Age | Commit message (Collapse) | Author |
|
|
|
PiperOrigin-RevId: 408426639
|
|
|
|
In a subsequent change, the Sleeper API will be plumbed through and used for
arbitrary task wakeups. This requires a non-static association of Wakers and
Sleepers, which means that a fixed ID no longer works. This is a relatively
simple change that removes the ID from the Waker association, and simply uses
the Waker pointer itself.
That change also makes minor improvements to the tests to ensure that the
benchmarks are more representative by removing goroutine start from the hot
path (and uses Wakers for required synchronization), adds assertion checks to
AddWaker, and clears relevant fields during Done (to allow assertions to pass).
PiperOrigin-RevId: 407719630
|
|
|
|
Connection tracking is agnostic to whether the packet is inbound or outbound. It
cares who initiated the connection. The naming can get confusing as conntrack
can track connections originating from any host.
Part of resolving #6736.
PiperOrigin-RevId: 405997540
|
|
|
|
Fixes #6590
PiperOrigin-RevId: 404007524
|
|
|
|
These can be used by applications to manipulate iptables rules without enabling
arbitrary reads from and writes to the underlying packet socket.
PiperOrigin-RevId: 402924733
|
|
|
|
Fixes #6725
PiperOrigin-RevId: 402683244
|
|
|
|
Updates #1584, #3556.
PiperOrigin-RevId: 402354066
|
|
|
|
- Implements RFC 3522 (Eifel detection algorithm) to detect if the connection
entered loss recovery unnecessarily.
- Added a new metric to count the total number of spurious loss recoveries.
- Added tests to verify the new metric.
PiperOrigin-RevId: 401637359
|
|
TestRACKWithWindowFull was sending ACK for the last packet to avoid TLP. But,
sometimes the ACK is delayed and the sender sends the re-transmitted packet
before receiving ACK.
The test is now modified to expect the re-transmitted packet always and then
send a DSACK to avoid entering recovery.
Before: http://sponge2/6473db18-137a-4afb-9d60-c3eafd236ea9
After: http://sponge2/6a0f744c-7ea3-40fa-8f76-68503bf142ca
PiperOrigin-RevId: 401606848
|
|
|
|
Rather than boiling down to an integer eagerly, do it as late as possible.
PiperOrigin-RevId: 401599308
|
|
|
|
Before checking if there is space in the accept queue, the listener
should verify that the cookie is valid. If it is not, instead of
silently dropping the packet, reply with an RST.
Fixes #6683
PiperOrigin-RevId: 400807346
|
|
|
|
This obsoletes the need for the pendingMu and pending, since they are redundant
with acceptMu and pendingAccepted.
Fixes #6671.
PiperOrigin-RevId: 400162391
|
|
|
|
PiperOrigin-RevId: 399765414
|
|
|
|
Rename cap -> capacity to avoid collision with the builtin.
PiperOrigin-RevId: 399753630
|
|
|
|
This is redundant with listenContext.pendingEndpoints
PiperOrigin-RevId: 399722472
|
|
|
|
This function has only one caller.
Remove segment reference count manipulation since it is only used
synchronously.
PiperOrigin-RevId: 399525343
|
|
|
|
PiperOrigin-RevId: 399276940
|
|
|
|
There's no need for synthetic keys here.
PiperOrigin-RevId: 399263134
|
|
|
|
PiperOrigin-RevId: 398559780
|
|
|
|
An ICMP endpoint's write path can use the datagram-based endpoint.
Updates #6565.
Test: Datagram-based generic socket + ICMP/ping syscall tests.
PiperOrigin-RevId: 398539844
|
|
|
|
This circular reference is misleading at best, and the various code and
commentary that claim `listenEP` can be nil are impossible by
definition.
Add checklocks annotations to enforce preconditions.
PiperOrigin-RevId: 398517574
|
|
|
|
This will enable NAT to be performed on UDP packets that are sent
in response to packets sent by the stack.
This will also enable ICMP errors to be properly NAT-ed in response
to UDP packets (#5916).
Updates #5915.
PiperOrigin-RevId: 398373251
|
|
This prevents go module errors of the form
found packages tcp (accept.go) and rcv (rcv_test.go) in ...
PiperOrigin-RevId: 398370042
|
|
|
|
Fixes #6495
PiperOrigin-RevId: 398121921
|
|
|
|
Before this change, when a new connection was created after receiving
an ACK that matched a SYN-cookie, it was always delivered asynchronously
to the accept queue. There was a chance that the listening endpoint
would process a SYN from another client before the delivery happened,
and the listening endpoint would not know yet that the queue was about
to be full, once the delivery happened.
Now, when an ACK matching a SYN-cookie is received, the new endpoint is
created and moved to the accept queue synchronously, while holding the
accept lock.
Fixes #6545
PiperOrigin-RevId: 398107254
|
|
|
|
Updates #6621
PiperOrigin-RevId: 397898852
|