Enable a `NetworkBehaviour` or a user via `Swarm::dial` to override the
dial concurrency factor per dial. This is especially relevant in the
case of libp2p-autonat where one wants to probe addresses in sequence to
reduce the amount of work a remote peer can force onto the local node.
To enable the above, this commit also:
- Introduces `libp2p_core::DialOpts` mirroring `libp2p_swarm::DialOpts`.
Passed as an argument to `Network::dial`.
- Removes `Peer::dial` in favor of `Network::dial`.
- Simplifies `Swarm::dial_with_handler`.
The introduction of `libp2p_core::DialOpts` will be useful beyond this
feature, e.g. for https://github.com/libp2p/rust-libp2p/pull/2363.
In the long run I would like to move and merge `libp2p_core::Network`
and `libp2p_core::Pool` into `libp2p_swarm::Swarm` thus deduplicating
`libp2p_core::DialOpts` and `libp2p_swarm::DialOpts`.
Fixes#2385.
Concurrently dial address candidates within a single dial attempt.
Main motivation for this feature is to increase success rate on hole punching
(see https://github.com/libp2p/rust-libp2p/issues/1896#issuecomment-885894496
for details). Though, as a nice side effect, as one would expect, it does
improve connection establishment time.
Cleanups and fixes done along the way:
- Merge `pool.rs` and `manager.rs`.
- Instead of manually implementing state machines in `task.rs` use
`async/await`.
- Fix bug where `NetworkBehaviour::inject_connection_closed` is called without a
previous `NetworkBehaviour::inject_connection_established` (see
https://github.com/libp2p/rust-libp2p/issues/2242).
- Return handler to behaviour on incoming connection limit error. Missed in
https://github.com/libp2p/rust-libp2p/issues/2242.
