Age | Commit message (Collapse) | Author |
|
Linux controls socket send/receive buffers using a few sysctl variables
- net.core.rmem_default
- net.core.rmem_max
- net.core.wmem_max
- net.core.wmem_default
- net.ipv4.tcp_rmem
- net.ipv4.tcp_wmem
The first 4 control the default socket buffer sizes for all sockets
raw/packet/tcp/udp and also the maximum permitted socket buffer that can be
specified in setsockopt(SOL_SOCKET, SO_(RCV|SND)BUF,...).
The last two control the TCP auto-tuning limits and override the default
specified in rmem_default/wmem_default as well as the max limits.
Netstack today only implements tcp_rmem/tcp_wmem and incorrectly uses it
to limit the maximum size in setsockopt() as well as uses it for raw/udp
sockets.
This changelist introduces the other 4 and updates the udp/raw sockets to use
the newly introduced variables. The values for min/max match the current
tcp_rmem/wmem values and the default value buffers for UDP/RAW sockets is
updated to match the linux value of 212KiB up from the really low current value
of 32 KiB.
Updates #3043
Fixes #3043
PiperOrigin-RevId: 318089805
|
|
For TCP sockets, SO_REUSEADDR relaxes the rules for binding addresses.
gVisor/netstack already supported a behavior similar to SO_REUSEADDR, but did
not allow disabling it. This change brings the SO_REUSEADDR behavior closer to
the behavior implemented by Linux and adds a new SO_REUSEADDR disabled
behavior. Like Linux, SO_REUSEADDR is now disabled by default.
PiperOrigin-RevId: 317984380
|
|
... and unify logic for detached netsted endpoints.
sniffer.go caused crashes if a packet delivery is attempted when the dispatcher
is nil.
Extracted the endpoint nesting logic into a common composable type so it can be
used by the Fuchsia Netstack (the pattern is widespread there).
PiperOrigin-RevId: 317682842
|
|
Test:
- TestIncrementChecksumErrors
Fixes #2943
PiperOrigin-RevId: 317348158
|
|
Users that never set iptables rules shouldn't incur the iptables performance
cost. Suggested by Ian (@iangudger).
PiperOrigin-RevId: 317232921
|
|
Metadata was useful for debugging and safety, but enough tests exist that we
should see failures when (de)serialization is broken. It made stack
initialization more cumbersome and it's also getting in the way of ip6tables.
PiperOrigin-RevId: 317210653
|
|
Updates #173,#6
Fixes #2888
PiperOrigin-RevId: 317087652
|
|
When a tcp.timer or tcpip.Route is no longer used, clean up its
resources so that unused memory may be released.
PiperOrigin-RevId: 317046582
|
|
... to help reduce flakes.
When waiting for an event to occur, use a timeout of 10s. When waiting
for an event to not occur, use a timeout of 1s.
Test: Ran test locally w/ run count of 1000 with and without gotsan.
PiperOrigin-RevId: 316998128
|
|
Ensure that CurrentConnected stat is updated on any errors and cleanups
during connected state processing.
Fixes #2968
PiperOrigin-RevId: 316919426
|
|
PiperOrigin-RevId: 316767969
|
|
In passive open cases, we transition to Established state after
initializing endpoint's sender and receiver. With this we lose out
on any updates coming from the ACK that completes the handshake.
This change ensures that we uniformly transition to Established in all
cases and does minor cleanups.
Fixes #2938
PiperOrigin-RevId: 316567014
|
|
I am not really sure what the point of this is, but someone filed a bug about
it, so I assume something relies on it.
PiperOrigin-RevId: 316225127
|
|
Tentative addresses should not be used when finding a route. This change
fixes a bug where a tentative address may have been used.
Test: stack_test.TestDADResolve
PiperOrigin-RevId: 315997624
|
|
On UDP sockets, SO_REUSEADDR allows multiple sockets to bind to the same
address, but only delivers packets to the most recently bound socket. This
differs from the behavior of SO_REUSEADDR on TCP sockets. SO_REUSEADDR for TCP
sockets will likely need an almost completely independent implementation.
SO_REUSEADDR has some odd interactions with the similar SO_REUSEPORT. These
interactions are tested fairly extensively and all but one particularly odd
one (that honestly seems like a bug) behave the same on gVisor and Linux.
PiperOrigin-RevId: 315844832
|
|
Minimum header sizes are already checked in each `case` arm below. Worse, the
ICMP entries in transportProtocolMinSizes are incorrect, and produce false "raw
packet" logs.
PiperOrigin-RevId: 315730073
|
|
PiperOrigin-RevId: 315711208
|
|
After this change e.mu is only promoted to exclusively locked during
route.Resolve. It downgrades back to read-lock afterwards.
This prevents the second RLock() call gets stuck later in the stack.
https://syzkaller.appspot.com/bug?id=065b893bd8d1d04a4e0a1d53c578537cde1efe99
Syzkaller logs does not contain interesting stack traces.
The following stack trace is obtained by running repro locally.
goroutine 53 [semacquire, 3 minutes]:
runtime.gopark(0xfd4278, 0x1896320, 0xc000301912, 0x4)
GOROOT/src/runtime/proc.go:304 +0xe0 fp=0xc0000e25f8 sp=0xc0000e25d8 pc=0x437170
runtime.goparkunlock(...)
GOROOT/src/runtime/proc.go:310
runtime.semacquire1(0xc0001220b0, 0xc00000a300, 0x1, 0x0)
GOROOT/src/runtime/sema.go:144 +0x1c0 fp=0xc0000e2660 sp=0xc0000e25f8 pc=0x4484e0
sync.runtime_Semacquire(0xc0001220b0)
GOROOT/src/runtime/sema.go:56 +0x42 fp=0xc0000e2690 sp=0xc0000e2660 pc=0x448132
gvisor.dev/gvisor/pkg/sync.(*RWMutex).RLock(...)
pkg/sync/rwmutex_unsafe.go:76
gvisor.dev/gvisor/pkg/tcpip/transport/udp.(*endpoint).HandleControlPacket(0xc000122000, 0x7ee5, 0xc00053c16c, 0x4, 0x5e21, 0xc00053c224, 0x4, 0x1, 0x0, 0xc00007ed00)
pkg/tcpip/transport/udp/endpoint.go:1345 +0x169 fp=0xc0000e26d8 sp=0xc0000e2690 pc=0x9843f9
......
gvisor.dev/gvisor/pkg/tcpip/transport/udp.(*protocol).HandleUnknownDestinationPacket(0x18bb5a0, 0xc000556540, 0x5e21, 0xc00053c16c, 0x4, 0x7ee5, 0xc00053c1ec, 0x4, 0xc00007e680, 0x4)
pkg/tcpip/transport/udp/protocol.go:143 +0xb9a fp=0xc0000e8260 sp=0xc0000e7510 pc=0x9859ba
......
gvisor.dev/gvisor/pkg/tcpip/transport/udp.sendUDP(0xc0001220d0, 0xc00053ece0, 0x1, 0x1, 0x883, 0x1405e217ee5, 0x11100a0, 0xc000592000, 0xf88780)
pkg/tcpip/transport/udp/endpoint.go:924 +0x3b0 fp=0xc0000ed390 sp=0xc0000ec750 pc=0x981af0
gvisor.dev/gvisor/pkg/tcpip/transport/udp.(*endpoint).write(0xc000122000, 0x11104e0, 0xc00020a460, 0x0, 0x0, 0x0, 0x0, 0x0)
pkg/tcpip/transport/udp/endpoint.go:510 +0x4ad fp=0xc0000ed658 sp=0xc0000ed390 pc=0x97f2dd
PiperOrigin-RevId: 315590041
|
|
NDP packets are sent periodically from NDP timers. These timers do not
hold the NIC lock when sending packets as the packet write operation
may take some time. While the lock is not held, the NIC may be removed
by some other goroutine. This change handles that scenario gracefully.
Test: stack_test.TestRemoveNICWhileHandlingRSTimer
PiperOrigin-RevId: 315524143
|
|
Netstack has traditionally parsed headers on-demand as a packet moves up the
stack. This is conceptually simple and convenient, but incompatible with
iptables, where headers can be inspected and mangled before even a routing
decision is made.
This changes header parsing to happen early in the incoming packet path, as soon
as the NIC gets the packet from a link endpoint. Even if an invalid packet is
found (e.g. a TCP header of insufficient length), the packet is passed up the
stack for proper stats bookkeeping.
PiperOrigin-RevId: 315179302
|
|
PiperOrigin-RevId: 315041419
|
|
Loopback traffic is not affected by rules in the PREROUTING chain.
This change is also necessary for istio's envoy to talk to other
components in the same pod.
|
|
PiperOrigin-RevId: 315018295
|
|
PiperOrigin-RevId: 314996457
|
|
For TCP sockets gVisor incorrectly returns EAGAIN when no ephemeral ports are
available to bind during a connect. Linux returns EADDRNOTAVAIL. This change
fixes gVisor to return the correct code and adds a test for the same.
This change also fixes a minor bug for ping sockets where connect() would fail
with EINVAL unless the socket was bound first.
Also added tests for testing UDP Port exhaustion and Ping socket port
exhaustion.
PiperOrigin-RevId: 314988525
|
|
IPTables.connections contains a sync.RWMutex. Copying it will trigger copylocks
analysis. Tested by manually enabling nogo tests.
sync.RWMutex is added to IPTables for the additional race condition discovered.
PiperOrigin-RevId: 314817019
|
|
- Always split segments larger than MSS.
Currently, we base the segment split decision as a function of the
send congestion window and MSS, which could be greater than the MSS
advertised by remote.
- While splitting segments, ensure the PSH flag is reset when there
are segments that are queued to be sent.
- With TCP_CORK, hold up segments up until MSS. Fix a bug in computing
available send space before attempting to coalesce segments.
Fixes #2832
PiperOrigin-RevId: 314802928
|
|
Historically we've been passing PacketBuffer by shallow copying through out
the stack. Right now, this is only correct as the caller would not use
PacketBuffer after passing into the next layer in netstack.
With new buffer management effort in gVisor/netstack, PacketBuffer will
own a Buffer (to be added). Internally, both PacketBuffer and Buffer may
have pointers and shallow copying shouldn't be used.
Updates #2404.
PiperOrigin-RevId: 314610879
|
|
If the entire segment cannot be accommodated in the receiver advertised
window and if there are still unacknowledged pending segments, skip
splitting the segment. The segment transmit would get retried by the
retransmit handler.
PiperOrigin-RevId: 314538523
|
|
Fixes #1666
PiperOrigin-RevId: 314148384
|
|
None of the dependencies have changed in 1.15. It may be possible to simplify
some of the wrappers in rawfile following 1.13, but that can come in a later
change.
PiperOrigin-RevId: 313863264
|
|
PiperOrigin-RevId: 313842690
|
|
Updates #2404.
PiperOrigin-RevId: 313834784
|
|
RST handling is broken when the TCP state transitions
from SYN-SENT to SYN-RCVD in case of simultaneous open.
An incoming RST should trigger cleanup of the endpoint.
RFC793, section 3.9, page 70.
Fixes #2814
PiperOrigin-RevId: 313828777
|
|
|
|
The specified LinkEndpoint is not being used in a significant way.
No behavior change, existing tests pass.
This change is a breaking change.
PiperOrigin-RevId: 313496602
|
|
PiperOrigin-RevId: 313414690
|
|
If there is a Timestamps option in the arriving segment and SEG.TSval
< TS.Recent and if TS.Recent is valid, then treat the arriving segment
as not acceptable: Send an acknowledgement in reply as specified in
RFC-793 page 69 and drop the segment.
https://tools.ietf.org/html/rfc1323#page-19
PiperOrigin-RevId: 312590678
|
|
PiperOrigin-RevId: 312559963
|
|
* Aggregate architecture Overview in "What is gVisor?" as it makes more sense
in one place.
* Drop "user-space kernel" and use "application kernel". The term "user-space
kernel" is confusing when some platform implementation do not run in
user-space (instead running in guest ring zero).
* Clear up the relationship between the Platform page in the user guide and the
Platform page in the architecture guide, and ensure they are cross-linked.
* Restore the call-to-action quick start link in the main page, and drop the
GitHub link (which also appears in the top-right).
* Improve image formatting by centering all doc and blog images, and move the
image captions to the alt text.
PiperOrigin-RevId: 311845158
|
|
As per RFC 1122 and Linux retransmit timeout handling:
- The segment retransmit timeout needs to exponentially increase and
cap at a predefined value.
- TCP connection needs to timeout after a predefined number of
segment retransmissions.
- TCP connection should not timeout when the retranmission timeout
exceeds MaxRTO, predefined upper bound.
Fixes #2673
PiperOrigin-RevId: 311463961
|
|
This change adds support for TCP_SYNCNT and TCP_WINDOW_CLAMP options
in GetSockOpt/SetSockOpt. This change does not really change any
behaviour in Netstack and only stores/returns the stored value.
Actual honoring of these options will be added as required.
Fixes #2626, #2625
PiperOrigin-RevId: 311453777
|
|
PiperOrigin-RevId: 310963404
|
|
view.ToVectorisedView() now just returns an empty vectorised
view if the view is of zero length. Earlier it would return
a VectorisedView of zero length but with 1 empty view. This
has been a source of bugs as lower layers don't expect
zero length views in VectorisedViews.
VectorisedView.AppendView() now is a no-op if the view being
appended is of zero length.
Fixes #2658
PiperOrigin-RevId: 310942269
|
|
Enables commands with -o (--out-interface) for iptables rules.
$ iptables -A OUTPUT -o eth0 -j ACCEPT
PiperOrigin-RevId: 310642286
|
|
This fixed the corresponding packetimpact test.
PiperOrigin-RevId: 310593470
|
|
Only the last test was running before since the goroutines won't be executed
until after this loop. I added t.Log(test.name) and this is was the result:
TestListenNoAcceptNonUnicastV4/SourceUnspecified: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/DestUnspecified: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/DestOtherMulticast: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/SourceBroadcast: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/DestOurMulticast: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/DestBroadcast: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/SourceOtherMulticast: DestOtherMulticast
TestListenNoAcceptNonUnicastV4/SourceOurMulticast: DestOtherMulticast
https://github.com/golang/go/wiki/TableDrivenTests#parallel-testing
PiperOrigin-RevId: 310440629
|
|
PiperOrigin-RevId: 310417191
|
|
Every call to sender.NextSeg does not need to iterate from the
front of the writeList as in a given recovery episode we can cache
the last nextSeg returned. There cannot be a lower sequenced segment
that matches the next call to NextSeg as otherwise we would have
returned that instead in the previous call.
This fixes the issue of excessive CPU usage w/ large send buffers
where we spend a lot of time iterating from the front of the list on
every NextSeg invocation.
Further the following other bugs were also fixed:
* Iteration of segments never sent in NextSeg() when looking for segments for
retransmission that match step1/3/4 of the NextSeg algorithm
* Correctly setting rescueRxt only if the rescue segment was actually sent.
* Correctly initializing rescueRxt/highRxt when entering SACK recovery.
* Correctly re-arming the timer only on retransmissions when SACK is in use
and not for every segment being sent as it was being done before.
* Copy over xmitTime and xmitCount on segment clone.
* Move writeNext along when skipping over SACKED segments. This is required
to prevent spurious retransmissions where we end up retransmitting data
that was never lost.
PiperOrigin-RevId: 310387671
|
|
PiperOrigin-RevId: 310380911
|