diff options
73 files changed, 746 insertions, 232 deletions
diff --git a/Documentation/networking/tuntap.txt b/Documentation/networking/tuntap.txt index 76750fb..839cbb7 100644 --- a/Documentation/networking/tuntap.txt +++ b/Documentation/networking/tuntap.txt @@ -39,10 +39,13 @@ Copyright (C) 1999-2000 Maxim Krasnyansky <max_mk@yahoo.com> mknod /dev/net/tun c 10 200 Set permissions: - e.g. chmod 0700 /dev/net/tun - if you want the device only accessible by root. Giving regular users the - right to assign network devices is NOT a good idea. Users could assign - bogus network interfaces to trick firewalls or administrators. + e.g. chmod 0666 /dev/net/tun + There's no harm in allowing the device to be accessible by non-root users, + since CAP_NET_ADMIN is required for creating network devices or for + connecting to network devices which aren't owned by the user in question. + If you want to create persistent devices and give ownership of them to + unprivileged users, then you need the /dev/net/tun device to be usable by + those users. Driver module autoloading diff --git a/drivers/net/3c527.c b/drivers/net/3c527.c index 1b1cb00..157eda5 100644 --- a/drivers/net/3c527.c +++ b/drivers/net/3c527.c @@ -1031,8 +1031,7 @@ static int mc32_send_packet(struct sk_buff *skb, struct net_device *dev) return 1; } - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) { + if (skb_padto(skb, ETH_ZLEN)) { netif_wake_queue(dev); return 0; } diff --git a/drivers/net/8139cp.c b/drivers/net/8139cp.c index a26077a..0cdc830 100644 --- a/drivers/net/8139cp.c +++ b/drivers/net/8139cp.c @@ -797,7 +797,7 @@ static int cp_start_xmit (struct sk_buff *skb, struct net_device *dev) entry = cp->tx_head; eor = (entry == (CP_TX_RING_SIZE - 1)) ? RingEnd : 0; if (dev->features & NETIF_F_TSO) - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; if (skb_shinfo(skb)->nr_frags == 0) { struct cp_desc *txd = &cp->tx_ring[entry]; diff --git a/drivers/net/82596.c b/drivers/net/82596.c index da0c878..8a9f7d6 100644 --- a/drivers/net/82596.c +++ b/drivers/net/82596.c @@ -1070,8 +1070,7 @@ static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->len, (unsigned int)skb->data)); if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/a2065.c b/drivers/net/a2065.c index 79bb56b..71165ac 100644 --- a/drivers/net/a2065.c +++ b/drivers/net/a2065.c @@ -573,8 +573,7 @@ static int lance_start_xmit (struct sk_buff *skb, struct net_device *dev) if (len < ETH_ZLEN) { len = ETH_ZLEN; - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; } diff --git a/drivers/net/ariadne.c b/drivers/net/ariadne.c index d1b6b1f..a9bb7a4 100644 --- a/drivers/net/ariadne.c +++ b/drivers/net/ariadne.c @@ -607,8 +607,7 @@ static int ariadne_start_xmit(struct sk_buff *skb, struct net_device *dev) /* FIXME: is the 79C960 new enough to do its own padding right ? */ if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; len = ETH_ZLEN; } diff --git a/drivers/net/arm/ether1.c b/drivers/net/arm/ether1.c index 36475eb..312955d 100644 --- a/drivers/net/arm/ether1.c +++ b/drivers/net/arm/ether1.c @@ -700,8 +700,7 @@ ether1_sendpacket (struct sk_buff *skb, struct net_device *dev) } if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) goto out; } diff --git a/drivers/net/arm/ether3.c b/drivers/net/arm/ether3.c index f1d5b10..0810741 100644 --- a/drivers/net/arm/ether3.c +++ b/drivers/net/arm/ether3.c @@ -518,8 +518,7 @@ ether3_sendpacket(struct sk_buff *skb, struct net_device *dev) length = (length + 1) & ~1; if (length != skb->len) { - skb = skb_padto(skb, length); - if (skb == NULL) + if (skb_padto(skb, length)) goto out; } diff --git a/drivers/net/atarilance.c b/drivers/net/atarilance.c index 442b2cb..91783a8 100644 --- a/drivers/net/atarilance.c +++ b/drivers/net/atarilance.c @@ -804,8 +804,7 @@ static int lance_start_xmit( struct sk_buff *skb, struct net_device *dev ) ++len; if (len > skb->len) { - skb = skb_padto(skb, len); - if (skb == NULL) + if (skb_padto(skb, len)) return 0; } diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 702d546..7635736 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -1640,7 +1640,7 @@ bnx2_tx_int(struct bnx2 *bp) skb = tx_buf->skb; #ifdef BCM_TSO /* partial BD completions possible with TSO packets */ - if (skb_shinfo(skb)->tso_size) { + if (skb_shinfo(skb)->gso_size) { u16 last_idx, last_ring_idx; last_idx = sw_cons + @@ -4428,7 +4428,7 @@ bnx2_start_xmit(struct sk_buff *skb, struct net_device *dev) (TX_BD_FLAGS_VLAN_TAG | (vlan_tx_tag_get(skb) << 16)); } #ifdef BCM_TSO - if ((mss = skb_shinfo(skb)->tso_size) && + if ((mss = skb_shinfo(skb)->gso_size) && (skb->len > (bp->dev->mtu + ETH_HLEN))) { u32 tcp_opt_len, ip_tcp_len; diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c index 39f36aa..565a54f 100644 --- a/drivers/net/cassini.c +++ b/drivers/net/cassini.c @@ -2915,8 +2915,7 @@ static int cas_start_xmit(struct sk_buff *skb, struct net_device *dev) */ static int ring; - skb = skb_padto(skb, cp->min_frame_size); - if (!skb) + if (skb_padto(skb, cp->min_frame_size)) return 0; /* XXX: we need some higher-level QoS hooks to steer packets to diff --git a/drivers/net/chelsio/sge.c b/drivers/net/chelsio/sge.c index 4391bf4..53efff6 100644 --- a/drivers/net/chelsio/sge.c +++ b/drivers/net/chelsio/sge.c @@ -1418,7 +1418,7 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev) struct cpl_tx_pkt *cpl; #ifdef NETIF_F_TSO - if (skb_shinfo(skb)->tso_size) { + if (skb_shinfo(skb)->gso_size) { int eth_type; struct cpl_tx_pkt_lso *hdr; @@ -1433,7 +1433,7 @@ int t1_start_xmit(struct sk_buff *skb, struct net_device *dev) hdr->ip_hdr_words = skb->nh.iph->ihl; hdr->tcp_hdr_words = skb->h.th->doff; hdr->eth_type_mss = htons(MK_ETH_TYPE_MSS(eth_type, - skb_shinfo(skb)->tso_size)); + skb_shinfo(skb)->gso_size)); hdr->len = htonl(skb->len - sizeof(*hdr)); cpl = (struct cpl_tx_pkt *)hdr; sge->stats.tx_lso_pkts++; diff --git a/drivers/net/declance.c b/drivers/net/declance.c index f130bda..d3d958e 100644 --- a/drivers/net/declance.c +++ b/drivers/net/declance.c @@ -885,8 +885,7 @@ static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev) len = skblen; if (len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; len = ETH_ZLEN; } diff --git a/drivers/net/depca.c b/drivers/net/depca.c index 0941d40..e946c43d 100644 --- a/drivers/net/depca.c +++ b/drivers/net/depca.c @@ -938,11 +938,8 @@ static int depca_start_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->len < 1) goto out; - if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) - goto out; - } + if (skb_padto(skb, ETH_ZLEN)) + goto out; netif_stop_queue(dev); diff --git a/drivers/net/e1000/e1000_main.c b/drivers/net/e1000/e1000_main.c index a373ccb..32b7d44 100644 --- a/drivers/net/e1000/e1000_main.c +++ b/drivers/net/e1000/e1000_main.c @@ -2394,7 +2394,7 @@ e1000_tso(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, uint8_t ipcss, ipcso, tucss, tucso, hdr_len; int err; - if (skb_shinfo(skb)->tso_size) { + if (skb_shinfo(skb)->gso_size) { if (skb_header_cloned(skb)) { err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); if (err) @@ -2402,7 +2402,7 @@ e1000_tso(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, } hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2)); - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; if (skb->protocol == htons(ETH_P_IP)) { skb->nh.iph->tot_len = 0; skb->nh.iph->check = 0; @@ -2519,7 +2519,7 @@ e1000_tx_map(struct e1000_adapter *adapter, struct e1000_tx_ring *tx_ring, * tso gets written back prematurely before the data is fully * DMA'd to the controller */ if (!skb->data_len && tx_ring->last_tx_tso && - !skb_shinfo(skb)->tso_size) { + !skb_shinfo(skb)->gso_size) { tx_ring->last_tx_tso = 0; size -= 4; } @@ -2757,7 +2757,7 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) } #ifdef NETIF_F_TSO - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; /* The controller does a simple calculation to * make sure there is enough room in the FIFO before * initiating the DMA for each buffer. The calc is: @@ -2807,7 +2807,7 @@ e1000_xmit_frame(struct sk_buff *skb, struct net_device *netdev) #ifdef NETIF_F_TSO /* Controller Erratum workaround */ if (!skb->data_len && tx_ring->last_tx_tso && - !skb_shinfo(skb)->tso_size) + !skb_shinfo(skb)->gso_size) count++; #endif diff --git a/drivers/net/eepro.c b/drivers/net/eepro.c index a806dfe..e70f172 100644 --- a/drivers/net/eepro.c +++ b/drivers/net/eepro.c @@ -1154,8 +1154,7 @@ static int eepro_send_packet(struct sk_buff *skb, struct net_device *dev) printk(KERN_DEBUG "%s: entering eepro_send_packet routine.\n", dev->name); if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/eexpress.c b/drivers/net/eexpress.c index 82bd356..a74b207 100644 --- a/drivers/net/eexpress.c +++ b/drivers/net/eexpress.c @@ -677,8 +677,7 @@ static int eexp_xmit(struct sk_buff *buf, struct net_device *dev) #endif if (buf->len < ETH_ZLEN) { - buf = skb_padto(buf, ETH_ZLEN); - if (buf == NULL) + if (skb_padto(buf, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/epic100.c b/drivers/net/epic100.c index 8d680ce..724d7dc 100644 --- a/drivers/net/epic100.c +++ b/drivers/net/epic100.c @@ -1027,11 +1027,8 @@ static int epic_start_xmit(struct sk_buff *skb, struct net_device *dev) u32 ctrl_word; unsigned long flags; - if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) - return 0; - } + if (skb_padto(skb, ETH_ZLEN)) + return 0; /* Caution: the write order is important here, set the field with the "ownership" bit last. */ diff --git a/drivers/net/eth16i.c b/drivers/net/eth16i.c index b67545b..4bf76f8 100644 --- a/drivers/net/eth16i.c +++ b/drivers/net/eth16i.c @@ -1064,8 +1064,7 @@ static int eth16i_tx(struct sk_buff *skb, struct net_device *dev) unsigned long flags; if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/forcedeth.c b/drivers/net/forcedeth.c index 191383d4..21be4fa 100644 --- a/drivers/net/forcedeth.c +++ b/drivers/net/forcedeth.c @@ -1495,8 +1495,8 @@ static int nv_start_xmit(struct sk_buff *skb, struct net_device *dev) np->tx_skbuff[nr] = skb; #ifdef NETIF_F_TSO - if (skb_shinfo(skb)->tso_size) - tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->tso_size << NV_TX2_TSO_SHIFT); + if (skb_shinfo(skb)->gso_size) + tx_flags_extra = NV_TX2_TSO | (skb_shinfo(skb)->gso_size << NV_TX2_TSO_SHIFT); else #endif tx_flags_extra = (skb->ip_summed == CHECKSUM_HW ? (NV_TX2_CHECKSUM_L3|NV_TX2_CHECKSUM_L4) : 0); diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c index 247c8ca..dd1dc32 100644 --- a/drivers/net/hp100.c +++ b/drivers/net/hp100.c @@ -1487,11 +1487,8 @@ static int hp100_start_xmit_bm(struct sk_buff *skb, struct net_device *dev) if (skb->len <= 0) return 0; - if (skb->len < ETH_ZLEN && lp->chip == HP100_CHIPID_SHASTA) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) - return 0; - } + if (lp->chip == HP100_CHIPID_SHASTA && skb_padto(skb, ETH_ZLEN)) + return 0; /* Get Tx ring tail pointer */ if (lp->txrtail->next == lp->txrhead) { diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index 57006fb..8bb32f9 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1173,7 +1173,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) uint16_t ipcse, tucse, mss; int err; - if(likely(skb_shinfo(skb)->tso_size)) { + if(likely(skb_shinfo(skb)->gso_size)) { if (skb_header_cloned(skb)) { err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); if (err) @@ -1181,7 +1181,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) } hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2)); - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; skb->nh.iph->tot_len = 0; skb->nh.iph->check = 0; skb->h.th->check = ~csum_tcpudp_magic(skb->nh.iph->saddr, diff --git a/drivers/net/lance.c b/drivers/net/lance.c index bb5ad47..c1c3452 100644 --- a/drivers/net/lance.c +++ b/drivers/net/lance.c @@ -968,8 +968,7 @@ static int lance_start_xmit(struct sk_buff *skb, struct net_device *dev) /* The old LANCE chips doesn't automatically pad buffers to min. size. */ if (chip_table[lp->chip_version].flags & LANCE_MUST_PAD) { if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) goto out; lp->tx_ring[entry].length = -ETH_ZLEN; } diff --git a/drivers/net/lasi_82596.c b/drivers/net/lasi_82596.c index 957888d..1ab0944 100644 --- a/drivers/net/lasi_82596.c +++ b/drivers/net/lasi_82596.c @@ -1083,8 +1083,7 @@ static int i596_start_xmit(struct sk_buff *skb, struct net_device *dev) skb->len, skb->data)); if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c index b79d6e8..43fef7d 100644 --- a/drivers/net/loopback.c +++ b/drivers/net/loopback.c @@ -74,7 +74,7 @@ static void emulate_large_send_offload(struct sk_buff *skb) struct iphdr *iph = skb->nh.iph; struct tcphdr *th = (struct tcphdr*)(skb->nh.raw + (iph->ihl * 4)); unsigned int doffset = (iph->ihl + th->doff) * 4; - unsigned int mtu = skb_shinfo(skb)->tso_size + doffset; + unsigned int mtu = skb_shinfo(skb)->gso_size + doffset; unsigned int offset = 0; u32 seq = ntohl(th->seq); u16 id = ntohs(iph->id); @@ -139,7 +139,7 @@ static int loopback_xmit(struct sk_buff *skb, struct net_device *dev) #endif #ifdef LOOPBACK_TSO - if (skb_shinfo(skb)->tso_size) { + if (skb_shinfo(skb)->gso_size) { BUG_ON(skb->protocol != htons(ETH_P_IP)); BUG_ON(skb->nh.iph->protocol != IPPROTO_TCP); diff --git a/drivers/net/lp486e.c b/drivers/net/lp486e.c index 94d5ea1..bf3f343 100644 --- a/drivers/net/lp486e.c +++ b/drivers/net/lp486e.c @@ -877,8 +877,7 @@ static int i596_start_xmit (struct sk_buff *skb, struct net_device *dev) { length = skb->len; if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 5a74f63..dbdf189 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -1879,7 +1879,7 @@ again: #ifdef NETIF_F_TSO if (skb->len > (dev->mtu + ETH_HLEN)) { - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; if (mss != 0) max_segments = MYRI10GE_MAX_SEND_DESC_TSO; } @@ -1939,8 +1939,7 @@ again: /* pad frames to at least ETH_ZLEN bytes */ if (unlikely(skb->len < ETH_ZLEN)) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) { + if (skb_padto(skb, ETH_ZLEN)) { /* The packet is gone, so we must * return 0 */ mgp->stats.tx_dropped += 1; @@ -2113,7 +2112,7 @@ abort_linearize: } idx = (idx + 1) & tx->mask; } while (idx != last_idx); - if (skb_shinfo(skb)->tso_size) { + if (skb_shinfo(skb)->gso_size) { printk(KERN_ERR "myri10ge: %s: TSO but wanted to linearize?!?!?\n", mgp->dev->name); diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index 09b1176..ea93b8f1 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -831,8 +831,7 @@ static int fjn_start_xmit(struct sk_buff *skb, struct net_device *dev) if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/pcmcia/xirc2ps_cs.c b/drivers/net/pcmcia/xirc2ps_cs.c index e80d1e3..9bae77c 100644 --- a/drivers/net/pcmcia/xirc2ps_cs.c +++ b/drivers/net/pcmcia/xirc2ps_cs.c @@ -1374,8 +1374,7 @@ do_start_xmit(struct sk_buff *skb, struct net_device *dev) */ if (pktlen < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; pktlen = ETH_ZLEN; } diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 9945cc6..12d1cb2 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -2172,7 +2172,7 @@ static int rtl8169_xmit_frags(struct rtl8169_private *tp, struct sk_buff *skb, static inline u32 rtl8169_tso_csum(struct sk_buff *skb, struct net_device *dev) { if (dev->features & NETIF_F_TSO) { - u32 mss = skb_shinfo(skb)->tso_size; + u32 mss = skb_shinfo(skb)->gso_size; if (mss) return LargeSend | ((mss & MSSMask) << MSSShift); @@ -2222,8 +2222,7 @@ static int rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev) len = skb->len; if (unlikely(len < ETH_ZLEN)) { - skb = skb_padto(skb, ETH_ZLEN); - if (!skb) + if (skb_padto(skb, ETH_ZLEN)) goto err_update_stats; len = ETH_ZLEN; } diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index 11daed4..3defe5d 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -3959,8 +3959,8 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) txdp->Control_1 = 0; txdp->Control_2 = 0; #ifdef NETIF_F_TSO - mss = skb_shinfo(skb)->tso_size; - if (mss) { + mss = skb_shinfo(skb)->gso_size; + if (skb_shinfo(skb)->gso_type == SKB_GSO_TCPV4) { txdp->Control_1 |= TXD_TCP_LSO_EN; txdp->Control_1 |= TXD_TCP_LSO_MSS(mss); } @@ -3980,10 +3980,10 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) } frg_len = skb->len - skb->data_len; - if (skb_shinfo(skb)->ufo_size) { + if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) { int ufo_size; - ufo_size = skb_shinfo(skb)->ufo_size; + ufo_size = skb_shinfo(skb)->gso_size; ufo_size &= ~7; txdp->Control_1 |= TXD_UFO_EN; txdp->Control_1 |= TXD_UFO_MSS(ufo_size); @@ -4009,7 +4009,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) txdp->Host_Control = (unsigned long) skb; txdp->Control_1 |= TXD_BUFFER0_SIZE(frg_len); - if (skb_shinfo(skb)->ufo_size) + if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) txdp->Control_1 |= TXD_UFO_EN; frg_cnt = skb_shinfo(skb)->nr_frags; @@ -4024,12 +4024,12 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) (sp->pdev, frag->page, frag->page_offset, frag->size, PCI_DMA_TODEVICE); txdp->Control_1 = TXD_BUFFER0_SIZE(frag->size); - if (skb_shinfo(skb)->ufo_size) + if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) txdp->Control_1 |= TXD_UFO_EN; } txdp->Control_1 |= TXD_GATHER_CODE_LAST; - if (skb_shinfo(skb)->ufo_size) + if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) frg_cnt++; /* as Txd0 was used for inband header */ tx_fifo = mac_control->tx_FIFO_start[queue]; @@ -4043,7 +4043,7 @@ static int s2io_xmit(struct sk_buff *skb, struct net_device *dev) if (mss) val64 |= TX_FIFO_SPECIAL_FUNC; #endif - if (skb_shinfo(skb)->ufo_size) + if (skb_shinfo(skb)->gso_type == SKB_GSO_UDPV4) val64 |= TX_FIFO_SPECIAL_FUNC; writeq(val64, &tx_fifo->List_Control); diff --git a/drivers/net/seeq8005.c b/drivers/net/seeq8005.c index bcef03f..efd0f23 100644 --- a/drivers/net/seeq8005.c +++ b/drivers/net/seeq8005.c @@ -396,8 +396,7 @@ static int seeq8005_send_packet(struct sk_buff *skb, struct net_device *dev) unsigned char *buf; if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/sis190.c b/drivers/net/sis190.c index 31dd3f0..df39f34 100644 --- a/drivers/net/sis190.c +++ b/drivers/net/sis190.c @@ -1156,8 +1156,7 @@ static int sis190_start_xmit(struct sk_buff *skb, struct net_device *dev) dma_addr_t mapping; if (unlikely(skb->len < ETH_ZLEN)) { - skb = skb_padto(skb, ETH_ZLEN); - if (!skb) { + if (skb_padto(skb, ETH_ZLEN)) { tp->stats.tx_dropped++; goto out; } diff --git a/drivers/net/sk98lin/skge.c b/drivers/net/sk98lin/skge.c index 38a26df..f3efbd1 100644 --- a/drivers/net/sk98lin/skge.c +++ b/drivers/net/sk98lin/skge.c @@ -1525,7 +1525,7 @@ struct sk_buff *pMessage) /* pointer to send-message */ ** This is to resolve faulty padding by the HW with 0xaa bytes. */ if (BytesSend < C_LEN_ETHERNET_MINSIZE) { - if ((pMessage = skb_padto(pMessage, C_LEN_ETHERNET_MINSIZE)) == NULL) { + if (skb_padto(pMessage, C_LEN_ETHERNET_MINSIZE)) { spin_unlock_irqrestore(&pTxPort->TxDesRingLock, Flags); return 0; } diff --git a/drivers/net/skge.c b/drivers/net/skge.c index 536dd1c..19a4a16 100644 --- a/drivers/net/skge.c +++ b/drivers/net/skge.c @@ -2310,8 +2310,7 @@ static int skge_xmit_frame(struct sk_buff *skb, struct net_device *dev) u64 map; unsigned long flags; - skb = skb_padto(skb, ETH_ZLEN); - if (!skb) + if (skb_padto(skb, ETH_ZLEN)) return NETDEV_TX_OK; if (!spin_trylock_irqsave(&skge->tx_lock, flags)) diff --git a/drivers/net/sky2.c b/drivers/net/sky2.c index fba1e4d4..d357787 100644 --- a/drivers/net/sky2.c +++ b/drivers/net/sky2.c @@ -1160,7 +1160,7 @@ static unsigned tx_le_req(const struct sk_buff *skb) count = sizeof(dma_addr_t) / sizeof(u32); count += skb_shinfo(skb)->nr_frags * count; - if (skb_shinfo(skb)->tso_size) + if (skb_shinfo(skb)->gso_size) ++count; if (skb->ip_summed == CHECKSUM_HW) @@ -1232,7 +1232,7 @@ static int sky2_xmit_frame(struct sk_buff *skb, struct net_device *dev) } /* Check for TCP Segmentation Offload */ - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; if (mss != 0) { /* just drop the packet if non-linear expansion fails */ if (skb_header_cloned(skb) && diff --git a/drivers/net/smc9194.c b/drivers/net/smc9194.c index 6cf16f3..8b0321f 100644 --- a/drivers/net/smc9194.c +++ b/drivers/net/smc9194.c @@ -523,8 +523,7 @@ static int smc_wait_to_send_packet( struct sk_buff * skb, struct net_device * de length = skb->len; if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) { + if (skb_padto(skb, ETH_ZLEN)) { netif_wake_queue(dev); return 0; } diff --git a/drivers/net/sonic.c b/drivers/net/sonic.c index 90b818a..cab0dd9 100644 --- a/drivers/net/sonic.c +++ b/drivers/net/sonic.c @@ -231,8 +231,7 @@ static int sonic_send_packet(struct sk_buff *skb, struct net_device *dev) length = skb->len; if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/starfire.c b/drivers/net/starfire.c index 9b7805b..c158eed 100644 --- a/drivers/net/starfire.c +++ b/drivers/net/starfire.c @@ -1349,8 +1349,7 @@ static int start_tx(struct sk_buff *skb, struct net_device *dev) #if defined(ZEROCOPY) && defined(HAS_BROKEN_FIRMWARE) if (skb->ip_summed == CHECKSUM_HW) { - skb = skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK); - if (skb == NULL) + if (skb_padto(skb, (skb->len + PADDING_MASK) & ~PADDING_MASK)) return NETDEV_TX_OK; } #endif /* ZEROCOPY && HAS_BROKEN_FIRMWARE */ diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index b2ddd45..e3e380f 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -3780,7 +3780,7 @@ static int tg3_start_xmit(struct sk_buff *skb, struct net_device *dev) #if TG3_TSO_SUPPORT != 0 mss = 0; if (skb->len > (tp->dev->mtu + ETH_HLEN) && - (mss = skb_shinfo(skb)->tso_size) != 0) { + (mss = skb_shinfo(skb)->gso_size) != 0) { int tcp_opt_len, ip_tcp_len; if (skb_header_cloned(skb) && @@ -3905,7 +3905,7 @@ static int tg3_start_xmit_dma_bug(struct sk_buff *skb, struct net_device *dev) #if TG3_TSO_SUPPORT != 0 mss = 0; if (skb->len > (tp->dev->mtu + ETH_HLEN) && - (mss = skb_shinfo(skb)->tso_size) != 0) { + (mss = skb_shinfo(skb)->gso_size) != 0) { int tcp_opt_len, ip_tcp_len; if (skb_header_cloned(skb) && diff --git a/drivers/net/tun.c b/drivers/net/tun.c index a1ed2d9..6c62d5c 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -490,6 +490,9 @@ static int tun_set_iff(struct file *file, struct ifreq *ifr) err = -EINVAL; + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + /* Set dev type */ if (ifr->ifr_flags & IFF_TUN) { /* TUN device */ diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index d9258d4..e49e8b5 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -340,7 +340,7 @@ enum state_values { #endif #if defined(NETIF_F_TSO) -#define skb_tso_size(x) (skb_shinfo(x)->tso_size) +#define skb_tso_size(x) (skb_shinfo(x)->gso_size) #define TSO_NUM_DESCRIPTORS 2 #define TSO_OFFLOAD_ON TYPHOON_OFFLOAD_TCP_SEGMENT #else diff --git a/drivers/net/via-rhine.c b/drivers/net/via-rhine.c index fdc2103..c80a4f1 100644 --- a/drivers/net/via-rhine.c +++ b/drivers/net/via-rhine.c @@ -1284,11 +1284,8 @@ static int rhine_start_tx(struct sk_buff *skb, struct net_device *dev) /* Calculate the next Tx descriptor entry. */ entry = rp->cur_tx % TX_RING_SIZE; - if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) - return 0; - } + if (skb_padto(skb, ETH_ZLEN)) + return 0; rp->tx_skbuff[entry] = skb; diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c index 879eb42..a915fe6 100644 --- a/drivers/net/wireless/ray_cs.c +++ b/drivers/net/wireless/ray_cs.c @@ -924,8 +924,7 @@ static int ray_dev_start_xmit(struct sk_buff *skb, struct net_device *dev) if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/net/wireless/wavelan_cs.c b/drivers/net/wireless/wavelan_cs.c index f7724eb..561250f 100644 --- a/drivers/net/wireless/wavelan_cs.c +++ b/drivers/net/wireless/wavelan_cs.c @@ -3194,11 +3194,8 @@ wavelan_packet_xmit(struct sk_buff * skb, * and we don't have the Ethernet specific requirement of beeing * able to detect collisions, therefore in theory we don't really * need to pad. Jean II */ - if (skb->len < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) - return 0; - } + if (skb_padto(skb, ETH_ZLEN)) + return 0; wv_packet_write(dev, skb->data, skb->len); diff --git a/drivers/net/yellowfin.c b/drivers/net/yellowfin.c index fd0f43b..ecec8e5 100644 --- a/drivers/net/yellowfin.c +++ b/drivers/net/yellowfin.c @@ -862,13 +862,11 @@ static int yellowfin_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Fix GX chipset errata. */ if (cacheline_end > 24 || cacheline_end == 0) { len = skb->len + 32 - cacheline_end + 1; - if (len != skb->len) - skb = skb_padto(skb, len); - } - if (skb == NULL) { - yp->tx_skbuff[entry] = NULL; - netif_wake_queue(dev); - return 0; + if (skb_padto(skb, len)) { + yp->tx_skbuff[entry] = NULL; + netif_wake_queue(dev); + return 0; + } } } yp->tx_skbuff[entry] = skb; diff --git a/drivers/net/znet.c b/drivers/net/znet.c index 3ac047b..a7c089d 100644 --- a/drivers/net/znet.c +++ b/drivers/net/znet.c @@ -544,8 +544,7 @@ static int znet_send_packet(struct sk_buff *skb, struct net_device *dev) printk(KERN_DEBUG "%s: ZNet_send_packet.\n", dev->name); if (length < ETH_ZLEN) { - skb = skb_padto(skb, ETH_ZLEN); - if (skb == NULL) + if (skb_padto(skb, ETH_ZLEN)) return 0; length = ETH_ZLEN; } diff --git a/drivers/s390/net/qeth_eddp.c b/drivers/s390/net/qeth_eddp.c index 0bab60a2..38aad83 100644 --- a/drivers/s390/net/qeth_eddp.c +++ b/drivers/s390/net/qeth_eddp.c @@ -420,7 +420,7 @@ __qeth_eddp_fill_context_tcp(struct qeth_eddp_context *ctx, } tcph = eddp->skb->h.th; while (eddp->skb_offset < eddp->skb->len) { - data_len = min((int)skb_shinfo(eddp->skb)->tso_size, + data_len = min((int)skb_shinfo(eddp->skb)->gso_size, (int)(eddp->skb->len - eddp->skb_offset)); /* prepare qdio hdr */ if (eddp->qh.hdr.l2.id == QETH_HEADER_TYPE_LAYER2){ @@ -515,20 +515,20 @@ qeth_eddp_calc_num_pages(struct qeth_eddp_context *ctx, struct sk_buff *skb, QETH_DBF_TEXT(trace, 5, "eddpcanp"); /* can we put multiple skbs in one page? */ - skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->tso_size + hdr_len); + skbs_per_page = PAGE_SIZE / (skb_shinfo(skb)->gso_size + hdr_len); if (skbs_per_page > 1){ - ctx->num_pages = (skb_shinfo(skb)->tso_segs + 1) / + ctx->num_pages = (skb_shinfo(skb)->gso_segs + 1) / skbs_per_page + 1; ctx->elements_per_skb = 1; } else { /* no -> how many elements per skb? */ - ctx->elements_per_skb = (skb_shinfo(skb)->tso_size + hdr_len + + ctx->elements_per_skb = (skb_shinfo(skb)->gso_size + hdr_len + PAGE_SIZE) >> PAGE_SHIFT; ctx->num_pages = ctx->elements_per_skb * - (skb_shinfo(skb)->tso_segs + 1); + (skb_shinfo(skb)->gso_segs + 1); } ctx->num_elements = ctx->elements_per_skb * - (skb_shinfo(skb)->tso_segs + 1); + (skb_shinfo(skb)->gso_segs + 1); } static inline struct qeth_eddp_context * diff --git a/drivers/s390/net/qeth_main.c b/drivers/s390/net/qeth_main.c index 9e671a4..56009d7 100644 --- a/drivers/s390/net/qeth_main.c +++ b/drivers/s390/net/qeth_main.c @@ -4417,7 +4417,7 @@ qeth_send_packet(struct qeth_card *card, struct sk_buff *skb) struct qeth_eddp_context *ctx = NULL; int tx_bytes = skb->len; unsigned short nr_frags = skb_shinfo(skb)->nr_frags; - unsigned short tso_size = skb_shinfo(skb)->tso_size; + unsigned short tso_size = skb_shinfo(skb)->gso_size; int rc; QETH_DBF_TEXT(trace, 6, "sendpkt"); @@ -4453,7 +4453,7 @@ qeth_send_packet(struct qeth_card *card, struct sk_buff *skb) queue = card->qdio.out_qs [qeth_get_priority_queue(card, skb, ipv, cast_type)]; - if (skb_shinfo(skb)->tso_size) + if (skb_shinfo(skb)->gso_size) large_send = card->options.large_send; /*are we able to do TSO ? If so ,prepare and send it from here */ diff --git a/drivers/s390/net/qeth_tso.h b/drivers/s390/net/qeth_tso.h index 24ef40c..593f298 100644 --- a/drivers/s390/net/qeth_tso.h +++ b/drivers/s390/net/qeth_tso.h @@ -51,7 +51,7 @@ qeth_tso_fill_header(struct qeth_card *card, struct sk_buff *skb) hdr->ext.hdr_version = 1; hdr->ext.hdr_len = 28; /*insert non-fix values */ - hdr->ext.mss = skb_shinfo(skb)->tso_size; + hdr->ext.mss = skb_shinfo(skb)->gso_size; hdr->ext.dg_hdr_len = (__u16)(iph->ihl*4 + tcph->doff*4); hdr->ext.payload_len = (__u16)(skb->len - hdr->ext.dg_hdr_len - sizeof(struct qeth_hdr_tso)); diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index cf2abec..c6310ae 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -411,6 +411,8 @@ struct ethtool_ops { #define ETHTOOL_GPERMADDR 0x00000020 /* Get permanent hardware address */ #define ETHTOOL_GUFO 0x00000021 /* Get UFO enable (ethtool_value) */ #define ETHTOOL_SUFO 0x00000022 /* Set UFO enable (ethtool_value) */ +#define ETHTOOL_GGSO 0x00000023 /* Get GSO enable (ethtool_value) */ +#define ETHTOOL_SGSO 0x00000024 /* Set GSO enable (ethtool_value) */ /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cead6be..bc747e5 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -308,9 +308,13 @@ struct net_device #define NETIF_F_HW_VLAN_RX 256 /* Receive VLAN hw acceleration */ #define NETIF_F_HW_VLAN_FILTER 512 /* Receive filtering on VLAN */ #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ -#define NETIF_F_TSO 2048 /* Can offload TCP/IP segmentation */ +#define NETIF_F_GSO 2048 /* Enable software GSO. */ #define NETIF_F_LLTX 4096 /* LockLess TX */ -#define NETIF_F_UFO 8192 /* Can offload UDP Large Send*/ + + /* Segmentation offload features */ +#define NETIF_F_GSO_SHIFT 16 +#define NETIF_F_TSO (SKB_GSO_TCPV4 << NETIF_F_GSO_SHIFT) +#define NETIF_F_UFO (SKB_GSO_UDPV4 << NETIF_F_GSO_SHIFT) #define NETIF_F_GEN_CSUM (NETIF_F_NO_CSUM | NETIF_F_HW_CSUM) #define NETIF_F_ALL_CSUM (NETIF_F_IP_CSUM | NETIF_F_GEN_CSUM) @@ -402,6 +406,9 @@ struct net_device struct list_head qdisc_list; unsigned long tx_queue_len; /* Max frames per queue allowed */ + /* Partially transmitted GSO packet. */ + struct sk_buff *gso_skb; + /* ingress path synchronizer */ spinlock_t ingress_lock; struct Qdisc *qdisc_ingress; @@ -536,6 +543,7 @@ struct packet_type { struct net_device *, struct packet_type *, struct net_device *); + struct sk_buff *(*gso_segment)(struct sk_buff *skb, int sg); void *af_packet_priv; struct list_head list; }; @@ -686,7 +694,8 @@ extern int dev_change_name(struct net_device *, char *); extern int dev_set_mtu(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); -extern void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); +extern int dev_hard_start_xmit(struct sk_buff *skb, + struct net_device *dev); extern void dev_init(void); @@ -960,6 +969,7 @@ extern int netdev_max_backlog; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb, int inward); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else @@ -979,6 +989,13 @@ extern void dev_seq_stop(struct seq_file *seq, void *v); extern void linkwatch_run_queue(void); +static inline int netif_needs_gso(struct net_device *dev, struct sk_buff *skb) +{ + int feature = skb_shinfo(skb)->gso_type << NETIF_F_GSO_SHIFT; + return skb_shinfo(skb)->gso_size && + (dev->features & feature) != feature; +} + #endif /* __KERNEL__ */ #endif /* _LINUX_DEV_H */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 66f8819..16eef03 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -134,9 +134,10 @@ struct skb_frag_struct { struct skb_shared_info { atomic_t dataref; unsigned short nr_frags; - unsigned short tso_size; - unsigned short tso_segs; - unsigned short ufo_size; + unsigned short gso_size; + /* Warning: this field is not always filled in (UFO)! */ + unsigned short gso_segs; + unsigned short gso_type; unsigned int ip6_frag_id; struct sk_buff *frag_list; skb_frag_t frags[MAX_SKB_FRAGS]; @@ -168,6 +169,11 @@ enum { SKB_FCLONE_CLONE, }; +enum { + SKB_GSO_TCPV4 = 1 << 0, + SKB_GSO_UDPV4 = 1 << 1, +}; + /** * struct sk_buff - socket buffer * @next: Next buffer in list @@ -209,6 +215,8 @@ enum { * @nf_bridge: Saved data about a bridged frame - see br_netfilter.c * @tc_index: Traffic control index * @tc_verd: traffic control verdict + * @dma_cookie: a cookie to one of several possible DMA operations + * done by skb DMA functions * @secmark: security marking */ @@ -345,7 +353,7 @@ extern struct sk_buff *skb_realloc_headroom(struct sk_buff *skb, extern struct sk_buff *skb_copy_expand(const struct sk_buff *skb, int newheadroom, int newtailroom, gfp_t priority); -extern struct sk_buff * skb_pad(struct sk_buff *skb, int pad); +extern int skb_pad(struct sk_buff *skb, int pad); #define dev_kfree_skb(a) kfree_skb(a) extern void skb_over_panic(struct sk_buff *skb, int len, void *here); @@ -1122,16 +1130,15 @@ static inline int skb_cow(struct sk_buff *skb, unsigned int headroom) * * Pads up a buffer to ensure the trailing bytes exist and are * blanked. If the buffer already contains sufficient data it - * is untouched. Returns the buffer, which may be a replacement - * for the original, or NULL for out of memory - in which case - * the original buffer is still freed. + * is untouched. Otherwise it is extended. Returns zero on + * success. The skb is freed on error. */ -static inline struct sk_buff *skb_padto(struct sk_buff *skb, unsigned int len) +static inline int skb_padto(struct sk_buff *skb, unsigned int len) { unsigned int size = skb->len; if (likely(size >= len)) - return skb; + return 0; return skb_pad(skb, len-size); } @@ -1292,6 +1299,7 @@ extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); extern void skb_release_data(struct sk_buff *skb); +extern struct sk_buff *skb_segment(struct sk_buff *skb, int sg); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 420a689..8ebf497 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -18,7 +18,6 @@ #define _LINUX_TCP_H #include <linux/types.h> -#include <linux/dmaengine.h> #include <asm/byteorder.h> struct tcphdr { @@ -161,6 +160,7 @@ struct tcp_info #ifdef __KERNEL__ #include <linux/skbuff.h> +#include <linux/dmaengine.h> #include <net/sock.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> diff --git a/include/net/protocol.h b/include/net/protocol.h index bcaee39..3b6dc15 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -36,6 +36,7 @@ struct net_protocol { int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); + struct sk_buff *(*gso_segment)(struct sk_buff *skb, int sg); int no_policy; }; diff --git a/include/net/sock.h b/include/net/sock.h index d10dfec..2d8d6ad 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1030,9 +1030,13 @@ static inline void sk_setup_caps(struct sock *sk, struct dst_entry *dst) { __sk_dst_set(sk, dst); sk->sk_route_caps = dst->dev->features; + if (sk->sk_route_caps & NETIF_F_GSO) + sk->sk_route_caps |= NETIF_F_TSO; if (sk->sk_route_caps & NETIF_F_TSO) { if (sock_flag(sk, SOCK_NO_LARGESEND) || dst->header_len) sk->sk_route_caps &= ~NETIF_F_TSO; + else + sk->sk_route_caps |= NETIF_F_SG | NETIF_F_HW_CSUM; } } @@ -1265,6 +1269,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from * @skb: socket buffer to eat + * @copied_early: flag indicating whether DMA operations copied this data early * * This routine must be called with interrupts disabled or with the socket * locked so that the sk_buff queue operation is ok. diff --git a/include/net/tcp.h b/include/net/tcp.h index 5f4eb5c..ca3d38d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -569,13 +569,13 @@ struct tcp_skb_cb { */ static inline int tcp_skb_pcount(const struct sk_buff *skb) { - return skb_shinfo(skb)->tso_segs; + return skb_shinfo(skb)->gso_segs; } /* This is valid iff tcp_skb_pcount() > 1. */ static inline int tcp_skb_mss(const struct sk_buff *skb) { - return skb_shinfo(skb)->tso_size; + return skb_shinfo(skb)->gso_size; } static inline void tcp_dec_pcount_approx(__u32 *count, @@ -1086,6 +1086,8 @@ extern struct request_sock_ops tcp_request_sock_ops; extern int tcp_v4_destroy_sock(struct sock *sk); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg); + #ifdef CONFIG_PROC_FS extern int tcp4_proc_init(void); extern void tcp4_proc_exit(void); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 0dca027..8be9f21 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -34,8 +34,8 @@ static inline unsigned packet_length(const struct sk_buff *skb) int br_dev_queue_push_xmit(struct sk_buff *skb) { - /* drop mtu oversized packets except tso */ - if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->tso_size) + /* drop mtu oversized packets except gso */ + if (packet_length(skb) > skb->dev->mtu && !skb_shinfo(skb)->gso_size) kfree_skb(skb); else { #ifdef CONFIG_BRIDGE_NETFILTER diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index fdec773..07956ec 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -376,15 +376,20 @@ void br_features_recompute(struct net_bridge *br) features = br->feature_mask & ~NETIF_F_ALL_CSUM; list_for_each_entry(p, &br->port_list, list) { - if (checksum & NETIF_F_NO_CSUM && - !(p->dev->features & NETIF_F_NO_CSUM)) + unsigned long feature = p->dev->features; + + if (checksum & NETIF_F_NO_CSUM && !(feature & NETIF_F_NO_CSUM)) checksum ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM; - if (checksum & NETIF_F_HW_CSUM && - !(p->dev->features & NETIF_F_HW_CSUM)) + if (checksum & NETIF_F_HW_CSUM && !(feature & NETIF_F_HW_CSUM)) checksum ^= NETIF_F_HW_CSUM | NETIF_F_IP_CSUM; - if (!(p->dev->features & NETIF_F_IP_CSUM)) + if (!(feature & NETIF_F_IP_CSUM)) checksum = 0; - features &= p->dev->features; + + if (feature & NETIF_F_GSO) + feature |= NETIF_F_TSO; + feature |= NETIF_F_GSO; + + features &= feature; } br->dev->features = features | checksum | NETIF_F_LLTX; diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 3e41f9d..8298a51 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -761,7 +761,7 @@ static int br_nf_dev_queue_xmit(struct sk_buff *skb) { if (skb->protocol == htons(ETH_P_IP) && skb->len > skb->dev->mtu && - !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) + !skb_shinfo(skb)->gso_size) return ip_fragment(skb, br_dev_queue_push_xmit); else return br_dev_queue_push_xmit(skb); diff --git a/net/core/dev.c b/net/core/dev.c index 195a5e9..ea24693 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -116,6 +116,7 @@ #include <asm/current.h> #include <linux/audit.h> #include <linux/dmaengine.h> +#include <linux/err.h> /* * The list of packet types we will receive (as opposed to discard) @@ -1048,7 +1049,7 @@ static inline void net_timestamp(struct sk_buff *skb) * taps currently in use. */ -void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) +static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; @@ -1186,6 +1187,40 @@ out: return ret; } +/** + * skb_gso_segment - Perform segmentation on skb. + * @skb: buffer to segment + * @sg: whether scatter-gather is supported on the target. + * + * This function segments the given skb and returns a list of segments. + */ +struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg) +{ + struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); + struct packet_type *ptype; + int type = skb->protocol; + + BUG_ON(skb_shinfo(skb)->frag_list); + BUG_ON(skb->ip_summed != CHECKSUM_HW); + + skb->mac.raw = skb->data; + skb->mac_len = skb->nh.raw - skb->data; + __skb_pull(skb, skb->mac_len); + + rcu_read_lock(); + list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) { + if (ptype->type == type && !ptype->dev && ptype->gso_segment) { + segs = ptype->gso_segment(skb, sg); + break; + } + } + rcu_read_unlock(); + + return segs; +} + +EXPORT_SYMBOL(skb_gso_segment); + /* Take action when hardware reception checksum errors are detected. */ #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev) @@ -1222,6 +1257,86 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) #define illegal_highdma(dev, skb) (0) #endif +struct dev_gso_cb { + void (*destructor)(struct sk_buff *skb); +}; + +#define DEV_GSO_CB(skb) ((struct dev_gso_cb *)(skb)->cb) + +static void dev_gso_skb_destructor(struct sk_buff *skb) +{ + struct dev_gso_cb *cb; + + do { + struct sk_buff *nskb = skb->next; + + skb->next = nskb->next; + nskb->next = NULL; + kfree_skb(nskb); + } while (skb->next); + + cb = DEV_GSO_CB(skb); + if (cb->destructor) + cb->destructor(skb); +} + +/** + * dev_gso_segment - Perform emulated hardware segmentation on skb. + * @skb: buffer to segment + * + * This function segments the given skb and stores the list of segments + * in skb->next. + */ +static int dev_gso_segment(struct sk_buff *skb) +{ + struct net_device *dev = skb->dev; + struct sk_buff *segs; + + segs = skb_gso_segment(skb, dev->features & NETIF_F_SG && + !illegal_highdma(dev, skb)); + if (unlikely(IS_ERR(segs))) + return PTR_ERR(segs); + + skb->next = segs; + DEV_GSO_CB(skb)->destructor = skb->destructor; + skb->destructor = dev_gso_skb_destructor; + + return 0; +} + +int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + if (likely(!skb->next)) { + if (netdev_nit) + dev_queue_xmit_nit(skb, dev); + + if (!netif_needs_gso(dev, skb)) + return dev->hard_start_xmit(skb, dev); + + if (unlikely(dev_gso_segment(skb))) + goto out_kfree_skb; + } + + do { + struct sk_buff *nskb = skb->next; + int rc; + + skb->next = nskb->next; + nskb->next = NULL; + rc = dev->hard_start_xmit(nskb, dev); + if (unlikely(rc)) { + skb->next = nskb; + return rc; + } + } while (skb->next); + + skb->destructor = DEV_GSO_CB(skb)->destructor; + +out_kfree_skb: + kfree_skb(skb); + return 0; +} + #define HARD_TX_LOCK(dev, cpu) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ netif_tx_lock(dev); \ @@ -1266,6 +1381,10 @@ int dev_queue_xmit(struct sk_buff *skb) struct Qdisc *q; int rc = -ENOMEM; + /* GSO will handle the following emulations directly. */ + if (netif_needs_gso(dev, skb)) + goto gso; + if (skb_shinfo(skb)->frag_list && !(dev->features & NETIF_F_FRAGLIST) && __skb_linearize(skb)) @@ -1290,12 +1409,13 @@ int dev_queue_xmit(struct sk_buff *skb) if (skb_checksum_help(skb, 0)) goto out_kfree_skb; +gso: spin_lock_prefetch(&dev->queue_lock); /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ - local_bh_disable(); + rcu_read_lock_bh(); /* Updates of qdisc are serialized by queue_lock. * The struct Qdisc which is pointed to by qdisc is now a @@ -1346,11 +1466,8 @@ int dev_queue_xmit(struct sk_buff *skb) HARD_TX_LOCK(dev, cpu); if (!netif_queue_stopped(dev)) { - if (netdev_nit) - dev_queue_xmit_nit(skb, dev); - rc = 0; - if (!dev->hard_start_xmit(skb, dev)) { + if (!dev_hard_start_xmit(skb, dev)) { HARD_TX_UNLOCK(dev); goto out; } @@ -1369,13 +1486,13 @@ int dev_queue_xmit(struct sk_buff *skb) } rc = -ENETDOWN; - local_bh_enable(); + rcu_read_unlock_bh(); out_kfree_skb: kfree_skb(skb); return rc; out: - local_bh_enable(); + rcu_read_unlock_bh(); return rc; } @@ -3301,8 +3418,8 @@ static void net_dma_rebalance(void) /** * netdev_dma_event - event callback for the net_dma_client * @client: should always be net_dma_client - * @chan: - * @event: + * @chan: DMA channel for the event + * @event: event type */ static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan, enum dma_event event) diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 33ce7ed..27ce168 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -614,6 +614,29 @@ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) return dev->ethtool_ops->set_ufo(dev, edata.data); } +static int ethtool_get_gso(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { ETHTOOL_GGSO }; + + edata.data = dev->features & NETIF_F_GSO; + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + +static int ethtool_set_gso(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata; + + if (copy_from_user(&edata, useraddr, sizeof(edata))) + return -EFAULT; + if (edata.data) + dev->features |= NETIF_F_GSO; + else + dev->features &= ~NETIF_F_GSO; + return 0; +} + static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; @@ -905,6 +928,12 @@ int dev_ethtool(struct ifreq *ifr) case ETHTOOL_SUFO: rc = ethtool_set_ufo(dev, useraddr); break; + case ETHTOOL_GGSO: + rc = ethtool_get_gso(dev, useraddr); + break; + case ETHTOOL_SGSO: + rc = ethtool_set_gso(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index bb7210f..8e5044b 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -172,9 +172,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo = skb_shinfo(skb); atomic_set(&shinfo->dataref, 1); shinfo->nr_frags = 0; - shinfo->tso_size = 0; - shinfo->tso_segs = 0; - shinfo->ufo_size = 0; + shinfo->gso_size = 0; + shinfo->gso_segs = 0; + shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; shinfo->frag_list = NULL; @@ -238,8 +238,9 @@ struct sk_buff *alloc_skb_from_cache(kmem_cache_t *cp, atomic_set(&(skb_shinfo(skb)->dataref), 1); skb_shinfo(skb)->nr_frags = 0; - skb_shinfo(skb)->tso_size = 0; - skb_shinfo(skb)->tso_segs = 0; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_segs = 0; + skb_shinfo(skb)->gso_type = 0; skb_shinfo(skb)->frag_list = NULL; out: return skb; @@ -528,8 +529,9 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif skb_copy_secmark(new, old); atomic_set(&new->users, 1); - skb_shinfo(new)->tso_size = skb_shinfo(old)->tso_size; - skb_shinfo(new)->tso_segs = skb_shinfo(old)->tso_segs; + skb_shinfo(new)->gso_size = skb_shinfo(old)->gso_size; + skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; + skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } /** @@ -781,24 +783,40 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, * filled. Used by network drivers which may DMA or transfer data * beyond the buffer end onto the wire. * - * May return NULL in out of memory cases. + * May return error in out of memory cases. The skb is freed on error. */ -struct sk_buff *skb_pad(struct sk_buff *skb, int pad) +int skb_pad(struct sk_buff *skb, int pad) { - struct sk_buff *nskb; + int err; + int ntail; /* If the skbuff is non linear tailroom is always zero.. */ - if (skb_tailroom(skb) >= pad) { + if (!skb_cloned(skb) && skb_tailroom(skb) >= pad) { memset(skb->data+skb->len, 0, pad); - return skb; + return 0; } - - nskb = skb_copy_expand(skb, skb_headroom(skb), skb_tailroom(skb) + pad, GFP_ATOMIC); + + ntail = skb->data_len + pad - (skb->end - skb->tail); + if (likely(skb_cloned(skb) || ntail > 0)) { + err = pskb_expand_head(skb, 0, ntail, GFP_ATOMIC); + if (unlikely(err)) + goto free_skb; + } + + /* FIXME: The use of this function with non-linear skb's really needs + * to be audited. + */ + err = skb_linearize(skb); + if (unlikely(err)) + goto free_skb; + + memset(skb->data + skb->len, 0, pad); + return 0; + +free_skb: kfree_skb(skb); - if (nskb) - memset(nskb->data+nskb->len, 0, pad); - return nskb; + return err; } /* Trims skb to length len. It can change skb pointers. @@ -1824,6 +1842,132 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) EXPORT_SYMBOL_GPL(skb_pull_rcsum); +/** + * skb_segment - Perform protocol segmentation on skb. + * @skb: buffer to segment + * @sg: whether scatter-gather can be used for generated segments + * + * This function performs segmentation on the given skb. It returns + * the segment at the given position. It returns NULL if there are + * no more segments to generate, or when an error is encountered. + */ +struct sk_buff *skb_segment(struct sk_buff *skb, int sg) +{ + struct sk_buff *segs = NULL; + struct sk_buff *tail = NULL; + unsigned int mss = skb_shinfo(skb)->gso_size; + unsigned int doffset = skb->data - skb->mac.raw; + unsigned int offset = doffset; + unsigned int headroom; + unsigned int len; + int nfrags = skb_shinfo(skb)->nr_frags; + int err = -ENOMEM; + int i = 0; + int pos; + + __skb_push(skb, doffset); + headroom = skb_headroom(skb); + pos = skb_headlen(skb); + + do { + struct sk_buff *nskb; + skb_frag_t *frag; + int hsize, nsize; + int k; + int size; + + len = skb->len - offset; + if (len > mss) + len = mss; + + hsize = skb_headlen(skb) - offset; + if (hsize < 0) + hsize = 0; + nsize = hsize + doffset; + if (nsize > len + doffset || !sg) + nsize = len + doffset; + + nskb = alloc_skb(nsize + headroom, GFP_ATOMIC); + if (unlikely(!nskb)) + goto err; + + if (segs) + tail->next = nskb; + else + segs = nskb; + tail = nskb; + + nskb->dev = skb->dev; + nskb->priority = skb->priority; + nskb->protocol = skb->protocol; + nskb->dst = dst_clone(skb->dst); + memcpy(nskb->cb, skb->cb, sizeof(skb->cb)); + nskb->pkt_type = skb->pkt_type; + nskb->mac_len = skb->mac_len; + + skb_reserve(nskb, headroom); + nskb->mac.raw = nskb->data; + nskb->nh.raw = nskb->data + skb->mac_len; + nskb->h.raw = nskb->nh.raw + (skb->h.raw - skb->nh.raw); + memcpy(skb_put(nskb, doffset), skb->data, doffset); + + if (!sg) { + nskb->csum = skb_copy_and_csum_bits(skb, offset, + skb_put(nskb, len), + len, 0); + continue; + } + + frag = skb_shinfo(nskb)->frags; + k = 0; + + nskb->ip_summed = CHECKSUM_HW; + nskb->csum = skb->csum; + memcpy(skb_put(nskb, hsize), skb->data + offset, hsize); + + while (pos < offset + len) { + BUG_ON(i >= nfrags); + + *frag = skb_shinfo(skb)->frags[i]; + get_page(frag->page); + size = frag->size; + + if (pos < offset) { + frag->page_offset += offset - pos; + frag->size -= offset - pos; + } + + k++; + + if (pos + size <= offset + len) { + i++; + pos += size; + } else { + frag->size -= pos + size - (offset + len); + break; + } + + frag++; + } + + skb_shinfo(nskb)->nr_frags = k; + nskb->data_len = len - hsize; + nskb->len += nskb->data_len; + nskb->truesize += nskb->data_len; + } while ((offset += len) < skb->len); + + return segs; + +err: + while ((skb = segs)) { + segs = skb->next; + kfree(skb); + } + return ERR_PTR(err); +} + +EXPORT_SYMBOL_GPL(skb_segment); + void __init skb_init(void) { skbuff_head_cache = kmem_cache_create("skbuff_head_cache", diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0a27745..461216b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -68,6 +68,7 @@ */ #include <linux/config.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -1096,6 +1097,54 @@ int inet_sk_rebuild_header(struct sock *sk) EXPORT_SYMBOL(inet_sk_rebuild_header); +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int sg) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct iphdr *iph; + struct net_protocol *ops; + int proto; + int ihl; + int id; + + if (!pskb_may_pull(skb, sizeof(*iph))) + goto out; + + iph = skb->nh.iph; + ihl = iph->ihl * 4; + if (ihl < sizeof(*iph)) + goto out; + + if (!pskb_may_pull(skb, ihl)) + goto out; + + skb->h.raw = __skb_pull(skb, ihl); + iph = skb->nh.iph; + id = ntohs(iph->id); + proto = iph->protocol & (MAX_INET_PROTOS - 1); + segs = ERR_PTR(-EPROTONOSUPPORT); + + rcu_read_lock(); + ops = rcu_dereference(inet_protos[proto]); + if (ops && ops->gso_segment) + segs = ops->gso_segment(skb, sg); + rcu_read_unlock(); + + if (IS_ERR(segs)) + goto out; + + skb = segs; + do { + iph = skb->nh.iph; + iph->id = htons(id++); + iph->tot_len = htons(skb->len - skb->mac_len); + iph->check = 0; + iph->check = ip_fast_csum(skb->nh.raw, iph->ihl); + } while ((skb = skb->next)); + +out: + return segs; +} + #ifdef CONFIG_IP_MULTICAST static struct net_protocol igmp_protocol = { .handler = igmp_rcv, @@ -1105,6 +1154,7 @@ static struct net_protocol igmp_protocol = { static struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, + .gso_segment = tcp_tso_segment, .no_policy = 1, }; @@ -1150,6 +1200,7 @@ static int ipv4_proc_init(void); static struct packet_type ip_packet_type = { .type = __constant_htons(ETH_P_IP), .func = ip_rcv, + .gso_segment = inet_gso_segment, }; static int __init inet_init(void) diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8538aac..7624fd1 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -210,8 +210,7 @@ static inline int ip_finish_output(struct sk_buff *skb) return dst_output(skb); } #endif - if (skb->len > dst_mtu(skb->dst) && - !(skb_shinfo(skb)->ufo_size || skb_shinfo(skb)->tso_size)) + if (skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) return ip_fragment(skb, ip_finish_output2); else return ip_finish_output2(skb); @@ -362,7 +361,7 @@ packet_routed: } ip_select_ident_more(iph, &rt->u.dst, sk, - (skb_shinfo(skb)->tso_segs ?: 1) - 1); + (skb_shinfo(skb)->gso_segs ?: 1) - 1); /* Add an IP checksum. */ ip_send_check(iph); @@ -744,7 +743,8 @@ static inline int ip_ufo_append_data(struct sock *sk, (length - transhdrlen)); if (!err) { /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen); + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; + skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4; __skb_queue_tail(&sk->sk_write_queue, skb); return 0; @@ -1087,14 +1087,16 @@ ssize_t ip_append_page(struct sock *sk, struct page *page, inet->cork.length += size; if ((sk->sk_protocol == IPPROTO_UDP) && - (rt->u.dst.dev->features & NETIF_F_UFO)) - skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen); + (rt->u.dst.dev->features & NETIF_F_UFO)) { + skb_shinfo(skb)->gso_size = mtu - fragheaderlen; + skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4; + } while (size > 0) { int i; - if (skb_shinfo(skb)->ufo_size) + if (skb_shinfo(skb)->gso_size) len = size; else { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 74998f2..0e029c4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -258,6 +258,7 @@ #include <linux/random.h> #include <linux/bootmem.h> #include <linux/cache.h> +#include <linux/err.h> #include <net/icmp.h> #include <net/tcp.h> @@ -571,7 +572,7 @@ new_segment: skb->ip_summed = CHECKSUM_HW; tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; - skb_shinfo(skb)->tso_segs = 0; + skb_shinfo(skb)->gso_segs = 0; if (!copied) TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH; @@ -818,7 +819,7 @@ new_segment: tp->write_seq += copy; TCP_SKB_CB(skb)->end_seq += copy; - skb_shinfo(skb)->tso_segs = 0; + skb_shinfo(skb)->gso_segs = 0; from += copy; copied += copy; @@ -2144,6 +2145,67 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int sg) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + struct tcphdr *th; + unsigned thlen; + unsigned int seq; + unsigned int delta; + unsigned int oldlen; + unsigned int len; + + if (!pskb_may_pull(skb, sizeof(*th))) + goto out; + + th = skb->h.th; + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + goto out; + + if (!pskb_may_pull(skb, thlen)) + goto out; + + oldlen = ~htonl(skb->len); + __skb_pull(skb, thlen); + + segs = skb_segment(skb, sg); + if (IS_ERR(segs)) + goto out; + + len = skb_shinfo(skb)->gso_size; + delta = csum_add(oldlen, htonl(thlen + len)); + + skb = segs; + th = skb->h.th; + seq = ntohl(th->seq); + + do { + th->fin = th->psh = 0; + + if (skb->ip_summed == CHECKSUM_NONE) { + th->check = csum_fold(csum_partial( + skb->h.raw, thlen, csum_add(skb->csum, delta))); + } + + seq += len; + skb = skb->next; + th = skb->h.th; + + th->seq = htonl(seq); + th->cwr = 0; + } while (skb->next); + + if (skb->ip_summed == CHECKSUM_NONE) { + delta = csum_add(oldlen, htonl(skb->tail - skb->h.raw)); + th->check = csum_fold(csum_partial( + skb->h.raw, thlen, csum_add(skb->csum, delta))); + } + +out: + return segs; +} + extern void __skb_cb_too_small_for_tcp(int, int); extern struct tcp_congestion_ops tcp_reno; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e08245b..94fe5b1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1073,7 +1073,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, u32 prior_snd_ else pkt_len = (end_seq - TCP_SKB_CB(skb)->seq); - if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->tso_size)) + if (tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size)) break; pcount = tcp_skb_pcount(skb); } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 07bb5a2..bdd71db 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -515,15 +515,17 @@ static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned /* Avoid the costly divide in the normal * non-TSO case. */ - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; } else { unsigned int factor; factor = skb->len + (mss_now - 1); factor /= mss_now; - skb_shinfo(skb)->tso_segs = factor; - skb_shinfo(skb)->tso_size = mss_now; + skb_shinfo(skb)->gso_segs = factor; + skb_shinfo(skb)->gso_size = mss_now; + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; } } @@ -914,7 +916,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int if (!tso_segs || (tso_segs > 1 && - skb_shinfo(skb)->tso_size != mss_now)) { + tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(sk, skb, mss_now); tso_segs = tcp_skb_pcount(skb); } @@ -1724,8 +1726,9 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) tp->snd_una == (TCP_SKB_CB(skb)->end_seq - 1)) { if (!pskb_trim(skb, 0)) { TCP_SKB_CB(skb)->seq = TCP_SKB_CB(skb)->end_seq - 1; - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; skb->ip_summed = CHECKSUM_NONE; skb->csum = 0; } @@ -1930,8 +1933,9 @@ void tcp_send_fin(struct sock *sk) skb->csum = 0; TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_FIN); TCP_SKB_CB(skb)->sacked = 0; - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; /* FIN eats a sequence byte, write_seq advanced by tcp_queue_skb(). */ TCP_SKB_CB(skb)->seq = tp->write_seq; @@ -1963,8 +1967,9 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) skb->csum = 0; TCP_SKB_CB(skb)->flags = (TCPCB_FLAG_ACK | TCPCB_FLAG_RST); TCP_SKB_CB(skb)->sacked = 0; - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; /* Send it off. */ TCP_SKB_CB(skb)->seq = tcp_acceptable_seq(sk, tp); @@ -2047,8 +2052,9 @@ struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst, TCP_SKB_CB(skb)->seq = tcp_rsk(req)->snt_isn; TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + 1; TCP_SKB_CB(skb)->sacked = 0; - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; th->seq = htonl(TCP_SKB_CB(skb)->seq); th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1); if (req->rcv_wnd == 0) { /* ignored for retransmitted syns */ @@ -2152,8 +2158,9 @@ int tcp_connect(struct sock *sk) TCP_SKB_CB(buff)->flags = TCPCB_FLAG_SYN; TCP_ECN_send_syn(sk, tp, buff); TCP_SKB_CB(buff)->sacked = 0; - skb_shinfo(buff)->tso_segs = 1; - skb_shinfo(buff)->tso_size = 0; + skb_shinfo(buff)->gso_segs = 1; + skb_shinfo(buff)->gso_size = 0; + skb_shinfo(buff)->gso_type = 0; buff->csum = 0; TCP_SKB_CB(buff)->seq = tp->write_seq++; TCP_SKB_CB(buff)->end_seq = tp->write_seq; @@ -2257,8 +2264,9 @@ void tcp_send_ack(struct sock *sk) buff->csum = 0; TCP_SKB_CB(buff)->flags = TCPCB_FLAG_ACK; TCP_SKB_CB(buff)->sacked = 0; - skb_shinfo(buff)->tso_segs = 1; - skb_shinfo(buff)->tso_size = 0; + skb_shinfo(buff)->gso_segs = 1; + skb_shinfo(buff)->gso_size = 0; + skb_shinfo(buff)->gso_type = 0; /* Send it off, this clears delayed acks for us. */ TCP_SKB_CB(buff)->seq = TCP_SKB_CB(buff)->end_seq = tcp_acceptable_seq(sk, tp); @@ -2293,8 +2301,9 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent) skb->csum = 0; TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK; TCP_SKB_CB(skb)->sacked = urgent; - skb_shinfo(skb)->tso_segs = 1; - skb_shinfo(skb)->tso_size = 0; + skb_shinfo(skb)->gso_segs = 1; + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; /* Use a previous sequence. This should cause the other * end to send an ack. Don't queue or clone SKB, just diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index ac9d91d..193363e 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -9,6 +9,8 @@ */ #include <linux/compiler.h> +#include <linux/if_ether.h> +#include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/netfilter_ipv4.h> @@ -97,16 +99,10 @@ error_nolock: goto out_exit; } -static int xfrm4_output_finish(struct sk_buff *skb) +static int xfrm4_output_finish2(struct sk_buff *skb) { int err; -#ifdef CONFIG_NETFILTER - if (!skb->dst->xfrm) { - IPCB(skb)->flags |= IPSKB_REROUTED; - return dst_output(skb); - } -#endif while (likely((err = xfrm4_output_one(skb)) == 0)) { nf_reset(skb); @@ -119,7 +115,7 @@ static int xfrm4_output_finish(struct sk_buff *skb) return dst_output(skb); err = nf_hook(PF_INET, NF_IP_POST_ROUTING, &skb, NULL, - skb->dst->dev, xfrm4_output_finish); + skb->dst->dev, xfrm4_output_finish2); if (unlikely(err != 1)) break; } @@ -127,6 +123,48 @@ static int xfrm4_output_finish(struct sk_buff *skb) return err; } +static int xfrm4_output_finish(struct sk_buff *skb) +{ + struct sk_buff *segs; + +#ifdef CONFIG_NETFILTER + if (!skb->dst->xfrm) { + IPCB(skb)->flags |= IPSKB_REROUTED; + return dst_output(skb); + } +#endif + + if (!skb_shinfo(skb)->gso_size) + return xfrm4_output_finish2(skb); + + skb->protocol = htons(ETH_P_IP); + segs = skb_gso_segment(skb, 0); + kfree_skb(skb); + if (unlikely(IS_ERR(segs))) + return PTR_ERR(segs); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = xfrm4_output_finish2(segs); + + if (unlikely(err)) { + while ((segs = nskb)) { + nskb = segs->next; + segs->next = NULL; + kfree_skb(segs); + } + return err; + } + + segs = nskb; + } while (segs); + + return 0; +} + int xfrm4_output(struct sk_buff *skb) { return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dst->dev, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c2c26fa..4da6645 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -862,6 +862,8 @@ static int inline ipv6_saddr_label(const struct in6_addr *addr, int type) * 2002::/16 2 * ::/96 3 * ::ffff:0:0/96 4 + * fc00::/7 5 + * 2001::/32 6 */ if (type & IPV6_ADDR_LOOPBACK) return 0; @@ -869,8 +871,12 @@ static int inline ipv6_saddr_label(const struct in6_addr *addr, int type) return 3; else if (type & IPV6_ADDR_MAPPED) return 4; + else if (addr->s6_addr32[0] == htonl(0x20010000)) + return 6; else if (addr->s6_addr16[0] == htons(0x2002)) return 2; + else if ((addr->s6_addr[0] & 0xfe) == 0xfc) + return 5; return 1; } @@ -1069,6 +1075,9 @@ int ipv6_dev_get_saddr(struct net_device *daddr_dev, if (hiscore.attrs & IPV6_SADDR_SCORE_PRIVACY) continue; } +#else + if (hiscore.rule < 7) + hiscore.rule++; #endif /* Rule 8: Use longest matching prefix */ if (hiscore.rule < 8) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d29620f..abb94de 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -148,7 +148,7 @@ static int ip6_output2(struct sk_buff *skb) int ip6_output(struct sk_buff *skb) { - if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->ufo_size) || + if ((skb->len > dst_mtu(skb->dst) && !skb_shinfo(skb)->gso_size) || dst_allfrag(skb->dst)) return ip6_fragment(skb, ip6_output2); else @@ -833,8 +833,9 @@ static inline int ip6_ufo_append_data(struct sock *sk, struct frag_hdr fhdr; /* specify the length of each IP datagram fragment*/ - skb_shinfo(skb)->ufo_size = (mtu - fragheaderlen) - - sizeof(struct frag_hdr); + skb_shinfo(skb)->gso_size = mtu - fragheaderlen - + sizeof(struct frag_hdr); + skb_shinfo(skb)->gso_type = SKB_GSO_UDPV4; ipv6_select_ident(skb, &fhdr); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 16e8425..48fccb1 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -94,7 +94,7 @@ error_nolock: goto out_exit; } -static int xfrm6_output_finish(struct sk_buff *skb) +static int xfrm6_output_finish2(struct sk_buff *skb) { int err; @@ -110,7 +110,7 @@ static int xfrm6_output_finish(struct sk_buff *skb) return dst_output(skb); err = nf_hook(PF_INET6, NF_IP6_POST_ROUTING, &skb, NULL, - skb->dst->dev, xfrm6_output_finish); + skb->dst->dev, xfrm6_output_finish2); if (unlikely(err != 1)) break; } @@ -118,6 +118,41 @@ static int xfrm6_output_finish(struct sk_buff *skb) return err; } +static int xfrm6_output_finish(struct sk_buff *skb) +{ + struct sk_buff *segs; + + if (!skb_shinfo(skb)->gso_size) + return xfrm6_output_finish2(skb); + + skb->protocol = htons(ETH_P_IP); + segs = skb_gso_segment(skb, 0); + kfree_skb(skb); + if (unlikely(IS_ERR(segs))) + return PTR_ERR(segs); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = xfrm6_output_finish2(segs); + + if (unlikely(err)) { + while ((segs = nskb)) { + nskb = segs->next; + segs->next = NULL; + kfree_skb(segs); + } + return err; + } + + segs = nskb; + } while (segs); + + return 0; +} + int xfrm6_output(struct sk_buff *skb) { return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb, NULL, skb->dst->dev, diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d7aca8e..74d4a1d 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -96,8 +96,11 @@ static inline int qdisc_restart(struct net_device *dev) struct sk_buff *skb; /* Dequeue packet */ - if ((skb = q->dequeue(q)) != NULL) { + if (((skb = dev->gso_skb)) || ((skb = q->dequeue(q)))) { unsigned nolock = (dev->features & NETIF_F_LLTX); + + dev->gso_skb = NULL; + /* * When the driver has LLTX set it does its own locking * in start_xmit. No need to add additional overhead by @@ -134,10 +137,8 @@ static inline int qdisc_restart(struct net_device *dev) if (!netif_queue_stopped(dev)) { int ret; - if (netdev_nit) - dev_queue_xmit_nit(skb, dev); - ret = dev->hard_start_xmit(skb, dev); + ret = dev_hard_start_xmit(skb, dev); if (ret == NETDEV_TX_OK) { if (!nolock) { netif_tx_unlock(dev); @@ -171,7 +172,10 @@ static inline int qdisc_restart(struct net_device *dev) */ requeue: - q->ops->requeue(skb, q); + if (skb->next) + dev->gso_skb = skb; + else + q->ops->requeue(skb, q); netif_schedule(dev); return 1; } @@ -181,9 +185,13 @@ requeue: void __qdisc_run(struct net_device *dev) { + if (unlikely(dev->qdisc == &noop_qdisc)) + goto out; + while (qdisc_restart(dev) < 0 && !netif_queue_stopped(dev)) /* NOTHING */; +out: clear_bit(__LINK_STATE_QDISC_RUNNING, &dev->state); } @@ -583,10 +591,17 @@ void dev_deactivate(struct net_device *dev) dev_watchdog_down(dev); - while (test_bit(__LINK_STATE_SCHED, &dev->state)) + /* Wait for outstanding dev_queue_xmit calls. */ + synchronize_rcu(); + + /* Wait for outstanding qdisc_run calls. */ + while (test_bit(__LINK_STATE_QDISC_RUNNING, &dev->state)) yield(); - spin_unlock_wait(&dev->_xmit_lock); + if (dev->gso_skb) { + kfree_skb(dev->gso_skb); + dev->gso_skb = NULL; + } } void dev_init_scheduler(struct net_device *dev) |
