Previously TCPSocket::send_tcp_packet() would try to send TCP packets
which matched whatever size the userspace program specified. We'd try to
break those packets up into smaller fragments, however a much better
approach is to limit TCP packets to the maximum segment size and
avoid fragmentation altogether.
There's no good reason to distinguish between network interfaces based
on their model. It's probably a good idea to try keep the names more
persistent so scripts written for a specific network interface will be
useable after hotplug event (or after rebooting with new hardware
setup).
Problem:
- `static` variables consume memory and sometimes are less
optimizable.
- `static const` variables can be `constexpr`, usually.
- `static` function-local variables require an initialization check
every time the function is run.
Solution:
- If a global `static` variable is only used in a single function then
move it into the function and make it non-`static` and `constexpr`.
- Make all global `static` variables `constexpr` instead of `const`.
- Change function-local `static const[expr]` variables to be just
`constexpr`.
This avoids two allocations when receiving network packets. One for
inserting a PacketWithTimestamp into m_packet_queue and another one
when inserting buffers into the list of unused packet buffers.
With this fixed the only allocations in NetworkTask happen when
initially allocating the PacketWithTimestamp structs and when switching
contexts.
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.
Avoid holding the sockets_by_tuple lock while allocating the TCPSocket.
While checking if the list contains the item we can also hold the lock
in shared mode, as we are only reading the hash table.
In addition the call to from_tuple appears to be superfluous, as we
created the socket, so we should be able to just return it directly.
This avoids the recursive lock acquisition, as well as the unnecessary
hash table lookups.
Note that the changes to IPv4Socket::create are unfortunately needed as
the return type of TCPSocket::create and IPv4Socket::create don't match.
- KResultOr<NonnullRefPtr<TcpSocket>>>
vs
- KResultOr<NonnullRefPtr<Socket>>>
To handle this we are forced to manually decompose the KResultOr<T> and
return the value() and error() separately.
This avoids allocations for initializing the Function<T>
for the NetworkAdapter::for_each callback argument.
Applying this patch decreases CPU utilization for NetworkTask
from 40% to 28% when receiving TCP packets at a rate of 100Mbit/s.
We already have another limit for the total number of packet buffers
allowed (max_packet_buffers). This second limit caused us to
repeatedly allocate and then free buffers.
This matches what other operating systems like Linux do:
$ ip route get 0.0.0.0
local 0.0.0.0 dev lo src 127.0.0.1 uid 1000
cache <local>
$ ssh 0.0.0.0
gunnar@0.0.0.0's password:
$ ss -na | grep :22 | grep ESTAB
tcp ESTAB 0 0 127.0.0.1:43118 127.0.0.1:22
tcp ESTAB 0 0 127.0.0.1:22 127.0.0.1:43118
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
When the MSS option header is missing the default maximum segment
size is 536 which results in lots of very small TCP packets that
NetworkTask has to handle.
This adds the MSS option header to outbound TCP SYN packets and
sets it to an appropriate value depending on the interface's MTU.
Note that we do not currently do path MTU discovery so this could
cause problems when hops don't fragment packets properly.
This increases the default TCP window size to a more reasonable
value of 64k. This allows TCP peers to send us more packets before
waiting for corresponding ACKs.
This increases the buffer size for connection-oriented sockets
to 256kB. In combination with the other patches in this series
I was able to receive TCP packets at a rate of about 120Mbps.
Previously we'd incorrectly use the default gateway's MAC address.
Instead we must use destination MAC addresses that are derived from
the multicast IPv4 address.
With this patch applied I can query mDNS on a real network.
When reading UDP packets from userspace with recvmsg()/recv() we
would hit a VERIFY() if the supplied buffer is smaller than the
received UDP packet. Instead we should just return truncated data
to the caller.
This can be reproduced with:
$ dd if=/dev/zero bs=1k count=1 | nc -u 192.168.3.190 68
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.
The previous patch already helped with this, however my idea of only
reading a few packets didn't work and we'd still sometimes end up not
receiving any more packets from the E1000 interface.
With this patch applied my NIC seems to receive packets just fine, at
least for now.
Raw sockets don't need a local port, so we shouldn't fail operations
if allocation yields an ENOPROTOOPT.
I'm not in love with the factoring here, just patching up the bug.
Without this patch we end up with sockets in the listener's accept
queue with state 'closed' when doing stealth SYN scans:
Client -> Server: SYN for port 22
Server -> Client: SYN/ACK
Client -> Server: RST (i.e. don't complete the TCP handshake)
This commit will add MSG_PEEK support, which allows a package to be
seen without taking it from the buffer, so that a subsequent recv()
without the MSG_PEEK flag can pick it up.
We had some inconsistencies before:
- Sometimes "The", sometimes "the"
- Sometimes trailing ".", sometimes no trailing "."
I picked the most common one (lowecase "the", trailing ".") and applied
it to all copyright headers.
By using the exact same string everywhere we can ensure nothing gets
missed during a global search (and replace), and that these
inconsistencies are not spread any further (as copyright headers are
commonly copied to new files).
Previously the E1000 network adapter would stop receiving further
packets when an RX buffer overrun occurred. This was the case
when connecting the adapter to a real network where enough broadcast
traffic caused the buffer to be full before the kernel had a chance
to clear the RX buffer.
The last IP address in an IPv4 subnet is considered the directed
broadcast address, e.g. for 192.168.3.0/24 the directed broadcast
address is 192.168.3.255. We need to consider this address as
belonging to the interface.
Here's an example with this fix applied, SerenityOS has 192.168.3.190:
[gunnar@nyx ~]$ ping -b 192.168.3.255
WARNING: pinging broadcast address
PING 192.168.3.255 (192.168.3.255) 56(84) bytes of data.
64 bytes from 192.168.3.175: icmp_seq=1 ttl=64 time=0.950 ms
64 bytes from 192.168.3.188: icmp_seq=1 ttl=64 time=2.33 ms
64 bytes from 192.168.3.46: icmp_seq=1 ttl=64 time=2.77 ms
64 bytes from 192.168.3.41: icmp_seq=1 ttl=64 time=4.15 ms
64 bytes from 192.168.3.190: icmp_seq=1 ttl=64 time=29.4 ms
64 bytes from 192.168.3.42: icmp_seq=1 ttl=64 time=30.8 ms
64 bytes from 192.168.3.55: icmp_seq=1 ttl=64 time=31.0 ms
64 bytes from 192.168.3.30: icmp_seq=1 ttl=64 time=33.2 ms
64 bytes from 192.168.3.31: icmp_seq=1 ttl=64 time=33.2 ms
64 bytes from 192.168.3.173: icmp_seq=1 ttl=64 time=41.7 ms
64 bytes from 192.168.3.43: icmp_seq=1 ttl=64 time=47.7 ms
^C
--- 192.168.3.255 ping statistics ---
1 packets transmitted, 1 received, +10 duplicates, 0% packet loss,
time 0ms, rtt min/avg/max/mdev = 0.950/23.376/47.676/16.539 ms
[gunnar@nyx ~]$
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 *
Binding to port 0 is used to signal to listen() to bind to any port
that is available. (in serenity's case, to the port range of 32768 to
60999, which are not privileged ports)
This patch adds a few missing ioctls which were required by Wine.
SIOCGIFNETMASK, SIOCGIFBRDADDR and SIOCGIFMTU are fully implemented,
while SIOCGIFFLAGS and SIOCGIFCONF are stubs.
Switch to using type-safe bitwise operators for the BlockFlags class,
this cleans up a lot of boilerplate casts which are necessary when the
enum is declared as `enum class`.
Mostly due to the fact that clang-format allows aligned comments via
AlignTrailingComments.
We could also use raw string literals in inline asm, which clang-format
deals with properly (and would be nicer in a lot of places).
copy_from_user can fail, for example when the user-supplied pointer is just before
the end of mapped address space. In that case, the first few bytes would get copied,
permanently overwriting the internal state of the Socket, potentially leaving it
in an inconsistent or at least difficult-to-predict state.
This may seem like a no-op change, however it shrinks down the Kernel by a bit:
.text -432
.unmap_after_init -60
.data -480
.debug_info -673
.debug_aranges 8
.debug_ranges -232
.debug_line -558
.debug_str -308
.debug_frame -40
With '= default', the compiler can do more inlining, hence the savings.
I intentionally omitted some opportunities for '= default', because they
would increase the Kernel size.
(...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.
If we try to align a number above 0xfffff000 to the next multiple of
the page size (4 KiB), it would wrap around to 0. This is most likely
never what we want, so let's assert if that happens.
Now that we no longer need to support the signal trampolines being
user-accessible inside the kernel memory range, we can get rid of the
"kernel" and "user-accessible" flags on Region and simply use the
address of the region to determine whether it's kernel or user.
This also tightens the page table mapping code, since it can now set
user-accessibility based solely on the virtual address of a page.
Since the payload size is user-controlled, this could be used to
overflow the kernel stack.
We should probably also be breaking things into smaller packets at a
higher level, e.g TCPSocket::protocol_send(), but let's do that as
a separate exercise.
Fixes#5310.
* 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.
This was done with the help of several scripts, I dump them here to
easily find them later:
awk '/#ifdef/ { print "#cmakedefine01 "$2 }' AK/Debug.h.in
for debug_macro in $(awk '/#ifdef/ { print $2 }' AK/Debug.h.in)
do
find . \( -name '*.cpp' -o -name '*.h' -o -name '*.in' \) -not -path './Toolchain/*' -not -path './Build/*' -exec sed -i -E 's/#ifdef '$debug_macro'/#if '$debug_macro'/' {} \;
done
# Remember to remove WRAPPER_GERNERATOR_DEBUG from the list.
awk '/#cmake/ { print "set("$2" ON)" }' AK/Debug.h.in
For some reason we were keeping the bits 04777 in file modes. That
doesn't seem right and I can't think of a reason why the set-uid bit
should be allowed to slip through.
..and allow implicit creation of KResult and KResultOr from ErrnoCode.
This means that kernel functions that return those types can finally
do "return EINVAL;" and it will just work.
There's a handful of functions that still deal with signed integers
that should be converted to return KResults.
We forgot to remove the automatic SMAP disablers after fixing up all
this code to not access userspace memory directly. Let's lock things
down at last. :^)
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.
These changes are arbitrarily divided into multiple commits to make it
easier to find potentially introduced bugs with git bisect.Everything:
The modifications in this commit were automatically made using the
following command:
find . -name '*.cpp' -exec sed -i -E 's/dbg\(\) << ("[^"{]*");/dbgln\(\1\);/' {} \;
When ProcFS could no longer allocate KBuffer objects to serve calls to
read, it would just return 0, indicating EOF. This then triggered
parsing errors because code assumed it read the file.
Because read isn't supposed to return ENOMEM, change ProcFS to populate
the file data upon file open or seek to the beginning. This also means
that calls to open can now return ENOMEM if needed. This allows the
caller to either be able to successfully open the file and read it, or
fail to open it in the first place.
Compared to version 10 this fixes a bunch of formatting issues, mostly
around structs/classes with attributes like [[gnu::packed]], and
incorrect insertion of spaces in parameter types ("T &"/"T &&").
I also removed a bunch of // clang-format off/on and FIXME comments that
are no longer relevant - on the other hand it tried to destroy a couple of
neatly formatted comments, so I had to add some as well.
The unblock_all variant used to ASSERT if a blocker didn't unblock,
but it wasn't clear from the name that it would do that. Because
the BlockCondition already asserts that no blockers are left at
destruction time, it would still catch blockers that haven't been
unblocked for whatever reason.
Fixes#4496
Since they're all covered by the same spec sheet, we can expect
the same code to cover most of the devices.
It can't currently differentiate between them, which would be nice to
add for determining what registers we can access.
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.
The overrides of this function don't need to know how the original
packet was stored, so let's just give them a ReadonlyBytes view of
the raw packet data.
This fixes an issue where TCP sockets could get into the Established
state too quickly and fail to unblock a subsequent sys$select() call.
This makes websites load *significantly* faster. :^)
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.
Problem:
- C-style arrays do not automatically provide bounds checking and are
less type safe overall.
- `__builtin_memcmp` is not a constant expression in the current gcc.
Solution:
- Change private m_data to be AK::Array.
- Eliminate constructor from C-style array.
- Change users of the C-style array constructor to use the default
constructor.
- Change `operator==()` to be a hand-written comparison loop and let
the optimizer figure out to use `memcmp`.
This makes most operations thread safe, especially so that they
can safely be used in the Kernel. This includes obtaining a strong
reference from a weak reference, which now requires an explicit
call to WeakPtr::strong_ref(). Another major change is that
Weakable::make_weak_ref() may require the explicit target type.
Previously we used reinterpret_cast in WeakPtr, assuming that it
can be properly converted. But WeakPtr does not necessarily have
the knowledge to be able to do this. Instead, we now ask the class
itself to deliver a WeakPtr to the type that we want.
Also, WeakLink is no longer specific to a target type. The reason
for this is that we want to be able to safely convert e.g. WeakPtr<T>
to WeakPtr<U>, and before this we just reinterpret_cast the internal
WeakLink<T> to WeakLink<U>, which is a bold assumption that it would
actually produce the correct code. Instead, WeakLink now operates
on just a raw pointer and we only make those constructors/operators
available if we can verify that it can be safely cast.
In order to guarantee thread safety, we now use the least significant
bit in the pointer for locking purposes. This also means that only
properly aligned pointers can be used.
We were stripping the L3 headers from packets received on raw sockets.
This didn't match what other systems do, so let's adjust our behavior.
Thanks to @SpencerCDixon for noticing this! :^)
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.
Problem: Defining the destructor violates the "rule of 0" and prevents
the copy/move constructor/assignment operators from being provided by
the compiler.
Solution: Change the constructor and destructor to be the default
compiler-provided definition.
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.
When SO_TIMESTAMP is set as an option on a SOCK_DGRAM socket, then
recvmsg() will return a SCM_TIMESTAMP control message that
contains a struct timeval with the system time that was current
when the socket was received.
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.
In addition to being the proper POSIX etiquette, it seems like a bad idea
for issues like the one seen in #3428 to result in a kernel crash. This patch
replaces the current behavior of failing on insufficient buffer size to truncating
SOCK_RAW messages to the buffer size. This will have to change if/when MSG_PEEK
is implemented, but for now this behavior is more compliant and logical than
just bailing.
Instead of FileDescriptor branching on the type of File it's wrapping,
add a File::stat() function that can be overridden to provide custom
behavior for the stat syscalls.
MemoryManager cannot use the Singleton class because
MemoryManager::initialize is called before the global constructors
are run. That caused the Singleton to be re-initialized, causing
it to create another MemoryManager instance.
Fixes#3226
This fixes a bunch of unchecked kernel reads and writes, seems like they
would might exploitable :). Write of sockaddr_in size to any address you
please...
Note that the data member is of type ImmutableBufferArgument, which has
no Userspace<T> usage. I left it alone for now, to be fixed in a future
change holistically for all usages.
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.
This compiles, and contains exactly the same bugs as before.
The regex 'FIXME: PID/' should reveal all markers that I left behind, including:
- Incomplete conversion
- Issues or things that look fishy
- Actual bugs that will go wrong during runtime
The way getsockopt is implemented for socket types requires us to push
down Userspace<T> using into those interfaces. This change does so, and
utilizes proper copy implementations instead of the kind of haphazard
pointer dereferencing that was occurring there before.
Allow passing in an optional timeout to Thread::block and move
the timeout check out of Thread::Blocker. This way all Blockers
implicitly support timeouts and don't need to implement it
themselves. Do however allow them to override timeouts (e.g.
for sockets).
Use copy_{to,from}_user() in the various File::ioctl() implementations
instead of disabling SMAP wholesale in sys$ioctl().
This patch does not port IPv4Socket::ioctl() to those API's since that
will be more involved. That function now creates a local SmapDisabler.
We were masking the fragment offset bits incorrectly in the IPv4 header
sent out with fragments. This worked up to ~32KB but after that, things
would get very confused. :^)
We now have BlockResult::WokeNormally and BlockResult::NotBlocked,
both of which indicate no error. We can no longer just check for
BlockResult::WokeNormally and assume anything else must be an
interruption.
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.
Random now gets entropy from the following drivers:
- KeyboardDevice
- PATAChannel
- PS2MouseDevice
- E1000NetworkAdapter
- RTL8139NetworkAdapter
Of these devices, PS2MouseDevice and PATAChannel provide the vast
majority of the entropy.
These new syscalls allow you to send and receive file descriptors over
a local domain socket. This will enable various privilege separation
techniques and other good stuff. :^)
We're going to make use of it in the next commit. But the idea is we want to
know how this File (more specifically, InodeFile) was opened in order to decide
how chown()/chmod() should behave, in particular whether it should be allowed or
not. Note that many other File operations, such as read(), write(), and ioctl(),
already require the caller to pass a FileDescription.
This was supposed to be the foundation for some kind of pre-kernel
environment, but nobody is working on it right now, so let's move
everything back into the kernel and remove all the confusion.
Since a Region is basically a view into a potentially larger VMObject,
it was always necessary to include the Region starting offset when
accessing its underlying physical pages.
Until now, you had to do that manually, but this patch adds a simple
Region::physical_page() for read-only access and a physical_page_slot()
when you want a mutable reference to the RefPtr<PhysicalPage> itself.
A lot of code is simplified by making use of this.
This commit is one step forward for pluggable driver modules.
Instead of creating instances of network adapter classes, we let
their detect() methods to figure out if there are existing devices
to initialize.
The PCI access layer was composed of a bunch of virtual functions that
did nothing but call other virtual functions. The first layer was never
overridden so there was no need for them to be virtual.
This patch removes the indirection and moves logic from PCI::Access
down into the various PCI::get_foo() helpers that were the sole users.
This patch adds a way for a socket to ask to be routed through a
specific interface.
Currently, this option only applies to sending, however, it should also
apply to receiving...somehow :^)
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 :)
This is not a complete fix, since spurious IRQs under heavy loads can
still occur. However, this fix limits the amount of spurious IRQs.
It is encouraged to provide a better fix in the future, probably
something that takes into account handling of PCI level-triggered
interrupts.
