Age | Commit message (Collapse) | Author |
|
|
|
The existing gvisor.dev/faq link returns 404 because the full URL has
mistakenly been capitalized.
PiperOrigin-RevId: 319233173
|
|
|
|
- Support FIOASYNC, FIO{SET,GET}OWN, SIOC{G,S}PGRP (refactor getting/setting
owner in the process).
- Unset signal recipient when setting owner with pid == 0 and
valid owner type.
Updates #2923.
PiperOrigin-RevId: 319231420
|
|
|
|
Fixes #3113
PiperOrigin-RevId: 319216671
|
|
|
|
a) When GSO is in use we should not cap the segment to maxPayloadSize in
sender.maybeSendSegment as the GSO logic will cap the segment to the correct
size. Without this the host GSO is not used as we end up breaking up large
segments into small MSS sized segments before writing the packets to the
host.
b) The check to not split a segment due to it not fitting in the receiver window
when there are pending segments is incorrect as segments in writeList can be
really large as we just take the write call's buffer size and create a single
large segment. So a write of say 128KB will just be 1 segment in the
writeList.
The linux code checks if 1 MSS sized segments fits in the receiver's window
and if not then does not split the current segment. gVisor's check was
incorrect that it was checking if the whole segment which could be >>> 1 MSS
would fit in the receiver's window. This was causing us to prematurely stop
sending and falling back to retransmit timer/probe from the other end to send
data.
This was seen when running HTTPD benchmarks where @ HEAD when sending large
files the benchmark was taking forever to run.
The tcp_splitseg_mss_test.go is being deleted as the test as written doesn't
test what is intended correctly. This is because GSO is enabled by default and
the reason the MSS+1 sized segment is sent is because GSO is in use. A proper
test will require disabling GSO on linux and netstack which is going to take a
bit of work in packetimpact to do it correctly.
Separately a new test probably should be written that verifies that a segment >
availableWindow is not split if the availableWindow is < 1 MSS.
Fixes #3107
PiperOrigin-RevId: 319172089
|
|
|
|
We were truncating buf using a index relative to the middle of the slice (i.e.
where envv begins), but we need to calculate the index relative to the entire
slice.
Updates #2923.
PiperOrigin-RevId: 319154950
|
|
|
|
Updates #2923.
PiperOrigin-RevId: 319153792
|
|
|
|
PiperOrigin-RevId: 319143410
|
|
|
|
-Waddress-of-packed-member warns on inet_aton() being used with a packed struct
member. This was added in cl/291990716.
PiperOrigin-RevId: 319111253
|
|
|
|
...by calling (*tcp.endpoint).EndpointState only once when possible.
Avoid wrapping (*sleep.Waker).Assert in a useless func while I'm here.
PiperOrigin-RevId: 319074149
|
|
|
|
This includes the provisional style guide in the website and fixes the broken
link from CONTRIBUTING.md. The style guide will be located under the "Community"
category as it's related to contributing to the project.
Also, add missing includes that were causing some presubmits to fail.
PiperOrigin-RevId: 319061410
|
|
|
|
Bring udp_socket_test into complianc by:
- Eliminating IsRunningOnGvisor() invocations.
- Wrapping sockets in RAII FileDescriptor objects.
- Creating a Bind() method so that the first bind happens on port 0.
PiperOrigin-RevId: 318909396
|
|
|
|
Also make some fixes to vfs1's F_SETOWN. The fcntl test now entirely passes
on vfs2.
Fixes #2920.
PiperOrigin-RevId: 318669529
|
|
|
|
Updates #2923.
PiperOrigin-RevId: 318648128
|
|
|
|
Updates #1479.
PiperOrigin-RevId: 318631247
|
|
|
|
PiperOrigin-RevId: 318591900
|
|
|
|
PiperOrigin-RevId: 318585377
|
|
|
|
IPv6 raw sockets never include the IPv6 header.
PiperOrigin-RevId: 318582989
|
|
|
|
SO_NO_CHECK is used to skip the UDP checksum generation on a TX socket
(UDP checksum is optional on IPv4).
Test:
- TestNoChecksum
- SoNoCheckOffByDefault (UdpSocketTest)
- SoNoCheck (UdpSocketTest)
Fixes #3055
PiperOrigin-RevId: 318575215
|
|
|
|
The Option Type identifiers are internally encoded such that their
highest-order two bits specify the action that must be taken if the
processing IPv6 node does not recognize the Option Type:
00 - skip over this option and continue processing the header.
01 - discard the packet.
10 - discard the packet and, regardless of whether or not the
packet's Destination Address was a multicast address, send an
ICMP Parameter Problem, Code 2, message to the packet's
Source Address, pointing to the unrecognized Option Type.
11 - discard the packet and, only if the packet's Destination
Address was not a multicast address, send an ICMP Parameter
Problem, Code 2, message to the packet's Source Address,
pointing to the unrecognized Option Type.
PiperOrigin-RevId: 318566613
|
|
|
|
PiperOrigin-RevId: 318563543
|
|
|
|
- IPv6 HopByHop Options Extension Header
- IPv6 Destination Options Extension Header
PiperOrigin-RevId: 318551425
|
|
|
|
Also, while we're here, make sure that gofer inotify events are generated when
files are created in remote revalidating mode.
Updates #1479.
PiperOrigin-RevId: 318536354
|
|
|
|
PiperOrigin-RevId: 318511615
|
|
|
|
We need docker IPv6 for ip6tables tests. Docker has spotty IPv6 support, so just
enabling IPv6 in daemon.json breaks the Ruby image test (AFAICT it breaks
anything that tries to use IPv6 to reach the internet). An ip6tables NAT rule is
added to handle this.
We could make these changes as part of scripts/, but these would overwrite
global values and possibly break users' systems.
PiperOrigin-RevId: 318508209
|
|
|
|
- Split connTrackForPacket into 2 functions instead of switching on flag
- Replace hash with struct keys.
- Remove prefixes where possible
- Remove unused connStatus, timeout
- Flatten ConnTrack struct a bit - some intermediate structs had no meaning
outside of the context of their parent.
- Protect conn.tcb with a mutex
- Remove redundant error checking (e.g. when is pkt.NetworkHeader valid)
- Clarify that HandlePacket and CreateConnFor are the expected entrypoints for
ConnTrack
PiperOrigin-RevId: 318407168
|