diff options
-rw-r--r-- | drivers/net/ethernet/broadcom/tg3.c | 32 | ||||
-rw-r--r-- | drivers/net/ethernet/broadcom/tg3.h | 2 | ||||
-rw-r--r-- | drivers/net/ppp/ppp_generic.c | 3 | ||||
-rw-r--r-- | include/linux/netdev_features.h | 3 | ||||
-rw-r--r-- | include/linux/netdevice.h | 2 | ||||
-rw-r--r-- | include/linux/skbuff.h | 27 | ||||
-rw-r--r-- | net/core/dev.c | 80 | ||||
-rw-r--r-- | net/core/ethtool.c | 1 | ||||
-rw-r--r-- | net/core/skbuff.c | 6 | ||||
-rw-r--r-- | net/ipv4/af_inet.c | 1 | ||||
-rw-r--r-- | net/ipv4/ah4.c | 3 | ||||
-rw-r--r-- | net/ipv4/gre.c | 118 | ||||
-rw-r--r-- | net/ipv4/ip_fragment.c | 2 | ||||
-rw-r--r-- | net/ipv4/ip_gre.c | 82 | ||||
-rw-r--r-- | net/ipv4/tcp.c | 1 | ||||
-rw-r--r-- | net/ipv4/tcp_output.c | 2 | ||||
-rw-r--r-- | net/ipv4/udp.c | 3 | ||||
-rw-r--r-- | net/ipv4/xfrm4_input.c | 2 | ||||
-rw-r--r-- | net/ipv4/xfrm4_mode_tunnel.c | 3 | ||||
-rw-r--r-- | net/ipv6/ah6.c | 3 | ||||
-rw-r--r-- | net/ipv6/ip6_offload.c | 1 | ||||
-rw-r--r-- | net/ipv6/netfilter/nf_conntrack_reasm.c | 2 | ||||
-rw-r--r-- | net/ipv6/reassembly.c | 2 | ||||
-rw-r--r-- | net/ipv6/udp_offload.c | 3 | ||||
-rw-r--r-- | net/ipv6/xfrm6_mode_tunnel.c | 3 | ||||
-rw-r--r-- | net/sched/act_ipt.c | 6 | ||||
-rw-r--r-- | net/sched/act_pedit.c | 3 |
27 files changed, 327 insertions, 69 deletions
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index b1b3bc01cbc..1b5987676f7 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -94,10 +94,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits) #define DRV_MODULE_NAME "tg3" #define TG3_MAJ_NUM 3 -#define TG3_MIN_NUM 129 +#define TG3_MIN_NUM 130 #define DRV_MODULE_VERSION \ __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM) -#define DRV_MODULE_RELDATE "January 06, 2013" +#define DRV_MODULE_RELDATE "February 14, 2013" #define RESET_KIND_SHUTDOWN 0 #define RESET_KIND_INIT 1 @@ -332,6 +332,7 @@ static DEFINE_PCI_DEVICE_TABLE(tg3_pci_tbl) = { {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5719)}, {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5720)}, {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57762)}, + {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_57766)}, {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5762)}, {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5725)}, {PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, TG3PCI_DEVICE_TIGON3_5727)}, @@ -9179,7 +9180,14 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) } if (GET_CHIP_REV(tp->pci_chip_rev_id) != CHIPREV_57765_AX) { - u32 grc_mode = tr32(GRC_MODE); + u32 grc_mode; + + /* Fix transmit hangs */ + val = tr32(TG3_CPMU_PADRNG_CTL); + val |= TG3_CPMU_PADRNG_CTL_RDIV2; + tw32(TG3_CPMU_PADRNG_CTL, val); + + grc_mode = tr32(GRC_MODE); /* Access the lower 1K of DL PCIE block registers. */ val = grc_mode & ~GRC_MODE_PCIE_PORT_MASK; @@ -9492,6 +9500,14 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) if (tg3_flag(tp, PCI_EXPRESS)) rdmac_mode |= RDMAC_MODE_FIFO_LONG_BURST; + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57766) { + tp->dma_limit = 0; + if (tp->dev->mtu <= ETH_DATA_LEN) { + rdmac_mode |= RDMAC_MODE_JMB_2K_MMRR; + tp->dma_limit = TG3_TX_BD_DMA_MAX_2K; + } + } + if (tg3_flag(tp, HW_TSO_1) || tg3_flag(tp, HW_TSO_2) || tg3_flag(tp, HW_TSO_3)) @@ -13867,7 +13883,8 @@ static void tg3_get_5720_nvram_info(struct tg3 *tp) tp->nvram_size = TG3_NVRAM_SIZE_1MB; break; default: - tp->nvram_size = TG3_NVRAM_SIZE_128KB; + if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5762) + tp->nvram_size = TG3_NVRAM_SIZE_128KB; break; } break; @@ -13913,7 +13930,8 @@ static void tg3_get_5720_nvram_info(struct tg3 *tp) tp->nvram_size = TG3_NVRAM_SIZE_1MB; break; default: - tp->nvram_size = TG3_NVRAM_SIZE_128KB; + if (GET_ASIC_REV(tp->pci_chip_rev_id) != ASIC_REV_5762) + tp->nvram_size = TG3_NVRAM_SIZE_128KB; break; } break; @@ -14498,7 +14516,7 @@ static int tg3_phy_probe(struct tg3 *tp) (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5720 || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5762 || - (tp->pdev->device == TG3PCI_DEVICE_TIGON3_5718 && + (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 && tp->pci_chip_rev_id != CHIPREV_ID_5717_A0) || (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765 && tp->pci_chip_rev_id != CHIPREV_ID_57765_A0))) @@ -16884,6 +16902,8 @@ static int tg3_init_one(struct pci_dev *pdev, tg3_timer_init(tp); + tg3_carrier_off(tp); + err = register_netdev(dev); if (err) { dev_err(&pdev->dev, "Cannot register net device, aborting\n"); diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index ef6ced2bf9c..b6767286d23 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -1164,6 +1164,8 @@ #define CPMU_MUTEX_GNT_DRIVER 0x00001000 #define TG3_CPMU_PHY_STRAP 0x00003664 #define TG3_CPMU_PHY_STRAP_IS_SERDES 0x00000020 +#define TG3_CPMU_PADRNG_CTL 0x00003668 +#define TG3_CPMU_PADRNG_CTL_RDIV2 0x00040000 /* 0x3664 --> 0x36b0 unused */ #define TG3_CPMU_EEE_MODE 0x000036b0 diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 0b2706abe3e..4fd754e74eb 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -1805,8 +1805,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) /* the filter instructions are constructed assuming a four-byte PPP header on each packet */ if (ppp->pass_filter || ppp->active_filter) { - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto err; *skb_push(skb, 2) = 0; diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 5ac32123035..3dd39340430 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -41,7 +41,7 @@ enum { NETIF_F_TSO_ECN_BIT, /* ... TCP ECN support */ NETIF_F_TSO6_BIT, /* ... TCPv6 segmentation */ NETIF_F_FSO_BIT, /* ... FCoE segmentation */ - NETIF_F_GSO_RESERVED1, /* ... free (fill GSO_MASK to 8 bits) */ + NETIF_F_GSO_GRE_BIT, /* ... GRE with TSO */ /**/NETIF_F_GSO_LAST, /* [can't be last bit, see GSO_MASK] */ NETIF_F_GSO_RESERVED2 /* ... free (fill GSO_MASK to 8 bits) */ = NETIF_F_GSO_LAST, @@ -102,6 +102,7 @@ enum { #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) #define NETIF_F_RXALL __NETIF_F(RXALL) +#define NETIF_F_GRE_GSO __NETIF_F(GSO_GRE) /* Features valid for ethtool to change */ /* = all defined minus driver/device-class-related */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9deb672d999..920361bc27e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2671,6 +2671,8 @@ extern void netdev_upper_dev_unlink(struct net_device *dev, extern int skb_checksum_help(struct sk_buff *skb); extern struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); +extern struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features); static inline struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9da99520ccd..821c7f45d2a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -314,6 +314,8 @@ enum { SKB_GSO_TCPV6 = 1 << 4, SKB_GSO_FCOE = 1 << 5, + + SKB_GSO_GRE = 1 << 6, }; #if BITS_PER_LONG > 32 @@ -804,6 +806,16 @@ static inline int skb_cloned(const struct sk_buff *skb) (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1; } +static inline int skb_unclone(struct sk_buff *skb, gfp_t pri) +{ + might_sleep_if(pri & __GFP_WAIT); + + if (skb_cloned(skb)) + return pskb_expand_head(skb, 0, 0, pri); + + return 0; +} + /** * skb_header_cloned - is the header a clone * @skb: buffer to check @@ -2722,6 +2734,21 @@ static inline struct sec_path *skb_sec_path(struct sk_buff *skb) } #endif +/* Keeps track of mac header offset relative to skb->head. + * It is useful for TSO of Tunneling protocol. e.g. GRE. + * For non-tunnel skb it points to skb_mac_header() and for + * tunnel skb it points to outer mac header. */ +struct skb_gso_cb { + int mac_offset; +}; +#define SKB_GSO_CB(skb) ((struct skb_gso_cb *)(skb)->cb) + +static inline int skb_tnl_header_len(const struct sk_buff *inner_skb) +{ + return (skb_mac_header(inner_skb) - inner_skb->head) - + SKB_GSO_CB(inner_skb)->mac_offset; +} + static inline bool skb_is_gso(const struct sk_buff *skb) { return skb_shinfo(skb)->gso_size; diff --git a/net/core/dev.c b/net/core/dev.c index f44473696b8..1cd6297fd34 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2327,37 +2327,20 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/* openvswitch calls this on rx path, so we need a different check. - */ -static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) -{ - if (tx_path) - return skb->ip_summed != CHECKSUM_PARTIAL; - else - return skb->ip_summed == CHECKSUM_NONE; -} - /** - * __skb_gso_segment - Perform segmentation on skb. + * skb_mac_gso_segment - mac layer segmentation handler. * @skb: buffer to segment * @features: features for the output path (see dev->features) - * @tx_path: whether it is called in TX path - * - * This function segments the given skb and returns a list of segments. - * - * It may return NULL if the skb requires no segmentation. This is - * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *__skb_gso_segment(struct sk_buff *skb, - netdev_features_t features, bool tx_path) +struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_offload *ptype; __be16 type = skb->protocol; - int vlan_depth = ETH_HLEN; - int err; while (type == htons(ETH_P_8021Q)) { + int vlan_depth = ETH_HLEN; struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) @@ -2368,22 +2351,14 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, vlan_depth += VLAN_HLEN; } - skb_reset_mac_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); - if (unlikely(skb_needs_check(skb, tx_path))) { - skb_warn_bad_offload(skb); - - if (skb_header_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) - return ERR_PTR(err); - } - rcu_read_lock(); list_for_each_entry_rcu(ptype, &offload_base, list) { if (ptype->type == type && ptype->callbacks.gso_segment) { if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + int err; + err = ptype->callbacks.gso_send_check(skb); segs = ERR_PTR(err); if (err || skb_gso_ok(skb, features)) @@ -2401,6 +2376,49 @@ struct sk_buff *__skb_gso_segment(struct sk_buff *skb, return segs; } +EXPORT_SYMBOL(skb_mac_gso_segment); + + +/* openvswitch calls this on rx path, so we need a different check. + */ +static inline bool skb_needs_check(struct sk_buff *skb, bool tx_path) +{ + if (tx_path) + return skb->ip_summed != CHECKSUM_PARTIAL; + else + return skb->ip_summed == CHECKSUM_NONE; +} + +/** + * __skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + * @tx_path: whether it is called in TX path + * + * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. + */ +struct sk_buff *__skb_gso_segment(struct sk_buff *skb, + netdev_features_t features, bool tx_path) +{ + if (unlikely(skb_needs_check(skb, tx_path))) { + int err; + + skb_warn_bad_offload(skb); + + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + + SKB_GSO_CB(skb)->mac_offset = skb_headroom(skb); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return skb_mac_gso_segment(skb, features); +} EXPORT_SYMBOL(__skb_gso_segment); /* Take action when hardware reception checksum errors are detected. */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d9d55209db6..3e9b2c3e30f 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -77,6 +77,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", + [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CSUM_BIT] = "tx-checksum-sctp", diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 6c1ad09f879..2a3ca33c30a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2738,6 +2738,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int doffset = skb->data - skb_mac_header(skb); unsigned int offset = doffset; + unsigned int tnl_hlen = skb_tnl_header_len(skb); unsigned int headroom; unsigned int len; int sg = !!(features & NETIF_F_SG); @@ -2814,7 +2815,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, netdev_features_t features) skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + skb_network_header_len(skb)); - skb_copy_from_linear_data(skb, nskb->data, doffset); + + skb_copy_from_linear_data_offset(skb, -tnl_hlen, + nskb->data - tnl_hlen, + doffset + tnl_hlen); if (fskb != skb_shinfo(skb)->frag_list) continue; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e6e5d850633..e225a4e5b57 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1287,6 +1287,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb, SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | 0))) goto out; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index a69b4e4a02b..2e7f1948216 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -321,8 +321,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index 42a491055c7..7a4c710c4cd 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -19,6 +19,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/netdevice.h> +#include <linux/if_tunnel.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> @@ -26,6 +27,11 @@ static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; static DEFINE_SPINLOCK(gre_proto_lock); +struct gre_base_hdr { + __be16 flags; + __be16 protocol; +}; +#define GRE_HEADER_SECTION 4 int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info) rcu_read_unlock(); } +static struct sk_buff *gre_gso_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + netdev_features_t enc_features; + int ghl = GRE_HEADER_SECTION; + struct gre_base_hdr *greh; + int mac_len = skb->mac_len; + int tnl_hlen; + bool csum; + + if (unlikely(skb_shinfo(skb)->gso_type & + ~(SKB_GSO_TCPV4 | + SKB_GSO_TCPV6 | + SKB_GSO_UDP | + SKB_GSO_DODGY | + SKB_GSO_TCP_ECN | + SKB_GSO_GRE))) + goto out; + + if (unlikely(!pskb_may_pull(skb, sizeof(*greh)))) + goto out; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + + if (greh->flags & GRE_KEY) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_SEQ) + ghl += GRE_HEADER_SECTION; + if (greh->flags & GRE_CSUM) { + ghl += GRE_HEADER_SECTION; + csum = true; + } else + csum = false; + + /* setup inner skb. */ + if (greh->protocol == htons(ETH_P_TEB)) { + struct ethhdr *eth = eth_hdr(skb); + skb->protocol = eth->h_proto; + } else { + skb->protocol = greh->protocol; + } + + skb->encapsulation = 0; + + if (unlikely(!pskb_may_pull(skb, ghl))) + goto out; + __skb_pull(skb, ghl); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (!segs || IS_ERR(segs)) + goto out; + + skb = segs; + tnl_hlen = skb_tnl_header_len(skb); + do { + __skb_push(skb, ghl); + if (csum) { + __be32 *pcsum; + + if (skb_has_shared_frag(skb)) { + int err; + + err = __skb_linearize(skb); + if (err) { + kfree_skb(segs); + segs = ERR_PTR(err); + goto out; + } + } + + greh = (struct gre_base_hdr *)(skb->data); + pcsum = (__be32 *)(greh + 1); + *pcsum = 0; + *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0)); + } + __skb_push(skb, tnl_hlen - ghl); + + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb->mac_len = mac_len; + } while ((skb = skb->next)); +out: + return segs; +} + +static int gre_gso_send_check(struct sk_buff *skb) +{ + if (!skb->encapsulation) + return -EINVAL; + return 0; +} + static const struct net_protocol net_gre_protocol = { .handler = gre_rcv, .err_handler = gre_err, .netns_ok = 1, }; +static const struct net_offload gre_offload = { + .callbacks = { + .gso_send_check = gre_gso_send_check, + .gso_segment = gre_gso_segment, + }, +}; + static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); @@ -127,11 +238,18 @@ static int __init gre_init(void) return -EAGAIN; } + if (inet_add_offload(&gre_offload, IPPROTO_GRE)) { + pr_err("can't add protocol offload\n"); + inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); + return -EAGAIN; + } + return 0; } static void __exit gre_exit(void) { + inet_del_offload(&gre_offload, IPPROTO_GRE); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1211613c6c3..b6d30acb600 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -590,7 +590,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_nomem; /* If the first fragment is fragmented itself, we split diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 00a14b9864e..a56f1182c17 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -735,8 +735,33 @@ drop: return 0; } +static struct sk_buff *handle_offloads(struct sk_buff *skb) +{ + int err; + + if (skb_is_gso(skb)) { + err = skb_unclone(skb, GFP_ATOMIC); + if (unlikely(err)) + goto error; + skb_shinfo(skb)->gso_type |= SKB_GSO_GRE; + return skb; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + err = skb_checksum_help(skb); + if (unlikely(err)) + goto error; + } + skb->ip_summed = CHECKSUM_NONE; + + return skb; + +error: + kfree_skb(skb); + return ERR_PTR(err); +} + static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { + struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats); struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *old_iph; const struct iphdr *tiph; @@ -751,10 +776,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev __be32 dst; int mtu; u8 ttl; + int err; + int pkt_len; - if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_help(skb)) - goto tx_error; + skb = handle_offloads(skb); + if (IS_ERR(skb)) { + dev->stats.tx_dropped++; + return NETDEV_TX_OK; + } + + if (!skb->encapsulation) { + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + } old_iph = ip_hdr(skb); @@ -855,7 +889,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb->protocol == htons(ETH_P_IP)) { df |= (old_iph->frag_off&htons(IP_DF)); - if ((old_iph->frag_off&htons(IP_DF)) && + if (!skb_is_gso(skb) && + (old_iph->frag_off&htons(IP_DF)) && mtu < ntohs(old_iph->tot_len)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); @@ -875,7 +910,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) { + if (!skb_is_gso(skb) && + mtu >= IPV6_MIN_MTU && + mtu < skb->len - tunnel->hlen + gre_hlen) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); ip_rt_put(rt); goto tx_error; @@ -936,6 +973,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->daddr = fl4.daddr; iph->saddr = fl4.saddr; iph->ttl = ttl; + iph->id = 0; if (ttl == 0) { if (skb->protocol == htons(ETH_P_IP)) @@ -964,9 +1002,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev *ptr = tunnel->parms.o_key; ptr--; } - if (tunnel->parms.o_flags&GRE_CSUM) { + /* Skip GRE checksum if skb is getting offloaded. */ + if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) && + (tunnel->parms.o_flags&GRE_CSUM)) { int offset = skb_transport_offset(skb); + if (skb_has_shared_frag(skb)) { + err = __skb_linearize(skb); + if (err) { + ip_rt_put(rt); + goto tx_error; + } + } + *ptr = 0; *(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset, skb->len - offset, @@ -974,7 +1022,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } } - iptunnel_xmit(skb, dev); + nf_reset(skb); + + pkt_len = skb->len - skb_transport_offset(skb); + err = ip_local_out(skb); + if (likely(net_xmit_eval(err) == 0)) { + u64_stats_update_begin(&tstats->syncp); + tstats->tx_bytes += pkt_len; + tstats->tx_packets++; + u64_stats_update_end(&tstats->syncp); + } else { + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; + } return NETDEV_TX_OK; #if IS_ENABLED(CONFIG_IPV6) @@ -1044,6 +1104,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) mtu = 68; tunnel->hlen = addend; + /* TCP offload with GRE SEQ is not supported. */ + if (!(tunnel->parms.o_flags & GRE_SEQ)) { + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + } return mtu; } @@ -1593,6 +1658,9 @@ static void ipgre_tap_setup(struct net_device *dev) dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; + + dev->features |= GRE_FEATURES; + dev->hw_features |= GRE_FEATURES; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1f0bedb8622..7a5ba48c2cc 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3043,6 +3043,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb, SKB_GSO_DODGY | SKB_GSO_TCP_ECN | SKB_GSO_TCPV6 | + SKB_GSO_GRE | 0) || !(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))) goto out; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6182d90e97b..fd0cea114b5 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1331,7 +1331,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) /* Remove acked data from a packet in the transmit queue. */ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) { - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return -ENOMEM; __pskb_trim_head(skb, len); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 6791aac06ea..39a5e7a9a77 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2305,7 +2305,8 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 06814b6216d..1f12c8b4586 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -132,7 +132,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) * header and optional ESP marker bytes) and then modify the * protocol to ESP, and then call into the transform receiver. */ - if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto drop; /* Now we can update and verify the packet length... */ diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index ddee0a099a2..1162ace3083 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -142,8 +142,7 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) for_each_input_rcu(rcv_notify_handlers, handler) handler->handler(skb); - if (skb_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + if (err = skb_unclone(skb, GFP_ATOMIC)) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index 384233188ac..bb02e176cb7 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -521,8 +521,7 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) /* We are going to _remove_ AH header to keep sockets happy, * so... Later this can change. */ - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) goto out; skb->ip_summed = CHECKSUM_NONE; diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index f26f0da7f09..8234c1dcdf7 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -99,6 +99,7 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, ~(SKB_GSO_UDP | SKB_GSO_DODGY | SKB_GSO_TCP_ECN | + SKB_GSO_GRE | SKB_GSO_TCPV6 | 0))) goto out; diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index c674f158efa..b89a8c3186c 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -368,7 +368,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) } /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) { + if (skb_unclone(head, GFP_ATOMIC)) { pr_debug("skb is cloned but can't expand head"); goto out_oom; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index bab2c270f29..e354743ed42 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -404,7 +404,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, goto out_oversize; /* Head of list must not be cloned. */ - if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC)) + if (skb_unclone(head, GFP_ATOMIC)) goto out_oom; /* If the first fragment is fragmented itself, we split diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 0c8934a317c..cf05cf073c5 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -56,7 +56,8 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, /* Packet is from an untrusted source, reset gso_segs. */ int type = skb_shinfo(skb)->gso_type; - if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) || + if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY | + SKB_GSO_GRE) || !(type & (SKB_GSO_UDP)))) goto out; diff --git a/net/ipv6/xfrm6_mode_tunnel.c b/net/ipv6/xfrm6_mode_tunnel.c index 9f2095b19ad..93c41a81c4c 100644 --- a/net/ipv6/xfrm6_mode_tunnel.c +++ b/net/ipv6/xfrm6_mode_tunnel.c @@ -69,8 +69,7 @@ static int xfrm6_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto out; - if (skb_cloned(skb) && - (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + if (err = skb_unclone(skb, GFP_ATOMIC)) goto out; if (x->props.flags & XFRM_STATE_DECAP_DSCP) diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 0fb9e3f567e..e0f6de64afe 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -207,10 +207,8 @@ static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_ipt *ipt = a->priv; struct xt_action_param par; - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - return TC_ACT_UNSPEC; - } + if (skb_unclone(skb, GFP_ATOMIC)) + return TC_ACT_UNSPEC; spin_lock(&ipt->tcf_lock); diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 0c3faddf3f2..7ed78c9e505 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -131,8 +131,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, int i, munged = 0; unsigned int off; - if (skb_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + if (skb_unclone(skb, GFP_ATOMIC)) return p->tcf_action; off = skb_network_offset(skb); |