diff options
Diffstat (limited to 'net')
129 files changed, 1716 insertions, 1010 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 73a65789271b..8ccee3d01822 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -693,7 +693,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/9p/client.c b/net/9p/client.c index 18c5271910dc..5c1343195292 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -225,7 +225,8 @@ static int parse_opts(char *opts, struct p9_client *clnt) } free_and_return: - v9fs_put_trans(clnt->trans_mod); + if (ret) + v9fs_put_trans(clnt->trans_mod); kfree(tmp_options); return ret; } diff --git a/net/Makefile b/net/Makefile index 13ec0d5415c7..bdaf53925acd 100644 --- a/net/Makefile +++ b/net/Makefile @@ -20,11 +20,7 @@ obj-$(CONFIG_TLS) += tls/ obj-$(CONFIG_XFRM) += xfrm/ obj-$(CONFIG_UNIX) += unix/ obj-$(CONFIG_NET) += ipv6/ -ifneq ($(CC_CAN_LINK),y) -$(warning CC cannot link executables. Skipping bpfilter.) -else obj-$(CONFIG_BPFILTER) += bpfilter/ -endif obj-$(CONFIG_PACKET) += packet/ obj-$(CONFIG_NET_KEY) += key/ obj-$(CONFIG_BRIDGE) += bridge/ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index be09a9883825..73bf6a93a3cf 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -2732,7 +2732,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -2780,6 +2780,8 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index ec93337ee259..6baec4e68898 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -927,7 +927,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, { struct batadv_neigh_ifinfo *router_ifinfo = NULL; struct batadv_neigh_node *router; - struct batadv_gw_node *curr_gw; + struct batadv_gw_node *curr_gw = NULL; int ret = 0; void *hdr; @@ -995,6 +995,8 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid, u32 seq, ret = 0; out: + if (curr_gw) + batadv_gw_node_put(curr_gw); if (router_ifinfo) batadv_neigh_ifinfo_put(router_ifinfo); if (router) diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 4229b01ac7b5..87479c60670e 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -19,6 +19,7 @@ #include "debugfs.h" #include "main.h" +#include <linux/dcache.h> #include <linux/debugfs.h> #include <linux/err.h> #include <linux/errno.h> @@ -344,6 +345,25 @@ out: } /** + * batadv_debugfs_rename_hardif() - Fix debugfs path for renamed hardif + * @hard_iface: hard interface which was renamed + */ +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ + const char *name = hard_iface->net_dev->name; + struct dentry *dir; + struct dentry *d; + + dir = hard_iface->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_hardif() - delete the base directory for a hard interface * in debugfs. * @hard_iface: hard interface which is deleted. @@ -414,6 +434,26 @@ out: } /** + * batadv_debugfs_rename_meshif() - Fix debugfs path for renamed softif + * @dev: net_device which was renamed + */ +void batadv_debugfs_rename_meshif(struct net_device *dev) +{ + struct batadv_priv *bat_priv = netdev_priv(dev); + const char *name = dev->name; + struct dentry *dir; + struct dentry *d; + + dir = bat_priv->debug_dir; + if (!dir) + return; + + d = debugfs_rename(dir->d_parent, dir, dir->d_parent, name); + if (!d) + pr_err("Can't rename debugfs dir to %s\n", name); +} + +/** * batadv_debugfs_del_meshif() - Remove interface dependent debugfs entries * @dev: netdev struct of the soft interface */ diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 37b069698b04..08a592ffbee5 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -30,8 +30,10 @@ struct net_device; void batadv_debugfs_init(void); void batadv_debugfs_destroy(void); int batadv_debugfs_add_meshif(struct net_device *dev); +void batadv_debugfs_rename_meshif(struct net_device *dev); void batadv_debugfs_del_meshif(struct net_device *dev); int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface); +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface); void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface); #else @@ -49,6 +51,10 @@ static inline int batadv_debugfs_add_meshif(struct net_device *dev) return 0; } +static inline void batadv_debugfs_rename_meshif(struct net_device *dev) +{ +} + static inline void batadv_debugfs_del_meshif(struct net_device *dev) { } @@ -60,6 +66,11 @@ int batadv_debugfs_add_hardif(struct batadv_hard_iface *hard_iface) } static inline +void batadv_debugfs_rename_hardif(struct batadv_hard_iface *hard_iface) +{ +} + +static inline void batadv_debugfs_del_hardif(struct batadv_hard_iface *hard_iface) { } diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index c405d15befd6..2f0d42f2f913 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -989,6 +989,32 @@ void batadv_hardif_remove_interfaces(void) rtnl_unlock(); } +/** + * batadv_hard_if_event_softif() - Handle events for soft interfaces + * @event: NETDEV_* event to handle + * @net_dev: net_device which generated an event + * + * Return: NOTIFY_* result + */ +static int batadv_hard_if_event_softif(unsigned long event, + struct net_device *net_dev) +{ + struct batadv_priv *bat_priv; + + switch (event) { + case NETDEV_REGISTER: + batadv_sysfs_add_meshif(net_dev); + bat_priv = netdev_priv(net_dev); + batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); + break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_meshif(net_dev); + break; + } + + return NOTIFY_DONE; +} + static int batadv_hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { @@ -997,12 +1023,8 @@ static int batadv_hard_if_event(struct notifier_block *this, struct batadv_hard_iface *primary_if = NULL; struct batadv_priv *bat_priv; - if (batadv_softif_is_valid(net_dev) && event == NETDEV_REGISTER) { - batadv_sysfs_add_meshif(net_dev); - bat_priv = netdev_priv(net_dev); - batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS); - return NOTIFY_DONE; - } + if (batadv_softif_is_valid(net_dev)) + return batadv_hard_if_event_softif(event, net_dev); hard_iface = batadv_hardif_get_by_netdev(net_dev); if (!hard_iface && (event == NETDEV_REGISTER || @@ -1051,6 +1073,9 @@ static int batadv_hard_if_event(struct notifier_block *this, if (batadv_is_wifi_hardif(hard_iface)) hard_iface->num_bcasts = BATADV_NUM_BCASTS_WIRELESS; break; + case NETDEV_CHANGENAME: + batadv_debugfs_rename_hardif(hard_iface); + break; default: break; } diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 3986551397ca..12a2b7d21376 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1705,7 +1705,9 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, ether_addr_copy(common->addr, tt_addr); common->vid = vid; - common->flags = flags; + if (!is_multicast_ether_addr(common->addr)) + common->flags = flags & (~BATADV_TT_SYNC_MASK); + tt_global_entry->roam_at = 0; /* node must store current time in case of roaming. This is * needed to purge this entry out on timeout (if nobody claims @@ -1768,7 +1770,8 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv, * TT_CLIENT_TEMP, therefore they have to be copied in the * client entry */ - common->flags |= flags & (~BATADV_TT_SYNC_MASK); + if (!is_multicast_ether_addr(common->addr)) + common->flags |= flags & (~BATADV_TT_SYNC_MASK); /* If there is the BATADV_TT_CLIENT_ROAM flag set, there is only * one originator left in the list and we previously received a diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 68c3578343b4..22a78eedf4b1 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -96,6 +96,7 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, u32 size = kattr->test.data_size_in; u32 repeat = kattr->test.repeat; u32 retval, duration; + int hh_len = ETH_HLEN; struct sk_buff *skb; void *data; int ret; @@ -131,12 +132,22 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr, skb_reset_network_header(skb); if (is_l2) - __skb_push(skb, ETH_HLEN); + __skb_push(skb, hh_len); if (is_direct_pkt_access) bpf_compute_data_pointers(skb); retval = bpf_test_run(prog, skb, repeat, &duration); - if (!is_l2) - __skb_push(skb, ETH_HLEN); + if (!is_l2) { + if (skb_headroom(skb) < hh_len) { + int nhead = HH_DATA_ALIGN(hh_len - skb_headroom(skb)); + + if (pskb_expand_head(skb, nhead, 0, GFP_USER)) { + kfree_skb(skb); + return -ENOMEM; + } + } + memset(__skb_push(skb, hh_len), 0, hh_len); + } + size = skb->len; /* bpf program can never convert linear skb to non-linear */ if (WARN_ON_ONCE(skb_is_nonlinear(skb))) diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig index a948b072c28f..76deb6615883 100644 --- a/net/bpfilter/Kconfig +++ b/net/bpfilter/Kconfig @@ -1,6 +1,5 @@ menuconfig BPFILTER bool "BPF based packet filtering framework (BPFILTER)" - default n depends on NET && BPF && INET help This builds experimental bpfilter framework that is aiming to @@ -9,6 +8,7 @@ menuconfig BPFILTER if BPFILTER config BPFILTER_UMH tristate "bpfilter kernel module with user mode helper" + depends on $(success,$(srctree)/scripts/cc-can-link.sh $(CC)) default m help This builds bpfilter kernel module with embedded user mode helper diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index 051dc18b8ccb..39c6980b5d99 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -15,20 +15,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y) HOSTLDFLAGS += -static endif -# a bit of elf magic to convert bpfilter_umh binary into a binary blob -# inside bpfilter_umh.o elf file referenced by -# _binary_net_bpfilter_bpfilter_umh_start symbol -# which bpfilter_kern.c passes further into umh blob loader at run-time -quiet_cmd_copy_umh = GEN $@ - cmd_copy_umh = echo ':' > $(obj)/.bpfilter_umh.o.cmd; \ - $(OBJCOPY) -I binary \ - `LC_ALL=C $(OBJDUMP) -f net/bpfilter/bpfilter_umh \ - |awk -F' |,' '/file format/{print "-O",$$NF} \ - /^architecture:/{print "-B",$$2}'` \ - --rename-section .data=.init.rodata $< $@ - -$(obj)/bpfilter_umh.o: $(obj)/bpfilter_umh - $(call cmd,copy_umh) +$(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh obj-$(CONFIG_BPFILTER_UMH) += bpfilter.o -bpfilter-objs += bpfilter_kern.o bpfilter_umh.o +bpfilter-objs += bpfilter_kern.o bpfilter_umh_blob.o diff --git a/net/bpfilter/bpfilter_kern.c b/net/bpfilter/bpfilter_kern.c index 09522573f611..f0fc182d3db7 100644 --- a/net/bpfilter/bpfilter_kern.c +++ b/net/bpfilter/bpfilter_kern.c @@ -10,11 +10,8 @@ #include <linux/file.h> #include "msgfmt.h" -#define UMH_start _binary_net_bpfilter_bpfilter_umh_start -#define UMH_end _binary_net_bpfilter_bpfilter_umh_end - -extern char UMH_start; -extern char UMH_end; +extern char bpfilter_umh_start; +extern char bpfilter_umh_end; static struct umh_info info; /* since ip_getsockopt() can run in parallel, serialize access to umh */ @@ -93,7 +90,9 @@ static int __init load_umh(void) int err; /* fork usermode process */ - err = fork_usermode_blob(&UMH_start, &UMH_end - &UMH_start, &info); + err = fork_usermode_blob(&bpfilter_umh_start, + &bpfilter_umh_end - &bpfilter_umh_start, + &info); if (err) return err; pr_info("Loaded bpfilter_umh pid %d\n", info.pid); diff --git a/net/bpfilter/bpfilter_umh_blob.S b/net/bpfilter/bpfilter_umh_blob.S new file mode 100644 index 000000000000..40311d10d2f2 --- /dev/null +++ b/net/bpfilter/bpfilter_umh_blob.S @@ -0,0 +1,7 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + .section .init.rodata, "a" + .global bpfilter_umh_start +bpfilter_umh_start: + .incbin "net/bpfilter/bpfilter_umh" + .global bpfilter_umh_end +bpfilter_umh_end: diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index e0adcd123f48..711d7156efd8 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -131,8 +131,10 @@ static void caif_flow_cb(struct sk_buff *skb) caifd = caif_get(skb->dev); WARN_ON(caifd == NULL); - if (caifd == NULL) + if (!caifd) { + rcu_read_unlock(); return; + } caifd_hold(caifd); rcu_read_unlock(); diff --git a/net/core/dev.c b/net/core/dev.c index a5aa1c7444e6..559a91271f82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7149,16 +7149,19 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len) dev->tx_queue_len = new_len; res = call_netdevice_notifiers(NETDEV_CHANGE_TX_QUEUE_LEN, dev); res = notifier_to_errno(res); - if (res) { - netdev_err(dev, - "refused to change device tx_queue_len\n"); - dev->tx_queue_len = orig_len; - return res; - } - return dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; + res = dev_qdisc_change_tx_queue_len(dev); + if (res) + goto err_rollback; } return 0; + +err_rollback: + netdev_err(dev, "refused to change device tx_queue_len\n"); + dev->tx_queue_len = orig_len; + return res; } /** diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index a04e1e88bf3a..50537ff961a7 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -285,16 +285,9 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_qlen < 0) return -EINVAL; if (dev->tx_queue_len ^ ifr->ifr_qlen) { - unsigned int orig_len = dev->tx_queue_len; - - dev->tx_queue_len = ifr->ifr_qlen; - err = call_netdevice_notifiers( - NETDEV_CHANGE_TX_QUEUE_LEN, dev); - err = notifier_to_errno(err); - if (err) { - dev->tx_queue_len = orig_len; + err = dev_change_tx_queue_len(dev, ifr->ifr_qlen); + if (err) return err; - } } return 0; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 126ffc5bc630..f64aa13811ea 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -416,6 +416,14 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->mark && r->mark != rule->mark) continue; + if (rule->suppress_ifgroup != -1 && + r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (rule->suppress_prefixlen != -1 && + r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; @@ -436,6 +444,9 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; + if (rule->proto && r->proto != rule->proto) + continue; + if (fib_rule_port_range_set(&rule->sport_range) && !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) @@ -645,6 +656,73 @@ errout: return err; } +static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, + struct nlattr **tb, struct fib_rule *rule) +{ + struct fib_rule *r; + + list_for_each_entry(r, &ops->rules_list, list) { + if (r->action != rule->action) + continue; + + if (r->table != rule->table) + continue; + + if (r->pref != rule->pref) + continue; + + if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) + continue; + + if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) + continue; + + if (r->mark != rule->mark) + continue; + + if (r->suppress_ifgroup != rule->suppress_ifgroup) + continue; + + if (r->suppress_prefixlen != rule->suppress_prefixlen) + continue; + + if (r->mark_mask != rule->mark_mask) + continue; + + if (r->tun_id != rule->tun_id) + continue; + + if (r->fr_net != rule->fr_net) + continue; + + if (r->l3mdev != rule->l3mdev) + continue; + + if (!uid_eq(r->uid_range.start, rule->uid_range.start) || + !uid_eq(r->uid_range.end, rule->uid_range.end)) + continue; + + if (r->ip_proto != rule->ip_proto) + continue; + + if (r->proto != rule->proto) + continue; + + if (!fib_rule_port_range_compare(&r->sport_range, + &rule->sport_range)) + continue; + + if (!fib_rule_port_range_compare(&r->dport_range, + &rule->dport_range)) + continue; + + if (!ops->compare(r, frh, tb)) + continue; + return 1; + } + return 0; +} + int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -679,7 +757,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout; if ((nlh->nlmsg_flags & NLM_F_EXCL) && - rule_find(ops, frh, tb, rule, user_priority)) { + rule_exists(ops, frh, tb, rule)) { err = -EEXIST; goto errout_free; } diff --git a/net/core/filter.c b/net/core/filter.c index e7f12e9f598c..9dfd145eedcc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -459,11 +459,21 @@ static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) (!unaligned_ok && offset >= 0 && offset + ip_align >= 0 && offset + ip_align % size == 0))) { + bool ldx_off_ok = offset <= S16_MAX; + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); - *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian); - *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, - offset); + *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, + size, 2 + endian + (!ldx_off_ok * 2)); + if (ldx_off_ok) { + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_D, offset); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_D); + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_TMP, offset); + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, + BPF_REG_TMP, 0); + } if (endian) *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); *insn++ = BPF_JMP_A(8); @@ -1702,24 +1712,26 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { + u8 *end = skb_tail_pointer(skb); + u8 *net = skb_network_header(skb); + u8 *mac = skb_mac_header(skb); u8 *ptr; - if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + if (unlikely(offset > 0xffff || len > (end - mac))) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = skb_mac_header(skb) + offset; + ptr = mac + offset; break; case BPF_HDR_START_NET: - ptr = skb_network_header(skb) + offset; + ptr = net + offset; break; default: goto err_clear; } - if (likely(ptr >= skb_mac_header(skb) && - ptr + len <= skb_tail_pointer(skb))) { + if (likely(ptr >= mac && ptr + len <= end)) { memcpy(to, ptr, len); return 0; } @@ -1762,6 +1774,37 @@ static const struct bpf_func_proto bpf_skb_pull_data_proto = { .arg2_type = ARG_ANYTHING, }; +static inline int sk_skb_try_make_writable(struct sk_buff *skb, + unsigned int write_len) +{ + int err = __bpf_try_make_writable(skb, write_len); + + bpf_compute_data_end_sk_skb(skb); + return err; +} + +BPF_CALL_2(sk_skb_pull_data, struct sk_buff *, skb, u32, len) +{ + /* Idea is the following: should the needed direct read/write + * test fail during runtime, we can pull in more data and redo + * again, since implicitly, we invalidate previous checks here. + * + * Or, since we know how much we need to make read/writeable, + * this can be done once at the program beginning for direct + * access case. By this we overcome limitations of only current + * headroom being accessible. + */ + return sk_skb_try_make_writable(skb, len ? : skb_headlen(skb)); +} + +static const struct bpf_func_proto sk_skb_pull_data_proto = { + .func = sk_skb_pull_data, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_5(bpf_l3_csum_replace, struct sk_buff *, skb, u32, offset, u64, from, u64, to, u64, flags) { @@ -2779,7 +2822,8 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 len_diff) static u32 __bpf_skb_max_len(const struct sk_buff *skb) { - return skb->dev->mtu + skb->dev->hard_header_len; + return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len : + SKB_MAX_ALLOC; } static int bpf_skb_adjust_net(struct sk_buff *skb, s32 len_diff) @@ -2863,8 +2907,8 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len) return __skb_trim_rcsum(skb, new_len); } -BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, - u64, flags) +static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len, + u64 flags) { u32 max_len = __bpf_skb_max_len(skb); u32 min_len = __bpf_skb_min_len(skb); @@ -2900,6 +2944,13 @@ BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, if (!ret && skb_is_gso(skb)) skb_gso_reset(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_tail, struct sk_buff *, skb, u32, new_len, + u64, flags) +{ + int ret = __bpf_skb_change_tail(skb, new_len, flags); bpf_compute_data_pointers(skb); return ret; @@ -2914,9 +2965,27 @@ static const struct bpf_func_proto bpf_skb_change_tail_proto = { .arg3_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, +BPF_CALL_3(sk_skb_change_tail, struct sk_buff *, skb, u32, new_len, u64, flags) { + int ret = __bpf_skb_change_tail(skb, new_len, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_tail_proto = { + .func = sk_skb_change_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; + +static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room, + u64 flags) +{ u32 max_len = __bpf_skb_max_len(skb); u32 new_len = skb->len + head_room; int ret; @@ -2941,8 +3010,16 @@ BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, skb_reset_mac_header(skb); } + return ret; +} + +BPF_CALL_3(bpf_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + bpf_compute_data_pointers(skb); - return 0; + return ret; } static const struct bpf_func_proto bpf_skb_change_head_proto = { @@ -2954,6 +3031,23 @@ static const struct bpf_func_proto bpf_skb_change_head_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_3(sk_skb_change_head, struct sk_buff *, skb, u32, head_room, + u64, flags) +{ + int ret = __bpf_skb_change_head(skb, head_room, flags); + + bpf_compute_data_end_sk_skb(skb); + return ret; +} + +static const struct bpf_func_proto sk_skb_change_head_proto = { + .func = sk_skb_change_head, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, +}; static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) { return xdp_data_meta_unsupported(xdp) ? 0 : @@ -3046,12 +3140,16 @@ static int __bpf_tx_xdp(struct net_device *dev, u32 index) { struct xdp_frame *xdpf; - int sent; + int err, sent; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } + err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(err)) + return err; + xdpf = convert_to_xdp_frame(xdp); if (unlikely(!xdpf)) return -EOVERFLOW; @@ -3285,7 +3383,8 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, goto err; } - if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) + err = xdp_ok_fwd_dev(fwd, skb->len); + if (unlikely(err)) goto err; skb->dev = fwd; @@ -4073,8 +4172,9 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; + params->ifindex = dev->ifindex; - return dev->ifindex; + return 0; } #endif @@ -4098,7 +4198,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* verify forwarding is enabled on this interface */ in_dev = __in_dev_get_rcu(dev); if (unlikely(!in_dev || !IN_DEV_FORWARD(in_dev))) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl4.flowi4_iif = 1; @@ -4123,7 +4223,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = fib_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF); } else { @@ -4135,8 +4235,20 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, err = fib_lookup(net, &fl4, &res, FIB_LOOKUP_NOREF); } - if (err || res.type != RTN_UNICAST) - return 0; + if (err) { + /* map fib lookup errors to RTN_ type */ + if (err == -EINVAL) + return BPF_FIB_LKUP_RET_BLACKHOLE; + if (err == -EHOSTUNREACH) + return BPF_FIB_LKUP_RET_UNREACHABLE; + if (err == -EACCES) + return BPF_FIB_LKUP_RET_PROHIBIT; + + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + + if (res.type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (res.fi->fib_nhs > 1) fib_select_path(net, &res, &fl4, NULL); @@ -4144,19 +4256,16 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ip_mtu_from_fib_result(&res, params->ipv4_dst); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } nh = &res.fi->fib_nh[res.nh_sel]; /* do not handle lwt encaps right now */ if (nh->nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; dev = nh->nh_dev; - if (unlikely(!dev)) - return 0; - if (nh->nh_gw) params->ipv4_dst = nh->nh_gw; @@ -4166,10 +4275,10 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, * rcu_read_lock_bh is not needed here */ neigh = __ipv4_neigh_lookup_noref(dev, (__force u32)params->ipv4_dst); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4190,7 +4299,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, /* link local addresses are never forwarded */ if (rt6_need_strict(dst) || rt6_need_strict(src)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; dev = dev_get_by_index_rcu(net, params->ifindex); if (unlikely(!dev)) @@ -4198,7 +4307,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, idev = __in6_dev_get_safely(dev); if (unlikely(!idev || !net->ipv6.devconf_all->forwarding)) - return 0; + return BPF_FIB_LKUP_RET_FWD_DISABLED; if (flags & BPF_FIB_LOOKUP_OUTPUT) { fl6.flowi6_iif = 1; @@ -4225,7 +4334,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, tb = ipv6_stub->fib6_get_table(net, tbid); if (unlikely(!tb)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; f6i = ipv6_stub->fib6_table_lookup(net, tb, oif, &fl6, strict); } else { @@ -4238,11 +4347,23 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, } if (unlikely(IS_ERR_OR_NULL(f6i) || f6i == net->ipv6.fib6_null_entry)) - return 0; + return BPF_FIB_LKUP_RET_NOT_FWDED; + + if (unlikely(f6i->fib6_flags & RTF_REJECT)) { + switch (f6i->fib6_type) { + case RTN_BLACKHOLE: + return BPF_FIB_LKUP_RET_BLACKHOLE; + case RTN_UNREACHABLE: + return BPF_FIB_LKUP_RET_UNREACHABLE; + case RTN_PROHIBIT: + return BPF_FIB_LKUP_RET_PROHIBIT; + default: + return BPF_FIB_LKUP_RET_NOT_FWDED; + } + } - if (unlikely(f6i->fib6_flags & RTF_REJECT || - f6i->fib6_type != RTN_UNICAST)) - return 0; + if (f6i->fib6_type != RTN_UNICAST) + return BPF_FIB_LKUP_RET_NOT_FWDED; if (f6i->fib6_nsiblings && fl6.flowi6_oif == 0) f6i = ipv6_stub->fib6_multipath_select(net, f6i, &fl6, @@ -4252,11 +4373,11 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, if (check_mtu) { mtu = ipv6_stub->ip6_mtu_from_fib6(f6i, dst, src); if (params->tot_len > mtu) - return 0; + return BPF_FIB_LKUP_RET_FRAG_NEEDED; } if (f6i->fib6_nh.nh_lwtstate) - return 0; + return BPF_FIB_LKUP_RET_UNSUPP_LWT; if (f6i->fib6_flags & RTF_GATEWAY) *dst = f6i->fib6_nh.nh_gw; @@ -4270,10 +4391,10 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, */ neigh = ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, dst, dev); - if (neigh) - return bpf_fib_set_fwd_params(params, neigh, dev); + if (!neigh) + return BPF_FIB_LKUP_RET_NO_NEIGH; - return 0; + return bpf_fib_set_fwd_params(params, neigh, dev); } #endif @@ -4315,7 +4436,7 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, struct bpf_fib_lookup *, params, int, plen, u32, flags) { struct net *net = dev_net(skb->dev); - int index = -EAFNOSUPPORT; + int rc = -EAFNOSUPPORT; if (plen < sizeof(*params)) return -EINVAL; @@ -4326,25 +4447,25 @@ BPF_CALL_4(bpf_skb_fib_lookup, struct sk_buff *, skb, switch (params->family) { #if IS_ENABLED(CONFIG_INET) case AF_INET: - index = bpf_ipv4_fib_lookup(net, params, flags, false); + rc = bpf_ipv4_fib_lookup(net, params, flags, false); break; #endif #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - index = bpf_ipv6_fib_lookup(net, params, flags, false); + rc = bpf_ipv6_fib_lookup(net, params, flags, false); break; #endif } - if (index > 0) { + if (!rc) { struct net_device *dev; - dev = dev_get_by_index_rcu(net, index); + dev = dev_get_by_index_rcu(net, params->ifindex); if (!is_skb_forwardable(dev, skb)) - index = 0; + rc = BPF_FIB_LKUP_RET_FRAG_NEEDED; } - return index; + return rc; } static const struct bpf_func_proto bpf_skb_fib_lookup_proto = { @@ -4417,10 +4538,10 @@ static const struct bpf_func_proto bpf_lwt_push_encap_proto = { .arg4_type = ARG_CONST_SIZE }; +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, const void *, from, u32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_tlvs, *srh_end, *ptr; @@ -4446,9 +4567,6 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset, memcpy(skb->data + offset, from, len); return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { @@ -4464,7 +4582,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = { BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, u32, action, void *, param, u32, param_len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); struct ipv6_sr_hdr *srh; @@ -4512,9 +4629,6 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb, default: return -EINVAL; } -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { @@ -4530,7 +4644,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_action_proto = { BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, s32, len) { -#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) struct seg6_bpf_srh_state *srh_state = this_cpu_ptr(&seg6_bpf_srh_states); void *srh_end, *srh_tlvs, *ptr; @@ -4574,9 +4687,6 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset, srh_state->hdrlen += len; srh_state->valid = 0; return 0; -#else /* CONFIG_IPV6_SEG6_BPF */ - return -EOPNOTSUPP; -#endif } static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { @@ -4587,6 +4697,7 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; +#endif /* CONFIG_IPV6_SEG6_BPF */ bool bpf_helper_changes_pkt_data(void *func) { @@ -4595,9 +4706,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_store_bytes || func == bpf_skb_change_proto || func == bpf_skb_change_head || + func == sk_skb_change_head || func == bpf_skb_change_tail || + func == sk_skb_change_tail || func == bpf_skb_adjust_room || func == bpf_skb_pull_data || + func == sk_skb_pull_data || func == bpf_clone_redirect || func == bpf_l3_csum_replace || func == bpf_l4_csum_replace || @@ -4605,11 +4719,12 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_xdp_adjust_meta || func == bpf_msg_pull_data || func == bpf_xdp_adjust_tail || - func == bpf_lwt_push_encap || +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) func == bpf_lwt_seg6_store_bytes || func == bpf_lwt_seg6_adjust_srh || - func == bpf_lwt_seg6_action - ) + func == bpf_lwt_seg6_action || +#endif + func == bpf_lwt_push_encap) return true; return false; @@ -4849,11 +4964,11 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; case BPF_FUNC_skb_pull_data: - return &bpf_skb_pull_data_proto; + return &sk_skb_pull_data_proto; case BPF_FUNC_skb_change_tail: - return &bpf_skb_change_tail_proto; + return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: - return &bpf_skb_change_head_proto; + return &sk_skb_change_head_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -4944,12 +5059,14 @@ static const struct bpf_func_proto * lwt_seg6local_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { +#if IS_ENABLED(CONFIG_IPV6_SEG6_BPF) case BPF_FUNC_lwt_seg6_store_bytes: return &bpf_lwt_seg6_store_bytes_proto; case BPF_FUNC_lwt_seg6_action: return &bpf_lwt_seg6_action_proto; case BPF_FUNC_lwt_seg6_adjust_srh: return &bpf_lwt_seg6_adjust_srh_proto; +#endif default: return lwt_out_func_proto(func_id, prog); } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index b2b2323bdc84..188d693cb251 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -77,8 +77,20 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, d->lock = lock; spin_lock_bh(lock); } - if (d->tail) - return gnet_stats_copy(d, type, NULL, 0, padattr); + if (d->tail) { + int ret = gnet_stats_copy(d, type, NULL, 0, padattr); + + /* The initial attribute added in gnet_stats_copy() may be + * preceded by a padding attribute, in which case d->tail will + * end up pointing at the padding instead of the real attribute. + * Fix this so gnet_stats_finish_copy() adjusts the length of + * the right attribute. + */ + if (ret == 0 && d->tail->nla_type == padattr) + d->tail = (struct nlattr *)((char *)d->tail + + NLA_ALIGN(d->tail->nla_len)); + return ret; + } return 0; } diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index e7e626fb87bb..e45098593dc0 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -217,7 +217,7 @@ static int bpf_parse_prog(struct nlattr *attr, struct bpf_lwt_prog *prog, if (!tb[LWT_BPF_PROG_FD] || !tb[LWT_BPF_PROG_NAME]) return -EINVAL; - prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_KERNEL); + prog->name = nla_memdup(tb[LWT_BPF_PROG_NAME], GFP_ATOMIC); if (!prog->name) return -ENOMEM; diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 68bf07206744..43a932cb609b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -269,7 +269,7 @@ static void __page_pool_empty_ring(struct page_pool *pool) struct page *page; /* Empty recycle ring */ - while ((page = ptr_ring_consume(&pool->ring))) { + while ((page = ptr_ring_consume_bh(&pool->ring))) { /* Verify the refcnt invariant of cached pages */ if (!(page_ref_count(page) == 1)) pr_crit("%s() page_pool refcnt %d violation\n", diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ef61222fdef..e3f743c141b3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) return err; } - dev->rtnl_link_state = RTNL_LINK_INITIALIZED; - - __dev_notify_flags(dev, old_flags, ~0U); + if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) { + __dev_notify_flags(dev, old_flags, 0U); + } else { + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + __dev_notify_flags(dev, old_flags, ~0U); + } return 0; } EXPORT_SYMBOL(rtnl_configure_link); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index c642304f178c..fb35b62af272 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -858,6 +858,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb) n->cloned = 1; n->nohdr = 0; n->peeked = 0; + C(pfmemalloc); n->destructor = NULL; C(tail); C(end); @@ -3719,6 +3720,7 @@ normal: net_warn_ratelimited( "skb_segment: too many frags: %u %u\n", pos, mss); + err = -EINVAL; goto err; } @@ -3752,11 +3754,10 @@ skip_fraglist: perform_csum_check: if (!csum) { - if (skb_has_shared_frag(nskb)) { - err = __skb_linearize(nskb); - if (err) - goto err; - } + if (skb_has_shared_frag(nskb) && + __skb_linearize(nskb)) + goto err; + if (!nskb->remcsum_offload) nskb->ip_summed = CHECKSUM_NONE; SKB_GSO_CB(nskb)->csum = @@ -5276,8 +5277,7 @@ struct sk_buff *alloc_skb_with_frags(unsigned long header_len, if (npages >= 1 << order) { page = alloc_pages((gfp_mask & ~__GFP_DIRECT_RECLAIM) | __GFP_COMP | - __GFP_NOWARN | - __GFP_NORETRY, + __GFP_NOWARN, order); if (page) goto fill_page; diff --git a/net/core/sock.c b/net/core/sock.c index bcc41829a16d..bc2d7a37297f 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2277,9 +2277,9 @@ int sk_alloc_sg(struct sock *sk, int len, struct scatterlist *sg, pfrag->offset += use; sge = sg + sg_curr - 1; - if (sg_curr > first_coalesce && sg_page(sg) == pfrag->page && - sg->offset + sg->length == orig_offset) { - sg->length += use; + if (sg_curr > first_coalesce && sg_page(sge) == pfrag->page && + sge->offset + sge->length == orig_offset) { + sge->length += use; } else { sge = sg + sg_curr; sg_unmark_end(sge); @@ -3243,7 +3243,8 @@ static int req_prot_init(const struct proto *prot) rsk_prot->slab = kmem_cache_create(rsk_prot->slab_name, rsk_prot->obj_size, 0, - prot->slab_flags, NULL); + SLAB_ACCOUNT | prot->slab_flags, + NULL); if (!rsk_prot->slab) { pr_crit("%s: Can't create request sock SLAB cache!\n", @@ -3258,7 +3259,8 @@ int proto_register(struct proto *prot, int alloc_slab) if (alloc_slab) { prot->slab = kmem_cache_create_usercopy(prot->name, prot->obj_size, 0, - SLAB_HWCACHE_ALIGN | prot->slab_flags, + SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT | + prot->slab_flags, prot->useroffset, prot->usersize, NULL); @@ -3281,6 +3283,7 @@ int proto_register(struct proto *prot, int alloc_slab) kmem_cache_create(prot->twsk_prot->twsk_slab_name, prot->twsk_prot->twsk_obj_size, 0, + SLAB_ACCOUNT | prot->slab_flags, NULL); if (prot->twsk_prot->twsk_slab == NULL) diff --git a/net/core/xdp.c b/net/core/xdp.c index 9d1f22072d5d..6771f1855b96 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -345,7 +345,8 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); - xa->zc_alloc->free(xa->zc_alloc, handle); + if (!WARN_ON_ONCE(!xa)) + xa->zc_alloc->free(xa->zc_alloc, handle); rcu_read_unlock(); default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index 40c851693f77..0c9478b91fa5 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -86,35 +86,39 @@ dns_resolver_preparse(struct key_preparsed_payload *prep) opt++; kdebug("options: '%s'", opt); do { + int opt_len, opt_nlen; const char *eq; - int opt_len, opt_nlen, opt_vlen, tmp; + char optval[128]; next_opt = memchr(opt, '#', end - opt) ?: end; opt_len = next_opt - opt; - if (opt_len <= 0 || opt_len > 128) { + if (opt_len <= 0 || opt_len > sizeof(optval)) { pr_warn_ratelimited("Invalid option length (%d) for dns_resolver key\n", opt_len); return -EINVAL; } - eq = memchr(opt, '=', opt_len) ?: end; - opt_nlen = eq - opt; - eq++; - opt_vlen = next_opt - eq; /* will be -1 if no value */ + eq = memchr(opt, '=', opt_len); + if (eq) { + opt_nlen = eq - opt; + eq++; + memcpy(optval, eq, next_opt - eq); + optval[next_opt - eq] = '\0'; + } else { + opt_nlen = opt_len; + optval[0] = '\0'; + } - tmp = opt_vlen >= 0 ? opt_vlen : 0; - kdebug("option '%*.*s' val '%*.*s'", - opt_nlen, opt_nlen, opt, tmp, tmp, eq); + kdebug("option '%*.*s' val '%s'", + opt_nlen, opt_nlen, opt, optval); /* see if it's an error number representing a DNS error * that's to be recorded as the result in this key */ if (opt_nlen == sizeof(DNS_ERRORNO_OPTION) - 1 && memcmp(opt, DNS_ERRORNO_OPTION, opt_nlen) == 0) { kdebug("dns error number option"); - if (opt_vlen <= 0) - goto bad_option_value; - ret = kstrtoul(eq, 10, &derrno); + ret = kstrtoul(optval, 10, &derrno); if (ret < 0) goto bad_option_value; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 1e3b6a6d8a40..732369c80644 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1248,6 +1248,9 @@ int dsa_slave_suspend(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_detach(slave_dev); rtnl_lock(); @@ -1261,6 +1264,9 @@ int dsa_slave_resume(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); + if (!netif_running(slave_dev)) + return 0; + netif_device_attach(slave_dev); rtnl_lock(); diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c index 275449b0d633..3297e7fa9945 100644 --- a/net/ieee802154/6lowpan/core.c +++ b/net/ieee802154/6lowpan/core.c @@ -90,12 +90,18 @@ static int lowpan_neigh_construct(struct net_device *dev, struct neighbour *n) return 0; } +static int lowpan_get_iflink(const struct net_device *dev) +{ + return lowpan_802154_dev(dev)->wdev->ifindex; +} + static const struct net_device_ops lowpan_netdev_ops = { .ndo_init = lowpan_dev_init, .ndo_start_xmit = lowpan_xmit, .ndo_open = lowpan_open, .ndo_stop = lowpan_stop, .ndo_neigh_construct = lowpan_neigh_construct, + .ndo_get_iflink = lowpan_get_iflink, }; static void lowpan_setup(struct net_device *ldev) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index b21833651394..2998b0e47d4b 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -292,18 +292,19 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) return ip_hdr(skb)->daddr; in_dev = __in_dev_get_rcu(dev); - BUG_ON(!in_dev); net = dev_net(dev); scope = RT_SCOPE_UNIVERSE; if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) { + bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev); struct flowi4 fl4 = { .flowi4_iif = LOOPBACK_IFINDEX, + .flowi4_oif = l3mdev_master_ifindex_rcu(dev), .daddr = ip_hdr(skb)->saddr, .flowi4_tos = RT_TOS(ip_hdr(skb)->tos), .flowi4_scope = scope, - .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0, + .flowi4_mark = vmark ? skb->mark : 0, }; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 1540db65241a..c9ec1603666b 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -448,9 +448,7 @@ next_proto: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, &grc); - skb->remcsum_offload = 0; + skb_gro_flush_final_remcsum(skb, pp, flush, &grc); return pp; } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 1859c473b21a..6a7d980105f6 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -223,7 +223,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head, out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 85b617b655bc..75151be21413 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -1200,13 +1200,13 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; - im->sfmode = pmc->sfmode; - if (pmc->sfmode == MCAST_INCLUDE) { + if (im->sfmode == MCAST_INCLUDE) { im->tomb = pmc->tomb; im->sources = pmc->sources; for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->crcount; + psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + } else { + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } in_dev_put(pmc->interface); kfree(pmc); @@ -1288,7 +1288,7 @@ static void igmp_group_dropped(struct ip_mc_list *im) #endif } -static void igmp_group_added(struct ip_mc_list *im) +static void igmp_group_added(struct ip_mc_list *im, unsigned int mode) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1316,7 +1316,13 @@ static void igmp_group_added(struct ip_mc_list *im) } /* else, v3 */ - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should + * not send filter-mode change record as the mode should be from + * IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + igmp_ifc_event(in_dev); #endif } @@ -1381,8 +1387,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ - -void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode) { struct ip_mc_list *im; #ifdef CONFIG_IP_MULTICAST @@ -1394,7 +1400,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; - ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); + ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } @@ -1408,8 +1414,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ - im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_EXCLUDE] = 1; + im->sfmode = mode; + im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST @@ -1426,12 +1432,17 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif - igmp_group_added(im); + igmp_group_added(im, mode); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } + +void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) +{ + __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) @@ -1688,7 +1699,7 @@ void ip_mc_remap(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -1751,7 +1762,7 @@ void ip_mc_up(struct in_device *in_dev) #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif - igmp_group_added(pmc); + igmp_group_added(pmc, pmc->sfmode); } } @@ -2130,8 +2141,8 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc) /* Join a multicast group */ - -int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; @@ -2172,15 +2183,30 @@ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; - iml->sfmode = MCAST_EXCLUDE; + iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); - ip_mc_inc_group(in_dev, addr); + __ip_mc_inc_group(in_dev, addr, mode); err = 0; done: return err; } + +/* Join ASM (Any-Source Multicast) group + */ +int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) +{ + return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ip_mc_join_group); +/* Join SSM (Source-Specific Multicast) group + */ +int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, + unsigned int mode) +{ + return __ip_mc_join_group(sk, imr, mode); +} + static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index c9e35b81d093..0d70608cc2e1 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr, void *arg) void inet_frags_exit_net(struct netns_frags *nf) { - nf->low_thresh = 0; /* prevent creation of new frags */ + nf->high_thresh = 0; /* prevent creation of new frags */ rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); } @@ -157,9 +157,6 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, { struct inet_frag_queue *q; - if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) - return NULL; - q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; @@ -204,6 +201,9 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { struct inet_frag_queue *fq; + if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) + return NULL; + rcu_read_lock(); fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 8e9528ebaa8e..d14d741fb05e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -383,11 +383,16 @@ found: int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */ if (i < next->len) { + int delta = -next->truesize; + /* Eat head of the next overlapped fragment * and leave the loop. The next ones cannot overlap. */ if (!pskb_pull(next, i)) goto err; + delta += next->truesize; + if (delta) + add_frag_mem_limit(qp->q.net, delta); next->ip_defrag_offset += i; qp->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b3308e9d9762..0e3edd25f881 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -523,6 +523,8 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + /* Copy the flags to each fragment. */ IPCB(to)->flags = IPCB(from)->flags; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index fc32fdbeefa6..c0fe5ad996f2 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -150,15 +150,18 @@ static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) { struct sockaddr_in sin; const struct iphdr *iph = ip_hdr(skb); - __be16 *ports = (__be16 *)skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 > (int)skb->len) + end = skb_transport_offset(skb) + 4; + if (end > 0 && !pskb_may_pull(skb, end)) return; /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin.sin_family = AF_INET; sin.sin_addr.s_addr = iph->daddr; @@ -984,7 +987,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr.s_addr = mreqs.imr_multiaddr; mreq.imr_address.s_addr = mreqs.imr_interface; mreq.imr_ifindex = 0; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; omode = MCAST_INCLUDE; @@ -1061,7 +1064,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, mreq.imr_multiaddr = psin->sin_addr; mreq.imr_address.s_addr = 0; mreq.imr_ifindex = greqs.gsr_interface; - err = ip_mc_join_group(sk, &mreq); + err = ip_mc_join_group_ssm(sk, &mreq, MCAST_INCLUDE); if (err && err != -EADDRINUSE) break; greqs.gsr_interface = mreq.imr_ifindex; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ca0dad90803a..e77872c93c20 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1898,6 +1898,7 @@ static struct xt_match ipt_builtin_mt[] __read_mostly = { .checkentry = icmp_checkentry, .proto = IPPROTO_ICMP, .family = NFPROTO_IPV4, + .me = THIS_MODULE, }, }; diff --git a/net/ipv4/netfilter/nf_tproxy_ipv4.c b/net/ipv4/netfilter/nf_tproxy_ipv4.c index 805e83ec3ad9..164714104965 100644 --- a/net/ipv4/netfilter/nf_tproxy_ipv4.c +++ b/net/ipv4/netfilter/nf_tproxy_ipv4.c @@ -37,7 +37,7 @@ nf_tproxy_handle_time_wait4(struct net *net, struct sk_buff *skb, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk2 = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr ? laddr : iph->daddr, hp->source, lport ? lport : hp->dest, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -71,7 +71,7 @@ __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr) EXPORT_SYMBOL_GPL(nf_tproxy_laddr4); struct sock * -nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, +nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, const u8 protocol, const __be32 saddr, const __be32 daddr, const __be16 sport, const __be16 dport, @@ -79,16 +79,21 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, ip_hdrlen(skb), + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet_lookup_listener(net, &tcp_hashinfo, skb, ip_hdrlen(skb) + - __tcp_hdrlen(tcph), + __tcp_hdrlen(hp), saddr, sport, daddr, dport, in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp4_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d06247ba08b2..5fa335fd3852 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -189,8 +189,9 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write, if (write && ret == 0) { low = make_kgid(user_ns, urange[0]); high = make_kgid(user_ns, urange[1]); - if (!gid_valid(low) || !gid_valid(high) || - (urange[1] < urange[0]) || gid_lt(high, low)) { + if (!gid_valid(low) || !gid_valid(high)) + return -EINVAL; + if (urange[1] < urange[0] || gid_lt(high, low)) { low = make_kgid(&init_user_ns, 1); high = make_kgid(&init_user_ns, 0); } @@ -265,8 +266,9 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ipv4.sysctl_tcp_fastopen); struct ctl_table tbl = { .maxlen = (TCP_FASTOPEN_KEY_LENGTH * 2 + 10) }; struct tcp_fastopen_context *ctxt; - int ret; u32 user_key[4]; /* 16 bytes, matching TCP_FASTOPEN_KEY_LENGTH */ + __le32 key[4]; + int ret, i; tbl.data = kmalloc(tbl.maxlen, GFP_KERNEL); if (!tbl.data) @@ -275,11 +277,14 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) - memcpy(user_key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); + memcpy(key, ctxt->key, TCP_FASTOPEN_KEY_LENGTH); else - memset(user_key, 0, sizeof(user_key)); + memset(key, 0, sizeof(key)); rcu_read_unlock(); + for (i = 0; i < ARRAY_SIZE(key); i++) + user_key[i] = le32_to_cpu(key[i]); + snprintf(tbl.data, tbl.maxlen, "%08x-%08x-%08x-%08x", user_key[0], user_key[1], user_key[2], user_key[3]); ret = proc_dostring(&tbl, write, buffer, lenp, ppos); @@ -290,13 +295,17 @@ static int proc_tcp_fastopen_key(struct ctl_table *table, int write, ret = -EINVAL; goto bad_key; } - tcp_fastopen_reset_cipher(net, NULL, user_key, + + for (i = 0; i < ARRAY_SIZE(user_key); i++) + key[i] = cpu_to_le32(user_key[i]); + + tcp_fastopen_reset_cipher(net, NULL, key, TCP_FASTOPEN_KEY_LENGTH); } bad_key: pr_debug("proc FO key set 0x%x-%x-%x-%x <- 0x%s: %u\n", - user_key[0], user_key[1], user_key[2], user_key[3], + user_key[0], user_key[1], user_key[2], user_key[3], (char *)tbl.data, ret); kfree(tbl.data); return ret; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e7b53d2a971f..4491faf83f4f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1998,7 +1998,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, * shouldn't happen. */ if (WARN(before(*seq, TCP_SKB_CB(skb)->seq), - "recvmsg bug: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags)) break; @@ -2013,7 +2013,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; WARN(!(flags & MSG_PEEK), - "recvmsg bug 2: copied %X seq %X rcvnxt %X fl %X\n", + "TCP recvmsg seq # bug 2: copied %X, seq %X, rcvnxt %X, fl %X\n", *seq, TCP_SKB_CB(skb)->seq, tp->rcv_nxt, flags); } @@ -2562,6 +2562,8 @@ int tcp_disconnect(struct sock *sk, int flags) tcp_clear_xmit_timers(sk); __skb_queue_purge(&sk->sk_receive_queue); + tp->copied_seq = tp->rcv_nxt; + tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); skb_rbtree_purge(&tp->out_of_order_queue); @@ -2821,14 +2823,17 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_REPAIR: if (!tcp_can_repair_sock(sk)) err = -EPERM; - else if (val == 1) { + else if (val == TCP_REPAIR_ON) { tp->repair = 1; sk->sk_reuse = SK_FORCE_REUSE; tp->repair_queue = TCP_NO_QUEUE; - } else if (val == 0) { + } else if (val == TCP_REPAIR_OFF) { tp->repair = 0; sk->sk_reuse = SK_NO_REUSE; tcp_send_window_probe(sk); + } else if (val == TCP_REPAIR_OFF_NO_WP) { + tp->repair = 0; + sk->sk_reuse = SK_NO_REUSE; } else err = -EINVAL; @@ -3720,8 +3725,7 @@ int tcp_abort(struct sock *sk, int err) struct request_sock *req = inet_reqsk(sk); local_bh_disable(); - inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, - req); + inet_csk_reqsk_queue_drop(req->rsk_listener, req); local_bh_enable(); return 0; } diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 58e2f479ffb4..4bfff3c87e8e 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -354,6 +354,10 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) /* Reduce delayed ACKs by rounding up cwnd to the next even number. */ cwnd = (cwnd + 1) & ~1U; + /* Ensure gain cycling gets inflight above BDP even for small BDPs. */ + if (bbr->mode == BBR_PROBE_BW && gain > BBR_UNIT) + cwnd += 2; + return cwnd; } diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c index 5f5e5936760e..8b637f9f23a2 100644 --- a/net/ipv4/tcp_dctcp.c +++ b/net/ipv4/tcp_dctcp.c @@ -55,7 +55,6 @@ struct dctcp { u32 dctcp_alpha; u32 next_seq; u32 ce_state; - u32 delayed_ack_reserved; u32 loss_cwnd; }; @@ -96,7 +95,6 @@ static void dctcp_init(struct sock *sk) ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA); - ca->delayed_ack_reserved = 0; ca->loss_cwnd = 0; ca->ce_state = 0; @@ -131,23 +129,14 @@ static void dctcp_ce_state_0_to_1(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=0 to CE=1 and delayed - * ACK has not sent yet. - */ - if (!ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=0. */ - tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (!ca->ce_state) { + /* State has changed from CE=0 to CE=1, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -161,23 +150,14 @@ static void dctcp_ce_state_1_to_0(struct sock *sk) struct dctcp *ca = inet_csk_ca(sk); struct tcp_sock *tp = tcp_sk(sk); - /* State has changed from CE=1 to CE=0 and delayed - * ACK has not sent yet. - */ - if (ca->ce_state && ca->delayed_ack_reserved) { - u32 tmp_rcv_nxt; - - /* Save current rcv_nxt. */ - tmp_rcv_nxt = tp->rcv_nxt; - - /* Generate previous ack with CE=1. */ - tp->ecn_flags |= TCP_ECN_DEMAND_CWR; - tp->rcv_nxt = ca->prior_rcv_nxt; - - tcp_send_ack(sk); - - /* Recover current rcv_nxt. */ - tp->rcv_nxt = tmp_rcv_nxt; + if (ca->ce_state) { + /* State has changed from CE=1 to CE=0, force an immediate + * ACK to reflect the new CE state. If an ACK was delayed, + * send that first to reflect the prior CE state. + */ + if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) + __tcp_send_ack(sk, ca->prior_rcv_nxt); + tcp_enter_quickack_mode(sk, 1); } ca->prior_rcv_nxt = tp->rcv_nxt; @@ -248,25 +228,6 @@ static void dctcp_state(struct sock *sk, u8 new_state) } } -static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev) -{ - struct dctcp *ca = inet_csk_ca(sk); - - switch (ev) { - case CA_EVENT_DELAYED_ACK: - if (!ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 1; - break; - case CA_EVENT_NON_DELAYED_ACK: - if (ca->delayed_ack_reserved) - ca->delayed_ack_reserved = 0; - break; - default: - /* Don't care for the rest. */ - break; - } -} - static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) { switch (ev) { @@ -276,10 +237,6 @@ static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev) case CA_EVENT_ECN_NO_CE: dctcp_ce_state_1_to_0(sk); break; - case CA_EVENT_DELAYED_ACK: - case CA_EVENT_NON_DELAYED_ACK: - dctcp_update_ack_reserved(sk, ev); - break; default: /* Don't care for the rest. */ break; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 355d3dffd021..f9dcb29be12d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -215,7 +215,7 @@ static void tcp_incr_quickack(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.quick = quickacks; } -static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) +void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -223,6 +223,7 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) icsk->icsk_ack.pingpong = 0; icsk->icsk_ack.ato = TCP_ATO_MIN; } +EXPORT_SYMBOL(tcp_enter_quickack_mode); /* Send ACKs quickly, if "quick" count is not exhausted * and the session is not interactive. @@ -245,8 +246,15 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp) static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb) { - if (tcp_hdr(skb)->cwr) + if (tcp_hdr(skb)->cwr) { tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR; + + /* If the sender is telling us it has entered CWR, then its + * cwnd may be very low (even just 1 packet), so we should ACK + * immediately. + */ + tcp_enter_quickack_mode((struct sock *)tp, 2); + } } static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp) @@ -265,7 +273,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) * it is probably a retransmit. */ if (tp->ecn_flags & TCP_ECN_SEEN) - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); break; case INET_ECN_CE: if (tcp_ca_needs_ecn(sk)) @@ -273,7 +281,7 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb) if (!(tp->ecn_flags & TCP_ECN_DEMAND_CWR)) { /* Better not delay acks, sender can have a very low cwnd */ - tcp_enter_quickack_mode(sk, 1); + tcp_enter_quickack_mode(sk, 2); tp->ecn_flags |= TCP_ECN_DEMAND_CWR; } tp->ecn_flags |= TCP_ECN_SEEN; @@ -3181,6 +3189,15 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); + + /* If any of the cumulatively ACKed segments was + * retransmitted, non-SACK case cannot confirm that + * progress was due to original transmission due to + * lack of TCPCB_SACKED_ACKED bits even if some of + * the packets may have been never retransmitted. + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + flag &= ~FLAG_ORIG_SACK_ACKED; } else { int delta; @@ -4348,6 +4365,23 @@ static bool tcp_try_coalesce(struct sock *sk, return true; } +static bool tcp_ooo_try_coalesce(struct sock *sk, + struct sk_buff *to, + struct sk_buff *from, + bool *fragstolen) +{ + bool res = tcp_try_coalesce(sk, to, from, fragstolen); + + /* In case tcp_drop() is called later, update to->gso_segs */ + if (res) { + u32 gso_segs = max_t(u16, 1, skb_shinfo(to)->gso_segs) + + max_t(u16, 1, skb_shinfo(from)->gso_segs); + + skb_shinfo(to)->gso_segs = min_t(u32, gso_segs, 0xFFFF); + } + return res; +} + static void tcp_drop(struct sock *sk, struct sk_buff *skb) { sk_drops_add(sk, skb); @@ -4471,8 +4505,8 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) /* In the typical case, we are adding an skb to the end of the list. * Use of ooo_last_skb avoids the O(Log(N)) rbtree lookup. */ - if (tcp_try_coalesce(sk, tp->ooo_last_skb, - skb, &fragstolen)) { + if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, + skb, &fragstolen)) { coalesce_done: tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); @@ -4500,7 +4534,7 @@ coalesce_done: /* All the bits are present. Drop. */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb); + tcp_drop(sk, skb); skb = NULL; tcp_dsack_set(sk, seq, end_seq); goto add_sack; @@ -4519,11 +4553,11 @@ coalesce_done: TCP_SKB_CB(skb1)->end_seq); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFOMERGE); - __kfree_skb(skb1); + tcp_drop(sk, skb1); goto merge_right; } - } else if (tcp_try_coalesce(sk, skb1, - skb, &fragstolen)) { + } else if (tcp_ooo_try_coalesce(sk, skb1, + skb, &fragstolen)) { goto coalesce_done; } p = &parent->rb_right; @@ -4892,6 +4926,7 @@ end: static void tcp_collapse_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + u32 range_truesize, sum_tiny = 0; struct sk_buff *skb, *head; u32 start, end; @@ -4903,6 +4938,7 @@ new_range: } start = TCP_SKB_CB(skb)->seq; end = TCP_SKB_CB(skb)->end_seq; + range_truesize = skb->truesize; for (head = skb;;) { skb = skb_rb_next(skb); @@ -4913,11 +4949,20 @@ new_range: if (!skb || after(TCP_SKB_CB(skb)->seq, end) || before(TCP_SKB_CB(skb)->end_seq, start)) { - tcp_collapse(sk, NULL, &tp->out_of_order_queue, - head, skb, start, end); + /* Do not attempt collapsing tiny skbs */ + if (range_truesize != head->truesize || + end - start >= SKB_WITH_OVERHEAD(SK_MEM_QUANTUM)) { + tcp_collapse(sk, NULL, &tp->out_of_order_queue, + head, skb, start, end); + } else { + sum_tiny += range_truesize; + if (sum_tiny > sk->sk_rcvbuf >> 3) + return; + } goto new_range; } + range_truesize += skb->truesize; if (unlikely(before(TCP_SKB_CB(skb)->seq, start))) start = TCP_SKB_CB(skb)->seq; if (after(TCP_SKB_CB(skb)->end_seq, end)) @@ -4932,6 +4977,7 @@ new_range: * 2) not add too big latencies if thousands of packets sit there. * (But if application shrinks SO_RCVBUF, we could still end up * freeing whole queue here) + * 3) Drop at least 12.5 % of sk_rcvbuf to avoid malicious attacks. * * Return true if queue has shrunk. */ @@ -4939,20 +4985,26 @@ static bool tcp_prune_ofo_queue(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct rb_node *node, *prev; + int goal; if (RB_EMPTY_ROOT(&tp->out_of_order_queue)) return false; NET_INC_STATS(sock_net(sk), LINUX_MIB_OFOPRUNED); + goal = sk->sk_rcvbuf >> 3; node = &tp->ooo_last_skb->rbnode; do { prev = rb_prev(node); rb_erase(node, &tp->out_of_order_queue); + goal -= rb_to_skb(node)->truesize; tcp_drop(sk, rb_to_skb(node)); - sk_mem_reclaim(sk); - if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && - !tcp_under_memory_pressure(sk)) - break; + if (!prev || goal <= 0) { + sk_mem_reclaim(sk); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf && + !tcp_under_memory_pressure(sk)) + break; + goal = sk->sk_rcvbuf >> 3; + } node = prev; } while (node); tp->ooo_last_skb = rb_to_skb(prev); @@ -4987,6 +5039,9 @@ static int tcp_prune_queue(struct sock *sk) else if (tcp_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf) + return 0; + tcp_collapse_ofo_queue(sk); if (!skb_queue_empty(&sk->sk_receive_queue)) tcp_collapse(sk, &sk->sk_receive_queue, NULL, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index bea17f1e8302..3b2711e33e4c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -156,11 +156,24 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) */ if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; - tp->rx_opt.ts_recent = tcptw->tw_ts_recent; - tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + /* In case of repair and re-using TIME-WAIT sockets we still + * want to be sure that it is safe as above but honor the + * sequence numbers and time stamps set as part of the repair + * process. + * + * Without this check re-using a TIME-WAIT socket with TCP + * repair would accumulate a -1 on the repair assigned + * sequence number. The first time it is reused the sequence + * is -1, the second time -2, etc. This fixes that issue + * without appearing to create any others. + */ + if (likely(!tp->repair)) { + tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; + if (tp->write_seq == 0) + tp->write_seq = 1; + tp->rx_opt.ts_recent = tcptw->tw_ts_recent; + tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; + } sock_hold(sktw); return 1; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8e08b409c71e..c4172c1fb198 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -160,7 +160,8 @@ static void tcp_event_data_sent(struct tcp_sock *tp, } /* Account for an ACK we sent. */ -static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) +static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts, + u32 rcv_nxt) { struct tcp_sock *tp = tcp_sk(sk); @@ -171,6 +172,9 @@ static inline void tcp_event_ack_sent(struct sock *sk, unsigned int pkts) if (hrtimer_try_to_cancel(&tp->compressed_ack_timer) == 1) __sock_put(sk); } + + if (unlikely(rcv_nxt != tp->rcv_nxt)) + return; /* Special ACK sent by DCTCP to reflect ECN */ tcp_dec_quickack_mode(sk, pkts); inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } @@ -1023,8 +1027,8 @@ static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) * We are working here with either a clone of the original * SKB, or a fresh unique copy made by the retransmit engine. */ -static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, - gfp_t gfp_mask) +static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, + int clone_it, gfp_t gfp_mask, u32 rcv_nxt) { const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_sock *inet; @@ -1100,7 +1104,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->source = inet->inet_sport; th->dest = inet->inet_dport; th->seq = htonl(tcb->seq); - th->ack_seq = htonl(tp->rcv_nxt); + th->ack_seq = htonl(rcv_nxt); *(((__be16 *)th) + 6) = htons(((tcp_header_size >> 2) << 12) | tcb->tcp_flags); @@ -1141,7 +1145,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, icsk->icsk_af_ops->send_check(sk, skb); if (likely(tcb->tcp_flags & TCPHDR_ACK)) - tcp_event_ack_sent(sk, tcp_skb_pcount(skb)); + tcp_event_ack_sent(sk, tcp_skb_pcount(skb), rcv_nxt); if (skb->len != tcp_header_size) { tcp_event_data_sent(tp, sk); @@ -1178,6 +1182,13 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, return err; } +static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, + gfp_t gfp_mask) +{ + return __tcp_transmit_skb(sk, skb, clone_it, gfp_mask, + tcp_sk(sk)->rcv_nxt); +} + /* This routine just queues the buffer for sending. * * NOTE: probe0 timer is not checked, do not forget tcp_push_pending_frames, @@ -3523,8 +3534,6 @@ void tcp_send_delayed_ack(struct sock *sk) int ato = icsk->icsk_ack.ato; unsigned long timeout; - tcp_ca_event(sk, CA_EVENT_DELAYED_ACK); - if (ato > TCP_DELACK_MIN) { const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; @@ -3573,7 +3582,7 @@ void tcp_send_delayed_ack(struct sock *sk) } /* This routine sends an ack and also updates the window. */ -void tcp_send_ack(struct sock *sk) +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt) { struct sk_buff *buff; @@ -3581,8 +3590,6 @@ void tcp_send_ack(struct sock *sk) if (sk->sk_state == TCP_CLOSE) return; - tcp_ca_event(sk, CA_EVENT_NON_DELAYED_ACK); - /* We are not putting this on the write queue, so * tcp_transmit_skb() will set the ownership to this * sock. @@ -3608,9 +3615,14 @@ void tcp_send_ack(struct sock *sk) skb_set_tcp_pure_ack(buff); /* Send it off, this clears delayed acks for us. */ - tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0); + __tcp_transmit_skb(sk, buff, 0, (__force gfp_t)0, rcv_nxt); +} +EXPORT_SYMBOL_GPL(__tcp_send_ack); + +void tcp_send_ack(struct sock *sk) +{ + __tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt); } -EXPORT_SYMBOL_GPL(tcp_send_ack); /* This routine sends a packet with an out of date sequence * number. It assumes the other end will try to ack it. diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 92dc9e5a7ff3..69c54540d5b4 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -394,7 +394,7 @@ unflush: out_unlock: rcu_read_unlock(); out: - NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_flush_final(skb, pp, flush); return pp; } EXPORT_SYMBOL(udp_gro_receive); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 0eff75525da1..b3885ca22d6f 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -108,6 +108,7 @@ config IPV6_MIP6 config IPV6_ILA tristate "IPv6: Identifier Locator Addressing (ILA)" depends on NETFILTER + select DST_CACHE select LWTUNNEL ---help--- Support for IPv6 Identifier Locator Addressing (ILA). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c134286d6a41..f66a1cae3366 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2374,7 +2374,8 @@ static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, continue; if ((rt->fib6_flags & noflags) != 0) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -4528,6 +4529,7 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, u32 flags) { struct fib6_info *f6i; + u32 prio; f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, @@ -4536,13 +4538,15 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, if (!f6i) return -ENOENT; - if (f6i->fib6_metric != ifp->rt_priority) { + prio = ifp->rt_priority ? : IP6_RT_PRIO_ADDRCONF; + if (f6i->fib6_metric != prio) { + /* delete old one */ + ip6_del_rt(dev_net(ifp->idev->dev), f6i); + /* add new one */ addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); - /* delete old one */ - ip6_del_rt(dev_net(ifp->idev->dev), f6i); } else { if (!expires) fib6_clean_expires(f6i); diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 1323b9679cf7..1c0bb9fb76e6 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -799,8 +799,7 @@ static int calipso_opt_update(struct sock *sk, struct ipv6_opt_hdr *hop) { struct ipv6_txoptions *old = txopt_get(inet6_sk(sk)), *txopts; - txopts = ipv6_renew_options_kern(sk, old, IPV6_HOPOPTS, - hop, hop ? ipv6_optlen(hop) : 0); + txopts = ipv6_renew_options(sk, old, IPV6_HOPOPTS, hop); txopt_put(old); if (IS_ERR(txopts)) return PTR_ERR(txopts); @@ -1222,8 +1221,7 @@ static int calipso_req_setattr(struct request_sock *req, if (IS_ERR(new)) return PTR_ERR(new); - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); kfree(new); @@ -1260,8 +1258,7 @@ static void calipso_req_delattr(struct request_sock *req) if (calipso_opt_del(req_inet->ipv6_opt->hopopt, &new)) return; /* Nothing to do */ - txopts = ipv6_renew_options_kern(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, - new, new ? ipv6_optlen(new) : 0); + txopts = ipv6_renew_options(sk, req_inet->ipv6_opt, IPV6_HOPOPTS, new); if (!IS_ERR(txopts)) { txopts = xchg(&req_inet->ipv6_opt, txopts); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 2ee08b6a86a4..1a1f876f8e28 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -700,13 +700,16 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg, } if (np->rxopt.bits.rxorigdstaddr) { struct sockaddr_in6 sin6; - __be16 *ports = (__be16 *) skb_transport_header(skb); + __be16 *ports; + int end; - if (skb_transport_offset(skb) + 4 <= (int)skb->len) { + end = skb_transport_offset(skb) + 4; + if (end <= 0 || pskb_may_pull(skb, end)) { /* All current transport protocols have the port numbers in the * first four bytes of the transport header and this function is * written with this assumption in mind. */ + ports = (__be16 *)skb_transport_header(skb); sin6.sin6_family = AF_INET6; sin6.sin6_addr = ipv6_hdr(skb)->daddr; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index 97513f35bcc5..88a7579c23bd 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -669,8 +669,10 @@ skip_cow: sg_init_table(sg, nfrags); ret = skb_to_sgvec(skb, sg, 0, skb->len); - if (unlikely(ret < 0)) + if (unlikely(ret < 0)) { + kfree(tmp); goto out; + } skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 5bc2bf3733ab..20291c2036fc 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -1015,29 +1015,21 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt) } EXPORT_SYMBOL_GPL(ipv6_dup_options); -static int ipv6_renew_option(void *ohdr, - struct ipv6_opt_hdr __user *newopt, int newoptlen, - int inherit, - struct ipv6_opt_hdr **hdr, - char **p) +static void ipv6_renew_option(int renewtype, + struct ipv6_opt_hdr **dest, + struct ipv6_opt_hdr *old, + struct ipv6_opt_hdr *new, + int newtype, char **p) { - if (inherit) { - if (ohdr) { - memcpy(*p, ohdr, ipv6_optlen((struct ipv6_opt_hdr *)ohdr)); - *hdr = (struct ipv6_opt_hdr *)*p; - *p += CMSG_ALIGN(ipv6_optlen(*hdr)); - } - } else { - if (newopt) { - if (copy_from_user(*p, newopt, newoptlen)) - return -EFAULT; - *hdr = (struct ipv6_opt_hdr *)*p; - if (ipv6_optlen(*hdr) > newoptlen) - return -EINVAL; - *p += CMSG_ALIGN(newoptlen); - } - } - return 0; + struct ipv6_opt_hdr *src; + + src = (renewtype == newtype ? new : old); + if (!src) + return; + + memcpy(*p, src, ipv6_optlen(src)); + *dest = (struct ipv6_opt_hdr *)*p; + *p += CMSG_ALIGN(ipv6_optlen(*dest)); } /** @@ -1063,13 +1055,11 @@ static int ipv6_renew_option(void *ohdr, */ struct ipv6_txoptions * ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, - struct ipv6_opt_hdr __user *newopt, int newoptlen) + int newtype, struct ipv6_opt_hdr *newopt) { int tot_len = 0; char *p; struct ipv6_txoptions *opt2; - int err; if (opt) { if (newtype != IPV6_HOPOPTS && opt->hopopt) @@ -1082,8 +1072,8 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, tot_len += CMSG_ALIGN(ipv6_optlen(opt->dst1opt)); } - if (newopt && newoptlen) - tot_len += CMSG_ALIGN(newoptlen); + if (newopt) + tot_len += CMSG_ALIGN(ipv6_optlen(newopt)); if (!tot_len) return NULL; @@ -1098,29 +1088,19 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->tot_len = tot_len; p = (char *)(opt2 + 1); - err = ipv6_renew_option(opt ? opt->hopopt : NULL, newopt, newoptlen, - newtype != IPV6_HOPOPTS, - &opt2->hopopt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst0opt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDRDSTOPTS, - &opt2->dst0opt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->srcrt : NULL, newopt, newoptlen, - newtype != IPV6_RTHDR, - (struct ipv6_opt_hdr **)&opt2->srcrt, &p); - if (err) - goto out; - - err = ipv6_renew_option(opt ? opt->dst1opt : NULL, newopt, newoptlen, - newtype != IPV6_DSTOPTS, - &opt2->dst1opt, &p); - if (err) - goto out; + ipv6_renew_option(IPV6_HOPOPTS, &opt2->hopopt, + (opt ? opt->hopopt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDRDSTOPTS, &opt2->dst0opt, + (opt ? opt->dst0opt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_RTHDR, + (struct ipv6_opt_hdr **)&opt2->srcrt, + (opt ? (struct ipv6_opt_hdr *)opt->srcrt : NULL), + newopt, newtype, &p); + ipv6_renew_option(IPV6_DSTOPTS, &opt2->dst1opt, + (opt ? opt->dst1opt : NULL), + newopt, newtype, &p); opt2->opt_nflen = (opt2->hopopt ? ipv6_optlen(opt2->hopopt) : 0) + (opt2->dst0opt ? ipv6_optlen(opt2->dst0opt) : 0) + @@ -1128,37 +1108,6 @@ ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, opt2->opt_flen = (opt2->dst1opt ? ipv6_optlen(opt2->dst1opt) : 0); return opt2; -out: - sock_kfree_s(sk, opt2, opt2->tot_len); - return ERR_PTR(err); -} - -/** - * ipv6_renew_options_kern - replace a specific ext hdr with a new one. - * - * @sk: sock from which to allocate memory - * @opt: original options - * @newtype: option type to replace in @opt - * @newopt: new option of type @newtype to replace (kernel-mem) - * @newoptlen: length of @newopt - * - * See ipv6_renew_options(). The difference is that @newopt is - * kernel memory, rather than user memory. - */ -struct ipv6_txoptions * -ipv6_renew_options_kern(struct sock *sk, struct ipv6_txoptions *opt, - int newtype, struct ipv6_opt_hdr *newopt, - int newoptlen) -{ - struct ipv6_txoptions *ret_val; - const mm_segment_t old_fs = get_fs(); - - set_fs(KERNEL_DS); - ret_val = ipv6_renew_options(sk, opt, newtype, - (struct ipv6_opt_hdr __user *)newopt, - newoptlen); - set_fs(old_fs); - return ret_val; } struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index be491bf6ab6e..ef2505aefc15 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -402,9 +402,10 @@ static int icmp6_iif(const struct sk_buff *skb) /* for local traffic to local address, skb dev is the loopback * device. Check if there is a dst attached to the skb and if so - * get the real device index. + * get the real device index. Same is needed for replies to a link + * local address on a device enslaved to an L3 master device */ - if (unlikely(iif == LOOPBACK_IFINDEX)) { + if (unlikely(iif == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) { const struct rt6_info *rt6 = skb_rt6_info(skb); if (rt6) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1fb2f3118d60..d212738e9d10 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -935,20 +935,19 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, { struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&rt->fib6_table->tb6_lock)); - enum fib_event_type event = FIB_EVENT_ENTRY_ADD; - struct fib6_info *iter = NULL, *match = NULL; + struct fib6_info *iter = NULL; struct fib6_info __rcu **ins; + struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); - int append = (info->nlh && - (info->nlh->nlmsg_flags & NLM_F_APPEND)); int add = (!info->nlh || (info->nlh->nlmsg_flags & NLM_F_CREATE)); int found = 0; + bool rt_can_ecmp = rt6_qualify_for_ecmp(rt); u16 nlflags = NLM_F_EXCL; int err; - if (append) + if (info->nlh && (info->nlh->nlmsg_flags & NLM_F_APPEND)) nlflags |= NLM_F_APPEND; ins = &fn->leaf; @@ -970,8 +969,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, nlflags &= ~NLM_F_EXCL; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (rt6_duplicate_nexthop(iter, rt)) { @@ -986,51 +990,71 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } - - /* first route that matches */ - if (!match) - match = iter; + /* If we have the same destination and the same metric, + * but not the same gateway, then the route we try to + * add is sibling to this route, increment our counter + * of siblings, and later we will add our route to the + * list. + * Only static routes (which don't have flag + * RTF_EXPIRES) are used for ECMPv6. + * + * To avoid long list, we only had siblings if the + * route have a gateway. + */ + if (rt_can_ecmp && + rt6_qualify_for_ecmp(iter)) + rt->fib6_nsiblings++; } if (iter->fib6_metric > rt->fib6_metric) break; +next_iter: ins = &iter->fib6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; /* Link this route to others same route. */ - if (append && match) { + if (rt->fib6_nsiblings) { + unsigned int fib6_nsiblings; struct fib6_info *sibling, *temp_sibling; - if (rt->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append a REJECT route"); - return -EINVAL; - } else if (match->fib6_flags & RTF_REJECT) { - NL_SET_ERR_MSG(extack, - "Can not append to a REJECT route"); - return -EINVAL; + /* Find the first route that have the same metric */ + sibling = leaf; + while (sibling) { + if (sibling->fib6_metric == rt->fib6_metric && + rt6_qualify_for_ecmp(sibling)) { + list_add_tail(&rt->fib6_siblings, + &sibling->fib6_siblings); + break; + } + sibling = rcu_dereference_protected(sibling->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } - event = FIB_EVENT_ENTRY_APPEND; - rt->fib6_nsiblings = match->fib6_nsiblings; - list_add_tail(&rt->fib6_siblings, &match->fib6_siblings); - match->fib6_nsiblings++; - /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ + fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, - &match->fib6_siblings, fib6_siblings) { + &rt->fib6_siblings, fib6_siblings) { sibling->fib6_nsiblings++; - BUG_ON(sibling->fib6_nsiblings != match->fib6_nsiblings); + BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); + fib6_nsiblings++; } - - rt6_multipath_rebalance(match); + BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); + rt6_multipath_rebalance(temp_sibling); } /* @@ -1043,8 +1067,9 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, add: nlflags |= NLM_F_CREATE; - err = call_fib6_entry_notifiers(info->nl_net, event, rt, - extack); + err = call_fib6_entry_notifiers(info->nl_net, + FIB_EVENT_ENTRY_ADD, + rt, extack); if (err) return err; @@ -1062,7 +1087,7 @@ add: } } else { - struct fib6_info *tmp; + int nsiblings; if (!found) { if (add) @@ -1077,57 +1102,48 @@ add: if (err) return err; - /* if route being replaced has siblings, set tmp to - * last one, otherwise tmp is current route. this is - * used to set fib6_next for new route - */ - if (iter->fib6_nsiblings) - tmp = list_last_entry(&iter->fib6_siblings, - struct fib6_info, - fib6_siblings); - else - tmp = iter; - - /* insert new route */ atomic_inc(&rt->fib6_ref); rcu_assign_pointer(rt->fib6_node, fn); - rt->fib6_next = tmp->fib6_next; + rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); - if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); if (!(fn->fn_flags & RTN_RTINFO)) { info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->fib6_nsiblings; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); - /* delete old route */ - rt = iter; - - if (rt->fib6_nsiblings) { - struct fib6_info *tmp; - + if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ - list_for_each_entry_safe(iter, tmp, &rt->fib6_siblings, - fib6_siblings) { - iter->fib6_node = NULL; - fib6_purge_rt(iter, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == iter) - fn->rr_ptr = NULL; - fib6_info_release(iter); - - rt->fib6_nsiblings--; - info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + ins = &rt->fib6_next; + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + while (iter) { + if (iter->fib6_metric > rt->fib6_metric) + break; + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->fib6_next; + iter->fib6_node = NULL; + fib6_purge_rt(iter, fn, info->nl_net); + if (rcu_access_pointer(fn->rr_ptr) == iter) + fn->rr_ptr = NULL; + fib6_info_release(iter); + nsiblings--; + info->nl_net->ipv6.rt6_stats->fib_rt_entries--; + } else { + ins = &iter->fib6_next; + } + iter = rcu_dereference_protected(*ins, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } + WARN_ON(nsiblings != 0); } - - WARN_ON(rt->fib6_nsiblings != 0); - - rt->fib6_node = NULL; - fib6_purge_rt(rt, fn, info->nl_net); - if (rcu_access_pointer(fn->rr_ptr) == rt) - fn->rr_ptr = NULL; - fib6_info_release(rt); } return 0; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index c8cf2fdbb13b..cd2cfb04e5d8 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -927,7 +927,6 @@ tx_err: static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { - struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct ip6_tnl *t = netdev_priv(dev); struct dst_entry *dst = skb_dst(skb); struct net_device_stats *stats; @@ -1010,6 +1009,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; } } else { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + switch (skb->protocol) { case htons(ETH_P_IP): memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index a14fb4fcdf18..3168847c30d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -570,6 +570,8 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->dev = from->dev; to->mark = from->mark; + skb_copy_hash(to, from); + #ifdef CONFIG_NET_SCHED to->tc_index = from->tc_index; #endif diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index b7f28deddaea..c72ae3a4fe09 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -480,10 +480,6 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) goto tx_err_dst_release; } - skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); - skb_dst_set(skb, dst); - skb->dev = skb_dst(skb)->dev; - mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { skb_dst_update_pmtu(skb, mtu); @@ -498,9 +494,14 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) htonl(mtu)); } - return -EMSGSIZE; + err = -EMSGSIZE; + goto tx_err_dst_release; } + skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); + skb_dst_set(skb, dst); + skb->dev = skb_dst(skb)->dev; + err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4d780c7f0130..568ca4187cd1 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -398,6 +398,12 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + struct ipv6_opt_hdr *new = NULL; + + /* hop-by-hop / destination options are privileged option */ + retv = -EPERM; + if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) + break; /* remove any sticky options header with a zero option * length, per RFC3542. @@ -409,17 +415,22 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, else if (optlen < sizeof(struct ipv6_opt_hdr) || optlen & 0x7 || optlen > 8 * 255) goto e_inval; - - /* hop-by-hop / destination options are privileged option */ - retv = -EPERM; - if (optname != IPV6_RTHDR && !ns_capable(net->user_ns, CAP_NET_RAW)) - break; + else { + new = memdup_user(optval, optlen); + if (IS_ERR(new)) { + retv = PTR_ERR(new); + break; + } + if (unlikely(ipv6_optlen(new) > optlen)) { + kfree(new); + goto e_inval; + } + } opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); - opt = ipv6_renew_options(sk, opt, optname, - (struct ipv6_opt_hdr __user *)optval, - optlen); + opt = ipv6_renew_options(sk, opt, optname, new); + kfree(new); if (IS_ERR(opt)) { retv = PTR_ERR(opt); break; @@ -718,8 +729,9 @@ done: struct sockaddr_in6 *psin6; psin6 = (struct sockaddr_in6 *)&greqs.gsr_group; - retv = ipv6_sock_mc_join(sk, greqs.gsr_interface, - &psin6->sin6_addr); + retv = ipv6_sock_mc_join_ssm(sk, greqs.gsr_interface, + &psin6->sin6_addr, + MCAST_INCLUDE); /* prior join w/ different source is ok */ if (retv && retv != -EADDRINUSE) break; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index c0c74088f2af..f60f310785fd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -95,6 +95,8 @@ static int ip6_mc_add_src(struct inet6_dev *idev, const struct in6_addr *pmca, int delta); static int ip6_mc_leave_src(struct sock *sk, struct ipv6_mc_socklist *iml, struct inet6_dev *idev); +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode); #define MLD_QRV_DEFAULT 2 /* RFC3810, 9.2. Query Interval */ @@ -132,7 +134,8 @@ static int unsolicited_report_interval(struct inet6_dev *idev) return iv > 0 ? iv : 1; } -int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +static int __ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) { struct net_device *dev = NULL; struct ipv6_mc_socklist *mc_lst; @@ -179,7 +182,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) } mc_lst->ifindex = dev->ifindex; - mc_lst->sfmode = MCAST_EXCLUDE; + mc_lst->sfmode = mode; rwlock_init(&mc_lst->sflock); mc_lst->sflist = NULL; @@ -187,7 +190,7 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) * now add/increase the group membership on the device */ - err = ipv6_dev_mc_inc(dev, addr); + err = __ipv6_dev_mc_inc(dev, addr, mode); if (err) { sock_kfree_s(sk, mc_lst, sizeof(*mc_lst)); @@ -199,8 +202,19 @@ int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } + +int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, MCAST_EXCLUDE); +} EXPORT_SYMBOL(ipv6_sock_mc_join); +int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, + const struct in6_addr *addr, unsigned int mode) +{ + return __ipv6_sock_mc_join(sk, ifindex, addr, mode); +} + /* * socket leave on multicast group */ @@ -646,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, return rv; } -static void igmp6_group_added(struct ifmcaddr6 *mc) +static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode) { struct net_device *dev = mc->idev->dev; char buf[MAX_ADDR_LEN]; @@ -672,7 +686,13 @@ static void igmp6_group_added(struct ifmcaddr6 *mc) } /* else v2 */ - mc->mca_crcount = mc->idev->mc_qrv; + /* Based on RFC3810 6.1, for newly added INCLUDE SSM, we + * should not send filter-mode change record as the mode + * should be from IN() to IN(A). + */ + if (mode == MCAST_EXCLUDE) + mc->mca_crcount = mc->idev->mc_qrv; + mld_ifc_event(mc->idev); } @@ -770,13 +790,13 @@ static void mld_del_delrec(struct inet6_dev *idev, struct ifmcaddr6 *im) spin_lock_bh(&im->mca_lock); if (pmc) { im->idev = pmc->idev; - im->mca_crcount = idev->mc_qrv; - im->mca_sfmode = pmc->mca_sfmode; - if (pmc->mca_sfmode == MCAST_INCLUDE) { + if (im->mca_sfmode == MCAST_INCLUDE) { im->mca_tomb = pmc->mca_tomb; im->mca_sources = pmc->mca_sources; for (psf = im->mca_sources; psf; psf = psf->sf_next) - psf->sf_crcount = im->mca_crcount; + psf->sf_crcount = idev->mc_qrv; + } else { + im->mca_crcount = idev->mc_qrv; } in6_dev_put(pmc->idev); kfree(pmc); @@ -831,7 +851,8 @@ static void ma_put(struct ifmcaddr6 *mc) } static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, - const struct in6_addr *addr) + const struct in6_addr *addr, + unsigned int mode) { struct ifmcaddr6 *mc; @@ -849,9 +870,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, refcount_set(&mc->mca_refcnt, 1); spin_lock_init(&mc->mca_lock); - /* initial mode is (EX, empty) */ - mc->mca_sfmode = MCAST_EXCLUDE; - mc->mca_sfcount[MCAST_EXCLUDE] = 1; + mc->mca_sfmode = mode; + mc->mca_sfcount[mode] = 1; if (ipv6_addr_is_ll_all_nodes(&mc->mca_addr) || IPV6_ADDR_MC_SCOPE(&mc->mca_addr) < IPV6_ADDR_SCOPE_LINKLOCAL) @@ -863,7 +883,8 @@ static struct ifmcaddr6 *mca_alloc(struct inet6_dev *idev, /* * device multicast group inc (add if not found) */ -int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +static int __ipv6_dev_mc_inc(struct net_device *dev, + const struct in6_addr *addr, unsigned int mode) { struct ifmcaddr6 *mc; struct inet6_dev *idev; @@ -887,14 +908,13 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) if (ipv6_addr_equal(&mc->mca_addr, addr)) { mc->mca_users++; write_unlock_bh(&idev->lock); - ip6_mc_add_src(idev, &mc->mca_addr, MCAST_EXCLUDE, 0, - NULL, 0); + ip6_mc_add_src(idev, &mc->mca_addr, mode, 0, NULL, 0); in6_dev_put(idev); return 0; } } - mc = mca_alloc(idev, addr); + mc = mca_alloc(idev, addr, mode); if (!mc) { write_unlock_bh(&idev->lock); in6_dev_put(idev); @@ -911,11 +931,16 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); mld_del_delrec(idev, mc); - igmp6_group_added(mc); + igmp6_group_added(mc, mode); ma_put(mc); return 0; } +int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) +{ + return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); +} + /* * device multicast group del */ @@ -1751,7 +1776,7 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ifmcaddr6 *pmc, psf_next = psf->sf_next; - if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { + if (!is_in(pmc, psf, type, gdeleted, sdeleted) && !crsend) { psf_prev = psf; continue; } @@ -2066,7 +2091,7 @@ static void mld_send_initial_cr(struct inet6_dev *idev) if (pmc->mca_sfcount[MCAST_EXCLUDE]) type = MLD2_CHANGE_TO_EXCLUDE; else - type = MLD2_CHANGE_TO_INCLUDE; + type = MLD2_ALLOW_NEW_SOURCES; skb = add_grec(skb, pmc, type, 0, 0, 1); spin_unlock_bh(&pmc->mca_lock); } @@ -2546,7 +2571,7 @@ void ipv6_mc_up(struct inet6_dev *idev) ipv6_mc_reset(idev); for (i = idev->mc_list; i; i = i->next) { mld_del_delrec(idev, i); - igmp6_group_added(i); + igmp6_group_added(i, i->mca_sfmode); } read_unlock_bh(&idev->lock); } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index e640d2f3c55c..0ec273997d1d 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -811,7 +811,7 @@ static void ndisc_recv_ns(struct sk_buff *skb) return; } } - if (ndopts.nd_opts_nonce) + if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1) memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6); inc = ipv6_addr_is_multicast(daddr); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7eab959734bc..daf2e9e9193d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1909,6 +1909,7 @@ static struct xt_match ip6t_builtin_mt[] __read_mostly = { .checkentry = icmp6_checkentry, .proto = IPPROTO_ICMPV6, .family = NFPROTO_IPV6, + .me = THIS_MODULE, }, }; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 5e0332014c17..e4d9e6976d3c 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -107,7 +107,7 @@ static int nf_ct_frag6_sysctl_register(struct net *net) if (hdr == NULL) goto err_reg; - net->nf_frag.sysctl.frags_hdr = hdr; + net->nf_frag_frags_hdr = hdr; return 0; err_reg: @@ -121,8 +121,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) { struct ctl_table *table; - table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg; - unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr); + table = net->nf_frag_frags_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->nf_frag_frags_hdr); if (!net_eq(net, &init_net)) kfree(table); } @@ -585,6 +585,8 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) fq->q.meat == fq->q.len && nf_ct_frag6_reasm(fq, skb, dev)) ret = 0; + else + skb_dst_drop(skb); out_unlock: spin_unlock_bh(&fq->q.lock); diff --git a/net/ipv6/netfilter/nf_tproxy_ipv6.c b/net/ipv6/netfilter/nf_tproxy_ipv6.c index bf1d6c421e3b..5dfd33af6451 100644 --- a/net/ipv6/netfilter/nf_tproxy_ipv6.c +++ b/net/ipv6/netfilter/nf_tproxy_ipv6.c @@ -55,7 +55,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, * to a listener socket if there's one */ struct sock *sk2; - sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, hp, tproto, + sk2 = nf_tproxy_get_sock_v6(net, skb, thoff, tproto, &iph->saddr, nf_tproxy_laddr6(skb, laddr, &iph->daddr), hp->source, @@ -72,7 +72,7 @@ nf_tproxy_handle_time_wait6(struct sk_buff *skb, int tproto, int thoff, EXPORT_SYMBOL_GPL(nf_tproxy_handle_time_wait6); struct sock * -nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, +nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, const u8 protocol, const struct in6_addr *saddr, const struct in6_addr *daddr, const __be16 sport, const __be16 dport, @@ -80,15 +80,20 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, const enum nf_tproxy_lookup_t lookup_type) { struct sock *sk; - struct tcphdr *tcph; switch (protocol) { - case IPPROTO_TCP: + case IPPROTO_TCP: { + struct tcphdr _hdr, *hp; + + hp = skb_header_pointer(skb, thoff, + sizeof(struct tcphdr), &_hdr); + if (hp == NULL) + return NULL; + switch (lookup_type) { case NF_TPROXY_LOOKUP_LISTENER: - tcph = hp; sk = inet6_lookup_listener(net, &tcp_hashinfo, skb, - thoff + __tcp_hdrlen(tcph), + thoff + __tcp_hdrlen(hp), saddr, sport, daddr, ntohs(dport), in->ifindex, 0); @@ -110,6 +115,7 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp, BUG(); } break; + } case IPPROTO_UDP: sk = udp6_lib_lookup(net, saddr, sport, daddr, dport, in->ifindex); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 86a0e4333d42..ec18b3ce8b6d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -972,10 +972,10 @@ static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) rt->dst.lastuse = jiffies; } +/* Caller must already hold reference to @from */ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) { rt->rt6i_flags &= ~RTF_EXPIRES; - fib6_info_hold(from); rcu_assign_pointer(rt->from, from); dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); if (from->fib6_metrics != &dst_default_metrics) { @@ -984,6 +984,7 @@ static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) } } +/* Caller must already hold reference to @ort */ static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) { struct net_device *dev = fib6_info_nh_dev(ort); @@ -1044,9 +1045,14 @@ static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) struct net_device *dev = rt->fib6_nh.nh_dev; struct rt6_info *nrt; + if (!fib6_info_hold_safe(rt)) + return NULL; + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); if (nrt) ip6_rt_copy_init(nrt, rt); + else + fib6_info_release(rt); return nrt; } @@ -1178,10 +1184,15 @@ static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, * Clone the route. */ + if (!fib6_info_hold_safe(ort)) + return NULL; + dev = ip6_rt_get_dev_rcu(ort); rt = ip6_dst_alloc(dev_net(dev), dev, 0); - if (!rt) + if (!rt) { + fib6_info_release(ort); return NULL; + } ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; @@ -1210,12 +1221,17 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) struct net_device *dev; struct rt6_info *pcpu_rt; + if (!fib6_info_hold_safe(rt)) + return NULL; + rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); - if (!pcpu_rt) + if (!pcpu_rt) { + fib6_info_release(rt); return NULL; + } ip6_rt_copy_init(pcpu_rt, rt); pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; @@ -2486,7 +2502,7 @@ restart: out: if (ret) - dst_hold(&ret->dst); + ip6_hold_safe(net, &ret, true); else ret = ip6_create_rt_rcu(rt); @@ -3303,7 +3319,8 @@ static int ip6_route_del(struct fib6_config *cfg, continue; if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3409,6 +3426,9 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu rcu_read_lock(); from = rcu_dereference(rt->from); + /* This fib6_info_hold() is safe here because we hold reference to rt + * and rt already holds reference to fib6_info. + */ fib6_info_hold(from); rcu_read_unlock(); @@ -3470,7 +3490,8 @@ static struct fib6_info *rt6_get_route_info(struct net *net, continue; if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - fib6_info_hold(rt); + if (!fib6_info_hold_safe(rt)) + continue; break; } out: @@ -3530,8 +3551,8 @@ struct fib6_info *rt6_get_dflt_router(struct net *net, ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } - if (rt) - fib6_info_hold(rt); + if (rt && !fib6_info_hold_safe(rt)) + rt = NULL; rcu_read_unlock(); return rt; } @@ -3579,8 +3600,8 @@ restart: struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!idev || idev->cnf.accept_ra != 2)) { - fib6_info_hold(rt); + (!idev || idev->cnf.accept_ra != 2) && + fib6_info_hold_safe(rt)) { rcu_read_unlock(); ip6_del_rt(net, rt); goto restart; @@ -3842,7 +3863,7 @@ static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { if (iter->fib6_metric == rt->fib6_metric && - iter->fib6_nsiblings) + rt6_qualify_for_ecmp(iter)) return iter; iter = rcu_dereference_protected(iter->fib6_next, lockdep_is_held(&rt->fib6_table->tb6_lock)); @@ -4388,6 +4409,13 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, rt = NULL; goto cleanup; } + if (!rt6_qualify_for_ecmp(rt)) { + err = -EINVAL; + NL_SET_ERR_MSG(extack, + "Device only routes can not be added for IPv6 using the multipath API."); + fib6_info_release(rt); + goto cleanup; + } rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1; @@ -4439,7 +4467,6 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); - cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND; nhn++; } diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 33fb35cbfac1..558fe8cc6d43 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -373,7 +373,7 @@ static int seg6_hmac_init_algo(void) return -ENOMEM; for_each_possible_cpu(cpu) { - tfm = crypto_alloc_shash(algo->name, 0, GFP_KERNEL); + tfm = crypto_alloc_shash(algo->name, 0, 0); if (IS_ERR(tfm)) return PTR_ERR(tfm); p_tfm = per_cpu_ptr(algo->tfms, cpu); diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 19ccf0dc996c..a8854dd3e9c5 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -101,7 +101,7 @@ static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, if (do_flowlabel > 0) { hash = skb_get_hash(skb); - rol32(hash, 16); + hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { flowlabel = ip6_flowlabel(inner_hdr); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7efa9fd7e109..03e6b7a2bc53 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -938,7 +938,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) &tcp_hashinfo, NULL, 0, &ipv6h->saddr, th->source, &ipv6h->daddr, - ntohs(th->source), tcp_v6_iif(skb), + ntohs(th->source), + tcp_v6_iif_l3_slave(skb), tcp_v6_sdif(skb)); if (!sk1) goto out; @@ -1609,7 +1610,8 @@ do_time_wait: skb, __tcp_hdrlen(th), &ipv6_hdr(skb)->saddr, th->source, &ipv6_hdr(skb)->daddr, - ntohs(th->dest), tcp_v6_iif(skb), + ntohs(th->dest), + tcp_v6_iif_l3_slave(skb), sdif); if (sk2) { struct inet_timewait_sock *tw = inet_twsk(sk); diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index e398797878a9..cf6cca260e7b 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1201,13 +1201,18 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel, l2tp_session_get(sock_net(sk), tunnel, stats.session_id); - if (session && session->pwtype == L2TP_PWTYPE_PPP) { - err = pppol2tp_session_ioctl(session, cmd, - arg); + if (!session) { + err = -EBADR; + break; + } + if (session->pwtype != L2TP_PWTYPE_PPP) { l2tp_session_dec_refcount(session); - } else { err = -EBADR; + break; } + + err = pppol2tp_session_ioctl(session, cmd, arg); + l2tp_session_dec_refcount(session); break; } #ifdef CONFIG_XFRM diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 0a38cc1cbebc..932985ca4e66 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -2254,11 +2254,8 @@ static void ieee80211_deliver_skb_to_local_stack(struct sk_buff *skb, sdata->control_port_over_nl80211)) { struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); bool noencrypt = status->flag & RX_FLAG_DECRYPTED; - struct ethhdr *ehdr = eth_hdr(skb); - cfg80211_rx_control_port(dev, skb->data, skb->len, - ehdr->h_source, - be16_to_cpu(skb->protocol), noencrypt); + cfg80211_rx_control_port(dev, skb, noencrypt); dev_kfree_skb(skb); } else { /* deliver to local stack */ diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 44b5dfe8727d..fa1f1e63a264 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -4845,7 +4845,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_reset_network_header(skb); skb_reset_mac_header(skb); + local_bh_disable(); __ieee80211_subif_start_xmit(skb, skb->dev, flags); + local_bh_enable(); return 0; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 5e2e511c4a6f..d02fbfec3783 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -2111,7 +2111,8 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (!sta->uploaded) continue; - if (sta->sdata->vif.type != NL80211_IFTYPE_AP) + if (sta->sdata->vif.type != NL80211_IFTYPE_AP && + sta->sdata->vif.type != NL80211_IFTYPE_AP_VLAN) continue; for (state = IEEE80211_STA_NOTEXIST; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index dbd7d1fad277..f0a1c536ef15 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -460,6 +460,13 @@ config NF_TABLES if NF_TABLES +config NF_TABLES_SET + tristate "Netfilter nf_tables set infrastructure" + help + This option enables the nf_tables set infrastructure that allows to + look up for elements in a set and to build one-way mappings between + matchings and actions. + config NF_TABLES_INET depends on IPV6 select NF_TABLES_IPV4 @@ -493,24 +500,6 @@ config NFT_FLOW_OFFLOAD This option adds the "flow_offload" expression that you can use to choose what flows are placed into the hardware. -config NFT_SET_RBTREE - tristate "Netfilter nf_tables rbtree set module" - help - This option adds the "rbtree" set type (Red Black tree) that is used - to build interval-based sets. - -config NFT_SET_HASH - tristate "Netfilter nf_tables hash set module" - help - This option adds the "hash" set type that is used to build one-way - mappings between matchings and actions. - -config NFT_SET_BITMAP - tristate "Netfilter nf_tables bitmap set module" - help - This option adds the "bitmap" set type that is used to build sets - whose keys are smaller or equal to 16 bits. - config NFT_COUNTER tristate "Netfilter nf_tables counter module" help diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 44449389e527..8a76dced974d 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -78,7 +78,11 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o +nf_tables_set-objs := nf_tables_set_core.o \ + nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o + obj-$(CONFIG_NF_TABLES) += nf_tables.o +obj-$(CONFIG_NF_TABLES_SET) += nf_tables_set.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o obj-$(CONFIG_NFT_CONNLIMIT) += nft_connlimit.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o @@ -91,9 +95,6 @@ obj-$(CONFIG_NFT_QUEUE) += nft_queue.o obj-$(CONFIG_NFT_QUOTA) += nft_quota.o obj-$(CONFIG_NFT_REJECT) += nft_reject.o obj-$(CONFIG_NFT_REJECT_INET) += nft_reject_inet.o -obj-$(CONFIG_NFT_SET_RBTREE) += nft_set_rbtree.o -obj-$(CONFIG_NFT_SET_HASH) += nft_set_hash.o -obj-$(CONFIG_NFT_SET_BITMAP) += nft_set_bitmap.o obj-$(CONFIG_NFT_COUNTER) += nft_counter.o obj-$(CONFIG_NFT_LOG) += nft_log.o obj-$(CONFIG_NFT_MASQ) += nft_masq.o diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c index d8383609fe28..510039862aa9 100644 --- a/net/netfilter/nf_conncount.c +++ b/net/netfilter/nf_conncount.c @@ -47,6 +47,8 @@ struct nf_conncount_tuple { struct hlist_node node; struct nf_conntrack_tuple tuple; struct nf_conntrack_zone zone; + int cpu; + u32 jiffies32; }; struct nf_conncount_rb { @@ -91,11 +93,42 @@ bool nf_conncount_add(struct hlist_head *head, return false; conn->tuple = *tuple; conn->zone = *zone; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; hlist_add_head(&conn->node, head); return true; } EXPORT_SYMBOL_GPL(nf_conncount_add); +static const struct nf_conntrack_tuple_hash * +find_or_evict(struct net *net, struct nf_conncount_tuple *conn) +{ + const struct nf_conntrack_tuple_hash *found; + unsigned long a, b; + int cpu = raw_smp_processor_id(); + __s32 age; + + found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); + if (found) + return found; + b = conn->jiffies32; + a = (u32)jiffies; + + /* conn might have been added just before by another cpu and + * might still be unconfirmed. In this case, nf_conntrack_find() + * returns no result. Thus only evict if this cpu added the + * stale entry or if the entry is older than two jiffies. + */ + age = a - b; + if (conn->cpu == cpu || age >= 2) { + hlist_del(&conn->node); + kmem_cache_free(conncount_conn_cachep, conn); + return ERR_PTR(-ENOENT); + } + + return ERR_PTR(-EAGAIN); +} + unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, const struct nf_conntrack_tuple *tuple, const struct nf_conntrack_zone *zone, @@ -103,18 +136,27 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head, { const struct nf_conntrack_tuple_hash *found; struct nf_conncount_tuple *conn; - struct hlist_node *n; struct nf_conn *found_ct; + struct hlist_node *n; unsigned int length = 0; *addit = tuple ? true : false; /* check the saved connections */ hlist_for_each_entry_safe(conn, n, head, node) { - found = nf_conntrack_find_get(net, &conn->zone, &conn->tuple); - if (found == NULL) { - hlist_del(&conn->node); - kmem_cache_free(conncount_conn_cachep, conn); + found = find_or_evict(net, conn); + if (IS_ERR(found)) { + /* Not found, but might be about to be confirmed */ + if (PTR_ERR(found) == -EAGAIN) { + length++; + if (!tuple) + continue; + + if (nf_ct_tuple_equal(&conn->tuple, tuple) && + nf_ct_zone_id(&conn->zone, conn->zone.dir) == + nf_ct_zone_id(zone, zone->dir)) + *addit = false; + } continue; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3465da2a98bd..3d5280425027 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -2043,7 +2043,7 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp) return -EOPNOTSUPP; /* On boot, we can set this without any fancy locking. */ - if (!nf_conntrack_htable_size) + if (!nf_conntrack_hash) return param_set_uint(val, kp); rc = kstrtouint(val, 0, &hashsize); diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 551a1eddf0fa..a75b11c39312 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -465,6 +465,11 @@ void nf_conntrack_helper_unregister(struct nf_conntrack_helper *me) nf_ct_expect_iterate_destroy(expect_iter_me, NULL); nf_ct_iterate_destroy(unhelp, me); + + /* Maybe someone has gotten the helper already when unhelp above. + * So need to wait it. + */ + synchronize_rcu(); } EXPORT_SYMBOL_GPL(nf_conntrack_helper_unregister); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index abe647d5b8c6..9ce6336d1e55 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -243,14 +243,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, [CT_DCCP_ROLE_SERVER] = { @@ -371,14 +371,14 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = * We currently ignore Sync packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, [DCCP_PKT_SYNCACK] = { /* * We currently ignore SyncAck packets * * sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */ - sIG, sIG, sIG, sIG, sIG, sIG, sIG, sIG, + sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, }, }, }; diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 426457047578..a61d6df6e5f6 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -424,6 +424,10 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, if (write) { struct ctl_table tmp = *table; + /* proc_dostring() can append to existing strings, so we need to + * initialize it as an empty string. + */ + buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) @@ -442,14 +446,17 @@ static int nf_log_proc_dostring(struct ctl_table *table, int write, rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { + struct ctl_table tmp = *table; + + tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) - table->data = "NONE"; + strlcpy(buf, "NONE", sizeof(buf)); else - table->data = logger->name; - r = proc_dostring(table, write, buffer, lenp, ppos); + strlcpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); + r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 896d4a36081d..f5745e4c6513 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -75,6 +75,7 @@ static void nft_ctx_init(struct nft_ctx *ctx, { ctx->net = net; ctx->family = family; + ctx->level = 0; ctx->table = table; ctx->chain = chain; ctx->nla = nla; @@ -1597,7 +1598,6 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, struct nft_base_chain *basechain; struct nft_stats *stats = NULL; struct nft_chain_hook hook; - const struct nlattr *name; struct nf_hook_ops *ops; struct nft_trans *trans; int err; @@ -1645,12 +1645,11 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, return PTR_ERR(stats); } + err = -ENOMEM; trans = nft_trans_alloc(ctx, NFT_MSG_NEWCHAIN, sizeof(struct nft_trans_chain)); - if (trans == NULL) { - free_percpu(stats); - return -ENOMEM; - } + if (trans == NULL) + goto err; nft_trans_chain_stats(trans) = stats; nft_trans_chain_update(trans) = true; @@ -1660,19 +1659,37 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, else nft_trans_chain_policy(trans) = -1; - name = nla[NFTA_CHAIN_NAME]; - if (nla[NFTA_CHAIN_HANDLE] && name) { - nft_trans_chain_name(trans) = - nla_strdup(name, GFP_KERNEL); - if (!nft_trans_chain_name(trans)) { - kfree(trans); - free_percpu(stats); - return -ENOMEM; + if (nla[NFTA_CHAIN_HANDLE] && + nla[NFTA_CHAIN_NAME]) { + struct nft_trans *tmp; + char *name; + + err = -ENOMEM; + name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); + if (!name) + goto err; + + err = -EEXIST; + list_for_each_entry(tmp, &ctx->net->nft.commit_list, list) { + if (tmp->msg_type == NFT_MSG_NEWCHAIN && + tmp->ctx.table == table && + nft_trans_chain_update(tmp) && + nft_trans_chain_name(tmp) && + strcmp(name, nft_trans_chain_name(tmp)) == 0) { + kfree(name); + goto err; + } } + + nft_trans_chain_name(trans) = name; } list_add_tail(&trans->list, &ctx->net->nft.commit_list); return 0; +err: + free_percpu(stats); + kfree(trans); + return err; } static int nf_tables_newchain(struct net *net, struct sock *nlsk, @@ -2254,6 +2271,39 @@ done: return skb->len; } +static int nf_tables_dump_rules_start(struct netlink_callback *cb) +{ + const struct nlattr * const *nla = cb->data; + struct nft_rule_dump_ctx *ctx = NULL; + + if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) + return -ENOMEM; + + if (nla[NFTA_RULE_TABLE]) { + ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], + GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); + return -ENOMEM; + } + } + if (nla[NFTA_RULE_CHAIN]) { + ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], + GFP_ATOMIC); + if (!ctx->chain) { + kfree(ctx->table); + kfree(ctx); + return -ENOMEM; + } + } + } + + cb->data = ctx; + return 0; +} + static int nf_tables_dump_rules_done(struct netlink_callback *cb) { struct nft_rule_dump_ctx *ctx = cb->data; @@ -2283,38 +2333,13 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start= nf_tables_dump_rules_start, .dump = nf_tables_dump_rules, .done = nf_tables_dump_rules_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_RULE_TABLE] || nla[NFTA_RULE_CHAIN]) { - struct nft_rule_dump_ctx *ctx; - - ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; - - if (nla[NFTA_RULE_TABLE]) { - ctx->table = nla_strdup(nla[NFTA_RULE_TABLE], - GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); - return -ENOMEM; - } - } - if (nla[NFTA_RULE_CHAIN]) { - ctx->chain = nla_strdup(nla[NFTA_RULE_CHAIN], - GFP_ATOMIC); - if (!ctx->chain) { - kfree(ctx->table); - kfree(ctx); - return -ENOMEM; - } - } - c.data = ctx; - } - return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -2384,6 +2409,9 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) struct nft_rule *rule; int err; + if (ctx->level == NFT_JUMP_STACK_SIZE) + return -EMLINK; + list_for_each_entry(rule, &chain->rules, list) { if (!nft_is_active_next(ctx->net, rule)) continue; @@ -3161,6 +3189,18 @@ done: return skb->len; } +static int nf_tables_dump_sets_start(struct netlink_callback *cb) +{ + struct nft_ctx *ctx_dump = NULL; + + ctx_dump = kmemdup(cb->data, sizeof(*ctx_dump), GFP_ATOMIC); + if (ctx_dump == NULL) + return -ENOMEM; + + cb->data = ctx_dump; + return 0; +} + static int nf_tables_dump_sets_done(struct netlink_callback *cb) { kfree(cb->data); @@ -3188,18 +3228,12 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_sets_start, .dump = nf_tables_dump_sets, .done = nf_tables_dump_sets_done, + .data = &ctx, .module = THIS_MODULE, }; - struct nft_ctx *ctx_dump; - - ctx_dump = kmalloc(sizeof(*ctx_dump), GFP_ATOMIC); - if (ctx_dump == NULL) - return -ENOMEM; - - *ctx_dump = ctx; - c.data = ctx_dump; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -3849,6 +3883,15 @@ nla_put_failure: return -ENOSPC; } +static int nf_tables_dump_set_start(struct netlink_callback *cb) +{ + struct nft_set_dump_ctx *dump_ctx = cb->data; + + cb->data = kmemdup(dump_ctx, sizeof(*dump_ctx), GFP_ATOMIC); + + return cb->data ? 0 : -ENOMEM; +} + static int nf_tables_dump_set_done(struct netlink_callback *cb) { kfree(cb->data); @@ -4002,20 +4045,17 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_set_start, .dump = nf_tables_dump_set, .done = nf_tables_dump_set_done, .module = THIS_MODULE, }; - struct nft_set_dump_ctx *dump_ctx; - - dump_ctx = kmalloc(sizeof(*dump_ctx), GFP_ATOMIC); - if (!dump_ctx) - return -ENOMEM; - - dump_ctx->set = set; - dump_ctx->ctx = ctx; + struct nft_set_dump_ctx dump_ctx = { + .set = set, + .ctx = ctx, + }; - c.data = dump_ctx; + c.data = &dump_ctx; return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -4975,38 +5015,42 @@ done: return skb->len; } -static int nf_tables_dump_obj_done(struct netlink_callback *cb) +static int nf_tables_dump_obj_start(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_obj_filter *filter = NULL; - if (filter) { - kfree(filter->table); - kfree(filter); + if (nla[NFTA_OBJ_TABLE] || nla[NFTA_OBJ_TYPE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; + + if (nla[NFTA_OBJ_TABLE]) { + filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + + if (nla[NFTA_OBJ_TYPE]) + filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); } + cb->data = filter; return 0; } -static struct nft_obj_filter * -nft_obj_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter; - - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) - return ERR_PTR(-ENOMEM); + struct nft_obj_filter *filter = cb->data; - if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } + if (filter) { + kfree(filter->table); + kfree(filter); } - if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - return filter; + return 0; } /* called with rcu_read_lock held */ @@ -5027,21 +5071,13 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, .dump = nf_tables_dump_obj, .done = nf_tables_dump_obj_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_OBJ_TABLE] || - nla[NFTA_OBJ_TYPE]) { - struct nft_obj_filter *filter; - - filter = nft_obj_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5320,8 +5356,6 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; - flowtable->dev_name[i] = kstrdup(dev_array[i]->name, - GFP_KERNEL); } return err; @@ -5479,10 +5513,8 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, err6: i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) { - kfree(flowtable->dev_name[k]); + for (k = i - 1; k >= 0; k--) nf_unregister_net_hook(net, &flowtable->ops[k]); - } kfree(flowtable->ops); err4: @@ -5581,9 +5613,10 @@ static int nf_tables_fill_flowtable_info(struct sk_buff *skb, struct net *net, goto nla_put_failure; for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->dev_name[i][0] && - nla_put_string(skb, NFTA_DEVICE_NAME, - flowtable->dev_name[i])) + const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); + + if (dev && + nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@ -5650,37 +5683,39 @@ done: return skb->len; } -static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) +static int nf_tables_dump_flowtable_start(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter = cb->data; + const struct nlattr * const *nla = cb->data; + struct nft_flowtable_filter *filter = NULL; - if (!filter) - return 0; + if (nla[NFTA_FLOWTABLE_TABLE]) { + filter = kzalloc(sizeof(*filter), GFP_ATOMIC); + if (!filter) + return -ENOMEM; - kfree(filter->table); - kfree(filter); + filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], + GFP_ATOMIC); + if (!filter->table) { + kfree(filter); + return -ENOMEM; + } + } + cb->data = filter; return 0; } -static struct nft_flowtable_filter * -nft_flowtable_filter_alloc(const struct nlattr * const nla[]) +static int nf_tables_dump_flowtable_done(struct netlink_callback *cb) { - struct nft_flowtable_filter *filter; + struct nft_flowtable_filter *filter = cb->data; - filter = kzalloc(sizeof(*filter), GFP_ATOMIC); if (!filter) - return ERR_PTR(-ENOMEM); + return 0; - if (nla[NFTA_FLOWTABLE_TABLE]) { - filter->table = nla_strdup(nla[NFTA_FLOWTABLE_TABLE], - GFP_ATOMIC); - if (!filter->table) { - kfree(filter); - return ERR_PTR(-ENOMEM); - } - } - return filter; + kfree(filter->table); + kfree(filter); + + return 0; } /* called with rcu_read_lock held */ @@ -5700,20 +5735,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (nlh->nlmsg_flags & NLM_F_DUMP) { struct netlink_dump_control c = { + .start = nf_tables_dump_flowtable_start, .dump = nf_tables_dump_flowtable, .done = nf_tables_dump_flowtable_done, .module = THIS_MODULE, + .data = (void *)nla, }; - if (nla[NFTA_FLOWTABLE_TABLE]) { - struct nft_flowtable_filter *filter; - - filter = nft_flowtable_filter_alloc(nla); - if (IS_ERR(filter)) - return -ENOMEM; - - c.data = filter; - } return nft_netlink_dump_start_rcu(nlsk, skb, nlh, &c); } @@ -5783,6 +5811,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); + kfree(flowtable); } static int nf_tables_fill_gen_info(struct sk_buff *skb, struct net *net, @@ -5825,7 +5854,6 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, continue; nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->dev_name[i][0] = '\0'; flowtable->ops[i].dev = NULL; break; } @@ -6086,6 +6114,9 @@ static void nft_commit_release(struct nft_trans *trans) case NFT_MSG_DELTABLE: nf_tables_table_destroy(&trans->ctx); break; + case NFT_MSG_NEWCHAIN: + kfree(nft_trans_chain_name(trans)); + break; case NFT_MSG_DELCHAIN: nf_tables_chain_destroy(&trans->ctx); break; @@ -6315,13 +6346,15 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nf_tables_table_notify(&trans->ctx, NFT_MSG_DELTABLE); break; case NFT_MSG_NEWCHAIN: - if (nft_trans_chain_update(trans)) + if (nft_trans_chain_update(trans)) { nft_chain_commit_update(trans); - else + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + /* trans destroyed after rcu grace period */ + } else { nft_clear(net, trans->ctx.chain); - - nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); - nft_trans_destroy(trans); + nf_tables_chain_notify(&trans->ctx, NFT_MSG_NEWCHAIN); + nft_trans_destroy(trans); + } break; case NFT_MSG_DELCHAIN: nft_chain_del(trans->ctx.chain); @@ -6471,7 +6504,7 @@ static int __nf_tables_abort(struct net *net) case NFT_MSG_NEWCHAIN: if (nft_trans_chain_update(trans)) { free_percpu(nft_trans_chain_stats(trans)); - + kfree(nft_trans_chain_name(trans)); nft_trans_destroy(trans); } else { trans->ctx.table->use--; @@ -6837,13 +6870,6 @@ int nft_validate_register_store(const struct nft_ctx *ctx, err = nf_tables_check_loops(ctx, data->verdict.chain); if (err < 0) return err; - - if (ctx->chain->level + 1 > - data->verdict.chain->level) { - if (ctx->chain->level + 1 == NFT_JUMP_STACK_SIZE) - return -EMLINK; - data->verdict.chain->level = ctx->chain->level + 1; - } } return 0; diff --git a/net/netfilter/nf_tables_set_core.c b/net/netfilter/nf_tables_set_core.c new file mode 100644 index 000000000000..814789644bd3 --- /dev/null +++ b/net/netfilter/nf_tables_set_core.c @@ -0,0 +1,28 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <net/netfilter/nf_tables_core.h> + +static int __init nf_tables_set_module_init(void) +{ + nft_register_set(&nft_set_hash_fast_type); + nft_register_set(&nft_set_hash_type); + nft_register_set(&nft_set_rhash_type); + nft_register_set(&nft_set_bitmap_type); + nft_register_set(&nft_set_rbtree_type); + + return 0; +} + +static void __exit nf_tables_set_module_exit(void) +{ + nft_unregister_set(&nft_set_rbtree_type); + nft_unregister_set(&nft_set_bitmap_type); + nft_unregister_set(&nft_set_rhash_type); + nft_unregister_set(&nft_set_hash_type); + nft_unregister_set(&nft_set_hash_fast_type); +} + +module_init(nf_tables_set_module_init); +module_exit(nf_tables_set_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 4ccd2988f9db..ea4ba551abb2 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -1243,6 +1243,9 @@ static int nfqnl_recv_unsupp(struct net *net, struct sock *ctnl, static const struct nla_policy nfqa_cfg_policy[NFQA_CFG_MAX+1] = { [NFQA_CFG_CMD] = { .len = sizeof(struct nfqnl_msg_config_cmd) }, [NFQA_CFG_PARAMS] = { .len = sizeof(struct nfqnl_msg_config_params) }, + [NFQA_CFG_QUEUE_MAXLEN] = { .type = NLA_U32 }, + [NFQA_CFG_MASK] = { .type = NLA_U32 }, + [NFQA_CFG_FLAGS] = { .type = NLA_U32 }, }; static const struct nf_queue_handler nfqh = { diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 8d1ff654e5af..32535eea51b2 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -832,10 +832,18 @@ nft_target_select_ops(const struct nft_ctx *ctx, rev = ntohl(nla_get_be32(tb[NFTA_TARGET_REV])); family = ctx->family; + if (strcmp(tg_name, XT_ERROR_TARGET) == 0 || + strcmp(tg_name, XT_STANDARD_TARGET) == 0 || + strcmp(tg_name, "standard") == 0) + return ERR_PTR(-EINVAL); + /* Re-use the existing target if it's already loaded. */ list_for_each_entry(nft_target, &nft_target_list, head) { struct xt_target *target = nft_target->ops.data; + if (!target->target) + continue; + if (nft_target_cmp(target, tg_name, rev, family)) return &nft_target->ops; } @@ -844,6 +852,11 @@ nft_target_select_ops(const struct nft_ctx *ctx, if (IS_ERR(target)) return ERR_PTR(-ENOENT); + if (!target->target) { + err = -EINVAL; + goto err; + } + if (target->targetsize > nla_len(tb[NFTA_TARGET_INFO])) { err = -EINVAL; goto err; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 15adf8ca82c3..0777a93211e2 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -98,6 +98,7 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, const struct nft_data **d) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; int err; @@ -109,9 +110,11 @@ static int nft_immediate_validate(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: + pctx->level++; err = nft_chain_validate(ctx, data->verdict.chain); if (err < 0) return err; + pctx->level--; break; default: break; diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index 42e6fadf1417..c2a1d84cdfc4 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -155,7 +155,9 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, struct nft_set_elem *elem) { const struct nft_set_ext *ext = nft_set_elem_ext(set, elem->priv); + struct nft_ctx *pctx = (struct nft_ctx *)ctx; const struct nft_data *data; + int err; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && *nft_set_ext_flags(ext) & NFT_SET_ELEM_INTERVAL_END) @@ -165,10 +167,17 @@ static int nft_lookup_validate_setelem(const struct nft_ctx *ctx, switch (data->verdict.code) { case NFT_JUMP: case NFT_GOTO: - return nft_chain_validate(ctx, data->verdict.chain); + pctx->level++; + err = nft_chain_validate(ctx, data->verdict.chain); + if (err < 0) + return err; + pctx->level--; + break; default: - return 0; + break; } + + return 0; } static int nft_lookup_validate(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index d6626e01c7ee..128bc16f52dd 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -296,7 +296,7 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_bitmap_type __read_mostly = { +struct nft_set_type nft_set_bitmap_type __read_mostly = { .owner = THIS_MODULE, .ops = { .privsize = nft_bitmap_privsize, @@ -314,20 +314,3 @@ static struct nft_set_type nft_bitmap_type __read_mostly = { .get = nft_bitmap_get, }, }; - -static int __init nft_bitmap_module_init(void) -{ - return nft_register_set(&nft_bitmap_type); -} - -static void __exit nft_bitmap_module_exit(void) -{ - nft_unregister_set(&nft_bitmap_type); -} - -module_init(nft_bitmap_module_init); -module_exit(nft_bitmap_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index 6f9a1365a09f..90c3e7e6cacb 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -387,6 +387,7 @@ static void nft_rhash_destroy(const struct nft_set *set) struct nft_rhash *priv = nft_set_priv(set); cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); rhashtable_free_and_destroy(&priv->ht, nft_rhash_elem_destroy, (void *)set); } @@ -654,7 +655,7 @@ static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features return true; } -static struct nft_set_type nft_rhash_type __read_mostly = { +struct nft_set_type nft_set_rhash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT | NFT_SET_EVAL, @@ -677,7 +678,7 @@ static struct nft_set_type nft_rhash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_type __read_mostly = { +struct nft_set_type nft_set_hash_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -697,7 +698,7 @@ static struct nft_set_type nft_hash_type __read_mostly = { }, }; -static struct nft_set_type nft_hash_fast_type __read_mostly = { +struct nft_set_type nft_set_hash_fast_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_MAP | NFT_SET_OBJECT, .ops = { @@ -716,26 +717,3 @@ static struct nft_set_type nft_hash_fast_type __read_mostly = { .get = nft_hash_get, }, }; - -static int __init nft_hash_module_init(void) -{ - if (nft_register_set(&nft_hash_fast_type) || - nft_register_set(&nft_hash_type) || - nft_register_set(&nft_rhash_type)) - return 1; - return 0; -} - -static void __exit nft_hash_module_exit(void) -{ - nft_unregister_set(&nft_rhash_type); - nft_unregister_set(&nft_hash_type); - nft_unregister_set(&nft_hash_fast_type); -} - -module_init(nft_hash_module_init); -module_exit(nft_hash_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 7f3a9a211034..9873d734b494 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -381,7 +381,7 @@ static void nft_rbtree_gc(struct work_struct *work) gcb = nft_set_gc_batch_check(set, gcb, GFP_ATOMIC); if (!gcb) - goto out; + break; atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); @@ -390,10 +390,12 @@ static void nft_rbtree_gc(struct work_struct *work) rbe = rb_entry(prev, struct nft_rbtree_elem, node); atomic_dec(&set->nelems); nft_set_gc_batch_add(gcb, rbe); + prev = NULL; } node = rb_next(node); + if (!node) + break; } -out: if (gcb) { for (i = 0; i < gcb->head.cnt; i++) { rbe = gcb->elems[i]; @@ -440,6 +442,7 @@ static void nft_rbtree_destroy(const struct nft_set *set) struct rb_node *node; cancel_delayed_work_sync(&priv->gc_work); + rcu_barrier(); while ((node = priv->root.rb_node) != NULL) { rb_erase(node, &priv->root); rbe = rb_entry(node, struct nft_rbtree_elem, node); @@ -462,7 +465,7 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_rbtree_type __read_mostly = { +struct nft_set_type nft_set_rbtree_type __read_mostly = { .owner = THIS_MODULE, .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, .ops = { @@ -481,20 +484,3 @@ static struct nft_set_type nft_rbtree_type __read_mostly = { .get = nft_rbtree_get, }, }; - -static int __init nft_rbtree_module_init(void) -{ - return nft_register_set(&nft_rbtree_type); -} - -static void __exit nft_rbtree_module_exit(void) -{ - nft_unregister_set(&nft_rbtree_type); -} - -module_init(nft_rbtree_module_init); -module_exit(nft_rbtree_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_SET(); diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c index 58fce4e749a9..d76550a8b642 100644 --- a/net/netfilter/xt_TPROXY.c +++ b/net/netfilter/xt_TPROXY.c @@ -61,7 +61,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, iph->daddr, hp->source, hp->dest, skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED); @@ -77,7 +77,7 @@ tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport, else if (!sk) /* no, there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v4(net, skb, hp, iph->protocol, + sk = nf_tproxy_get_sock_v4(net, skb, iph->protocol, iph->saddr, laddr, hp->source, lport, skb->dev, NF_TPROXY_LOOKUP_LISTENER); @@ -150,7 +150,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) * addresses, this happens if the redirect already happened * and the current packet belongs to an already established * connection */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, tproto, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, &iph->daddr, hp->source, hp->dest, xt_in(par), NF_TPROXY_LOOKUP_ESTABLISHED); @@ -171,7 +171,7 @@ tproxy_tg6_v1(struct sk_buff *skb, const struct xt_action_param *par) else if (!sk) /* no there's no established connection, check if * there's a listener on the redirected addr/port */ - sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, hp, + sk = nf_tproxy_get_sock_v6(xt_net(par), skb, thoff, tproto, &iph->saddr, laddr, hp->source, lport, xt_in(par), NF_TPROXY_LOOKUP_LISTENER); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 393573a99a5a..56704d95f82d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -63,6 +63,7 @@ #include <linux/hash.h> #include <linux/genetlink.h> #include <linux/net_namespace.h> +#include <linux/nospec.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -679,6 +680,7 @@ static int netlink_create(struct net *net, struct socket *sock, int protocol, if (protocol < 0 || protocol >= MAX_LINKS) return -EPROTONOSUPPORT; + protocol = array_index_nospec(protocol, MAX_LINKS); netlink_lock_table(); #ifdef CONFIG_MODULES @@ -1009,6 +1011,11 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, return err; } + if (nlk->ngroups == 0) + groups = 0; + else if (nlk->ngroups < 8*sizeof(groups)) + groups &= (1UL << nlk->ngroups) - 1; + bound = nlk->bound; if (bound) { /* Ensure nlk->portid is up-to-date. */ diff --git a/net/nfc/llcp_commands.c b/net/nfc/llcp_commands.c index 2ceefa183cee..6a196e438b6c 100644 --- a/net/nfc/llcp_commands.c +++ b/net/nfc/llcp_commands.c @@ -752,11 +752,14 @@ int nfc_llcp_send_ui_frame(struct nfc_llcp_sock *sock, u8 ssap, u8 dsap, pr_debug("Fragment %zd bytes remaining %zd", frag_len, remaining_len); - pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, MSG_DONTWAIT, + pdu = nfc_alloc_send_skb(sock->dev, &sock->sk, 0, frag_len + LLCP_HEADER_SIZE, &err); if (pdu == NULL) { - pr_err("Could not allocate PDU\n"); - continue; + pr_err("Could not allocate PDU (error=%d)\n", err); + len -= remaining_len; + if (len == 0) + len = err; + break; } pdu = llcp_add_header(pdu, dsap, ssap, LLCP_PDU_UI); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 9696ef96b719..1a30e165eeb4 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -104,7 +104,7 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, __skb_pull(skb, nsh_len); skb_reset_mac_header(skb); - skb_reset_mac_len(skb); + skb->mac_len = proto == htons(ETH_P_TEB) ? ETH_HLEN : 0; skb->protocol = proto; features &= NETIF_F_SG; diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index b891a91577f8..c038e021a591 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -211,6 +211,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) if (!meter) return ERR_PTR(-ENOMEM); + meter->id = nla_get_u32(a[OVS_METER_ATTR_ID]); meter->used = div_u64(ktime_get_ns(), 1000 * 1000); meter->kbps = a[OVS_METER_ATTR_KBPS] ? 1 : 0; meter->keep_stats = !a[OVS_METER_ATTR_CLEAR]; @@ -280,6 +281,10 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) u32 meter_id; bool failed; + if (!a[OVS_METER_ATTR_ID]) { + return -ENODEV; + } + meter = dp_meter_create(a); if (IS_ERR_OR_NULL(meter)) return PTR_ERR(meter); @@ -298,11 +303,6 @@ static int ovs_meter_cmd_set(struct sk_buff *skb, struct genl_info *info) goto exit_unlock; } - if (!a[OVS_METER_ATTR_ID]) { - err = -ENODEV; - goto exit_unlock; - } - meter_id = nla_get_u32(a[OVS_METER_ATTR_ID]); /* Cannot fail after this. */ diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 57634bc3da74..9b27d0cd766d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2878,6 +2878,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } else if (reserve) { skb_reserve(skb, -reserve); + if (len < reserve) + skb_reset_network_header(skb); } /* Returns -EFAULT on error */ diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 2aa07b547b16..86e1e37eb4e8 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -191,8 +191,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->type = cpu_to_le32(type); hdr->src_node_id = cpu_to_le32(from->sq_node); hdr->src_port_id = cpu_to_le32(from->sq_port); - hdr->dst_node_id = cpu_to_le32(to->sq_node); - hdr->dst_port_id = cpu_to_le32(to->sq_port); + if (to->sq_port == QRTR_PORT_CTRL) { + hdr->dst_node_id = cpu_to_le32(node->nid); + hdr->dst_port_id = cpu_to_le32(QRTR_NODE_BCAST); + } else { + hdr->dst_node_id = cpu_to_le32(to->sq_node); + hdr->dst_port_id = cpu_to_le32(to->sq_port); + } hdr->size = cpu_to_le32(len); hdr->confirm_rx = 0; @@ -764,6 +769,10 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { enqueue_fn = qrtr_bcast_enqueue; + if (addr->sq_port != QRTR_PORT_CTRL) { + release_sock(sk); + return -ENOTCONN; + } } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { diff --git a/net/rds/connection.c b/net/rds/connection.c index abef75da89a7..cfb05953b0e5 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -659,11 +659,19 @@ static void rds_conn_info(struct socket *sock, unsigned int len, int rds_conn_init(void) { + int ret; + + ret = rds_loop_net_init(); /* register pernet callback */ + if (ret) + return ret; + rds_conn_slab = kmem_cache_create("rds_connection", sizeof(struct rds_connection), 0, 0, NULL); - if (!rds_conn_slab) + if (!rds_conn_slab) { + rds_loop_net_exit(); return -ENOMEM; + } rds_info_register_func(RDS_INFO_CONNECTIONS, rds_conn_info); rds_info_register_func(RDS_INFO_SEND_MESSAGES, @@ -676,6 +684,7 @@ int rds_conn_init(void) void rds_conn_exit(void) { + rds_loop_net_exit(); /* unregister pernet callback */ rds_loop_exit(); WARN_ON(!hlist_empty(rds_conn_hash)); diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c index 48332a6ed738..d152e48ea371 100644 --- a/net/rds/ib_frmr.c +++ b/net/rds/ib_frmr.c @@ -344,6 +344,11 @@ struct rds_ib_mr *rds_ib_reg_frmr(struct rds_ib_device *rds_ibdev, struct rds_ib_frmr *frmr; int ret; + if (!ic) { + /* TODO: Add FRWR support for RDS_GET_MR using proxy qp*/ + return ERR_PTR(-EOPNOTSUPP); + } + do { if (ibmr) rds_ib_free_frmr(ibmr, true); diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 0ea4ab017a8c..655f01d427fe 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -115,7 +115,8 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo); void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index e678699268a2..2e49a40a5e11 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -537,11 +537,12 @@ void rds_ib_flush_mrs(void) } void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, - struct rds_sock *rs, u32 *key_ret) + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; - struct rds_ib_connection *ic = rs->rs_conn->c_transport_data; + struct rds_ib_connection *ic = NULL; int ret; rds_ibdev = rds_ib_get_device(rs->rs_bound_addr); @@ -550,6 +551,9 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (conn) + ic = conn->c_transport_data; + if (!rds_ibdev->mr_8k_pool || !rds_ibdev->mr_1m_pool) { ret = -ENODEV; goto out; @@ -559,17 +563,18 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, ibmr = rds_ib_reg_frmr(rds_ibdev, ic, sg, nents, key_ret); else ibmr = rds_ib_reg_fmr(rds_ibdev, sg, nents, key_ret); - if (ibmr) - rds_ibdev = NULL; - - out: - if (!ibmr) + if (IS_ERR(ibmr)) { + ret = PTR_ERR(ibmr); pr_warn("RDS/IB: rds_ib_get_mr failed (errno=%d)\n", ret); + } else { + return ibmr; + } + out: if (rds_ibdev) rds_ib_dev_put(rds_ibdev); - return ibmr; + return ERR_PTR(ret); } void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *pool) diff --git a/net/rds/loop.c b/net/rds/loop.c index dac6218a460e..feea1f96ee2a 100644 --- a/net/rds/loop.c +++ b/net/rds/loop.c @@ -33,6 +33,8 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/in.h> +#include <net/net_namespace.h> +#include <net/netns/generic.h> #include "rds_single_path.h" #include "rds.h" @@ -40,6 +42,17 @@ static DEFINE_SPINLOCK(loop_conns_lock); static LIST_HEAD(loop_conns); +static atomic_t rds_loop_unloading = ATOMIC_INIT(0); + +static void rds_loop_set_unloading(void) +{ + atomic_set(&rds_loop_unloading, 1); +} + +static bool rds_loop_is_unloading(struct rds_connection *conn) +{ + return atomic_read(&rds_loop_unloading) != 0; +} /* * This 'loopback' transport is a special case for flows that originate @@ -165,6 +178,8 @@ void rds_loop_exit(void) struct rds_loop_connection *lc, *_lc; LIST_HEAD(tmp_list); + rds_loop_set_unloading(); + synchronize_rcu(); /* avoid calling conn_destroy with irqs off */ spin_lock_irq(&loop_conns_lock); list_splice(&loop_conns, &tmp_list); @@ -177,6 +192,46 @@ void rds_loop_exit(void) } } +static void rds_loop_kill_conns(struct net *net) +{ + struct rds_loop_connection *lc, *_lc; + LIST_HEAD(tmp_list); + + spin_lock_irq(&loop_conns_lock); + list_for_each_entry_safe(lc, _lc, &loop_conns, loop_node) { + struct net *c_net = read_pnet(&lc->conn->c_net); + + if (net != c_net) + continue; + list_move_tail(&lc->loop_node, &tmp_list); + } + spin_unlock_irq(&loop_conns_lock); + + list_for_each_entry_safe(lc, _lc, &tmp_list, loop_node) { + WARN_ON(lc->conn->c_passive); + rds_conn_destroy(lc->conn); + } +} + +static void __net_exit rds_loop_exit_net(struct net *net) +{ + rds_loop_kill_conns(net); +} + +static struct pernet_operations rds_loop_net_ops = { + .exit = rds_loop_exit_net, +}; + +int rds_loop_net_init(void) +{ + return register_pernet_device(&rds_loop_net_ops); +} + +void rds_loop_net_exit(void) +{ + unregister_pernet_device(&rds_loop_net_ops); +} + /* * This is missing .xmit_* because loop doesn't go through generic * rds_send_xmit() and doesn't call rds_recv_incoming(). .listen_stop and @@ -194,4 +249,5 @@ struct rds_transport rds_loop_transport = { .inc_free = rds_loop_inc_free, .t_name = "loopback", .t_type = RDS_TRANS_LOOP, + .t_unloading = rds_loop_is_unloading, }; diff --git a/net/rds/loop.h b/net/rds/loop.h index 469fa4b2da4f..bbc8cdd030df 100644 --- a/net/rds/loop.h +++ b/net/rds/loop.h @@ -5,6 +5,8 @@ /* loop.c */ extern struct rds_transport rds_loop_transport; +int rds_loop_net_init(void); +void rds_loop_net_exit(void); void rds_loop_exit(void); #endif diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 634cfcb7bba6..80920e47f2c7 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -170,7 +170,8 @@ static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, } static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, - u64 *cookie_ret, struct rds_mr **mr_ret) + u64 *cookie_ret, struct rds_mr **mr_ret, + struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; unsigned int nr_pages; @@ -269,7 +270,8 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key); + &mr->r_key, + cp ? cp->cp_conn : NULL); if (IS_ERR(trans_private)) { for (i = 0 ; i < nents; i++) @@ -330,7 +332,7 @@ int rds_get_mr(struct rds_sock *rs, char __user *optval, int optlen) sizeof(struct rds_get_mr_args))) return -EFAULT; - return __rds_rdma_map(rs, &args, NULL, NULL); + return __rds_rdma_map(rs, &args, NULL, NULL, NULL); } int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) @@ -354,7 +356,7 @@ int rds_get_mr_for_dest(struct rds_sock *rs, char __user *optval, int optlen) new_args.cookie_addr = args.cookie_addr; new_args.flags = args.flags; - return __rds_rdma_map(rs, &new_args, NULL, NULL); + return __rds_rdma_map(rs, &new_args, NULL, NULL, NULL); } /* @@ -782,7 +784,8 @@ int rds_cmsg_rdma_map(struct rds_sock *rs, struct rds_message *rm, rm->m_rdma_cookie != 0) return -EINVAL; - return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, &rm->rdma.op_rdma_mr); + return __rds_rdma_map(rs, CMSG_DATA(cmsg), &rm->m_rdma_cookie, + &rm->rdma.op_rdma_mr, rm->m_conn_path); } /* diff --git a/net/rds/rds.h b/net/rds/rds.h index f2272fb8cd45..60b3b787fbdb 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -464,6 +464,8 @@ struct rds_message { struct scatterlist *op_sg; } data; }; + + struct rds_conn_path *m_conn_path; }; /* @@ -544,7 +546,8 @@ struct rds_transport { unsigned int avail); void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, - struct rds_sock *rs, u32 *key_ret); + struct rds_sock *rs, u32 *key_ret, + struct rds_connection *conn); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); diff --git a/net/rds/send.c b/net/rds/send.c index 94c7f74909be..59f17a2335f4 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1169,6 +1169,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) rs->rs_conn = conn; } + if (conn->c_trans->t_mp_capable) + cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; + else + cpath = &conn->c_path[0]; + + rm->m_conn_path = cpath; + /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr); if (ret) { @@ -1192,11 +1199,6 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) goto out; } - if (conn->c_trans->t_mp_capable) - cpath = &conn->c_path[rds_send_mprds_hash(rs, conn)]; - else - cpath = &conn->c_path[0]; - if (rds_destroy_pending(conn)) { ret = -EAGAIN; goto out; diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index a9a9be5519b9..9d1e298b784c 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -116,9 +116,9 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, while (*pp) { parent = *pp; xcall = rb_entry(parent, struct rxrpc_call, sock_node); - if (user_call_ID < call->user_call_ID) + if (user_call_ID < xcall->user_call_ID) pp = &(*pp)->rb_left; - else if (user_call_ID > call->user_call_ID) + else if (user_call_ID > xcall->user_call_ID) pp = &(*pp)->rb_right; else goto id_in_use; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 526a8e491626..6e7124e57918 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -91,7 +91,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla, } params_old = rtnl_dereference(p->params); - params_new->action = parm->action; + p->tcf_action = parm->action; params_new->update_flags = parm->update_flags; rcu_assign_pointer(p->params, params_new); if (params_old) @@ -561,7 +561,7 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&p->tcf_tm); bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(p->tcf_action); if (unlikely(action == TC_ACT_SHOT)) goto drop_stats; @@ -599,11 +599,11 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind, .index = p->tcf_index, .refcnt = p->tcf_refcnt - ref, .bindcnt = p->tcf_bindcnt - bind, + .action = p->tcf_action, }; struct tcf_t t; params = rtnl_dereference(p->params); - opt.action = params->action; opt.update_flags = params->update_flags; if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt)) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 626dac81a48a..9bc6c2ae98a5 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -36,7 +36,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&t->tcf_tm); bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb); - action = params->action; + action = READ_ONCE(t->tcf_action); switch (params->tcft_action) { case TCA_TUNNEL_KEY_ACT_RELEASE: @@ -182,7 +182,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla, params_old = rtnl_dereference(t->params); - params_new->action = parm->action; + t->tcf_action = parm->action; params_new->tcft_action = parm->t_action; params_new->tcft_enc_metadata = metadata; @@ -254,13 +254,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a, .index = t->tcf_index, .refcnt = t->tcf_refcnt - ref, .bindcnt = t->tcf_bindcnt - bind, + .action = t->tcf_action, }; struct tcf_t tm; params = rtnl_dereference(t->params); opt.t_action = params->tcft_action; - opt.action = params->action; if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt)) goto nla_put_failure; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index cdc3c87c53e6..f74513a7c7a8 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1053,7 +1053,7 @@ static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, for (tp = rtnl_dereference(chain->filter_chain); tp; tp = rtnl_dereference(tp->next)) tfilter_notify(net, oskb, n, tp, block, - q, parent, 0, event, false); + q, parent, NULL, event, false); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1444,7 +1444,7 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, memset(&cb->args[1], 0, sizeof(cb->args) - sizeof(cb->args[0])); if (cb->args[1] == 0) { - if (tcf_fill_node(net, skb, tp, block, q, parent, 0, + if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWTFILTER) <= 0) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index cd2e0e342fb6..6c0a9d5dbf94 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -479,24 +479,28 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, q->cparams.mtu = psched_mtu(qdisc_dev(sch)); if (opt) { - int err = fq_codel_change(sch, opt, extack); + err = fq_codel_change(sch, opt, extack); if (err) - return err; + goto init_failure; } err = tcf_block_get(&q->block, &q->filter_list, sch, extack); if (err) - return err; + goto init_failure; if (!q->flows) { q->flows = kvcalloc(q->flows_cnt, sizeof(struct fq_codel_flow), GFP_KERNEL); - if (!q->flows) - return -ENOMEM; + if (!q->flows) { + err = -ENOMEM; + goto init_failure; + } q->backlogs = kvcalloc(q->flows_cnt, sizeof(u32), GFP_KERNEL); - if (!q->backlogs) - return -ENOMEM; + if (!q->backlogs) { + err = -ENOMEM; + goto alloc_failure; + } for (i = 0; i < q->flows_cnt; i++) { struct fq_codel_flow *flow = q->flows + i; @@ -509,6 +513,13 @@ static int fq_codel_init(struct Qdisc *sch, struct nlattr *opt, else sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; + +alloc_failure: + kvfree(q->flows); + q->flows = NULL; +init_failure: + q->flows_cnt = 0; + return err; } static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 445b7ef61677..12cac85da994 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -282,7 +282,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) if (dst) { /* Re-fetch, as under layers may have a higher minimum size */ - pmtu = SCTP_TRUNC4(dst_mtu(dst)); + pmtu = sctp_dst_mtu(dst); change = t->pathmtu != pmtu; } t->pathmtu = pmtu; diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 973b4471b532..05e4ffe5aabd 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -45,6 +45,7 @@ static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group */ static void smc_tcp_listen_work(struct work_struct *); +static void smc_connect_work(struct work_struct *); static void smc_set_keepalive(struct sock *sk, int val) { @@ -122,6 +123,12 @@ static int smc_release(struct socket *sock) goto out; smc = smc_sk(sk); + + /* cleanup for a dangling non-blocking connect */ + flush_work(&smc->connect_work); + kfree(smc->connect_info); + smc->connect_info = NULL; + if (sk->sk_state == SMC_LISTEN) /* smc_close_non_accepted() is called and acquires * sock lock for child sockets again @@ -140,7 +147,8 @@ static int smc_release(struct socket *sock) smc->clcsock = NULL; } if (smc->use_fallback) { - sock_put(sk); /* passive closing */ + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } @@ -186,6 +194,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, sk->sk_protocol = protocol; smc = smc_sk(sk); INIT_WORK(&smc->tcp_listen_work, smc_tcp_listen_work); + INIT_WORK(&smc->connect_work, smc_connect_work); INIT_DELAYED_WORK(&smc->conn.tx_work, smc_tx_work); INIT_LIST_HEAD(&smc->accept_q); spin_lock_init(&smc->accept_q_lock); @@ -409,12 +418,18 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code) { int rc; - if (reason_code < 0) /* error, fallback is not possible */ + if (reason_code < 0) { /* error, fallback is not possible */ + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return reason_code; + } if (reason_code != SMC_CLC_DECL_REPLY) { rc = smc_clc_send_decline(smc, reason_code); - if (rc < 0) + if (rc < 0) { + if (smc->sk.sk_state == SMC_INIT) + sock_put(&smc->sk); /* passive closing */ return rc; + } } return smc_connect_fallback(smc); } @@ -427,8 +442,6 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, smc_lgr_forget(smc->conn.lgr); mutex_unlock(&smc_create_lgr_pending); smc_conn_free(&smc->conn); - if (reason_code < 0 && smc->sk.sk_state == SMC_INIT) - sock_put(&smc->sk); /* passive closing */ return reason_code; } @@ -576,6 +589,35 @@ static int __smc_connect(struct smc_sock *smc) return 0; } +static void smc_connect_work(struct work_struct *work) +{ + struct smc_sock *smc = container_of(work, struct smc_sock, + connect_work); + int rc; + + lock_sock(&smc->sk); + rc = kernel_connect(smc->clcsock, &smc->connect_info->addr, + smc->connect_info->alen, smc->connect_info->flags); + if (smc->clcsock->sk->sk_err) { + smc->sk.sk_err = smc->clcsock->sk->sk_err; + goto out; + } + if (rc < 0) { + smc->sk.sk_err = -rc; + goto out; + } + + rc = __smc_connect(smc); + if (rc < 0) + smc->sk.sk_err = -rc; + +out: + smc->sk.sk_state_change(&smc->sk); + kfree(smc->connect_info); + smc->connect_info = NULL; + release_sock(&smc->sk); +} + static int smc_connect(struct socket *sock, struct sockaddr *addr, int alen, int flags) { @@ -605,15 +647,32 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, smc_copy_sock_settings_to_clc(smc); tcp_sk(smc->clcsock->sk)->syn_smc = 1; - rc = kernel_connect(smc->clcsock, addr, alen, flags); - if (rc) - goto out; + if (flags & O_NONBLOCK) { + if (smc->connect_info) { + rc = -EALREADY; + goto out; + } + smc->connect_info = kzalloc(alen + 2 * sizeof(int), GFP_KERNEL); + if (!smc->connect_info) { + rc = -ENOMEM; + goto out; + } + smc->connect_info->alen = alen; + smc->connect_info->flags = flags ^ O_NONBLOCK; + memcpy(&smc->connect_info->addr, addr, alen); + schedule_work(&smc->connect_work); + rc = -EINPROGRESS; + } else { + rc = kernel_connect(smc->clcsock, addr, alen, flags); + if (rc) + goto out; - rc = __smc_connect(smc); - if (rc < 0) - goto out; - else - rc = 0; /* success cases including fallback */ + rc = __smc_connect(smc); + if (rc < 0) + goto out; + else + rc = 0; /* success cases including fallback */ + } out: release_sock(sk); @@ -1279,40 +1338,20 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, struct sock *sk = sock->sk; __poll_t mask = 0; struct smc_sock *smc; - int rc; if (!sk) return EPOLLNVAL; smc = smc_sk(sock->sk); - sock_hold(sk); - lock_sock(sk); if ((sk->sk_state == SMC_INIT) || smc->use_fallback) { /* delegate to CLC child sock */ - release_sock(sk); mask = smc->clcsock->ops->poll(file, smc->clcsock, wait); - lock_sock(sk); sk->sk_err = smc->clcsock->sk->sk_err; - if (sk->sk_err) { + if (sk->sk_err) mask |= EPOLLERR; - } else { - /* if non-blocking connect finished ... */ - if (sk->sk_state == SMC_INIT && - mask & EPOLLOUT && - smc->clcsock->sk->sk_state != TCP_CLOSE) { - rc = __smc_connect(smc); - if (rc < 0) - mask |= EPOLLERR; - /* success cases including fallback */ - mask |= EPOLLOUT | EPOLLWRNORM; - } - } } else { - if (sk->sk_state != SMC_CLOSED) { - release_sock(sk); + if (sk->sk_state != SMC_CLOSED) sock_poll_wait(file, sk_sleep(sk), wait); - lock_sock(sk); - } if (sk->sk_err) mask |= EPOLLERR; if ((sk->sk_shutdown == SHUTDOWN_MASK) || @@ -1338,10 +1377,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock, } if (smc->conn.urg_state == SMC_URG_VALID) mask |= EPOLLPRI; - } - release_sock(sk); - sock_put(sk); return mask; } @@ -1421,7 +1457,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (optlen < sizeof(int)) return -EINVAL; - get_user(val, (int __user *)optval); + if (get_user(val, (int __user *)optval)) + return -EFAULT; lock_sock(sk); switch (optname) { @@ -1489,10 +1526,13 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, return -EBADF; return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); } + lock_sock(&smc->sk); switch (cmd) { case SIOCINQ: /* same as FIONREAD */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1501,8 +1541,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQ: /* output queue size (not send + not acked) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1512,8 +1554,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, break; case SIOCOUTQNSD: /* output queue size (not send only) */ - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) answ = 0; @@ -1521,8 +1565,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, answ = smc_tx_prepared_sends(&smc->conn); break; case SIOCATMARK: - if (smc->sk.sk_state == SMC_LISTEN) + if (smc->sk.sk_state == SMC_LISTEN) { + release_sock(&smc->sk); return -EINVAL; + } if (smc->sk.sk_state == SMC_INIT || smc->sk.sk_state == SMC_CLOSED) { answ = 0; @@ -1538,8 +1584,10 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, } break; default: + release_sock(&smc->sk); return -ENOIOCTLCMD; } + release_sock(&smc->sk); return put_user(answ, (int __user *)arg); } diff --git a/net/smc/smc.h b/net/smc/smc.h index 51ae1f10d81a..d7ca26570482 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -187,11 +187,19 @@ struct smc_connection { struct work_struct close_work; /* peer sent some closing */ }; +struct smc_connect_info { + int flags; + int alen; + struct sockaddr addr; +}; + struct smc_sock { /* smc sock container */ struct sock sk; struct socket *clcsock; /* internal tcp socket */ struct smc_connection conn; /* smc connection */ struct smc_sock *listen_smc; /* listen parent */ + struct smc_connect_info *connect_info; /* connect address & flags */ + struct work_struct connect_work; /* handle non-blocking connect*/ struct work_struct tcp_listen_work;/* handle tcp socket accepts */ struct work_struct smc_listen_work;/* prepare new accept socket */ struct list_head accept_q; /* sockets to be accepted */ diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index a7e8d63fc8ae..9bde1e4ca288 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -233,7 +233,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, /* force immediate tx of current consumer cursor, but * under send_lock to guarantee arrival in seqno-order */ - smc_tx_sndbuf_nonempty(conn); + if (smc->sk.sk_state != SMC_INIT) + smc_tx_sndbuf_nonempty(conn); } } diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 717449b1da0b..ae5d168653ce 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -250,6 +250,7 @@ out: int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, u8 expected_type) { + long rcvtimeo = smc->clcsock->sk->sk_rcvtimeo; struct sock *clc_sk = smc->clcsock->sk; struct smc_clc_msg_hdr *clcm = buf; struct msghdr msg = {NULL, 0}; @@ -306,7 +307,6 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, memset(&msg, 0, sizeof(struct msghdr)); iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); krflags = MSG_WAITALL; - smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { smc->sk.sk_err = EPROTO; @@ -322,6 +322,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, } out: + smc->clcsock->sk->sk_rcvtimeo = rcvtimeo; return reason_code; } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index fa41d9881741..ac961dfb1ea1 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -107,6 +107,8 @@ static void smc_close_active_abort(struct smc_sock *smc) } switch (sk->sk_state) { case SMC_INIT: + sk->sk_state = SMC_PEERABORTWAIT; + break; case SMC_ACTIVE: sk->sk_state = SMC_PEERABORTWAIT; release_sock(sk); diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index cee666400752..f82886b7d1d8 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -495,7 +495,8 @@ out: void smc_tx_consumer_update(struct smc_connection *conn, bool force) { - union smc_host_cursor cfed, cons; + union smc_host_cursor cfed, cons, prod; + int sender_free = conn->rmb_desc->len; int to_confirm; smc_curs_write(&cons, @@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) smc_curs_read(&conn->rx_curs_confirmed, conn), conn); to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons); + if (to_confirm > conn->rmbe_update_limit) { + smc_curs_write(&prod, + smc_curs_read(&conn->local_rx_ctrl.prod, conn), + conn); + sender_free = conn->rmb_desc->len - + smc_curs_diff(conn->rmb_desc->len, &prod, &cfed); + } if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || force || ((to_confirm > conn->rmbe_update_limit) && - ((to_confirm > (conn->rmb_desc->len / 2)) || + ((sender_free <= (conn->rmb_desc->len / 2)) || conn->local_rx_ctrl.prod_flags.write_blocked))) { if ((smc_cdc_get_slot_and_msg_send(conn) < 0) && conn->alert_token_local) { /* connection healthy */ diff --git a/net/socket.c b/net/socket.c index 85633622c94d..8c24d5dc4bc8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -89,6 +89,7 @@ #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> +#include <linux/nospec.h> #include <linux/uaccess.h> #include <asm/unistd.h> @@ -2522,6 +2523,7 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; + call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) @@ -2688,7 +2690,8 @@ EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { - return family < NPROTO && rcu_access_pointer(net_families[family]); + return family < NPROTO && + rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]); } static int __init sock_init(void) diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c index 373836615c57..625acb27efcc 100644 --- a/net/strparser/strparser.c +++ b/net/strparser/strparser.c @@ -35,7 +35,6 @@ struct _strp_msg { */ struct strp_msg strp; int accum_len; - int early_eaten; }; static inline struct _strp_msg *_strp_msg(struct sk_buff *skb) @@ -115,20 +114,6 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, head = strp->skb_head; if (head) { /* Message already in progress */ - - stm = _strp_msg(head); - if (unlikely(stm->early_eaten)) { - /* Already some number of bytes on the receive sock - * data saved in skb_head, just indicate they - * are consumed. - */ - eaten = orig_len <= stm->early_eaten ? - orig_len : stm->early_eaten; - stm->early_eaten -= eaten; - - return eaten; - } - if (unlikely(orig_offset)) { /* Getting data with a non-zero offset when a message is * in progress is not expected. If it does happen, we @@ -297,9 +282,9 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb, } stm->accum_len += cand_len; + eaten += cand_len; strp->need_bytes = stm->strp.full_len - stm->accum_len; - stm->early_eaten = cand_len; STRP_STATS_ADD(strp->stats.bytes, cand_len); desc->count = 0; /* Stop reading socket */ break; diff --git a/net/tipc/discover.c b/net/tipc/discover.c index 9f666e0650e2..2830709957bd 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -133,6 +133,8 @@ static void disc_dupl_alert(struct tipc_bearer *b, u32 node_addr, } /* tipc_disc_addr_trial(): - handle an address uniqueness trial from peer + * Returns true if message should be dropped by caller, i.e., if it is a + * trial message or we are inside trial period. Otherwise false. */ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, struct tipc_media_addr *maddr, @@ -168,8 +170,9 @@ static bool tipc_disc_addr_trial_msg(struct tipc_discoverer *d, msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); } + /* Accept regular link requests/responses only after trial period */ if (mtyp != DSC_TRIAL_MSG) - return false; + return trial; sugg_addr = tipc_node_try_addr(net, peer_id, src); if (sugg_addr) @@ -284,7 +287,6 @@ static void tipc_disc_timeout(struct timer_list *t) { struct tipc_discoverer *d = from_timer(d, t, timer); struct tipc_net *tn = tipc_net(d->net); - u32 self = tipc_own_addr(d->net); struct tipc_media_addr maddr; struct sk_buff *skb = NULL; struct net *net = d->net; @@ -298,12 +300,14 @@ static void tipc_disc_timeout(struct timer_list *t) goto exit; } - /* Did we just leave the address trial period ? */ - if (!self && !time_before(jiffies, tn->addr_trial_end)) { - self = tn->trial_addr; - tipc_net_finalize(net, self); - msg_set_prevnode(buf_msg(d->skb), self); + /* Trial period over ? */ + if (!time_before(jiffies, tn->addr_trial_end)) { + /* Did we just leave it ? */ + if (!tipc_own_addr(net)) + tipc_net_finalize(net, tn->trial_addr); + msg_set_type(buf_msg(d->skb), DSC_REQ_MSG); + msg_set_prevnode(buf_msg(d->skb), tipc_own_addr(net)); } /* Adjust timeout interval according to discovery phase */ diff --git a/net/tipc/net.c b/net/tipc/net.c index 4fbaa0464405..a7f6964c3a4b 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -121,12 +121,17 @@ int tipc_net_init(struct net *net, u8 *node_id, u32 addr) void tipc_net_finalize(struct net *net, u32 addr) { - tipc_set_node_addr(net, addr); - smp_mb(); - tipc_named_reinit(net); - tipc_sk_reinit(net); - tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, - TIPC_CLUSTER_SCOPE, 0, addr); + struct tipc_net *tn = tipc_net(net); + + spin_lock_bh(&tn->node_list_lock); + if (!tipc_own_addr(net)) { + tipc_set_node_addr(net, addr); + tipc_named_reinit(net); + tipc_sk_reinit(net); + tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, + TIPC_CLUSTER_SCOPE, 0, addr); + } + spin_unlock_bh(&tn->node_list_lock); } void tipc_net_stop(struct net *net) diff --git a/net/tipc/node.c b/net/tipc/node.c index 6a44eb812baf..0453bd451ce8 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -797,6 +797,7 @@ static u32 tipc_node_suggest_addr(struct net *net, u32 addr) } /* tipc_node_try_addr(): Check if addr can be used by peer, suggest other if not + * Returns suggested address if any, otherwise 0 */ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) { @@ -819,12 +820,14 @@ u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr) if (n) { addr = n->addr; tipc_node_put(n); + return addr; } - /* Even this node may be in trial phase */ + + /* Even this node may be in conflict */ if (tn->trial_addr == addr) return tipc_node_suggest_addr(net, addr); - return addr; + return 0; } void tipc_node_check_dest(struct net *net, u32 addr, diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index d2380548f8f6..1f3d9789af30 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -440,7 +440,7 @@ alloc_encrypted: ret = tls_push_record(sk, msg->msg_flags, record_type); if (!ret) continue; - if (ret == -EAGAIN) + if (ret < 0) goto send_end; copied -= try_to_copy; @@ -646,6 +646,9 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, return NULL; } + if (sk->sk_shutdown & RCV_SHUTDOWN) + return NULL; + if (sock_flag(sk, SOCK_DONE)) return NULL; @@ -701,6 +704,10 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, nsg = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); + if (nsg < 0) { + ret = nsg; + goto out; + } tls_make_aad(ctx->rx_aad_ciphertext, rxm->full_len - tls_ctx->rx.overhead_size, @@ -712,6 +719,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, rxm->full_len - tls_ctx->rx.overhead_size, skb, sk->sk_allocation); +out: if (sgin != &sgin_arr[0]) kfree(sgin); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index c7bbe5f0aae8..80bc986c79e5 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -4409,6 +4409,7 @@ static int parse_station_flags(struct genl_info *info, params->sta_flags_mask = BIT(NL80211_STA_FLAG_AUTHENTICATED) | BIT(NL80211_STA_FLAG_MFP) | BIT(NL80211_STA_FLAG_AUTHORIZED); + break; default: return -EINVAL; } @@ -6231,7 +6232,7 @@ do { \ nl80211_check_s32); /* * Check HT operation mode based on - * IEEE 802.11 2012 8.4.2.59 HT Operation element. + * IEEE 802.11-2016 9.4.2.57 HT Operation element. */ if (tb[NL80211_MESHCONF_HT_OPMODE]) { ht_opmode = nla_get_u16(tb[NL80211_MESHCONF_HT_OPMODE]); @@ -6241,22 +6242,9 @@ do { \ IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) return -EINVAL; - if ((ht_opmode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT) && - (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; + /* NON_HT_STA bit is reserved, but some programs set it */ + ht_opmode &= ~IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT; - switch (ht_opmode & IEEE80211_HT_OP_MODE_PROTECTION) { - case IEEE80211_HT_OP_MODE_PROTECTION_NONE: - case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ: - if (ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT) - return -EINVAL; - break; - case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER: - case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED: - if (!(ht_opmode & IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT)) - return -EINVAL; - break; - } cfg->ht_opmode = ht_opmode; mask |= (1 << (NL80211_MESHCONF_HT_OPMODE - 1)); } @@ -10962,9 +10950,12 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, - info->extack); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, + info->extack); + if (err) + goto error; + err = -EINVAL; if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) @@ -11213,8 +11204,11 @@ static int nl80211_parse_coalesce_rule(struct cfg80211_registered_device *rdev, rem) { u8 *mask_pat; - nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, - nl80211_packet_pattern_policy, NULL); + err = nla_parse_nested(pat_tb, MAX_NL80211_PKTPAT, pat, + nl80211_packet_pattern_policy, NULL); + if (err) + return err; + if (!pat_tb[NL80211_PKTPAT_MASK] || !pat_tb[NL80211_PKTPAT_PATTERN]) return -EINVAL; @@ -14930,20 +14924,24 @@ void cfg80211_mgmt_tx_status(struct wireless_dev *wdev, u64 cookie, EXPORT_SYMBOL(cfg80211_mgmt_tx_status); static int __nl80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, + struct sk_buff *skb, bool unencrypted, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); + struct ethhdr *ehdr = eth_hdr(skb); + const u8 *addr = ehdr->h_source; + u16 proto = be16_to_cpu(skb->protocol); struct sk_buff *msg; void *hdr; + struct nlattr *frame; + u32 nlportid = READ_ONCE(wdev->conn_owner_nlportid); if (!nlportid) return -ENOENT; - msg = nlmsg_new(100 + len, gfp); + msg = nlmsg_new(100 + skb->len, gfp); if (!msg) return -ENOMEM; @@ -14957,13 +14955,17 @@ static int __nl80211_rx_control_port(struct net_device *dev, nla_put_u32(msg, NL80211_ATTR_IFINDEX, dev->ifindex) || nla_put_u64_64bit(msg, NL80211_ATTR_WDEV, wdev_id(wdev), NL80211_ATTR_PAD) || - nla_put(msg, NL80211_ATTR_FRAME, len, buf) || nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, addr) || nla_put_u16(msg, NL80211_ATTR_CONTROL_PORT_ETHERTYPE, proto) || (unencrypted && nla_put_flag(msg, NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT))) goto nla_put_failure; + frame = nla_reserve(msg, NL80211_ATTR_FRAME, skb->len); + if (!frame) + goto nla_put_failure; + + skb_copy_bits(skb, 0, nla_data(frame), skb->len); genlmsg_end(msg, hdr); return genlmsg_unicast(wiphy_net(&rdev->wiphy), msg, nlportid); @@ -14974,14 +14976,12 @@ static int __nl80211_rx_control_port(struct net_device *dev, } bool cfg80211_rx_control_port(struct net_device *dev, - const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted) + struct sk_buff *skb, bool unencrypted) { int ret; - trace_cfg80211_rx_control_port(dev, buf, len, addr, proto, unencrypted); - ret = __nl80211_rx_control_port(dev, buf, len, addr, proto, - unencrypted, GFP_ATOMIC); + trace_cfg80211_rx_control_port(dev, skb, unencrypted); + ret = __nl80211_rx_control_port(dev, skb, unencrypted, GFP_ATOMIC); trace_cfg80211_return_bool(ret == 0); return ret == 0; } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index bbe6298e4bb9..4fc66a117b7d 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2240,7 +2240,9 @@ static void wiphy_update_regulatory(struct wiphy *wiphy, * as some drivers used this to restore its orig_* reg domain. */ if (initiator == NL80211_REGDOM_SET_BY_CORE && - wiphy->regulatory_flags & REGULATORY_CUSTOM_REG) + wiphy->regulatory_flags & REGULATORY_CUSTOM_REG && + !(wiphy->regulatory_flags & + REGULATORY_WIPHY_SELF_MANAGED)) reg_call_notifier(wiphy, lr); return; } @@ -2787,26 +2789,6 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) } } -static bool reg_only_self_managed_wiphys(void) -{ - struct cfg80211_registered_device *rdev; - struct wiphy *wiphy; - bool self_managed_found = false; - - ASSERT_RTNL(); - - list_for_each_entry(rdev, &cfg80211_rdev_list, list) { - wiphy = &rdev->wiphy; - if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) - self_managed_found = true; - else - return false; - } - - /* make sure at least one self-managed wiphy exists */ - return self_managed_found; -} - /* * Processes regulatory hints, this is all the NL80211_REGDOM_SET_BY_* * Regulatory hints come on a first come first serve basis and we @@ -2839,10 +2821,6 @@ static void reg_process_pending_hints(void) spin_unlock(®_requests_lock); notify_self_managed_wiphys(reg_request); - if (reg_only_self_managed_wiphys()) { - reg_free_request(reg_request); - return; - } reg_process_hint(reg_request); diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2b417a2fe63f..7c73510b161f 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2627,23 +2627,25 @@ TRACE_EVENT(cfg80211_mgmt_tx_status, ); TRACE_EVENT(cfg80211_rx_control_port, - TP_PROTO(struct net_device *netdev, const u8 *buf, size_t len, - const u8 *addr, u16 proto, bool unencrypted), - TP_ARGS(netdev, buf, len, addr, proto, unencrypted), + TP_PROTO(struct net_device *netdev, struct sk_buff *skb, + bool unencrypted), + TP_ARGS(netdev, skb, unencrypted), TP_STRUCT__entry( NETDEV_ENTRY - MAC_ENTRY(addr) + __field(int, len) + MAC_ENTRY(from) __field(u16, proto) __field(bool, unencrypted) ), TP_fast_assign( NETDEV_ASSIGN; - MAC_ASSIGN(addr, addr); - __entry->proto = proto; + __entry->len = skb->len; + MAC_ASSIGN(from, eth_hdr(skb)->h_source); + __entry->proto = be16_to_cpu(skb->protocol); __entry->unencrypted = unencrypted; ), - TP_printk(NETDEV_PR_FMT ", " MAC_PR_FMT " proto: 0x%x, unencrypted: %s", - NETDEV_PR_ARG, MAC_PR_ARG(addr), + TP_printk(NETDEV_PR_FMT ", len=%d, " MAC_PR_FMT ", proto: 0x%x, unencrypted: %s", + NETDEV_PR_ARG, __entry->len, MAC_PR_ARG(from), __entry->proto, BOOL_TO_STR(__entry->unencrypted)) ); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 59fb7d3c36a3..4e937cd7c17d 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -84,10 +84,8 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { int err = xskq_produce_batch_desc(xs->rx, (u64)xdp->handle, len); - if (err) { - xdp_return_buff(xdp); + if (err) xs->rx_dropped++; - } return err; } @@ -199,8 +197,11 @@ static void xsk_destruct_skb(struct sk_buff *skb) { u64 addr = (u64)(long)skb_shinfo(skb)->destructor_arg; struct xdp_sock *xs = xdp_sk(skb->sk); + unsigned long flags; + spin_lock_irqsave(&xs->tx_completion_lock, flags); WARN_ON_ONCE(xskq_produce_addr(xs->umem->cq, addr)); + spin_unlock_irqrestore(&xs->tx_completion_lock, flags); sock_wfree(skb); } @@ -215,9 +216,6 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, struct sk_buff *skb; int err = 0; - if (unlikely(!xs->tx)) - return -ENOBUFS; - mutex_lock(&xs->mutex); while (xskq_peek_desc(xs->tx, &desc)) { @@ -230,22 +228,13 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, goto out; } - if (xskq_reserve_addr(xs->umem->cq)) { - err = -EAGAIN; + if (xskq_reserve_addr(xs->umem->cq)) goto out; - } - len = desc.len; - if (unlikely(len > xs->dev->mtu)) { - err = -EMSGSIZE; + if (xs->queue_id >= xs->dev->real_num_tx_queues) goto out; - } - - if (xs->queue_id >= xs->dev->real_num_tx_queues) { - err = -ENXIO; - goto out; - } + len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); if (unlikely(!skb)) { err = -EAGAIN; @@ -268,15 +257,15 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, skb->destructor = xsk_destruct_skb; err = dev_direct_xmit(skb, xs->queue_id); + xskq_discard_desc(xs->tx); /* Ignore NET_XMIT_CN as packet might have been sent */ if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { - err = -EAGAIN; - /* SKB consumed by dev_direct_xmit() */ + /* SKB completed but not sent */ + err = -EBUSY; goto out; } sent_frame = true; - xskq_discard_desc(xs->tx); } out: @@ -297,6 +286,8 @@ static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) return -ENXIO; if (unlikely(!(xs->dev->flags & IFF_UP))) return -ENETDOWN; + if (unlikely(!xs->tx)) + return -ENOBUFS; if (need_wait) return -EOPNOTSUPP; @@ -755,6 +746,7 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, xs = xdp_sk(sk); mutex_init(&xs->mutex); + spin_lock_init(&xs->tx_completion_lock); local_bh_disable(); sock_prot_inuse_add(net, &xsk_proto, 1); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index ef6a6f0ec949..8a64b150be54 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -62,14 +62,9 @@ static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) return (entries > dcnt) ? dcnt : entries; } -static inline u32 xskq_nb_free_lazy(struct xsk_queue *q, u32 producer) -{ - return q->nentries - (producer - q->cons_tail); -} - static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) { - u32 free_entries = xskq_nb_free_lazy(q, producer); + u32 free_entries = q->nentries - (producer - q->cons_tail); if (free_entries >= dcnt) return free_entries; @@ -129,7 +124,7 @@ static inline int xskq_produce_addr(struct xsk_queue *q, u64 addr) { struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; - if (xskq_nb_free(q, q->prod_tail, LAZY_UPDATE_THRESHOLD) == 0) + if (xskq_nb_free(q, q->prod_tail, 1) == 0) return -ENOSPC; ring->desc[q->prod_tail++ & q->ring_mask] = addr; @@ -255,7 +250,7 @@ static inline bool xskq_full_desc(struct xsk_queue *q) static inline bool xskq_empty_desc(struct xsk_queue *q) { - return xskq_nb_free(q, q->prod_tail, 1) == q->nentries; + return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 5f48251c1319..7c5e8978aeaa 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2286,6 +2286,9 @@ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, if (IS_ERR(dst) && PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); + if (IS_ERR(dst)) + dst_release(dst_orig); + return dst; } EXPORT_SYMBOL(xfrm_lookup_route); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 080035f056d9..33878e6e0d0a 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1025,10 +1025,12 @@ static inline int xfrm_nlmsg_multicast(struct net *net, struct sk_buff *skb, { struct sock *nlsk = rcu_dereference(net->xfrm.nlsk); - if (nlsk) - return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); - else - return -1; + if (!nlsk) { + kfree_skb(skb); + return -EPIPE; + } + + return nlmsg_multicast(nlsk, skb, pid, group, GFP_ATOMIC); } static inline unsigned int xfrm_spdinfo_msgsize(void) @@ -1671,9 +1673,11 @@ static inline unsigned int userpolicy_type_attrsize(void) #ifdef CONFIG_XFRM_SUB_POLICY static int copy_to_user_policy_type(u8 type, struct sk_buff *skb) { - struct xfrm_userpolicy_type upt = { - .type = type, - }; + struct xfrm_userpolicy_type upt; + + /* Sadly there are two holes in struct xfrm_userpolicy_type */ + memset(&upt, 0, sizeof(upt)); + upt.type = type; return nla_put(skb, XFRMA_POLICY_TYPE, sizeof(upt), &upt); } |