aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
Commit message (Collapse)AuthorAge
...
| * | | | ipv4: Remove inet_lro libraryBen Hutchings2016-02-17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There are no longer any in-tree drivers that use it. Signed-off-by: Ben Hutchings <ben@decadent.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: Export ip fragment sysctl to unprivileged usersNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that all the ip fragmentation related sysctls are namespaceified there is no reason to hide them anymore from "root" users inside containers. Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: namespacify ip fragment max dist sysctl knobNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: namespacify ip_early_demux sysctl knobNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespacify ip_dynaddr sysctl knobNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | igmp: net: Move igmp namespace init to correct fileNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When igmp related sysctl were namespacified their initializatin was erroneously put into the tcp socket namespace constructor. This patch moves the relevant code into the igmp namespace constructor to keep things consistent. Also sprinkle some #ifdefs to silence warnings Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify ip_default_ttl sysctl knobNikolay Borisov2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: add tcpi_min_rtt and tcpi_notsent_bytes to tcp_infoEric Dumazet2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tcpi_min_rtt reports the minimal rtt observed by TCP stack for the flow, in usec unit. Might be ~0U if not yet known. tcpi_notsent_bytes reports the amount of bytes in the write queue that were not yet sent. This is done in a single patch to not add a temporary 32bit padding hole in tcp_info. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net/ipv4: add dst cache support for gre lwtunnelsPaolo Abeni2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In case of UDP traffic with datagram length below MTU this gives about 4% performance increase Signed-off-by: Paolo Abeni <pabeni@redhat.com> Suggested-and-Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ip_tunnel: replace dst_cache with generic implementationPaolo Abeni2016-02-16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current ip_tunnel cache implementation is prone to a race that will cause the wrong dst to be cached on cuncurrent dst cache miss and ip tunnel update via netlink. Replacing with the generic implementation fix the issue. Signed-off-by: Paolo Abeni <pabeni@redhat.com> Suggested-and-acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: ip_tunnel: remove 'csum_help' argument to iptunnel_handle_offloadsEdward Cree2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | All users now pass false, so we can remove it, and remove the code that was conditional upon it. Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: gre: Implement LCO for GRE over IPv4Edward Cree2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | fou: enable LCO in FOU and GUEEdward Cree2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: udp: always set up for CHECKSUM_PARTIAL offloadEdward Cree2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | If the dst device doesn't support it, it'll get fixed up later anyway by validate_xmit_skb(). Also, this allows us to take advantage of LCO to avoid summing the payload multiple times. Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: local checksum offload for encapsulationEdward Cree2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The arithmetic properties of the ones-complement checksum mean that a correctly checksummed inner packet, including its checksum, has a ones complement sum depending only on whatever value was used to initialise the checksum field before checksumming (in the case of TCP and UDP, this is the ones complement sum of the pseudo header, complemented). Consequently, if we are going to offload the inner checksum with CHECKSUM_PARTIAL, we can compute the outer checksum based only on the packed data not covered by the inner checksum, and the initial value of the inner checksum field. Signed-off-by: Edward Cree <ecree@solarflare.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp/dccp: better use of ephemeral ports in bind()Eric Dumazet2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Implement strategy used in __inet_hash_connect() in opposite way : Try to find a candidate using odd ports, then fallback to even ports. We no longer disable BH for whole traversal, but one bucket at a time. We also use cond_resched() to yield cpu to other tasks if needed. I removed one indentation level and tried to mirror the loop we have in __inet_hash_connect() and variable names to ease code maintenance. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp/dccp: better use of ephemeral ports in connect()Eric Dumazet2016-02-12
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit 07f4c90062f8 ("tcp/dccp: try to not exhaust ip_local_port_range in connect()"), I added a very simple heuristic, so that we got better chances to use even ports, and allow bind() users to have more available slots. It gave nice results, but with more than 200,000 TCP sessions on a typical server, the ~30,000 ephemeral ports are still a rare resource. I chose to go a step further, by looking at all even ports, and if none was available, fallback to odd ports. The companion patch does the same in bind(), but in opposite way. I've seen exec times of up to 30ms on busy servers, so I no longer disable BH for the whole traversal, but only for each hash bucket. I also call cond_resched() to be gentle to other tasks. Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | igmp: Namespacify igmp_qrv sysctl knobNikolay Borisov2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | igmp: Namespaceify igmp_llm_reports sysctl knobNikolay Borisov2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This was initially introduced in df2cf4a78e488d26 ("IGMP: Inhibit reports for local multicast groups") by defining the sysctl in the ipv4_net_table array, however it was never implemented to be namespace aware. Fix this by changing the code accordingly. Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | igmp: Namespaceify igmp_max_msf sysctl knobNikolay Borisov2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | igmp: Namespaceify igmp_max_memberships sysctl knobNikolay Borisov2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | udp: Use uh->len instead of skb->len to compute checksum in segmentationAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The segmentation code was having to do a bunch of work to pull the skb->len and strip the udp header offset before the value could be used to adjust the checksum. Instead of doing all this work we can just use the value that goes into uh->len since that is the correct value with the correct byte order that we need anyway. By using this value we can save ourselves a bunch of pain as there is no need to do multiple byte swaps. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | udp: Clean up the use of flags in UDP segmentation offloadAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch goes though and cleans up the logic related to several of the control flags used in UDP segmentation. Specifically the use of dont_encap isn't really needed as we can just check the skb for CHECKSUM_PARTIAL and if it isn't set then we don't need to update the internal headers. As such we can just drop that value. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | gre: Use inner_proto to obtain inner header protocolAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Instead of parsing headers to determine the inner protocol we can just pull the value from inner_proto. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | gre: Use GSO flags to determine csum need instead of GRE flagsAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch updates the gre checksum path to follow something much closer to the UDP checksum path. By doing this we can avoid needing to do as much header inspection and can just make use of the fields we were already reading in the sk_buff structure. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: Move skb_has_shared_frag check out of GRE code and into segmentationAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The call skb_has_shared_frag is used in the GRE path and skb_checksum_help to verify that no frags can be modified by an external entity. This check really doesn't belong in the GRE path but in the skb_segment function itself. This way any protocol that might be segmented will be performing this check before attempting to offload a checksum to software. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: Store checksum result for offloaded GSO checksumsAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch makes it so that we can offload the checksums for a packet up to a certain point and then begin computing the checksums via software. Setting this up is fairly straight forward as all we need to do is reset the values stored in csum and csum_start for the GSO context block. One complication for this is remote checksum offload. In order to allow the inner checksums to be offloaded while computing the outer checksum manually we needed to have some way of indicating that the offload wasn't real. In order to do that I replaced CHECKSUM_PARTIAL with CHECKSUM_UNNECESSARY in the case of us computing checksums for the outer header while skipping computing checksums for the inner headers. We clean up the ip_summed flag and set it to either CHECKSUM_PARTIAL or CHECKSUM_NONE once we hand the packet off to the next lower level. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: Update remote checksum segmentation to support use of GSO checksumAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch addresses two main issues. First in the case of remote checksum offload we were avoiding dealing with scatter-gather issues. As a result it would be possible to assemble a series of frames that used frags instead of being linearized as they should have if remote checksum offload was enabled. Second I have updated the code so that we now let GSO take care of doing the checksum on the data itself and drop the special case that was added for remote checksum offload. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | net: Drop unecessary enc_features variable from tunnel segmentation functionsAlexander Duyck2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The enc_features variable isn't necessary since features isn't used anywhere after we create enc_features so instead just use a destructive AND on features itself and save ourselves the variable declaration. Signed-off-by: Alexander Duyck <aduyck@mirantis.com> Acked-by: Tom Herbert <tom@herbertland.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: add option to drop gratuitous ARP packetsJohannes Berg2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In certain 802.11 wireless deployments, there will be ARP proxies that use knowledge of the network to correctly answer requests. To prevent gratuitous ARP frames on the shared medium from being a problem, on such deployments wireless needs to drop them. Enable this by providing an option called "drop_gratuitous_arp". Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: add option to drop unicast encapsulated in L2 multicastJohannes Berg2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to solve a problem with 802.11, the so-called hole-196 attack, add an option (sysctl) called "drop_unicast_in_l2_multicast" which, if enabled, causes the stack to drop IPv4 unicast packets encapsulated in link-layer multi- or broadcast frames. Such frames can (as an attack) be created by any member of the same wireless network and transmitted as valid encrypted frames since the symmetric key for broadcast frames is shared between all stations. Additionally, enabling this option provides compliance with a SHOULD clause of RFC 1122. Reviewed-by: Julian Anastasov <ja@ssi.bg> Signed-off-by: Johannes Berg <johannes.berg@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | soreuseport: fast reuseport TCP socket selectionCraig Gallek2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This change extends the fast SO_REUSEPORT socket lookup implemented for UDP to TCP. Listener sockets with SO_REUSEPORT and the same receive address are additionally added to an array for faster random access. This means that only a single socket from the group must be found in the listener list before any socket in the group can be used to receive a packet. Previously, every socket in the group needed to be considered before handing off the incoming packet. This feature also exposes the ability to use a BPF program when selecting a socket from a reuseport group. Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | inet: refactor inet[6]_lookup functions to take skbCraig Gallek2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a preliminary step to allow fast socket lookup of SO_REUSEPORT groups. Doing so with a BPF filter will require access to the skb in question. This change plumbs the skb (and offset to payload data) through the call stack to the listening socket lookup implementations where it will be used in a following patch. Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | sock: struct proto hash function may errorCraig Gallek2016-02-11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In order to support fast reuseport lookups in TCP, the hash function defined in struct proto must be capable of returning an error code. This patch changes the function signature of all related hash functions to return an integer and handles or propagates this return value at all call sites. Signed-off-by: Craig Gallek <kraig@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: Fix syncookies sysctl default.David S. Miller2016-02-08
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Unintentionally the default was changed to zero, fix that. Fixes: 12ed8244ed ("ipv4: Namespaceify tcp syncookies sysctl knob") Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp_notsent_lowat sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp_fin_timeout sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp_orphan_retries sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp_retries2 sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp_retries1 sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp reordering sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp syncookies sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp synack retries sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | ipv4: Namespaceify tcp syn retries sysctl knobNikolay Borisov2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | Signed-off-by: Nikolay Borisov <kernel@kyup.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: tcp_cong_control helperYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Refactor and consolidate cwnd and rate updates into a new function tcp_cong_control(). Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: make congestion control more robust against reorderingYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This change enables congestion control to update cwnd based on not only packet cumulatively acked but also packets delivered out-of-order. This makes congestion control robust against packet reordering because it may raise cwnd as long as packets are being delivered once reordering has been detected (i.e., it only cares the amount of packets delivered, not the ordering among them). Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: refactor pkts acked accountingYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | A small refactoring that gets number of packets cumulatively acked from tcp_clean_rtx_queue() directly. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: new delivery accountingYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch changes the accounting of how many packets are newly acked or sacked when the sender receives an ACK. The current approach basically computes newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out) where prior_packets and prior_sacked out are snapshot at the beginning of the ACK processing. The new approach tracks the delivery information via a new TCP state variable "delivered" which monotically increases as new packets are delivered in order or out-of-order. The reason for this change is that the current approach is brittle that produces negative or inaccurate estimate. 1) For non-SACK connections, an ACK that advances the SND.UNA could reset the DUPACK counters (tp->sacked_out) in tcp_process_loss() or tcp_fastretrans_alert(). This inflates the inflight suddenly and causes under-estimate or even negative estimate. Here is a real example: before after (processing ACK) packets_out 75 73 sacked_out 23 0 ca state Loss Open The old approach computes (75-23) - (73 - 0) = -21 delivered while the new approach computes 1 delivered since it considers the 2nd-24th packets are delivered OOO. 2) MSS change would re-count packets_out and sacked_out so the estimate is in-accurate and can even become negative. E.g., the inflight is doubled when MSS is halved. 3) Spurious retransmission signaled by DSACK is not accounted The new approach is simpler and more robust. For SACK connections, tp->delivered increments as packets are being acked or sacked in SACK and ACK processing. For non-sack connections, it's done in tcp_remove_reno_sacks() and tcp_add_reno_sack(). When an ACK advances the SND.UNA, tp->delivered is incremented by the number of packets ACKed (less the current number of DUPACKs received plus one packet hole). Upon receiving a DUPACK, tp->delivered is incremented assuming one out-of-order packet is delivered. Upon receiving a DSACK, tp->delivered is incremtened assuming one retransmission is delivered in tcp_sacktag_write_queue(). Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: move cwnd reduction after recovery state procesingYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Currently the cwnd is reduced and increased in various different places. The reduction happens in various places in the recovery state processing (tcp_fastretrans_alert) while the increase happens afterward. A better sequence is to identify lost packets and update the congestion control state (icsk_ca_state) first. Then base on the new state, up/down the cwnd in one central place. It's more clear to reason cwnd changes. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
| * | | | tcp: retransmit after recovery processing and congestion controlYuchung Cheng2016-02-07
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The retransmission and F-RTO transmission currently happen inside recovery state processing (tcp_fastretrans_alert) but before congestion control. This refactoring moves the logic after both s.t. we can determine how much to send (cwnd) before deciding what to send. Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Eric Dumazet <ncardwell@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
generated by cgit v1.2.2 (git 2.25.0) at 2025-04-21 23:29:08 -0400