From d206940319c41df4299db75ed56142177bb2e5f6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:11 +0100 Subject: net: core: introduce netif_skb_dev_features Will be used by upcoming ipv4 forward path change that needs to determine feature mask using skb->dst->dev instead of skb->dev. Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/netdevice.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 440a02ee6f92..21d4e6be8949 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3068,7 +3068,12 @@ void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -netdev_features_t netif_skb_features(struct sk_buff *skb); +netdev_features_t netif_skb_dev_features(struct sk_buff *skb, + const struct net_device *dev); +static inline netdev_features_t netif_skb_features(struct sk_buff *skb) +{ + return netif_skb_dev_features(skb, skb->dev); +} static inline bool net_gso_ok(netdev_features_t features, int gso_type) { -- cgit v1.3 From fe6cc55f3a9a053482a76f5a6b2257cee51b4663 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Feb 2014 23:09:12 +0100 Subject: net: ip, ipv6: handle gso skbs in forwarding path Marcelo Ricardo Leitner reported problems when the forwarding link path has a lower mtu than the incoming one if the inbound interface supports GRO. Given: Host R1 R2 Host sends tcp stream which is routed via R1 and R2. R1 performs GRO. In this case, the kernel will fail to send ICMP fragmentation needed messages (or pkt too big for ipv6), as GSO packets currently bypass dstmtu checks in forward path. Instead, Linux tries to send out packets exceeding the mtu. When locking route MTU on Host (i.e., no ipv4 DF bit set), R1 does not fragment the packets when forwarding, and again tries to send out packets exceeding R1-R2 link mtu. This alters the forwarding dstmtu checks to take the individual gso segment lengths into account. For ipv6, we send out pkt too big error for gso if the individual segments are too big. For ipv4, we either send icmp fragmentation needed, or, if the DF bit is not set, perform software segmentation and let the output path create fragments when the packet is leaving the machine. It is not 100% correct as the error message will contain the headers of the GRO skb instead of the original/segmented one, but it seems to work fine in my (limited) tests. Eric Dumazet suggested to simply shrink mss via ->gso_size to avoid sofware segmentation. However it turns out that skb_segment() assumes skb nr_frags is related to mss size so we would BUG there. I don't want to mess with it considering Herbert and Eric disagree on what the correct behavior should be. Hannes Frederic Sowa notes that when we would shrink gso_size skb_segment would then also need to deal with the case where SKB_MAX_FRAGS would be exceeded. This uses sofware segmentation in the forward path when we hit ipv4 non-DF packets and the outgoing link mtu is too small. Its not perfect, but given the lack of bug reports wrt. GRO fwd being broken this is a rare case anyway. Also its not like this could not be improved later once the dust settles. Acked-by: Herbert Xu Reported-by: Marcelo Ricardo Leitner Signed-off-by: Florian Westphal Signed-off-by: David S. Miller --- include/linux/skbuff.h | 17 ++++++++++++ net/ipv4/ip_forward.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++-- net/ipv6/ip6_output.c | 17 ++++++++++-- 3 files changed, 101 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af8cbf..3ebbbe7b6d05 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2916,5 +2916,22 @@ static inline bool skb_head_is_locked(const struct sk_buff *skb) { return !skb->head_frag || skb_cloned(skb); } + +/** + * skb_gso_network_seglen - Return length of individual segments of a gso packet + * + * @skb: GSO skb + * + * skb_gso_network_seglen is used to determine the real size of the + * individual segments, including Layer3 (IP, IPv6) and L4 headers (TCP/UDP). + * + * The MAC/L2 header is not accounted for. + */ +static inline unsigned int skb_gso_network_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - + skb_network_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} #endif /* __KERNEL__ */ #endif /* _LINUX_SKBUFF_H */ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e9f1217a8afd..f3869c186d97 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -39,6 +39,71 @@ #include #include +static bool ip_may_fragment(const struct sk_buff *skb) +{ + return unlikely((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) || + !skb->local_df; +} + +static bool ip_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + +static bool ip_gso_exceeds_dst_mtu(const struct sk_buff *skb) +{ + unsigned int mtu; + + if (skb->local_df || !skb_is_gso(skb)) + return false; + + mtu = ip_dst_mtu_maybe_forward(skb_dst(skb), true); + + /* if seglen > mtu, do software segmentation for IP fragmentation on + * output. DF bit cannot be set since ip_forward would have sent + * icmp error. + */ + return skb_gso_network_seglen(skb) > mtu; +} + +/* called if GSO skb needs to be fragmented on forward */ +static int ip_forward_finish_gso(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + netdev_features_t features; + struct sk_buff *segs; + int ret = 0; + + features = netif_skb_dev_features(skb, dst->dev); + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + if (IS_ERR(segs)) { + kfree_skb(skb); + return -ENOMEM; + } + + consume_skb(skb); + + do { + struct sk_buff *nskb = segs->next; + int err; + + segs->next = NULL; + err = dst_output(segs); + + if (err && ret == 0) + ret = err; + segs = nskb; + } while (segs); + + return ret; +} + static int ip_forward_finish(struct sk_buff *skb) { struct ip_options *opt = &(IPCB(skb)->opt); @@ -49,6 +114,9 @@ static int ip_forward_finish(struct sk_buff *skb) if (unlikely(opt->optlen)) ip_forward_options(skb); + if (ip_gso_exceeds_dst_mtu(skb)) + return ip_forward_finish_gso(skb); + return dst_output(skb); } @@ -91,8 +159,7 @@ int ip_forward(struct sk_buff *skb) IPCB(skb)->flags |= IPSKB_FORWARDED; mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (unlikely(skb->len > mtu && !skb_is_gso(skb) && - (ip_hdr(skb)->frag_off & htons(IP_DF))) && !skb->local_df) { + if (!ip_may_fragment(skb) && ip_exceeds_mtu(skb, mtu)) { IP_INC_STATS(dev_net(rt->dst.dev), IPSTATS_MIB_FRAGFAILS); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26ccf81..070a2fae2375 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -342,6 +342,20 @@ static unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) return mtu; } +static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu || skb->local_df) + return false; + + if (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu) + return true; + + if (skb_is_gso(skb) && skb_gso_network_seglen(skb) <= mtu) + return false; + + return true; +} + int ip6_forward(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -466,8 +480,7 @@ int ip6_forward(struct sk_buff *skb) if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; - if ((!skb->local_df && skb->len > mtu && !skb_is_gso(skb)) || - (IP6CB(skb)->frag_max_size && IP6CB(skb)->frag_max_size > mtu)) { + if (ip6_pkt_too_big(skb, mtu)) { /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); -- cgit v1.3 From ef2820a735f74ea60335f8ba3801b844f0cb184d Mon Sep 17 00:00:00 2001 From: Matija Glavinic Pecotic Date: Fri, 14 Feb 2014 14:51:18 +0100 Subject: net: sctp: Fix a_rwnd/rwnd management to reflect real state of the receiver's buffer Implementation of (a)rwnd calculation might lead to severe performance issues and associations completely stalling. These problems are described and solution is proposed which improves lksctp's robustness in congestion state. 1) Sudden drop of a_rwnd and incomplete window recovery afterwards Data accounted in sctp_assoc_rwnd_decrease takes only payload size (sctp data), but size of sk_buff, which is blamed against receiver buffer, is not accounted in rwnd. Theoretically, this should not be the problem as actual size of buffer is double the amount requested on the socket (SO_RECVBUF). Problem here is that this will have bad scaling for data which is less then sizeof sk_buff. E.g. in 4G (LTE) networks, link interfacing radio side will have a large portion of traffic of this size (less then 100B). An example of sudden drop and incomplete window recovery is given below. Node B exhibits problematic behavior. Node A initiates association and B is configured to advertise rwnd of 10000. A sends messages of size 43B (size of typical sctp message in 4G (LTE) network). On B data is left in buffer by not reading socket in userspace. Lets examine when we will hit pressure state and declare rwnd to be 0 for scenario with above stated parameters (rwnd == 10000, chunk size == 43, each chunk is sent in separate sctp packet) Logic is implemented in sctp_assoc_rwnd_decrease: socket_buffer (see below) is maximum size which can be held in socket buffer (sk_rcvbuf). current_alloced is amount of data currently allocated (rx_count) A simple expression is given for which it will be examined after how many packets for above stated parameters we enter pressure state: We start by condition which has to be met in order to enter pressure state: socket_buffer < currently_alloced; currently_alloced is represented as size of sctp packets received so far and not yet delivered to userspace. x is the number of chunks/packets (since there is no bundling, and each chunk is delivered in separate packet, we can observe each chunk also as sctp packet, and what is important here, having its own sk_buff): socket_buffer < x*each_sctp_packet; each_sctp_packet is sctp chunk size + sizeof(struct sk_buff). socket_buffer is twice the amount of initially requested size of socket buffer, which is in case of sctp, twice the a_rwnd requested: 2*rwnd < x*(payload+sizeof(struc sk_buff)); sizeof(struct sk_buff) is 190 (3.13.0-rc4+). Above is stated that rwnd is 10000 and each payload size is 43 20000 < x(43+190); x > 20000/233; x ~> 84; After ~84 messages, pressure state is entered and 0 rwnd is advertised while received 84*43B ~= 3612B sctp data. This is why external observer notices sudden drop from 6474 to 0, as it will be now shown in example: IP A.34340 > B.12345: sctp (1) [INIT] [init tag: 1875509148] [rwnd: 81920] [OS: 10] [MIS: 65535] [init TSN: 1096057017] IP B.12345 > A.34340: sctp (1) [INIT ACK] [init tag: 3198966556] [rwnd: 10000] [OS: 10] [MIS: 10] [init TSN: 902132839] IP A.34340 > B.12345: sctp (1) [COOKIE ECHO] IP B.12345 > A.34340: sctp (1) [COOKIE ACK] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057017] [SID: 0] [SSEQ 0] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057017] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057018] [SID: 0] [SSEQ 1] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057018] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057019] [SID: 0] [SSEQ 2] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057019] [a_rwnd 9914] [#gap acks 0] [#dup tsns 0] <...> IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057098] [SID: 0] [SSEQ 81] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057098] [a_rwnd 6517] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057099] [SID: 0] [SSEQ 82] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057099] [a_rwnd 6474] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057100] [SID: 0] [SSEQ 83] [PPID 0x18] --> Sudden drop IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] At this point, rwnd_press stores current rwnd value so it can be later restored in sctp_assoc_rwnd_increase. This however doesn't happen as condition to start slowly increasing rwnd until rwnd_press is returned to rwnd is never met. This condition is not met since rwnd, after it hit 0, must first reach rwnd_press by adding amount which is read from userspace. Let us observe values in above example. Initial a_rwnd is 10000, pressure was hit when rwnd was ~6500 and the amount of actual sctp data currently waiting to be delivered to userspace is ~3500. When userspace starts to read, sctp_assoc_rwnd_increase will be blamed only for sctp data, which is ~3500. Condition is never met, and when userspace reads all data, rwnd stays on 3569. IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 1505] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057100] [a_rwnd 3010] [#gap acks 0] [#dup tsns 0] IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057101] [SID: 0] [SSEQ 84] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057101] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0] --> At this point userspace read everything, rwnd recovered only to 3569 IP A.34340 > B.12345: sctp (1) [DATA] (B)(E) [TSN: 1096057102] [SID: 0] [SSEQ 85] [PPID 0x18] IP B.12345 > A.34340: sctp (1) [SACK] [cum ack 1096057102] [a_rwnd 3569] [#gap acks 0] [#dup tsns 0] Reproduction is straight forward, it is enough for sender to send packets of size less then sizeof(struct sk_buff) and receiver keeping them in its buffers. 2) Minute size window for associations sharing the same socket buffer In case multiple associations share the same socket, and same socket buffer (sctp.rcvbuf_policy == 0), different scenarios exist in which congestion on one of the associations can permanently drop rwnd of other association(s). Situation will be typically observed as one association suddenly having rwnd dropped to size of last packet received and never recovering beyond that point. Different scenarios will lead to it, but all have in common that one of the associations (let it be association from 1)) nearly depleted socket buffer, and the other association blames socket buffer just for the amount enough to start the pressure. This association will enter pressure state, set rwnd_press and announce 0 rwnd. When data is read by userspace, similar situation as in 1) will occur, rwnd will increase just for the size read by userspace but rwnd_press will be high enough so that association doesn't have enough credit to reach rwnd_press and restore to previous state. This case is special case of 1), being worse as there is, in the worst case, only one packet in buffer for which size rwnd will be increased. Consequence is association which has very low maximum rwnd ('minute size', in our case down to 43B - size of packet which caused pressure) and as such unusable. Scenario happened in the field and labs frequently after congestion state (link breaks, different probabilities of packet drop, packet reordering) and with scenario 1) preceding. Here is given a deterministic scenario for reproduction: >From node A establish two associations on the same socket, with rcvbuf_policy being set to share one common buffer (sctp.rcvbuf_policy == 0). On association 1 repeat scenario from 1), that is, bring it down to 0 and restore up. Observe scenario 1). Use small payload size (here we use 43). Once rwnd is 'recovered', bring it down close to 0, as in just one more packet would close it. This has as a consequence that association number 2 is able to receive (at least) one more packet which will bring it in pressure state. E.g. if association 2 had rwnd of 10000, packet received was 43, and we enter at this point into pressure, rwnd_press will have 9957. Once payload is delivered to userspace, rwnd will increase for 43, but conditions to restore rwnd to original state, just as in 1), will never be satisfied. --> Association 1, between A.y and B.12345 IP A.55915 > B.12345: sctp (1) [INIT] [init tag: 836880897] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 4032536569] IP B.12345 > A.55915: sctp (1) [INIT ACK] [init tag: 2873310749] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3799315613] IP A.55915 > B.12345: sctp (1) [COOKIE ECHO] IP B.12345 > A.55915: sctp (1) [COOKIE ACK] --> Association 2, between A.z and B.12346 IP A.55915 > B.12346: sctp (1) [INIT] [init tag: 534798321] [rwnd: 10000] [OS: 10] [MIS: 65535] [init TSN: 2099285173] IP B.12346 > A.55915: sctp (1) [INIT ACK] [init tag: 516668823] [rwnd: 81920] [OS: 10] [MIS: 10] [init TSN: 3676403240] IP A.55915 > B.12346: sctp (1) [COOKIE ECHO] IP B.12346 > A.55915: sctp (1) [COOKIE ACK] --> Deplete socket buffer by sending messages of size 43B over association 1 IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315613] [SID: 0] [SSEQ 0] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315613] [a_rwnd 9957] [#gap acks 0] [#dup tsns 0] <...> IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315696] [a_rwnd 6388] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315697] [SID: 0] [SSEQ 84] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315697] [a_rwnd 6345] [#gap acks 0] [#dup tsns 0] --> Sudden drop on 1 IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315698] [SID: 0] [SSEQ 85] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315698] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Here userspace read, rwnd 'recovered' to 3698, now deplete again using association 1 so there is place in buffer for only one more packet IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315799] [SID: 0] [SSEQ 186] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315799] [a_rwnd 86] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315800] [SID: 0] [SSEQ 187] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 43] [#gap acks 0] [#dup tsns 0] --> Socket buffer is almost depleted, but there is space for one more packet, send them over association 2, size 43B IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403240] [SID: 0] [SSEQ 0] [PPID 0x18] IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403240] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Immediate drop IP A.60995 > B.12346: sctp (1) [SACK] [cum ack 387491510] [a_rwnd 0] [#gap acks 0] [#dup tsns 0] --> Read everything from the socket, both association recover up to maximum rwnd they are capable of reaching, note that association 1 recovered up to 3698, and association 2 recovered only to 43 IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 1548] [#gap acks 0] [#dup tsns 0] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315800] [a_rwnd 3053] [#gap acks 0] [#dup tsns 0] IP B.12345 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3799315801] [SID: 0] [SSEQ 188] [PPID 0x18] IP A.55915 > B.12345: sctp (1) [SACK] [cum ack 3799315801] [a_rwnd 3698] [#gap acks 0] [#dup tsns 0] IP B.12346 > A.55915: sctp (1) [DATA] (B)(E) [TSN: 3676403241] [SID: 0] [SSEQ 1] [PPID 0x18] IP A.55915 > B.12346: sctp (1) [SACK] [cum ack 3676403241] [a_rwnd 43] [#gap acks 0] [#dup tsns 0] A careful reader might wonder why it is necessary to reproduce 1) prior reproduction of 2). It is simply easier to observe when to send packet over association 2 which will push association into the pressure state. Proposed solution: Both problems share the same root cause, and that is improper scaling of socket buffer with rwnd. Solution in which sizeof(sk_buff) is taken into concern while calculating rwnd is not possible due to fact that there is no linear relationship between amount of data blamed in increase/decrease with IP packet in which payload arrived. Even in case such solution would be followed, complexity of the code would increase. Due to nature of current rwnd handling, slow increase (in sctp_assoc_rwnd_increase) of rwnd after pressure state is entered is rationale, but it gives false representation to the sender of current buffer space. Furthermore, it implements additional congestion control mechanism which is defined on implementation, and not on standard basis. Proposed solution simplifies whole algorithm having on mind definition from rfc: o Receiver Window (rwnd): This gives the sender an indication of the space available in the receiver's inbound buffer. Core of the proposed solution is given with these lines: sctp_assoc_rwnd_update: if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; else asoc->rwnd = 0; We advertise to sender (half of) actual space we have. Half is in the braces depending whether you would like to observe size of socket buffer as SO_RECVBUF or twice the amount, i.e. size is the one visible from userspace, that is, from kernelspace. In this way sender is given with good approximation of our buffer space, regardless of the buffer policy - we always advertise what we have. Proposed solution fixes described problems and removes necessity for rwnd restoration algorithm. Finally, as proposed solution is simplification, some lines of code, along with some bytes in struct sctp_association are saved. Version 2 of the patch addressed comments from Vlad. Name of the function is set to be more descriptive, and two parts of code are changed, in one removing the superfluous call to sctp_assoc_rwnd_update since call would not result in update of rwnd, and the other being reordering of the code in a way that call to sctp_assoc_rwnd_update updates rwnd. Version 3 corrected change introduced in v2 in a way that existing function is not reordered/copied in line, but it is correctly called. Thanks Vlad for suggesting. Signed-off-by: Matija Glavinic Pecotic Reviewed-by: Alexander Sverdlin Acked-by: Vlad Yasevich Signed-off-by: David S. Miller --- include/net/sctp/structs.h | 14 +------- net/sctp/associola.c | 82 ++++++++++------------------------------------ net/sctp/sm_statefuns.c | 2 +- net/sctp/socket.c | 6 ---- net/sctp/ulpevent.c | 8 +++-- 5 files changed, 25 insertions(+), 87 deletions(-) (limited to 'include') diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index d992ca3145fe..6ee76c804893 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -1653,17 +1653,6 @@ struct sctp_association { /* This is the last advertised value of rwnd over a SACK chunk. */ __u32 a_rwnd; - /* Number of bytes by which the rwnd has slopped. The rwnd is allowed - * to slop over a maximum of the association's frag_point. - */ - __u32 rwnd_over; - - /* Keeps treack of rwnd pressure. This happens when we have - * a window, but not recevie buffer (i.e small packets). This one - * is releases slowly (1 PMTU at a time ). - */ - __u32 rwnd_press; - /* This is the sndbuf size in use for the association. * This corresponds to the sndbuf size for the association, * as specified in the sk->sndbuf. @@ -1892,8 +1881,7 @@ void sctp_assoc_update(struct sctp_association *old, __u32 sctp_association_get_next_tsn(struct sctp_association *); void sctp_assoc_sync_pmtu(struct sock *, struct sctp_association *); -void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); -void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); +void sctp_assoc_rwnd_update(struct sctp_association *, bool); void sctp_assoc_set_primary(struct sctp_association *, struct sctp_transport *); void sctp_assoc_del_nonprimary_peers(struct sctp_association *, diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 5ae609200674..f558433537b8 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1367,44 +1367,35 @@ static inline bool sctp_peer_needs_update(struct sctp_association *asoc) return false; } -/* Increase asoc's rwnd by len and send any window update SACK if needed. */ -void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) +/* Update asoc's rwnd for the approximated state in the buffer, + * and check whether SACK needs to be sent. + */ +void sctp_assoc_rwnd_update(struct sctp_association *asoc, bool update_peer) { + int rx_count; struct sctp_chunk *sack; struct timer_list *timer; - if (asoc->rwnd_over) { - if (asoc->rwnd_over >= len) { - asoc->rwnd_over -= len; - } else { - asoc->rwnd += (len - asoc->rwnd_over); - asoc->rwnd_over = 0; - } - } else { - asoc->rwnd += len; - } + if (asoc->ep->rcvbuf_policy) + rx_count = atomic_read(&asoc->rmem_alloc); + else + rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - /* If we had window pressure, start recovering it - * once our rwnd had reached the accumulated pressure - * threshold. The idea is to recover slowly, but up - * to the initial advertised window. - */ - if (asoc->rwnd_press && asoc->rwnd >= asoc->rwnd_press) { - int change = min(asoc->pathmtu, asoc->rwnd_press); - asoc->rwnd += change; - asoc->rwnd_press -= change; - } + if ((asoc->base.sk->sk_rcvbuf - rx_count) > 0) + asoc->rwnd = (asoc->base.sk->sk_rcvbuf - rx_count) >> 1; + else + asoc->rwnd = 0; - pr_debug("%s: asoc:%p rwnd increased by %d to (%u, %u) - %u\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->a_rwnd); + pr_debug("%s: asoc:%p rwnd=%u, rx_count=%d, sk_rcvbuf=%d\n", + __func__, asoc, asoc->rwnd, rx_count, + asoc->base.sk->sk_rcvbuf); /* Send a window update SACK if the rwnd has increased by at least the * minimum of the association's PMTU and half of the receive buffer. * The algorithm used is similar to the one described in * Section 4.2.3.3 of RFC 1122. */ - if (sctp_peer_needs_update(asoc)) { + if (update_peer && sctp_peer_needs_update(asoc)) { asoc->a_rwnd = asoc->rwnd; pr_debug("%s: sending window update SACK- asoc:%p rwnd:%u " @@ -1426,45 +1417,6 @@ void sctp_assoc_rwnd_increase(struct sctp_association *asoc, unsigned int len) } } -/* Decrease asoc's rwnd by len. */ -void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) -{ - int rx_count; - int over = 0; - - if (unlikely(!asoc->rwnd || asoc->rwnd_over)) - pr_debug("%s: association:%p has asoc->rwnd:%u, " - "asoc->rwnd_over:%u!\n", __func__, asoc, - asoc->rwnd, asoc->rwnd_over); - - if (asoc->ep->rcvbuf_policy) - rx_count = atomic_read(&asoc->rmem_alloc); - else - rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc); - - /* If we've reached or overflowed our receive buffer, announce - * a 0 rwnd if rwnd would still be positive. Store the - * the potential pressure overflow so that the window can be restored - * back to original value. - */ - if (rx_count >= asoc->base.sk->sk_rcvbuf) - over = 1; - - if (asoc->rwnd >= len) { - asoc->rwnd -= len; - if (over) { - asoc->rwnd_press += asoc->rwnd; - asoc->rwnd = 0; - } - } else { - asoc->rwnd_over = len - asoc->rwnd; - asoc->rwnd = 0; - } - - pr_debug("%s: asoc:%p rwnd decreased by %d to (%u, %u, %u)\n", - __func__, asoc, len, asoc->rwnd, asoc->rwnd_over, - asoc->rwnd_press); -} /* Build the bind address list for the association based on info from the * local endpoint and the remote peer. diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 483dcd71b3c5..591b44d3b7de 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6176,7 +6176,7 @@ static int sctp_eat_data(const struct sctp_association *asoc, * PMTU. In cases, such as loopback, this might be a rather * large spill over. */ - if ((!chunk->data_accepted) && (!asoc->rwnd || asoc->rwnd_over || + if ((!chunk->data_accepted) && (!asoc->rwnd || (datalen > asoc->rwnd + asoc->frag_point))) { /* If this is the next TSN, consider reneging to make diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9e91d6e5df63..7075ac847fde 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2092,12 +2092,6 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk, sctp_skb_pull(skb, copied); skb_queue_head(&sk->sk_receive_queue, skb); - /* When only partial message is copied to the user, increase - * rwnd by that amount. If all the data in the skb is read, - * rwnd is updated when the event is freed. - */ - if (!sctp_ulpevent_is_notification(event)) - sctp_assoc_rwnd_increase(event->asoc, copied); goto out; } else if ((event->msg_flags & MSG_NOTIFICATION) || (event->msg_flags & MSG_EOR)) diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 85c64658bd0b..8d198ae03606 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -989,7 +989,7 @@ static void sctp_ulpevent_receive_data(struct sctp_ulpevent *event, skb = sctp_event2skb(event); /* Set the owner and charge rwnd for bytes received. */ sctp_ulpevent_set_owner(event, asoc); - sctp_assoc_rwnd_decrease(asoc, skb_headlen(skb)); + sctp_assoc_rwnd_update(asoc, false); if (!skb->data_len) return; @@ -1011,6 +1011,7 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) { struct sk_buff *skb, *frag; unsigned int len; + struct sctp_association *asoc; /* Current stack structures assume that the rcv buffer is * per socket. For UDP style sockets this is not true as @@ -1035,8 +1036,11 @@ static void sctp_ulpevent_release_data(struct sctp_ulpevent *event) } done: - sctp_assoc_rwnd_increase(event->asoc, len); + asoc = event->asoc; + sctp_association_hold(asoc); sctp_ulpevent_release_owner(event); + sctp_assoc_rwnd_update(asoc, true); + sctp_association_put(asoc); } static void sctp_ulpevent_release_frag_data(struct sctp_ulpevent *event) -- cgit v1.3 From 99932d4fc03a13bb3e94938fe25458fabc8f2fc3 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:20 +0100 Subject: netdevice: add queue selection fallback handler for ndo_select_queue Add a new argument for ndo_select_queue() callback that passes a fallback handler. This gets invoked through netdev_pick_tx(); fallback handler is currently __netdev_pick_tx() as most drivers invoke this function within their customized implementation in case for skbs that don't need any special handling. This fallback handler can then be replaced on other call-sites with different queue selection methods (e.g. in packet sockets, pktgen etc). This also has the nice side-effect that __netdev_pick_tx() is then only invoked from netdev_pick_tx() and export of that function to modules can be undone. Suggested-by: David S. Miller Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +++--- drivers/net/ethernet/lantiq_etop.c | 2 +- drivers/net/ethernet/mellanox/mlx4/en_tx.c | 4 ++-- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 2 +- drivers/net/ethernet/tile/tilegx.c | 2 +- drivers/net/team/team.c | 2 +- drivers/net/tun.c | 2 +- drivers/net/wireless/mwifiex/main.c | 2 +- drivers/staging/bcm/Bcmnet.c | 2 +- drivers/staging/netlogic/xlr_net.c | 2 +- drivers/staging/rtl8188eu/os_dep/os_intfs.c | 2 +- include/linux/netdevice.h | 9 ++++++--- net/core/flow_dissector.c | 7 +++---- net/mac80211/iface.c | 6 ++++-- 17 files changed, 31 insertions(+), 27 deletions(-) (limited to 'include') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 867664918715..1c6104d3501d 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3707,7 +3707,7 @@ static inline int bond_slave_override(struct bonding *bond, static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index 9d7419e0390b..66c0df78c3ff 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -1873,7 +1873,7 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw) } u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct bnx2x *bp = netdev_priv(dev); @@ -1895,7 +1895,7 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, } /* select a non-FCoE queue */ - return __netdev_pick_tx(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); + return fallback(dev, skb) % BNX2X_NUM_ETH_QUEUES(bp); } void bnx2x_set_num_queues(struct bnx2x *bp) diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index bfc58d488bb5..a89a40f88c25 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -496,7 +496,7 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); /* select_queue callback */ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); static inline void bnx2x_update_rx_prod(struct bnx2x *bp, struct bnx2x_fastpath *fp, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6d4ada72dfd0..18076c4178b4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6881,7 +6881,7 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) } static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; #ifdef IXGBE_FCOE @@ -6907,7 +6907,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) break; default: - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); } f = &adapter->ring_feature[RING_F_FCOE]; @@ -6920,7 +6920,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, return txq + f->offset; #else - return __netdev_pick_tx(dev, skb); + return fallback(dev, skb); #endif } diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c index 8f9266c64c75..fd4b6aecf6ee 100644 --- a/drivers/net/ethernet/lantiq_etop.c +++ b/drivers/net/ethernet/lantiq_etop.c @@ -619,7 +619,7 @@ ltq_etop_set_multicast_list(struct net_device *dev) static u16 ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* we are currently only using the first queue */ return 0; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 8e8a7eb43a2c..13457032d15f 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -629,7 +629,7 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc, struct sk_buff *sk } u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct mlx4_en_priv *priv = netdev_priv(dev); u16 rings_p_up = priv->num_tx_rings_p_up; @@ -641,7 +641,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, if (vlan_tx_tag_present(skb)) up = vlan_tx_tag_get(skb) >> VLAN_PRIO_SHIFT; - return __netdev_pick_tx(dev, skb) % rings_p_up + up * rings_p_up; + return fallback(dev, skb) % rings_p_up + up * rings_p_up; } static void mlx4_bf_copy(void __iomem *dst, unsigned long *src, unsigned bytecnt) diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 3af04c3f42ea..9ca223bc90fc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -723,7 +723,7 @@ int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq); void mlx4_en_tx_irq(struct mlx4_cq *mcq); u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev); int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv, diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index 023237a65720..17503da9f7a5 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -2071,7 +2071,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) /* Return subqueue id on this core (one per core). */ static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return smp_processor_id(); } diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index 28407426fd6f..c8624a8235ab 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -1648,7 +1648,7 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev) } static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { /* * This helper function exists to help dev_pick_tx get the correct diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 44c4db8450f0..8fe9cb7d0f72 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -366,7 +366,7 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash) * hope the rxq no. may help here. */ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; diff --git a/drivers/net/wireless/mwifiex/main.c b/drivers/net/wireless/mwifiex/main.c index 4d79761b9c87..9d3d2758ec35 100644 --- a/drivers/net/wireless/mwifiex/main.c +++ b/drivers/net/wireless/mwifiex/main.c @@ -748,7 +748,7 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev) static u16 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { skb->priority = cfg80211_classify8021d(skb, NULL); return mwifiex_1d_to_wmm_queue[skb->priority]; diff --git a/drivers/staging/bcm/Bcmnet.c b/drivers/staging/bcm/Bcmnet.c index 8dfdd2732bdc..95a2358267ba 100644 --- a/drivers/staging/bcm/Bcmnet.c +++ b/drivers/staging/bcm/Bcmnet.c @@ -40,7 +40,7 @@ static INT bcm_close(struct net_device *dev) } static u16 bcm_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return ClassifyPacket(netdev_priv(dev), skb); } diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c index eedffed17e39..6f9ac27730af 100644 --- a/drivers/staging/netlogic/xlr_net.c +++ b/drivers/staging/netlogic/xlr_net.c @@ -307,7 +307,7 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb, } static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { return (u16)smp_processor_id(); } diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c index 68f98fa114d2..7c9ee58f47bb 100644 --- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c +++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c @@ -653,7 +653,7 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb) } static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, select_queue_fallback_t fallback) { struct adapter *padapter = rtw_netdev_priv(dev); struct mlme_priv *pmlmepriv = &padapter->mlmepriv; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 21d4e6be8949..1de9c136b066 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -752,6 +752,9 @@ struct netdev_phys_port_id { unsigned char id_len; }; +typedef u16 (*select_queue_fallback_t)(struct net_device *dev, + struct sk_buff *skb); + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -783,7 +786,7 @@ struct netdev_phys_port_id { * Required can not be NULL. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - * void *accel_priv); + * void *accel_priv, select_queue_fallback_t fallback); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -1005,7 +1008,8 @@ struct net_device_ops { struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, - void *accel_priv); + void *accel_priv, + select_queue_fallback_t fallback); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1551,7 +1555,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, void *accel_priv); -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* * Net namespace inlines diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 87577d447554..75fe83f590ea 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -372,7 +372,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) #endif } -u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) +static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) { struct sock *sk = skb->sk; int queue_index = sk_tx_queue_get(sk); @@ -392,7 +392,6 @@ u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb) return queue_index; } -EXPORT_SYMBOL(__netdev_pick_tx); struct netdev_queue *netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, @@ -403,8 +402,8 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, if (dev->real_num_tx_queues != 1) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb, - accel_priv); + queue_index = ops->ndo_select_queue(dev, skb, accel_priv, + __netdev_pick_tx); else queue_index = __netdev_pick_tx(dev, skb); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d6d1f1df9119..ce1c44370610 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1057,7 +1057,8 @@ static void ieee80211_uninit(struct net_device *dev) static u16 ieee80211_netdev_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb); } @@ -1075,7 +1076,8 @@ static const struct net_device_ops ieee80211_dataif_ops = { static u16 ieee80211_monitor_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv) + void *accel_priv, + select_queue_fallback_t fallback) { struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); struct ieee80211_local *local = sdata->local; -- cgit v1.3 From b9507bdaf40e91fea2b1c0c1ee7dc627c8ee6fd6 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 16 Feb 2014 15:55:21 +0100 Subject: netdevice: move netdev_cap_txqueue for shared usage to header In order to allow users to invoke netdev_cap_txqueue, it needs to be moved into netdevice.h header file. While at it, also add kernel doc header to document the API. Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- include/linux/netdevice.h | 20 ++++++++++++++++++++ net/core/flow_dissector.c | 13 +------------ 2 files changed, 21 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1de9c136b066..e8eeebd49a98 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2278,6 +2278,26 @@ static inline void netdev_reset_queue(struct net_device *dev_queue) netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } +/** + * netdev_cap_txqueue - check if selected tx queue exceeds device queues + * @dev: network device + * @queue_index: given tx queue index + * + * Returns 0 if given tx queue index >= number of device tx queues, + * otherwise returns the originally passed tx queue index. + */ +static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + return 0; + } + + return queue_index; +} + /** * netif_running - test if up * @dev: network device diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 75fe83f590ea..e29e810663d7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -323,17 +323,6 @@ u32 __skb_get_poff(const struct sk_buff *skb) return poff; } -static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) -{ - if (unlikely(queue_index >= dev->real_num_tx_queues)) { - net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", - dev->name, queue_index, - dev->real_num_tx_queues); - return 0; - } - return queue_index; -} - static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) { #ifdef CONFIG_XPS @@ -408,7 +397,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev, queue_index = __netdev_pick_tx(dev, skb); if (!accel_priv) - queue_index = dev_cap_txqueue(dev, queue_index); + queue_index = netdev_cap_txqueue(dev, queue_index); } skb_set_queue_mapping(skb, queue_index); -- cgit v1.3