summaryrefslogtreecommitdiffhomepage
path: root/pkg/tcpip/transport
AgeCommit message (Collapse)Author
2019-10-18Fix typo while initializing protocol for UDP endpoints.Mithun Iyer
Fixes #763 PiperOrigin-RevId: 275563222
2019-10-14Internal change.gVisor bot
PiperOrigin-RevId: 274700093
2019-10-14Reorder BUILD license and load functions in netstack.Kevin Krakauer
PiperOrigin-RevId: 274672346
2019-10-09Internal change.gVisor bot
PiperOrigin-RevId: 273861936
2019-10-07Implement IP_TTL.Ian Gudger
Also change the default TTL to 64 to match Linux. PiperOrigin-RevId: 273430341
2019-10-03Implement proper local broadcast behaviorChris Kuiper
The behavior for sending and receiving local broadcast (255.255.255.255) traffic is as follows: Outgoing -------- * A broadcast packet sent on a socket that is bound to an interface goes out that interface * A broadcast packet sent on an unbound socket follows the route table to select the outgoing interface + if an explicit route entry exists for 255.255.255.255/32, use that one + else use the default route * Broadcast packets are looped back and delivered following the rules for incoming packets (see next). This is the same behavior as for multicast packets, except that it cannot be disabled via sockopt. Incoming -------- * Sockets wishing to receive broadcast packets must bind to either INADDR_ANY (0.0.0.0) or INADDR_BROADCAST (255.255.255.255). No other socket receives broadcast packets. * Broadcast packets are multiplexed to all sockets matching it. This is the same behavior as for multicast packets. * A socket can bind to 255.255.255.255:<port> and then receive its own broadcast packets sent to 255.255.255.255:<port> In addition, this change implicitly fixes an issue with multicast reception. If two sockets want to receive a given multicast stream and one is bound to ANY while the other is bound to the multicast address, only one of them will receive the traffic. PiperOrigin-RevId: 272792377
2019-09-30Fix bugs in PickEphemeralPort for TCP.Bhasker Hariharan
Netstack always picks a random start point everytime PickEphemeralPort is called. While this is required for UDP so that DNS requests go out through a randomized set of ports it is not required for TCP. Infact Linux explicitly hashes the (srcip, dstip, dstport) and a one time secret initialized at start of the application to get a random offset. But to ensure it doesn't start from the same point on every scan it uses a static hint that is incremented by 2 in every call to pick ephemeral ports. The reason for 2 is Linux seems to split the port ranges where active connects seem to use even ones while odd ones are used by listening sockets. This CL implements a similar strategy where we use a hash + hint to generate the offset to start the search for a free Ephemeral port. This ensures that we cycle through the available port space in order for repeated connects to the same destination and significantly reduces the chance of picking a recently released port. PiperOrigin-RevId: 272058370
2019-09-27Implement SO_BINDTODEVICE sockoptgVisor bot
PiperOrigin-RevId: 271644926
2019-09-25Remove centralized registration of protocols.Kevin Krakauer
Also removes the need for protocol names. PiperOrigin-RevId: 271186030
2019-09-23netstack: convert more socket options to {Set,Get}SockOptIntAndrei Vagin
PiperOrigin-RevId: 270763208
2019-09-12Implement splice methods for pipes and sockets.Adin Scannell
This also allows the tee(2) implementation to be enabled, since dup can now be properly supported via WriteTo. Note that this change necessitated some minor restructoring with the fs.FileOperations splice methods. If the *fs.File is passed through directly, then only public API methods are accessible, which will deadlock immediately since the locking is already done by fs.Splice. Instead, we pass through an abstract io.Reader or io.Writer, which elide locks and use the underlying fs.FileOperations directly. PiperOrigin-RevId: 268805207
2019-09-12Remove go_test from go_stateify and go_marshalMichael Pratt
They are no-ops, so the standard rule works fine. PiperOrigin-RevId: 268776264
2019-09-09Fix ephemeral port leak.Ian Gudger
Fix a bug where udp.(*endpoint).Disconnect [accessible in gVisor via epsocket.(*SocketOperations).Connect with AF_UNSPEC] would leak a port reservation if the socket/endpoint had an ephemeral port assigned to it. glibc's getaddrinfo uses connect with AF_UNSPEC, causing each call of getaddrinfo to leak a port. Call getaddrinfo too many times and you run out of ports (shows up as connect returning EAGAIN and getaddrinfo returning EAI_NONAME "Name or service not known"). PiperOrigin-RevId: 268071160
2019-09-06Remove reundant global tcpip.LinkEndpointID.Ian Gudger
PiperOrigin-RevId: 267709597
2019-09-04Fix RST generation bugs.Bhasker Hariharan
There are a few cases addressed by this change - We no longer generate a RST in response to a RST packet. - When we receive a RST we cleanup and release all reservations immediately as the connection is now aborted. - An ACK received by a listening socket generates a RST when SYN cookies are not in-use. The only reason an ACK should land at the listening socket is if we are using SYN cookies otherwise the goroutine for the handshake in progress should have gotten the packet and it should never have arrived at the listening endpoint. - Also fixes the error returned when a connection times out due to a Keepalive timer expiration from ECONNRESET to a ETIMEDOUT. PiperOrigin-RevId: 267238427
2019-09-03Make UDP traceroute work.Bhasker Hariharan
Adds support to generate Port Unreachable messages for UDP datagrams received on a port for which there is no valid endpoint. Fixes #703 PiperOrigin-RevId: 267034418
2019-08-29Implement /proc/net/udp.Rahat Mahmood
PiperOrigin-RevId: 266229756
2019-08-26netstack/tcp: Add LastAck transition.Rahat Mahmood
Add missing state transition to LastAck, which should happen when the endpoint has already recieved a FIN from the remote side, and is sending its own FIN. PiperOrigin-RevId: 265568314
2019-08-21Support binding to multicast and broadcast addressesChris Kuiper
This fixes the issue of not being able to bind to either a multicast or broadcast address as well as to send and receive data from it. The way to solve this is to treat these addresses similar to the ANY address and register their transport endpoint ID with the global stack's demuxer rather than the NIC's. That way there is no need to require an endpoint with that multicast or broadcast address. The stack's demuxer is in fact the only correct one to use, because neither broadcast- nor multicast-bound sockets care which NIC a packet was received on (for multicast a join is still needed to receive packets on a NIC). I also took the liberty of refactoring udp_test.go to consolidate a lot of duplicate code and make it easier to create repetitive tests that test the same feature for a variety of packet and socket types. For this purpose I created a "flowType" that represents two things: 1) the type of packet being sent or received and 2) the type of socket used for the test. E.g., a "multicastV4in6" flow represents a V4-mapped multicast packet run through a V6-dual socket. This allows writing significantly simpler tests. A nice example is testTTL(). PiperOrigin-RevId: 264766909
2019-08-21Use tcpip.Subnet in tcpip.RouteTamir Duberstein
This is the first step in replacing some of the redundant types with the standard library equivalents. PiperOrigin-RevId: 264706552
2019-08-16netstack: disconnect an unix socket only if the address family is AF_UNSPECAndrei Vagin
Linux allows to call connect for ANY and the zero port. PiperOrigin-RevId: 263892534
2019-08-15Don't dereference errors passed to panic()Tamir Duberstein
These errors are always pointers; there's no sense in dereferencing them in the panic call. Changed one false positive for clarity. PiperOrigin-RevId: 263611579
2019-08-15netstack: move resumption logic into *_state.goTamir Duberstein
13a98df rearranged some of this code in a way that broke compilation of the netstack-only export at github.com/google/netstack because *_state.go files are not included in that export. This commit moves resumption logic back into *_state.go, fixing the compilation breakage. PiperOrigin-RevId: 263601629
2019-08-14Replace uinptr with int64 when returning lengthsTamir Duberstein
This is in accordance with newer parts of the standard library. PiperOrigin-RevId: 263449916
2019-08-14Improve SendMsg performance.Bhasker Hariharan
SendMsg before this change would copy all the data over into a new slice even if the underlying socket could only accept a small amount of data. This is really inefficient with non-blocking sockets and under high throughput where large writes could get ErrWouldBlock or if there was say a timeout associated with the sendmsg() syscall. With this change we delay copying bytes in till they are needed and only copy what can be potentially sent/held in the socket buffer. Reducing the need to repeatedly copy data over. Also a minor fix to change state FIN-WAIT-1 when shutdown(..., SHUT_WR) is called instead of when we transmit the actual FIN. Otherwise the socket could remain in CONNECTED state even though the user has called shutdown() on the socket. Updates #627 PiperOrigin-RevId: 263430505
2019-08-09Add congestion control states to sender.Bhasker Hariharan
This change just introduces different congestion control states and ensures the sender.state is updated to reflect the current state of the connection. It is not used for any decisions yet but this is required before algorithms like Eiffel/PRR can be implemented. Fixes #394 PiperOrigin-RevId: 262638292
2019-08-08netstack: Don't start endpoint goroutines too soon on restore.Rahat Mahmood
Endpoint protocol goroutines were previously started as part of loading the endpoint. This is potentially too soon, as resources used by these goroutine may not have been loaded. Protocol goroutines may perform meaningful work as soon as they're started (ex: incoming connect) which can cause them to indirectly access resources that haven't been loaded yet. This CL defers resuming all protocol goroutines until the end of restore. PiperOrigin-RevId: 262409429
2019-08-06Fix for a panic due to writing to a closed accept channel.Bhasker Hariharan
This can happen because endpoint.Close() closes the accept channel first and then drains/resets any accepted but not delivered connections. But there can be connections that are connected but not delivered to the channel as the channel was full. But closing the channel can cause these writes to fail with a write to a closed channel. The correct solution is to abort any connections in SYN-RCVD state and drain/abort all completed connections before closing the accept channel. PiperOrigin-RevId: 261951132
2019-08-02Plumbing for iptables sockopts.Kevin Krakauer
PiperOrigin-RevId: 261413396
2019-08-02Automated rollback of changelist 261191548Rahat Mahmood
PiperOrigin-RevId: 261373749
2019-08-01Implement getsockopt(TCP_INFO).Rahat Mahmood
Export some readily-available fields for TCP_INFO and stub out the rest. PiperOrigin-RevId: 261191548
2019-07-31Test connecting UDP sockets to the ANY addressTamir Duberstein
This doesn't currently pass on gVisor. While I'm here, fix a bug where connecting to the v6-mapped v4 address doesn't work in gVisor. PiperOrigin-RevId: 260923961
2019-07-24Add support for a subnet prefix length on interface network addressesChris Kuiper
This allows the user code to add a network address with a subnet prefix length. The prefix length value is stored in the network endpoint and provided back to the user in the ProtocolAddress type. PiperOrigin-RevId: 259807693
2019-07-23Deduplicate EndpointState.connected someTamir Duberstein
This fixes a bug introduced in cl/251934850 that caused connect-accept-close-connect races to result in the second connect call failiing when it should have succeeded. PiperOrigin-RevId: 259584525
2019-07-19Handle interfaceAddr and NIC options separately for IP_MULTICAST_IFChris Kuiper
This tweaks the handling code for IP_MULTICAST_IF to ignore the InterfaceAddr if a NICID is given. PiperOrigin-RevId: 258982541
2019-07-18net/tcp/setockopt: impelment setsockopt(fd, SOL_TCP, TCP_INQ)Andrei Vagin
PiperOrigin-RevId: 258859507
2019-07-16Internal change.gVisor bot
PiperOrigin-RevId: 258424489
2019-07-12Add IPPROTO_RAW, which allows raw sockets to write IP headers.Kevin Krakauer
iptables also relies on IPPROTO_RAW in a way. It opens such a socket to manipulate the kernel's tables, but it doesn't actually use any of the functionality. Blegh. PiperOrigin-RevId: 257903078
2019-07-12Stub out support for TCP_MAXSEG.Bhasker Hariharan
Adds support to set/get the TCP_MAXSEG value but does not really change the segment sizes emitted by netstack or alter the MSS advertised by the endpoint. This is currently being added only to unblock iperf3 on gVisor. Plumbing this correctly requires a bit more work which will come in separate CLs. PiperOrigin-RevId: 257859112
2019-07-03netstack/udp: connect with the AF_UNSPEC address family means disconnectAndrei Vagin
PiperOrigin-RevId: 256433283
2019-06-27Fix various spelling issues in the documentationMichael Pratt
Addresses obvious typos, in the documentation only. COPYBARA_INTEGRATE_REVIEW=https://github.com/google/gvisor/pull/443 from Pixep:fix/documentation-spelling 4d0688164eafaf0b3010e5f4824b35d1e7176d65 PiperOrigin-RevId: 255477779
2019-06-21Fix the logic for sending zero window updates.Bhasker Hariharan
Today we have the logic split in two places between endpoint Read() and the worker goroutine which actually sends a zero window. This change makes it so that when a zero window ACK is sent we set a flag in the endpoint which can be read by the endpoint to decide if it should notify the worker to send a nonZeroWindow update. The worker now does not do the check again but instead sends an ACK and flips the flag right away. Similarly today when SO_RECVBUF is set the SetSockOpt call has logic to decide if a zero window update is required. Rather than do that we move the logic to the worker goroutine and it can check the zeroWindow flag and send an update if required. PiperOrigin-RevId: 254505447
2019-06-13Add support for TCP receive buffer auto tuning.Bhasker Hariharan
The implementation is similar to linux where we track the number of bytes consumed by the application to grow the receive buffer of a given TCP endpoint. This ensures that the advertised window grows at a reasonable rate to accomodate for the sender's rate and prevents large amounts of data being held in stack buffers if the application is not actively reading or not reading fast enough. The original paper that was used to implement the linux receive buffer auto- tuning is available @ https://public.lanl.gov/radiant/pubs/drs/lacsi2001.pdf NOTE: Linux does not implement DRS as defined in that paper, it's just a good reference to understand the solution space. Updates #230 PiperOrigin-RevId: 253168283
2019-06-13Update canonical repository.Adin Scannell
This can be merged after: https://github.com/google/gvisor-website/pull/77 or https://github.com/google/gvisor-website/pull/78 PiperOrigin-RevId: 253132620
2019-06-12Minor BUILD file cleanup.Adin Scannell
PiperOrigin-RevId: 252918338
2019-06-12Add support for TCP_CONGESTION socket option.Bhasker Hariharan
This CL also cleans up the error returned for setting congestion control which was incorrectly returning EINVAL instead of ENOENT. PiperOrigin-RevId: 252889093
2019-06-10Fixes to listen backlog handling.Bhasker Hariharan
Changes netstack to confirm to current linux behaviour where if the backlog is full then we drop the SYN and do not send a SYN-ACK. Similarly we allow upto backlog connections to be in SYN-RCVD state as long as the backlog is not full. We also now drop a SYN if syn cookies are in use and the backlog for the listening endpoint is full. Added new tests to confirm the behaviour. Also reverted the change to increase the backlog in TcpPortReuseMultiThread syscall test. Fixes #236 PiperOrigin-RevId: 252500462
2019-06-06Track and export socket state.Rahat Mahmood
This is necessary for implementing network diagnostic interfaces like /proc/net/{tcp,udp,unix} and sock_diag(7). For pass-through endpoints such as hostinet, we obtain the socket state from the backend. For netstack, we add explicit tracking of TCP states. PiperOrigin-RevId: 251934850
2019-06-05netstack/tcp: fix calculating a number of outstanding packetsAndrei Vagin
In case of GSO, a segment can container more than one packet and we need to use the pCount() helper to get a number of packets. PiperOrigin-RevId: 251743020
2019-06-04Fix data race in synRcvdState.Bhasker Hariharan
When checking the length of the acceptedChan we should hold the endpoint mutex otherwise a syn received while the listening socket is being closed can result in a data race where the cleanupLocked routine sets acceptedChan to nil while a handshake goroutine in progress could try and check it at the same time. PiperOrigin-RevId: 251537697