diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 95 | ||||
-rw-r--r-- | net/core/dst.c | 15 | ||||
-rw-r--r-- | net/core/ethtool.c | 224 | ||||
-rw-r--r-- | net/core/filter.c | 709 | ||||
-rw-r--r-- | net/core/flow.c | 8 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 2 | ||||
-rw-r--r-- | net/core/net_namespace.c | 2 | ||||
-rw-r--r-- | net/core/netclassid_cgroup.c | 15 | ||||
-rw-r--r-- | net/core/netprio_cgroup.c | 41 | ||||
-rw-r--r-- | net/core/pktgen.c | 60 | ||||
-rw-r--r-- | net/core/ptp_classifier.c | 2 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 53 | ||||
-rw-r--r-- | net/core/skbuff.c | 20 | ||||
-rw-r--r-- | net/core/sock.c | 53 | ||||
-rw-r--r-- | net/core/sock_diag.c | 4 |
15 files changed, 773 insertions, 530 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 48d81e4..867adb2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1661,6 +1661,29 @@ bool is_skb_forwardable(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(is_skb_forwardable); +int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, GFP_ATOMIC)) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + } + + if (unlikely(!is_skb_forwardable(dev, skb))) { + atomic_long_inc(&dev->rx_dropped); + kfree_skb(skb); + return NET_RX_DROP; + } + + skb_scrub_packet(skb, true); + skb->protocol = eth_type_trans(skb, dev); + + return 0; +} +EXPORT_SYMBOL_GPL(__dev_forward_skb); + /** * dev_forward_skb - loopback an skb to another netif * @@ -1681,24 +1704,7 @@ EXPORT_SYMBOL_GPL(is_skb_forwardable); */ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) { - if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { - if (skb_copy_ubufs(skb, GFP_ATOMIC)) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - } - - if (unlikely(!is_skb_forwardable(dev, skb))) { - atomic_long_inc(&dev->rx_dropped); - kfree_skb(skb); - return NET_RX_DROP; - } - - skb_scrub_packet(skb, true); - skb->protocol = eth_type_trans(skb, dev); - - return netif_rx_internal(skb); + return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -2284,7 +2290,7 @@ EXPORT_SYMBOL(skb_checksum_help); __be16 skb_network_protocol(struct sk_buff *skb, int *depth) { __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; + int vlan_depth = skb->mac_len; /* Tunnel gso handlers can set protocol to ethernet. */ if (type == htons(ETH_P_TEB)) { @@ -2418,7 +2424,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); * 2. No high memory really exists on this machine. */ -static int illegal_highdma(const struct net_device *dev, struct sk_buff *skb) +static int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_HIGHMEM int i; @@ -2493,38 +2499,36 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) } static netdev_features_t harmonize_features(struct sk_buff *skb, - const struct net_device *dev, - netdev_features_t features) + netdev_features_t features) { int tmp; if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) { features &= ~NETIF_F_ALL_CSUM; - } else if (illegal_highdma(dev, skb)) { + } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } return features; } -netdev_features_t netif_skb_dev_features(struct sk_buff *skb, - const struct net_device *dev) +netdev_features_t netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - netdev_features_t features = dev->features; + netdev_features_t features = skb->dev->features; - if (skb_shinfo(skb)->gso_segs > dev->gso_max_segs) + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } - features &= (dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX); if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) @@ -2532,9 +2536,9 @@ netdev_features_t netif_skb_dev_features(struct sk_buff *skb, NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX; - return harmonize_features(skb, dev, features); + return harmonize_features(skb, features); } -EXPORT_SYMBOL(netif_skb_dev_features); +EXPORT_SYMBOL(netif_skb_features); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) @@ -3439,7 +3443,7 @@ out: * @rx_handler: receive handler to register * @rx_handler_data: data pointer that is used by rx handler * - * Register a receive hander for a device. This handler will then be + * Register a receive handler for a device. This handler will then be * called from __netif_receive_skb. A negative errno code is returned * on a failure. * @@ -4043,6 +4047,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) skb->vlan_tci = 0; skb->dev = napi->dev; skb->skb_iif = 0; + skb->truesize = SKB_TRUESIZE(skb_end_offset(skb)); napi->skb = skb; } @@ -4155,8 +4160,8 @@ static void net_rps_action_and_irq_enable(struct softnet_data *sd) struct softnet_data *next = remsd->rps_ipi_next; if (cpu_online(remsd->cpu)) - __smp_call_function_single(remsd->cpu, - &remsd->csd, 0); + smp_call_function_single_async(remsd->cpu, + &remsd->csd); remsd = next; } } else @@ -4588,8 +4593,7 @@ void *netdev_lower_get_next_private(struct net_device *dev, if (&lower->list == &dev->adj_list.lower) return NULL; - if (iter) - *iter = lower->list.next; + *iter = lower->list.next; return lower->private; } @@ -4617,8 +4621,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev, if (&lower->list == &dev->adj_list.lower) return NULL; - if (iter) - *iter = &lower->list; + *iter = &lower->list; return lower->private; } @@ -5239,6 +5242,7 @@ void __dev_set_rx_mode(struct net_device *dev) if (ops->ndo_set_rx_mode) ops->ndo_set_rx_mode(dev); } +EXPORT_SYMBOL(__dev_set_rx_mode); void dev_set_rx_mode(struct net_device *dev) { @@ -5600,10 +5604,6 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - if (!dev->rtnl_link_ops || - dev->rtnl_link_state == RTNL_LINK_INITIALIZED) - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); - /* * Flush the unicast and multicast chains */ @@ -5613,6 +5613,10 @@ static void rollback_registered_many(struct list_head *head) if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U, GFP_KERNEL); + /* Notifier chain MUST detach us all upper devices. */ WARN_ON(netdev_has_any_upper_dev(dev)); @@ -5696,6 +5700,13 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, } } +#ifdef CONFIG_NET_RX_BUSY_POLL + if (dev->netdev_ops->ndo_busy_poll) + features |= NETIF_F_BUSY_POLL; + else +#endif + features &= ~NETIF_F_BUSY_POLL; + return features; } diff --git a/net/core/dst.c b/net/core/dst.c index ca4231e..80d6286 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -142,12 +142,12 @@ loop: mutex_unlock(&dst_gc_mutex); } -int dst_discard(struct sk_buff *skb) +int dst_discard_sk(struct sock *sk, struct sk_buff *skb) { kfree_skb(skb); return 0; } -EXPORT_SYMBOL(dst_discard); +EXPORT_SYMBOL(dst_discard_sk); const u32 dst_default_metrics[RTAX_MAX + 1] = { /* This initializer is needed to force linker to place this variable @@ -184,7 +184,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->xfrm = NULL; #endif dst->input = dst_discard; - dst->output = dst_discard; + dst->output = dst_discard_sk; dst->error = 0; dst->obsolete = initial_obsolete; dst->header_len = 0; @@ -209,8 +209,10 @@ static void ___dst_free(struct dst_entry *dst) /* The first case (dev==NULL) is required, when protocol module is unloaded. */ - if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) - dst->input = dst->output = dst_discard; + if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) { + dst->input = dst_discard; + dst->output = dst_discard_sk; + } dst->obsolete = DST_OBSOLETE_DEAD; } @@ -361,7 +363,8 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, return; if (!unregister) { - dst->input = dst->output = dst_discard; + dst->input = dst_discard; + dst->output = dst_discard_sk; } else { dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 30071de..aa8978ac 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -97,6 +97,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_RXFCS_BIT] = "rx-fcs", [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", + [NETIF_F_BUSY_POLL_BIT] = "busy-poll", }; static int ethtool_get_features(struct net_device *dev, void __user *useraddr) @@ -556,6 +557,25 @@ err_out: return ret; } +static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, + struct ethtool_rxnfc *rx_rings, + u32 size) +{ + int ret = 0, i; + + if (copy_from_user(indir, useraddr, size * sizeof(indir[0]))) + ret = -EFAULT; + + /* Validate ring indices */ + for (i = 0; i < size; i++) { + if (indir[i] >= rx_rings->data) { + ret = -EINVAL; + break; + } + } + return ret; +} + static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { @@ -612,6 +632,7 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, u32 *indir; const struct ethtool_ops *ops = dev->ethtool_ops; int ret; + u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]); if (!ops->get_rxfh_indir_size || !ops->set_rxfh_indir || !ops->get_rxnfc) @@ -642,28 +663,196 @@ static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, for (i = 0; i < dev_size; i++) indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); } else { - if (copy_from_user(indir, - useraddr + - offsetof(struct ethtool_rxfh_indir, - ring_index[0]), - dev_size * sizeof(indir[0]))) { + ret = ethtool_copy_validate_indir(indir, + useraddr + ringidx_offset, + &rx_rings, + dev_size); + if (ret) + goto out; + } + + ret = ops->set_rxfh_indir(dev, indir); + +out: + kfree(indir); + return ret; +} + +static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, + void __user *useraddr) +{ + int ret; + const struct ethtool_ops *ops = dev->ethtool_ops; + u32 user_indir_size = 0, user_key_size = 0; + u32 dev_indir_size = 0, dev_key_size = 0; + u32 total_size; + u32 indir_offset, indir_bytes; + u32 key_offset; + u32 *indir = NULL; + u8 *hkey = NULL; + u8 *rss_config; + + if (!(dev->ethtool_ops->get_rxfh_indir_size || + dev->ethtool_ops->get_rxfh_key_size) || + !dev->ethtool_ops->get_rxfh) + return -EOPNOTSUPP; + + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + + indir_offset = offsetof(struct ethtool_rxfh, indir_size); + + if (copy_from_user(&user_indir_size, + useraddr + indir_offset, + sizeof(user_indir_size))) + return -EFAULT; + + if (copy_to_user(useraddr + indir_offset, + &dev_indir_size, sizeof(dev_indir_size))) + return -EFAULT; + + if (ops->get_rxfh_key_size) + dev_key_size = ops->get_rxfh_key_size(dev); + + if ((dev_key_size + dev_indir_size) == 0) + return -EOPNOTSUPP; + + key_offset = offsetof(struct ethtool_rxfh, key_size); + + if (copy_from_user(&user_key_size, + useraddr + key_offset, + sizeof(user_key_size))) + return -EFAULT; + + if (copy_to_user(useraddr + key_offset, + &dev_key_size, sizeof(dev_key_size))) + return -EFAULT; + + /* If the user buffer size is 0, this is just a query for the + * device table size and key size. Otherwise, if the User size is + * not equal to device table size or key size it's an error. + */ + if (!user_indir_size && !user_key_size) + return 0; + + if ((user_indir_size && (user_indir_size != dev_indir_size)) || + (user_key_size && (user_key_size != dev_key_size))) + return -EINVAL; + + indir_bytes = user_indir_size * sizeof(indir[0]); + total_size = indir_bytes + user_key_size; + rss_config = kzalloc(total_size, GFP_USER); + if (!rss_config) + return -ENOMEM; + + if (user_indir_size) + indir = (u32 *)rss_config; + + if (user_key_size) + hkey = rss_config + indir_bytes; + + ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey); + if (!ret) { + if (copy_to_user(useraddr + + offsetof(struct ethtool_rxfh, rss_config[0]), + rss_config, total_size)) ret = -EFAULT; + } + + kfree(rss_config); + + return ret; +} + +static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, + void __user *useraddr) +{ + int ret; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rxnfc rx_rings; + u32 user_indir_size = 0, dev_indir_size = 0, i; + u32 user_key_size = 0, dev_key_size = 0; + u32 *indir = NULL, indir_bytes = 0; + u8 *hkey = NULL; + u8 *rss_config; + u32 indir_offset, key_offset; + u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); + + if (!(ops->get_rxfh_indir_size || ops->get_rxfh_key_size) || + !ops->get_rxnfc || !ops->set_rxfh) + return -EOPNOTSUPP; + + if (ops->get_rxfh_indir_size) + dev_indir_size = ops->get_rxfh_indir_size(dev); + + indir_offset = offsetof(struct ethtool_rxfh, indir_size); + if (copy_from_user(&user_indir_size, + useraddr + indir_offset, + sizeof(user_indir_size))) + return -EFAULT; + + if (ops->get_rxfh_key_size) + dev_key_size = dev->ethtool_ops->get_rxfh_key_size(dev); + + if ((dev_key_size + dev_indir_size) == 0) + return -EOPNOTSUPP; + + key_offset = offsetof(struct ethtool_rxfh, key_size); + if (copy_from_user(&user_key_size, + useraddr + key_offset, + sizeof(user_key_size))) + return -EFAULT; + + /* If either indir or hash key is valid, proceed further. + */ + if ((user_indir_size && ((user_indir_size != 0xDEADBEEF) && + user_indir_size != dev_indir_size)) || + (user_key_size && (user_key_size != dev_key_size))) + return -EINVAL; + + if (user_indir_size != 0xDEADBEEF) + indir_bytes = dev_indir_size * sizeof(indir[0]); + + rss_config = kzalloc(indir_bytes + user_key_size, GFP_USER); + if (!rss_config) + return -ENOMEM; + + rx_rings.cmd = ETHTOOL_GRXRINGS; + ret = ops->get_rxnfc(dev, &rx_rings, NULL); + if (ret) + goto out; + + /* user_indir_size == 0 means reset the indir table to default. + * user_indir_size == 0xDEADBEEF means indir setting is not requested. + */ + if (user_indir_size && user_indir_size != 0xDEADBEEF) { + indir = (u32 *)rss_config; + ret = ethtool_copy_validate_indir(indir, + useraddr + rss_cfg_offset, + &rx_rings, + user_indir_size); + if (ret) goto out; - } + } else if (user_indir_size == 0) { + indir = (u32 *)rss_config; + for (i = 0; i < dev_indir_size; i++) + indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); + } - /* Validate ring indices */ - for (i = 0; i < dev_size; i++) { - if (indir[i] >= rx_rings.data) { - ret = -EINVAL; - goto out; - } + if (user_key_size) { + hkey = rss_config + indir_bytes; + if (copy_from_user(hkey, + useraddr + rss_cfg_offset + indir_bytes, + user_key_size)) { + ret = -EFAULT; + goto out; } } - ret = ops->set_rxfh_indir(dev, indir); + ret = ops->set_rxfh(dev, indir, hkey); out: - kfree(indir); + kfree(rss_config); return ret; } @@ -1490,6 +1679,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: case ETHTOOL_GRXFHINDIR: + case ETHTOOL_GRSSH: case ETHTOOL_GFEATURES: case ETHTOOL_GCHANNELS: case ETHTOOL_GET_TS_INFO: @@ -1627,6 +1817,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXFHINDIR: rc = ethtool_set_rxfh_indir(dev, useraddr); break; + case ETHTOOL_GRSSH: + rc = ethtool_get_rxfh(dev, useraddr); + break; + case ETHTOOL_SRSSH: + rc = ethtool_set_rxfh(dev, useraddr); + break; case ETHTOOL_GFEATURES: rc = ethtool_get_features(dev, useraddr); break; diff --git a/net/core/filter.c b/net/core/filter.c index 765556b..7067cb2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -45,6 +45,27 @@ #include <linux/seccomp.h> #include <linux/if_vlan.h> +/* Registers */ +#define BPF_R0 regs[BPF_REG_0] +#define BPF_R1 regs[BPF_REG_1] +#define BPF_R2 regs[BPF_REG_2] +#define BPF_R3 regs[BPF_REG_3] +#define BPF_R4 regs[BPF_REG_4] +#define BPF_R5 regs[BPF_REG_5] +#define BPF_R6 regs[BPF_REG_6] +#define BPF_R7 regs[BPF_REG_7] +#define BPF_R8 regs[BPF_REG_8] +#define BPF_R9 regs[BPF_REG_9] +#define BPF_R10 regs[BPF_REG_10] + +/* Named registers */ +#define A regs[insn->a_reg] +#define X regs[insn->x_reg] +#define FP regs[BPF_REG_FP] +#define ARG1 regs[BPF_REG_ARG1] +#define CTX regs[BPF_REG_CTX] +#define K insn->imm + /* No hurry in this branch * * Exported for the bpf jit load helper. @@ -57,9 +78,9 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns ptr = skb_network_header(skb) + k - SKF_NET_OFF; else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; + return NULL; } @@ -68,6 +89,7 @@ static inline void *load_pointer(const struct sk_buff *skb, int k, { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); + return bpf_internal_load_pointer_neg_helper(skb, k, size); } @@ -131,210 +153,208 @@ noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) * keep, 0 for none. @ctx is the data we are operating on, @insn is the * array of filter instructions. */ -unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) +static unsigned int __sk_run_filter(void *ctx, const struct sock_filter_int *insn) { u64 stack[MAX_BPF_STACK / sizeof(u64)]; u64 regs[MAX_BPF_REG], tmp; - void *ptr; - int off; - -#define K insn->imm -#define A regs[insn->a_reg] -#define X regs[insn->x_reg] -#define R0 regs[0] - -#define CONT ({insn++; goto select_insn; }) -#define CONT_JMP ({insn++; goto select_insn; }) - static const void *jumptable[256] = { [0 ... 255] = &&default_label, /* Now overwrite non-defaults ... */ -#define DL(A, B, C) [A|B|C] = &&A##_##B##_##C - DL(BPF_ALU, BPF_ADD, BPF_X), - DL(BPF_ALU, BPF_ADD, BPF_K), - DL(BPF_ALU, BPF_SUB, BPF_X), - DL(BPF_ALU, BPF_SUB, BPF_K), - DL(BPF_ALU, BPF_AND, BPF_X), - DL(BPF_ALU, BPF_AND, BPF_K), - DL(BPF_ALU, BPF_OR, BPF_X), - DL(BPF_ALU, BPF_OR, BPF_K), - DL(BPF_ALU, BPF_LSH, BPF_X), - DL(BPF_ALU, BPF_LSH, BPF_K), - DL(BPF_ALU, BPF_RSH, BPF_X), - DL(BPF_ALU, BPF_RSH, BPF_K), - DL(BPF_ALU, BPF_XOR, BPF_X), - DL(BPF_ALU, BPF_XOR, BPF_K), - DL(BPF_ALU, BPF_MUL, BPF_X), - DL(BPF_ALU, BPF_MUL, BPF_K), - DL(BPF_ALU, BPF_MOV, BPF_X), - DL(BPF_ALU, BPF_MOV, BPF_K), - DL(BPF_ALU, BPF_DIV, BPF_X), - DL(BPF_ALU, BPF_DIV, BPF_K), - DL(BPF_ALU, BPF_MOD, BPF_X), - DL(BPF_ALU, BPF_MOD, BPF_K), - DL(BPF_ALU, BPF_NEG, 0), - DL(BPF_ALU, BPF_END, BPF_TO_BE), - DL(BPF_ALU, BPF_END, BPF_TO_LE), - DL(BPF_ALU64, BPF_ADD, BPF_X), - DL(BPF_ALU64, BPF_ADD, BPF_K), - DL(BPF_ALU64, BPF_SUB, BPF_X), - DL(BPF_ALU64, BPF_SUB, BPF_K), - DL(BPF_ALU64, BPF_AND, BPF_X), - DL(BPF_ALU64, BPF_AND, BPF_K), - DL(BPF_ALU64, BPF_OR, BPF_X), - DL(BPF_ALU64, BPF_OR, BPF_K), - DL(BPF_ALU64, BPF_LSH, BPF_X), - DL(BPF_ALU64, BPF_LSH, BPF_K), - DL(BPF_ALU64, BPF_RSH, BPF_X), - DL(BPF_ALU64, BPF_RSH, BPF_K), - DL(BPF_ALU64, BPF_XOR, BPF_X), - DL(BPF_ALU64, BPF_XOR, BPF_K), - DL(BPF_ALU64, BPF_MUL, BPF_X), - DL(BPF_ALU64, BPF_MUL, BPF_K), - DL(BPF_ALU64, BPF_MOV, BPF_X), - DL(BPF_ALU64, BPF_MOV, BPF_K), - DL(BPF_ALU64, BPF_ARSH, BPF_X), - DL(BPF_ALU64, BPF_ARSH, BPF_K), - DL(BPF_ALU64, BPF_DIV, BPF_X), - DL(BPF_ALU64, BPF_DIV, BPF_K), - DL(BPF_ALU64, BPF_MOD, BPF_X), - DL(BPF_ALU64, BPF_MOD, BPF_K), - DL(BPF_ALU64, BPF_NEG, 0), - DL(BPF_JMP, BPF_CALL, 0), - DL(BPF_JMP, BPF_JA, 0), - DL(BPF_JMP, BPF_JEQ, BPF_X), - DL(BPF_JMP, BPF_JEQ, BPF_K), - DL(BPF_JMP, BPF_JNE, BPF_X), - DL(BPF_JMP, BPF_JNE, BPF_K), - DL(BPF_JMP, BPF_JGT, BPF_X), - DL(BPF_JMP, BPF_JGT, BPF_K), - DL(BPF_JMP, BPF_JGE, BPF_X), - DL(BPF_JMP, BPF_JGE, BPF_K), - DL(BPF_JMP, BPF_JSGT, BPF_X), - DL(BPF_JMP, BPF_JSGT, BPF_K), - DL(BPF_JMP, BPF_JSGE, BPF_X), - DL(BPF_JMP, BPF_JSGE, BPF_K), - DL(BPF_JMP, BPF_JSET, BPF_X), - DL(BPF_JMP, BPF_JSET, BPF_K), - DL(BPF_JMP, BPF_EXIT, 0), - DL(BPF_STX, BPF_MEM, BPF_B), - DL(BPF_STX, BPF_MEM, BPF_H), - DL(BPF_STX, BPF_MEM, BPF_W), - DL(BPF_STX, BPF_MEM, BPF_DW), - DL(BPF_STX, BPF_XADD, BPF_W), - DL(BPF_STX, BPF_XADD, BPF_DW), - DL(BPF_ST, BPF_MEM, BPF_B), - DL(BPF_ST, BPF_MEM, BPF_H), - DL(BPF_ST, BPF_MEM, BPF_W), - DL(BPF_ST, BPF_MEM, BPF_DW), - DL(BPF_LDX, BPF_MEM, BPF_B), - DL(BPF_LDX, BPF_MEM, BPF_H), - DL(BPF_LDX, BPF_MEM, BPF_W), - DL(BPF_LDX, BPF_MEM, BPF_DW), - DL(BPF_LD, BPF_ABS, BPF_W), - DL(BPF_LD, BPF_ABS, BPF_H), - DL(BPF_LD, BPF_ABS, BPF_B), - DL(BPF_LD, BPF_IND, BPF_W), - DL(BPF_LD, BPF_IND, BPF_H), - DL(BPF_LD, BPF_IND, BPF_B), +#define DL(A, B, C) [BPF_##A|BPF_##B|BPF_##C] = &&A##_##B##_##C + DL(ALU, ADD, X), + DL(ALU, ADD, K), + DL(ALU, SUB, X), + DL(ALU, SUB, K), + DL(ALU, AND, X), + DL(ALU, AND, K), + DL(ALU, OR, X), + DL(ALU, OR, K), + DL(ALU, LSH, X), + DL(ALU, LSH, K), + DL(ALU, RSH, X), + DL(ALU, RSH, K), + DL(ALU, XOR, X), + DL(ALU, XOR, K), + DL(ALU, MUL, X), + DL(ALU, MUL, K), + DL(ALU, MOV, X), + DL(ALU, MOV, K), + DL(ALU, DIV, X), + DL(ALU, DIV, K), + DL(ALU, MOD, X), + DL(ALU, MOD, K), + DL(ALU, NEG, 0), + DL(ALU, END, TO_BE), + DL(ALU, END, TO_LE), + DL(ALU64, ADD, X), + DL(ALU64, ADD, K), + DL(ALU64, SUB, X), + DL(ALU64, SUB, K), + DL(ALU64, AND, X), + DL(ALU64, AND, K), + DL(ALU64, OR, X), + DL(ALU64, OR, K), + DL(ALU64, LSH, X), + DL(ALU64, LSH, K), + DL(ALU64, RSH, X), + DL(ALU64, RSH, K), + DL(ALU64, XOR, X), + DL(ALU64, XOR, K), + DL(ALU64, MUL, X), + DL(ALU64, MUL, K), + DL(ALU64, MOV, X), + DL(ALU64, MOV, K), + DL(ALU64, ARSH, X), + DL(ALU64, ARSH, K), + DL(ALU64, DIV, X), + DL(ALU64, DIV, K), + DL(ALU64, MOD, X), + DL(ALU64, MOD, K), + DL(ALU64, NEG, 0), + DL(JMP, CALL, 0), + DL(JMP, JA, 0), + DL(JMP, JEQ, X), + DL(JMP, JEQ, K), + DL(JMP, JNE, X), + DL(JMP, JNE, K), + DL(JMP, JGT, X), + DL(JMP, JGT, K), + DL(JMP, JGE, X), + DL(JMP, JGE, K), + DL(JMP, JSGT, X), + DL(JMP, JSGT, K), + DL(JMP, JSGE, X), + DL(JMP, JSGE, K), + DL(JMP, JSET, X), + DL(JMP, JSET, K), + DL(JMP, EXIT, 0), + DL(STX, MEM, B), + DL(STX, MEM, H), + DL(STX, MEM, W), + DL(STX, MEM, DW), + DL(STX, XADD, W), + DL(STX, XADD, DW), + DL(ST, MEM, B), + DL(ST, MEM, H), + DL(ST, MEM, W), + DL(ST, MEM, DW), + DL(LDX, MEM, B), + DL(LDX, MEM, H), + DL(LDX, MEM, W), + DL(LDX, MEM, DW), + DL(LD, ABS, W), + DL(LD, ABS, H), + DL(LD, ABS, B), + DL(LD, IND, W), + DL(LD, IND, H), + DL(LD, IND, B), #undef DL }; + void *ptr; + int off; - regs[FP_REG] = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; - regs[ARG1_REG] = (u64) (unsigned long) ctx; +#define CONT ({ insn++; goto select_insn; }) +#define CONT_JMP ({ insn++; goto select_insn; }) + + FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; + ARG1 = (u64) (unsigned long) ctx; + + /* Register for user BPF programs need to be reset first. */ + regs[BPF_REG_A] = 0; + regs[BPF_REG_X] = 0; select_insn: goto *jumptable[insn->code]; /* ALU */ #define ALU(OPCODE, OP) \ - BPF_ALU64_##OPCODE##_BPF_X: \ + ALU64_##OPCODE##_X: \ A = A OP X; \ CONT; \ - BPF_ALU_##OPCODE##_BPF_X: \ + ALU_##OPCODE##_X: \ A = (u32) A OP (u32) X; \ CONT; \ - BPF_ALU64_##OPCODE##_BPF_K: \ + ALU64_##OPCODE##_K: \ A = A OP K; \ CONT; \ - BPF_ALU_##OPCODE##_BPF_K: \ + ALU_##OPCODE##_K: \ A = (u32) A OP (u32) K; \ CONT; - ALU(BPF_ADD, +) - ALU(BPF_SUB, -) - ALU(BPF_AND, &) - ALU(BPF_OR, |) - ALU(BPF_LSH, <<) - ALU(BPF_RSH, >>) - ALU(BPF_XOR, ^) - ALU(BPF_MUL, *) + ALU(ADD, +) + ALU(SUB, -) + ALU(AND, &) + ALU(OR, |) + ALU(LSH, <<) + ALU(RSH, >>) + ALU(XOR, ^) + ALU(MUL, *) #undef ALU - BPF_ALU_BPF_NEG_0: + ALU_NEG_0: A = (u32) -A; CONT; - BPF_ALU64_BPF_NEG_0: + ALU64_NEG_0: A = -A; CONT; - BPF_ALU_BPF_MOV_BPF_X: + ALU_MOV_X: A = (u32) X; CONT; - BPF_ALU_BPF_MOV_BPF_K: + ALU_MOV_K: A = (u32) K; CONT; - BPF_ALU64_BPF_MOV_BPF_X: + ALU64_MOV_X: A = X; CONT; - BPF_ALU64_BPF_MOV_BPF_K: + ALU64_MOV_K: A = K; CONT; - BPF_ALU64_BPF_ARSH_BPF_X: + ALU64_ARSH_X: (*(s64 *) &A) >>= X; CONT; - BPF_ALU64_BPF_ARSH_BPF_K: + ALU64_ARSH_K: (*(s64 *) &A) >>= K; CONT; - BPF_ALU64_BPF_MOD_BPF_X: + ALU64_MOD_X: + if (unlikely(X == 0)) + return 0; tmp = A; - if (X) - A = do_div(tmp, X); + A = do_div(tmp, X); CONT; - BPF_ALU_BPF_MOD_BPF_X: + ALU_MOD_X: + if (unlikely(X == 0)) + return 0; tmp = (u32) A; - if (X) - A = do_div(tmp, (u32) X); + A = do_div(tmp, (u32) X); CONT; - BPF_ALU64_BPF_MOD_BPF_K: + ALU64_MOD_K: tmp = A; - if (K) - A = do_div(tmp, K); + A = do_div(tmp, K); CONT; - BPF_ALU_BPF_MOD_BPF_K: + ALU_MOD_K: tmp = (u32) A; - if (K) - A = do_div(tmp, (u32) K); + A = do_div(tmp, (u32) K); CONT; - BPF_ALU64_BPF_DIV_BPF_X: - if (X) - do_div(A, X); + ALU64_DIV_X: + if (unlikely(X == 0)) + return 0; + do_div(A, X); CONT; - BPF_ALU_BPF_DIV_BPF_X: + ALU_DIV_X: + if (unlikely(X == 0)) + return 0; tmp = (u32) A; - if (X) - do_div(tmp, (u32) X); + do_div(tmp, (u32) X); A = (u32) tmp; CONT; - BPF_ALU64_BPF_DIV_BPF_K: - if (K) - do_div(A, K); + ALU64_DIV_K: + do_div(A, K); CONT; - BPF_ALU_BPF_DIV_BPF_K: + ALU_DIV_K: tmp = (u32) A; - if (K) - do_div(tmp, (u32) K); + do_div(tmp, (u32) K); A = (u32) tmp; CONT; - BPF_ALU_BPF_END_BPF_TO_BE: + ALU_END_TO_BE: switch (K) { case 16: A = (__force u16) cpu_to_be16(A); @@ -347,7 +367,7 @@ select_insn: break; } CONT; - BPF_ALU_BPF_END_BPF_TO_LE: + ALU_END_TO_LE: switch (K) { case 16: A = (__force u16) cpu_to_le16(A); @@ -362,142 +382,144 @@ select_insn: CONT; /* CALL */ - BPF_JMP_BPF_CALL_0: - /* Function call scratches R1-R5 registers, preserves R6-R9, - * and stores return value into R0. + JMP_CALL_0: + /* Function call scratches BPF_R1-BPF_R5 registers, + * preserves BPF_R6-BPF_R9, and stores return value + * into BPF_R0. */ - R0 = (__bpf_call_base + insn->imm)(regs[1], regs[2], regs[3], - regs[4], regs[5]); + BPF_R0 = (__bpf_call_base + insn->imm)(BPF_R1, BPF_R2, BPF_R3, + BPF_R4, BPF_R5); CONT; /* JMP */ - BPF_JMP_BPF_JA_0: + JMP_JA_0: insn += insn->off; CONT; - BPF_JMP_BPF_JEQ_BPF_X: + JMP_JEQ_X: if (A == X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JEQ_BPF_K: + JMP_JEQ_K: if (A == K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JNE_BPF_X: + JMP_JNE_X: if (A != X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JNE_BPF_K: + JMP_JNE_K: if (A != K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGT_BPF_X: + JMP_JGT_X: if (A > X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGT_BPF_K: + JMP_JGT_K: if (A > K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGE_BPF_X: + JMP_JGE_X: if (A >= X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JGE_BPF_K: + JMP_JGE_K: if (A >= K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGT_BPF_X: - if (((s64)A) > ((s64)X)) { + JMP_JSGT_X: + if (((s64) A) > ((s64) X)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGT_BPF_K: - if (((s64)A) > ((s64)K)) { + JMP_JSGT_K: + if (((s64) A) > ((s64) K)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGE_BPF_X: - if (((s64)A) >= ((s64)X)) { + JMP_JSGE_X: + if (((s64) A) >= ((s64) X)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSGE_BPF_K: - if (((s64)A) >= ((s64)K)) { + JMP_JSGE_K: + if (((s64) A) >= ((s64) K)) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSET_BPF_X: + JMP_JSET_X: if (A & X) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_JSET_BPF_K: + JMP_JSET_K: if (A & K) { insn += insn->off; CONT_JMP; } CONT; - BPF_JMP_BPF_EXIT_0: - return R0; + JMP_EXIT_0: + return BPF_R0; /* STX and ST and LDX*/ #define LDST(SIZEOP, SIZE) \ - BPF_STX_BPF_MEM_##SIZEOP: \ + STX_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (A + insn->off) = X; \ CONT; \ - BPF_ST_BPF_MEM_##SIZEOP: \ + ST_MEM_##SIZEOP: \ *(SIZE *)(unsigned long) (A + insn->off) = K; \ CONT; \ - BPF_LDX_BPF_MEM_##SIZEOP: \ + LDX_MEM_##SIZEOP: \ A = *(SIZE *)(unsigned long) (X + insn->off); \ CONT; - LDST(BPF_B, u8) - LDST(BPF_H, u16) - LDST(BPF_W, u32) - LDST(BPF_DW, u64) + LDST(B, u8) + LDST(H, u16) + LDST(W, u32) + LDST(DW, u64) #undef LDST - BPF_STX_BPF_XADD_BPF_W: /* lock xadd *(u32 *)(A + insn->off) += X */ + STX_XADD_W: /* lock xadd *(u32 *)(A + insn->off) += X */ atomic_add((u32) X, (atomic_t *)(unsigned long) (A + insn->off)); CONT; - BPF_STX_BPF_XADD_BPF_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ + STX_XADD_DW: /* lock xadd *(u64 *)(A + insn->off) += X */ atomic64_add((u64) X, (atomic64_t *)(unsigned long) (A + insn->off)); CONT; - BPF_LD_BPF_ABS_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + K)) */ + LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + K)) */ off = K; load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only - * appearing in the programs where ctx == skb. All programs - * keep 'ctx' in regs[CTX_REG] == R6, sk_convert_filter() - * saves it in R6, internal BPF verifier will check that - * R6 == ctx. + /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are + * only appearing in the programs where ctx == + * skb. All programs keep 'ctx' in regs[BPF_REG_CTX] + * == BPF_R6, sk_convert_filter() saves it in BPF_R6, + * internal BPF verifier will check that BPF_R6 == + * ctx. * - * BPF_ABS and BPF_IND are wrappers of function calls, so - * they scratch R1-R5 registers, preserve R6-R9, and store - * return value into R0. + * BPF_ABS and BPF_IND are wrappers of function calls, + * so they scratch BPF_R1-BPF_R5 registers, preserve + * BPF_R6-BPF_R9, and store return value into BPF_R0. * * Implicit input: * ctx @@ -507,39 +529,39 @@ load_word: * K == 32-bit immediate * * Output: - * R0 - 8/16/32-bit skb data converted to cpu endianness + * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness */ ptr = load_pointer((struct sk_buff *) ctx, off, 4, &tmp); if (likely(ptr != NULL)) { - R0 = get_unaligned_be32(ptr); + BPF_R0 = get_unaligned_be32(ptr); CONT; } return 0; - BPF_LD_BPF_ABS_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + K)) */ + LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + K)) */ off = K; load_half: ptr = load_pointer((struct sk_buff *) ctx, off, 2, &tmp); if (likely(ptr != NULL)) { - R0 = get_unaligned_be16(ptr); + BPF_R0 = get_unaligned_be16(ptr); CONT; } return 0; - BPF_LD_BPF_ABS_BPF_B: /* R0 = *(u8 *) (ctx + K) */ + LD_ABS_B: /* BPF_R0 = *(u8 *) (ctx + K) */ off = K; load_byte: ptr = load_pointer((struct sk_buff *) ctx, off, 1, &tmp); if (likely(ptr != NULL)) { - R0 = *(u8 *)ptr; + BPF_R0 = *(u8 *)ptr; CONT; } return 0; - BPF_LD_BPF_IND_BPF_W: /* R0 = ntohl(*(u32 *) (skb->data + X + K)) */ + LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + X + K)) */ off = K + X; goto load_word; - BPF_LD_BPF_IND_BPF_H: /* R0 = ntohs(*(u16 *) (skb->data + X + K)) */ + LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + X + K)) */ off = K + X; goto load_half; - BPF_LD_BPF_IND_BPF_B: /* R0 = *(u8 *) (skb->data + X + K) */ + LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + X + K) */ off = K + X; goto load_byte; @@ -547,24 +569,8 @@ load_byte: /* If we ever reach this, we have a bug somewhere. */ WARN_RATELIMIT(1, "unknown opcode %02x\n", insn->code); return 0; -#undef CONT_JMP -#undef CONT - -#undef R0 -#undef X -#undef A -#undef K } -u32 sk_run_filter_int_seccomp(const struct seccomp_data *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); - -u32 sk_run_filter_int_skb(const struct sk_buff *ctx, - const struct sock_filter_int *insni) - __attribute__ ((alias ("__sk_run_filter"))); -EXPORT_SYMBOL_GPL(sk_run_filter_int_skb); - /* Helper to find the offset of pkt_type in sk_buff structure. We want * to make sure its still a 3bit field starting at a byte boundary; * taken from arch/x86/net/bpf_jit_comp.c. @@ -585,64 +591,67 @@ static unsigned int pkt_type_offset(void) return -1; } -static u64 __skb_get_pay_offset(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_pay_offset(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; - - return __skb_get_poff(skb); + return __skb_get_poff((struct sk_buff *)(unsigned long) ctx); } -static u64 __skb_get_nlattr(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_nlattr(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; - if (A > skb->len - sizeof(struct nlattr)) + if (skb->len < sizeof(struct nlattr)) return 0; - nla = nla_find((struct nlattr *) &skb->data[A], skb->len - A, X); + if (a > skb->len - sizeof(struct nlattr)) + return 0; + + nla = nla_find((struct nlattr *) &skb->data[a], skb->len - a, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } -static u64 __skb_get_nlattr_nest(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __skb_get_nlattr_nest(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { - struct sk_buff *skb = (struct sk_buff *)(long) ctx; + struct sk_buff *skb = (struct sk_buff *)(unsigned long) ctx; struct nlattr *nla; if (skb_is_nonlinear(skb)) return 0; - if (A > skb->len - sizeof(struct nlattr)) + if (skb->len < sizeof(struct nlattr)) return 0; - nla = (struct nlattr *) &skb->data[A]; - if (nla->nla_len > A - skb->len) + if (a > skb->len - sizeof(struct nlattr)) return 0; - nla = nla_find_nested(nla, X); + nla = (struct nlattr *) &skb->data[a]; + if (nla->nla_len > skb->len - a) + return 0; + + nla = nla_find_nested(nla, x); if (nla) return (void *) nla - (void *) skb->data; return 0; } -static u64 __get_raw_cpu_id(u64 ctx, u64 A, u64 X, u64 r4, u64 r5) +static u64 __get_raw_cpu_id(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) { return raw_smp_processor_id(); } -/* Register mappings for user programs. */ -#define A_REG 0 -#define X_REG 7 -#define TMP_REG 8 -#define ARG2_REG 2 -#define ARG3_REG 3 +/* note that this only generates 32-bit random numbers */ +static u64 __get_random_u32(u64 ctx, u64 a, u64 x, u64 r4, u64 r5) +{ + return prandom_u32(); +} static bool convert_bpf_extensions(struct sock_filter *fp, struct sock_filter_int **insnp) @@ -653,57 +662,46 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_PROTOCOL: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, protocol); + /* A = *(u16 *) (ctx + offsetof(protocol)) */ + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, protocol)); insn++; /* A = ntohs(A) [emitting a nop or swap16] */ insn->code = BPF_ALU | BPF_END | BPF_FROM_BE; - insn->a_reg = A_REG; + insn->a_reg = BPF_REG_A; insn->imm = 16; break; case SKF_AD_OFF + SKF_AD_PKTTYPE: - insn->code = BPF_LDX | BPF_MEM | BPF_B; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = pkt_type_offset(); + *insn = BPF_LDX_MEM(BPF_B, BPF_REG_A, BPF_REG_CTX, + pkt_type_offset()); if (insn->off < 0) return false; insn++; - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = PKT_TYPE_MAX; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, PKT_TYPE_MAX); break; case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - if (FIELD_SIZEOF(struct sk_buff, dev) == 8) - insn->code = BPF_LDX | BPF_MEM | BPF_DW; - else - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = TMP_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, dev); + *insn = BPF_LDX_MEM(size_to_bpf(FIELD_SIZEOF(struct sk_buff, dev)), + BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, dev)); insn++; - insn->code = BPF_JMP | BPF_JNE | BPF_K; - insn->a_reg = TMP_REG; - insn->imm = 0; - insn->off = 1; + /* if (tmp != 0) goto pc+1 */ + *insn = BPF_JMP_IMM(BPF_JNE, BPF_REG_TMP, 0, 1); insn++; - insn->code = BPF_JMP | BPF_EXIT; + *insn = BPF_EXIT_INSN(); insn++; BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); - insn->a_reg = A_REG; - insn->x_reg = TMP_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_TMP; if (fp->k == SKF_AD_OFF + SKF_AD_IFINDEX) { insn->code = BPF_LDX | BPF_MEM | BPF_W; @@ -717,55 +715,45 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_MARK: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, mark); + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, mark)); break; case SKF_AD_OFF + SKF_AD_RXHASH: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, hash); + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, hash)); break; case SKF_AD_OFF + SKF_AD_QUEUE: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, queue_mapping); + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, queue_mapping)); break; case SKF_AD_OFF + SKF_AD_VLAN_TAG: case SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT: BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); - insn->code = BPF_LDX | BPF_MEM | BPF_H; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = offsetof(struct sk_buff, vlan_tci); + /* A = *(u16 *) (ctx + offsetof(vlan_tci)) */ + *insn = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, + offsetof(struct sk_buff, vlan_tci)); insn++; BUILD_BUG_ON(VLAN_TAG_PRESENT != 0x1000); if (fp->k == SKF_AD_OFF + SKF_AD_VLAN_TAG) { - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = ~VLAN_TAG_PRESENT; + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, + ~VLAN_TAG_PRESENT); } else { - insn->code = BPF_ALU | BPF_RSH | BPF_K; - insn->a_reg = A_REG; - insn->imm = 12; + /* A >>= 12 */ + *insn = BPF_ALU32_IMM(BPF_RSH, BPF_REG_A, 12); insn++; - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = 1; + /* A &= 1 */ + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 1); } break; @@ -773,22 +761,17 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_NLATTR: case SKF_AD_OFF + SKF_AD_NLATTR_NEST: case SKF_AD_OFF + SKF_AD_CPU: + case SKF_AD_OFF + SKF_AD_RANDOM: /* arg1 = ctx */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG1_REG; - insn->x_reg = CTX_REG; + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG1, BPF_REG_CTX); insn++; /* arg2 = A */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG2_REG; - insn->x_reg = A_REG; + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG2, BPF_REG_A); insn++; /* arg3 = X */ - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = ARG3_REG; - insn->x_reg = X_REG; + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_ARG3, BPF_REG_X); insn++; /* Emit call(ctx, arg2=A, arg3=X) */ @@ -806,13 +789,15 @@ static bool convert_bpf_extensions(struct sock_filter *fp, case SKF_AD_OFF + SKF_AD_CPU: insn->imm = __get_raw_cpu_id - __bpf_call_base; break; + case SKF_AD_OFF + SKF_AD_RANDOM: + insn->imm = __get_random_u32 - __bpf_call_base; + break; } break; case SKF_AD_OFF + SKF_AD_ALU_XOR_X: - insn->code = BPF_ALU | BPF_XOR | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = X_REG; + /* A ^= X */ + *insn = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_X); break; default: @@ -862,7 +847,7 @@ int sk_convert_filter(struct sock_filter *prog, int len, u8 bpf_src; BUILD_BUG_ON(BPF_MEMWORDS * sizeof(u32) > MAX_BPF_STACK); - BUILD_BUG_ON(FP_REG + 1 != MAX_BPF_REG); + BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG); if (len <= 0 || len >= BPF_MAXINSNS) return -EINVAL; @@ -878,9 +863,7 @@ do_pass: fp = prog; if (new_insn) { - new_insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - new_insn->a_reg = CTX_REG; - new_insn->x_reg = ARG1_REG; + *new_insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_CTX, BPF_REG_ARG1); } new_insn++; @@ -930,8 +913,8 @@ do_pass: break; insn->code = fp->code; - insn->a_reg = A_REG; - insn->x_reg = X_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_X; insn->imm = fp->k; break; @@ -965,16 +948,16 @@ do_pass: * in compare insn. */ insn->code = BPF_ALU | BPF_MOV | BPF_K; - insn->a_reg = TMP_REG; + insn->a_reg = BPF_REG_TMP; insn->imm = fp->k; insn++; - insn->a_reg = A_REG; - insn->x_reg = TMP_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_TMP; bpf_src = BPF_X; } else { - insn->a_reg = A_REG; - insn->x_reg = X_REG; + insn->a_reg = BPF_REG_A; + insn->x_reg = BPF_REG_X; insn->imm = fp->k; bpf_src = BPF_SRC(fp->code); } @@ -1008,34 +991,28 @@ do_pass: /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ case BPF_LDX | BPF_MSH | BPF_B: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = TMP_REG; - insn->x_reg = A_REG; + /* tmp = A */ + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_TMP, BPF_REG_A); insn++; - insn->code = BPF_LD | BPF_ABS | BPF_B; - insn->a_reg = A_REG; - insn->imm = fp->k; + /* A = BPF_R0 = *(u8 *) (skb->data + K) */ + *insn = BPF_LD_ABS(BPF_B, fp->k); insn++; - insn->code = BPF_ALU | BPF_AND | BPF_K; - insn->a_reg = A_REG; - insn->imm = 0xf; + /* A &= 0xf */ + *insn = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); insn++; - insn->code = BPF_ALU | BPF_LSH | BPF_K; - insn->a_reg = A_REG; - insn->imm = 2; + /* A <<= 2 */ + *insn = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); insn++; - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = X_REG; - insn->x_reg = A_REG; + /* X = A */ + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A); insn++; - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = TMP_REG; + /* A = tmp */ + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_TMP); break; /* RET_K, RET_A are remaped into 2 insns. */ @@ -1045,19 +1022,20 @@ do_pass: (BPF_RVAL(fp->code) == BPF_K ? BPF_K : BPF_X); insn->a_reg = 0; - insn->x_reg = A_REG; + insn->x_reg = BPF_REG_A; insn->imm = fp->k; insn++; - insn->code = BPF_JMP | BPF_EXIT; + *insn = BPF_EXIT_INSN(); break; /* Store to stack. */ case BPF_ST: case BPF_STX: insn->code = BPF_STX | BPF_MEM | BPF_W; - insn->a_reg = FP_REG; - insn->x_reg = fp->code == BPF_ST ? A_REG : X_REG; + insn->a_reg = BPF_REG_FP; + insn->x_reg = fp->code == BPF_ST ? + BPF_REG_A : BPF_REG_X; insn->off = -(BPF_MEMWORDS - fp->k) * 4; break; @@ -1066,8 +1044,8 @@ do_pass: case BPF_LDX | BPF_MEM: insn->code = BPF_LDX | BPF_MEM | BPF_W; insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; - insn->x_reg = FP_REG; + BPF_REG_A : BPF_REG_X; + insn->x_reg = BPF_REG_FP; insn->off = -(BPF_MEMWORDS - fp->k) * 4; break; @@ -1076,22 +1054,18 @@ do_pass: case BPF_LDX | BPF_IMM: insn->code = BPF_ALU | BPF_MOV | BPF_K; insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; + BPF_REG_A : BPF_REG_X; insn->imm = fp->k; break; /* X = A */ case BPF_MISC | BPF_TAX: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = X_REG; - insn->x_reg = A_REG; + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_X, BPF_REG_A); break; /* A = X */ case BPF_MISC | BPF_TXA: - insn->code = BPF_ALU64 | BPF_MOV | BPF_X; - insn->a_reg = A_REG; - insn->x_reg = X_REG; + *insn = BPF_ALU64_REG(BPF_MOV, BPF_REG_A, BPF_REG_X); break; /* A = skb->len or X = skb->len */ @@ -1099,17 +1073,15 @@ do_pass: case BPF_LDX | BPF_W | BPF_LEN: insn->code = BPF_LDX | BPF_MEM | BPF_W; insn->a_reg = BPF_CLASS(fp->code) == BPF_LD ? - A_REG : X_REG; - insn->x_reg = CTX_REG; + BPF_REG_A : BPF_REG_X; + insn->x_reg = BPF_REG_CTX; insn->off = offsetof(struct sk_buff, len); break; /* access seccomp_data fields */ case BPF_LDX | BPF_ABS | BPF_W: - insn->code = BPF_LDX | BPF_MEM | BPF_W; - insn->a_reg = A_REG; - insn->x_reg = CTX_REG; - insn->off = fp->k; + /* A = *(u32 *) (ctx + K) */ + *insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, fp->k); break; default: @@ -1356,6 +1328,7 @@ int sk_chk_filter(struct sock_filter *filter, unsigned int flen) ANCILLARY(VLAN_TAG); ANCILLARY(VLAN_TAG_PRESENT); ANCILLARY(PAY_OFFSET); + ANCILLARY(RANDOM); } /* ancillary operation unknown or unsupported */ @@ -1415,7 +1388,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu) struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); sk_release_orig_filter(fp); - bpf_jit_free(fp); + sk_filter_free(fp); } /** @@ -1453,7 +1426,7 @@ static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp, fp_new = sock_kmalloc(sk, len, GFP_KERNEL); if (fp_new) { - memcpy(fp_new, fp, sizeof(struct sk_filter)); + *fp_new = *fp; /* As we're kepping orig_prog in fp_new along, * we need to make sure we're not evicting it * from the old fp. @@ -1515,7 +1488,6 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, goto out_err_free; } - fp->bpf_func = sk_run_filter_int_skb; fp->len = new_len; /* 2nd pass: remap sock_filter insns into sock_filter_int insns. */ @@ -1528,6 +1500,8 @@ static struct sk_filter *__sk_migrate_filter(struct sk_filter *fp, */ goto out_err_free; + sk_filter_select_runtime(fp); + kfree(old_prog); return fp; @@ -1542,6 +1516,33 @@ out_err: return ERR_PTR(err); } +void __weak bpf_int_jit_compile(struct sk_filter *prog) +{ +} + +/** + * sk_filter_select_runtime - select execution runtime for BPF program + * @fp: sk_filter populated with internal BPF program + * + * try to JIT internal BPF program, if JIT is not available select interpreter + * BPF program will be executed via SK_RUN_FILTER() macro + */ +void sk_filter_select_runtime(struct sk_filter *fp) +{ + fp->bpf_func = (void *) __sk_run_filter; + + /* Probe if internal BPF can be JITed */ + bpf_int_jit_compile(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_select_runtime); + +/* free internal BPF program */ +void sk_filter_free(struct sk_filter *fp) +{ + bpf_jit_free(fp); +} +EXPORT_SYMBOL_GPL(sk_filter_free); + static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp, struct sock *sk) { @@ -1737,10 +1738,10 @@ void sk_decode_filter(struct sock_filter *filt, struct sock_filter *to) [BPF_S_ANC_RXHASH] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_CPU] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_ALU_XOR_X] = BPF_LD|BPF_B|BPF_ABS, - [BPF_S_ANC_SECCOMP_LD_W] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_VLAN_TAG] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_VLAN_TAG_PRESENT] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_ANC_PAY_OFFSET] = BPF_LD|BPF_B|BPF_ABS, + [BPF_S_ANC_RANDOM] = BPF_LD|BPF_B|BPF_ABS, [BPF_S_LD_W_LEN] = BPF_LD|BPF_W|BPF_LEN, [BPF_S_LD_W_IND] = BPF_LD|BPF_W|BPF_IND, [BPF_S_LD_H_IND] = BPF_LD|BPF_H|BPF_IND, diff --git a/net/core/flow.c b/net/core/flow.c index 31cfb36..a0348fd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -455,6 +455,8 @@ int flow_cache_init(struct net *net) if (!fc->percpu) return -ENOMEM; + cpu_notifier_register_begin(); + for_each_online_cpu(i) { if (flow_cache_cpu_prepare(fc, i)) goto err; @@ -462,7 +464,9 @@ int flow_cache_init(struct net *net) fc->hotcpu_notifier = (struct notifier_block){ .notifier_call = flow_cache_cpu, }; - register_hotcpu_notifier(&fc->hotcpu_notifier); + __register_hotcpu_notifier(&fc->hotcpu_notifier); + + cpu_notifier_register_done(); setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, (unsigned long) fc); @@ -478,6 +482,8 @@ err: fcp->hash_table = NULL; } + cpu_notifier_register_done(); + free_percpu(fc->percpu); fc->percpu = NULL; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 4623962..1cac29e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -802,7 +802,7 @@ exit: kobject_put(kobj); return error; } -#endif /* CONFIG_SYFS */ +#endif /* CONFIG_SYSFS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 81d3a9a..05e949d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -273,7 +273,7 @@ static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp; - LIST_HEAD(net_kill_list); + struct list_head net_kill_list; LIST_HEAD(net_exit_list); /* Atomically snapshot the list of namespaces to cleanup */ diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 719efd5..22931e1 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -23,7 +23,7 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state struct cgroup_cls_state *task_cls_state(struct task_struct *p) { - return css_cls_state(task_css(p, net_cls_subsys_id)); + return css_cls_state(task_css(p, net_cls_cgrp_id)); } EXPORT_SYMBOL_GPL(task_cls_state); @@ -73,7 +73,7 @@ static void cgrp_attach(struct cgroup_subsys_state *css, void *v = (void *)(unsigned long)cs->classid; struct task_struct *p; - cgroup_taskset_for_each(p, css, tset) { + cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_classid, v); task_unlock(p); @@ -102,19 +102,10 @@ static struct cftype ss_files[] = { { } /* terminate */ }; -struct cgroup_subsys net_cls_subsys = { - .name = "net_cls", +struct cgroup_subsys net_cls_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = cgrp_attach, - .subsys_id = net_cls_subsys_id, .base_cftypes = ss_files, - .module = THIS_MODULE, }; - -static int __init init_netclassid_cgroup(void) -{ - return cgroup_load_subsys(&net_cls_subsys); -} -__initcall(init_netclassid_cgroup); diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 9043cae..3825f66 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -186,7 +186,7 @@ static int read_priomap(struct seq_file *sf, void *v) } static int write_priomap(struct cgroup_subsys_state *css, struct cftype *cft, - const char *buffer) + char *buffer) { char devname[IFNAMSIZ + 1]; struct net_device *dev; @@ -224,7 +224,7 @@ static void net_prio_attach(struct cgroup_subsys_state *css, struct task_struct *p; void *v = (void *)(unsigned long)css->cgroup->id; - cgroup_taskset_for_each(p, css, tset) { + cgroup_taskset_for_each(p, tset) { task_lock(p); iterate_fd(p->files, 0, update_netprio, v); task_unlock(p); @@ -244,15 +244,12 @@ static struct cftype ss_files[] = { { } /* terminate */ }; -struct cgroup_subsys net_prio_subsys = { - .name = "net_prio", +struct cgroup_subsys net_prio_cgrp_subsys = { .css_alloc = cgrp_css_alloc, .css_online = cgrp_css_online, .css_free = cgrp_css_free, .attach = net_prio_attach, - .subsys_id = net_prio_subsys_id, .base_cftypes = ss_files, - .module = THIS_MODULE, }; static int netprio_device_event(struct notifier_block *unused, @@ -283,37 +280,9 @@ static struct notifier_block netprio_device_notifier = { static int __init init_cgroup_netprio(void) { - int ret; - - ret = cgroup_load_subsys(&net_prio_subsys); - if (ret) - goto out; - register_netdevice_notifier(&netprio_device_notifier); - -out: - return ret; -} - -static void __exit exit_cgroup_netprio(void) -{ - struct netprio_map *old; - struct net_device *dev; - - unregister_netdevice_notifier(&netprio_device_notifier); - - cgroup_unload_subsys(&net_prio_subsys); - - rtnl_lock(); - for_each_netdev(&init_net, dev) { - old = rtnl_dereference(dev->priomap); - RCU_INIT_POINTER(dev->priomap, NULL); - if (old) - kfree_rcu(old, rcu); - } - rtnl_unlock(); + return 0; } -module_init(init_cgroup_netprio); -module_exit(exit_cgroup_netprio); +subsys_initcall(init_cgroup_netprio); MODULE_LICENSE("GPL v2"); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d0dac57..fc17a9d 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -573,7 +573,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) is_zero_ether_addr(pkt_dev->src_mac) ? pkt_dev->odev->dev_addr : pkt_dev->src_mac); - seq_printf(seq, "dst_mac: "); + seq_puts(seq, "dst_mac: "); seq_printf(seq, "%pM\n", pkt_dev->dst_mac); seq_printf(seq, @@ -588,7 +588,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->nr_labels) { unsigned int i; - seq_printf(seq, " mpls: "); + seq_puts(seq, " mpls: "); for (i = 0; i < pkt_dev->nr_labels; i++) seq_printf(seq, "%08x%s", ntohl(pkt_dev->labels[i]), i == pkt_dev->nr_labels-1 ? "\n" : ", "); @@ -613,67 +613,67 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->node >= 0) seq_printf(seq, " node: %d\n", pkt_dev->node); - seq_printf(seq, " Flags: "); + seq_puts(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) - seq_printf(seq, "IPV6 "); + seq_puts(seq, "IPV6 "); if (pkt_dev->flags & F_IPSRC_RND) - seq_printf(seq, "IPSRC_RND "); + seq_puts(seq, "IPSRC_RND "); if (pkt_dev->flags & F_IPDST_RND) - seq_printf(seq, "IPDST_RND "); + seq_puts(seq, "IPDST_RND "); if (pkt_dev->flags & F_TXSIZE_RND) - seq_printf(seq, "TXSIZE_RND "); + seq_puts(seq, "TXSIZE_RND "); if (pkt_dev->flags & F_UDPSRC_RND) - seq_printf(seq, "UDPSRC_RND "); + seq_puts(seq, "UDPSRC_RND "); if (pkt_dev->flags & F_UDPDST_RND) - seq_printf(seq, "UDPDST_RND "); + seq_puts(seq, "UDPDST_RND "); if (pkt_dev->flags & F_UDPCSUM) - seq_printf(seq, "UDPCSUM "); + seq_puts(seq, "UDPCSUM "); if (pkt_dev->flags & F_MPLS_RND) - seq_printf(seq, "MPLS_RND "); + seq_puts(seq, "MPLS_RND "); if (pkt_dev->flags & F_QUEUE_MAP_RND) - seq_printf(seq, "QUEUE_MAP_RND "); + seq_puts(seq, "QUEUE_MAP_RND "); if (pkt_dev->flags & F_QUEUE_MAP_CPU) - seq_printf(seq, "QUEUE_MAP_CPU "); + seq_puts(seq, "QUEUE_MAP_CPU "); if (pkt_dev->cflows) { if (pkt_dev->flags & F_FLOW_SEQ) - seq_printf(seq, "FLOW_SEQ "); /*in sequence flows*/ + seq_puts(seq, "FLOW_SEQ "); /*in sequence flows*/ else - seq_printf(seq, "FLOW_RND "); + seq_puts(seq, "FLOW_RND "); } #ifdef CONFIG_XFRM if (pkt_dev->flags & F_IPSEC_ON) { - seq_printf(seq, "IPSEC "); + seq_puts(seq, "IPSEC "); if (pkt_dev->spi) seq_printf(seq, "spi:%u", pkt_dev->spi); } #endif if (pkt_dev->flags & F_MACSRC_RND) - seq_printf(seq, "MACSRC_RND "); + seq_puts(seq, "MACSRC_RND "); if (pkt_dev->flags & F_MACDST_RND) - seq_printf(seq, "MACDST_RND "); + seq_puts(seq, "MACDST_RND "); if (pkt_dev->flags & F_VID_RND) - seq_printf(seq, "VID_RND "); + seq_puts(seq, "VID_RND "); if (pkt_dev->flags & F_SVID_RND) - seq_printf(seq, "SVID_RND "); + seq_puts(seq, "SVID_RND "); if (pkt_dev->flags & F_NODE) - seq_printf(seq, "NODE_ALLOC "); + seq_puts(seq, "NODE_ALLOC "); seq_puts(seq, "\n"); @@ -716,7 +716,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->result[0]) seq_printf(seq, "Result: %s\n", pkt_dev->result); else - seq_printf(seq, "Result: Idle\n"); + seq_puts(seq, "Result: Idle\n"); return 0; } @@ -1735,14 +1735,14 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) BUG_ON(!t); - seq_printf(seq, "Running: "); + seq_puts(seq, "Running: "); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) seq_printf(seq, "%s ", pkt_dev->odevname); - seq_printf(seq, "\nStopped: "); + seq_puts(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) @@ -1751,7 +1751,7 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); else - seq_printf(seq, "\nResult: NA\n"); + seq_puts(seq, "\nResult: NA\n"); if_unlock(t); @@ -3338,9 +3338,11 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) queue_map = skb_get_queue_mapping(pkt_dev->skb); txq = netdev_get_tx_queue(odev, queue_map); - __netif_tx_lock_bh(txq); + local_bh_disable(); - if (unlikely(netif_xmit_frozen_or_stopped(txq))) { + HARD_TX_LOCK(odev, txq, smp_processor_id()); + + if (unlikely(netif_xmit_frozen_or_drv_stopped(txq))) { ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; @@ -3374,7 +3376,9 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 0; } unlock: - __netif_tx_unlock_bh(txq); + HARD_TX_UNLOCK(odev, txq); + + local_bh_enable(); /* If pkt_dev->count is zero, then run forever */ if ((pkt_dev->count != 0) && (pkt_dev->sofar >= pkt_dev->count)) { diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index eaba0f6..37d8615 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -88,7 +88,7 @@ EXPORT_SYMBOL_GPL(ptp_classify_raw); void __init ptp_classifier_init(void) { - static struct sock_filter ptp_filter[] = { + static struct sock_filter ptp_filter[] __initdata = { { 0x28, 0, 0, 0x0000000c }, { 0x15, 0, 12, 0x00000800 }, { 0x30, 0, 0, 0x00000017 }, diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d4ff417..9837beb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -774,7 +774,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, return 0; } -static size_t rtnl_port_size(const struct net_device *dev) +static size_t rtnl_port_size(const struct net_device *dev, + u32 ext_filter_mask) { size_t port_size = nla_total_size(4) /* PORT_VF */ + nla_total_size(PORT_PROFILE_MAX) /* PORT_PROFILE */ @@ -790,7 +791,8 @@ static size_t rtnl_port_size(const struct net_device *dev) size_t port_self_size = nla_total_size(sizeof(struct nlattr)) + port_size; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; if (dev_num_vf(dev->dev.parent)) return port_self_size + vf_ports_size + @@ -826,7 +828,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(ext_filter_mask & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ - + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + + rtnl_port_size(dev, ext_filter_mask) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ @@ -888,11 +890,13 @@ static int rtnl_port_self_fill(struct sk_buff *skb, struct net_device *dev) return 0; } -static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) +static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev, + u32 ext_filter_mask) { int err; - if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent) + if (!dev->netdev_ops->ndo_get_vf_port || !dev->dev.parent || + !(ext_filter_mask & RTEXT_FILTER_VF)) return 0; err = rtnl_port_self_fill(skb, dev); @@ -1079,7 +1083,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, nla_nest_end(skb, vfinfo); } - if (rtnl_port_fill(skb, dev)) + if (rtnl_port_fill(skb, dev, ext_filter_mask)) goto nla_put_failure; if (dev->rtnl_link_ops || rtnl_have_link_slave_info(dev)) { @@ -1198,6 +1202,7 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) struct hlist_head *head; struct nlattr *tb[IFLA_MAX+1]; u32 ext_filter_mask = 0; + int err; s_h = cb->args[0]; s_idx = cb->args[1]; @@ -1218,11 +1223,17 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI, - ext_filter_mask) <= 0) + err = rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI, + ext_filter_mask); + /* If we ran out of room on the first message, + * we're in trouble + */ + WARN_ON((err == -EMSGSIZE) && (skb->len == 0)); + + if (err <= 0) goto out; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -1395,7 +1406,8 @@ static int do_set_master(struct net_device *dev, int ifindex) return 0; } -static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, +static int do_setlink(const struct sk_buff *skb, + struct net_device *dev, struct ifinfomsg *ifm, struct nlattr **tb, char *ifname, int modified) { const struct net_device_ops *ops = dev->netdev_ops; @@ -1407,7 +1419,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, err = PTR_ERR(net); goto errout; } - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) { + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { err = -EPERM; goto errout; } @@ -1661,7 +1673,7 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh) if (err < 0) goto errout; - err = do_setlink(dev, ifm, tb, ifname, 0); + err = do_setlink(skb, dev, ifm, tb, ifname, 0); errout: return err; } @@ -1778,7 +1790,8 @@ err: } EXPORT_SYMBOL(rtnl_create_link); -static int rtnl_group_changelink(struct net *net, int group, +static int rtnl_group_changelink(const struct sk_buff *skb, + struct net *net, int group, struct ifinfomsg *ifm, struct nlattr **tb) { @@ -1787,7 +1800,7 @@ static int rtnl_group_changelink(struct net *net, int group, for_each_netdev(net, dev) { if (dev->group == group) { - err = do_setlink(dev, ifm, tb, NULL, 0); + err = do_setlink(skb, dev, ifm, tb, NULL, 0); if (err < 0) return err; } @@ -1929,12 +1942,12 @@ replay: modified = 1; } - return do_setlink(dev, ifm, tb, ifname, modified); + return do_setlink(skb, dev, ifm, tb, ifname, modified); } if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) - return rtnl_group_changelink(net, + return rtnl_group_changelink(skb, net, nla_get_u32(tb[IFLA_GROUP]), ifm, tb); return -ENODEV; @@ -2321,7 +2334,7 @@ static int rtnl_fdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) int err = -EINVAL; __u8 *addr; - if (!capable(CAP_NET_ADMIN)) + if (!netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); @@ -2773,7 +2786,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) sz_idx = type>>2; kind = type&3; - if (kind != 2 && !ns_capable(net->user_ns, CAP_NET_ADMIN)) + if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 30c7d35..3d74530 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -694,7 +694,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif memcpy(new->cb, old->cb, sizeof(old->cb)); new->csum = old->csum; - new->local_df = old->local_df; + new->ignore_df = old->ignore_df; new->pkt_type = old->pkt_type; new->ip_summed = old->ip_summed; skb_copy_queue_mapping(new, old); @@ -3458,8 +3458,6 @@ static void sock_rmem_free(struct sk_buff *skb) */ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { - int len = skb->len; - if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned int)sk->sk_rcvbuf) return -ENOMEM; @@ -3474,7 +3472,7 @@ int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) skb_queue_tail(&sk->sk_error_queue, skb); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_err_skb); @@ -3915,7 +3913,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet) skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; - skb->local_df = 0; + skb->ignore_df = 0; skb_dst_drop(skb); skb->mark = 0; secpath_reset(skb); @@ -3937,12 +3935,14 @@ EXPORT_SYMBOL_GPL(skb_scrub_packet); unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) { const struct skb_shared_info *shinfo = skb_shinfo(skb); - unsigned int hdr_len; if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))) - hdr_len = tcp_hdrlen(skb); - else - hdr_len = sizeof(struct udphdr); - return hdr_len + shinfo->gso_size; + return tcp_hdrlen(skb) + shinfo->gso_size; + + /* UFO sets gso_size to the size of the fragmentation + * payload, i.e. the size of the L4 (UDP) header is already + * accounted for. + */ + return shinfo->gso_size; } EXPORT_SYMBOL_GPL(skb_gso_transport_seglen); diff --git a/net/core/sock.c b/net/core/sock.c index c0fc6bd..664ee42 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -145,6 +145,55 @@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list); +/** + * sk_ns_capable - General socket capability test + * @sk: Socket to use a capability on or through + * @user_ns: The user namespace of the capability to use + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in the user + * namespace @user_ns. + */ +bool sk_ns_capable(const struct sock *sk, + struct user_namespace *user_ns, int cap) +{ + return file_ns_capable(sk->sk_socket->file, user_ns, cap) && + ns_capable(user_ns, cap); +} +EXPORT_SYMBOL(sk_ns_capable); + +/** + * sk_capable - Socket global capability test + * @sk: Socket to use a capability on or through + * @cap: The global capbility to use + * + * Test to see if the opener of the socket had when the socket was + * created and the current process has the capability @cap in all user + * namespaces. + */ +bool sk_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, &init_user_ns, cap); +} +EXPORT_SYMBOL(sk_capable); + +/** + * sk_net_capable - Network namespace socket capability test + * @sk: Socket to use a capability on or through + * @cap: The capability to use + * + * Test to see if the opener of the socket had when the socke was created + * and the current process has the capability @cap over the network namespace + * the socket is a member of. + */ +bool sk_net_capable(const struct sock *sk, int cap) +{ + return sk_ns_capable(sk, sock_net(sk)->user_ns, cap); +} +EXPORT_SYMBOL(sk_net_capable); + + #ifdef CONFIG_MEMCG_KMEM int mem_cgroup_sockets_init(struct mem_cgroup *memcg, struct cgroup_subsys *ss) { @@ -428,7 +477,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk, skb_len); + sk->sk_data_ready(sk); return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -2196,7 +2245,7 @@ static void sock_def_error_report(struct sock *sk) rcu_read_unlock(); } -static void sock_def_readable(struct sock *sk, int len) +static void sock_def_readable(struct sock *sk) { struct socket_wq *wq; diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index d7af188..a4216a4 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -49,7 +49,7 @@ int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype) } EXPORT_SYMBOL_GPL(sock_diag_put_meminfo); -int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, +int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk, struct sk_buff *skb, int attrtype) { struct sock_fprog_kern *fprog; @@ -58,7 +58,7 @@ int sock_diag_put_filterinfo(struct user_namespace *user_ns, struct sock *sk, unsigned int flen; int err = 0; - if (!ns_capable(user_ns, CAP_NET_ADMIN)) { + if (!may_report_filterinfo) { nla_reserve(skb, attrtype, 0); return 0; } |