From 82dc3c63c692b1e1d59378ecee948ac88e034aad Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Mar 2013 15:57:22 +0000 Subject: net: introduce NAPI_POLL_WEIGHT Some drivers use a too big NAPI poll weight. This patch adds a NAPI_POLL_WEIGHT default value and issues an error message if a driver attempts to use a bigger weight. Signed-off-by: Eric Dumazet Cc: Eilon Greenstein Signed-off-by: David S. Miller --- net/core/dev.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index a06a7a58dd11..96103894ad69 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4057,6 +4057,9 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi, napi->gro_list = NULL; napi->skb = NULL; napi->poll = poll; + if (weight > NAPI_POLL_WEIGHT) + pr_err_once("netif_napi_add() called with weight %d on device %s\n", + weight, dev->name); napi->weight = weight; list_add(&napi->dev_list, &dev->napi_list); napi->dev = dev; -- cgit From ec5f061564238892005257c83565a0b58ec79295 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 09:28:01 +0000 Subject: net: Kill link between CSUM and SG features. Earlier SG was unset if CSUM was not available for given device to force skb copy to avoid sending inconsistent csum. Commit c9af6db4c11c (net: Fix possible wrong checksum generation) added explicit flag to force copy to fix this issue. Therefore there is no need to link SG and CSUM, following patch kills this link between there two features. This patch is also required following patch in series. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/core/dev.c | 63 ++++++++++++++++++++++++++++++---------------------------- 1 file changed, 33 insertions(+), 30 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 96103894ad69..bb999931729f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2208,16 +2208,8 @@ out: } EXPORT_SYMBOL(skb_checksum_help); -/** - * skb_mac_gso_segment - mac layer segmentation handler. - * @skb: buffer to segment - * @features: features for the output path (see dev->features) - */ -struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, - netdev_features_t features) +__be16 skb_network_protocol(struct sk_buff *skb) { - struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); - struct packet_offload *ptype; __be16 type = skb->protocol; while (type == htons(ETH_P_8021Q)) { @@ -2225,13 +2217,31 @@ struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb, struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) - return ERR_PTR(-EINVAL); + return 0; vh = (struct vlan_hdr *)(skb->data + vlan_depth); type = vh->h_vlan_encapsulated_proto; vlan_depth += VLAN_HLEN; } + return type; +} + +/** + * skb_mac_gso_segment - mac layer segmentation handler. + * @skb: buffer to segment + * @features: features for the output path (see dev->features) + */ +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_network_protocol(skb); + + if (unlikely(!type)) + return ERR_PTR(-EINVAL); + __skb_pull(skb, skb->mac_len); rcu_read_lock(); @@ -2398,24 +2408,12 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) return 0; } -static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) -{ - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_V4_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_V6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - static netdev_features_t harmonize_features(struct sk_buff *skb, __be16 protocol, netdev_features_t features) { if (skb->ip_summed != CHECKSUM_NONE && !can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; - features &= ~NETIF_F_SG; } else if (illegal_highdma(skb->dev, skb)) { features &= ~NETIF_F_SG; } @@ -4921,20 +4919,25 @@ static netdev_features_t netdev_fix_features(struct net_device *dev, features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } - /* Fix illegal SG+CSUM combinations. */ - if ((features & NETIF_F_SG) && - !(features & NETIF_F_ALL_CSUM)) { - netdev_dbg(dev, - "Dropping NETIF_F_SG since no checksum feature.\n"); - features &= ~NETIF_F_SG; - } - /* TSO requires that SG is present as well. */ if ((features & NETIF_F_ALL_TSO) && !(features & NETIF_F_SG)) { netdev_dbg(dev, "Dropping TSO features since no SG feature.\n"); features &= ~NETIF_F_ALL_TSO; } + if ((features & NETIF_F_TSO) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IP_CSUM)) { + netdev_dbg(dev, "Dropping TSO features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO; + features &= ~NETIF_F_TSO_ECN; + } + + if ((features & NETIF_F_TSO6) && !(features & NETIF_F_HW_CSUM) && + !(features & NETIF_F_IPV6_CSUM)) { + netdev_dbg(dev, "Dropping TSO6 features since no CSUM feature.\n"); + features &= ~NETIF_F_TSO6; + } + /* TSO ECN requires that TSO is present as well. */ if ((features & NETIF_F_ALL_TSO) == NETIF_F_TSO_ECN) features &= ~NETIF_F_TSO_ECN; -- cgit From ee579677c29954f20e48e5bb80ae85b30100c2e0 Mon Sep 17 00:00:00 2001 From: Pravin B Shelar Date: Thu, 7 Mar 2013 09:28:08 +0000 Subject: tunnel: Inherit NETIF_F_SG for hw_enc_features. Inherit scatergather feature for tunnel devices to avoid copy for TSO packets of tunneling device like GRE. Signed-off-by: Pravin B Shelar Signed-off-by: David S. Miller --- net/core/dev.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index bb999931729f..90cee5be1c0f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5205,6 +5205,10 @@ int register_netdevice(struct net_device *dev) */ dev->vlan_features |= NETIF_F_HIGHDMA; + /* Make NETIF_F_SG inheritable to tunnel devices. + */ + dev->hw_enc_features |= NETIF_F_SG; + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) -- cgit From 166ec3696823e69dbbdec47726735eb7aa4f7d96 Mon Sep 17 00:00:00 2001 From: Kusanagi Kouichi Date: Mon, 18 Mar 2013 02:59:52 +0000 Subject: net: Fix a comment typo Signed-off-by: Kusanagi Kouichi Signed-off-by: David S. Miller --- net/core/dev.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 0caa38ee8935..8c47ab243926 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3324,7 +3324,7 @@ EXPORT_SYMBOL_GPL(netdev_rx_handler_register); * netdev_rx_handler_unregister - unregister receive handler * @dev: device to unregister a handler from * - * Unregister a receive hander from a device. + * Unregister a receive handler from a device. * * The caller must hold the rtnl_mutex. */ -- cgit From 15e5a030716468dce4032fa0f398d840fa2756f6 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Mon, 25 Mar 2013 20:19:59 +0000 Subject: net_sched: better precise estimation on packet length for untrusted packets gso_segs were reset to zero when kernel receive packets from untrusted source. But we use this zero value to estimate precise packet len which is wrong. So this patch tries to estimate the correct gso_segs value before using it in qdisc_pkt_len_init(). Cc: Eric Dumazet Signed-off-by: Jason Wang Signed-off-by: David S. Miller --- net/core/dev.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index de930b751712..f5ad23bb24fc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2588,6 +2588,7 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) */ if (shinfo->gso_size) { unsigned int hdr_len; + u16 gso_segs = shinfo->gso_segs; /* mac layer + network layer */ hdr_len = skb_transport_header(skb) - skb_mac_header(skb); @@ -2597,7 +2598,12 @@ static void qdisc_pkt_len_init(struct sk_buff *skb) hdr_len += tcp_hdrlen(skb); else hdr_len += sizeof(struct udphdr); - qdisc_skb_cb(skb)->pkt_len += (shinfo->gso_segs - 1) * hdr_len; + + if (shinfo->gso_type & SKB_GSO_DODGY) + gso_segs = DIV_ROUND_UP(skb->len - hdr_len, + shinfo->gso_size); + + qdisc_skb_cb(skb)->pkt_len += (gso_segs - 1) * hdr_len; } } -- cgit From f646968f8f7c624587de729115d802372b9063dd Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:27 +0000 Subject: net: vlan: rename NETIF_F_HW_VLAN_* feature flags to NETIF_F_HW_VLAN_CTAG_* Rename the hardware VLAN acceleration features to include "CTAG" to indicate that they only support CTAGs. Follow up patches will introduce 802.1ad server provider tagging (STAGs) and require the distinction for hardware not supporting acclerating both. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 3655ff927315..07a8e9dc43fc 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2435,13 +2435,13 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) return harmonize_features(skb, protocol, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX); + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX); if (protocol != htons(ETH_P_8021Q)) { return harmonize_features(skb, protocol, features); } else { features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX; + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX; return harmonize_features(skb, protocol, features); } } @@ -2482,7 +2482,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && - !(features & NETIF_F_HW_VLAN_TX)) { + !(features & NETIF_F_HW_VLAN_CTAG_TX)) { skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out; @@ -5180,7 +5180,8 @@ int register_netdevice(struct net_device *dev) } } - if (((dev->hw_features | dev->features) & NETIF_F_HW_VLAN_FILTER) && + if (((dev->hw_features | dev->features) & + NETIF_F_HW_VLAN_CTAG_FILTER) && (!dev->netdev_ops->ndo_vlan_rx_add_vid || !dev->netdev_ops->ndo_vlan_rx_kill_vid)) { netdev_WARN(dev, "Buggy VLAN acceleration in driver!\n"); -- cgit From 86a9bad3ab6b6f858fd4443b48738cabbb6d094c Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:30 +0000 Subject: net: vlan: add protocol argument to packet tagging functions Add a protocol argument to the VLAN packet tagging functions. In case of HW tagging, we need that protocol available in the ndo_start_xmit functions, so it is stored in a new field in the skb. The new field fits into a hole (on 64 bit) and doesn't increase the sks's size. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/core/dev.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 07a8e9dc43fc..3a12ee132b59 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2482,8 +2482,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && - !(features & NETIF_F_HW_VLAN_CTAG_TX)) { - skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + !vlan_hw_offload_capable(features, skb->vlan_proto)) { + skb = __vlan_put_tag(skb, skb->vlan_proto, + vlan_tx_tag_get(skb)); if (unlikely(!skb)) goto out; -- cgit From 8ad227ff89a7e6f05d07cd0acfd95ed3a24450ca Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 19 Apr 2013 02:04:31 +0000 Subject: net: vlan: add 802.1ad support Add support for 802.1ad VLAN devices. This mainly consists of checking for ETH_P_8021AD in addition to ETH_P_8021Q in a couple of places and check offloading capabilities based on the used protocol. Configuration is done using "ip link": # ip link add link eth0 eth0.1000 \ type vlan proto 802.1ad id 1000 # ip link add link eth0.1000 eth0.1000.1000 \ type vlan proto 802.1q id 1000 52:54:00:12:34:56 > 92:b1:54:28:e4:8c, ethertype 802.1Q (0x8100), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 0, offset 0, flags [DF], proto ICMP (1), length 84) 20.1.0.2 > 20.1.0.1: ICMP echo request, id 3003, seq 8, length 64 92:b1:54:28:e4:8c > 52:54:00:12:34:56, ethertype 802.1Q-QinQ (0x88a8), length 106: vlan 1000, p 0, ethertype 802.1Q, vlan 1000, p 0, ethertype IPv4, (tos 0x0, ttl 64, id 47944, offset 0, flags [none], proto ICMP (1), length 84) 20.1.0.1 > 20.1.0.2: ICMP echo reply, id 3003, seq 8, length 64 Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- net/core/dev.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 3a12ee132b59..fad4c385f7a1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2212,7 +2212,7 @@ __be16 skb_network_protocol(struct sk_buff *skb) __be16 type = skb->protocol; int vlan_depth = ETH_HLEN; - while (type == htons(ETH_P_8021Q)) { + while (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) { struct vlan_hdr *vh; if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) @@ -2428,20 +2428,22 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) features &= ~NETIF_F_GSO_MASK; - if (protocol == htons(ETH_P_8021Q)) { + if (protocol == htons(ETH_P_8021Q) || protocol == htons(ETH_P_8021AD)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; } else if (!vlan_tx_tag_present(skb)) { return harmonize_features(skb, protocol, features); } - features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX); + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX); - if (protocol != htons(ETH_P_8021Q)) { + if (protocol != htons(ETH_P_8021Q) && protocol != htons(ETH_P_8021AD)) { return harmonize_features(skb, protocol, features); } else { features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | - NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX; + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; return harmonize_features(skb, protocol, features); } } @@ -3360,6 +3362,7 @@ static bool skb_pfmemalloc_protocol(struct sk_buff *skb) case __constant_htons(ETH_P_IP): case __constant_htons(ETH_P_IPV6): case __constant_htons(ETH_P_8021Q): + case __constant_htons(ETH_P_8021AD): return true; default: return false; @@ -3400,7 +3403,8 @@ another_round: __this_cpu_inc(softnet_data.processed); - if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { + if (skb->protocol == cpu_to_be16(ETH_P_8021Q) || + skb->protocol == cpu_to_be16(ETH_P_8021AD)) { skb = vlan_untag(skb); if (unlikely(!skb)) goto unlock; -- cgit From 53759be99772f39db5148a7066a768066592a1e7 Mon Sep 17 00:00:00 2001 From: dingtianhong Date: Wed, 17 Apr 2013 22:17:50 +0000 Subject: net: Remove return value from list_netdevice() The return value from list_netdevice() is not used and no need, so remove it. Signed-off-by: Ding Tianhong Signed-off-by: David S. Miller --- net/core/dev.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index fad4c385f7a1..8a3cb2c50fbf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -200,7 +200,7 @@ static inline void rps_unlock(struct softnet_data *sd) } /* Device list insertion */ -static int list_netdevice(struct net_device *dev) +static void list_netdevice(struct net_device *dev) { struct net *net = dev_net(dev); @@ -214,8 +214,6 @@ static int list_netdevice(struct net_device *dev) write_unlock_bh(&dev_base_lock); dev_base_seq_inc(net); - - return 0; } /* Device list removal -- cgit From e12472dc574ca91be4cb87b14fb8cf90bee02c60 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Apr 2013 14:31:34 +0000 Subject: net: remove redundant code in dev_hard_start_xmit() This reverts commit 068a2de57ddf4f4 (net: release dst entry while cache-hot for GSO case too) Before GSO packet segmentation, we already take care of skb->dst if it can be released. There is no point adding extra test for every segment in the gso loop. Signed-off-by: Eric Dumazet Cc: Krishna Kumar Signed-off-by: David S. Miller --- net/core/dev.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 9e26b8d9eafe..7c30dcecee1d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2546,13 +2546,6 @@ gso: skb->next = nskb->next; nskb->next = NULL; - /* - * If device doesn't need nskb->dst, release it right now while - * its hot in this cpu cache - */ - if (dev->priv_flags & IFF_XMIT_DST_RELEASE) - skb_dst_drop(nskb); - if (!list_empty(&ptype_all)) dev_queue_xmit_nit(nskb, dev); -- cgit From 0c772159d1ae15c664304f0830c9aec4702593da Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Mon, 29 Apr 2013 13:02:42 +0000 Subject: net: Use consume_skb() to free gso segmented skb Use consume_skb() to free the original skb that is successfully transmitted as gso segmented skbs so that it is not treated as a drop due to an error. Signed-off-by: Sridhar Samudrala Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 7c30dcecee1d..4040673f806a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2565,8 +2565,11 @@ gso: } while (skb->next); out_kfree_gso_skb: - if (likely(skb->next == NULL)) + if (likely(skb->next == NULL)) { skb->destructor = DEV_GSO_CB(skb)->destructor; + consume_skb(skb); + return rc; + } out_kfree_skb: kfree_skb(skb); out: -- cgit