diff options
27 files changed, 362 insertions, 124 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 6cc825857722..6a288d59ff79 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14350,9 +14350,8 @@ F: Documentation/devicetree/bindings/sound/nxp,tfa989x.yaml F: sound/soc/codecs/tfa989x.c NXP-NCI NFC DRIVER -R: Charles Gorand <[email protected]> L: [email protected] (subscribers-only) -S: Supported +S: Orphan F: Documentation/devicetree/bindings/net/nfc/nxp,nci.yaml F: drivers/nfc/nxp-nci diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 303c8d32d451..007d43e46dcb 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1302,12 +1302,12 @@ int bond_alb_initialize(struct bonding *bond, int rlb_enabled) return res; if (rlb_enabled) { - bond->alb_info.rlb_enabled = 1; res = rlb_initialize(bond); if (res) { tlb_deinitialize(bond); return res; } + bond->alb_info.rlb_enabled = 1; } else { bond->alb_info.rlb_enabled = 0; } diff --git a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h index cc51149790ff..3d5d39a52fe6 100644 --- a/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h +++ b/drivers/net/ethernet/marvell/octeon_ep/octep_regs_cn9k_pf.h @@ -52,7 +52,7 @@ #define CN93_SDP_EPF_RINFO_SRN(val) ((val) & 0xFF) #define CN93_SDP_EPF_RINFO_RPVF(val) (((val) >> 32) & 0xF) -#define CN93_SDP_EPF_RINFO_NVFS(val) (((val) >> 48) && 0xFF) +#define CN93_SDP_EPF_RINFO_NVFS(val) (((val) >> 48) & 0xFF) /* SDP Function select */ #define CN93_SDP_FUNC_SEL_EPF_BIT_POS 8 diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c index a0654e88444c..0329caf63279 100644 --- a/drivers/net/ethernet/smsc/epic100.c +++ b/drivers/net/ethernet/smsc/epic100.c @@ -1515,14 +1515,14 @@ static void epic_remove_one(struct pci_dev *pdev) struct net_device *dev = pci_get_drvdata(pdev); struct epic_private *ep = netdev_priv(dev); + unregister_netdev(dev); dma_free_coherent(&pdev->dev, TX_TOTAL_SIZE, ep->tx_ring, ep->tx_ring_dma); dma_free_coherent(&pdev->dev, RX_TOTAL_SIZE, ep->rx_ring, ep->rx_ring_dma); - unregister_netdev(dev); pci_iounmap(pdev, ep->ioaddr); - pci_release_regions(pdev); free_netdev(dev); + pci_release_regions(pdev); pci_disable_device(pdev); /* pci_power_off(pdev, -1); */ } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7fd0288c3789..e2eb35887394 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -273,6 +273,12 @@ static void tun_napi_init(struct tun_struct *tun, struct tun_file *tfile, } } +static void tun_napi_enable(struct tun_file *tfile) +{ + if (tfile->napi_enabled) + napi_enable(&tfile->napi); +} + static void tun_napi_disable(struct tun_file *tfile) { if (tfile->napi_enabled) @@ -653,8 +659,10 @@ static void __tun_detach(struct tun_file *tfile, bool clean) if (clean) { RCU_INIT_POINTER(tfile->tun, NULL); sock_put(&tfile->sk); - } else + } else { tun_disable_queue(tun, tfile); + tun_napi_disable(tfile); + } synchronize_net(); tun_flow_delete_by_queue(tun, tun->numqueues + 1); @@ -808,6 +816,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, if (tfile->detached) { tun_enable_queue(tfile); + tun_napi_enable(tfile); } else { sock_hold(&tfile->sk); tun_napi_init(tun, tfile, napi, napi_frags); diff --git a/drivers/net/usb/asix.h b/drivers/net/usb/asix.h index 2c81236c6c7c..45d3cc5cc355 100644 --- a/drivers/net/usb/asix.h +++ b/drivers/net/usb/asix.h @@ -126,8 +126,7 @@ AX_MEDIUM_RE) #define AX88772_MEDIUM_DEFAULT \ - (AX_MEDIUM_FD | AX_MEDIUM_RFC | \ - AX_MEDIUM_TFC | AX_MEDIUM_PS | \ + (AX_MEDIUM_FD | AX_MEDIUM_PS | \ AX_MEDIUM_AC | AX_MEDIUM_RE) /* AX88772 & AX88178 RX_CTL values */ diff --git a/drivers/net/usb/asix_common.c b/drivers/net/usb/asix_common.c index 632fa6c1d5e3..b4a1b7abcfc9 100644 --- a/drivers/net/usb/asix_common.c +++ b/drivers/net/usb/asix_common.c @@ -431,6 +431,7 @@ void asix_adjust_link(struct net_device *netdev) asix_write_medium_mode(dev, mode, 0); phy_print_status(phydev); + usbnet_link_change(dev, phydev->link, 0); } int asix_write_gpio(struct usbnet *dev, u16 value, int sleep, int in_pm) diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index ceef81d93ac9..01329b91d59d 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -167,9 +167,9 @@ static int nfcmrvl_i2c_parse_dt(struct device_node *node, pdata->irq_polarity = IRQF_TRIGGER_RISING; ret = irq_of_parse_and_map(node, 0); - if (ret < 0) { - pr_err("Unable to get irq, error: %d\n", ret); - return ret; + if (!ret) { + pr_err("Unable to get irq\n"); + return -EINVAL; } pdata->irq = ret; diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index a38e2fcdfd39..ad3359a4942c 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -115,9 +115,9 @@ static int nfcmrvl_spi_parse_dt(struct device_node *node, } ret = irq_of_parse_and_map(node, 0); - if (ret < 0) { - pr_err("Unable to get irq, error: %d\n", ret); - return ret; + if (!ret) { + pr_err("Unable to get irq\n"); + return -EINVAL; } pdata->irq = ret; diff --git a/drivers/nfc/nxp-nci/i2c.c b/drivers/nfc/nxp-nci/i2c.c index 7e451c10985d..ae2ba08d8ac3 100644 --- a/drivers/nfc/nxp-nci/i2c.c +++ b/drivers/nfc/nxp-nci/i2c.c @@ -122,7 +122,9 @@ static int nxp_nci_i2c_fw_read(struct nxp_nci_i2c_phy *phy, skb_put_data(*skb, &header, NXP_NCI_FW_HDR_LEN); r = i2c_master_recv(client, skb_put(*skb, frame_len), frame_len); - if (r != frame_len) { + if (r < 0) { + goto fw_read_exit_free_skb; + } else if (r != frame_len) { nfc_err(&client->dev, "Invalid frame length: %u (expected %zu)\n", r, frame_len); @@ -162,8 +164,13 @@ static int nxp_nci_i2c_nci_read(struct nxp_nci_i2c_phy *phy, skb_put_data(*skb, (void *)&header, NCI_CTRL_HDR_SIZE); + if (!header.plen) + return 0; + r = i2c_master_recv(client, skb_put(*skb, header.plen), header.plen); - if (r != header.plen) { + if (r < 0) { + goto nci_read_exit_free_skb; + } else if (r != header.plen) { nfc_err(&client->dev, "Invalid frame payload length: %u (expected %u)\n", r, header.plen); diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 921963589904..dfe19bf13f4c 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -2,16 +2,17 @@ #ifndef _UAPI_MPTCP_H #define _UAPI_MPTCP_H +#ifndef __KERNEL__ +#include <netinet/in.h> /* for sockaddr_in and sockaddr_in6 */ +#include <sys/socket.h> /* for struct sockaddr */ +#endif + #include <linux/const.h> #include <linux/types.h> #include <linux/in.h> /* for sockaddr_in */ #include <linux/in6.h> /* for sockaddr_in6 */ #include <linux/socket.h> /* for sockaddr_storage and sa_family */ -#ifndef __KERNEL__ -#include <sys/socket.h> /* for struct sockaddr */ -#endif - #define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) #define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) #define MPTCP_SUBFLOW_FLAG_JOIN_REM _BITUL(2) diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1b1932502e9e..5864cbc30db6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1109,10 +1109,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, goto out; } - if (net->ipv6.devconf_all->disable_policy || - idev->cnf.disable_policy) - f6i->dst_nopolicy = true; - neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *cfg->pfx; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d25dc83bac62..828355710c57 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4569,8 +4569,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, } f6i = ip6_route_info_create(&cfg, gfp_flags, NULL); - if (!IS_ERR(f6i)) + if (!IS_ERR(f6i)) { f6i->dst_nocount = true; + + if (!anycast && + (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy)) + f6i->dst_nopolicy = true; + } + return f6i; } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 6de01185cc68..d43c50a7310d 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -406,7 +406,6 @@ int __net_init seg6_hmac_net_init(struct net *net) return rhashtable_init(&sdata->hmac_infos, &rht_params); } -EXPORT_SYMBOL(seg6_hmac_net_init); void seg6_hmac_exit(void) { diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c0b138c20992..6bcd5e419a08 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; - rcu_read_lock(); - ca = min(t->prl_count, cmax); if (!kp) { @@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u } } - c = 0; + rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; @@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u if (kprl.addr != htonl(INADDR_ANY)) break; } -out: + rcu_read_unlock(); len = sizeof(*kp) * c; @@ -362,7 +360,7 @@ out: ret = -EFAULT; kfree(kp); - +out: return ret; } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index be3b918a6d15..aead331866a0 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -765,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu opts->suboptions |= OPTION_MPTCP_RST; opts->reset_transient = subflow->reset_transient; opts->reset_reason = subflow->reset_reason; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); return true; } @@ -788,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, opts->rcvr_key = msk->remote_key; pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } @@ -809,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, opts->fail_seq = subflow->map_seq; pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; } @@ -833,13 +836,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); } /* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */ if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); } return true; } @@ -966,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, goto reset; subflow->mp_capable = 0; pr_fallback(msk); - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); return false; } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 59a85220edc9..45e2a48397b9 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -299,23 +299,21 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - struct sock *s = (struct sock *)msk; pr_debug("fail_seq=%llu", fail_seq); if (!READ_ONCE(msk->allow_infinite_fallback)) return; - if (!READ_ONCE(subflow->mp_fail_response_expect)) { + if (!subflow->fail_tout) { pr_debug("send MP_FAIL response and infinite map"); subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); subflow->send_infinite_map = 1; - } else if (!sock_flag(sk, SOCK_DEAD)) { + tcp_send_ack(sk); + } else { pr_debug("MP_FAIL response received"); - - sk_stop_timer(s, &s->sk_timer); + WRITE_ONCE(subflow->fail_tout, 0); } } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 17e13396024a..e475212f2618 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -500,7 +500,7 @@ static void mptcp_set_timeout(struct sock *sk) __mptcp_set_timeout(sk, tout); } -static bool tcp_can_send_ack(const struct sock *ssk) +static inline bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); @@ -1245,7 +1245,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX); mptcp_subflow_ctx(ssk)->send_infinite_map = 0; pr_fallback(msk); - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); } static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, @@ -2175,21 +2175,6 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static struct mptcp_subflow_context * -mp_fail_response_expect_subflow(struct mptcp_sock *msk) -{ - struct mptcp_subflow_context *subflow, *ret = NULL; - - mptcp_for_each_subflow(msk, subflow) { - if (READ_ONCE(subflow->mp_fail_response_expect)) { - ret = subflow; - break; - } - } - - return ret; -} - static void mptcp_timeout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2346,6 +2331,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ + if (ssk->sk_state == TCP_LISTEN) { + tcp_set_state(ssk, TCP_CLOSE); + mptcp_subflow_queue_clean(ssk); + inet_csk_listen_stop(ssk); + } __tcp_close(ssk, 0); /* close acquired an extra ref */ @@ -2518,27 +2508,50 @@ reset_timer: mptcp_reset_timer(sk); } +/* schedule the timeout timer for the relevant event: either close timeout + * or mp_fail timeout. The close timeout takes precedence on the mp_fail one + */ +void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +{ + struct sock *sk = (struct sock *)msk; + unsigned long timeout, close_timeout; + + if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + return; + + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + + /* the close timeout takes precedence on the fail one, and here at least one of + * them is active + */ + timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + + sk_reset_timer(sk, &sk->sk_timer, timeout); +} + static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) { - struct mptcp_subflow_context *subflow; - struct sock *ssk; + struct sock *ssk = msk->first; bool slow; - subflow = mp_fail_response_expect_subflow(msk); - if (subflow) { - pr_debug("MP_FAIL doesn't respond, reset the subflow"); + if (!ssk) + return; - ssk = mptcp_subflow_tcp_sock(subflow); - slow = lock_sock_fast(ssk); - mptcp_subflow_reset(ssk); - unlock_sock_fast(ssk, slow); - } + pr_debug("MP_FAIL doesn't respond, reset the subflow"); + + slow = lock_sock_fast(ssk); + mptcp_subflow_reset(ssk); + WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); + unlock_sock_fast(ssk, slow); + + mptcp_reset_timeout(msk, 0); } static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); struct sock *sk = &msk->sk.icsk_inet.sk; + unsigned long fail_tout; int state; lock_sock(sk); @@ -2575,7 +2588,9 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); - mptcp_mp_fail_no_response(msk); + fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0; + if (fail_tout && time_after(jiffies, fail_tout)) + mptcp_mp_fail_no_response(msk); unlock: release_sock(sk); @@ -2822,6 +2837,7 @@ static void __mptcp_destroy_sock(struct sock *sk) static void mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; lock_sock(sk); @@ -2840,10 +2856,16 @@ static void mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + /* since the close timeout takes precedence on the fail one, + * cancel the latter + */ + if (ssk == msk->first) + subflow->fail_tout = 0; + sock_orphan(ssk); unlock_sock_fast(ssk, slow); } @@ -2852,13 +2874,13 @@ cleanup: sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (mptcp_sk(sk)->token) - mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); + mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN); + mptcp_reset_timeout(msk, 0); } release_sock(sk); if (do_cancel_work) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 200f89f6d62f..c14d70c036d0 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -306,6 +306,7 @@ struct mptcp_sock { u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; + struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) @@ -468,7 +469,6 @@ struct mptcp_subflow_context { local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; - bool mp_fail_response_expect; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -482,6 +482,7 @@ struct mptcp_subflow_context { u8 stale_count; long delegated_status; + unsigned long fail_tout; ); @@ -608,6 +609,7 @@ void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); void mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_subflow_queue_clean(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); @@ -662,6 +664,7 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); +void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && @@ -926,12 +929,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } -static inline void mptcp_do_fallback(struct sock *sk) +static inline void mptcp_do_fallback(struct sock *ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct mptcp_sock *msk = mptcp_sk(subflow->conn); + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = subflow->conn; + struct mptcp_sock *msk; + msk = mptcp_sk(sk); __mptcp_do_fallback(msk); + if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) { + gfp_t saved_allocation = ssk->sk_allocation; + + /* we are in a atomic (BH) scope, override ssk default for data + * fin allocation + */ + ssk->sk_allocation = GFP_ATOMIC; + ssk->sk_shutdown |= SEND_SHUTDOWN; + tcp_shutdown(ssk, SEND_SHUTDOWN); + ssk->sk_allocation = saved_allocation; + } } #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8841e8cd9ad8..63e8892ec807 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -843,7 +843,8 @@ enum mapping_status { MAPPING_INVALID, MAPPING_EMPTY, MAPPING_DATA_FIN, - MAPPING_DUMMY + MAPPING_DUMMY, + MAPPING_BAD_CSUM }; static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) @@ -958,11 +959,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - if (subflow->mp_join || subflow->valid_csum_seen) { - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); - } - return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; + return MAPPING_BAD_CSUM; } subflow->valid_csum_seen = 1; @@ -974,7 +971,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool csum_reqd = READ_ONCE(msk->csum_enabled); - struct sock *sk = (struct sock *)msk; struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; @@ -1016,9 +1012,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, pr_debug("infinite mapping received"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; - if (!sock_flag(ssk, SOCK_DEAD)) - sk_stop_timer(sk, &sk->sk_timer); - return MAPPING_INVALID; } @@ -1165,6 +1158,33 @@ static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) return !subflow->fully_established; } +static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + unsigned long fail_tout; + + /* greceful failure can happen only on the MPC subflow */ + if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) + return; + + /* since the close timeout take precedence on the fail one, + * no need to start the latter when the first is already set + */ + if (sock_flag((struct sock *)msk, SOCK_DEAD)) + return; + + /* we don't need extreme accuracy here, use a zero fail_tout as special + * value meaning no fail timeout at all; + */ + fail_tout = jiffies + TCP_RTO_MAX; + if (!fail_tout) + fail_tout = 1; + WRITE_ONCE(subflow->fail_tout, fail_tout); + tcp_send_ack(ssk); + + mptcp_reset_timeout(msk, subflow->fail_tout); +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1184,10 +1204,8 @@ static bool subflow_check_data_avail(struct sock *ssk) status = get_mapping_status(ssk, msk); trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue)); - if (unlikely(status == MAPPING_INVALID)) - goto fallback; - - if (unlikely(status == MAPPING_DUMMY)) + if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY || + status == MAPPING_BAD_CSUM)) goto fallback; if (status != MAPPING_OK) @@ -1229,22 +1247,17 @@ no_data: fallback: if (!__mptcp_check_fallback(msk)) { /* RFC 8684 section 3.7. */ - if (subflow->send_mp_fail) { + if (status == MAPPING_BAD_CSUM && + (subflow->mp_join || subflow->valid_csum_seen)) { + subflow->send_mp_fail = 1; + if (!READ_ONCE(msk->allow_infinite_fallback)) { - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; - tcp_send_active_reset(ssk, GFP_ATOMIC); - while ((skb = skb_peek(&ssk->sk_receive_queue))) - sk_eat_skb(ssk, skb); - } else if (!sock_flag(ssk, SOCK_DEAD)) { - WRITE_ONCE(subflow->mp_fail_response_expect, true); - sk_reset_timer((struct sock *)msk, - &((struct sock *)msk)->sk_timer, - jiffies + TCP_RTO_MAX); + goto reset; } - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + mptcp_subflow_fail(msk, ssk); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1252,16 +1265,20 @@ fallback: /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; + +reset: + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); tcp_send_active_reset(ssk, GFP_ATOMIC); WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); return false; } - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); } skb = skb_peek(&ssk->sk_receive_queue); @@ -1706,6 +1723,58 @@ static void subflow_state_change(struct sock *sk) } } +void mptcp_subflow_queue_clean(struct sock *listener_ssk) +{ + struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; + struct mptcp_sock *msk, *next, *head = NULL; + struct request_sock *req; + + /* build a list of all unaccepted mptcp sockets */ + spin_lock_bh(&queue->rskq_lock); + for (req = queue->rskq_accept_head; req; req = req->dl_next) { + struct mptcp_subflow_context *subflow; + struct sock *ssk = req->sk; + struct mptcp_sock *msk; + + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + /* skip if already in list */ + msk = mptcp_sk(subflow->conn); + if (msk->dl_next || msk == head) + continue; + + msk->dl_next = head; + head = msk; + } + spin_unlock_bh(&queue->rskq_lock); + if (!head) + return; + + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (msk = head; msk; msk = next) { + struct sock *sk = (struct sock *)msk; + bool slow; + + slow = lock_sock_fast_nested(sk); + next = msk->dl_next; + msk->first = NULL; + msk->dl_next = NULL; + unlock_sock_fast(sk, slow); + } + + /* we are still under the listener msk socket lock */ + lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); +} + static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index da9733da9868..817065aa2833 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -588,7 +588,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p) } static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct nlattr *nest; int n_i = 0; @@ -604,20 +605,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; + ret = 0; mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { if (IS_ERR(p)) continue; ret = tcf_idr_release_unsafe(p); - if (ret == ACT_P_DELETED) { + if (ret == ACT_P_DELETED) module_put(ops->owner); - n_i++; - } else if (ret < 0) { - mutex_unlock(&idrinfo->lock); - goto nla_put_failure; - } + else if (ret < 0) + break; + n_i++; } mutex_unlock(&idrinfo->lock); + if (ret < 0) { + if (n_i) + NL_SET_ERR_MSG(extack, "Unable to flush all TC actions"); + else + goto nla_put_failure; + } ret = nla_put_u32(skb, TCA_FCNT, n_i); if (ret) @@ -638,7 +644,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct tcf_idrinfo *idrinfo = tn->idrinfo; if (type == RTM_DELACTION) { - return tcf_del_walker(idrinfo, skb, ops); + return tcf_del_walker(idrinfo, skb, ops, extack); } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else { diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 17f8c523e33b..43509c7e90fc 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sock_init_data(sock, sk); tipc_set_sk_state(sk, TIPC_OPEN); if (tipc_sk_insert(tsk)) { + sk_free(sk); pr_warn("Socket create failed; port number exhausted\n"); return -EINVAL; } diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 9dd43d7d957b..515859a5168b 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -61,6 +61,39 @@ chk_msk_nr() __chk_nr "grep -c token:" $* } +wait_msk_nr() +{ + local condition="grep -c token:" + local expected=$1 + local timeout=20 + local msg nr + local max=0 + local i=0 + + shift 1 + msg=$* + + while [ $i -lt $timeout ]; do + nr=$(ss -inmHMN $ns | $condition) + [ $nr == $expected ] && break; + [ $nr -gt $max ] && max=$nr + i=$((i + 1)) + sleep 1 + done + + printf "%-50s" "$msg" + if [ $i -ge $timeout ]; then + echo "[ fail ] timeout while expecting $expected max $max last $nr" + ret=$test_cnt + elif [ $nr != $expected ]; then + echo "[ fail ] expected $expected found $nr" + ret=$test_cnt + else + echo "[ ok ]" + fi + test_cnt=$((test_cnt+1)) +} + chk_msk_fallback_nr() { __chk_nr "grep -c fallback" $* @@ -146,7 +179,7 @@ ip -n $ns link set dev lo up echo "a" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -l -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -l -t ${timeout_poll} -w 20 \ 0.0.0.0 >/dev/null & wait_local_port_listen $ns 10000 chk_msk_nr 0 "no msk on netns creation" @@ -155,7 +188,7 @@ chk_msk_listen 10000 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} \ + ./mptcp_connect -p 10000 -r 0 -t ${timeout_poll} -w 20 \ 127.0.0.1 >/dev/null & wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " @@ -167,13 +200,13 @@ flush_pids echo "a" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -l -s TCP -t ${timeout_poll} -w 20 \ 0.0.0.0 >/dev/null & wait_local_port_listen $ns 10001 echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} \ + ./mptcp_connect -p 10001 -r 0 -t ${timeout_poll} -w 20 \ 127.0.0.1 >/dev/null & wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" @@ -184,7 +217,7 @@ for I in `seq 1 $NR_CLIENTS`; do echo "a" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p $((I+10001)) -l -w 10 \ + ./mptcp_connect -p $((I+10001)) -l -w 20 \ -t ${timeout_poll} 0.0.0.0 >/dev/null & done wait_local_port_listen $ns $((NR_CLIENTS + 10001)) @@ -193,12 +226,11 @@ for I in `seq 1 $NR_CLIENTS`; do echo "b" | \ timeout ${timeout_test} \ ip netns exec $ns \ - ./mptcp_connect -p $((I+10001)) -w 10 \ + ./mptcp_connect -p $((I+10001)) -w 20 \ -t ${timeout_poll} 127.0.0.1 >/dev/null & done -sleep 1.5 -chk_msk_nr $((NR_CLIENTS*2)) "many msk socket present" +wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" flush_pids exit $ret diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 8628aa61b763..e2ea6c126c99 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -265,7 +265,7 @@ static void sock_test_tcpulp(int sock, int proto, unsigned int line) static int sock_listen_mptcp(const char * const listenaddr, const char * const port) { - int sock; + int sock = -1; struct addrinfo hints = { .ai_protocol = IPPROTO_TCP, .ai_socktype = SOCK_STREAM, diff --git a/tools/testing/selftests/net/mptcp/mptcp_inq.c b/tools/testing/selftests/net/mptcp/mptcp_inq.c index 29f75e2a1116..8672d898f8cd 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_inq.c +++ b/tools/testing/selftests/net/mptcp/mptcp_inq.c @@ -88,7 +88,7 @@ static void xgetaddrinfo(const char *node, const char *service, static int sock_listen_mptcp(const char * const listenaddr, const char * const port) { - int sock; + int sock = -1; struct addrinfo hints = { .ai_protocol = IPPROTO_TCP, .ai_socktype = SOCK_STREAM, diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index ac9a4d9c1764..ae61f39556ca 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -136,7 +136,7 @@ static void xgetaddrinfo(const char *node, const char *service, static int sock_listen_mptcp(const char * const listenaddr, const char * const port) { - int sock; + int sock = -1; struct addrinfo hints = { .ai_protocol = IPPROTO_TCP, .ai_socktype = SOCK_STREAM, diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json index b24494c6f546..c652e8c1157d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/gact.json @@ -609,5 +609,82 @@ "teardown": [ "$TC actions flush action gact" ] + }, + { + "id": "7f52", + "name": "Try to flush action which is referenced by filter", + "category": [ + "actions", + "gact" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress", + "$TC actions add action pass index 1", + "$TC filter add dev $DEV1 protocol all ingress prio 1 handle 0x1234 matchall action gact index 1" + ], + "cmdUnderTest": "$TC actions flush action gact", + "expExitCode": "1", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "total acts 1.*action order [0-9]*: gact action pass.*index 1 ref 2 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + [ + "sleep 1; $TC actions flush action gact", + 0, + 1 + ] + ] + }, + { + "id": "ae1e", + "name": "Try to flush actions when last one is referenced by filter", + "category": [ + "actions", + "gact" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + [ + "$TC actions flush action gact", + 0, + 1, + 255 + ], + "$TC qdisc add dev $DEV1 ingress", + [ + "$TC actions add action pass index 1", + 0, + 1, + 255 + ], + "$TC actions add action reclassify index 2", + "$TC actions add action drop index 3", + "$TC filter add dev $DEV1 protocol all ingress prio 1 handle 0x1234 matchall action gact index 3" + ], + "cmdUnderTest": "$TC actions flush action gact", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action gact", + "matchPattern": "total acts 1.*action order [0-9]*: gact action drop.*index 3 ref 2 bind 1", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV1 ingress", + [ + "sleep 1; $TC actions flush action gact", + 0, + 1 + ] + ] } ] |