In accordance with RFC 793, if the receiver is in the SYN-SENT state
it should respond to a RST by aborting the connection and immediately
move to the CLOSED state.
Previously the system would ACK all RST/ACKs, and the remote peer would
just respond with more RST packets.
Instead of initializing network adapters in init.cpp, let's move that
logic into a separate class to handle this.
Also, it seems like a good idea to shift responsiblity on enumeration
of network adapters after the boot process, so this singleton will take
care of finding the appropriate network adapter when asked to with an
IPv4 address or interface name.
With this change being merged, we simplify the creation logic of
NetworkAdapter derived classes, so we enumerate the PCI bus only once,
searching for driver candidates when doing so, and we let each driver
to test if it is resposible for the specified PCI device.
When receiving a SYN packet for a connection that's in the "SYN
received" state we should ignore the duplicate SYN packet instead of
closing the connection. This can happen when we didn't accept the
connection in time and our peer has sent us another SYN packet because
it thought that the initial SYN packet was lost.
Previously we'd allocate buffers when sending packets. This patch
avoids these allocations by using the NetworkAdapter's packet queue.
At the same time this also avoids copying partially constructed
packets in order to prepend Ethernet and/or IPv4 headers. It also
properly truncates UDP and raw IP packets.
Occasionally we'll see messages in the serial console like:
handle_tcp: unexpected flags in FinWait1 state
In these cases it would be nice to know what flags we are receiving that
we aren't expecting.
Previously we didn't retransmit lost TCP packets which would cause
connections to hang if packets were lost. Also we now time out
TCP connections after a number of retransmission attempts.
This wakes up NetworkTask every 500 milliseconds so that it can send
pending delayed TCP ACKs and isn't forced to send all of them early
when it goes to sleep like it did before.
When establishing the connection we should send ACKs right away so
as to not delay the connection process. This didn't previously
matter because we'd flush all delayed ACKs when NetworkTask waits
for incoming packets.
When we receive a TCP packet with a sequence number that is not what
we expected we have lost one or more packets. We can signal this to
the sender by sending a TCP ACK with the previous ack number so that
they can resend the missing TCP fragments.
Previously we'd process TCP packets in whatever order we received
them in. In the case where packets arrived out of order we'd end
up passing garbage to the userspace process.
This was most evident for TLS connections:
courage:~ $ git clone https://github.com/SerenityOS/serenity
Cloning into 'serenity'...
remote: Enumerating objects: 178826, done.
remote: Counting objects: 100% (1880/1880), done.
remote: Compressing objects: 100% (907/907), done.
error: RPC failed; curl 56 OpenSSL SSL_read: error:1408F119:SSL
routines:SSL3_GET_RECORD:decryption failed or bad record mac, errno 0
error: 1918 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output
An IP socket can now join a multicast group by using the
IP_ADD_MEMBERSHIP sockopt, which will cause it to start receiving
packets sent to the multicast address, even though this address does
not belong to this host.
SPDX License Identifiers are a more compact / standardized
way of representing file license information.
See: https://spdx.dev/resources/use/#identifiers
This was done with the `ambr` search and replace tool.
ambr --no-parent-ignore --key-from-file --rep-from-file key.txt rep.txt *
(...and ASSERT_NOT_REACHED => VERIFY_NOT_REACHED)
Since all of these checks are done in release builds as well,
let's rename them to VERIFY to prevent confusion, as everyone is
used to assertions being compiled out in release.
We can introduce a new ASSERT macro that is specifically for debug
checks, but I'm doing this wholesale conversion first since we've
accumulated thousands of these already, and it's not immediately
obvious which ones are suitable for ASSERT.
In preparation for marking BlockingResult [[nodiscard]], there are a few
places that perform infinite waits, which we never observe the result of
the wait. Instead of suppressing them, add an alternate function which
returns void when performing and infinite wait.
* We don't have to lock the "all IPv4 sockets" in exclusive mode, shared mode is
enough for just reading the list (as opposed to modifying it).
* We don't have to lock socket's own lock at all, the IPv4Socket::did_receive()
implementation takes care of this.
* Most importantly, we don't have to hold the "all IPv4 sockets" across the
IPv4Socket::did_receive() call(s). We can copy the current ICMP socket list
while holding the lock, then release the lock, and then call
IPv4Socket::did_receive() on all the ICMP sockets in our list.
These changes fix a deadlock triggered by receiving ICMP messages when using tap
networking setup (as opposed to QEMU's default user/SLIRP networking) on the host.
Problem:
- Many constructors are defined as `{}` rather than using the ` =
default` compiler-provided constructor.
- Some types provide an implicit conversion operator from `nullptr_t`
instead of requiring the caller to default construct. This violates
the C++ Core Guidelines suggestion to declare single-argument
constructors explicit
(https://isocpp.github.io/CppCoreGuidelines/CppCoreGuidelines#c46-by-default-declare-single-argument-constructors-explicit).
Solution:
- Change default constructors to use the compiler-provided default
constructor.
- Remove implicit conversion operators from `nullptr_t` and change
usage to enforce type consistency without conversion.
Problem:
- `(void)` simply casts the expression to void. This is understood to
indicate that it is ignored, but this is really a compiler trick to
get the compiler to not generate a warning.
Solution:
- Use the `[[maybe_unused]]` attribute to indicate the value is unused.
Note:
- Functions taking a `(void)` argument list have also been changed to
`()` because this is not needed and shows up in the same grep
command.
Fix some problems with join blocks where the joining thread block
condition was added twice, which lead to a crash when trying to
unblock that condition a second time.
Deferred block condition evaluation by File objects were also not
properly keeping the File object alive, which lead to some random
crashes and corruption problems.
Other problems were caused by the fact that the Queued state didn't
handle signals/interruptions consistently. To solve these issues we
remove this state entirely, along with Thread::wait_on and change
the WaitQueue into a BlockCondition instead.
Also, deliver signals even if there isn't going to be a context switch
to another thread.
Fixes#4336 and #4330
This makes the Scheduler a lot leaner by not having to evaluate
block conditions every time it is invoked. Instead evaluate them as
the states change, and unblock threads at that point.
This also implements some more waitid/waitpid/wait features and
behavior. For example, WUNTRACED and WNOWAIT are now supported. And
wait will now not return EINTR when SIGCHLD is delivered at the
same time.
This adds the ability to pass a pointer to kernel thread/process.
Also add the ability to use a closure as thread function, which
allows passing information to a kernel thread more easily.
This fixes an issue where making a TCP connection to localhost didn't
work correctly since the loopback interface is currently synchronous.
(Sending something to localhost would enqueue a packet on the same
interface and then immediately wake the network task to process that
packet.)
This was preventing the TCP handshake from working correctly with
localhost since we'd send out the SYN packet before moving to the
SynSent state. The lock is now held long enough for this operation
to be atomic.
Similar to Process, we need to make Thread refcounted. This will solve
problems that will appear once we schedule threads on more than one
processor. This allows us to hold onto threads without necessarily
holding the scheduler lock for the entire duration.
Since the receiving socket isn't yet known at packet receive time,
keep timestamps for all packets.
This is useful for keeping statistics about in-kernel queue latencies
in the future, and it can be used to implement SO_TIMESTAMP.
Since the CPU already does almost all necessary validation steps
for us, we don't really need to attempt to do this. Doing it
ourselves doesn't really work very reliably, because we'd have to
account for other processors modifying virtual memory, and we'd
have to account for e.g. pages not being able to be allocated
due to insufficient resources.
So change the copy_to/from_user (and associated helper functions)
to use the new safe_memcpy, which will return whether it succeeded
or not. The only manual validation step needed (which the CPU
can't perform for us) is making sure the pointers provided by user
mode aren't pointing to kernel mappings.
To make it easier to read/write from/to either kernel or user mode
data add the UserOrKernelBuffer helper class, which will internally
either use copy_from/to_user or directly memcpy, or pass the data
through directly using a temporary buffer on the stack.
Last but not least we need to keep syscall params trivial as we
need to copy them from/to user mode using copy_from/to_user.
The SI prefixes "k", "M", "G" mean "10^3", "10^6", "10^9".
The IEC prefixes "Ki", "Mi", "Gi" mean "2^10", "2^20", "2^30".
Let's use the correct name, at least in code.
Only changes the name of the constants, no other behavior change.
I originally defined the bytes() method for the String class, because it
made it obvious that it's a span of bytes instead of span of characters.
This commit makes this more consistent by defining a bytes() method when
the type of the span is known to be u8.
Additionaly, the cast operator to Bytes is overloaded for ByteBuffer and
such.
The Lock class still permits no reason, but for everything else
require a reason to be passed to Thread::wait_on. This makes it
easier to diagnose why a Thread is in Queued state.
This patch relaxes how we think about UDP packets being "for us" a bit;
the proper way to handle this would be to also check if the matched
socket has SO_BROADCAST set, but we don't have that :)
Also, duplicate data in dbg() and klog() calls were removed.
In addition, leakage of virtual address to kernel log is prevented.
This is done by replacing kprintf() calls to dbg() calls with the
leaked data instead.
Also, other kprintf() calls were replaced with klog().
We can now participate in the TCP connection closing handshake. :^)
This implementation is definitely not complete and needs to handle a
bunch of other cases. But it's a huge improvement over not being able
to close connections at all.
Note that we hold on to pending-close sockets indefinitely, until they
are moved into the Closed state. This should also have a timeout but
that's still a FIXME. :^)
Fixes#428.
As suggested by Joshua, this commit adds the 2-clause BSD license as a
comment block to the top of every source file.
For the first pass, I've just added myself for simplicity. I encourage
everyone to add themselves as copyright holders of any file they've
added or modified in some significant way. If I've added myself in
error somewhere, feel free to replace it with the appropriate copyright
holder instead.
Going forward, all new source files should include a license header.
The majority of the time in NetworkTask was being spent in allocating
and deallocating KBuffers for each incoming packet.
We'll now keep up to 100 buffers around and reuse them for new packets
if the next incoming packet fits in an old buffer. This is pretty
naively implemented but definitely cuts down on time spent here.
Made getsockopt() and setsockopt() virtual so we can handle them in the
various Socket subclasses. The subclasses map kinda nicely to "levels".
This will allow us to implement things like "traceroute", although..
I spent some time trying to do that, but then hit a wall when it turned
out that the user-mode networking in QEMU doesn't preserve TTL in the
ICMP packets passing through.
This approach is a bit naiive - whenever we send a packet out, we
check to see if there are any other packets we should try to send.
This works well enough for a busy connection but not very well for a
quiet one. Ideally we would check for not-acked packets on some kind
of timer, and use the length of this not-acked list as feedback to
throttle the writes coming from userspace.
This allows us to take advantage of unsolicited ARP replies, such as
those that are emitted by many systems after their network interfaces
are enabled, or after their DHCP client sets their IP.
This also makes us a bit more vulnerable to ARP flooding, but we need
some kind of eviction strategy anyway, so we can deal with that later.
An incoming socket should only be considered connected after a
program has received it from accept(). Before that point, it's only
"half" open, and it might not ever actually be served to a program.
Socket::accept is where m_connected is correctly set.
This replaces the previous placeholder routing layer with a real one!
It's still very primitive, doesn't deal with things like timeouts very
well, and will probably need several more iterations to support more
normal networking things.
I haven't confirmed that this works with anything other than the QEMU
user networking layer, but I suspect that's what nearly everybody is
using at this point, so that's the important target to keep working.
By setting up the devices in init() and looping over the registered
network adapters in NetworkTask_main, we can remove the remaining
hard-coded adapter references from the network code.
This also assigns IPs according to the default range supplied by QEMU
in its slirp networking mode.
Once we've converted from an Ethernet frame to an IPv4 packet, we can
pass the IPv4Packet around instead of the EthernetFrameHeader.
Also add some more code to ignore invalid-looking packets.
This is comprised of five small changes:
* Keep a counter for tx/rx packets/bytes per TCP socket
* Keep a counter for tx/rx packets/bytes per network adapter
* Expose that data in /proc/net_tcp and /proc/netadapters
* Convert /proc/netadapters to JSON
* Fix up ifconfig to read the JSON from netadapters
This has several significant changes to the networking stack.
* Significant refactoring of the TCP state machine. Right now it's
probably more fragile than it used to be, but handles quite a lot
more of the handshake process.
* `TCPSocket` holds a `NetworkAdapter*`, assigned during `connect()` or
`bind()`, whichever comes first.
* `listen()` is now virtual in `Socket` and intended to be implemented
in its child classes
* `listen()` no longer works without `bind()` - this is a bit of a
regression, but listening sockets didn't work at all before, so it's
not possible to observe the regression.
* A file is exposed at `/proc/net_tcp`, which is a JSON document listing
the current TCP sockets with a bit of metadata.
* There's an `ETHERNET_VERY_DEBUG` flag for dumping packet's content out
to `kprintf`. It is, indeed, _very debug_.
A KBuffer always contains a valid KBufferImpl. If you need a "null"
state buffer, use Optional<KBuffer>.
This makes KBuffer very easy to work with and pass around, just like
ByteBuffer before it.
There's no need for send_ipv4() to take a ByteBuffer&&, the data is
immediately cooked into a packet and transmitted. Instead, just pass
it the address+length of whatever buffer we've been using locally.
The more we can reduce the pressure on kmalloc the better. :^)