dev->rtnl_link_state == RTNL_LINK_INITIALIZED) skb = rtmsg_ifinfo_build_skb(RTM_DELLINK, dev, ~0U, 0, GFP_KERNEL, NULL, 0, - portid, nlmsg_seq(nlh)); + portid, nlh); /* * Flush the unicast and multicast chains diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5d8eb57867a9..6e44e92ebdf5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -3972,16 +3972,23 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, unsigned int change, u32 event, gfp_t flags, int *new_nsid, - int new_ifindex, u32 portid, u32 seq) + int new_ifindex, u32 portid, + const struct nlmsghdr *nlh) { struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + u32 seq = 0; skb = nlmsg_new(if_nlmsg_size(dev, 0), flags); if (skb == NULL) goto errout; + if (nlmsg_report(nlh)) + seq = nlmsg_seq(nlh); + else + portid = 0; + err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, portid, seq, change, 0, 0, event, new_nsid, new_ifindex, -1, flags); @@ -4017,7 +4024,7 @@ static void rtmsg_ifinfo_event(int type, struct net_device *dev, return; skb = rtmsg_ifinfo_build_skb(type, dev, change, event, flags, new_nsid, - new_ifindex, portid, nlmsg_seq(nlh)); + new_ifindex, portid, nlh); if (skb) rtmsg_ifinfo_send(skb, dev, flags, portid, nlh); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 1a31815104d6..4c0879798eb8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -5599,18 +5599,18 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, if (skb_cloned(to)) return false; - /* In general, avoid mixing slab allocated and page_pool allocated - * pages within the same SKB. However when @to is not pp_recycle and - * @from is cloned, we can transition frag pages from page_pool to - * reference counted. - * - * On the other hand, don't allow coalescing two pp_recycle SKBs if - * @from is cloned, in case the SKB is using page_pool fragment + /* In general, avoid mixing page_pool and non-page_pool allocated + * pages within the same SKB. Additionally avoid dealing with clones + * with page_pool pages, in case the SKB is using page_pool fragment * references (PP_FLAG_PAGE_FRAG). Since we only take full page * references for cloned SKBs at the moment that would result in * inconsistent reference counts. + * In theory we could take full references if @from is cloned and + * !@to->pp_recycle but its tricky (due to potential race with + * the clone disappearing) and rare, so not worth dealing with. */ - if (to->pp_recycle != (from->pp_recycle && !skb_cloned(from))) + if (to->pp_recycle != from->pp_recycle || + (from->pp_recycle && skb_cloned(from))) return false; if (len <= skb_tailroom(to)) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 528d4b37983d..fb85aca81961 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -734,13 +734,21 @@ __bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *tim * bpf_xdp_metadata_rx_hash - Read XDP frame RX hash. * @ctx: XDP context pointer. * @hash: Return value pointer. + * @rss_type: Return value pointer for RSS type. + * + * The RSS hash type (@rss_type) specifies what portion of packet headers NIC + * hardware used when calculating RSS hash value. The RSS type can be decoded + * via &enum xdp_rss_hash_type either matching on individual L3/L4 bits + * ``XDP_RSS_L*`` or by combined traditional *RSS Hashing Types* + * ``XDP_RSS_TYPE_L*``. * * Return: * * Returns 0 on success or ``-errno`` on error. * * ``-EOPNOTSUPP`` : means device driver doesn't implement kfunc * * ``-ENODATA`` : means no RX-hash available for this frame */ -__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash) +__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash, + enum xdp_rss_hash_type *rss_type) { return -EOPNOTSUPP; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d0cc4ef2b85..40fe70fc2015 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -25,6 +25,7 @@ static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; static int tcp_adv_win_scale_min = -31; static int tcp_adv_win_scale_max = 31; +static int tcp_app_win_max = 31; static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS; static int tcp_min_snd_mss_max = 65535; static int ip_privileged_port_min; @@ -1198,6 +1199,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = &tcp_app_win_max, }, { .procname = "tcp_adv_win_scale", diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ea370afa70ed..b9d55277cb85 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2780,7 +2780,7 @@ static int tcp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, static void bpf_iter_tcp_put_batch(struct bpf_tcp_iter_state *iter) { while (iter->cur_sk < iter->end_sk) - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } static int bpf_iter_tcp_realloc_batch(struct bpf_tcp_iter_state *iter, @@ -2941,7 +2941,7 @@ static void *bpf_iter_tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) * st->bucket. See tcp_seek_last_pos(). */ st->offset++; - sock_put(iter->batch[iter->cur_sk++]); + sock_gen_put(iter->batch[iter->cur_sk++]); } if (iter->cur_sk < iter->end_sk) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fb2f33ee3a7..a675acfb901d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1395,9 +1395,11 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); do_udp_sendmsg: - if (ipv6_only_sock(sk)) - return -ENETUNREACH; - return udp_sendmsg(sk, msg, len); + err = ipv6_only_sock(sk) ? + -ENETUNREACH : udp_sendmsg(sk, msg, len); + msg->msg_name = sin6; + msg->msg_namelen = addr_len; + return err; } } diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index d237d142171c..bceaab8dd8e4 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -9,11 +9,18 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow, struct request_sock *req) { - struct sock *ssk = subflow->tcp_sock; - struct sock *sk = subflow->conn; + struct sock *sk, *ssk; struct sk_buff *skb; struct tcp_sock *tp; + /* on early fallback the subflow context is deleted by + * subflow_syn_recv_sock() + */ + if (!subflow) + return; + + ssk = subflow->tcp_sock; + sk = subflow->conn; tp = tcp_sk(ssk); subflow->is_mptfo = 1; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index b30cea2fbf3f..355f798d575a 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1192,9 +1192,8 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) */ if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) { if (mp_opt.data_fin && mp_opt.data_len == 1 && - mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64) && - schedule_work(&msk->work)) - sock_hold(subflow->conn); + mptcp_update_rcv_data_fin(msk, mp_opt.data_seq, mp_opt.dsn64)) + mptcp_schedule_work((struct sock *)msk); return true; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 60b23b2716c4..06c5872e3b00 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2626,7 +2626,7 @@ static void mptcp_worker(struct work_struct *work) lock_sock(sk); state = sk->sk_state; - if (unlikely(state == TCP_CLOSE)) + if (unlikely((1 << state) & (TCPF_CLOSE | TCPF_LISTEN))) goto unlock; mptcp_check_data_fin_ack(sk); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index a0041360ee9d..d34588850545 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -408,9 +408,8 @@ void mptcp_subflow_reset(struct sock *ssk) tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); - if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && - schedule_work(&mptcp_sk(sk)->work)) - return; /* worker will put sk for us */ + if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } @@ -1118,8 +1117,8 @@ static enum mapping_status get_mapping_status(struct sock *ssk, skb_ext_del(skb, SKB_EXT_MPTCP); return MAPPING_OK; } else { - if (updated && schedule_work(&msk->work)) - sock_hold((struct sock *)msk); + if (updated) + mptcp_schedule_work((struct sock *)msk); return MAPPING_DATA_FIN; } @@ -1222,17 +1221,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb, /* sched mptcp worker to remove the subflow if no more data is pending */ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk) { - struct sock *sk = (struct sock *)msk; - if (likely(ssk->sk_state != TCP_CLOSE)) return; if (skb_queue_empty(&ssk->sk_receive_queue) && - !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) { - sock_hold(sk); - if (!schedule_work(&msk->work)) - sock_put(sk); - } + !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) + mptcp_schedule_work((struct sock *)msk); } static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index ca3ebfdb3023..a8cf9a88758e 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -913,7 +913,7 @@ static void do_output(struct datapath *dp, struct sk_buff *skb, int out_port, { struct vport *vport = ovs_vport_rcu(dp, out_port); - if (likely(vport)) { + if (likely(vport && netif_carrier_ok(vport->dev))) { u16 mru = OVS_CB(skb)->mru; u32 cutlen = OVS_CB(skb)->cutlen; diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 3a70255c8d02..76f0434d3d06 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -498,6 +498,11 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (!size || len != ALIGN(size, 4) + hdrlen) goto err; + if ((cb->type == QRTR_TYPE_NEW_SERVER || + cb->type == QRTR_TYPE_RESUME_TX) && + size < sizeof(struct qrtr_ctrl_pkt)) + goto err; + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && cb->type != QRTR_TYPE_RESUME_TX) goto err; @@ -510,9 +515,6 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) /* Remote node endpoint can bridge other distant nodes */ const struct qrtr_ctrl_pkt *pkt; - if (size < sizeof(*pkt)) - goto err; - pkt = data + hdrlen; qrtr_node_assign(node, le32_to_cpu(pkt->server.node)); } diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c index 94727feb07b3..b046b11200c9 100644 --- a/net/sctp/stream_interleave.c +++ b/net/sctp/stream_interleave.c @@ -1154,7 +1154,8 @@ static void sctp_generate_iftsn(struct sctp_outq *q, __u32 ctsn) #define _sctp_walk_ifwdtsn(pos, chunk, end) \ for (pos = chunk->subh.ifwdtsn_hdr->skip; \ - (void *)pos < (void *)chunk->subh.ifwdtsn_hdr->skip + (end); pos++) + (void *)pos <= (void *)chunk->subh.ifwdtsn_hdr->skip + (end) - \ + sizeof(struct sctp_ifwdtsn_skip); pos++) #define sctp_walk_ifwdtsn(pos, ch) \ _sctp_walk_ifwdtsn((pos), (ch), ntohs((ch)->chunk_hdr->length) - \ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c6b4a62276f6..50c38b624f77 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -3270,6 +3270,17 @@ static int __smc_create(struct net *net, struct socket *sock, int protocol, sk_common_release(sk); goto out; } + + /* smc_clcsock_release() does not wait smc->clcsock->sk's + * destruction; its sk_state might not be TCP_CLOSE after + * smc->sk is close()d, and TCP timers can be fired later, + * which need net ref. + */ + sk = smc->clcsock->sk; + __netns_tracker_free(net, &sk->ns_tracker, false); + sk->sk_net_refcnt = 1; + get_net_track(net, &sk->ns_tracker, GFP_KERNEL); + sock_inuse_add(net, 1); } else { smc->clcsock = clcsock; } diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c index 7271a18ab3e2..8251a0fc6ee9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_do_redirect.c @@ -167,8 +167,7 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | - NETDEV_XDP_ACT_NDO_XMIT_SG, + NETDEV_XDP_ACT_RX_SG, "veth_src query_opts.feature_flags")) goto out; @@ -178,9 +177,34 @@ void test_xdp_do_redirect(void) if (!ASSERT_EQ(query_opts.feature_flags, NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_RX_SG, + "veth_dst query_opts.feature_flags")) + goto out; + + /* Enable GRO */ + SYS("ethtool -K veth_src gro on"); + SYS("ethtool -K veth_dst gro on"); + + err = bpf_xdp_query(ifindex_src, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_src bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | NETDEV_XDP_ACT_NDO_XMIT_SG, - "veth_dst query_opts.feature_flags")) + "veth_src query_opts.feature_flags gro on")) + goto out; + + err = bpf_xdp_query(ifindex_dst, XDP_FLAGS_DRV_MODE, &query_opts); + if (!ASSERT_OK(err, "veth_dst bpf_xdp_query gro on")) + goto out; + + if (!ASSERT_EQ(query_opts.feature_flags, + NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT | NETDEV_XDP_ACT_RX_SG | + NETDEV_XDP_ACT_NDO_XMIT_SG, + "veth_dst query_opts.feature_flags gro on")) goto out; memcpy(skel->rodata->expect_dst, &pkt_udp.eth.h_dest, ETH_ALEN); diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c index aa4beae99f4f..8c5e98da9ae9 100644 --- a/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c +++ b/tools/testing/selftests/bpf/prog_tests/xdp_metadata.c @@ -273,6 +273,8 @@ static int verify_xsk_metadata(struct xsk *xsk) if (!ASSERT_NEQ(meta->rx_hash, 0, "rx_hash")) return -1; + ASSERT_EQ(meta->rx_hash_type, 0, "rx_hash_type"); + xsk_ring_cons__release(&xsk->rx, 1); refill_rx(xsk, comp_addr); diff --git a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c index 4c55b4d79d3d..e1c787815e44 100644 --- a/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_hw_metadata.c @@ -12,10 +12,14 @@ struct { __type(value, __u32); } xsk SEC(".maps"); +__u64 pkts_skip = 0; +__u64 pkts_fail = 0; +__u64 pkts_redir = 0; + extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -26,7 +30,7 @@ int rx(struct xdp_md *ctx) struct udphdr *udp = NULL; struct iphdr *iph = NULL; struct xdp_meta *meta; - int ret; + int err; data = (void *)(long)ctx->data; data_end = (void *)(long)ctx->data_end; @@ -46,17 +50,20 @@ int rx(struct xdp_md *ctx) udp = NULL; } - if (!udp) + if (!udp) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - if (udp->dest != bpf_htons(9091)) + /* Forwarding UDP:9091 to AF_XDP */ + if (udp->dest != bpf_htons(9091)) { + __sync_add_and_fetch(&pkts_skip, 1); return XDP_PASS; + } - bpf_printk("forwarding UDP:9091 to AF_XDP"); - - ret = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); - if (ret != 0) { - bpf_printk("bpf_xdp_adjust_meta returned %d", ret); + err = bpf_xdp_adjust_meta(ctx, -(int)sizeof(struct xdp_meta)); + if (err) { + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } @@ -65,20 +72,19 @@ int rx(struct xdp_md *ctx) meta = data_meta; if (meta + 1 > data) { - bpf_printk("bpf_xdp_adjust_meta doesn't appear to work"); + __sync_add_and_fetch(&pkts_fail, 1); return XDP_PASS; } - if (!bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp)) - bpf_printk("populated rx_timestamp with %llu", meta->rx_timestamp); - else + err = bpf_xdp_metadata_rx_timestamp(ctx, &meta->rx_timestamp); + if (err) meta->rx_timestamp = 0; /* Used by AF_XDP as not avail signal */ - if (!bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash)) - bpf_printk("populated rx_hash with %u", meta->rx_hash); - else - meta->rx_hash = 0; /* Used by AF_XDP as not avail signal */ + err = bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); + if (err < 0) + meta->rx_hash_err = err; /* Used by AF_XDP as no hash signal */ + __sync_add_and_fetch(&pkts_redir, 1); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata.c b/tools/testing/selftests/bpf/progs/xdp_metadata.c index 77678b034389..d151d406a123 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata.c @@ -21,8 +21,8 @@ struct { extern int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, __u64 *timestamp) __ksym; -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; SEC("xdp") int rx(struct xdp_md *ctx) @@ -56,7 +56,7 @@ int rx(struct xdp_md *ctx) if (timestamp == 0) meta->rx_timestamp = 1; - bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash); + bpf_xdp_metadata_rx_hash(ctx, &meta->rx_hash, &meta->rx_hash_type); return bpf_redirect_map(&xsk, ctx->rx_queue_index, XDP_PASS); } diff --git a/tools/testing/selftests/bpf/progs/xdp_metadata2.c b/tools/testing/selftests/bpf/progs/xdp_metadata2.c index cf69d05451c3..85f88d9d7a78 100644 --- a/tools/testing/selftests/bpf/progs/xdp_metadata2.c +++ b/tools/testing/selftests/bpf/progs/xdp_metadata2.c @@ -5,17 +5,18 @@ #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> -extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, - __u32 *hash) __ksym; +extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash, + enum xdp_rss_hash_type *rss_type) __ksym; int called; SEC("freplace/rx") int freplace_rx(struct xdp_md *ctx) { + enum xdp_rss_hash_type type = 0; u32 hash = 0; /* Call _any_ metadata function to make sure we don't crash. */ - bpf_xdp_metadata_rx_hash(ctx, &hash); + bpf_xdp_metadata_rx_hash(ctx, &hash, &type); called++; return XDP_PASS; } diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c index 1c8acb68b977..987cf0db5ebc 100644 --- a/tools/testing/selftests/bpf/xdp_hw_metadata.c +++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c @@ -141,7 +141,11 @@ static void verify_xdp_metadata(void *data) meta = data - sizeof(*meta); printf("rx_timestamp: %llu\n", meta->rx_timestamp); - printf("rx_hash: %u\n", meta->rx_hash); + if (meta->rx_hash_err < 0) + printf("No rx_hash err=%d\n", meta->rx_hash_err); + else + printf("rx_hash: 0x%X with RSS type:0x%X\n", + meta->rx_hash, meta->rx_hash_type); } static void verify_skb_metadata(int fd) @@ -212,7 +216,9 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd) while (true) { errno = 0; ret = poll(fds, rxq + 1, 1000); - printf("poll: %d (%d)\n", ret, errno); + printf("poll: %d (%d) skip=%llu fail=%llu redir=%llu\n", + ret, errno, bpf_obj->bss->pkts_skip, + bpf_obj->bss->pkts_fail, bpf_obj->bss->pkts_redir); if (ret < 0) break; if (ret == 0) diff --git a/tools/testing/selftests/bpf/xdp_metadata.h b/tools/testing/selftests/bpf/xdp_metadata.h index f6780fbb0a21..0c4624dc6f2f 100644 --- a/tools/testing/selftests/bpf/xdp_metadata.h +++ b/tools/testing/selftests/bpf/xdp_metadata.h @@ -12,4 +12,8 @@ struct xdp_meta { __u64 rx_timestamp; __u32 rx_hash; + union { + __u32 rx_hash_type; + __s32 rx_hash_err; + }; }; diff --git a/tools/testing/selftests/drivers/net/bonding/Makefile b/tools/testing/selftests/drivers/net/bonding/Makefile index a39bb2560d9b..03f92d7aeb19 100644 --- a/tools/testing/selftests/drivers/net/bonding/Makefile +++ b/tools/testing/selftests/drivers/net/bonding/Makefile @@ -8,11 +8,12 @@ TEST_PROGS := \ dev_addr_lists.sh \ mode-1-recovery-updelay.sh \ mode-2-recovery-updelay.sh \ - option_prio.sh \ + bond_options.sh \ bond-eth-type-change.sh TEST_FILES := \ lag_lib.sh \ + bond_topo_3d1c.sh \ net_forwarding_lib.sh include ../../../lib.mk diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh new file mode 100755 index 000000000000..db29a3146a86 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -0,0 +1,264 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Test bonding options with mode 1,5,6 + +ALL_TESTS=" + prio + arp_validate +" + +REQUIRE_MZ=no +NUM_NETIFS=0 +lib_dir=$(dirname "$0") +source ${lib_dir}/net_forwarding_lib.sh +source ${lib_dir}/bond_topo_3d1c.sh + +skip_prio() +{ + local skip=1 + + # check if iproute support prio option + ip -n ${s_ns} link set eth0 type bond_slave prio 10 + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support prio option + ip -n ${s_ns} -d link show eth0 | grep -q "prio 10" + [[ $? -ne 0 ]] && skip=0 + + return $skip +} + +skip_ns() +{ + local skip=1 + + # check if iproute support ns_ip6_target option + ip -n ${s_ns} link add bond1 type bond ns_ip6_target ${g_ip6} + [[ $? -ne 0 ]] && skip=0 + + # check if kernel support ns_ip6_target option + ip -n ${s_ns} -d link show bond1 | grep -q "ns_ip6_target ${g_ip6}" + [[ $? -ne 0 ]] && skip=0 + + ip -n ${s_ns} link del bond1 + + return $skip +} + +active_slave="" +check_active_slave() +{ + local target_active_slave=$1 + active_slave=$(cmd_jq "ip -n ${s_ns} -d -j link show bond0" ".[].linkinfo.info_data.active_slave") + test "$active_slave" = "$target_active_slave" + check_err $? "Current active slave is $active_slave but not $target_active_slave" +} + + +# Test bonding prio option +prio_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + # check bonding member prio value + ip -n ${s_ns} link set eth0 type bond_slave prio 0 + ip -n ${s_ns} link set eth1 type bond_slave prio 10 + ip -n ${s_ns} link set eth2 type bond_slave prio 11 + cmd_jq "ip -n ${s_ns} -d -j link show eth0" \ + ".[].linkinfo.info_slave_data | select (.prio == 0)" "-e" &> /dev/null + check_err $? "eth0 prio is not 0" + cmd_jq "ip -n ${s_ns} -d -j link show eth1" \ + ".[].linkinfo.info_slave_data | select (.prio == 10)" "-e" &> /dev/null + check_err $? "eth1 prio is not 10" + cmd_jq "ip -n ${s_ns} -d -j link show eth2" \ + ".[].linkinfo.info_slave_data | select (.prio == 11)" "-e" &> /dev/null + check_err $? "eth2 prio is not 11" + + bond_check_connection "setup" + + # active slave should be the primary slave + check_active_slave eth1 + + # active slave should be the higher prio slave + ip -n ${s_ns} link set $active_slave down + bond_check_connection "fail over" + check_active_slave eth2 + + # when only 1 slave is up + ip -n ${s_ns} link set $active_slave down + bond_check_connection "only 1 slave up" + check_active_slave eth0 + + # when a higher prio slave change to up + ip -n ${s_ns} link set eth2 up + bond_check_connection "higher prio slave up" + case $primary_reselect in + "0") + check_active_slave "eth2" + ;; + "1") + check_active_slave "eth0" + ;; + "2") + check_active_slave "eth0" + ;; + esac + local pre_active_slave=$active_slave + + # when the primary slave change to up + ip -n ${s_ns} link set eth1 up + bond_check_connection "primary slave up" + case $primary_reselect in + "0") + check_active_slave "eth1" + ;; + "1") + check_active_slave "$pre_active_slave" + ;; + "2") + check_active_slave "$pre_active_slave" + ip -n ${s_ns} link set $active_slave down + bond_check_connection "pre_active slave down" + check_active_slave "eth1" + ;; + esac + + # Test changing bond slave prio + if [[ "$primary_reselect" == "0" ]];then + ip -n ${s_ns} link set eth0 type bond_slave prio 1000000 + ip -n ${s_ns} link set eth1 type bond_slave prio 0 + ip -n ${s_ns} link set eth2 type bond_slave prio -50 + ip -n ${s_ns} -d link show eth0 | grep -q 'prio 1000000' + check_err $? "eth0 prio is not 1000000" + ip -n ${s_ns} -d link show eth1 | grep -q 'prio 0' + check_err $? "eth1 prio is not 0" + ip -n ${s_ns} -d link show eth2 | grep -q 'prio -50' + check_err $? "eth3 prio is not -50" + check_active_slave "eth1" + + ip -n ${s_ns} link set $active_slave down + bond_check_connection "change slave prio" + check_active_slave "eth0" + fi +} + +prio_miimon() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode $mode miimon 100 primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode miimon primary_reselect $primary_reselect" + done +} + +prio_arp() +{ + local primary_reselect + local mode=$1 + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 arp_ip_target ${g_ip4} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode arp_ip_target primary_reselect $primary_reselect" + done +} + +prio_ns() +{ + local primary_reselect + local mode=$1 + + if skip_ns; then + log_test_skip "prio ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for primary_reselect in 0 1 2; do + prio_test "mode active-backup arp_interval 100 ns_ip6_target ${g_ip6} primary eth1 primary_reselect $primary_reselect" + log_test "prio" "$mode ns_ip6_target primary_reselect $primary_reselect" + done +} + +prio() +{ + local mode modes="active-backup balance-tlb balance-alb" + + if skip_prio; then + log_test_skip "prio" "Current iproute or kernel doesn't support bond option 'prio'." + return 0 + fi + + for mode in $modes; do + prio_miimon $mode + prio_arp $mode + prio_ns $mode + done +} + +arp_validate_test() +{ + local param="$1" + RET=0 + + # create bond + bond_reset "${param}" + + bond_check_connection + [ $RET -ne 0 ] && log_test "arp_validate" "$retmsg" + + # wait for a while to make sure the mii status stable + sleep 5 + for i in $(seq 0 2); do + mii_status=$(cmd_jq "ip -n ${s_ns} -j -d link show eth$i" ".[].linkinfo.info_slave_data.mii_status") + if [ ${mii_status} != "UP" ]; then + RET=1 + log_test "arp_validate" "interface eth$i mii_status $mii_status" + fi + done +} + +arp_validate_arp() +{ + local mode=$1 + local val + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 arp_ip_target ${g_ip4} arp_validate $val" + log_test "arp_validate" "$mode arp_ip_target arp_validate $val" + done +} + +arp_validate_ns() +{ + local mode=$1 + local val + + if skip_ns; then + log_test_skip "arp_validate ns" "Current iproute or kernel doesn't support bond option 'ns_ip6_target'." + return 0 + fi + + for val in $(seq 0 6); do + arp_validate_test "mode $mode arp_interval 100 ns_ip6_target ${g_ip6} arp_validate $val" + log_test "arp_validate" "$mode ns_ip6_target arp_validate $val" + done +} + +arp_validate() +{ + arp_validate_arp "active-backup" + arp_validate_ns "active-backup" +} + +trap cleanup EXIT + +setup_prepare +setup_wait +tests_run + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh new file mode 100644 index 000000000000..4045ca97fb22 --- /dev/null +++ b/tools/testing/selftests/drivers/net/bonding/bond_topo_3d1c.sh @@ -0,0 +1,143 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 +# +# Topology for Bond mode 1,5,6 testing +# +# +-------------------------------------+ +# | bond0 | +# | + | Server +# | eth0 | eth1 eth2 | 192.0.2.1/24 +# | +-------------------+ | 2001:db8::1/24 +# | | | | | +# +-------------------------------------+ +# | | | +# +-------------------------------------+ +# | | | | | +# | +---+---------+---------+---+ | Gateway +# | | br0 | | 192.0.2.254/24 +# | +-------------+-------------+ | 2001:db8::254/24 +# | | | +# +-------------------------------------+ +# | +# +-------------------------------------+ +# | | | Client +# | + | 192.0.2.10/24 +# | eth0 | 2001:db8::10/24 +# +-------------------------------------+ + +s_ns="s-$(mktemp -u XXXXXX)" +c_ns="c-$(mktemp -u XXXXXX)" +g_ns="g-$(mktemp -u XXXXXX)" +s_ip4="192.0.2.1" +c_ip4="192.0.2.10" +g_ip4="192.0.2.254" +s_ip6="2001:db8::1" +c_ip6="2001:db8::10" +g_ip6="2001:db8::254" + +gateway_create() +{ + ip netns add ${g_ns} + ip -n ${g_ns} link add br0 type bridge + ip -n ${g_ns} link set br0 up + ip -n ${g_ns} addr add ${g_ip4}/24 dev br0 + ip -n ${g_ns} addr add ${g_ip6}/24 dev br0 +} + +gateway_destroy() +{ + ip -n ${g_ns} link del br0 + ip netns del ${g_ns} +} + +server_create() +{ + ip netns add ${s_ns} + ip -n ${s_ns} link add bond0 type bond mode active-backup miimon 100 + + for i in $(seq 0 2); do + ip -n ${s_ns} link add eth${i} type veth peer name s${i} netns ${g_ns} + + ip -n ${g_ns} link set s${i} up + ip -n ${g_ns} link set s${i} master br0 + ip -n ${s_ns} link set eth${i} master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +# Reset bond with new mode and options +bond_reset() +{ + local param="$1" + + ip -n ${s_ns} link set bond0 down + ip -n ${s_ns} link del bond0 + + ip -n ${s_ns} link add bond0 type bond $param + for i in $(seq 0 2); do + ip -n ${s_ns} link set eth$i master bond0 + done + + ip -n ${s_ns} link set bond0 up + ip -n ${s_ns} addr add ${s_ip4}/24 dev bond0 + ip -n ${s_ns} addr add ${s_ip6}/24 dev bond0 + sleep 2 +} + +server_destroy() +{ + for i in $(seq 0 2); do + ip -n ${s_ns} link del eth${i} + done + ip netns del ${s_ns} +} + +client_create() +{ + ip netns add ${c_ns} + ip -n ${c_ns} link add eth0 type veth peer name c0 netns ${g_ns} + + ip -n ${g_ns} link set c0 up + ip -n ${g_ns} link set c0 master br0 + + ip -n ${c_ns} link set eth0 up + ip -n ${c_ns} addr add ${c_ip4}/24 dev eth0 + ip -n ${c_ns} addr add ${c_ip6}/24 dev eth0 +} + +client_destroy() +{ + ip -n ${c_ns} link del eth0 + ip netns del ${c_ns} +} + +setup_prepare() +{ + gateway_create + server_create + client_create +} + +cleanup() +{ + pre_cleanup + + client_destroy + server_destroy + gateway_destroy +} + +bond_check_connection() +{ + local msg=${1:-"check connection"} + + sleep 2 + ip netns exec ${s_ns} ping ${c_ip4} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping failed" + ip netns exec ${s_ns} ping6 ${c_ip6} -c5 -i 0.1 &>/dev/null + check_err $? "${msg}: ping6 failed" +} diff --git a/tools/testing/selftests/drivers/net/bonding/option_prio.sh b/tools/testing/selftests/drivers/net/bonding/option_prio.sh deleted file mode 100755 index c32eebff5005..000000000000 --- a/tools/testing/selftests/drivers/net/bonding/option_prio.sh +++ /dev/null @@ -1,245 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# -# Test bonding option prio -# - -ALL_TESTS=" - prio_arp_ip_target_test - prio_miimon_test -" - -REQUIRE_MZ=no -REQUIRE_JQ=no -NUM_NETIFS=0 -lib_dir=$(dirname "$0") -source "$lib_dir"/net_forwarding_lib.sh - -destroy() -{ - ip link del bond0 &>/dev/null - ip link del br0 &>/dev/null - ip link del veth0 &>/dev/null - ip link del veth1 &>/dev/null - ip link del veth2 &>/dev/null - ip netns del ns1 &>/dev/null - ip link del veth3 &>/dev/null -} - -cleanup() -{ - pre_cleanup - - destroy -} - -skip() -{ - local skip=1 - ip link add name bond0 type bond mode 1 miimon 100 &>/dev/null - ip link add name veth0 type veth peer name veth0_p - ip link set veth0 master bond0 - - # check if iproute support prio option - ip link set dev veth0 type bond_slave prio 10 - [[ $? -ne 0 ]] && skip=0 - - # check if bonding support prio option - ip -d link show veth0 | grep -q "prio 10" - [[ $? -ne 0 ]] && skip=0 - - ip link del bond0 &>/dev/null - ip link del veth0 - - return $skip -} - -active_slave="" -check_active_slave() -{ - local target_active_slave=$1 - active_slave="$(cat /sys/class/net/bond0/bonding/active_slave)" - test "$active_slave" = "$target_active_slave" - check_err $? "Current active slave is $active_slave but not $target_active_slave" -} - - -# Test bonding prio option with mode=$mode monitor=$monitor -# and primary_reselect=$primary_reselect -prio_test() -{ - RET=0 - - local monitor=$1 - local mode=$2 - local primary_reselect=$3 - - local bond_ip4="192.169.1.2" - local peer_ip4="192.169.1.1" - local bond_ip6="2009:0a:0b::02" - local peer_ip6="2009:0a:0b::01" - - - # create veths - ip link add name veth0 type veth peer name veth0_p - ip link add name veth1 type veth peer name veth1_p - ip link add name veth2 type veth peer name veth2_p - - # create bond - if [[ "$monitor" == "miimon" ]];then - ip link add name bond0 type bond mode $mode miimon 100 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "arp_ip_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 arp_ip_target $peer_ip4 primary veth1 primary_reselect $primary_reselect - elif [[ "$monitor" == "ns_ip6_target" ]];then - ip link add name bond0 type bond mode $mode arp_interval 1000 ns_ip6_target $peer_ip6 primary veth1 primary_reselect $primary_reselect - fi - ip link set bond0 up - ip link set veth0 master bond0 - ip link set veth1 master bond0 - ip link set veth2 master bond0 - # check bonding member prio value - ip link set dev veth0 type bond_slave prio 0 - ip link set dev veth1 type bond_slave prio 10 - ip link set dev veth2 type bond_slave prio 11 - ip -d link show veth0 | grep -q 'prio 0' - check_err $? "veth0 prio is not 0" - ip -d link show veth1 | grep -q 'prio 10' - check_err $? "veth0 prio is not 10" - ip -d link show veth2 | grep -q 'prio 11' - check_err $? "veth0 prio is not 11" - - ip link set veth0 up - ip link set veth1 up - ip link set veth2 up - ip link set veth0_p up - ip link set veth1_p up - ip link set veth2_p up - - # prepare ping target - ip link add name br0 type bridge - ip link set br0 up - ip link set veth0_p master br0 - ip link set veth1_p master br0 - ip link set veth2_p master br0 - ip link add name veth3 type veth peer name veth3_p - ip netns add ns1 - ip link set veth3_p master br0 up - ip link set veth3 netns ns1 up - ip netns exec ns1 ip addr add $peer_ip4/24 dev veth3 - ip netns exec ns1 ip addr add $peer_ip6/64 dev veth3 - ip addr add $bond_ip4/24 dev bond0 - ip addr add $bond_ip6/64 dev bond0 - sleep 5 - - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 1." - ping6 $peer_ip6 -c5 -I bond0 &>/dev/null - check_err $? "ping6 failed 1." - - # active salve should be the primary slave - check_active_slave veth1 - - # active slave should be the higher prio slave - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 2." - check_active_slave veth2 - - # when only 1 slave is up - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 3." - check_active_slave veth0 - - # when a higher prio slave change to up - ip link set veth2 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 4." - case $primary_reselect in - "0") - check_active_slave "veth2" - ;; - "1") - check_active_slave "veth0" - ;; - "2") - check_active_slave "veth0" - ;; - esac - local pre_active_slave=$active_slave - - # when the primary slave change to up - ip link set veth1 up - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 5." - case $primary_reselect in - "0") - check_active_slave "veth1" - ;; - "1") - check_active_slave "$pre_active_slave" - ;; - "2") - check_active_slave "$pre_active_slave" - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 6." - check_active_slave "veth1" - ;; - esac - - # Test changing bond salve prio - if [[ "$primary_reselect" == "0" ]];then - ip link set dev veth0 type bond_slave prio 1000000 - ip link set dev veth1 type bond_slave prio 0 - ip link set dev veth2 type bond_slave prio -50 - ip -d link show veth0 | grep -q 'prio 1000000' - check_err $? "veth0 prio is not 1000000" - ip -d link show veth1 | grep -q 'prio 0' - check_err $? "veth1 prio is not 0" - ip -d link show veth2 | grep -q 'prio -50' - check_err $? "veth3 prio is not -50" - check_active_slave "veth1" - - ip link set $active_slave down - ping $peer_ip4 -c5 -I bond0 &>/dev/null - check_err $? "ping failed 7." - check_active_slave "veth0" - fi - - cleanup - - log_test "prio_test" "Test bonding option 'prio' with mode=$mode monitor=$monitor and primary_reselect=$primary_reselect" -} - -prio_miimon_test() -{ - local mode - local primary_reselect - - for mode in 1 5 6; do - for primary_reselect in 0 1 2; do - prio_test "miimon" $mode $primary_reselect - done - done -} - -prio_arp_ip_target_test() -{ - local primary_reselect - - for primary_reselect in 0 1 2; do - prio_test "arp_ip_target" 1 $primary_reselect - done -} - -if skip;then - log_test_skip "option_prio.sh" "Current iproute doesn't support 'prio'." - exit 0 -fi - -trap cleanup EXIT - -tests_run - -exit "$EXIT_STATUS" diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config index cc9fd55ab869..2529226ce87c 100644 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@ -48,3 +48,4 @@ CONFIG_BAREUDP=m CONFIG_IPV6_IOAM6_LWTUNNEL=y CONFIG_CRYPTO_SM4_GENERIC=y CONFIG_AMT=m +CONFIG_IP_SCTP=m diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 48e52f995a98..b1eb7bce599d 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -913,6 +913,7 @@ test_listener() $client4_port > /dev/null 2>&1 & local listener_pid=$! + sleep 0.5 verify_listener_events $client_evts $LISTENER_CREATED $AF_INET 10.0.2.2 $client4_port # ADD_ADDR from client to server machine reusing the subflow port @@ -928,6 +929,7 @@ test_listener() # Delete the listener from the client ns, if one was created kill_wait $listener_pid + sleep 0.5 verify_listener_events $client_evts $LISTENER_CLOSED $AF_INET 10.0.2.2 $client4_port } diff --git a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py index 3243c90d449e..5d467d1993cb 100644 --- a/tools/testing/selftests/net/openvswitch/ovs-dpctl.py +++ b/tools/testing/selftests/net/openvswitch/ovs-dpctl.py @@ -62,7 +62,7 @@ class OvsDatapath(GenericNetlinkSocket): nla_map = ( ("OVS_DP_ATTR_UNSPEC", "none"), ("OVS_DP_ATTR_NAME", "asciiz"), - ("OVS_DP_ATTR_UPCALL_PID", "uint32"), + ("OVS_DP_ATTR_UPCALL_PID", "array(uint32)"), ("OVS_DP_ATTR_STATS", "dpstats"), ("OVS_DP_ATTR_MEGAFLOW_STATS", "megaflowstats"), ("OVS_DP_ATTR_USER_FEATURES", "uint32"), |