diff options
author | Jakub Kicinski <kuba@kernel.org> | 2020-12-11 20:12:36 -0800 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2020-12-11 22:29:38 -0800 |
commit | 46d5e62dd3c34770f3bfd0642daa9a7772a00362 (patch) | |
tree | 72f00a33d177cae0c8c9d7337ced3a6c6bbad45d /net | |
parent | 91163f82143630a9629a8bf0227d49173697c69c (diff) | |
parent | 7f376f1917d7461e05b648983e8d2aea9d0712b2 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
xdp_return_frame_bulk() needs to pass a xdp_buff
to __xdp_return().
strlcpy got converted to strscpy but here it makes no
functional difference, so just keep the right code.
Conflicts:
net/netfilter/nf_tables_api.c
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net')
37 files changed, 197 insertions, 131 deletions
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index adb674a860d3..3f2f06b4dd27 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -173,6 +173,9 @@ static int br_dev_open(struct net_device *dev) br_stp_enable_bridge(br); br_multicast_open(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + return 0; } @@ -193,6 +196,9 @@ static int br_dev_stop(struct net_device *dev) br_stp_disable_bridge(br); br_multicast_stop(br); + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_leave_snoopers(br); + netif_stop_queue(dev); return 0; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 484820c223a3..257ac4e25f6d 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -3291,7 +3291,7 @@ static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) } #endif -static void br_multicast_join_snoopers(struct net_bridge *br) +void br_multicast_join_snoopers(struct net_bridge *br) { br_ip4_multicast_join_snoopers(br); br_ip6_multicast_join_snoopers(br); @@ -3322,7 +3322,7 @@ static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) } #endif -static void br_multicast_leave_snoopers(struct net_bridge *br) +void br_multicast_leave_snoopers(struct net_bridge *br) { br_ip4_multicast_leave_snoopers(br); br_ip6_multicast_leave_snoopers(br); @@ -3341,9 +3341,6 @@ static void __br_multicast_open(struct net_bridge *br, void br_multicast_open(struct net_bridge *br) { - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_join_snoopers(br); - __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); @@ -3359,9 +3356,6 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif - - if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) - br_multicast_leave_snoopers(br); } void br_multicast_dev_del(struct net_bridge *br) @@ -3492,6 +3486,7 @@ static void br_multicast_start_querier(struct net_bridge *br, int br_multicast_toggle(struct net_bridge *br, unsigned long val) { struct net_bridge_port *port; + bool change_snoopers = false; spin_lock_bh(&br->multicast_lock); if (!!br_opt_get(br, BROPT_MULTICAST_ENABLED) == !!val) @@ -3500,7 +3495,7 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) br_mc_disabled_update(br->dev, val); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { - br_multicast_leave_snoopers(br); + change_snoopers = true; goto unlock; } @@ -3511,9 +3506,30 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) list_for_each_entry(port, &br->port_list, list) __br_multicast_enable_port(port); + change_snoopers = true; + unlock: spin_unlock_bh(&br->multicast_lock); + /* br_multicast_join_snoopers has the potential to cause + * an MLD Report/Leave to be delivered to br_multicast_rcv, + * which would in turn call br_multicast_add_group, which would + * attempt to acquire multicast_lock. This function should be + * called after the lock has been released to avoid deadlocks on + * multicast_lock. + * + * br_multicast_leave_snoopers does not have the problem since + * br_multicast_rcv first checks BROPT_MULTICAST_ENABLED, and + * returns without calling br_multicast_ipv4/6_rcv if it's not + * enabled. Moved both functions out just for symmetry. + */ + if (change_snoopers) { + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + else + br_multicast_leave_snoopers(br); + } + return 0; } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index d538ccec0acd..d62c6e1af64a 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -797,6 +797,8 @@ void br_multicast_del_port(struct net_bridge_port *port); void br_multicast_enable_port(struct net_bridge_port *port); void br_multicast_disable_port(struct net_bridge_port *port); void br_multicast_init(struct net_bridge *br); +void br_multicast_join_snoopers(struct net_bridge *br); +void br_multicast_leave_snoopers(struct net_bridge *br); void br_multicast_open(struct net_bridge *br); void br_multicast_stop(struct net_bridge *br); void br_multicast_dev_del(struct net_bridge *br); @@ -980,6 +982,14 @@ static inline void br_multicast_init(struct net_bridge *br) { } +static inline void br_multicast_join_snoopers(struct net_bridge *br) +{ +} + +static inline void br_multicast_leave_snoopers(struct net_bridge *br) +{ +} + static inline void br_multicast_open(struct net_bridge *br) { } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index d07008678d32..701cad646b20 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -266,8 +266,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, } masterv = br_vlan_get_master(br, v->vid, extack); - if (!masterv) + if (!masterv) { + err = -ENOMEM; goto out_filt; + } v->brvlan = masterv; if (br_opt_get(br, BROPT_VLAN_STATS_PER_PORT)) { v->stats = diff --git a/net/can/isotp.c b/net/can/isotp.c index 09f781b63d66..7839c3b9e5be 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1173,6 +1173,9 @@ static int isotp_setsockopt(struct socket *sock, int level, int optname, if (level != SOL_CAN_ISOTP) return -EINVAL; + if (so->bound) + return -EISCONN; + switch (optname) { case CAN_ISOTP_OPTS: if (optlen != sizeof(struct can_isotp_options)) diff --git a/net/core/dev.c b/net/core/dev.c index ce8fea2e2788..bde98cfd166f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -8958,6 +8958,17 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev, return dev->xdp_state[mode].prog; } +static u8 dev_xdp_prog_count(struct net_device *dev) +{ + u8 count = 0; + int i; + + for (i = 0; i < __MAX_XDP_MODE; i++) + if (dev->xdp_state[i].prog || dev->xdp_state[i].link) + count++; + return count; +} + u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode) { struct bpf_prog *prog = dev_xdp_prog(dev, mode); @@ -9048,6 +9059,7 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack struct bpf_xdp_link *link, struct bpf_prog *new_prog, struct bpf_prog *old_prog, u32 flags) { + unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES); struct bpf_prog *cur_prog; enum bpf_xdp_mode mode; bpf_op_t bpf_op; @@ -9063,11 +9075,17 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack NL_SET_ERR_MSG(extack, "Invalid XDP flags for BPF link attachment"); return -EINVAL; } - /* just one XDP mode bit should be set, zero defaults to SKB mode */ - if (hweight32(flags & XDP_FLAGS_MODES) > 1) { + /* just one XDP mode bit should be set, zero defaults to drv/skb mode */ + if (num_modes > 1) { NL_SET_ERR_MSG(extack, "Only one XDP mode flag can be set"); return -EINVAL; } + /* avoid ambiguity if offload + drv/skb mode progs are both loaded */ + if (!num_modes && dev_xdp_prog_count(dev) > 1) { + NL_SET_ERR_MSG(extack, + "More than one program loaded, unset mode is ambiguous"); + return -EINVAL; + } /* old_prog != NULL implies XDP_FLAGS_REPLACE is set */ if (old_prog && !(flags & XDP_FLAGS_REPLACE)) { NL_SET_ERR_MSG(extack, "XDP_FLAGS_REPLACE is not specified"); diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c index d4474c812b64..715b67f6c62f 100644 --- a/net/core/flow_offload.c +++ b/net/core/flow_offload.c @@ -381,10 +381,8 @@ static void __flow_block_indr_cleanup(void (*release)(void *cb_priv), list_for_each_entry_safe(this, next, &flow_block_indr_list, indr.list) { if (this->release == release && - this->indr.cb_priv == cb_priv) { + this->indr.cb_priv == cb_priv) list_move(&this->indr.list, cleanup_list); - return; - } } } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index 7d3438215f32..2f7940bcf715 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -39,12 +39,11 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, { int ret; - /* Preempt disable is needed to protect per-cpu redirect_info between - * BPF prog and skb_do_redirect(). The call_rcu in bpf_prog_put() and - * access to maps strictly require a rcu_read_lock() for protection, - * mixing with BH RCU lock doesn't work. + /* Migration disable and BH disable are needed to protect per-cpu + * redirect_info between BPF prog and skb_do_redirect(). */ - preempt_disable(); + migrate_disable(); + local_bh_disable(); bpf_compute_data_pointers(skb); ret = bpf_prog_run_save_cb(lwt->prog, skb); @@ -78,7 +77,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt, break; } - preempt_enable(); + local_bh_enable(); + migrate_enable(); return ret; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 17ffd33c6b18..3a8c9ab4ecbe 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -336,11 +336,10 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling - * of xdp_frames/pages in those cases. This path is never used by the - * MEM_TYPE_XSK_BUFF_POOL memory type, so it's explicitly not part of - * the switch-statement. + * of xdp_frames/pages in those cases. */ -static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) +static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, + struct xdp_buff *xdp) { struct xdp_mem_allocator *xa; struct page *page; @@ -362,6 +361,10 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; + case MEM_TYPE_XSK_BUFF_POOL: + /* NB! Only valid from an xdp_buff! */ + xsk_buff_free(xdp); + break; default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ WARN(1, "Incorrect XDP memory type (%d) usage", mem->type); @@ -371,13 +374,13 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct) void xdp_return_frame(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, false); + __xdp_return(xdpf->data, &xdpf->mem, false, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { - __xdp_return(xdpf->data, &xdpf->mem, true); + __xdp_return(xdpf->data, &xdpf->mem, true, NULL); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); @@ -412,7 +415,7 @@ void xdp_return_frame_bulk(struct xdp_frame *xdpf, struct xdp_mem_allocator *xa; if (mem->type != MEM_TYPE_PAGE_POOL) { - __xdp_return(xdpf->data, &xdpf->mem, false); + __xdp_return(xdpf->data, &xdpf->mem, false, NULL); return; } @@ -437,7 +440,7 @@ EXPORT_SYMBOL_GPL(xdp_return_frame_bulk); void xdp_return_buff(struct xdp_buff *xdp) { - __xdp_return(xdp->data, &xdp->rxq->mem, true); + __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp); } /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ @@ -455,18 +458,6 @@ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) } EXPORT_SYMBOL_GPL(__xdp_release_frame); -bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, - struct netdev_bpf *bpf) -{ - if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { - NL_SET_ERR_MSG(bpf->extack, - "program loaded with different flags"); - return false; - } - return true; -} -EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); - void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { diff --git a/net/ethtool/bitset.c b/net/ethtool/bitset.c index 1fb3603d92ad..0515d6604b3b 100644 --- a/net/ethtool/bitset.c +++ b/net/ethtool/bitset.c @@ -628,6 +628,8 @@ int ethnl_parse_bitset(unsigned long *val, unsigned long *mask, return ret; change_bits = nla_get_u32(tb[ETHTOOL_A_BITSET_SIZE]); + if (change_bits > nbits) + change_bits = nbits; bitmap_from_arr32(val, nla_data(tb[ETHTOOL_A_BITSET_VALUE]), change_bits); if (change_bits < nbits) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b87140a1fa28..cdf6ec5aa45d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, if (has_gw && has_via) { NL_SET_ERR_MSG(extack, "Nexthop configuration can not contain both GATEWAY and VIA"); - goto errout; + return -EINVAL; } return 0; diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d1e04d2b5170..563b62b76a5f 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -203,7 +203,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; @@ -649,7 +649,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change * (other than comefrom, which userspace doesn't care @@ -673,7 +673,7 @@ static int copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct arpt_entry *e; struct xt_counters *counters; - struct xt_table_info *private = table->private; + struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; void *loc_cpu_entry; @@ -807,7 +807,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, NFPROTO_ARP, name); if (!IS_ERR(t)) { struct arpt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -860,7 +860,7 @@ static int get_entries(struct net *net, struct arpt_get_entries __user *uptr, t = xt_find_table_lock(net, NFPROTO_ARP, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, @@ -1017,7 +1017,7 @@ static int do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1330,7 +1330,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index f15bc21d7301..6e2851f8d3a3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -258,7 +258,7 @@ ipt_do_table(struct sk_buff *skb, WARN_ON(!(table->valid_hooks & (1 << hook))); local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; @@ -791,7 +791,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -815,7 +815,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ipt_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -964,7 +964,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET, name); if (!IS_ERR(t)) { struct ipt_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1018,7 +1018,7 @@ get_entries(struct net *net, struct ipt_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET, get.name); if (!IS_ERR(t)) { - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1173,7 +1173,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1543,7 +1543,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9e8a6c1aa019..d6ad3b5c38e7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -510,7 +510,6 @@ static void tcp_init_buffer_space(struct sock *sk) if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) tcp_sndbuf_expand(sk); - tp->rcvq_space.space = min_t(u32, tp->rcv_wnd, TCP_INIT_CWND * tp->advmss); tcp_mstamp_refresh(tp); tp->rcvq_space.time = tp->tcp_mstamp; tp->rcvq_space.seq = tp->copied_seq; @@ -534,6 +533,8 @@ static void tcp_init_buffer_space(struct sock *sk) tp->rcv_ssthresh = min(tp->rcv_ssthresh, tp->window_clamp); tp->snd_cwnd_stamp = tcp_jiffies32; + tp->rcvq_space.space = min3(tp->rcv_ssthresh, tp->rcv_wnd, + (u32)TCP_INIT_CWND * tp->advmss); } /* 4. Recalculate window clamp after socket hit its memory bounds. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index af2338294598..58207c7769d0 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -984,7 +984,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (inet_sk(sk)->tos & INET_ECN_MASK) : inet_sk(sk)->tos; if (!INET_ECN_is_capable(tos) && @@ -1546,7 +1547,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 41880d3521ed..f322e798a351 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1882,7 +1882,8 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) * window, and remember whether we were cwnd-limited then. */ if (!before(tp->snd_una, tp->max_packets_seq) || - tp->packets_out > tp->max_packets_out) { + tp->packets_out > tp->max_packets_out || + is_cwnd_limited) { tp->max_packets_out = tp->packets_out; tp->max_packets_seq = tp->snd_nxt; tp->is_cwnd_limited = is_cwnd_limited; @@ -2706,6 +2707,10 @@ repair: else tcp_chrono_stop(sk, TCP_CHRONO_RWND_LIMITED); + is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); + if (likely(sent_pkts || is_cwnd_limited)) + tcp_cwnd_validate(sk, is_cwnd_limited); + if (likely(sent_pkts)) { if (tcp_in_cwnd_reduction(sk)) tp->prr_out += sent_pkts; @@ -2713,8 +2718,6 @@ repair: /* Send one loss probe per tail loss episode. */ if (push_one != 2) tcp_schedule_loss_probe(sk, false); - is_cwnd_limited |= (tcp_packets_in_flight(tp) >= tp->snd_cwnd); - tcp_cwnd_validate(sk, is_cwnd_limited); return false; } return !tp->packets_out && !tcp_write_queue_empty(sk); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index a3f105227ccc..dece195f212c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2175,7 +2175,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) - ip_protocol_deliver_rcu(dev_net(skb->dev), skb, -ret); + ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 2e2119bfcf13..c4f532f4d311 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -280,7 +280,7 @@ ip6t_do_table(struct sk_buff *skb, local_bh_disable(); addend = xt_write_recseq_begin(); - private = READ_ONCE(table->private); /* Address dependency. */ + private = rcu_access_pointer(table->private); cpu = smp_processor_id(); table_base = private->entries; jumpstack = (struct ip6t_entry **)private->jumpstack[cpu]; @@ -807,7 +807,7 @@ static struct xt_counters *alloc_counters(const struct xt_table *table) { unsigned int countersize; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); /* We need atomic snapshot of counters: rest doesn't change (other than comefrom, which userspace doesn't care @@ -831,7 +831,7 @@ copy_entries_to_user(unsigned int total_size, unsigned int off, num; const struct ip6t_entry *e; struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); int ret = 0; const void *loc_cpu_entry; @@ -980,7 +980,7 @@ static int get_info(struct net *net, void __user *user, const int *len) t = xt_request_find_table_lock(net, AF_INET6, name); if (!IS_ERR(t)) { struct ip6t_getinfo info; - const struct xt_table_info *private = t->private; + const struct xt_table_info *private = xt_table_get_private_protected(t); #ifdef CONFIG_COMPAT struct xt_table_info tmp; @@ -1035,7 +1035,7 @@ get_entries(struct net *net, struct ip6t_get_entries __user *uptr, t = xt_find_table_lock(net, AF_INET6, get.name); if (!IS_ERR(t)) { - struct xt_table_info *private = t->private; + struct xt_table_info *private = xt_table_get_private_protected(t); if (get.size == private->size) ret = copy_entries_to_user(private->size, t, uptr->entrytable); @@ -1189,7 +1189,7 @@ do_add_counters(struct net *net, sockptr_t arg, unsigned int len) } local_bh_disable(); - private = t->private; + private = xt_table_get_private_protected(t); if (private->number != tmp.num_counters) { ret = -EINVAL; goto unlock_up_free; @@ -1552,7 +1552,7 @@ compat_copy_entries_to_user(unsigned int total_size, struct xt_table *table, void __user *userptr) { struct xt_counters *counters; - const struct xt_table_info *private = table->private; + const struct xt_table_info *private = xt_table_get_private_protected(table); void __user *pos; unsigned int size; int ret = 0; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 1a1510513739..e254569a3005 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -528,7 +528,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? - tcp_rsk(req)->syn_tos & ~INET_ECN_MASK : + (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | + (np->tclass & INET_ECN_MASK) : np->tclass; if (!INET_ECN_is_capable(tclass) && @@ -1325,7 +1326,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * if (np->repflow) newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb)); - /* Set ToS of the new socket based upon the value of incoming SYN. */ + /* Set ToS of the new socket based upon the value of incoming SYN. + * ECT bits are set later in tcp_init_transfer(). + */ if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index f5d4ceb72882..3b9ec4ef81c3 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -940,6 +940,8 @@ int ieee80211_add_virtual_monitor(struct ieee80211_local *local) return ret; } + set_bit(SDATA_STATE_RUNNING, &sdata->state); + ret = ieee80211_check_queues(sdata, NL80211_IFTYPE_MONITOR); if (ret) { kfree(sdata); diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 48f31ac9233c..620ecf922408 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -60,6 +60,7 @@ static struct mesh_table *mesh_table_alloc(void) atomic_set(&newtbl->entries, 0); spin_lock_init(&newtbl->gates_lock); spin_lock_init(&newtbl->walk_lock); + rhashtable_init(&newtbl->rhead, &mesh_rht_params); return newtbl; } @@ -773,9 +774,6 @@ int mesh_pathtbl_init(struct ieee80211_sub_if_data *sdata) goto free_path; } - rhashtable_init(&tbl_path->rhead, &mesh_rht_params); - rhashtable_init(&tbl_mpp->rhead, &mesh_rht_params); - sdata->u.mesh.mesh_paths = tbl_path; sdata->u.mesh.mpp_paths = tbl_mpp; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 8c3c01a1b923..6a59a56f0daa 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -3456,7 +3456,7 @@ bool ieee80211_chandef_he_6ghz_oper(struct ieee80211_sub_if_data *sdata, *chandef = he_chandef; - return false; + return true; } bool ieee80211_chandef_s1g_oper(const struct ieee80211_s1g_oper_ie *oper, diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 84d119436b22..b921cbdd9aaa 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -67,6 +67,7 @@ void mptcp_seq_show(struct seq_file *seq) for (i = 0; mptcp_snmp_list[i].name; i++) seq_puts(seq, " 0"); + seq_putc(seq, '\n'); return; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index a11bc8dcaa82..9d6c317878ff 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -1724,6 +1724,10 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, } nla_strscpy(ifname, attr, IFNAMSIZ); + /* nf_tables_netdev_event() is called under rtnl_mutex, this is + * indirectly serializing all the other holders of the commit_mutex with + * the rtnl_mutex. + */ dev = __dev_get_by_name(net, ifname); if (!dev) { err = -ENOENT; @@ -3720,7 +3724,7 @@ cont: return 0; } -static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) { u64 ms = be64_to_cpu(nla_get_be64(nla)); u64 max = (u64)(~((u64)0)); @@ -3734,7 +3738,7 @@ static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) return 0; } -static __be64 nf_jiffies64_to_msecs(u64 input) +__be64 nf_jiffies64_to_msecs(u64 input) { return cpu_to_be64(jiffies64_to_msecs(input)); } diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index a8c4d442231c..8bcd49f14797 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -177,8 +177,6 @@ static void nft_ct_get_eval(const struct nft_expr *expr, } #endif case NFT_CT_ID: - if (!nf_ct_is_confirmed(ct)) - goto err; *dest = nf_ct_get_id(ct); return; default: diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 64ca13a1885b..9af4f93c7f0e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -157,8 +157,10 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (tb[NFTA_DYNSET_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - tb[NFTA_DYNSET_TIMEOUT]))); + + err = nf_msecs_to_jiffies64(tb[NFTA_DYNSET_TIMEOUT], &timeout); + if (err) + return err; } priv->sreg_key = nft_parse_register(tb[NFTA_DYNSET_SREG_KEY]); @@ -267,7 +269,7 @@ static int nft_dynset_dump(struct sk_buff *skb, const struct nft_expr *expr) if (nla_put_string(skb, NFTA_DYNSET_SET_NAME, priv->set->name)) goto nla_put_failure; if (nla_put_be64(skb, NFTA_DYNSET_TIMEOUT, - cpu_to_be64(jiffies_to_msecs(priv->timeout)), + nf_jiffies64_to_msecs(priv->timeout), NFTA_DYNSET_PAD)) goto nla_put_failure; if (priv->expr && nft_expr_dump(skb, NFTA_DYNSET_EXPR, priv->expr)) diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index af22dbe85e2c..acce622582e3 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1349,6 +1349,14 @@ struct xt_counters *xt_counters_alloc(unsigned int counters) } EXPORT_SYMBOL(xt_counters_alloc); +struct xt_table_info +*xt_table_get_private_protected(const struct xt_table *table) +{ + return rcu_dereference_protected(table->private, + mutex_is_locked(&xt[table->af].mutex)); +} +EXPORT_SYMBOL(xt_table_get_private_protected); + struct xt_table_info * xt_replace_table(struct xt_table *table, unsigned int num_counters, @@ -1356,7 +1364,6 @@ xt_replace_table(struct xt_table *table, int *error) { struct xt_table_info *private; - unsigned int cpu; int ret; ret = xt_jumpstack_alloc(newinfo); @@ -1366,47 +1373,20 @@ xt_replace_table(struct xt_table *table, } /* Do the substitution. */ - local_bh_disable(); - private = table->private; + private = xt_table_get_private_protected(table); /* Check inside lock: is the old number correct? */ if (num_counters != private->number) { pr_debug("num_counters != table->private->number (%u/%u)\n", num_counters, private->number); - local_bh_enable(); *error = -EAGAIN; return NULL; } newinfo->initial_entries = private->initial_entries; - /* - * Ensure contents of newinfo are visible before assigning to - * private. - */ - smp_wmb(); - table->private = newinfo; - - /* make sure all cpus see new ->private value */ - smp_wmb(); - /* - * Even though table entries have now been swapped, other CPU's - * may still be using the old entries... - */ - local_bh_enable(); - - /* ... so wait for even xt_recseq on all cpus */ - for_each_possible_cpu(cpu) { - seqcount_t *s = &per_cpu(xt_recseq, cpu); - u32 seq = raw_read_seqcount(s); - - if (seq & 1) { - do { - cond_resched(); - cpu_relax(); - } while (seq == raw_read_seqcount(s)); - } - } + rcu_assign_pointer(table->private, newinfo); + synchronize_rcu(); audit_log_nfcfg(table->name, table->af, private->number, !private->number ? AUDIT_XT_OP_REGISTER : @@ -1442,12 +1422,12 @@ struct xt_table *xt_register_table(struct net *net, } /* Simplifies replace_table code. */ - table->private = bootstrap; + rcu_assign_pointer(table->private, bootstrap); if (!xt_replace_table(table, 0, newinfo, &ret)) goto unlock; - private = table->private; + private = xt_table_get_private_protected(table); pr_debug("table->private->number = %u\n", private->number); /* save number of initial entries */ @@ -1470,7 +1450,8 @@ void *xt_unregister_table(struct xt_table *table) struct xt_table_info *private; mutex_lock(&xt[table->af].mutex); - private = table->private; + private = xt_table_get_private_protected(table); + RCU_INIT_POINTER(table->private, NULL); list_del(&table->list); mutex_unlock(&xt[table->af].mutex); audit_log_nfcfg(table->name, table->af, private->number, diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index ec0689ddc635..4c5c2331e764 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -2531,7 +2531,7 @@ static int validate_and_copy_dec_ttl(struct net *net, action_start = add_nested_action_start(sfa, OVS_DEC_TTL_ATTR_ACTION, log); if (action_start < 0) - return start; + return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, vlan_tci, mpls_label_count, log); diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index fed18fd2c50b..1319986693fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2424,8 +2424,8 @@ static int fl_dump_key_mpls_opt_lse(struct sk_buff *skb, return err; } if (lse_mask->mpls_label) { - err = nla_put_u8(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, - lse_key->mpls_label); + err = nla_put_u32(skb, TCA_FLOWER_KEY_MPLS_OPT_LSE_LABEL, + lse_key->mpls_label); if (err) return err; } diff --git a/net/sched/sch_fq_pie.c b/net/sched/sch_fq_pie.c index 4dda15588cf4..949163fe68af 100644 --- a/net/sched/sch_fq_pie.c +++ b/net/sched/sch_fq_pie.c @@ -401,6 +401,7 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, INIT_LIST_HEAD(&q->new_flows); INIT_LIST_HEAD(&q->old_flows); + timer_setup(&q->adapt_timer, fq_pie_timer, 0); if (opt) { err = fq_pie_change(sch, opt, extack); @@ -426,7 +427,6 @@ static int fq_pie_init(struct Qdisc *sch, struct nlattr *opt, pie_vars_init(&flow->vars); } - timer_setup(&q->adapt_timer, fq_pie_timer, 0); mod_timer(&q->adapt_timer, jiffies + HZ / 2); return 0; diff --git a/net/tipc/node.c b/net/tipc/node.c index 86b4d7ffb47a..83d9eb830592 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2206,9 +2206,11 @@ void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, &xmitq); else if (prop == TIPC_NLA_PROP_MTU) tipc_link_set_mtu(e->link, b->mtu); + + /* Update MTU for node link entry */ + e->mtu = tipc_link_mss(e->link); } - /* Update MTU for node link entry */ - e->mtu = tipc_link_mss(e->link); + tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr, NULL); } diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 8811a4b69f21..cf37cea1ff42 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -12644,7 +12644,7 @@ static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) struct net_device *dev = info->user_ptr[1]; struct wireless_dev *wdev = dev->ieee80211_ptr; struct nlattr *tb[NUM_NL80211_REKEY_DATA]; - struct cfg80211_gtk_rekey_data rekey_data; + struct cfg80211_gtk_rekey_data rekey_data = {}; int err; if (!info->attrs[NL80211_ATTR_REKEY_DATA]) diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 56c46e5f57bc..310cfc68875a 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -212,6 +212,14 @@ static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len, return 0; } +static bool xsk_tx_writeable(struct xdp_sock *xs) +{ + if (xskq_cons_present_entries(xs->tx) > xs->tx->nentries / 2) + return false; + + return true; +} + static bool xsk_is_bound(struct xdp_sock *xs) { if (READ_ONCE(xs->state) == XSK_BOUND) { @@ -298,7 +306,8 @@ void xsk_tx_release(struct xsk_buff_pool *pool) rcu_read_lock(); list_for_each_entry_rcu(xs, &pool->xsk_tx_list, tx_list) { __xskq_cons_release(xs->tx); - xs->sk.sk_write_space(&xs->sk); + if (xsk_tx_writeable(xs)) + xs->sk.sk_write_space(&xs->sk); } rcu_read_unlock(); } @@ -495,7 +504,8 @@ static int xsk_generic_xmit(struct sock *sk) out: if (sent_frame) - sk->sk_write_space(sk); + if (xsk_tx_writeable(xs)) + sk->sk_write_space(sk); mutex_unlock(&xs->mutex); return err; @@ -577,11 +587,13 @@ static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int fl static __poll_t xsk_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait) { - __poll_t mask = datagram_poll(file, sock, wait); + __poll_t mask = 0; struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct xsk_buff_pool *pool; + sock_poll_wait(file, sock, wait); + if (unlikely(!xsk_is_bound(xs))) return mask; @@ -597,7 +609,7 @@ static __poll_t xsk_poll(struct file *file, struct socket *sock, if (xs->rx && !xskq_prod_is_empty(xs->rx)) mask |= EPOLLIN | EPOLLRDNORM; - if (xs->tx && !xskq_cons_is_full(xs->tx)) + if (xs->tx && xsk_tx_writeable(xs)) mask |= EPOLLOUT | EPOLLWRNORM; return mask; diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 556d82d03687..67a4494d63b6 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -174,6 +174,7 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool, if (!pool->dma_pages) { WARN(1, "Driver did not DMA map zero-copy buffers"); + err = -EINVAL; goto err_unreg_xsk; } pool->umem->zc = true; diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index b936c46b1e16..4a9663aa7afe 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -307,6 +307,12 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q) q->nentries; } +static inline u32 xskq_cons_present_entries(struct xsk_queue *q) +{ + /* No barriers needed since data is not accessed */ + return READ_ONCE(q->ring->producer) - READ_ONCE(q->ring->consumer); +} + /* Functions for producers */ static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) diff --git a/net/xfrm/xfrm_compat.c b/net/xfrm/xfrm_compat.c index e28f0c9ecd6a..d8e8a11ca845 100644 --- a/net/xfrm/xfrm_compat.c +++ b/net/xfrm/xfrm_compat.c @@ -234,6 +234,7 @@ static int xfrm_xlate64_attr(struct sk_buff *dst, const struct nlattr *src) case XFRMA_PAD: /* Ignore */ return 0; + case XFRMA_UNSPEC: case XFRMA_ALG_AUTH: case XFRMA_ALG_CRYPT: case XFRMA_ALG_COMP: @@ -387,7 +388,7 @@ static int xfrm_attr_cpy32(void *dst, size_t *pos, const struct nlattr *src, memcpy(nla, src, nla_attr_size(copy_len)); nla->nla_len = nla_attr_size(payload); - *pos += nla_attr_size(payload); + *pos += nla_attr_size(copy_len); nlmsg->nlmsg_len += nla->nla_len; memset(dst + *pos, 0, payload - copy_len); @@ -563,7 +564,7 @@ static struct nlmsghdr *xfrm_user_rcv_msg_compat(const struct nlmsghdr *h32, return NULL; len += NLMSG_HDRLEN; - h64 = kvmalloc(len, GFP_KERNEL | __GFP_ZERO); + h64 = kvmalloc(len, GFP_KERNEL); if (!h64) return ERR_PTR(-ENOMEM); diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index a77da7aae6fe..2f1517827995 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2382,8 +2382,10 @@ int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) if (in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); - if (!xtr) + if (!xtr) { + kfree(data); return -EOPNOTSUPP; + } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); |