Misc: some updates.

1.add interface `ff_dup` and `ff_dup2`.
2.add interface `ff_ioctl_freebsd`/`ff_getsockopt_freebsd`/`ff_setsockopt_freebsd` for tools.
3.initial parameter `proc-type` can be NULL,

Misc: some updates.

1.add interface `ff_dup` and `ff_dup2`.
2.add interface `ff_ioctl_freebsd`/`ff_getsockopt_freebsd`/`ff_setsockopt_freebsd` for tools.
3.initial parameter `proc-type` can be NULL, default "auto".

show more ...

Fstack: fixbug, bad checksum would lead to memleak of dpdk mbuf

Fix compling error in the newer version of gcc and openssl.

`RAND_pseudo_bytes` is deprecated in the newer version of openssl.
Use `RAND_bytes` instead.

DPDK: upgrade to 17.11.2 LTS.

Changes:
1. This version is downloaded from
https://fast.dpdk.org/rel/dpdk-17.11.2.tar.xz.
2. Adapt the new interface `rte_ring_dequeue_burst`.
3. Change the type of `p

DPDK: upgrade to 17.11.2 LTS.

Changes:
1. This version is downloaded from
https://fast.dpdk.org/rel/dpdk-17.11.2.tar.xz.
2. Adapt the new interface `rte_ring_dequeue_burst`.
3. Change the type of `port_id` from uint8_t to uint16_t.
4. Just link libdpdk.a instead of the other libaries.
5. Install libnuma-dev first.
6. Update the documents.

show more ...

kern_timeout: decrease the cpu usage of timer.

There's a bug of last version, every tick, the timer will traverse all the
entries in callwheel, when lots of connections comming, the callout
process

kern_timeout: decrease the cpu usage of timer.

There's a bug of last version, every tick, the timer will traverse all the
entries in callwheel, when lots of connections comming, the callout
process will use lots of cpu resources.

This commit fixes it, every tick, check the bucket which is hashed with current
tick, if there are entries, compare the callout tick, and invoke
callbacks.

show more ...

API: [BugFix] On success, `ff_sendmsg` return the number of chars sent.

API : ff_sendmsg, use transient variables to avoid polluting user's data.

API : fix bug of ff_sendmsg and ff_recvmsg
freebsd and linux have a different "struct sockaddr".
In ff_recvmsg and ff_recvmsg, ```msg->msg_name```,which can refer to address, can be expected to be co

API : fix bug of ff_sendmsg and ff_recvmsg
freebsd and linux have a different "struct sockaddr".
In ff_recvmsg and ff_recvmsg, ```msg->msg_name```,which can refer to address, can be expected to be converted .

show more ...

ff_kern_timeout: optimize the timecounter.

This timecounter implementation retrieves the current time and reports it
as the equivalent number of counts from a counter incrementing at 'hz'.

FreeBSD: initialize `mp_ncpus`.

Fix crash when executing `./sysctl -w kern.callout_stat=1`.

Ipfw: fix "invalid argument" when using `divert`.

Note that this only fix the error, `divert` is still not usable, refer to #136.
If you want to use NAT, you can just use the built-in `ipfw nat`
ins

Ipfw: fix "invalid argument" when using `divert`.

Note that this only fix the error, `divert` is still not usable, refer to #136.
If you want to use NAT, you can just use the built-in `ipfw nat`
instead.

show more ...

Misc: add "extern C" in public header files.

Remove the unusable api `ff_socketpair`.

Since F-Stack doesn't support AF_UNIX. ff_socketpair couldn't work and
should be removed.

Fix #124

Fix #124: set/get user data in epoll

Nginx: support kernel network stack, so we can do what fstack can't do,
e.g. unix socket, ipc (with APP on kernel network stack), packet from kernel network stack.
1. Add a new directive kernel_netw

Nginx: support kernel network stack, so we can do what fstack can't do,
e.g. unix socket, ipc (with APP on kernel network stack), packet from kernel network stack.
1. Add a new directive kernel_network_stack :
Syntax: kernel_network_stack on | off;
Default: kernel_network_stack off;
Context: http, server
This directive is available only when NGX_HAVE_FF_STACK is defined.
Determines whether server should run on kernel network stack or fstack.
2. Use a simpler and more effective solution to discriminate fstack fd(file descriptor, only socket for now) from kernel fd.

show more ...

ff_epoll: rewrite `ff_epoll_ctl`.

ff_epoll: support edge-triggered mode.

Convert epoll EPOLLET to kqueue EV_CLEAR.

Fix bug: incorrect usage of `rte_pktmbuf_clone` when dispatching arp packets.

Since f-stack uses `rte_pktmbuf_clone` to copy mbuf to other lcores when dispatching arp packets, but it doesn't real co

Fix bug: incorrect usage of `rte_pktmbuf_clone` when dispatching arp packets.

Since f-stack uses `rte_pktmbuf_clone` to copy mbuf to other lcores when dispatching arp packets, but it doesn't real copy the packet data. The buf_addr of pktmbuf is pointed to the same address.

The arp response packet is generated with the same mbuf from the request
packet, it just swaps the src and dst address, so the copied mbufs will also be changed.

What we need is a deep copy function, and the arp packets are really small, so deep copy will not harm performance too much.

Fix #53 #111 #112.

show more ...

Fix #107: some invalid usages of kqueue in `ff_epoll`.

1.Both EVFILT_READ and EVFILT_WRITE are values but not flags. It needs to check whether it is equal but not to do logic and.

2.If the read dir

Fix #107: some invalid usages of kqueue in `ff_epoll`.

1.Both EVFILT_READ and EVFILT_WRITE are values but not flags. It needs to check whether it is equal but not to do logic and.

2.If the read direction of the socket has shutdown, then the filter also sets EV_EOF in `flags`, and returns the socket error (if any) in `fflags`.

show more ...

Use general protocol header length in protocol filter.

Fix #100: tcp anomaly when TSO is enabled.

1.Fix the wrong ip header length and tcp header length.
2.Recalculate the pseudo header checksum and set it to tcp header.

Add tool: ipfw.

ipfw -- interface for firewall, packet scheduler, NAT and so on.

It is comprised of several components: the kernel firewall filter rule processor and its integrated packet accountin

Add tool: ipfw.

ipfw -- interface for firewall, packet scheduler, NAT and so on.

It is comprised of several components: the kernel firewall filter rule processor and its integrated packet accounting facility, the logging facility, NAT, a forward facility, a bridge facility, and an ipstealth facility.
Note that the `dummynet` traffic shaper is not merged.

show more ...

Fix bug: process input packets error if packet fragment

modified: lib/ff_dpdk_if.c

Api: add packet dispatch callback function register.

In some cases, for example, packets are forwarded to your server through
IP tunnel, and they will be received on fixed queues, since RSS doesn't

Api: add packet dispatch callback function register.

In some cases, for example, packets are forwarded to your server through
IP tunnel, and they will be received on fixed queues, since RSS doesn't support tunnels.So we need to dispatch them again.

With this commit, we can implement a dispatcher callback function and regist
it, packets retrieved from rx queue will be dispatched again according to
the dispatcher result.

show more ...

Add tool: ngctl.

ngctl -- netgraph control utility.
The ngctl utility creates a new netgraph node of type socket which can be used to issue netgraph commands.