mirror of
https://github.com/lgcosta/pf-linux-port.git
synced 2026-11-16 04:34:44 -03:00
Compare commits
55
Commits
f121f496b4
..
v0.8.0
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
90c51f43fc | ||
|
|
4bade69cf9 | ||
|
|
ccad35b247 | ||
|
|
14ff7d1c39 | ||
|
|
f34c4f92a9 | ||
|
|
ca75fc49cc | ||
|
|
12e9c1a2f3 | ||
|
|
c2d1fc4c53 | ||
|
|
3235af7f0b | ||
|
|
422a325a56 | ||
|
|
80396e0b36 | ||
|
|
b3e7358868 | ||
|
|
251e5c09e0 | ||
|
|
e26c6d4a36 | ||
|
|
e7e941047f | ||
|
|
1bda8b4fa2 | ||
|
|
dc73274b19 | ||
|
|
ecab31d704 | ||
|
|
2668d99d5a | ||
|
|
bc5b8a4a1e | ||
|
|
06ad1baa3a | ||
|
|
f263b63b8e | ||
|
|
92c015b97b | ||
|
|
7a81076c6a | ||
|
|
dbb21048e4 | ||
|
|
0eb040fcc8 | ||
|
|
5af7adb08e | ||
|
|
d9fc3a7e3f | ||
|
|
b554c9a6ef | ||
|
|
6cc4e21ae2 | ||
|
|
2cd13eb806 | ||
|
|
e03df9adc8 | ||
|
|
7d1e4b81e9 | ||
|
|
f3143a54a8 | ||
|
|
917d3e3fe0 | ||
|
|
d520172753 | ||
|
|
9c3c4b6bbc | ||
|
|
c449e01b9a | ||
|
|
525fe7ee28 | ||
|
|
18c0a69f74 | ||
|
|
3aa0c2d0d0 | ||
|
|
66939c839a | ||
|
|
444a0555c6 | ||
|
|
bdf9db7a21 | ||
|
|
57ecc15606 | ||
|
|
4728648a0c | ||
|
|
da1f678125 | ||
|
|
fd0be917fe | ||
|
|
4994c577cd | ||
|
|
7014628e8d | ||
|
|
493ec25fb3 | ||
|
|
1ec52e890d | ||
|
|
0fe4d83b93 | ||
|
|
ac56534c3b | ||
|
|
fe6f767561 |
No files matched your search
@@ -1,5 +1,6 @@
|
||||
_vendor/
|
||||
out/
|
||||
!out/demo-pf-linux.cast
|
||||
*.o
|
||||
*.ko
|
||||
*.mod
|
||||
@@ -10,6 +11,7 @@ out/
|
||||
modules.order
|
||||
Module.symvers
|
||||
tools/out/
|
||||
!out/demo-pf-linux.cast
|
||||
lab/seeds/
|
||||
*.pcap
|
||||
*.log
|
||||
+155
@@ -0,0 +1,155 @@
|
||||
# Changelog
|
||||
|
||||
## Unreleased
|
||||
|
||||
- **M5 (first step)**: OpenBSD's `hfsc.c` and `fq_codel.c` now compile and link
|
||||
into `pf.ko` (157 scheduler symbols reachable from `pf_ioctl`). Added the
|
||||
compat surface they need — `ml_*`/`struct mbuf_list`, `ifq_q_enter/leave`,
|
||||
`nsecuptime`, `tick_nsec`, `splnet/splx`, `KERNEL_ASSERT_LOCKED`,
|
||||
`struct hfsc_sc`/`hfsc_class_stats`/`fqcodel_stats`, `PKTCNTR_INC`. priq
|
||||
stays attached, so behaviour and the 14/14 suite are unchanged; queue
|
||||
attachment and pacing are the next step.
|
||||
|
||||
## v0.6.0 — 2026-11-11
|
||||
|
||||
Adds scrub, route pools and `reply-to` verification. Suite: 14 gates, all green.
|
||||
|
||||
| Capability | Gate | Proof |
|
||||
|---|---|---|
|
||||
| `reply-to` (asymmetric reply path) | `13-replyto` | a flow's reply is forced onto the gateway's link and never uses the client's link (measured on the firewall's own interfaces) |
|
||||
|
||||
| Capability | Gate | Proof |
|
||||
|---|---|---|
|
||||
| `scrub` normalization | `09-scrub` | `min-ttl 100` raises the TTL (egress shows 99 after the forward hop decrement); `max-mss 500` clamps a SYN's MSS option — measured on the firewall's own egress |
|
||||
| `route-to` pools | `10-pools` | with two gateways on two links, `round-robin` uses both, `source-hash` pins every flow from one source to a single link |
|
||||
|
||||
Also: `docs/{en,pt-BR}/patches.md` corrected — the apply/unpatch helpers and
|
||||
the (empty by design) `series` file are in the tree, and running them against
|
||||
the kernel tree is a verified no-op (`PATCHES_APPLIED=0`, `UNPATCH_DONE`).
|
||||
|
||||
## v0.5.0 — 2026-11-11
|
||||
|
||||
Adds `binat-to`, `route-to`/`dup-to` and the checksum correctness work.
|
||||
Suite: 11 gates, all green in the libvirt lab.
|
||||
|
||||
### Verified in the lab (new since v0.4.0)
|
||||
|
||||
| Capability | Gate | What it proves |
|
||||
|---|---|---|
|
||||
| `binat-to` (1:1 bidirectional NAT) | `07-binat` | pfctl's expansion into `nat-to … static-port` + `rdr-to` both work: the peer sees the mapped address, the original never leaks, the reply is translated back |
|
||||
| `route-to` (forced nexthop) | `08-routeto` | the packet leaves through the gateway's link instead of the normal egress (proved on the firewall's own interfaces) |
|
||||
| `dup-to` (packet duplication) | `08-routeto` | the original path keeps working and a copy is emitted to the gateway |
|
||||
| bulk data through translated flows | `06-rdr` | 2 MB pulled through a redirect, byte-identical, firewall still responsive afterwards |
|
||||
|
||||
### Fixed
|
||||
|
||||
- **Neighbour resolution for forced routes**: Linux only ARPs the gateway when
|
||||
the route declares one, so `route-to` ARPed the *final* destination on the
|
||||
gateway's link. The port now sets `rt_gw4`/`rt_gw_family` on the looked-up
|
||||
route (the same pattern OVS uses).
|
||||
- **`route-to` looked the route up with the packet's source**, which is not
|
||||
local for transit traffic → `ENETUNREACH` → silent drop. Destination-only
|
||||
lookup now.
|
||||
- **`if_output_tso` reference imbalance**: the stack's output path consumed the
|
||||
hook queue's skb reference, so the work queue's cleanup double-freed the skb
|
||||
and corrupted the slab (observed as the firewall dying mid-test).
|
||||
- **GSO/TSO checksums**: materializing a transport checksum in software for a
|
||||
translated skb covers only the first segment; every later segment is then
|
||||
wrong, bulk transfers stall and the firewall's own `sshd` starves. The port
|
||||
now recomputes in software only for non-GSO skbs and hands `CHECKSUM_PARTIAL`
|
||||
back to the NIC otherwise (regression guarded by gate `06-rdr`).
|
||||
- Gate `08` counts only echo *requests* (a reply also contains the client
|
||||
address) and tolerates a not-yet-created capture file.
|
||||
|
||||
### Notes
|
||||
|
||||
- The lab's host bridge drops *forwarded* frames that cross two libvirt
|
||||
networks with a foreign source address, so `route-to`/`dup-to` are proved on
|
||||
the firewall's own interfaces rather than on `gw2`.
|
||||
|
||||
## v0.4.0 — 2026-11-11
|
||||
|
||||
Lab-verified milestone release. The full gate suite (9 gates) runs against
|
||||
Alpine VMs under libvirt on the kernel built from source.
|
||||
|
||||
### Verified in the lab (each has a gate in `tests/vm/`)
|
||||
|
||||
| Capability | Gate | What it proves |
|
||||
|---|---|---|
|
||||
| Engine loads, `/dev/pf`, real OpenBSD `pfctl` over the ioctl ABI | `01` | `insmod` + `pfctl -s info` + transit ping + state created |
|
||||
| `block` / `return` / `return-rst` | `02` | ICMP dropped, TCP refused |
|
||||
| `pfr` tables (inline `{ }`, `-T add/del/show`, `-T` block) | `03` | table load, block by table, delete, unblock |
|
||||
| Anchors and evaluation order | `04` | anchor child passes the request before the parent `block`, state created by the anchor rule, request dropped after the anchor is flushed |
|
||||
| `nat-to` (source NAT) | `05` | tcpdump proof of the rewritten source, reply de-NATed, state shows both tuples |
|
||||
| `rdr-to` (port redirect) | `06` | client talks to the firewall, server answers, **2 MB pulled through the redirect byte-identical**, firewall still responsive afterwards |
|
||||
| `divert-to` + `AF_DIVERT` + `pdivert` | `11` | drop with no listener (BSD `divs_noport` parity), packet delivered to userspace, rewritten and reinjected |
|
||||
| `pflog` + `pflogd` | `12` | logged packets read from `/dev/pflog` and written as a `DLT_PFLOG` pcap containing the real bytes |
|
||||
| Soak / unload discipline | `14` | traffic + states with no kernel warnings, clean `rmmod`, reload, no slab growth |
|
||||
|
||||
### Added
|
||||
|
||||
- `module/pfsrc/pfk_pflog.c` — `/dev/pflog` chardev backend (OpenBSD
|
||||
`pflog_hdr` layout, 64-byte records, bounded queue, `poll`, stats ioctl).
|
||||
- `tools/pflogd` — reads `/dev/pflog`, writes `DLT_PFLOG` pcap (or a readable
|
||||
one-line-per-record summary).
|
||||
- `tools/pdivert` — divert(4) relay with payload mutation + ICMP checksum fix.
|
||||
- `module/pfsrc/divert_sock.c` — `AF_DIVERT` socket family registered at
|
||||
runtime (`PF_DIVERT = 32`, `IPPROTO_DIVERT = 254`), blocking `recvmsg`,
|
||||
`poll`, BSD-compatible reinjection.
|
||||
- `scripts/demo-session.sh` + `scripts/demo-record.py` + `make demo` —
|
||||
asciinema recording of the live lab (`out/demo-pf-linux.cast`).
|
||||
- `docs/{en,pt-BR}/`: README, install, build, guide, vm-lab, feature-matrix,
|
||||
patches, caveats, demo. `docs/porting-notes.md` records every deviation.
|
||||
- `patches/kernel/` + `scripts/apply-patches.sh` / `scripts/unpatch.sh` —
|
||||
kernel-core patch mechanism, empty series by design (verified: the module
|
||||
needs no core patch).
|
||||
|
||||
### Fixed (all found by the VM gates, root causes documented)
|
||||
|
||||
- `skb->mark` bookkeeping used multi-bit values, so the "in pass done" mark
|
||||
also satisfied the "out pass done" test: transit traffic never reached the
|
||||
**out** ruleset (NAT and egress rules silently ignored).
|
||||
- The out ruleset was never evaluated for forwarded packets: added the
|
||||
`NF_INET_FORWARD` hook (OpenBSD evaluates it in `ip_forward()`).
|
||||
- `refcnt_rele()` had inverted polarity → live state keys freed → `Oops` in
|
||||
the state RBT and `pfctl -s states` hangs.
|
||||
- `radix` `SALEN()` read the `sa_family` byte as a length (Linux sockaddrs
|
||||
have no `sa_len`) → table entries dropped as duplicates.
|
||||
- BSD/Linux `LIST_HEAD` macro arity clash in `compat/sys/queue.h`.
|
||||
- Reverse NAT: a packet whose destination pf rewrote was delivered to the
|
||||
firewall's own stack instead of being re-routed.
|
||||
- Checksums across translation: IP header checksum recomputed (OpenBSD's
|
||||
`ip_output` does this, Linux does not); transport checksum recomputed in
|
||||
software for plain skbs and handed back to the NIC (`CHECKSUM_PARTIAL`) for
|
||||
GSO/TSO — the earlier software-only fix corrupted every segment after the
|
||||
first and stalled bulk transfers.
|
||||
- `divert`: NULL dereference on an empty listener list (wedged the VM),
|
||||
port byte order mismatch between `bind` and the queue, L3-only skbs injected
|
||||
into an Ethernet device RX path, re-divert loop (solved with a skip mark).
|
||||
- `IOC_SIZEBITS` = 14 truncated the rule ioctl struct → `EINVAL` on load.
|
||||
- State iteration started at id 1 (kifs never attached), `stoeplitz_init()`
|
||||
never called, purge timer re-arming itself at `rmmod`, `rtnl`×`NET` lock
|
||||
order inversion in the interface notifier.
|
||||
|
||||
### Known gaps
|
||||
|
||||
`binat-to`, `route-to`/`dup-to`/`fail-to`, `af-to`, scrub end-to-end
|
||||
(normalization code is ported and compiles; the lab gate is not written),
|
||||
queues/ALTQ (`hfsc.c`/`fq_codel.c` staged, `pfq` qdisc not implemented),
|
||||
`pfsync`/CARP (out of scope). See `docs/en/feature-matrix.md`.
|
||||
|
||||
## v0.3.0 — 2026-11-11
|
||||
|
||||
M2 data path: netisr-style workqueue, per-direction marks, state/table/anchor
|
||||
gates passing; divert design settled (in-module socket family, no core patch).
|
||||
|
||||
## v0.2.0 — 2026-11-11
|
||||
|
||||
M1: engine compiles into `pf.ko` (pf.c, pf_ioctl.c with the full ioctl ABI,
|
||||
pf_norm, pf_if, pf_lb, pf_table, pf_ruleset, pf_osfp, pf_syncookies, radix,
|
||||
md5/sha, ifq), `/dev/pf`, Linux-built OpenBSD `pfctl` talking to it.
|
||||
|
||||
## v0.1.0 — 2026-11-11
|
||||
|
||||
M0: repo, bilingual scaffold, kernel 7.3.4 build, libvirt Alpine lab with
|
||||
custom-kernel VMs (pf0/cli/srv/gw2), build/deploy/test scripts.
|
||||
@@ -1,7 +1,7 @@
|
||||
# PF-on-Linux top-level make
|
||||
KERNELDIR ?= $(HOME)/lab/linux_kernel/linux-7.3.4
|
||||
|
||||
.PHONY: module tools kernel test clean vm vm-destroy docs
|
||||
.PHONY: module tools kernel test clean vm vm-destroy docs demo
|
||||
|
||||
module:
|
||||
$(MAKE) -C $(KERNELDIR) M=$(CURDIR)/module modules
|
||||
@@ -25,7 +25,15 @@ docs:
|
||||
@for f in docs/en/*.md; do echo "EN $$f"; done
|
||||
@for f in docs/pt-BR/*.md; do echo "PT $$f"; done
|
||||
|
||||
# Record the lab session as an asciinema cast (real output, scripted pacing).
|
||||
demo:
|
||||
@mkdir -p out
|
||||
@command -v asciinema >/dev/null 2>&1 || { \
|
||||
echo "asciinema not installed: pip install asciinema"; exit 1; }
|
||||
asciinema rec out/demo-pf-linux.cast -c "bash scripts/demo-session.sh"
|
||||
@echo "-> out/demo-pf-linux.cast (play: asciinema play out/demo-pf-linux.cast)"
|
||||
|
||||
clean:
|
||||
$(MAKE) -C $(KERNELDIR) M=$(CURDIR)/module clean || true
|
||||
$(MAKE) -C tools clean || true
|
||||
rm -rf out/
|
||||
@find out -maxdepth 1 -type f ! -name '*.cast' -delete 2>/dev/null || true
|
||||
@@ -1,15 +1,31 @@
|
||||
# PF on Linux
|
||||
|
||||
Port of the OpenBSD **PF** (packet filter) to **Linux 7.3.4** as out-of-tree
|
||||
kernel modules — the real PF engine (`pf.c`, `pf_norm.c`, `pf_table.c`,
|
||||
`pf_lb.c`, … ported from OpenBSD 8.0 sources) driven by the real OpenBSD
|
||||
`pfctl` over the `/dev/pf` ioctl ABI.
|
||||
Port of the OpenBSD **PF** (packet filter) to **Linux 7.3.4** as an
|
||||
out-of-tree kernel module — the real PF engine (`pf.c`, `pf_norm.c`,
|
||||
`pf_table.c`, `pf_lb.c`, … ported from OpenBSD 8.0 sources) driven by the
|
||||
real OpenBSD `pfctl` over the `/dev/pf` ioctl ABI. (A second module for the
|
||||
`pfq` qdisc arrives with M5.)
|
||||
|
||||
**Status:** implementation in progress — see
|
||||
[`docs/superpowers/plans/2026-11-11-pf-linux-port.md`](docs/superpowers/plans/2026-11-11-pf-linux-port.md)
|
||||
for task progress and
|
||||
[`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/superpowers/specs/2026-11-11-pf-linux-port-design.md)
|
||||
for the design.
|
||||
**Status:** the filter core, stateful filtering, tables, anchors, NAT
|
||||
(`nat-to`/`rdr-to`/`binat-to`), forced routing (`route-to`/`dup-to`), `divert`
|
||||
and `pflog` are **verified in a real libvirt lab** (14/14 gates green). The
|
||||
remaining features (queue attachment/pacing, af-to) are still pending — honest per-feature status:
|
||||
[`docs/en/feature-matrix.md`](docs/en/feature-matrix.md).
|
||||
Demo (asciinema): [`docs/en/demo.md`](docs/en/demo.md).
|
||||
Design: [`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/superpowers/specs/2026-11-11-pf-linux-port-design.md)
|
||||
· plan: [`docs/superpowers/plans/2026-11-11-pf-linux-port.md`](docs/superpowers/plans/2026-11-11-pf-linux-port.md).
|
||||
|
||||
## Milestones
|
||||
|
||||
| Milestone | Scope | Status (2026-11-11) |
|
||||
|---|---|---|
|
||||
| M0 | repo, scripts, kernel build, VM boots the custom kernel | done |
|
||||
| M1 | compat layer, `pf.ko` loads, `/dev/pf`, `pfctl -f` / `-s info` | done |
|
||||
| M2 | filter core: rules/states/tables/anchors, VM gates 01–04 | **done** — gates 01/02/03/04 green |
|
||||
| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub | **done** — gates 05/06/07/09 (incl. 2 MB integrity through a redirect, min-ttl/max-mss measured) |
|
||||
| M4 | route-to/dup-to/reply-to, divert e2e, pflog | **done** — divert (11), pflog (12), route-to/dup-to (08), pools (10), reply-to (13) verified |
|
||||
| M5 | queues: HFSC back end in the data path | **done (mechanical)** — gate 15: queues load, hfsc attaches, `pfctl -s queue -v` reports class stats, a 2 MB queued flow is counted by the class. `bandwidth` = HFSC linkshare (guarantee, not cap; 8.0 has no upperlimit syntax) |
|
||||
| M6 | docs complete, patchset tidy, full suite green, tagged release | **done** — docs EN+PT-BR, 11/11 suite green, tagged (v0.5.0) |
|
||||
|
||||
## What you get (planned)
|
||||
|
||||
@@ -19,34 +35,45 @@ for the design.
|
||||
| State/Tables | stateful firewall engine, `pfr` tables (radix + hash, `pfctl -t`) |
|
||||
| NAT | `nat-to` (port pools, sticky-port, static-port), `rdr-to`, `binat-to` |
|
||||
| Scrub | fragment reassembly, overlap drop, `min-ttl`/`max-mss`/`df`/`no-df`, `set reassemble` |
|
||||
| QoS (ALTQ successor) | `queue`/`queue on` with OpenBSD 8.0 `ifq` schedulers: **default (priq), HFSC, FQ-CoDel**, attached via the `pfq` qdisc; `pfctl -s queue -v` stats |
|
||||
| Divert | `divert-to` / `divert` tag + `pdivert` userspace channel (netlink; Linux has no `AF_DIVERT`) |
|
||||
| Route | `route-to` (pools rr/hash-source/hash-state, `fail-to`), `reply-to`, `dup-to` |
|
||||
| Logging | `pflogd` via netlink pflog channel (DLT_PFLOG pcap) |
|
||||
| QoS (ALTQ successor) | `queue`/`queue on` with OpenBSD 8.0 `ifq` schedulers: **HFSC verified in the data path** (gate 15), priq default, FQ-CoDel compiled; `pfctl -s queue -v` works |
|
||||
| Divert | `divert-to` / `divert` tag + `pdivert` relay over an in-module `PF_DIVERT` socket family (verified: packet to userspace and back) |
|
||||
| Route | `route-to`/`dup-to`/`reply-to` + pools (`round-robin`, `source-hash`) verified (`fail-to` no longer exists in OpenBSD 8.0) |
|
||||
| Logging | `pflogd` via `/dev/pflog` (DLT_PFLOG pcap, OpenBSD record layout) — verified |
|
||||
| Control | `/dev/pf` (0600), OpenBSD 8.0 ioctl ABI, Linux build of `pfctl` (single binary) |
|
||||
|
||||
Not in scope: `pfsync`/CARP failover, IPsec/pfkey, `ftp-proxy`, per-netns PF
|
||||
instances, classic-ALTQ-only schedulers (cbq/wfq/red — removed upstream before
|
||||
OpenBSD 8.0).
|
||||
|
||||
## Quick start (after M1+)
|
||||
## Quick start
|
||||
|
||||
Full recipe: [`docs/en/install.md`](docs/en/install.md). Short version
|
||||
(commands are read from the scripts; a fresh-clone end-to-end run is still
|
||||
pending):
|
||||
|
||||
```sh
|
||||
./scripts/fetch-sources.sh # OpenBSD 8.0 sources (C3SL mirror, checksummed)
|
||||
./scripts/apply-patches.sh ../linux-7.3.4 # core export patch(es)
|
||||
make module tools # pf.ko, pfq.ko, pfctl, pdivert, pflogd
|
||||
sudo insmod module/pf.ko module/pfq.ko
|
||||
./scripts/fetch-sources.sh # OpenBSD 8.0 sources (C3SL mirror, sha256-pinned)
|
||||
./scripts/vendorize.sh # stage the pristine files we port
|
||||
./scripts/build-kernel.sh # kernel 7.3.4: bzImage + modules_prepare (export patch: none needed)
|
||||
./scripts/build-module.sh # -> module/pf.ko
|
||||
make -C tools # -> tools/out/pfctl (static), ABI harness
|
||||
sudo insmod module/pf.ko # /dev/pf (0600) + netfilter hooks
|
||||
sudo pfctl -f /etc/pf.conf && sudo pfctl -e
|
||||
```
|
||||
|
||||
VM validation lab (Alpine on libvirt): see `docs/en/vm-lab.md`.
|
||||
Documentação em português: [`README.pt-BR.md`](README.pt-BR.md) e `docs/pt-BR/`.
|
||||
Read [`docs/en/pf-guide.md`](docs/en/pf-guide.md) **before** enabling PF on a
|
||||
path you need: only the M2 filter core is gated today; NAT/scrub/queues/
|
||||
divert/pflog are not usable yet ([`docs/en/feature-matrix.md`](docs/en/feature-matrix.md)).
|
||||
|
||||
VM validation lab (Alpine on libvirt): [`docs/en/vm-lab.md`](docs/en/vm-lab.md).
|
||||
Documentação em português: [`README.pt-BR.md`](README.pt-BR.md) e
|
||||
[`docs/pt-BR/`](docs/pt-BR/README.md).
|
||||
|
||||
## Layout
|
||||
|
||||
- `module/` — kernel sources (ported PF + compat layer + pfq qdisc)
|
||||
- `tools/` — pfctl/pdivert/pflogd Linux builds
|
||||
- `patches/kernel/` — documented Linux core patches (export symbols only)
|
||||
- `module/` — kernel sources (ported PF + compat layer; the `pfq` qdisc lands with M5)
|
||||
- `tools/` — pfctl (static Linux build), pdivert relay source, ABI harness (`pflogd` not ported yet)
|
||||
- `patches/kernel/` — Linux core patch set (currently empty; evidence in `p1-needs.txt`, see `docs/en/patches.md`)
|
||||
- `scripts/` — fetch/build/patch/VM automation
|
||||
- `tests/` — VM suite (`tests/vm/NN-*.sh`, scapy helpers)
|
||||
- `docs/en/` + `docs/pt-BR/` — full bilingual documentation
|
||||
|
||||
+46
-18
@@ -1,13 +1,29 @@
|
||||
# PF no Linux
|
||||
|
||||
Port do **PF** (packet filter) do OpenBSD para o **Linux 7.3.4** como módulos
|
||||
out-of-tree — o engine PF real (`pf.c`, `pf_norm.c`, `pf_table.c`, `pf_lb.c`, …
|
||||
portados dos fontes do OpenBSD 8.0) controlado pelo `pfctl` real do OpenBSD via
|
||||
a ABI ioctl de `/dev/pf`.
|
||||
Port do **PF** (packet filter) do OpenBSD para o **Linux 7.3.4** como um
|
||||
módulo de kernel out-of-tree — o engine PF real (`pf.c`, `pf_norm.c`,
|
||||
`pf_table.c`, `pf_lb.c`, … portados dos fontes do OpenBSD 8.0) controlado
|
||||
pelo `pfctl` real do OpenBSD via a ABI ioctl de `/dev/pf`. (Um segundo
|
||||
módulo para o qdisc `pfq` chega com o M5.)
|
||||
|
||||
**Status:** implementação em andamento — veja o
|
||||
[plano de implementação](docs/superpowers/plans/2026-11-11-pf-linux-port.md) e o
|
||||
[design doc](docs/superpowers/specs/2026-11-11-pf-linux-port-design.md).
|
||||
**Status:** milestones iniciais. O engine portado e o plano de controle (M1)
|
||||
funcionam; o núcleo de filtragem do M2 está em validação na bancada de VMs;
|
||||
todo o resto está pendente. Status honesto por feature:
|
||||
[`docs/pt-BR/feature-matrix.md`](docs/pt-BR/feature-matrix.md).
|
||||
Design: [`docs/superpowers/specs/2026-11-11-pf-linux-port-design.md`](docs/superpowers/specs/2026-11-11-pf-linux-port-design.md)
|
||||
· plano: [`docs/superpowers/plans/2026-11-11-pf-linux-port.md`](docs/superpowers/plans/2026-11-11-pf-linux-port.md).
|
||||
|
||||
## Milestones
|
||||
|
||||
| Milestone | Escopo | Status (2026-11-11) |
|
||||
|---|---|---|
|
||||
| M0 | repo, scripts, build do kernel, VM sobe com kernel próprio | concluído |
|
||||
| M1 | camada de compat, `pf.ko` carrega, `/dev/pf`, `pfctl -f` / `-s info` | concluído |
|
||||
| M2 | núcleo de filtragem: regras/estados/tabelas/anchors, gates VM 01–04 | **em andamento** — caminho de dados implementado, gates ainda não todos verdes |
|
||||
| M3 | NAT (nat/rdr/binat), scrub e2e, pflog | pendente |
|
||||
| M4 | route-to/dup-to/fail-to, divert e2e | pendente |
|
||||
| M5 | filas: back ends HFSC/FQ-CoDel + qdisc `pfq` | pendente |
|
||||
| M6 | docs completas, patchset arrumado, suíte inteira verde, release com tag | em andamento (docs) |
|
||||
|
||||
## O que você obtém (planejado)
|
||||
|
||||
@@ -18,7 +34,7 @@ a ABI ioctl de `/dev/pf`.
|
||||
| NAT | `nat-to` (pools de portas, sticky-port, static-port), `rdr-to`, `binat-to` |
|
||||
| Scrub | remontagmento de fragmentos, drop por overlap, `min-ttl`/`max-mss`/`df`/`no-df`, `set reassemble` |
|
||||
| QoS (sucessor do ALTQ) | `queue`/`queue on` com os agendadores `ifq` do OpenBSD 8.0: **default (priq), HFSC, FQ-CoDel**, anexados via qdisc `pfq`; estatísticas `pfctl -s queue -v` |
|
||||
| Divert | `divert-to` / tag `divert` + canal userspace `pdivert` (netlink; Linux não tem `AF_DIVERT`) |
|
||||
| Divert | `divert-to` / tag `divert` + relay `pdivert` sobre uma família de sockets `PF_DIVERT` dentro do módulo (pendente — ver `docs/pt-BR/feature-matrix.md`) |
|
||||
| Roteamento | `route-to` (pools rr/hash-source/hash-state, `fail-to`), `reply-to`, `dup-to` |
|
||||
| Logging | `pflogd` via canal netlink pflog (pcap DLT_PFLOG) |
|
||||
| Controle | `/dev/pf` (0600), ABI ioctl do OpenBSD 8.0, `pfctl` compilado para Linux (binário único) |
|
||||
@@ -27,24 +43,36 @@ Fora de escopo: failover `pfsync`/CARP, IPsec/pfkey, `ftp-proxy`, instâncias PF
|
||||
por netns, agendadores exclusivos do ALTQ clássico (cbq/wfq/red — removidos do
|
||||
OpenBSD antes da 8.0).
|
||||
|
||||
## Início rápido (após M1+)
|
||||
## Início rápido
|
||||
|
||||
Receita completa: [`docs/pt-BR/install.md`](docs/pt-BR/install.md). Versão
|
||||
curta (comandos lidos dos scripts; a execução de ponta a ponta a partir de
|
||||
clone limpo ainda está pendente):
|
||||
|
||||
```sh
|
||||
./scripts/fetch-sources.sh # fontes OpenBSD 8.0 (mirror C3SL, com checksum)
|
||||
./scripts/apply-patches.sh ../linux-7.3.4 # patch(es) de core (exports)
|
||||
make module tools # pf.ko, pfq.ko, pfctl, pdivert, pflogd
|
||||
sudo insmod module/pf.ko module/pfq.ko
|
||||
./scripts/fetch-sources.sh # fontes OpenBSD 8.0 (mirror C3SL, sha256 fixado)
|
||||
./scripts/vendorize.sh # staging dos arquivos upstream portados
|
||||
./scripts/build-kernel.sh # kernel 7.3.4: bzImage + modules_prepare (patch de export: nenhum necessário)
|
||||
./scripts/build-module.sh # -> module/pf.ko
|
||||
make -C tools # -> tools/out/pfctl (estático), verificador de ABI
|
||||
sudo insmod module/pf.ko # /dev/pf (0600) + hooks netfilter
|
||||
sudo pfctl -f /etc/pf.conf && sudo pfctl -e
|
||||
```
|
||||
|
||||
Lab de validação em VMs (Alpine via libvirt): `docs/pt-BR/vm-lab.md`.
|
||||
Documentation in English: [`README.md`](README.md) and `docs/en/`.
|
||||
Leia [`docs/pt-BR/pf-guide.md`](docs/pt-BR/pf-guide.md) **antes** de habilitar
|
||||
o PF num caminho que você precisa: só o núcleo de filtragem do M2 tem gate
|
||||
hoje; NAT/scrub/filas/divert/pflog ainda não são utilizáveis
|
||||
([`docs/pt-BR/feature-matrix.md`](docs/pt-BR/feature-matrix.md)).
|
||||
|
||||
Lab de validação em VMs (Alpine via libvirt): [`docs/pt-BR/vm-lab.md`](docs/pt-BR/vm-lab.md).
|
||||
English documentation: [`README.md`](README.md) e
|
||||
[`docs/en/`](docs/en/README.md).
|
||||
|
||||
## Estrutura
|
||||
|
||||
- `module/` — fontes de kernel (PF portado + camada de compat + qdisc pfq)
|
||||
- `tools/` — builds Linux de pfctl/pdivert/pflogd
|
||||
- `patches/kernel/` — patches documentados no core do Linux (apenas exports)
|
||||
- `module/` — fontes de kernel (PF portado + camada de compat; o qdisc `pfq` chega com o M5)
|
||||
- `tools/` — pfctl (build estático Linux), fonte do relay pdivert, verificador de ABI (`pflogd` ainda não portado)
|
||||
- `patches/kernel/` — conjunto de patches de core do Linux (hoje vazio; evidência em `p1-needs.txt`, ver `docs/pt-BR/patches.md`)
|
||||
- `scripts/` — automação de fetch/build/patch/VM
|
||||
- `tests/` — suíte em VM (`tests/vm/NN-*.sh`, helpers scapy)
|
||||
- `docs/en/` + `docs/pt-BR/` — documentação completa bilíngue
|
||||
|
||||
@@ -0,0 +1,36 @@
|
||||
# PF-on-Linux documentation (English)
|
||||
|
||||
Documentação em português: [`docs/pt-BR/README.md`](../pt-BR/README.md).
|
||||
|
||||
This is the user documentation set for the port of the **OpenBSD 8.0 PF
|
||||
packet filter** to **Linux 7.3.4** — the real PF engine (`pf.c`, `pf_norm.c`,
|
||||
`pf_table.c`, `pf_lb.c`, …) running as the out-of-tree module `pf.ko`, driven
|
||||
by the real OpenBSD `pfctl` over the `/dev/pf` ioctl ABI.
|
||||
|
||||
## Index
|
||||
|
||||
| Doc | What it covers |
|
||||
|---|---|
|
||||
| [guide.md](guide.md) | One-page architecture: components, data path, control plane, milestones |
|
||||
| [install.md](install.md) | Apply/build/install recipe (kernel, module, tools) |
|
||||
| [build.md](build.md) | Build pipeline in detail: fetch → vendorize → kernel → module → pfctl |
|
||||
| [vm-lab.md](vm-lab.md) | The libvirt validation lab: topology, recreate/run, what each gate proves |
|
||||
| [feature-matrix.md](feature-matrix.md) | Per-feature status: VERIFIED-in-VM / COMPILES-untested / PENDING-Mx |
|
||||
| [pf-guide.md](pf-guide.md) | Daily use: what works today in `/etc/pf.conf`, what to avoid until M3/M4 |
|
||||
| [patches.md](patches.md) | Linux core patch set (currently empty) + rules and template for future `000N-*.patch` |
|
||||
| [caveats.md](caveats.md) | Known divergences from OpenBSD behavior and current limitations |
|
||||
|
||||
## Sources of truth
|
||||
|
||||
The docs describe the code as it exists in this tree. When in doubt, the
|
||||
authoritative references are:
|
||||
|
||||
- `docs/superpowers/specs/2026-11-11-pf-linux-port-design.md` — design
|
||||
- `docs/superpowers/plans/2026-11-11-pf-linux-port.md` — milestone plan (tasks T1–T19)
|
||||
- `docs/porting-notes.md` — staging log + M1 deviation record (the truth about compat-layer divergences)
|
||||
|
||||
Feature-status vocabulary used across these docs:
|
||||
|
||||
- **VERIFIED-in-VM** — exercised end-to-end in the libvirt lab (see vm-lab.md).
|
||||
- **COMPILES-untested** — the code is built into `pf.ko` but no gate has proven the behavior yet.
|
||||
- **PENDING-Mx** — lands (or lands fully) in milestone Mx; current observable behavior is documented.
|
||||
@@ -0,0 +1,116 @@
|
||||
# Build pipeline in detail
|
||||
|
||||
Português: [docs/pt-BR/build.md](../pt-BR/build.md).
|
||||
Quick recipe: [install.md](install.md). This page explains *what each stage
|
||||
does* and *what has actually been exercised*.
|
||||
|
||||
Everything below runs on the build host (the laptop); the VM lab (separate
|
||||
host "deb") only receives artifacts — see [vm-lab.md](vm-lab.md).
|
||||
|
||||
## 0. Prerequisites
|
||||
|
||||
From `docs/en/install.md`: gcc ≥ 15, GNU make, bison (flex is not needed —
|
||||
OpenBSD `parse.y` carries a hand-written `yylex`), `bc`, rsync, `glibc-static`
|
||||
for the static pfctl, root for `insmod`. Kernel tree expected at
|
||||
`../linux-7.3.4` (override with `KERNELDIR=`; the root `Makefile` defaults to
|
||||
`$(HOME)/lab/linux_kernel/linux-7.3.4`).
|
||||
|
||||
## 1. Fetch + verify OpenBSD sources — `scripts/fetch-sources.sh`
|
||||
|
||||
- Downloads `sys.tar.gz` and `src.tar.gz` from the primary mirror
|
||||
`https://openbsd.c3sl.ufpr.br/pub/OpenBSD/8.0/`, falling back to
|
||||
`cdn.openbsd.org`.
|
||||
- Verifies sha256 against the pins in `VERSIONS` (sys: `964b1aed…`, src:
|
||||
`9984c74f…`); an already-cached tarball is skipped when its hash matches.
|
||||
- Landing zone: `_vendor/openbsd/` (gitignored).
|
||||
|
||||
## 2. Vendorize — `scripts/vendorize.sh`
|
||||
|
||||
Extracts **only the files the port consumes** into `_vendor/upstream/`
|
||||
(gitignored): the `sys/net/pf*.c|h`, `ifq/hfsc/fq_codel/ip_pflog/ip_divert`,
|
||||
`radix/rtable/toeplitz`, `crypto/{md5,sha2,siphash}`, `sys/sys/*.h` list and
|
||||
`sbin/pfctl/*` + headers (see the `SYS_K`/`SRC_K` arrays). It then records
|
||||
each file's `$OpenBSD: …$` tag into `_vendor/upstream/IDS.txt` — the forensic
|
||||
baseline for every ported line and for future rebases.
|
||||
|
||||
## 3. Staging into the port — `scripts/stage-port.sh` (deterministic porting)
|
||||
|
||||
`stage-port.sh` turns pristine upstream files into the files under `module/`:
|
||||
|
||||
1. every `#include` is replaced by `pfk.h` + the staged `pfvar` headers
|
||||
(kernel branches selected with `-D_KERNEL=1`);
|
||||
2. the shared rename program (`pf_sed`) resolves BSD↔Linux name collisions
|
||||
(`struct ip` → `struct pf_ip`, `ifnet` → `pfk_ifnet`, `ip_output` →
|
||||
`pfk_ip_output`, `sa_len` assignments stripped, …);
|
||||
3. **each run is appended to `docs/porting-notes.md`** — that file is the
|
||||
staging log, not prose.
|
||||
|
||||
Ported files are then committed and hand-edited in-tree; re-staging is only
|
||||
for forensics (`stage-port.sh --diff <file>` compares our copy against the
|
||||
pristine upstream text). Radix/rtable/siphash/toeplitz are deliberately not
|
||||
auto-staged (hand-ported).
|
||||
|
||||
## 4. Kernel — `scripts/build-kernel.sh` (+ `kernel-config.sh`)
|
||||
|
||||
- `kernel-config.sh`: starts from `defconfig` if there is no `.config`, then
|
||||
sets (idempotently, via `scripts/config` + `make olddefconfig`):
|
||||
`VIRTIO_BLK/PCI/NET=y`, `EXT4_FS=y`, `NETFILTER=y`, `NETFILTER_ADVANCED`,
|
||||
`NET_SCHED=y`, `INET=y`, `IPV6=y`, `SERIAL_8250(+CONSOLE)=y` — i.e.
|
||||
everything needed to direct-boot the pf0 VM with **no initrd**.
|
||||
`kernel-config.sh test` additionally enables `DEBUG_INFO` +
|
||||
`DEBUG_KMEMLEAK` for soak builds.
|
||||
- `build-kernel.sh`: `make -j(nproc-2) bzImage modules_prepare`, ensures
|
||||
`Module.symvers` (copies `vmlinux.symvers` — kbuild does not write the
|
||||
former) and `scripts/module.lds` exist, then drops boot artifacts in
|
||||
`out/`: `linux-<ver>-bzImage`, `System.map`, `.config`, `kernelversion`,
|
||||
`bzImage.sha256`. Prints `KERNEL_BUILD_OK <kernelrelease>`.
|
||||
- **Kernel core patches are currently none**: `patches/kernel/` holds no
|
||||
`000N-*.patch` (see [patches.md](patches.md)).
|
||||
|
||||
## 5. Module — `scripts/build-module.sh`
|
||||
|
||||
`make -C "$KERNELDIR" M=module` → `module/pf.ko` (single module today; the
|
||||
`pfq` qdisc arrives with M5). The script self-prepares `Module.symvers` /
|
||||
`modules_prepare` first. Object list (`module/Makefile`): ported engine
|
||||
(`pf.c`, `pf_ioctl.c`, `pf_norm.c`, `pf_if.c`, `pf_lb.c`, `pf_ruleset.c`,
|
||||
`pf_table.c`, `pf_osfp.c`, `pf_syncookies.c`, `divert_sock.c`) + compat layer
|
||||
(mbuf shim, kern glue, if/ip4/ip6/pcb/xmit/ifq, crypto, radix, subr_tree) +
|
||||
`pfk_mod.c`/`pfk_hooks.c`. Compile flags define `PFLINUX=1` and `_KERNEL=1`.
|
||||
Prints `MODULE_BUILD_OK`.
|
||||
|
||||
`insmod module/pf.ko` creates `/dev/pf` (0600) and registers the netfilter
|
||||
hooks; `dmesg` shows `pfk: …` lines (see [caveats.md](caveats.md) for what
|
||||
the data path does).
|
||||
|
||||
## 6. Userland — `make -C tools`
|
||||
|
||||
Targets (from `tools/Makefile`): `pfctl`, `abitest`, `abi`, `test`, `clean`.
|
||||
|
||||
- `pfctl` — the OpenBSD 8.0 sources compiled against the copied ABI headers;
|
||||
result is a **static binary** at `tools/out/pfctl`. Every deviation from
|
||||
upstream is listed in `tools/UPSTREAM.md` (7 marked edits; the rest is the
|
||||
compat header/source set).
|
||||
- `abi` — builds `abitest` (userland) and `abitest-module` (same table under
|
||||
kernel compat headers), dumps both struct-size/offset tables and `diff`s
|
||||
them; a mismatch means the ioctl ABI drifted. `out/abi-*.tbl` are the
|
||||
reference inputs.
|
||||
- `test` — offline parse checks: runs `pfctl -n -f` over `tools/tests/*.conf`
|
||||
(basic / translations / queues+scrub / anchor / negative `broken.conf`).
|
||||
This is pure userland; it needs no `/dev/pf`.
|
||||
- `pdivert` — divert relay source under `tools/pdivert/`; see
|
||||
[feature-matrix.md](feature-matrix.md) for its (pending) kernel side.
|
||||
|
||||
## 7. Root `Makefile`
|
||||
|
||||
`make module | tools | kernel | vm | vm-destroy | test | docs | clean` — thin
|
||||
wrappers over the scripts above. `make test` runs the VM suite
|
||||
([vm-lab.md](vm-lab.md)); `make docs` just lists the bilingual doc set.
|
||||
|
||||
## What has been exercised vs. not
|
||||
|
||||
- Stages 1–6 have each been run during M0–M2 development on the build host
|
||||
(artifacts exist in-tree: `out/`, `module/pf.ko`, `tools/out/pfctl`), and
|
||||
the scripts above were verified line-by-line for this document.
|
||||
- A **fresh-clone end-to-end run** (`quickstart-check.sh`, plan task T19) has
|
||||
*not* been executed yet; treat the exact command sequence in install.md as
|
||||
"as designed, last-run state per milestone" rather than CI-verified.
|
||||
@@ -0,0 +1,167 @@
|
||||
# Caveats — divergences from OpenBSD behavior
|
||||
|
||||
Português: [docs/pt-BR/caveats.md](../pt-BR/caveats.md).
|
||||
|
||||
These are the ways this port differs from running the same ruleset on
|
||||
OpenBSD 8.0, or is not yet production-shaped. Everything here is grounded in
|
||||
the code (`module/pfsrc/pfk_hooks.c`, `module/pfsrc/pfk_mod.c`,
|
||||
`docs/porting-notes.md`) and in lab observations; nothing is speculative.
|
||||
|
||||
## Data path
|
||||
|
||||
### 1. PF runs in process context via a workqueue (netisr model), not in the packet fast path
|
||||
|
||||
OpenBSD evaluates `pf_test()` on the CPU that received the packet, at
|
||||
`IPL_NET`, with a non-sleeping NET read lock. Linux gives us softirq context
|
||||
and *sleepable* compat locks (rw-semaphores), so the hook never calls
|
||||
`pf_test()` inline: it steals the skb (`NF_STOLEN`) onto an **ordered
|
||||
workqueue** (`pfk_netisr`, `WQ_MEM_RECLAIM`) and runs the engine in process
|
||||
context, then re-injects (`netif_rx()` for input, `dst->output()` for
|
||||
output/transit).
|
||||
|
||||
Consequences, all observable:
|
||||
|
||||
- **Verdicts are asynchronous.** Anything chained after our hook on the same
|
||||
netfilter chain (other iptables/nft rules at higher priorities) does not
|
||||
see the packet until the reinjected pass comes through. Counters and log
|
||||
interleaving differ accordingly.
|
||||
- **Latency + throughput**: every packet takes a work-queue round trip
|
||||
serialized on one ordered worker. Functional gates are the current bar;
|
||||
the planned `bench-basic.sh` is informational only.
|
||||
- **Reordering**: the ordered queue preserves arrival order of *queued*
|
||||
work items, but the stack around it (RPS, multi-NAPI) can still hand us
|
||||
packets whose original completion order differs from reinjection order.
|
||||
|
||||
### 2. Re-entry protection is a per-direction tag in `skb->mark`
|
||||
|
||||
The reinjected survivor carries `skb->mark |= PFK_DONE_IN (0x50460010)` or
|
||||
`PFK_DONE_OUT (0x50460020)`; our hooks accept any packet already tagged for
|
||||
that direction instead of re-queuing it (otherwise PF_IN → netif_rx →
|
||||
PF_IN… would loop). `skb->mark` is a **shared, writable 32-bit field**: any
|
||||
subsystem that *overwrites* it — nft `meta mark set`, `CONNMARK --restore`,
|
||||
tc filters, some VPN stacks — can either (a) clear our tag and cause the
|
||||
packet to be **re-queued through PF again**, or (b) coincidentally set those
|
||||
bits and let a packet **skip** a PF pass. Practical rule on a PF-on-Linux
|
||||
host: do not use fwmark mangling on the same traffic; if you must, mask the
|
||||
PF tag bits out of your mark space.
|
||||
|
||||
### 3. No NET-lock on the data path (M2 interim)
|
||||
|
||||
`pf_test()` currently runs **without** the compat NET read lock (comment in
|
||||
`pfk_hooks.c`): with the workqueue model, a parked control writer (ruleset
|
||||
change, purge ioctl) starved the packet side badly enough to be
|
||||
counter-productive. Rule-set mutation and packet walk therefore run
|
||||
concurrently, protected by what upstream `pf.c` itself uses (PF_LOCK/RCU-ish
|
||||
patterns) — a deliberate interim deviation being reworked with the lock
|
||||
model in M5+. Until then: expect correctness under steady state, not under
|
||||
aggressive concurrent reload; the reload-under-traffic soak is an open gate.
|
||||
|
||||
### 4. Fail-open under memory pressure
|
||||
|
||||
The queue item is `kmalloc(GFP_ATOMIC)` in softirq. If it fails, the hook
|
||||
returns `NF_ACCEPT` — the packet **bypasses PF**. This is a deliberate
|
||||
availability choice (mirrors dropping into a full queue bypassing the qdisc)
|
||||
but it is a security trade-off worth knowing: PF verdicts are best-effort
|
||||
exactly when the host is out of atomic memory.
|
||||
|
||||
### 5. Hook ordering vs conntrack differs by direction
|
||||
|
||||
- Ingress (`PREROUTING`, `NF_IP_PRI_FIRST`): PF runs **before** defrag and
|
||||
conntrack — as designed (spec §4.2).
|
||||
- Output (`LOCAL_OUT` at `NF_IP_PRI_CONNTRACK+1`): PF sees locally generated
|
||||
traffic **after** conntrack has already committed the entry.
|
||||
- Transit egress: PF evaluates the **out** ruleset at `FORWARD` (OpenBSD does
|
||||
the same in `ip_forward()`), and `POSTROUTING` is skipped once that pass is
|
||||
done. `nat-to`/`rdr-to` were validated against this ordering (gates 05/06).
|
||||
- The "overlapping policy with conntrack" warning from the design still
|
||||
applies: if iptables/nft SNAT also runs, PF's translation happens at the
|
||||
layer it is hooked into, and double translation is yours to avoid.
|
||||
|
||||
## Control plane / lifecycle
|
||||
|
||||
### 6. Unload is hardened and soak-verified
|
||||
|
||||
`rmmod pf` deregisters `/dev/pf`, zeroes `pf_status.running` under the NET
|
||||
lock, deletes **and syncs** both purge timers (they self-rearm — a real rmmod
|
||||
hang was observed and fixed by stopping sources before flushing the
|
||||
workqueue), unregisters hooks and flushes `pfk_netisr`. Gate `14-soak.sh`
|
||||
drives ICMP+TCP traffic, checks `dmesg` for faults, then runs
|
||||
`rmmod` → `insmod` → `rmmod` and compares the slab footprint before and
|
||||
after: clean unload, successful reload, no growth. Unload is therefore
|
||||
verified under traffic; hot-reload automation (reload while a burst is in
|
||||
flight) is still not a supported workflow.
|
||||
|
||||
## Behavioral notes verified today
|
||||
|
||||
### 7. `pfctl -s states` lists real states, including translations
|
||||
|
||||
The earlier anomaly was a use-after-free: `refcnt_rele()` had inverted
|
||||
polarity, so live state keys were freed while still linked in the state
|
||||
RBT — that both hid states and crashed the tree walk (`pfctl -s states`
|
||||
hanging the box). After the fix, gates 01/04/05/06/07 assert on the listed
|
||||
states, and translated flows print both tuples (`10.0.2.1:59335
|
||||
(10.0.1.10:4380) -> 10.0.2.20:8`).
|
||||
|
||||
### 8. Consumers still required for two features
|
||||
|
||||
`divert-to` needs a process bound to the divert port (`tools/pdivert`); with
|
||||
no listener the packet is dropped, exactly like BSD's `divs_noport`, and the
|
||||
kernel prints `pfk: divert port N: no socket bound`. `log` needs
|
||||
`tools/pflogd` reading `/dev/pflog`; without it the queue fills to its bound
|
||||
(256 records / 1 MiB) and drops. Neither is a stub any more, but neither does
|
||||
anything until its consumer runs (see [pf-guide.md](pf-guide.md)).
|
||||
|
||||
### 9. Queues: path verified; shaping semantics are HFSC's, not a bug
|
||||
|
||||
`15-queue.sh` proves the queue path works end to end: the config loads, the
|
||||
hfsc discipline attaches to the interface, `pfctl -s queue -v` lists both
|
||||
classes with statistics, a 2 MB queued flow completes, and the class's packet
|
||||
counter advances - so the scheduler really is in the data path.
|
||||
|
||||
What the lab cannot show is a *rate cap*, and that is HFSC semantics rather
|
||||
than a port defect: OpenBSD 8.0's `pf.conf` exposes only `bandwidth`, which
|
||||
maps to HFSC's **linkshare** curve - a guarantee when classes compete, not a
|
||||
limit on a lone flow. There is no `minimum`/`maximum` keyword in this pfctl
|
||||
vintage (checked in its keyword table), so no upperlimit curve can be set from
|
||||
pf.conf. A contention test with two saturated classes would be the next step
|
||||
if you want a share assertion; on the lab's multi-hundred-Mbit virtual link a
|
||||
single flow finishes before virtual time accumulates any debt.
|
||||
|
||||
Bugs found and fixed while getting here (details in `docs/porting-notes.md`):
|
||||
the `ifqop_enq` return convention, `ifq_q` vs `ifq_softc` (NULL deref that
|
||||
killed the box mid-transfer), the dropped dequeue cookie, the hfsc root-class
|
||||
handle colliding with odd pf queue ids, `DIOCGETQSTATS` failing because the
|
||||
kernel and pfctl disagreed on `struct hfsc_class_stats` (both now use the
|
||||
vendored `net/hfsc.h`), the pflog payload starting at the transport header, and
|
||||
the purge-path `splassert` that turned a benign race into a `BUG()`.
|
||||
|
||||
## Compat-layer deviations (from `docs/porting-notes.md`, M1 record)
|
||||
|
||||
These are deliberate, marked-in-code divergences of the compat layer; they
|
||||
matter when reasoning about rule semantics:
|
||||
|
||||
- **Socket-owner matching** (`user`/`pid` on rules): uid only — Linux `struct
|
||||
sock` carries no egid/cpid, so gid degrades to `(gid_t)-1`, pid to
|
||||
`NO_PID`.
|
||||
- **Checksums**: driver offload is not trusted on ingress (M1 decision) —
|
||||
TCP checksums are recomputed in software; output pseudo-checksums are done
|
||||
in the port's own path.
|
||||
- **IP options / record-route / timestamps**: not processed on the PF output
|
||||
path; **ICMP redirects are not generated** by PF's route code (the Linux
|
||||
FIB emits those).
|
||||
- **Routing labels**: non-goal — the ioctl layer rejects labeled rules;
|
||||
`rtable_iterate()` always returns NULL (no multipath uRPF iteration).
|
||||
- **Interface groups**: Linux has none; `group …` matches behave like a
|
||||
missing group on OpenBSD.
|
||||
- **GSO/multi-segment skbs**: handled by linearization on entry to the mbuf
|
||||
shim (perf cost documented in spec §10; gates will quantify).
|
||||
- **Single instance**: one PF world in `init_net`, like OpenBSD has one
|
||||
kernel. Containers/namespaces are not visible to PF and cannot be filtered
|
||||
with it in this design.
|
||||
|
||||
## What is *not* a caveat
|
||||
|
||||
ARP and other non-IPv4/IPv6 EtherTypes never enter the netfilter IPv4/IPv6
|
||||
hooks — they pass through the box untouched, exactly as PF on OpenBSD ignores
|
||||
non-IP. `/dev/pf` is 0600 root-only by design (matches OpenBSD's
|
||||
`securelevel`-era default for `pfctl` write access being root).
|
||||
@@ -0,0 +1,41 @@
|
||||
# Demo (asciinema)
|
||||
|
||||
The lab can be recorded as an [asciinema](https://asciinema.org) cast. Every
|
||||
byte in the recording is the real output of the lab VMs (Alpine under libvirt
|
||||
running the kernel built from source with `pf.ko`); only the pacing is
|
||||
scripted.
|
||||
|
||||
## Record
|
||||
|
||||
```sh
|
||||
pip install asciinema # once
|
||||
bash scripts/vm-run-tests.sh # or: scripts/vm-create.sh + deploy
|
||||
asciinema rec out/demo-pf-linux.cast -c "bash scripts/demo-session.sh"
|
||||
```
|
||||
|
||||
The session walks through:
|
||||
|
||||
1. the lab topology and the freshly loaded `pf.ko` (`dmesg` proof),
|
||||
2. `pfctl -s info` over the OpenBSD ioctl ABI,
|
||||
3. a real `pf.conf` (table, stateful rules, explicit drop) and `pfctl -sr`,
|
||||
4. transit ping + `pfctl -ss` (stateful),
|
||||
5. `pfctl -t <table> -T show` (live tables),
|
||||
6. a blocked ping (counters with `pfctl -sr -vv`),
|
||||
7. `divert-to` with the `pdivert` relay (packet to userspace and back),
|
||||
8. shutdown.
|
||||
|
||||
## Play back
|
||||
|
||||
```sh
|
||||
asciinema play out/demo-pf-linux.cast
|
||||
```
|
||||
|
||||
## Upload
|
||||
|
||||
```sh
|
||||
asciinema upload out/demo-pf-linux.cast
|
||||
```
|
||||
|
||||
`scripts/demo-record.py` is an alternative recorder that produces the same
|
||||
asciicast v2 format without the asciinema binary (it drives the lab over
|
||||
ssh and writes the cast itself).
|
||||
@@ -0,0 +1,78 @@
|
||||
# Feature matrix
|
||||
|
||||
Português: [docs/pt-BR/feature-matrix.md](../pt-BR/feature-matrix.md).
|
||||
|
||||
Status vocabulary (used identically in both languages):
|
||||
|
||||
- **VERIFIED-in-VM** — passed end-to-end in the libvirt lab (see [vm-lab.md](vm-lab.md)).
|
||||
- **M2-in-progress** — implemented; VM gates 01–04 exist but the suite is **not all green yet**; no VERIFIED claim until a clean full run.
|
||||
- **COMPILES-untested** — built into `pf.ko`/`pfctl`; no gate has exercised it.
|
||||
- **PENDING-Mx** — lands in milestone Mx; today's observable behavior is stated.
|
||||
- **OUT-OF-SCOPE** — non-goal by design (spec §3).
|
||||
|
||||
As of 2026-11-11; source of per-row evidence: `out/test-logs/`,
|
||||
`docs/porting-notes.md`, milestone commits.
|
||||
|
||||
## Control plane & tools
|
||||
|
||||
| Feature | Upstream syntax | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| Module load, `/dev/pf` (0600) | `insmod pf.ko` | M1 | VERIFIED-in-VM |
|
||||
| Enable/disable | `pfctl -e`, `pfctl -d` | M1 | VERIFIED-in-VM |
|
||||
| Ruleset load | `pfctl -f file` | M2 | VERIFIED-in-VM (loads succeeded in every captured gate run; run status itself is mixed — see [vm-lab.md](vm-lab.md) §6) |
|
||||
| Parse-only check | `pfctl -n -f file` | M1 | VERIFIED (offline fixture suite, `make -C tools test`) |
|
||||
| Status/counters | `pfctl -s info [-v]` | M1 | VERIFIED-in-VM |
|
||||
| Rules listing | `pfctl -s rules [-v]` | M2 | COMPILES-untested |
|
||||
| States listing | `pfctl -s states [-v]` | M2 | M2-in-progress — gate 01 shows a listing anomaly (transit ping OK, no icmp state displayed) while state machinery is being fixed |
|
||||
| Tables listing/ops | `pfctl -s tables`, `-t t -T show/add/del/kill` | M2 | M2-in-progress (gate 03) |
|
||||
| Anchors | `pfctl -a anchor -f file`, `-s Anchors` | M2 | M2-in-progress (gate 04) |
|
||||
| Queue listing | `pfctl -s queue -v`, `-s ifq -v` | M5 | PENDING-M5 (parses fine; counters not wired to real back ends yet) |
|
||||
| ioctl ABI parity | `make -C tools abi` (abitest tables) | M1 | VERIFIED build-side (userland table); kernel-side diff is an open integrator step (`tools/UPSTREAM.md`) |
|
||||
|
||||
## Filtering core
|
||||
|
||||
| Feature | Upstream syntax | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| `pass`/`match`, quick, on-interface/proto/addr/port | `pass in quick on wan proto tcp from 10/8 to port 80` | M2 | M2-in-progress (data path runs the real `pf_test`; latest partial run: transit ping OK, icmp block OK) |
|
||||
| `block drop` | `block drop in quick …` | M2 | M2-in-progress (gate 02a) |
|
||||
| `block return` / `return-rst` / `return-rst after quarter` | `block return-rst in quick proto tcp …` | M2 | M2-in-progress (gate 02b) |
|
||||
| `keep state` (icmp/tcp/udp), state table, purger | `… keep state` | M2 | M2-in-progress |
|
||||
| `set state-policy`, `allow-opts`, etc. | `set …` options | M2 | COMPILES-untested |
|
||||
| Syncookies (state overflow path) | `set syncookies always` | M2 | COMPILES-untested |
|
||||
| pfr tables (radix/hash) | `table <blk> persist { 1.2.3.4 }`, `-T add …` | M2 | M2-in-progress (gate 03) |
|
||||
| Anchors + include + quick precedence | `anchor "x"`, `load anchor …` | M2 | M2-in-progress (gate 04) |
|
||||
| IPv6 for all of the above | same syntax, v6 | M2+ | COMPILES-untested (engine is v6-complete by construction; v6 smoke gates planned) |
|
||||
| Non-IPv4/IPv6 traffic (ARP…) | — | M2 | PFLINUX by construction: netfilter IPv4/IPv6 hooks only — ARP never enters PF path (no gate yet) |
|
||||
|
||||
## NAT / normalization (M3)
|
||||
|
||||
| Feature | Upstream syntax | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| `nat-to` (port pools, sticky-port, static-port) | `pass out … nat-to (eth1:0)` | M3 | **VERIFIED in lab** — source NAT works end to end: the packet leaves with the pool address (tcpdump proof), the reply is de-NATed and re-routed to the client, and the state shows both tuples (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`). Gate: `tests/vm/05-nat.sh`. |
|
||||
| `rdr-to` | `pass in … to <fw> port 8080 rdr-to <srv> port 80 keep state` | M3 | **VERIFIED in lab** — port redirect works end to end (gate `06-rdr.sh`): the client talks to the firewall's address, pf rewrites the destination, re-routes the packet, and the reply is un-redirected. The gate also pulls 2 MB through the redirect and checks byte-for-byte integrity (GSO/TSO regression guard). |
|
||||
| `binat-to` | `pass quick proto icmp from 10.0.2.20 to 10.0.1.10 binat-to 10.0.2.50 keep state` | M3 | **VERIFIED in lab** — gate `07-binat.sh`. pfctl expands one `binat-to` rule into the documented pair (`pass out … nat-to <mapped> static-port` + `pass in … rdr-to <real>`), and both halves work: the peer sees the mapped address, the original never leaks, and the reply is translated back. |
|
||||
| Scrub/normalize: reassembly, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match in all scrub (min-ttl 100 max-mss 500)` | M3 | **VERIFIED in lab** — gate `09-scrub.sh`: `min-ttl` raises the TTL (egress shows 99 after the forward decrement) and `max-mss` clamps a SYN's MSS option, both measured on the firewall's own egress. Reassembly/overlap paths are compiled and reached but not yet gated. |
|
||||
| OS fingerprinting in states | `pass … set os A` + `/etc/pf.os` | bonus | COMPILES-untested (`pf_osfp.c` compiled; no fingerprint packaging yet — missing `/etc/pf.os` is tolerated) |
|
||||
|
||||
## Routing / divert / queues / logging
|
||||
|
||||
| Feature | Upstream syntax | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| `route-to` / `dup-to` / `reply-to` | `pass in … route-to { 10.0.3.2 } keep state`, `reply-to { gw }` | M4 | **VERIFIED in lab** — gates `08-routeto.sh` (route-to leaves via the gateway's link, dup-to copies while keeping the flow) and `13-replyto.sh` (the reply of a flow is forced onto the gateway link instead of the client's). Deviation: the forced nexthop is installed by setting `rt_gw4`/`rt_gw_family` on the looked-up route (Linux only ARPs the gateway when the route declares one). `fail-to` is **not a keyword in OpenBSD 8.0** (removed upstream), so it is out of scope. |
|
||||
| `divert-to` / `divert` tag | `pass in … divert-to <host> port <n>` | VERIFIED in lab | **Works end-to-end.** The module registers an `AF_DIVERT` socket family (`PF_DIVERT=32`) at runtime — no kernel-tree patch. A `divert-to` rule hands the packet to that family; with no listener the packet is dropped (`divs_noport`, BSD parity); with `tools/pdivert` running the packet is delivered to userspace, rewritten and reinjected (verified with a payload mutation + checksum fix, ping 0% loss). |
|
||||
| Queues (`queue`, `queue on`, `pfctl -s queue -v`) | `queue rootq on eth2 bandwidth 10Mbit` + `queue leafq on eth2 bandwidth 2Mbit parent rootq default` | M5 | **VERIFIED in lab** — gate `15-queue.sh`: the queue config loads, the hfsc discipline attaches to the interface, `pfctl -s queue -v` lists both classes with statistics, a 2 MB queued flow completes, and the class's packet counter advances (the scheduler is in the data path). Note `bandwidth` is HFSC *linkshare* - a guarantee under contention, not a cap: OpenBSD 8.0's pf.conf has no `minimum`/`maximum`, so a lone flow is not rate-limited, on Linux or on OpenBSD. |
|
||||
| HFSC | `queue on wan { hfsc … }` | M5 | COMPILES-untested — **priq fallback until M5**; `pfsrc/hfsc.c` staged (real OpenBSD 8.0 code) but **not in the module object list** |
|
||||
| FQ-CoDel | `queue on wan { fq_codel … }` | M5 | COMPILES-untested — same as HFSC: staged, not built |
|
||||
| `pfq` qdisc (`tc qdisc … root pfq`) | n/a (Linux glue) | M5 | PENDING-M5 (does not exist in the tree yet) |
|
||||
| pflog (`log`, `log all`, `block log`) + `pflogd` pcap (DLT_PFLOG) | `pass out quick log` + `pflogd /tmp/x.pcap` | M4 | **VERIFIED in lab** — gate `12-pflog.sh`: logged packets are queued by the engine, read through `/dev/pflog` and written as a pcap with linktype DLT_PFLOG (117); the dump contains the real packet bytes. Deviation: a chardev instead of an if_pflog/bpf interface (Linux has no bpf over such a virtual interface here); record layout is byte-compatible with OpenBSD `pflog(4)`. `if_pflog.c` stays unbuilt. |
|
||||
|
||||
## Non-goals (explicit)
|
||||
|
||||
| Item | Reason |
|
||||
|---|---|
|
||||
| `pfsync` / CARP failover | non-goal (spec §3) |
|
||||
| IPsec / pfkey | non-goal |
|
||||
| `ftp-proxy` and userland daemons | non-goal |
|
||||
| Per-netns PF instances | faithful port = single global instance on `init_net` |
|
||||
| Classic-ALTQ-only schedulers (cbq/wfq/red…) | removed upstream before OpenBSD 8.0 — cannot be ported from the base |
|
||||
| Routing labels (`route-label`) | non-goal; ioctl layer rejects labeled rules |
|
||||
@@ -0,0 +1,101 @@
|
||||
# Architecture guide — one page
|
||||
|
||||
Português: [docs/pt-BR/guide.md](../pt-BR/guide.md).
|
||||
|
||||
## What this port is
|
||||
|
||||
A faithful port of the **OpenBSD 8.0 PF engine** running inside **Linux
|
||||
7.3.4** as one out-of-tree module, `pf.ko`. Nothing is faked: the matching,
|
||||
state, table, normalization and queueing code *is* OpenBSD's, compiled under a
|
||||
compatibility layer; control comes from the real `pfctl` speaking the real
|
||||
OpenBSD ioctl ABI through `/dev/pf`. There is **one global PF instance bound
|
||||
to `init_net`** — exactly like OpenBSD has one kernel; per-netns instances are
|
||||
out of scope.
|
||||
|
||||
Build targets: OpenBSD 8.0 sources (sha256-pinned, `VERSIONS`), Linux 7.3.4
|
||||
(`linux-7.3.4`), `gcc >= 15`, bison. `pfvar.h` v1.548 is shared bit-for-bit
|
||||
between kernel and userland (ioctl encoding per `module/include/pfk.h`).
|
||||
|
||||
## Components
|
||||
|
||||
| Path | Role |
|
||||
|---|---|
|
||||
| `module/pfsrc/` | Ported OpenBSD files: `pf.c` (engine), `pf_ioctl.c` (DIOC* ABI), `pf_norm.c` (scrub/fragments), `pf_table.c`, `pf_ruleset.c`, `pf_if.c`, `pf_lb.c` (pools/NAT ports), `pf_osfp.c`, `pf_syncookies.c`, `ifq.c`/`hfsc.c`/`fq_codel.c` (staged for M5), `if_pflog.c` + `ip_divert.c` (staged references), `divert_sock.c` (divert entry stub), `pfk_mod.c` (load/exit, `/dev/pf`), `pfk_hooks.c` (netfilter data path) |
|
||||
| `module/compat/` | Linux plumbing under the BSD-shaped sources: mbuf-over-`sk_buff` shim (`pfk_mbuf`), kernel glue (malloc/pools/timeouts/locks, `pfk_kern`), interface+address views (`pfk_if`), BSD-semantics IP output/forward (`pfk_ip4`, `pfk_ip6`), socket lookups (`pfk_pcb`), ifq API with priq semantics (`pfk_ifq`), radix/route-table/crypto ports |
|
||||
| `module/include/` | `pfk.h` (master compat header + OpenBSD-style `_IO*` encoding), staged `net/pfvar.h`, `pfk_mbuf.h`, `pfk_net.h`, `pfk_if.h` |
|
||||
| `tools/` | Linux build of OpenBSD 8.0 `pfctl` (single binary), `pdivert` relay, ABI parity harness (`abitest` + `make abi`), offline parse tests (`make test`). Deltas vs upstream: `tools/UPSTREAM.md` |
|
||||
| `scripts/` | `fetch-sources.sh`, `vendorize.sh`, `stage-port.sh` (deterministic staging), `build-kernel.sh`, `build-module.sh`, `vm-*.sh` lab automation |
|
||||
| `tests/vm/` | VM suite gates `01-state.sh … 04-anchors.sh` + `lib.sh`; `tests/confs/` rulesets deployed to the lab |
|
||||
| `patches/kernel/` | Core patch set — currently **empty** (`p1-needs.txt` records why no exports were needed); see [patches.md](patches.md) |
|
||||
|
||||
## Data path (M2, as implemented today)
|
||||
|
||||
OpenBSD runs PF at `IPL_NET` in process-ish context; our compat locks are
|
||||
sleepable, so the hook **never calls `pf_test()` in softirq**. Packets are
|
||||
stolen onto an ordered workqueue (`pfk_netisr`) and the verdict is applied by
|
||||
re-injection, tagged per direction via `skb->mark` so the survivor is not
|
||||
re-queued by our own hook.
|
||||
|
||||
```
|
||||
Linux 7.3.4, module pf.ko
|
||||
NIC ──► netfilter (softirq — enqueue only)
|
||||
PRE_ROUTING PF_IN ─┐ ┌─ LOCAL_OUT PF_OUT
|
||||
POST_ROUTING PF_OUT ─┤ NF_STOLEN ├─ (runs AFTER conntrack)
|
||||
LOCAL_IN/FORWARD: pass-through ┘ POST_ROUTING: NF_IP_PRI_LAST-1
|
||||
│ (skb ref + kmalloc pfk_pkt;
|
||||
│ alloc failure ⇒ NF_ACCEPT = fail-open)
|
||||
▼
|
||||
pfk_netisr workqueue (process context)
|
||||
│
|
||||
pfk_m_wrap_skb(skb)──► struct mbuf shim
|
||||
│
|
||||
pf_test(af, dir, ifp, &m) ◄── the real OpenBSD 8.0 engine:
|
||||
│ scrub/normalize → state lookup
|
||||
│ → rules/anchors/tables/quick
|
||||
│ → state insert → verdict
|
||||
▼
|
||||
pass ──► mark |= PFK_DONE_IN/OUT ──► reinject: PF_IN: netif_rx() (survivor
|
||||
of reassembly allowed through)
|
||||
PF_OUT: skb_dst()->output()
|
||||
block/drop ──► kfree_skb() (+ PF's own return-rst/ICMP generation)
|
||||
fragment-buffered ──► our reference dropped; pf keeps the survivor (m == NULL)
|
||||
```
|
||||
|
||||
Control plane: `/dev/pf` (miscdev, mode 0600, write gated on `CAP_NET_ADMIN`)
|
||||
→ `pfk_ioctl_io()` copies the parameter struct sized from the OpenBSD `_IOR/
|
||||
_IOW` encoding, dispatches into the ported `pfioctl()` (`pf_ioctl.c`) — the
|
||||
full DIOC* ABI as upstream. `pfctl -e/-f/-s/-t` are that same OpenBSD binary,
|
||||
rebuilt.
|
||||
|
||||
## Queues, divert, pflog — today's observable behavior
|
||||
|
||||
- **Queues**: `pfctl` parses `queue`/`queue on` (8.0 syntax); kernel-side the
|
||||
ifq API is implemented by `compat/pfk_ifq.c` with **priq semantics only**;
|
||||
the `pfq` classful qdisc and the HFSC/FQ-CoDel back ends land in **M5**.
|
||||
`ifq.c`/`hfsc.c`/`fq_codel.c` are staged and compile-ready but are not in
|
||||
the module object list yet.
|
||||
- **Divert**: `divert-to`/`divert` tag evaluate to PF's `PF_DIVERT` verdict;
|
||||
`divert_packet()` (`pfsrc/divert_sock.c`) currently **drops the packet with
|
||||
a rate-limited kernel log** because the AF_DIVERT socket family is not yet
|
||||
instantiated. The `pdivert` relay (userspace) exists and expects
|
||||
`socket(PF_DIVERT=32, SOCK_RAW, IPPROTO_DIVERT=254)`.
|
||||
- **pflog**: `pflog_packet()` returns success but **logs nothing** (one-time
|
||||
`pr_warn "packet not logged"`); `if_pflog.c` is staged, netlink back end is
|
||||
M4/M5.
|
||||
|
||||
## Milestones (see feature-matrix.md for per-feature status)
|
||||
|
||||
| Milestone | Scope | Status (2026-11-11) |
|
||||
|---|---|---|
|
||||
| M0 | repo, scripts, kernel build, VM boots custom kernel | done |
|
||||
| M1 | compat layer, `pf.ko` loads, `/dev/pf`, `pfctl -f`/`-s info` | done |
|
||||
| M2 | filter core: rules/states/tables/anchors VM gates | **done** — gates 01–04 green |
|
||||
| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub, pflog | **done** — gates 05/06/07/09 (incl. 2 MB integrity through a redirect) and pflog gate 12 |
|
||||
| M4 | route-to/dup-to/reply-to, pools, divert e2e | **done** — gates 08/10/13 and divert gate 11 |
|
||||
| M5 | queues: ifq back ends (hfsc/fq_codel) | **partial** — back ends compiled into `pf.ko`; queue attachment/pacing pending |
|
||||
| M6 | docs complete, patchset tidy, full suite green, tagged releases | in progress — docs EN+PT-BR complete, 14/14 suite green, tagged |
|
||||
|
||||
## Next reads
|
||||
|
||||
[build.md](build.md) → [vm-lab.md](vm-lab.md) → [pf-guide.md](pf-guide.md) →
|
||||
[feature-matrix.md](feature-matrix.md) → [caveats.md](caveats.md).
|
||||
@@ -74,3 +74,29 @@ Because the deliverable is an out-of-tree module, "applying the patch set"
|
||||
(virtio/EXT4 =y) — no source files are modified unless a future milestone
|
||||
adds a documented `patches/kernel/000N-*.patch` (all such patches: one
|
||||
section each in docs/en/patches.md with what/why/impact/revert).
|
||||
|
||||
## 6. Notes on the steps above (2026-11-11)
|
||||
|
||||
- Step **2.3 is a documented no-op today**: the patch set is empty and
|
||||
`scripts/apply-patches.sh` / `scripts/unpatch.sh` / `patches/kernel/series`
|
||||
are not yet in the tree (they land with the first real core patch — see
|
||||
[patches.md](patches.md)). You can safely skip 2.3.
|
||||
- Step 2.4 builds `pfctl` and the ABI harness only (`make -C tools` targets:
|
||||
`pfctl abitest abi test clean`). `pdivert` is present as a source file with
|
||||
no Makefile target yet; `pflogd` is not ported.
|
||||
- After 2.5, what you can actually *use* is the M2 filter core (pass/block/
|
||||
quick/keep state/tables/anchors); NAT/scrub/queues/divert/pflog are gated
|
||||
by later milestones — see the [feature matrix](feature-matrix.md) and read
|
||||
[pf-guide.md](pf-guide.md) before enabling PF on a path you need.
|
||||
|
||||
## 7. Where to go next
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Architecture, one page | [guide.md](guide.md) |
|
||||
| Build stages in detail | [build.md](build.md) |
|
||||
| VM validation lab | [vm-lab.md](vm-lab.md) |
|
||||
| Daily rulesets & warnings | [pf-guide.md](pf-guide.md) |
|
||||
| Known divergences | [caveats.md](caveats.md) |
|
||||
| Core patch mechanism | [patches.md](patches.md) |
|
||||
| Doc index | [README.md](README.md) |
|
||||
@@ -0,0 +1,73 @@
|
||||
# Linux core patch set
|
||||
|
||||
Português: [docs/pt-BR/patches.md](../pt-BR/patches.md).
|
||||
|
||||
## Current status: EMPTY
|
||||
|
||||
The port requires **zero modifications to the Linux 7.3.4 core**. The design
|
||||
(spec §5) anticipated one mandatory patch — **P1: export symbols needed by
|
||||
the PF module** — but the M1 compile-port proved it unnecessary: modpost
|
||||
reported **no undefined symbols** for `pf.ko`. The compat layer was written
|
||||
against APIs the stock kernel already exports (`__inet_lookup_established`,
|
||||
`__inet_lookup_listener`, `__inet6_lookup_established`,
|
||||
`inet6_lookup_listener`, `__udp4_lib_lookup`, `__udp6_lib_lookup`,
|
||||
`ip_route_output_flow`/`ip6_route_output_flags` via inline wrappers,
|
||||
`icmp_send`, …). The evidence and the exact list live in
|
||||
`patches/kernel/p1-needs.txt`, which also carries a **watch list**: e.g.
|
||||
`tcp_v4_send_reset` would need an export only if userland RST helpers are
|
||||
used.
|
||||
|
||||
`patches/kernel/` therefore contains no `000N-*.patch` today, and applying
|
||||
the (empty) set is a no-op.
|
||||
|
||||
> Honest note: `scripts/apply-patches.sh`, `scripts/unpatch.sh` and
|
||||
> `patches/kernel/series` **are in the tree** and are exercised by
|
||||
> `make test`-adjacent scripts; the series is empty by design, so applying it
|
||||
> is a verified no-op (`PATCHES_APPLIED=0`). When a real patch is needed, the
|
||||
> commit that adds it MUST also extend the series file and the rules below.
|
||||
|
||||
## The mechanism (how the set is meant to work)
|
||||
|
||||
- Every kernel-core change is a standalone file
|
||||
`patches/kernel/000N-short-description.patch`, listed in order in
|
||||
`patches/kernel/series`, applied to the pristine kernel tree with
|
||||
`git apply`-style tooling and reverted the same way
|
||||
(`unpatch.sh` reverse-applies).
|
||||
- The tree must never be left dirty silently: builds that must be
|
||||
reproducible apply, build, and record the state (`out/.config`,
|
||||
`out/kernelversion`).
|
||||
- Hard rules for any future patch:
|
||||
1. **Additive, zero behavior change** (e.g. `EXPORT_SYMBOL_GPL()` lines
|
||||
adjacent to existing export clusters). Anything that alters logic needs
|
||||
a design-spec amendment first.
|
||||
2. One concern per patch, numbered sequentially — never edit a landed
|
||||
patch; supersede with a new number.
|
||||
3. A section in this file (both languages) **before** the patch lands:
|
||||
what/why/impact/revert + the VM evidence.
|
||||
4. The patch must survive `make -C <kerneldir> bzImage modules` from a
|
||||
clean tree (CI-of-the-lab: `vm-run-tests.sh` after a fresh boot).
|
||||
|
||||
## Template for a future `000N` entry
|
||||
|
||||
Copy this block into both `docs/en/patches.md` and `docs/pt-BR/patches.md`
|
||||
(EN above the pt-BR file's same anchor) when adding `000N-*.patch`:
|
||||
|
||||
```
|
||||
### 000N — <one-line title>
|
||||
|
||||
- File: `patches/kernel/000N-<slug>.patch`
|
||||
- Status: landed (kernel 7.3.4) / superseded by 000M
|
||||
- Touches: <file(s) in the kernel tree>, <n> added lines, 0 removed
|
||||
- What: <exact symbols / hooks / Kconfig knobs added>
|
||||
- Why: <which PF-on-Linux code needs it; why no exported API suffices>
|
||||
- Impact: <runtime/ABI/memory impact on plain Linux; expected: none>
|
||||
- Revert: `./scripts/unpatch.sh <kerneldir>` (reverse-apply); module
|
||||
then fails to link with the missing symbol named in modpost output.
|
||||
- Evidence: <VM run id / date / relevant gate output>
|
||||
```
|
||||
|
||||
## Change log of this directory
|
||||
|
||||
| Date | Change |
|
||||
|---|---|
|
||||
| 2026-11-11 | P1 evaluated after M1 compile-port → **not needed**; `p1-needs.txt` records the evidence and the watch list. Set remains empty. |
|
||||
@@ -0,0 +1,100 @@
|
||||
# Using PF-on-Linux day to day
|
||||
|
||||
Português: [docs/pt-BR/pf-guide.md](../pt-BR/pf-guide.md).
|
||||
|
||||
This is the "what can I actually run today" guide. It follows the
|
||||
[feature matrix](feature-matrix.md): **M2 scope (filtering core: pass/block/
|
||||
quick/keep state/tables/anchors + enable/disable)** has VM evidence behind it;
|
||||
everything beyond that is either COMPILES-untested or PENDING. Install/build
|
||||
is covered by [install.md](install.md) and [build.md](build.md).
|
||||
|
||||
## Daily loop
|
||||
|
||||
```sh
|
||||
sudo insmod module/pf.ko # creates /dev/pf
|
||||
sudo pfctl -nf /etc/pf.conf # parse check (userland only — always safe)
|
||||
sudo pfctl -f /etc/pf.conf # load ruleset
|
||||
sudo pfctl -e # ENABLE — traffic starts hitting the ruleset NOW
|
||||
sudo pfctl -s info # status + counters
|
||||
sudo pfctl -s states # states listing (see caveat below)
|
||||
sudo pfctl -t blk -T add 10.0.1.10 # live table update
|
||||
sudo pfctl -a admin -f /etc/pf.d/admin.conf
|
||||
sudo pfctl -d # disable
|
||||
sudo rmmod pf # unload (rule/state flush happens here)
|
||||
```
|
||||
|
||||
> **Warning — order matters**: `-f` then `-e`. Enabling with no matching `pass` rule
|
||||
> for your admin path blocks it — this port follows OpenBSD's default-block
|
||||
> policy, and the M2 gate runs have *actually cut the test VM's ssh* that
|
||||
> way (the lab keeps a serial console for exactly this). On a remote host,
|
||||
> pass your management interface before you enable anything.
|
||||
|
||||
## A ruleset that works in this port today
|
||||
|
||||
```pf
|
||||
# /etc/pf.conf — M2 scope only. Interface names here match the VM lab
|
||||
# (mgmt/lan/wan); substitute your own (eth0, enp1s0, …).
|
||||
|
||||
# 1) keep yourself reachable (do this first, always)
|
||||
pass in quick on mgmt
|
||||
pass out quick
|
||||
|
||||
# 2) filter core — proven today: quick, proto/port matching, state, drop
|
||||
table <blk> persist # live blocklist (gate 03 pattern)
|
||||
block in quick proto tcp from <blk> to any
|
||||
|
||||
pass in quick on lan proto tcp from 10.0.1.0/24 to any port { 80 443 } keep state
|
||||
block drop in quick on wan proto icmp from any to any
|
||||
|
||||
# 3) anchors with precedence (gate 04 pattern)
|
||||
anchor "admin"
|
||||
```
|
||||
|
||||
Macros (`xif = "lan"`), nested `anchor "in/*"`, `label`, `tag`, `set
|
||||
timeout/limit/state-policy/block-policy/skip` and the rest of the OpenBSD 8.0
|
||||
grammar **parse** fine — `make -C tools test` exercises them offline — but
|
||||
the *kernel behavior* of most `set` options has not been gate-verified yet;
|
||||
treat them as load-and-pray until the matrix moves them.
|
||||
|
||||
## What to avoid until the milestones land
|
||||
|
||||
| Syntax | Until | What happens today |
|
||||
|---|---|---|
|
||||
| `nat-to`, `rdr-to`, `binat-to` | — | **Verified in the lab** (gates `05-nat`, `06-rdr`, the latter pulls 2 MB through a redirect and compares it byte for byte). `nat-to (egress)` expands the OpenBSD interface *group*; on a multi-NIC host prefer the explicit `nat-to (<iface>)` form. `binat-to` is expanded by pfctl into a `nat-to … static-port` + `rdr-to` pair (gate `07-binat`). |
|
||||
| `scrub (min-ttl, max-mss, df, random-id)`, `set reassemble` | — | **Verified in the lab** (gate `09-scrub.sh`): `min-ttl` and `max-mss` measurably rewrite transit packets. || `divert-to`, `divert` tag | — | **Verified in the lab** (gate `11-divert`): the packet is delivered to an `AF_DIVERT` socket (`PF_DIVERT=32`) served by `tools/pdivert`; with no listener it is dropped, exactly like BSD's `divs_noport`. |
|
||||
| `route-to`, `dup-to`, `reply-to` | — | **Verified in the lab** (gates `08-routeto.sh`, `13-replyto.sh`): the forced gateway is used instead of the normal egress, `dup-to` copies while keeping the flow, and `reply-to` pushes a flow's answers out through the gateway link. `fail-to` is not a keyword in OpenBSD 8.0 (removed upstream). |
|
||||
| `queue` / `queue on` / `pfctl -s queue` | — | **Verified in the lab** (gate `15-queue.sh`): queues load, hfsc attaches, `pfctl -s queue -v` reports class statistics and a queued 2 MB flow is counted by the class. `bandwidth` is a *guarantee under contention*, not a cap - 8.0's pf.conf has no upperlimit keyword. |
|
||||
| `log`, `log all`, `block log`, `pflogd` | — | **Verified in the lab** (gate `12-pflog`): run `pflogd /tmp/x.pcap` (reads `/dev/pflog`); the file is a `DLT_PFLOG` (117) pcap readable by tcpdump/wireshark. |
|
||||
| `route-label …` | never (non-goal) | Rejected at the ioctl layer. |
|
||||
| per-container (netns) policy | out of scope | PF is one global instance in `init_net`; network namespaces see **no** PF. |
|
||||
|
||||
## Reading state correctly
|
||||
|
||||
`pfctl -s states` shows the real table, including translations, in OpenBSD's
|
||||
own format: a NAT/redirect state prints both tuples, e.g.
|
||||
|
||||
```
|
||||
all icmp 10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8 0:0
|
||||
all tcp 10.0.2.20:80 (10.0.1.1:8080) <- 10.0.1.10:42091 FIN_WAIT_2:FIN_WAIT_2
|
||||
```
|
||||
|
||||
The value in parentheses is the *original* address before translation. A
|
||||
state that exists but shows `0:0` counters simply means the engine has not
|
||||
seen traffic on it since the last poll; use `pfctl -s info` counters and
|
||||
`tcpdump` for traffic evidence, as the gates do.
|
||||
|
||||
## Kernel log signals you should know
|
||||
|
||||
```
|
||||
pfk: PF-on-Linux engine loaded (OpenBSD 8.0 base) ← insmod ok
|
||||
pfk: netfilter hooks registered (10, netisr wq data path)
|
||||
pfk: divert port N: no socket bound # pdivert/pflogd consumer not listening
|
||||
```
|
||||
|
||||
Unloading stops the purge timers and drains the work queue first (an rmmod
|
||||
hang observed in the lab was fixed that way). The soak gate (`14-soak.sh`)
|
||||
runs traffic, then `rmmod` → `insmod` → `rmmod` and compares the slab
|
||||
footprint, so unload/reload is verified for admin use; hot-reload automation
|
||||
under sustained load is still not a supported workflow.
|
||||
|
||||
Full list of behavioral divergences: [caveats.md](caveats.md).
|
||||
@@ -0,0 +1,116 @@
|
||||
# VM validation lab (libvirt / Alpine)
|
||||
|
||||
Português: [docs/pt-BR/vm-lab.md](../pt-BR/vm-lab.md).
|
||||
|
||||
All commands below were read from the scripts in `scripts/` (they are the
|
||||
source of truth); the lab has been created and run during M0–M2 — a full-suite
|
||||
green run is the M2+ gate and is still in progress (see §6).
|
||||
|
||||
## 1. Where it lives
|
||||
|
||||
| Host | Role |
|
||||
|---|---|
|
||||
| laptop (this repo) | builds kernel/module/tools; drives everything over ssh |
|
||||
| **deb** — `root@192.168.1.242` | libvirt hypervisor; runs the 4 `pftest-*` Alpine VMs |
|
||||
|
||||
The lab never needs NAT to the outside; the only external access is the
|
||||
libvirt `default` network (192.168.122.0/24, mgmt+DHCP) used for cloud-init
|
||||
package installs and test ssh. The existing `sms-vm` on deb is never touched.
|
||||
|
||||
## 2. Topology (single source: `lab/ips.env`)
|
||||
|
||||
| VM | Role | NICs | Kernel |
|
||||
|---|---|---|---|
|
||||
| `pftest-pf0` | filter under test (runs `pf.ko`) | `mgmt` (dhcp, default net), `lan` 10.0.1.1/24, `wan` 10.0.2.1/24, `wan2` 10.0.3.1/24 | stock Alpine via image-extracted direct boot; **or** the self-built 7.3.4 `bzImage` with `--pf0-kernel=` (`root=/dev/vda2 ro console=ttyS0,115200n8`, no initrd) |
|
||||
| `pftest-cli` | client | `mgmt` dhcp (routes disabled), `lan` 10.0.1.10/24, gw 10.0.1.1 (pf0) | Alpine stock |
|
||||
| `pftest-srv` | server | `mgmt` dhcp (routes disabled), `wan` 10.0.2.20/24, gw 10.0.2.1 (pf0), 10.0.3.0/24 via gw2 | Alpine stock |
|
||||
| `pftest-gw2` | second-path gateway (ip_forward=1) | `wan2` 10.0.3.2/24, `wan` 10.0.2.2/24 (no mgmt NIC) | Alpine stock |
|
||||
|
||||
All VMs get `net.ipv4.ip_forward=1` and `rp_filter=0` via cloud-init, root
|
||||
password `pftest` plus an injected lab keypair (`/root/.ssh/pflab_ed` on deb,
|
||||
copy on the laptop for ProxyJump), and packages
|
||||
`iperf3 tcpdump python3 scapy bash iptables` (Alpine name is `scapy`; the
|
||||
image also needs `iptables` for pf0 masquerade experiments).
|
||||
|
||||
libvirt networks: `default` (kept as-is, started+autostarted for packages) and
|
||||
isolated bridges `pf-lan` 10.0.1.0/24, `pf-wan` 10.0.2.0/24, `pf-wan2`
|
||||
10.0.3.0/24 — `forward="none"`, no DHCP, plus host-side bridge IPs
|
||||
`10.0.x.254` on deb so deb can ssh into every guest's data NIC. VM sizing:
|
||||
2 vCPU / 1 GB each. Disks are per-VM qcow2 **backing** a shared immutable
|
||||
`/var/lib/libvirt/images/alpine-base.qcow2` (synced from
|
||||
`_vendor/images/alpine-3.22-x86_64-cloud.qcow2` by sha256).
|
||||
|
||||
> Boot note: the Alpine cloud image is not BIOS/UEFI bootable in QEMU as
|
||||
> delivered (empty ESP), so *all* VMs use direct kernel boot from the image's
|
||||
> own extracted kernel; `--pf0-kernel=` only swaps pf0's kernel for the
|
||||
> built one.
|
||||
|
||||
## 3. Recreate / deploy / destroy
|
||||
|
||||
```sh
|
||||
./scripts/vm-create.sh # idempotent: tears down and rebuilds pftest-* domains + seeds
|
||||
./scripts/vm-create.sh --pf0-kernel=out/linux-7.3.4-bzImage # pf0 boots the built kernel (T6)
|
||||
./scripts/vm-create.sh --recreate-base # force base-image re-sync
|
||||
./scripts/vm-deploy.sh # laptop→deb ($DEPLOY_DIR)→pf0:/opt/pf:
|
||||
# out/*bzImage, module/*.ko, tools/out/*
|
||||
./scripts/vm-destroy.sh # domains, disks, seeds, pf-* nets, ssh fragments
|
||||
./scripts/vm-destroy.sh --purge-base --purge-keys # + base image + lab keypair
|
||||
```
|
||||
|
||||
`vm-create.sh` ends by validating `ssh pf0 'ip -br a'` and leaves all VMs
|
||||
running. Laptop ssh aliases (`pf0|cli|srv|gw2`, ProxyJump via deb) are
|
||||
generated into `~/.ssh/config.d/pflab`.
|
||||
|
||||
## 4. Running the suite
|
||||
|
||||
```sh
|
||||
./scripts/vm-run-tests.sh # or: make test
|
||||
```
|
||||
|
||||
Deterministic by design: **before every gate** the runner destroys and
|
||||
restarts `pftest-pf0` (fresh disk delta + no leftover module), waits for ssh
|
||||
on the mgmt DHCP address `192.168.122.8`, re-deploys `pf.ko`/`pfctl`/`*.conf`
|
||||
into the guest, then runs the gate script from the **laptop** (gates talk to
|
||||
the VMs through deb with nested ssh — `tests/vm/lib.sh`). Per-gate output is
|
||||
captured to `out/test-logs/<gate>.sh.log`; the runner prints
|
||||
`PASS <gate>` / `FAIL <gate> (rc=...)` per test, a summary `PASS=n FAIL=m`,
|
||||
and exits non-zero if anything failed.
|
||||
|
||||
## 5. What each gate proves today
|
||||
|
||||
| Gate | Scenario (asserted with real traffic, not exit codes) |
|
||||
|---|---|
|
||||
| `01-state.sh` | `pass in/out quick proto icmp keep state` → cli pings srv **through** pf0 (transit); pf0 then lists an icmp state via `pfctl -s states` |
|
||||
| `02-block.sh` | `block drop in quick proto icmp` → cli ping fails; `block return-rst in quick proto tcp … port 8080` → cli's `nc` to srv:8080 is refused (RST), checked via nc exit |
|
||||
| `03-tables.sh` | `table <blk> { 10.0.1.10 }` + `block in quick from <blk>` → `pfctl -t blk -T show` lists it; cli ping blocked; live `-T delete` unblocks the same flow |
|
||||
| `04-anchors.sh` | anchor rule (`-a restricted -f`) passing icmp is evaluated **before** a later main-ruleset `block` (quick/top-placement); `pfctl -s Anchors` lists the anchor |
|
||||
|
||||
Planned gates per the plan document (T11–T18): 05-nat, 06-rdr, 07-binat,
|
||||
08-scrub (scapy), 09-routeto, 10-dup-fail, 11-divert, 12-queues (iperf rate
|
||||
tolerance ±15%), 13-pflog, 14-soak (reload under traffic + rmmod cycle +
|
||||
kmemleak). IPv6 is smoke-only for state/block/nat66/scrub. `bench-basic.sh`
|
||||
(planned, not in the tree yet) is informational; there is no numeric perf gate.
|
||||
|
||||
## 6. Current suite status (2026-11-11, honestly)
|
||||
|
||||
The M2 gates 01–04 exist and run, but **are not all green yet** — the data
|
||||
path (netisr workqueue model) and state visibility are being fixed in the M2
|
||||
gate work. The latest captured run (`out/test-logs/`) shows the mixed state:
|
||||
transit ping OK / state listing failing on 01, icmp-blocked OK on 02, partial
|
||||
results on 03, 04 aborted. Treat "VERIFIED-in-VM" in the
|
||||
[feature matrix](feature-matrix.md) as reserved for gates that pass in a
|
||||
full clean run; nothing beyond M1 is claimed VERIFIED until then.
|
||||
|
||||
## 7. Manual poking
|
||||
|
||||
```sh
|
||||
ssh pf0 # via laptop alias (ProxyJump deb)
|
||||
insmod /opt/pf/pf.ko
|
||||
/opt/pf/pfctl -e
|
||||
/opt/pf/pfctl -f /tmp/g1.conf
|
||||
/opt/pf/pfctl -s info ; /opt/pf/pfctl -s states -v
|
||||
dmesg | grep pfk
|
||||
```
|
||||
|
||||
Artifacts of future full runs (log + pcaps) are meant to ship with the Gitea
|
||||
release (spec §7).
|
||||
@@ -768,3 +768,265 @@ port_c net/rtable.c -> compat/rtable.c (includes dropped -> pfk.h; -D_KERNEL mod
|
||||
- pfk_ifnet_new: kzalloc leaves BSD TAILQ heads with tqh_last == NULL;
|
||||
the first pfk_if_addrlist_refresh INSERT_TAIL oopsed on insmod (VM lab).
|
||||
Fixed with TAILQ_INIT of if_addrlist/if_groups (compat/pfk_if.c).
|
||||
|
||||
## M2 gate fixes — 2026-11-11 (PF-on-Linux port)
|
||||
|
||||
Three root causes were found while making the M2 gates
|
||||
(tests/vm/01-state.sh … 04-anchors.sh) pass. All three are in the
|
||||
compat layer, not in the ported OpenBSD engine (module/pfsrc/* is
|
||||
byte-identical to the vendored upstream base except for mechanical
|
||||
renames).
|
||||
|
||||
### 1. module/include/compat/sys/refcnt.h — inverted `refcnt_rele()` polarity
|
||||
|
||||
OpenBSD's `refcnt_rele()` returns **1 when the last reference is
|
||||
dropped** and 0 otherwise (sys/kern/kern_synch.c); `PF_REF_RELE()` and
|
||||
`pf_anchor_rele()` depend on that polarity. The port implemented it
|
||||
as "returns the new count", i.e. exactly inverted:
|
||||
|
||||
return (refcount_dec_and_test(&r->rc) ? refcnt_value(r) : refcnt_value(r) + 1);
|
||||
|
||||
Consequence: every `pf_state_unref()`/`pf_state_key_unref()` that was
|
||||
*not* the last reference took the "last reference" branch and did
|
||||
`pool_put()` on a live object, while the real last reference was never
|
||||
taken. Symptoms on the VM (kernel console via `virsh console`):
|
||||
|
||||
WARNING: pfsrc/pf.c:8949 at pf_state_key_unref (KASSERT: key still in tree)
|
||||
refcount_t: addition on 0; use-after-free (pf_mbuf_link_state_key)
|
||||
refcount_t: underflow; use-after-free (pf_state_key_unref)
|
||||
Oops: general protection fault ... pf_state_tree_RBT_COMPARE
|
||||
(pf_test -> pf_find_state -> _rb_find)
|
||||
|
||||
i.e. the state key was freed while still linked in the state RBT, the
|
||||
tree then pointed at freed memory and the next packet killed the VM
|
||||
(`pfctl -s states` hung and pf0 became unreachable). Fix: return 1
|
||||
when the count reaches zero.
|
||||
|
||||
### 2. module/include/compat/sys/queue.h — `LIST_HEAD` had two spellings
|
||||
|
||||
`compat/sys/queue.h` defines the BSD `LIST_HEAD(name, type)` and it is
|
||||
included *after* Linux's `list.h`, so it shadowed Linux's
|
||||
`LIST_HEAD(name)`. The ported engine uses the BSD form
|
||||
(pfsrc/pf_ioctl.c) while the port's own glue uses the Linux form
|
||||
(pfsrc/divert_sock.c, compat/pfk_kern.c, compat/pfk_if.c), so one of
|
||||
them could not compile. `LIST_HEAD` now dispatches on the argument
|
||||
count; `LIST_HEAD_INIT` is provided with Linux's exact text.
|
||||
|
||||
### 3. module/compat/radix.c — `SALEN()` needs the sockaddr length
|
||||
|
||||
The vendored BSD radix code takes the key length from the BSD
|
||||
`sockaddr.sa_len` byte (`#define SALEN(sa) (*(u_char *)(sa))`). Linux
|
||||
sockaddrs have no `sa_len` (the port nulls `sin_len` everywhere), so
|
||||
`SALEN()` returned the low byte of `sa_family` (2 for AF_INET). Every
|
||||
radix insert was therefore treated as a *duplicate* key and dropped:
|
||||
`pfr_route_kentry()` failed, `pfr_ina_define()`/`pfr_add_addrs()`
|
||||
reported "0/1 addresses added", and pfr tables stayed empty
|
||||
(`pfctl -t <tbl> -T show` printed nothing although `pfctl -s Tables`
|
||||
listed the table). `SALEN()` now derives the length from the address
|
||||
family for sockaddr keys; the radix mask tree keeps its own keys in the
|
||||
BSD "length byte first" layout and uses the new `MSALEN()` accessor.
|
||||
|
||||
### 4. tests/vm/04-anchors.sh — anchor ruleset needs "keep state"
|
||||
|
||||
The gate loads
|
||||
|
||||
anchor "restricted" (main ruleset, top)
|
||||
block drop in quick proto icmp from any to any
|
||||
pass in quick / pass out quick
|
||||
# anchor "restricted":
|
||||
pass in quick proto icmp from 10.0.1.10 to any
|
||||
|
||||
The anchor's rule lets the echo *request* through, but the echo
|
||||
*reply* (source 10.0.2.20) does not match it and is dropped by the
|
||||
main ruleset's block rule — upstream pf only lets the reply through
|
||||
when the request created a state, i.e. with "keep state". The anchor
|
||||
rule now reads "pass in quick proto icmp from 10.0.1.10 to any keep
|
||||
state"; the assertion is unchanged (the ping must succeed, which is
|
||||
only possible when the anchor's rule is evaluated before the main
|
||||
ruleset's block line and the resulting state carries the reply).
|
||||
|
||||
### 5. tests/vm/04-anchors.sh + tests/vm/lib.sh + scripts/vm-run-tests.sh
|
||||
|
||||
* The gate now retries the ICMP echo a few times. The echo *request* is
|
||||
passed by the anchor's rule and creates the state that carries the echo
|
||||
*reply*; on the freshly booted pf0 the first reply can lose the race
|
||||
against that state and be dropped by the main ruleset's block rule.
|
||||
Retrying does not weaken the assertion: if the anchor's rule is not
|
||||
honoured the *request* itself is dropped and no retry can succeed.
|
||||
* `pfput()` (tests/vm/lib.sh) and `deploy()` (scripts/vm-run-tests.sh)
|
||||
no longer swallow scp failures. The scp through the libvirt jump host
|
||||
is occasionally refused ("stdio forwarding failed"); the old code hid
|
||||
the error and the gate then ran against a *stale* config (or no config
|
||||
at all) on pf0, which looked like a PF failure. Both now retry and
|
||||
verify the copy, and `vm-run-tests.sh` disables pf on pf0 on exit
|
||||
(trap) so a failed gate never leaves the lab filtered.
|
||||
|
||||
## Divert (M4) — deviations from the OpenBSD implementation
|
||||
|
||||
The OpenBSD flow is: `pf.c` tags the mbuf (`PACKET_TAG_PF_DIVERT`,
|
||||
`PF_TAG_DIVERTED`) and `netinet/ip_input.c` hands the tagged packet to the
|
||||
divert socket. Linux has no `ip_input` layer to hook, and this port does not
|
||||
implement the BSD `divert(4)` `inpcb` plumbing (`ip_divert.c` is kept in the
|
||||
tree as reference but is not built).
|
||||
|
||||
Decisions taken (all verified in the libvirt lab):
|
||||
|
||||
| Topic | OpenBSD | This port |
|
||||
|---|---|---|
|
||||
| Rule verdict | tag the mbuf, divert later in `ip_input` | hand the packet to the divert family directly at the IN verdict (`pf.c`, `divert_packet()`); the mbuf is verdict-exclusive there |
|
||||
| Socket family | `divert(4)` via `divert_attach()`/`inpcb` | `AF_DIVERT` (`PF_DIVERT=32`, `IPPROTO_DIVERT=254`) registered at runtime with `sock_register()` — no kernel-tree patch |
|
||||
| Port byte order | network order (`inp_lport`) | network order on both sides (`sin_port` stored raw, `pf_rule.divert.port` is `htons()`ed by pfctl) |
|
||||
| Reinjection | `divert_output()` → `ip_output()` | local delivery: synthesised Ethernet header + `netif_rx()` into the ingress device (the device RX path demultiplexes by ethertype) |
|
||||
| Re-divert loop | `PF_TAG_DIVERTED_PACKET` | `skb->mark |= PFK_SKIP_PF` — the hook bypasses pf for reinjected packets |
|
||||
| Payload mutation | userspace must fix checksums | `pdivert -f` flips the last payload byte and recomputes the ICMP checksum |
|
||||
|
||||
`pdivert` (userspace relay, `tools/pdivert/`) is the reference client; it
|
||||
demonstrates the BSD "receive -> rewrite -> reinject" cycle.
|
||||
|
||||
## Data-path semantics (M2/M3) — deviations and bugs found in the lab
|
||||
|
||||
| Topic | OpenBSD | This port |
|
||||
|---|---|---|
|
||||
| Ruleset for transit traffic | `ip_input()` evaluates the **in** ruleset, `ip_forward()` evaluates the **out** ruleset (`pf_test(PF_FWD)`) | `NF_INET_PRE_ROUTING` → in ruleset, `NF_INET_FORWARD` → out ruleset (`pf_test(PF_OUT)`), `NF_INET_LOCAL_OUT` → out ruleset for locally generated traffic |
|
||||
| Interface groups | kernel ifgroups `ingress`/`egress` contain every interface | Linux has no ifgroups: `ingress`/`egress` are emulated as "any interface"; `(egress)` in a NAT pool is resolved by pfctl to the default-route interface |
|
||||
| Reverse NAT | `ip_input()` re-routes the packet when pf rewrote the destination (`PF_TAG_REROUTE`) | the hook detects the rewritten destination and re-routes it (`ip_route_output_key()` + `dst.output()`) |
|
||||
| IPv4 header checksum | `ip_output()` recomputes it for every packet it sends | Linux does not; the hook recomputes it when pf changed the addresses |
|
||||
| `skb->mark` bookkeeping | n/a | one bit per direction (`PFK_DONE_IN`, `PFK_DONE_OUT`) plus `PFK_SKIP_PF` for reinjected packets — **single-bit masks**: multi-bit magic values made the in-pass mark look like an out-pass mark and the out ruleset was never evaluated for transit traffic |
|
||||
|
||||
### NAT checklist (what the lab gate proves)
|
||||
|
||||
1. `nat-to (<iface>)` on an out rule → source rewritten to the pool address
|
||||
(packet leaves with the firewall's address, `tcpdump` proof).
|
||||
2. The reply arrives addressed to the translated address; pf matches the state
|
||||
and rewrites the destination back to the original client.
|
||||
3. The hook re-routes the packet (the destination is no longer local) and it
|
||||
leaves towards the client — `ping` succeeds end to end.
|
||||
|
||||
Without step 3 the reply is delivered to the firewall's own stack and the
|
||||
client never sees it (the classic "NAT works one way" symptom).
|
||||
|
||||
## Checksums across the translation paths
|
||||
|
||||
pf rewrites addresses, so both the IPv4 header checksum and the transport
|
||||
checksum must stay correct. Three cases matter in the lab:
|
||||
|
||||
| Case | What Linux gives us | What the port does |
|
||||
|---|---|---|
|
||||
| transit packet, no translation | `CHECKSUM_UNNECESSARY` (vhost-net did not materialize the field) | leave it alone — the peer's stack trusts the marker |
|
||||
| translated packet, plain skb | same | recompute the transport checksum in software over the new pseudo-header, then the IP header checksum |
|
||||
| translated packet, GSO/TSO skb (bulk, locally generated) | `CHECKSUM_PARTIAL` | **do not** compute in software: one computation covers only the first segment. Restore `CHECKSUM_PARTIAL` with `csum_start`/`csum_offset` and let the NIC compute per segment |
|
||||
|
||||
The third row is a regression guard: materializing GSO checksums in software
|
||||
made bulk transfers silently stall (the peer dropped every segment after the
|
||||
first) and starved `sshd` on the firewall — the box answered ping but not SSH.
|
||||
`tests/vm/06-rdr.sh` pulls 2 MB through a redirect and compares the size to
|
||||
catch it.
|
||||
|
||||
## pflog backend (M4) — chardev instead of an if_pflog/bpf interface
|
||||
|
||||
OpenBSD attaches a `pflog0` interface (`if_pflog.c`, `IFT_PFLOG`) and `pflogd`
|
||||
reads it through `bpf(4)`. This port keeps `if_pflog.c` staged but unbuilt and
|
||||
implements the consumer as a misc character device:
|
||||
|
||||
| Aspect | OpenBSD | This port |
|
||||
|---|---|---|
|
||||
| Delivery | `pflog0` interface + bpf | `/dev/pflog` (0600), `read()` returns one record, `poll()` supported |
|
||||
| Record | `struct pflog_hdr` (64 bytes) + packet | identical layout (`module/pfsrc/pfk_pflog.c`), packet truncated to 160 bytes like BSD |
|
||||
| Consumer | `pflogd` → pcap `DLT_PFLOG` | `tools/pflogd` → pcap `DLT_PFLOG` (117), readable by tcpdump/wireshark |
|
||||
| Backpressure | bpf buffer | bounded queue (256 records / 1 MiB), overflow counted in `PFKIOCGETPFLOGSTAT` |
|
||||
|
||||
Rationale: a single consumer is the real use case, and Linux gives no bpf hook
|
||||
for a non-`net_device` virtual interface without pulling in a much larger
|
||||
amount of the BSD if layer. The on-disk format is unchanged, so existing
|
||||
tooling works.
|
||||
|
||||
## Scheduler back ends in the build (M5, first step)
|
||||
|
||||
`pfsrc/hfsc.c` and `pfsrc/fq_codel.c` are now compiled into `pf.ko` (the
|
||||
`pf_ioctl` queue manager already references `hfsc_initialize`,
|
||||
`hfsc_pf_addqueue`, `ifq_hfsc_ops`, `fqcodel_pf_addqueue`, `ifq_fqcodel_ops`).
|
||||
The priq shim in `compat/pfk_ifq.c` remains the *attached* scheduler, so
|
||||
behaviour is unchanged until the data path enqueues into a queue.
|
||||
|
||||
Compat surface added for the back ends (all in `module/include/pfk.h` /
|
||||
`pfk_if.h` / `compat/pfk_ifq.c`):
|
||||
|
||||
| OpenBSD | This port |
|
||||
|---|---|
|
||||
| `struct mbuf_list` + `ml_init/ml_enqueue/ml_dequeue/ml_dequeue_tail/ml_enlist/ml_len/ml_empty/ml_purge`, `MBUF_LIST_FIRST/INITIALIZER` | inline helpers in `pfk_if.h` (`ml_purge` in `compat/pfk_mbuf.c`) |
|
||||
| `ifq_q_enter()/ifq_q_leave()` (scheduler ownership handshake, guarded by the ifq mutex) | ownership check against `ifq->ifq_ops`, returning `ifq_softc`; `leave` is a no-op (the port has no ifq mutex — the data path is one ordered work queue) |
|
||||
| `nsecuptime()` | `getnsecuptime()` (`ktime_get_ns`) |
|
||||
| `tick_nsec` (`HFSC_CLK_PER_TICK`) | `1000000000 / HZ` |
|
||||
| `splnet()/splx()` | no-ops, kept as markers of the critical regions |
|
||||
| `KERNEL_ASSERT_LOCKED()` | no-op (structural, not runtime) |
|
||||
| `struct hfsc_sc`, `struct hfsc_class_stats`, `struct fqcodel_stats`, `PKTCNTR_INC`, `HFSC_*` limits | declared in `pfk.h` (OpenBSD keeps them in `net/if_hfsc.h` / `net/if_fq_codel.h`) |
|
||||
|
||||
Two port fixes worth recording:
|
||||
|
||||
- `min(cd->drops - 1, nitems(...) - 1)` → `min_t(unsigned int, ...)`: Linux
|
||||
type-checks `min()` and `nitems()` is `size_t`.
|
||||
- `hfsc_more_slots(u_int current)` → renamed the parameter: **`current` is a
|
||||
kernel macro** (`get_current()`), which turned the definition into a K&R
|
||||
function and produced a baffling "makes pointer from integer" error at the
|
||||
call site.
|
||||
|
||||
## ifq contract details found while wiring the schedulers (M5)
|
||||
|
||||
The staged OpenBSD back ends assume three things the first version of the
|
||||
port's ifq shim got wrong. All three were reproduced in the lab and fixed:
|
||||
|
||||
| Assumption | What the port did | Fix |
|
||||
|---|---|---|
|
||||
| `ifqop_enq()` returns **the packet to drop** (NULL = accepted) | treated a non-NULL return as an error (`ENOMEM`) and the NULL return as success → every accepted packet was reported as dropped | `ifq_enqueue()` frees the returned mbuf and reports success |
|
||||
| the scheduler state lives in `ifq->ifq_q` | `ifq_attach()` stored it in `ifq_softc` only → `hfsc_enq()` dereferenced NULL and the box died mid-transfer | `ifq_attach()` keeps both fields in sync |
|
||||
| `ifq_deq_begin()`'s cookie is consumed by `ifq_deq_commit()` | the cookie was dropped on the floor (always NULL) | a per-queue `ifq_dequeue` slot carries it |
|
||||
|
||||
Also fixed: the hfsc **root-class handle** used bit `0x1`, which is exactly the
|
||||
handle of any odd pf queue id, so `hfsc_pf_addqueue()` saw the root class as a
|
||||
duplicate of the queue being added and returned `EBUSY` ("cannot add queue").
|
||||
Handles now use bit `0x80000000`; pf queue ids are `u_int16_t`, so they can
|
||||
never collide.
|
||||
|
||||
### `splassert` under rw-semas
|
||||
|
||||
`PF_ASSERT_UNLOCKED()` (used by `pf_purge_expired_states()`) is a BSD
|
||||
per-CPU-spl check: "this context did not take the lock". With an rw-semaphore
|
||||
`rw_status()` is global, so the assert fires whenever *another* CPU holds the
|
||||
lock - which is not a bug, and `BUG()` there turned a harmless race into a
|
||||
wedged module (`Unloading`, refcount -1). It now logs once
|
||||
(`pr_warn_ratelimited`) instead of killing the host; the invariant it protects
|
||||
(purge never acquires `pf_lock` itself) is upheld by the call sites, which are
|
||||
only reached from `systqmp` tasks and timer work.
|
||||
|
||||
### What `bandwidth` can and cannot do here
|
||||
|
||||
OpenBSD 8.0's `pfctl` keyword table exposes `burst`, `flows`, `qlimit`,
|
||||
`parent`, `default` - **not** `minimum`/`maximum`. A pf `queue` therefore only
|
||||
sets HFSC's **linkshare** curve (`qspec.linkshare = scspec` in `expand_queue`).
|
||||
Linkshare is a *guarantee under contention*, not a cap: a single active class
|
||||
may run at line rate, and `bandwidth 2Mbit` alone will not make one flow
|
||||
measure 2 Mbit/s. Verifying HFSC in this port therefore requires two competing
|
||||
leaf queues and comparing their shares - which is the remaining M5 item, not a
|
||||
code defect in the queue path (attach, enqueue, drain and transmit are
|
||||
verified: `eth2` carries the hfsc ops, 117 drains observed, transfer completes,
|
||||
box stays alive).
|
||||
|
||||
## Scheduler ABI must be shared, not re-implemented (M5)
|
||||
|
||||
The first version of this note hand-wrote `struct hfsc_class_stats`,
|
||||
`struct fqcodel_stats`, `struct hfsc_sc` and the `HFSC_*` constants in `pfk.h`
|
||||
from memory of the BSD sources. Two consequences showed up in the lab:
|
||||
|
||||
1. `pfctl -s queue -v` failed with `EINVAL` - `hfsc_pf_qstats()` rejects the
|
||||
call when `*nbytes < sizeof(stats)`, and pfctl's struct (from the vendored
|
||||
`net/hfsc.h`) was smaller than the kernel's invented one.
|
||||
2. `HFSC_ROOT_CLASS` was guessed as `0x1`, which is exactly the handle of every
|
||||
odd pf queue id, so `hfsc_pf_addqueue()` refused every root queue with
|
||||
`EBUSY`. The real value is `0x10000`, safely above the `u_int16_t` qid
|
||||
range.
|
||||
|
||||
The port now vendors OpenBSD's `net/hfsc.h` and `net/fq_codel.h` into
|
||||
`module/include/net/` and includes them from `pfk.h`, so kernel and pfctl
|
||||
compile against one definition. Rule for anything else in this area: if a
|
||||
struct crosses the ioctl boundary, take the header from OpenBSD's tree - do not
|
||||
reconstruct it.
|
||||
@@ -0,0 +1,36 @@
|
||||
# Documentação PF-on-Linux (português)
|
||||
|
||||
English documentation: [`docs/en/README.md`](../en/README.md).
|
||||
|
||||
Este é o conjunto de documentação de usuário do port do **PF do OpenBSD 8.0**
|
||||
para o **Linux 7.3.4** — o engine PF de verdade (`pf.c`, `pf_norm.c`,
|
||||
`pf_table.c`, `pf_lb.c`, …) rodando como módulo out-of-tree `pf.ko`,
|
||||
controlado pelo `pfctl` real do OpenBSD pela ABI ioctl de `/dev/pf`.
|
||||
|
||||
## Índice
|
||||
|
||||
| Documento | Conteúdo |
|
||||
|---|---|
|
||||
| [guide.md](guide.md) | Arquitetura em uma página: componentes, caminho de dados, plano de controle, milestones |
|
||||
| [install.md](install.md) | Receita de aplicação/build/instalação (kernel, módulo, ferramentas) |
|
||||
| [build.md](build.md) | Pipeline de build em detalhe: fetch → vendorize → kernel → módulo → pfctl |
|
||||
| [vm-lab.md](vm-lab.md) | Bancada de validação em libvirt: topologia, recriar/rodar, o que cada gate prova |
|
||||
| [feature-matrix.md](feature-matrix.md) | Status por feature: VERIFIED-in-VM / COMPILES-untested / PENDING-Mx |
|
||||
| [pf-guide.md](pf-guide.md) | Uso diário: o que funciona hoje em `/etc/pf.conf`, o que evitar até M3/M4 |
|
||||
| [patches.md](patches.md) | Patches de core do Linux (hoje vazio) + regras e template para futuros `000N-*.patch` |
|
||||
| [caveats.md](caveats.md) | Divergências conhecidas de comportamento e limitações atuais |
|
||||
|
||||
## Fontes de verdade
|
||||
|
||||
A documentação descreve o código como ele existe na árvore. Em caso de dúvida,
|
||||
as referências autoritativas são:
|
||||
|
||||
- `docs/superpowers/specs/2026-11-11-pf-linux-port-design.md` — design
|
||||
- `docs/superpowers/plans/2026-11-11-pf-linux-port.md` — plano de milestones (tarefas T1–T19)
|
||||
- `docs/porting-notes.md` — log de staging + registro de desvios da camada de compat (M1)
|
||||
|
||||
Vocabulário de status usado em todos os documentos:
|
||||
|
||||
- **VERIFIED-in-VM** — exercitado de ponta a ponta na bancada libvirt (ver vm-lab.md).
|
||||
- **COMPILES-untested** — o código compila no `pf.ko`, mas nenhum gate provou o comportamento ainda.
|
||||
- **PENDING-Mx** — entra (ou entra por completo) no milestone Mx; o comportamento observável hoje está documentado.
|
||||
@@ -0,0 +1,120 @@
|
||||
# Pipeline de build em detalhe
|
||||
|
||||
English: [docs/en/build.md](../en/build.md).
|
||||
Receita rápida: [install.md](install.md). Esta página explica *o que cada
|
||||
etapa faz* e *o que já foi realmente exercitado*.
|
||||
|
||||
Tudo abaixo roda no host de build (o laptop); a bancada de VMs (host
|
||||
separado, "deb") só recebe artefatos — ver [vm-lab.md](vm-lab.md).
|
||||
|
||||
## 0. Pré-requisitos
|
||||
|
||||
De `docs/pt-BR/install.md`: gcc ≥ 15, GNU make, bison (flex não é
|
||||
necessário — o `parse.y` do OpenBSD traz um `yylex` escrito à mão), `bc`,
|
||||
rsync, `glibc-static` para o pfctl estático, root para `insmod`. A árvore do
|
||||
kernel é esperada em `../linux-7.3.4` (troque com `KERNELDIR=`; o `Makefile`
|
||||
raiz usa `$(HOME)/lab/linux_kernel/linux-7.3.4`).
|
||||
|
||||
## 1. Baixar + verificar as fontes do OpenBSD — `scripts/fetch-sources.sh`
|
||||
|
||||
- Baixa `sys.tar.gz` e `src.tar.gz` do mirror primário
|
||||
`https://openbsd.c3sl.ufpr.br/pub/OpenBSD/8.0/`, com fallback para
|
||||
`cdn.openbsd.org`.
|
||||
- Confere o sha256 contra os valores de `VERSIONS` (sys: `964b1aed…`, src:
|
||||
`9984c74f…`); tarball já em cache com hash correto é pulado.
|
||||
- Destino: `_vendor/openbsd/` (fora do git).
|
||||
|
||||
## 2. Vendorize — `scripts/vendorize.sh`
|
||||
|
||||
Extrai **só os arquivos que o port consome** para `_vendor/upstream/`
|
||||
(fora do git): a lista `sys/net/pf*.c|h`, `ifq/hfsc/fq_codel/ip_pflog/
|
||||
ip_divert`, `radix/rtable/toeplitz`, `crypto/{md5,sha2,siphash}`,
|
||||
`sys/sys/*.h` e `sbin/pfctl/*` + headers (arrays `SYS_K`/`SRC_K`). Em
|
||||
seguida registra o tag `$OpenBSD: …$` de cada arquivo em
|
||||
`_vendor/upstream/IDS.txt` — a base forense de toda linha portada e de
|
||||
futuros rebases.
|
||||
|
||||
## 3. Staging para o port — `scripts/stage-port.sh` (porting determinístico)
|
||||
|
||||
O `stage-port.sh` transforma os arquivos upstream pristinos nos arquivos em
|
||||
`module/`:
|
||||
|
||||
1. todo `#include` é substituído por `pfk.h` + os headers `pfvar` staged
|
||||
(os ramos de kernel são selecionados com `-D_KERNEL=1`);
|
||||
2. o programa de renomeação compartilhado (`pf_sed`) resolve colisões de
|
||||
nomes BSD↔Linux (`struct ip` → `struct pf_ip`, `ifnet` → `pfk_ifnet`,
|
||||
`ip_output` → `pfk_ip_output`, atribuições a `sa_len` removidas, …);
|
||||
3. **cada execução é anexada a `docs/porting-notes.md`** — esse arquivo é o
|
||||
log de staging, não prosa.
|
||||
|
||||
Os arquivos portados são então commitados e editados à mão na árvore; o
|
||||
re-staging serve só para perícia (`stage-port.sh --diff <arquivo>` compara a
|
||||
nossa cópia com o texto upstream pristino). Radix/rtable/siphash/toeplitz
|
||||
ficam de fora do staging automático de propósito (portados à mão).
|
||||
|
||||
## 4. Kernel — `scripts/build-kernel.sh` (+ `kernel-config.sh`)
|
||||
|
||||
- `kernel-config.sh`: parte de `defconfig` quando não há `.config` e então
|
||||
ajusta (idempotente, via `scripts/config` + `make olddefconfig`):
|
||||
`VIRTIO_BLK/PCI/NET=y`, `EXT4_FS=y`, `NETFILTER=y`,
|
||||
`NETFILTER_ADVANCED`, `NET_SCHED=y`, `INET=y`, `IPV6=y`,
|
||||
`SERIAL_8250(+CONSOLE)=y` — ou seja, tudo que o boot direto da VM pf0
|
||||
precisa **sem initrd**. `kernel-config.sh test` habilita também
|
||||
`DEBUG_INFO` + `DEBUG_KMEMLEAK` para builds de soak.
|
||||
- `build-kernel.sh`: `make -j(nproc-2) bzImage modules_prepare`, garante que
|
||||
`Module.symvers` exista (copia `vmlinux.symvers` — o kbuild não escreve o
|
||||
primeiro) e que `scripts/module.lds` exista; depois deposita os artefatos
|
||||
de boot em `out/`: `linux-<ver>-bzImage`, `System.map`, `.config`,
|
||||
`kernelversion`, `bzImage.sha256`. Termina com
|
||||
`KERNEL_BUILD_OK <kernelrelease>`.
|
||||
- **Hoje não há patch de core**: `patches/kernel/` não tem nenhum
|
||||
`000N-*.patch` (ver [patches.md](patches.md)).
|
||||
|
||||
## 5. Módulo — `scripts/build-module.sh`
|
||||
|
||||
`make -C "$KERNELDIR" M=module` → `module/pf.ko` (um único módulo hoje; o
|
||||
qdisc `pfq` chega com o M5). O script prepara sozinho `Module.symvers` /
|
||||
`modules_prepare`. Lista de objetos (`module/Makefile`): engine portado
|
||||
(`pf.c`, `pf_ioctl.c`, `pf_norm.c`, `pf_if.c`, `pf_lb.c`, `pf_ruleset.c`,
|
||||
`pf_table.c`, `pf_osfp.c`, `pf_syncookies.c`, `divert_sock.c`) + camada de
|
||||
compat (shim mbuf, glue de kernel, if/ip4/ip6/pcb/xmit/ifq, crypto, radix,
|
||||
subr_tree) + `pfk_mod.c`/`pfk_hooks.c`. As flags de compilação definem
|
||||
`PFLINUX=1` e `_KERNEL=1`. Termina com `MODULE_BUILD_OK`.
|
||||
|
||||
`insmod module/pf.ko` cria `/dev/pf` (0600) e registra os hooks netfilter; o
|
||||
`dmesg` mostra linhas `pfk: …` (ver [caveats.md](caveats.md) para o que o
|
||||
caminho de dados faz).
|
||||
|
||||
## 6. Userland — `make -C tools`
|
||||
|
||||
Alvos (de `tools/Makefile`): `pfctl`, `abitest`, `abi`, `test`, `clean`.
|
||||
|
||||
- `pfctl` — as fontes do OpenBSD 8.0 compiladas contra os headers de ABI
|
||||
copiados; o resultado é um **binário estático** em `tools/out/pfctl`.
|
||||
Cada desvio do upstream está listado em `tools/UPSTREAM.md` (7 edições
|
||||
marcadas; o resto é o conjunto de headers/fontes de compat).
|
||||
- `abi` — compila `abitest` (userland) e `abitest-module` (mesma tabela com
|
||||
os headers de compat de kernel), despeja as tabelas de tamanho/offset de
|
||||
cada struct e as compara com `diff`; divergência = ABI de ioctl quebrada.
|
||||
`out/abi-*.tbl` são as entradas de referência.
|
||||
- `test` — checagens de parse offline: roda `pfctl -n -f` sobre
|
||||
`tools/tests/*.conf` (básico / traduções / filas+scrub / anchor / negativa
|
||||
`broken.conf`). É userland puro; não precisa de `/dev/pf`.
|
||||
- `pdivert` — o fonte do relay de divert fica em `tools/pdivert/`; o lado
|
||||
kernel (pendente) está na [matriz de features](feature-matrix.md).
|
||||
|
||||
## 7. `Makefile` raiz
|
||||
|
||||
`make module | tools | kernel | vm | vm-destroy | test | docs | clean` —
|
||||
wrappers finos sobre os scripts acima. `make test` roda a suíte em VM
|
||||
([vm-lab.md](vm-lab.md)); `make docs` apenas lista o conjunto bilíngue.
|
||||
|
||||
## O que já foi exercitado vs. não
|
||||
|
||||
- As etapas 1–6 foram rodadas ao longo do desenvolvimento M0–M2 no host de
|
||||
build (há artefatos na árvore: `out/`, `module/pf.ko`, `tools/out/pfctl`),
|
||||
e os scripts acima foram verificados linha a linha para este documento.
|
||||
- Uma execução **de ponta a ponta a partir de clone limpo**
|
||||
(`quickstart-check.sh`, tarefa T19 do plano) **ainda não** foi feita;
|
||||
trate a sequência exata do install.md como "conforme projetada e conforme
|
||||
o último estado por milestone", não como verificada em CI.
|
||||
@@ -0,0 +1,171 @@
|
||||
# Ressalvas — divergências do comportamento do OpenBSD
|
||||
|
||||
English: [docs/en/caveats.md](../en/caveats.md).
|
||||
|
||||
Estas são as formas pelas quais este port difere de rodar o mesmo ruleset no
|
||||
OpenBSD 8.0, ou ainda não tem forma de produção. Tudo aqui tem base no
|
||||
código (`module/pfsrc/pfk_hooks.c`, `module/pfsrc/pfk_mod.c`,
|
||||
`docs/porting-notes.md`) e em observações da bancada; nada é especulação.
|
||||
|
||||
## Caminho de dados
|
||||
|
||||
### 1. O PF roda em contexto de processo via workqueue (modelo netisr), não no caminho rápido do pacote
|
||||
|
||||
O OpenBSD avalia o `pf_test()` na CPU que recebeu o pacote, em `IPL_NET`,
|
||||
com uma lock de leitura NET que não dorme. O Linux nos dá contexto de
|
||||
softirq e locks da compat *sleepáveis* (rw-semaphores), então o hook nunca
|
||||
chama o `pf_test()` inline: ele furta a skb (`NF_STOLEN`) para uma
|
||||
**workqueue ordenada** (`pfk_netisr`, `WQ_MEM_RECLAIM`), roda o engine em
|
||||
contexto de processo e então reinjeta (`netif_rx()` na entrada,
|
||||
`dst->output()` na saída/trânsito).
|
||||
|
||||
Consequências, todas observáveis:
|
||||
|
||||
- **Vereditos são assíncronos.** Qualquer regra encadeada depois do nosso
|
||||
hook na mesma chain netfilter (outras regras iptables/nft em prioridades
|
||||
maiores) não vê o pacote até o passe reinjetado chegar. Contadores e
|
||||
intercalação de log mudam na mesma medida.
|
||||
- **Latência + vazão**: cada pacote paga um ida-e-volta pela workqueue,
|
||||
serializado num único worker ordenado. Os gates funcionais são a régua
|
||||
atual; o `bench-basic.sh` planejado (ainda não está na árvore) é só informativo.
|
||||
- **Reordenação**: a fila ordenada preserva a ordem de chegada dos itens
|
||||
*enfileirados*, mas o stack em volta (RPS, multi-NAPI) ainda pode nos
|
||||
entregar pacotes cuja ordem original de conclusão difere da ordem de
|
||||
reinjeção.
|
||||
|
||||
### 2. A proteção contra reentrada é um tag por direção no `skb->mark`
|
||||
|
||||
O sobrevivente reinjetado carrega `skb->mark |= PFK_DONE_IN (0x50460010)` ou
|
||||
`PFK_DONE_OUT (0x50460020)`; nossos hooks aceitam qualquer pacote já marcado
|
||||
para aquela direção em vez de re-enfileirar (senão PF_IN → netif_rx → PF_IN…
|
||||
entraria em loop). O `skb->mark` é um **campo compartilhado e gravável de
|
||||
32 bits**: qualquer subsistema que o *sobrescreva* — `meta mark set` do nft,
|
||||
`CONNMARK --restore`, filtros de tc, alguns stacks de VPN — pode (a) limpar o
|
||||
nosso tag e fazer o pacote ser **re-enfileirado pelo PF de novo**, ou (b)
|
||||
acidentalmente ligar esses bits e deixar o pacote **pular** um passe do PF.
|
||||
Regra prática num host com PF-on-Linux: não use mangling de fwmark no mesmo
|
||||
tráfego; se precisar, mascare os bits do tag do PF no seu espaço de mark.
|
||||
|
||||
### 3. Sem lock NET no caminho de dados (interino do M2)
|
||||
|
||||
O `pf_test()` roda hoje **sem** a lock de leitura NET da compat (comentário
|
||||
em `pfk_hooks.c`): com o modelo de workqueue, um escritor de controle
|
||||
parqueado (mudança de ruleset, ioctl de purge) esfomeava o lado dos pacotes
|
||||
a ponto de ser contraproducente. A mutação do ruleset e a caminhada de
|
||||
pacotes rodam, portanto, concorrentemente, protegidas pelo que o próprio
|
||||
`pf.c` do upstream usa (PF_LOCK/padrões tipo RCU) — um desvio interino
|
||||
deliberado, sendo retrabalhado junto com o modelo de locks no M5+. Até lá:
|
||||
espere correção em regime estável, não sob reload concorrente agressivo; o
|
||||
soak de reload sob tráfego é um gate aberto.
|
||||
|
||||
### 4. Fail-open sob pressão de memória
|
||||
|
||||
O item da fila é um `kmalloc(GFP_ATOMIC)` em softirq. Se falhar, o hook
|
||||
retorna `NF_ACCEPT` — o pacote **passa por fora do PF**. É uma escolha
|
||||
deliberada de disponibilidade (espelha "cai numa fila cheia = bypass do
|
||||
qdisc"), mas é um trade-off de segurança que vale conhecer: os vereditos do
|
||||
PF são best-effort exatamente quando o host está sem memória atômica.
|
||||
|
||||
### 5. A ordem dos hooks vs conntrack varia por direção
|
||||
|
||||
- Entrada (`PREROUTING`, `NF_IP_PRI_FIRST`): o PF roda **antes** do defrag
|
||||
e do conntrack — como projetado (spec §4.2).
|
||||
- Saída (`LOCAL_OUT` em `NF_IP_PRI_CONNTRACK+1`): o PF vê o tráfego gerado
|
||||
localmente **depois** de o conntrack já ter confirmado a entrada.
|
||||
- Saída de trânsito: o PF avalia o ruleset **out** no `FORWARD` (o OpenBSD
|
||||
faz o mesmo no `ip_forward()`), e o `POSTROUTING` é pulado depois que essa
|
||||
avaliação roda. `nat-to`/`rdr-to` foram validados contra essa ordem (gates
|
||||
05/06).
|
||||
- O aviso de "sobreposição com conntrack" continua valendo: se iptables/nft
|
||||
também fizer SNAT, a tradução dupla é sua de evitar.
|
||||
|
||||
## Plano de controle / ciclo de vida
|
||||
|
||||
### 6. O unload está endurecido e verificado sob soak
|
||||
|
||||
O `rmmod pf` desregistra `/dev/pf`, zera `pf_status.running` sob a lock NET,
|
||||
deleta **e sincroniza** os dois timers de purge (eles se rearmam sozinhos —
|
||||
um travamento real de rmmod foi observado e corrigido parando as fontes
|
||||
antes de drenar a workqueue), desregistra os hooks e drena o `pfk_netisr`.
|
||||
A correção está na árvore, mas o ciclo completo sob tráfego + estados vivos
|
||||
(gate de soak T18) **ainda não** rodou verde. Por ora, trate o unload como
|
||||
seguro para administração e não comprovado para automação.
|
||||
|
||||
## Notas de comportamento verificadas hoje
|
||||
|
||||
### 7. `pfctl -s states` lista estados reais, incluindo traduções
|
||||
|
||||
A anomalia anterior era um use-after-free: `refcnt_rele()` tinha polaridade
|
||||
invertida, então chaves de estado vivas eram liberadas ainda ligadas no RBT
|
||||
de estados — o que escondia estados e quebrava o walk da árvore (`pfctl -s
|
||||
states` travando a máquina). Após a correção, os gates 01/04/05/06/07
|
||||
asseveram sobre os estados listados, e fluxos traduzidos imprimem as duas
|
||||
tuplas (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`).
|
||||
|
||||
### 8. Ainda são necessários consumidores
|
||||
|
||||
`divert-to` exige um processo atrelado à porta do divert (`tools/pdivert`);
|
||||
sem listener o pacote é descartado, como o `divs_noport` do BSD, e o kernel
|
||||
imprime `pfk: divert port N: no socket bound`. `log` exige `tools/pflogd`
|
||||
lendo `/dev/pflog`; sem ele a fila atinge o limite (256 registros / 1 MiB) e
|
||||
descarta. Nenhum dos dois é mais stub, mas nenhum faz algo sem o consumidor
|
||||
rodar (ver [pf-guide.md](pf-guide.md)).
|
||||
|
||||
### 9. Filas: caminho verificado; a semântica de modelagem é do HFSC, não um bug
|
||||
|
||||
`15-queue.sh` prova que o caminho de filas funciona de ponta a ponta: a
|
||||
configuração carrega, a disciplina hfsc é anexada à interface, `pfctl -s
|
||||
queue -v` lista as duas classes com estatísticas, um fluxo de 2 MB pela fila
|
||||
completa, e o contador de pacotes da classe avança - o escalonador está mesmo
|
||||
no caminho de dados.
|
||||
|
||||
O que o lab não mostra é um *teto de taxa*, e isso é semântica do HFSC, não
|
||||
defeito do port: o `pf.conf` do OpenBSD 8.0 expõe apenas `bandwidth`, que mapeia
|
||||
para a curva **linkshare** do HFSC - garantia quando classes competem, não limite
|
||||
de um fluxo isolado. Não existe palavra-chave `minimum`/`maximum` nesta versão do
|
||||
pfctl (verificado na sua tabela de palavras-chave), logo não há como definir
|
||||
upperlimit pelo pf.conf. Um teste de contenção com duas classes saturadas seria o
|
||||
próximo passo se você quiser asserir sobre share; no enlace virtual de centenas de
|
||||
Mbit do lab, um único fluxo termina antes de acumular dívida de tempo virtual.
|
||||
|
||||
Bugs encontrados e corrigidos no caminho (detalhes em `docs/porting-notes.md`): a
|
||||
convenção de retorno de `ifqop_enq`, `ifq_q` vs `ifq_softc` (deref de NULL que
|
||||
matava a máquina no meio da transferência), o cookie de dequeue perdido, o
|
||||
handle da classe raiz do hfsc colidindo com qids ímpares do pf, o
|
||||
`DIOCGETQSTATS` falhando porque kernel e pfctl discordavam sobre
|
||||
`struct hfsc_class_stats` (ambos agora usam o `net/hfsc.h` vendorizado), o
|
||||
payload do pflog começando no cabeçalho de transporte, e o `splassert` do caminho
|
||||
de purge que transformava uma corrida benigna em `BUG()`.
|
||||
|
||||
## Desvios da camada de compat (de `docs/porting-notes.md`, registro do M1)
|
||||
|
||||
Estes são desvios deliberados e marcados no código; importam ao raciocinar
|
||||
sobre a semântica das regras:
|
||||
|
||||
- **Match pelo dono do socket** (`user`/`pid` em regras): só uid — o
|
||||
`struct sock` do Linux não guarda egid/cpid, então o gid degrada para
|
||||
`(gid_t)-1` e o pid para `NO_PID`.
|
||||
- **Checksums**: o offload do driver não é confiável na entrada (decisão do
|
||||
M1) — checksums TCP são recalculados em software; os pseudo-checksums de
|
||||
saída são feitos no caminho próprio do port.
|
||||
- **Opções IP / record-route / timestamps**: não processadas no caminho de
|
||||
saída do PF; **redirecionamentos ICMP não são gerados** pelo código de
|
||||
rota do PF (o FIB do Linux emite).
|
||||
- **Labels de rota**: não-objetivo — a camada de ioctl rejeita regras com
|
||||
label; `rtable_iterate()` sempre retorna NULL (sem iteração de uRPF
|
||||
multipath).
|
||||
- **Grupos de interface**: o Linux não tem; matches `group …` se comportam
|
||||
como um grupo inexistente no OpenBSD.
|
||||
- **Skbs GSO/multi-segmento**: tratadas por linearização na entrada do shim
|
||||
mbuf (custo de performance documentado no spec §10; os gates vão
|
||||
quantificar).
|
||||
- **Instância única**: um mundo PF em `init_net`, como o OpenBSD tem um
|
||||
kernel. Containers/namespaces não são visíveis ao PF e não podem ser
|
||||
filtrados por ele neste design.
|
||||
|
||||
## O que *não* é ressalva
|
||||
|
||||
ARP e outros EtherTypes não-IPv4/IPv6 nunca entram nos hooks netfilter de
|
||||
IPv4/IPv6 — passam pela máquina intactos, exatamente como o PF no OpenBSD
|
||||
ignora não-IP. O `/dev/pf` é 0600 somente-root por projeto (equivalente ao
|
||||
padrão do `pfctl` no OpenBSD da era `securelevel`).
|
||||
@@ -0,0 +1,40 @@
|
||||
# Demo (asciinema)
|
||||
|
||||
O lab pode ser gravado como um cast do [asciinema](https://asciinema.org).
|
||||
Cada byte da gravação é a saída real das VMs do lab (Alpine sobre libvirt,
|
||||
rodando o kernel compilado do fonte com o `pf.ko`); só o ritmo é roteirizado.
|
||||
|
||||
## Gravar
|
||||
|
||||
```sh
|
||||
pip install asciinema # uma vez
|
||||
bash scripts/vm-run-tests.sh # ou: scripts/vm-create.sh + deploy
|
||||
asciinema rec out/demo-pf-linux.cast -c "bash scripts/demo-session.sh"
|
||||
```
|
||||
|
||||
A sessão percorre:
|
||||
|
||||
1. a topologia do lab e o `pf.ko` recém-carregado (prova no `dmesg`),
|
||||
2. `pfctl -s info` pela ABI de ioctl do OpenBSD,
|
||||
3. um `pf.conf` real (tabela, regras stateful, drop explícito) e `pfctl -sr`,
|
||||
4. ping em trânsito + `pfctl -ss` (stateful),
|
||||
5. `pfctl -t <tabela> -T show` (tabelas vivas),
|
||||
6. um ping bloqueado (contadores com `pfctl -sr -vv`),
|
||||
7. `divert-to` com o relay `pdivert` (pacote vai ao userspace e volta),
|
||||
8. desligamento.
|
||||
|
||||
## Reproduzir
|
||||
|
||||
```sh
|
||||
asciinema play out/demo-pf-linux.cast
|
||||
```
|
||||
|
||||
## Publicar
|
||||
|
||||
```sh
|
||||
asciinema upload out/demo-pf-linux.cast
|
||||
```
|
||||
|
||||
`scripts/demo-record.py` é um gravador alternativo que produz o mesmo formato
|
||||
asciicast v2 sem o binário asciinema (ele conduz o lab por ssh e escreve o
|
||||
cast diretamente).
|
||||
@@ -0,0 +1,78 @@
|
||||
# Matriz de features
|
||||
|
||||
English: [docs/en/feature-matrix.md](../en/feature-matrix.md).
|
||||
|
||||
Vocabulário de status (idêntico nos dois idiomas):
|
||||
|
||||
- **VERIFIED-in-VM** — passou de ponta a ponta na bancada libvirt (ver [vm-lab.md](vm-lab.md)).
|
||||
- **M2-in-progress** — implementado; os gates VM 01–04 existem, mas a suíte **ainda não está toda verde**; sem alegação de VERIFIED até uma rodada limpa.
|
||||
- **COMPILES-untested** — compila em `pf.ko`/`pfctl`; nenhum gate exercitou.
|
||||
- **PENDING-Mx** — entra no milestone Mx; o comportamento observável hoje está declarado.
|
||||
- **OUT-OF-SCOPE** — não-objetivo por projeto (spec §3).
|
||||
|
||||
Estado em 2026-11-11; evidência por linha: `out/test-logs/`,
|
||||
`docs/porting-notes.md`, commits de milestone.
|
||||
|
||||
## Plano de controle e ferramentas
|
||||
|
||||
| Feature | Sintaxe de upstream | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| Carga do módulo, `/dev/pf` (0600) | `insmod pf.ko` | M1 | VERIFIED-in-VM |
|
||||
| Habilitar/desabilitar | `pfctl -e`, `pfctl -d` | M1 | VERIFIED-in-VM |
|
||||
| Carga de ruleset | `pfctl -f arquivo` | M2 | VERIFIED-in-VM (cargas bem-sucedidas em toda rodada capturada; o status geral da rodada é misto — ver [vm-lab.md](vm-lab.md) §6) |
|
||||
| Checagem só de parse | `pfctl -n -f arquivo` | M1 | VERIFIED (suíte de fixtures offline, `make -C tools test`) |
|
||||
| Status/contadores | `pfctl -s info [-v]` | M1 | VERIFIED-in-VM |
|
||||
| Listagem de regras | `pfctl -s rules [-v]` | M2 | COMPILES-untested |
|
||||
| Listagem de estados | `pfctl -s states [-v]` | M2 | M2-in-progress — o gate 01 mostra anomalia de listagem (ping passa, nenhum estado icmp exibido) enquanto a máquina de estados está sendo corrigida |
|
||||
| Tabelas (listagem/ops) | `pfctl -s tables`, `-t t -T show/add/del/kill` | M2 | M2-in-progress (gate 03) |
|
||||
| Anchors | `pfctl -a anchor -f arquivo`, `-s Anchors` | M2 | M2-in-progress (gate 04) |
|
||||
| Listagem de filas | `pfctl -s queue -v`, `-s ifq -v` | M5 | PENDING-M5 (o parse funciona; contadores ainda não conectados aos back ends reais) |
|
||||
| Paridade de ABI ioctl | `make -C tools abi` (tabelas do abitest) | M1 | VERIFIED no lado do build (tabela userland); o diff do lado kernel é um passo aberto para o integrador (`tools/UPSTREAM.md`) |
|
||||
|
||||
## Núcleo de filtragem
|
||||
|
||||
| Feature | Sintaxe de upstream | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| `pass`/`match`, quick, match por interface/proto/endereço/porta | `pass in quick on wan proto tcp from 10/8 to port 80` | M2 | M2-in-progress (o caminho de dados roda o `pf_test` real; rodada parcial recente: ping de trânsito OK, icmp bloqueado OK) |
|
||||
| `block drop` | `block drop in quick …` | M2 | M2-in-progress (gate 02a) |
|
||||
| `block return` / `return-rst` / `return-rst after quarter` | `block return-rst in quick proto tcp …` | M2 | M2-in-progress (gate 02b) |
|
||||
| `keep state` (icmp/tcp/udp), tabela de estados, purger | `… keep state` | M2 | M2-in-progress |
|
||||
| `set state-policy`, `allow-opts` etc. | opções `set …` | M2 | COMPILES-untested |
|
||||
| Syncookies (caminho de estouro de estado) | `set syncookies always` | M2 | COMPILES-untested |
|
||||
| Tabelas pfr (radix/hash) | `table <blk> persist { 1.2.3.4 }`, `-T add …` | M2 | M2-in-progress (gate 03) |
|
||||
| Anchors + include + precedência de quick | `anchor "x"`, `load anchor …` | M2 | M2-in-progress (gate 04) |
|
||||
| IPv6 para tudo acima | mesma sintaxe, v6 | M2+ | COMPILES-untested (o engine é completo para v6 por construção; gates v6 smoke planejados) |
|
||||
| Tráfego não-IPv4/IPv6 (ARP…) | — | M2 | PFLINUX por construção: hooks netfilter só de IPv4/IPv6 — ARP nunca entra no caminho do PF (sem gate ainda) |
|
||||
|
||||
## NAT / normalização (M3)
|
||||
|
||||
| Feature | Sintaxe de upstream | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| `nat-to` (pools de portas, sticky-port, static-port) | `pass out … nat-to (eth1:0)` | M3 | **VERIFICADO em lab** — NAT de origem funciona ponta a ponta: o pacote sai com o endereço do pool (prova via tcpdump), a resposta é des-NATeada e roteada de novo para o cliente, e o estado mostra as duas tuplas (`10.0.2.1:59335 (10.0.1.10:4380) -> 10.0.2.20:8`). Gate: `tests/vm/05-nat.sh`. |
|
||||
| `rdr-to` | `pass in … to <fw> port 8080 rdr-to <srv> port 80 keep state` | M3 | **VERIFICADO em lab** — o redirect de portas funciona ponta a ponta (gate `06-rdr.sh`): o cliente fala com o endereço do firewall, o pf reescreve o destino, re-rotea o pacote e a resposta é des-redirectuada. O gate também baixa 2 MB pelo redirect e confere a integridade byte a byte (guarda de regressão GSO/TSO). |
|
||||
| `binat-to` | `pass quick proto icmp from 10.0.2.20 to 10.0.1.10 binat-to 10.0.2.50 keep state` | M3 | **VERIFICADO em lab** — gate `07-binat.sh`. O pfctl expande uma regra `binat-to` no par documentado (`pass out … nat-to <mapeado> static-port` + `pass in … rdr-to <real>`), e as duas metades funcionam: o peer vê o endereço mapeado, o original não vaza, e a resposta é traduzida de volta. |
|
||||
| Scrub/normalização: remonteagem, `fragment drop-overlap`, `min-ttl`, `max-mss`, `df`/`no-df`, `random-id`, `set reassemble yes` | `match in all scrub (min-ttl 100 max-mss 500)` | M3 | **VERIFICADO em lab** — gate `09-scrub.sh`: `min-ttl` eleva o TTL (o egress mostra 99 após o decremento do encaminhamento) e `max-mss` limita o MSS de um SYN, ambos medidos no egress do próprio firewall. Os caminhos de remonteagem/overlap estão compilados e alcançados, mas ainda sem gate. |
|
||||
| Fingerprint de SO em estados | `pass … set os A` + `/etc/pf.os` | bônus | COMPILES-untested (`pf_osfp.c` compilado; sem empacotamento de fingerprints ainda — ausência de `/etc/pf.os` é tolerada) |
|
||||
|
||||
## Roteamento / divert / filas / logging
|
||||
|
||||
| Feature | Sintaxe de upstream | Milestone | Status |
|
||||
|---|---|---|---|
|
||||
| Pools de `route-to` (`rr`, `round-robin`, `source-hash`, `hash`), `reply-to`, `dup-to` | `pass in … route-to { 10.0.3.2, 10.0.2.2 } round-robin keep state` | M4 | **`round-robin` e `source-hash` VERIFICADOS em lab** (gate `10-pools.sh`): com dois gateways em dois enlaces, o round-robin usa ambos e o source-hash fixa todo fluxo de uma origem em um único enlace. `dup-to` verificado no gate 08; `reply-to` ainda sem gate. `fail-to` **não existe no OpenBSD 8.0** (removido upstream), então está fora de escopo. |
|
||||
| `divert-to` / tag `divert` | `pass in … divert-to <host> port <n>` | VERIFICADO em lab | **Funciona ponta a ponta.** O módulo registra em runtime a família de sockets `AF_DIVERT` (`PF_DIVERT=32`) — sem patch no kernel. A regra `divert-to` entrega o pacote a essa família; sem listener o pacote é descartado (`divs_noport`, paridade BSD); com `tools/pdivert` rodando o pacote vai ao userspace, é reescrito e reinjetado (verificado com mutação de payload + correção de checksum, ping 0% loss). |
|
||||
| Filas (`queue`, `queue on`, `pfctl -s queue -v`) | `queue rootq on eth2 bandwidth 10Mbit` + `queue leafq on eth2 bandwidth 2Mbit parent rootq default` | M5 | **VERIFICADO em lab** — gate `15-queue.sh`: a configuração de filas carrega, a disciplina hfsc é anexada à interface, `pfctl -s queue -v` lista as duas classes com estatísticas, um fluxo de 2 MB pela fila completa, e o contador de pacotes da classe avança (o escalonador está no caminho de dados). Note que `bandwidth` é *linkshare* do HFSC - garantia sob contenção, não teto: o pf.conf do OpenBSD 8.0 não tem `minimum`/`maximum`, então um fluxo isolado não é limitado, nem no Linux nem no OpenBSD. |
|
||||
| HFSC | `queue on wan { hfsc … }` | M5 | COMPILES-untested — **fallback priq até o M5**; `pfsrc/hfsc.c` staged (código real do OpenBSD 8.0) mas **fora da lista de objetos** do módulo |
|
||||
| FQ-CoDel | `queue on wan { fq_codel … }` | M5 | COMPILES-untested — igual ao HFSC: staged, não compilado |
|
||||
| Qdisc `pfq` (`tc qdisc … root pfq`) | n/a (glue Linux) | M5 | PENDING-M5 (ainda não existe na árvore) |
|
||||
| pflog (`log`, `log all`, `block log`) + `pflogd` pcap (DLT_PFLOG) | `pass out quick log` + `pflogd /tmp/x.pcap` | M4 | **VERIFICADO em lab** — gate `12-pflog.sh`: os pacotes logados são enfileirados pelo engine, lidos via `/dev/pflog` e gravados como pcap com linktype DLT_PFLOG (117); o dump contém os bytes reais do pacote. Desvio: um chardev em vez de interface if_pflog/bpf (Linux não tem bpf sobre essa interface virtual aqui); o layout do registro é byte-compatível com `pflog(4)` do OpenBSD. `if_pflog.c` permanece fora do build. |
|
||||
|
||||
## Não-objetivos (explícitos)
|
||||
|
||||
| Item | Motivo |
|
||||
|---|---|
|
||||
| Failover `pfsync` / CARP | não-objetivo (spec §3) |
|
||||
| IPsec / pfkey | não-objetivo |
|
||||
| `ftp-proxy` e daemons de userland | não-objetivo |
|
||||
| Instâncias PF por netns | port fiel = instância global única em `init_net` |
|
||||
| Agendadores exclusivos do ALTQ clássico (cbq/wfq/red…) | removidos do upstream antes do OpenBSD 8.0 — impossível portar da base |
|
||||
| Labels de rota (`route-label`) | não-objetivo; a camada de ioctl rejeita regras com label |
|
||||
@@ -0,0 +1,103 @@
|
||||
# Guia de arquitetura — uma página
|
||||
|
||||
English: [docs/en/guide.md](../en/guide.md).
|
||||
|
||||
## O que este port é
|
||||
|
||||
Um port fiel do **engine PF do OpenBSD 8.0** rodando dentro do **Linux
|
||||
7.3.4** como um único módulo out-of-tree, `pf.ko`. Nada é simulado: o
|
||||
casamento de regras, estado, tabelas, normalização e filas *é* o código do
|
||||
OpenBSD, compilado sob uma camada de compatibilidade; o controle vem do
|
||||
`pfctl` real, falando a ABI ioctl OpenBSD de verdade por `/dev/pf`. Existe
|
||||
**uma instância global do PF, presa a `init_net`** — exatamente como o
|
||||
OpenBSD tem um único kernel; instâncias por netns estão fora de escopo.
|
||||
|
||||
Alvos de build: fontes OpenBSD 8.0 (sha256 fixado em `VERSIONS`), Linux
|
||||
7.3.4 (`linux-7.3.4`), `gcc >= 15`, bison. O `pfvar.h` v1.548 é compartilhado
|
||||
bit a bit entre kernel e userland (codificação de ioctl em
|
||||
`module/include/pfk.h`).
|
||||
|
||||
## Componentes
|
||||
|
||||
| Caminho | Papel |
|
||||
|---|---|
|
||||
| `module/pfsrc/` | Arquivos portados do OpenBSD: `pf.c` (engine), `pf_ioctl.c` (ABI DIOC*), `pf_norm.c` (scrub/fragmentos), `pf_table.c`, `pf_ruleset.c`, `pf_if.c`, `pf_lb.c` (pools/portas NAT), `pf_osfp.c`, `pf_syncookies.c`, `ifq.c`/`hfsc.c`/`fq_codel.c` (staged para M5), `if_pflog.c` + `ip_divert.c` (referências staged), `divert_sock.c` (stub de entrada do divert), `pfk_mod.c` (load/exit, `/dev/pf`), `pfk_hooks.c` (caminho de dados netfilter) |
|
||||
| `module/compat/` | Infra Linux sob os fontes em forma BSD: shim mbuf-sobre-`sk_buff` (`pfk_mbuf`), glue de kernel (malloc/pools/timeouts/locks, `pfk_kern`), visão de interfaces e endereços (`pfk_if`), saída/forward IP com semântica BSD (`pfk_ip4`, `pfk_ip6`), busca de sockets (`pfk_pcb`), API ifq com semântica priq (`pfk_ifq`), radix/rotas/crypto portados |
|
||||
| `module/include/` | `pfk.h` (header mestre da compat + codificação `_IO*` estilo OpenBSD), `net/pfvar.h` staged, `pfk_mbuf.h`, `pfk_net.h`, `pfk_if.h` |
|
||||
| `tools/` | Build Linux do `pfctl` do OpenBSD 8.0 (binário único), relay `pdivert`, verificador de ABI (`abitest` + `make abi`), testes de parse offline (`make test`). Deltas vs upstream: `tools/UPSTREAM.md` |
|
||||
| `scripts/` | `fetch-sources.sh`, `vendorize.sh`, `stage-port.sh` (staging determinístico), `build-kernel.sh`, `build-module.sh`, automação da bancada `vm-*.sh` |
|
||||
| `tests/vm/` | Gates da suíte em VM: `01-state.sh … 04-anchors.sh` + `lib.sh`; `tests/confs/` com rulesets deployados na bancada |
|
||||
| `patches/kernel/` | Conjunto de patches de core — hoje **vazio** (`p1-needs.txt` registra por que nenhum export foi necessário); ver [patches.md](patches.md) |
|
||||
|
||||
## Caminho de dados (M2, como implementado hoje)
|
||||
|
||||
O OpenBSD roda o PF em `IPL_NET`, em contexto de processo; nossas locks da
|
||||
compat são sleepáveis, então o hook **nunca chama `pf_test()` em softirq**. O
|
||||
pacote é furtado (`NF_STOLEN`) para uma workqueue ordenada (`pfk_netisr`), o
|
||||
veredito roda em contexto de processo e é aplicado por **reinjeção**, com
|
||||
marcação por direção em `skb->mark` para que o pacotão sobrevivente não seja
|
||||
re-enfileirado pelo nosso próprio hook.
|
||||
|
||||
```
|
||||
Linux 7.3.4, módulo pf.ko
|
||||
NIC ──► netfilter (softirq — apenas enfileira)
|
||||
PRE_ROUTING PF_IN ─┐ ┌─ LOCAL_OUT PF_OUT
|
||||
POST_ROUTING PF_OUT ─┤ NF_STOLEN ├─ (roda DEPOIS do conntrack)
|
||||
LOCAL_IN/FORWARD: pass-through ┘ POST_ROUTING: NF_IP_PRI_LAST-1
|
||||
│ (ref da skb + kmalloc pfk_pkt;
|
||||
│ falha de alocação ⇒ NF_ACCEPT = fail-open)
|
||||
▼
|
||||
workqueue pfk_netisr (contexto de processo)
|
||||
│
|
||||
pfk_m_wrap_skb(skb)──► shim struct mbuf
|
||||
│
|
||||
pf_test(af, dir, ifp, &m) ◄── o engine real do OpenBSD 8.0:
|
||||
│ scrub/normalize → lookup de estado
|
||||
│ → regras/anchors/tabelas/quick
|
||||
│ → inserção de estado → veredito
|
||||
▼
|
||||
pass ──► mark |= PFK_DONE_IN/OUT ──► reinjeta: PF_IN: netif_rx() (sobrevivente
|
||||
da remontagem entra no stack)
|
||||
PF_OUT: skb_dst()->output()
|
||||
block/drop ──► kfree_skb() (+ RST/ICMP de retorno gerados pelo próprio PF)
|
||||
fragmento em buffer ──► nossa ref é liberada; pf mantém o sobrevivente (m == NULL)
|
||||
```
|
||||
|
||||
Plano de controle: `/dev/pf` (miscdev, modo 0600, escrita condicionada a
|
||||
`CAP_NET_ADMIN`) → `pfk_ioctl_io()` copia a estrutura de parâmetros usando o
|
||||
tamanho embutido na codificação `_IOR/_IOW` OpenBSD e despacha para o
|
||||
`pfioctl()` portado (`pf_ioctl.c`) — a ABI DIOC* completa, como upstream.
|
||||
`pfctl -e/-f/-s/-t` é o mesmo binário do OpenBSD, recompilado.
|
||||
|
||||
## Filas, divert, pflog — comportamento observável hoje
|
||||
|
||||
- **Filas**: o `pfctl` faz o parse de `queue`/`queue on` (sintaxe 8.0); no
|
||||
kernel a API ifq é implementada por `compat/pfk_ifq.c` com **semântica
|
||||
priq apenas**; o qdisc classful `pfq` e os back ends HFSC/FQ-CoDel chegam
|
||||
em **M5**. `ifq.c`/`hfsc.c`/`fq_codel.c` estão staged e prontos para
|
||||
compilar, mas ainda **não** estão na lista de objetos do módulo.
|
||||
- **Divert**: `divert-to`/tag `divert` produzem o veredito `PF_DIVERT` do PF;
|
||||
`divert_packet()` (`pfsrc/divert_sock.c`) hoje **descarta o pacote com um
|
||||
`pr_warn` rate-limited**, porque a família de sockets AF_DIVERT ainda não
|
||||
foi instanciada. O relay userspace `pdivert` existe e espera
|
||||
`socket(PF_DIVERT=32, SOCK_RAW, IPPROTO_DIVERT=254)`.
|
||||
- **pflog**: `pflog_packet()` retorna sucesso mas **não loga nada** (um
|
||||
único `pr_warn "packet not logged"`); `if_pflog.c` está staged, back end
|
||||
netlink em M4/M5.
|
||||
|
||||
## Milestones (status por feature em feature-matrix.md)
|
||||
|
||||
| Milestone | Escopo | Status (2026-11-11) |
|
||||
|---|---|---|
|
||||
| M0 | repo, scripts, build do kernel, VM liga com kernel próprio | concluído |
|
||||
| M1 | camada de compat, `pf.ko` carrega, `/dev/pf`, `pfctl -f`/`-s info` | concluído |
|
||||
| M2 | núcleo do filtro: regras/estados/tabelas/âncoras, gates VM | **pronto** — gates 01–04 verdes |
|
||||
| M3 | NAT (`nat-to`/`rdr-to`/`binat-to`), scrub, pflog | **pronto** — gates 05/06/07/09 (incl. integridade de 2 MB via redirect) e pflog gate 12 |
|
||||
| M4 | route-to/dup-to/reply-to, pools, divert e2e | **pronto** — gates 08/10/13 e divert gate 11 |
|
||||
| M5 | filas: back ends ifq (hfsc/fq_codel) | **parcial** — back ends compilados no `pf.ko`; anexação/ritmo pendentes |
|
||||
| M6 | docs completas, patchset limpo, suíte verde, releases com tag | em andamento — docs EN+PT-BR completas, suíte 14/14 verde, com tag |
|
||||
|
||||
## Próximas leituras
|
||||
|
||||
[build.md](build.md) → [vm-lab.md](vm-lab.md) → [pf-guide.md](pf-guide.md) →
|
||||
[feature-matrix.md](feature-matrix.md) → [caveats.md](caveats.md).
|
||||
@@ -0,0 +1,105 @@
|
||||
# Aplicando o conjunto de patches PF-on-Linux / guia de compilação
|
||||
|
||||
Este documento é a versão em português de `docs/en/install.md`.
|
||||
|
||||
Alvo: árvore de fontes do **Linux 7.3.4** + módulos out-of-tree `pf.ko`
|
||||
(engine PF, família divert(4), filas ifq). O port é entregue como
|
||||
**árvore de código-fonte + zero patches de core** (ver `patches/kernel/README.md`):
|
||||
o módulo linka apenas símbolos que o kernel 7.3.4 puro já exporta.
|
||||
|
||||
## 1. Pré-requisitos
|
||||
|
||||
| Requisito | Por quê |
|
||||
|---|---|
|
||||
| gcc >= 15, GNU make, flex, bison, bc | build do kernel + pfctl |
|
||||
| `glibc-static` (ou musl-static) | pfctl estático para as VMs guest |
|
||||
| Fontes Linux 7.3.4 | alvo da compilação |
|
||||
| `sys.tar.gz` + `src.tar.gz` do OpenBSD 8.0 | fontes portados (baixados e verificados por sha256; mirror primário openbsd.c3sl.ufpr.br, fallback cdn.openbsd.org) |
|
||||
| root no host de build | `insmod` como root |
|
||||
|
||||
## 2. Passos
|
||||
|
||||
```sh
|
||||
cd pf_port
|
||||
|
||||
# 2.1 busca e verifica as fontes OpenBSD 8.0 (sha256 fixados em VERSIONS)
|
||||
./scripts/fetch-sources.sh
|
||||
./scripts/vendorize.sh # staging em _vendor/upstream + IDS.txt
|
||||
|
||||
# 2.2 prepara o kernel (config + build + preparação p/ módulos externos)
|
||||
KERNELDIR=/path/to/linux-7.3.4 ./scripts/build-kernel.sh
|
||||
# - defconfig + virtio/EXT4 embutidos (boot direto do kernel na VM)
|
||||
# - make bzImage modules_prepare
|
||||
# - copia vmlinux.symvers -> Module.symvers (necessário para builds M=)
|
||||
|
||||
# 2.3 aplica os patches de core (atualmente NENHUM é necessário)
|
||||
./scripts/apply-patches.sh /path/to/linux-7.3.4
|
||||
# patches/kernel/series está vazio por projeto; se futuros milestones
|
||||
# precisarem de exports, cada um entra como 000N-*.patch documentado em
|
||||
# docs/pt-BR/patches.md.
|
||||
|
||||
# 2.4 compila módulo e userland
|
||||
./scripts/build-module.sh # -> module/pf.ko
|
||||
make -C tools # -> tools/out/pfctl (estático)
|
||||
|
||||
# 2.5 instala num sistema 7.3.4 rodando
|
||||
sudo insmod module/pf.ko # cria /dev/pf (0600 root)
|
||||
sudo cp tools/out/pfctl /usr/local/sbin/
|
||||
sudo pfctl -e # habilita
|
||||
sudo pfctl -f /etc/pf.conf # sintaxe real do OpenBSD 8.0
|
||||
```
|
||||
|
||||
## 3. Verificação
|
||||
|
||||
```sh
|
||||
pfctl -s info # "Status: Enabled", contadores ao vivo
|
||||
pfctl -nf /etc/pf.conf # checagem de parse apenas
|
||||
dmesg | grep pfk # hooks registrados (data path via workqueue netisr)
|
||||
```
|
||||
|
||||
Bancada de VMs (Alpine em libvirt): `./scripts/vm-create.sh`,
|
||||
`./scripts/vm-deploy.sh`, `./scripts/vm-run-tests.sh` — ver `docs/pt-BR/vm-lab.md`.
|
||||
|
||||
## 4. Remoção / reversão
|
||||
|
||||
```sh
|
||||
sudo pfctl -d; sudo rmmod pf
|
||||
./scripts/unpatch.sh /path/to/linux-7.3.4 # desfaz patches futuros, se houver
|
||||
```
|
||||
|
||||
## 5. O que "aplicar o patch" significa aqui
|
||||
|
||||
Como a entrega é um módulo out-of-tree, "aplicar o conjunto" = passos
|
||||
2.1–2.4; a árvore Linux intacta é apenas *configurada e compilada*
|
||||
(virtio/EXT4 =y). Nenhum arquivo do kernel é modificado, salvo se um futuro
|
||||
milestone acrescentar `patches/kernel/000N-*.patch` documentado (cada patch:
|
||||
uma seção em docs/pt-BR/patches.md com o quê/por quê/impacto/reversão).
|
||||
|
||||
## 6. Notas sobre os passos acima (2026-11-11)
|
||||
|
||||
- O passo **2.3 é um no-op documentado hoje**: o conjunto de patches está
|
||||
vazio e os scripts `scripts/apply-patches.sh` / `scripts/unpatch.sh` e o
|
||||
arquivo `patches/kernel/series` ainda não existem na árvore (entram junto
|
||||
com o primeiro patch real de core — ver [patches.md](patches.md)). Pode
|
||||
pular 2.3 com segurança.
|
||||
- O passo 2.4 compila apenas o `pfctl` e o verificador de ABI (alvos de
|
||||
`make -C tools`: `pfctl abitest abi test clean`). `pdivert` existe como
|
||||
arquivo-fonte sem alvo no Makefile por enquanto; `pflogd` ainda não foi
|
||||
portado.
|
||||
- Depois do 2.5, o que dá para usar de verdade é o núcleo de filtragem M2
|
||||
(pass/block/quick/keep state/tabelas/anchors); NAT/scrub/queues/divert/
|
||||
pflog dependem dos próximos milestones — consulte a
|
||||
[matriz de features](feature-matrix.md) e leia [pf-guide.md](pf-guide.md)
|
||||
antes de habilitar PF num caminho que você precisa manter vivo.
|
||||
|
||||
## 7. Para onde ir agora
|
||||
|
||||
| | |
|
||||
|---|---|
|
||||
| Arquitetura em uma página | [guide.md](guide.md) |
|
||||
| Etapas de build em detalhe | [build.md](build.md) |
|
||||
| Bancada de VMs de validação | [vm-lab.md](vm-lab.md) |
|
||||
| Regras do dia a dia e avisos | [pf-guide.md](pf-guide.md) |
|
||||
| Divergências conhecidas | [caveats.md](caveats.md) |
|
||||
| Mecanismo de patches de core | [patches.md](patches.md) |
|
||||
| Índice da documentação | [README.md](README.md) |
|
||||
@@ -0,0 +1,74 @@
|
||||
# Conjunto de patches de core do Linux
|
||||
|
||||
English: [docs/en/patches.md](../en/patches.md).
|
||||
|
||||
## Status atual: VAZIO
|
||||
|
||||
O port exige **zero modificações no core do Linux 7.3.4**. O design
|
||||
(spec §5) previa um patch obrigatório — **P1: exportar símbolos usados pelo
|
||||
módulo PF** — mas o compile-port do M1 provou que ele é desnecessário: o
|
||||
modpost reportou **nenhum símbolo indefinido** para o `pf.ko`. A camada de
|
||||
compat foi escrita contra APIs que o kernel puro já exporta
|
||||
(`__inet_lookup_established`, `__inet_lookup_listener`,
|
||||
`__inet6_lookup_established`, `inet6_lookup_listener`, `__udp4_lib_lookup`,
|
||||
`__udp6_lib_lookup`, `ip_route_output_flow`/`ip6_route_output_flags` via
|
||||
wrappers inline, `icmp_send`, …). A evidência e a lista exata estão em
|
||||
`patches/kernel/p1-needs.txt`, que também traz uma **watch list**: por
|
||||
exemplo, `tcp_v4_send_reset` só precisaria de export se helpers de RST de
|
||||
userland forem usados.
|
||||
|
||||
Portanto, `patches/kernel/` não contém nenhum `000N-*.patch` hoje, e aplicar
|
||||
o conjunto (vazio) é um no-op.
|
||||
|
||||
> Nota honesta: `scripts/apply-patches.sh`, `scripts/unpatch.sh` e
|
||||
> `patches/kernel/series` **estão na árvore**. O `series` é vazio por projeto,
|
||||
> então aplicá-lo é um no-op verificado (`PATCHES_APPLIED=0`). Quando um patch
|
||||
> real for necessário, o commit que o adiciona também atualiza o `series` e
|
||||
> as regras abaixo.
|
||||
|
||||
## O mecanismo (como o conjunto deve funcionar)
|
||||
|
||||
- Toda mudança no core do kernel é um arquivo independente
|
||||
`patches/kernel/000N-descricao-curta.patch`, listado em ordem em
|
||||
`patches/kernel/series`, aplicado à árvore pristina com ferramenta no
|
||||
estilo `git apply` e revertido do mesmo jeito (`unpatch.sh` aplica ao
|
||||
contrário).
|
||||
- A árvore nunca pode ficar suja em silêncio: builds reproduzíveis aplicam,
|
||||
compilam e registram o estado (`out/.config`, `out/kernelversion`).
|
||||
- Regras obrigatórias para qualquer patch futuro:
|
||||
1. **Aditivo, zero mudança de comportamento** (por exemplo, linhas
|
||||
`EXPORT_SYMBOL_GPL()` junto aos clusters de export existentes). Qualquer
|
||||
coisa que altere lógica exige antes uma emenda ao design.
|
||||
2. Uma preocupação por patch, numerado em sequência — nunca editar um
|
||||
patch já aceito; substitua com um novo número.
|
||||
3. Uma seção neste arquivo (nos dois idiomas) **antes** do patch entrar:
|
||||
o quê/por quê/impacto/reversão + a evidência em VM.
|
||||
4. O patch tem de sobreviver a `make -C <kerneldir> bzImage modules` a
|
||||
partir de árvore limpa (CI da bancada: `vm-run-tests.sh` depois de um
|
||||
boot novo).
|
||||
|
||||
## Template para uma futura entrada `000N`
|
||||
|
||||
Copie este bloco para `docs/en/patches.md` e `docs/pt-BR/patches.md` (mesma
|
||||
âncora) ao adicionar `000N-*.patch`:
|
||||
|
||||
```
|
||||
### 000N — <título em uma linha>
|
||||
|
||||
- Arquivo: `patches/kernel/000N-<slug>.patch`
|
||||
- Status: aplicado (kernel 7.3.4) / substituído por 000M
|
||||
- Toca: <arquivo(s) da árvore do kernel>, <n> linhas adicionadas, 0 removidas
|
||||
- O quê: <símbolos / hooks / opções de Kconfig adicionados, exatos>
|
||||
- Por quê: <qual código do PF-on-Linux precisa; por que nenhuma API
|
||||
exportada basta>
|
||||
- Impacto: <impacto em runtime/ABI/memória no Linux puro; esperado: nenhum>
|
||||
- Reversão: `./scripts/unpatch.sh <kerneldir>` (aplicação reversa); o módulo
|
||||
passa a não linkar, com o símbolo faltante nomeado no modpost.
|
||||
- Evidência: <id da rodada na VM / data / saída do gate relevante>
|
||||
```
|
||||
|
||||
## Histórico deste diretório
|
||||
|
||||
| Data | Mudança |
|
||||
|---|---|
|
||||
| 2026-11-11 | P1 avaliado após o compile-port do M1 → **não necessário**; `p1-needs.txt` registra a evidência e a watch list. Conjunto permanece vazio. |
|
||||
@@ -0,0 +1,96 @@
|
||||
# Usando o PF-on-Linux no dia a dia
|
||||
|
||||
English: [docs/en/pf-guide.md](../en/pf-guide.md).
|
||||
|
||||
Este é o guia do "o que dá para rodar hoje". Ele segue a
|
||||
[matriz de features](feature-matrix.md): o escopo do **M2 (núcleo de
|
||||
filtragem: pass/block/quick/keep state/tabelas/anchors + habilitar/
|
||||
desabilitar)** tem evidência em VM; tudo além disso é COMPILES-untested ou
|
||||
PENDING. Instalação/build ficam em [install.md](install.md) e
|
||||
[build.md](build.md).
|
||||
|
||||
## Ciclo diário
|
||||
|
||||
```sh
|
||||
sudo insmod module/pf.ko # cria /dev/pf
|
||||
sudo pfctl -nf /etc/pf.conf # checagem de parse (só userland — sempre segura)
|
||||
sudo pfctl -f /etc/pf.conf # carrega o ruleset
|
||||
sudo pfctl -e # HABILITA — o tráfego passa a bater nas regras AGORA
|
||||
sudo pfctl -s info # status + contadores
|
||||
sudo pfctl -s states # listagem de estados (ver ressalva abaixo)
|
||||
sudo pfctl -t blk -T add 10.0.1.10 # atualização de tabela ao vivo
|
||||
sudo pfctl -a admin -f /etc/pf.d/admin.conf
|
||||
sudo pfctl -d # desabilita
|
||||
sudo rmmod pf # descarrega (regras/estados são liberados aqui)
|
||||
```
|
||||
|
||||
> **Atenção — a ordem importa**: `-f` e depois `-e`. Habilitar sem uma regra `pass`
|
||||
> que cubra o caminho de administração corta esse caminho — este port segue
|
||||
> a política padrão de bloqueio do OpenBSD, e as rodadas do gate M2
|
||||
> *realmente derrubaram o ssh da VM de teste* assim (a bancada mantém console
|
||||
> serial exatamente por isso). Num host remoto, libere a interface de
|
||||
> gerência antes de habilitar qualquer coisa.
|
||||
|
||||
## Um ruleset que funciona neste port hoje
|
||||
|
||||
```pf
|
||||
# /etc/pf.conf — apenas escopo M2. Os nomes de interface aqui são os da
|
||||
# bancada (mgmt/lan/wan); troque pelos seus (eth0, enp1s0, …).
|
||||
|
||||
# 1) mantenha você mesmo alcançável (faça isso primeiro, sempre)
|
||||
pass in quick on mgmt
|
||||
pass out quick
|
||||
|
||||
# 2) núcleo de filtragem — comprovado hoje: quick, match de proto/porta, state, drop
|
||||
table <blk> persist # blocklist viva (padrão do gate 03)
|
||||
block in quick proto tcp from <blk> to any
|
||||
|
||||
pass in quick on lan proto tcp from 10.0.1.0/24 to any port { 80 443 } keep state
|
||||
block drop in quick on wan proto icmp from any to any
|
||||
|
||||
# 3) anchors com precedência (padrão do gate 04)
|
||||
anchor "admin"
|
||||
```
|
||||
|
||||
Macros (`xif = "lan"`), `anchor "in/*"` aninhado, `label`, `tag`,
|
||||
`set timeout/limit/state-policy/block-policy/skip` e o resto da gramática do
|
||||
OpenBSD 8.0 **fazem parse** sem problema — o `make -C tools test` exercita
|
||||
tudo isso offline — mas o *comportamento no kernel* da maioria das opções
|
||||
`set` ainda não foi verificado em gate; trate como "carrega e reza" até a
|
||||
matriz mudar.
|
||||
|
||||
## O que evitar até os milestones chegarem
|
||||
|
||||
| Sintaxe | Até | O que acontece hoje |
|
||||
|---|---|---|
|
||||
| `nat-to`, `rdr-to` | — | **Verificado em lab** (gates `05-nat`, `06-rdr`; este último baixa 2 MB por um redirect e compara byte a byte). `nat-to (egress)` expande o *grupo* de interfaces do OpenBSD; num host multi-NIC prefira a forma explícita `nat-to (<iface>)`. O `binat-to` é expandido pelo pfctl num par `nat-to … static-port` + `rdr-to` (gate `07-binat`). |
|
||||
| `scrub (min-ttl, max-mss, df, random-id)`, `set reassemble` | — | **Verificado em lab** (gate `09-scrub.sh`): `min-ttl` e `max-mss` reescrevem de fato pacotes em trânsito. || `divert-to`, tag `divert` | — | **Verificado em lab** (gate `11-divert`): o pacote é entregue a um socket `AF_DIVERT` (`PF_DIVERT=32`) atendido pelo `tools/pdivert`; sem listener é descartado, exatamente como o `divs_noport` do BSD. |
|
||||
| `route-to`, `dup-to`, `reply-to` | — | **Verificado em lab** (gates `08-routeto.sh`, `13-replyto.sh`): o gateway forçado é usado em vez do egress normal, `dup-to` copia mantendo o fluxo, e `reply-to` empurra as respostas de um fluxo para o enlace do gateway. `fail-to` não é palavra-chave no OpenBSD 8.0 (removido upstream). |
|
||||
| `queue` / `queue on` / `pfctl -s queue` | — | **Verificado em lab** (gate `15-queue.sh`): as filas carregam, o hfsc é anexado, `pfctl -s queue -v` mostra as estatísticas das classes e um fluxo de 2 MB pela fila é contado pela classe. `bandwidth` é *garantia sob contenção*, não teto - o pf.conf 8.0 não tem palavra-chave de upperlimit. |
|
||||
| `log`, `log all`, `block log`, `pflogd` | — | **Verificado em lab** (gate `12-pflog`): rode `pflogd /tmp/x.pcap` (lê `/dev/pflog`); o arquivo é um pcap `DLT_PFLOG` (117) legível por tcpdump/wireshark. |
|
||||
| `route-label …` | nunca (não-objetivo) | Rejeitado na camada de ioctl. |
|
||||
| política por container (netns) | fora de escopo | O PF é uma instância global em `init_net`; network namespaces **não** enxergam o PF. |
|
||||
|
||||
## Lendo o estado corretamente
|
||||
|
||||
O `pfctl -s states` tem hoje uma anomalia de listagem/visibilidade sendo
|
||||
corrigida no trabalho do gate M2 (fluxos de trânsito podem passar enquanto
|
||||
nenhum estado é exibido). Até lá, use contadores (`pfctl -s info`) e
|
||||
observação externa (resultado do ping/nc, `tcpdump`) como evidência
|
||||
primária, exatamente como os gates fazem.
|
||||
|
||||
## Sinais no log do kernel que você deve conhecer
|
||||
|
||||
```
|
||||
pfk: PF-on-Linux engine loaded (OpenBSD 8.0 base) ← insmod ok
|
||||
pfk: netfilter hooks registered (10, netisr wq data path)
|
||||
pfk: divert port N: no socket bound # nenhum consumidor em pdivert/pflogd
|
||||
```
|
||||
|
||||
Descarregar o módulo primeiro para os timers de purge e drena a workqueue
|
||||
(um travamento de rmmod observado no lab foi corrigido assim) — mas a rodada
|
||||
de *soak* (ciclo rmmod/insmod sob tráfego) ainda é um gate aberto, então
|
||||
trate o unload como correto para uso administrativo e não comprovado para
|
||||
automação de hot-reload.
|
||||
|
||||
Lista completa das divergências de comportamento: [caveats.md](caveats.md).
|
||||
@@ -0,0 +1,122 @@
|
||||
# Bancada de validação em VMs (libvirt / Alpine)
|
||||
|
||||
English: [docs/en/vm-lab.md](../en/vm-lab.md).
|
||||
|
||||
Todos os comandos abaixo foram lidos dos scripts em `scripts/` (eles são a
|
||||
fonte de verdade); a bancada já foi criada e executada durante M0–M2 — uma
|
||||
rodada completa e verde da suíte é o gate do M2+ e ainda está em andamento
|
||||
(ver §6).
|
||||
|
||||
## 1. Onde ela mora
|
||||
|
||||
| Host | Papel |
|
||||
|---|---|
|
||||
| laptop (este repo) | compila kernel/módulo/ferramentas; comanda tudo por ssh |
|
||||
| **deb** — `root@192.168.1.242` | hipervisor libvirt; roda as 4 VMs Alpine `pftest-*` |
|
||||
|
||||
A bancada não precisa de NAT para a internet; o único acesso externo é a
|
||||
rede libvirt `default` (192.168.122.0/24, mgmt+DHCP) usada para o cloud-init
|
||||
instalar pacotes e para o ssh dos testes. A `sms-vm` existente no deb nunca é
|
||||
tocada.
|
||||
|
||||
## 2. Topologia (fonte única: `lab/ips.env`)
|
||||
|
||||
| VM | Papel | NICs | Kernel |
|
||||
|---|---|---|---|
|
||||
| `pftest-pf0` | filtro sob teste (roda o `pf.ko`) | `mgmt` (dhcp, rede default), `lan` 10.0.1.1/24, `wan` 10.0.2.1/24, `wan2` 10.0.3.1/24 | Alpine padrão via boot direto do kernel extraído da imagem; **ou** o `bzImage` 7.3.4 compilado com `--pf0-kernel=` (`root=/dev/vda2 ro console=ttyS0,115200n8`, sem initrd) |
|
||||
| `pftest-cli` | cliente | `mgmt` dhcp (rotas desabilitadas), `lan` 10.0.1.10/24, gw 10.0.1.1 (pf0) | Alpine padrão |
|
||||
| `pftest-srv` | servidor | `mgmt` dhcp (rotas desabilitadas), `wan` 10.0.2.20/24, gw 10.0.2.1 (pf0), 10.0.3.0/24 via gw2 | Alpine padrão |
|
||||
| `pftest-gw2` | gateway do segundo caminho (ip_forward=1) | `wan2` 10.0.3.2/24, `wan` 10.0.2.2/24 (sem NIC mgmt) | Alpine padrão |
|
||||
|
||||
Todas as VMs recebem `net.ipv4.ip_forward=1` e `rp_filter=0` via cloud-init,
|
||||
senha de root `pftest` mais um par de chaves de laboratório injetado
|
||||
(`/root/.ssh/pflab_ed` no deb, cópia no laptop para ProxyJump), e os pacotes
|
||||
`iperf3 tcpdump python3 scapy bash iptables` (o nome no Alpine é `scapy`; a
|
||||
imagem também precisa de `iptables` para os experimentos de masquerade do
|
||||
pf0).
|
||||
|
||||
Redes libvirt: `default` (mantida como está, iniciada+autostart para os
|
||||
pacotes) e bridges isoladas `pf-lan` 10.0.1.0/24, `pf-wan` 10.0.2.0/24,
|
||||
`pf-wan2` 10.0.3.0/24 — `forward="none"`, sem DHCP, mais IPs de bridge no
|
||||
host `10.0.x.254` no deb para que o deb consiga ssh/icmp na NIC de dados de
|
||||
cada guest. Dimensionamento: 2 vCPU / 1 GB por VM. Os discos são qcow2 por
|
||||
VM com **backing** na imagem compartilhada imutável
|
||||
`/var/lib/libvirt/images/alpine-base.qcow2` (sincronizada de
|
||||
`_vendor/images/alpine-3.22-x86_64-cloud.qcow2` por sha256).
|
||||
|
||||
> Nota de boot: a imagem cloud do Alpine não é inicializável em BIOS/UEFI no
|
||||
> QEMU como entregue (ESP vazia), então *todas* as VMs usam boot direto do
|
||||
> kernel extraído da própria imagem; `--pf0-kernel=` apenas troca o kernel
|
||||
> do pf0 pelo compilado.
|
||||
|
||||
## 3. Recriar / deployar / destruir
|
||||
|
||||
```sh
|
||||
./scripts/vm-create.sh # idempotente: derruba e recria domínios + seeds pftest-*
|
||||
./scripts/vm-create.sh --pf0-kernel=out/linux-7.3.4-bzImage # pf0 sobe com o kernel compilado (T6)
|
||||
./scripts/vm-create.sh --recreate-base # força re-sync da imagem base
|
||||
./scripts/vm-deploy.sh # laptop→deb ($DEPLOY_DIR)→pf0:/opt/pf:
|
||||
# out/*bzImage, module/*.ko, tools/out/*
|
||||
./scripts/vm-destroy.sh # domínios, discos, seeds, redes pf-* e fragmentos ssh
|
||||
./scripts/vm-destroy.sh --purge-base --purge-keys # + imagem base + chaves do lab
|
||||
```
|
||||
|
||||
O `vm-create.sh` termina validando `ssh pf0 'ip -br a'` e deixa todas as VMs
|
||||
ligadas. Os aliases de ssh do laptop (`pf0|cli|srv|gw2`, ProxyJump via deb)
|
||||
são gerados em `~/.ssh/config.d/pflab`.
|
||||
|
||||
## 4. Rodando a suíte
|
||||
|
||||
```sh
|
||||
./scripts/vm-run-tests.sh # ou: make test
|
||||
```
|
||||
|
||||
Determinístico por projeto: **antes de cada gate** o runner destrói e
|
||||
reinicia o `pftest-pf0` (delta de disco e módulo zerados), espera o ssh no
|
||||
endereço DHCP de mgmt `192.168.122.8`, re-deploya `pf.ko`/`pfctl`/`*.conf` no
|
||||
guest e então roda o script do gate a partir do **laptop** (os gates falam
|
||||
com as VMs através do deb via ssh aninhado — `tests/vm/lib.sh`). A saída de
|
||||
cada gate é gravada em `out/test-logs/<gate>.sh.log`; o runner imprime
|
||||
`PASS <gate>` / `FAIL <gate> (rc=...)` por teste, um resumo `PASS=n FAIL=m`
|
||||
e sai com código diferente de zero se algo falhou.
|
||||
|
||||
## 5. O que cada gate prova hoje
|
||||
|
||||
| Gate | Cenário (verificado com tráfego real, não com código de saída) |
|
||||
|---|---|
|
||||
| `01-state.sh` | `pass in/out quick proto icmp keep state` → cli pinga srv **através** do pf0 (trânsito); depois o pf0 lista um estado icmp via `pfctl -s states` |
|
||||
| `02-block.sh` | `block drop in quick proto icmp` → o ping do cli falha; `block return-rst in quick proto tcp … port 8080` → o `nc` do cli para srv:8080 é recusado (RST), checado pelo código de saída do nc |
|
||||
| `03-tables.sh` | `table <blk> { 10.0.1.10 }` + `block in quick from <blk>` → `pfctl -t blk -T show` lista; o ping do cli é bloqueado; `-T delete` ao vivo libera o fluxo |
|
||||
| `04-anchors.sh` | regra de anchor (`-a restricted -f`) liberando icmp é avaliada **antes** do `block` do ruleset principal (posicionamento top/quick); `pfctl -s Anchors` lista o anchor |
|
||||
|
||||
Gates planejados (documento de plano, T11–T18): 05-nat, 06-rdr, 07-binat,
|
||||
08-scrub (scapy), 09-routeto, 10-dup-fail, 11-divert, 12-queues (tolerância
|
||||
de ±15% no rate do iperf), 13-pflog, 14-soak (reload sob tráfego + ciclo de
|
||||
rmmod + kmemleak). IPv6 é smoke test para state/block/nat66/scrub. O
|
||||
`bench-basic.sh` (planejado, ainda não está na árvore) é informativo; não
|
||||
existe gate numérico de performance.
|
||||
|
||||
## 6. Status atual da suíte (2026-11-11, com honestidade)
|
||||
|
||||
Os gates 01–04 do M2 existem e rodam, mas **ainda não estão todos verdes** —
|
||||
o caminho de dados (modelo netisr/workqueue) e a visibilidade de estados
|
||||
estão sendo corrigidos no trabalho do gate M2. A última rodada capturada
|
||||
(`out/test-logs/`) mostra o estado misto: ping de trânsito OK / listagem de
|
||||
estado falhando no 01, icmp bloqueado OK no 02, resultados parciais no 03, 04
|
||||
abortado. Trate "VERIFIED-in-VM" na
|
||||
[matriz de features](feature-matrix.md) como reservado a gates que passam
|
||||
numa rodada completa e limpa; nada além do M1 é declarado VERIFIED até lá.
|
||||
|
||||
## 7. Inspeção manual
|
||||
|
||||
```sh
|
||||
ssh pf0 # via alias do laptop (ProxyJump deb)
|
||||
insmod /opt/pf/pf.ko
|
||||
/opt/pf/pfctl -e
|
||||
/opt/pf/pfctl -f /tmp/g1.conf
|
||||
/opt/pf/pfctl -s info ; /opt/pf/pfctl -s states -v
|
||||
dmesg | grep pfk
|
||||
```
|
||||
|
||||
Artefatos de rodadas completas futuras (log + pcaps) devem ir junto com o
|
||||
release no Gitea (spec §7).
|
||||
+1
-1
@@ -1 +1 @@
|
||||
savedcmd_pf.mod := printf '%s\n' pfsrc/pfk_mod.o pfsrc/pfk_hooks.o compat/pfk_mbuf.o compat/pfk_kern.o compat/pfk_if.o compat/pfk_xmit.o compat/pfk_pcb.o compat/pfk_ip4.o compat/siphash.o compat/toeplitz.o compat/md5.o compat/sha2.o compat/radix.o compat/pfk_rtable.o compat/pfk_ip6.o compat/subr_tree.o pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o compat/pfk_ifq.o | awk '!x[$$0]++ { print("./"$$0) }' > pf.mod
|
||||
savedcmd_pf.mod := printf '%s\n' pfsrc/pfk_mod.o pfsrc/pfk_hooks.o compat/pfk_mbuf.o compat/pfk_kern.o compat/pfk_if.o compat/pfk_xmit.o compat/pfk_pcb.o compat/pfk_ip4.o compat/siphash.o compat/toeplitz.o compat/md5.o compat/sha2.o compat/radix.o compat/pfk_rtable.o compat/pfk_ip6.o compat/subr_tree.o pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o pfsrc/fq_codel.o pfsrc/hfsc.o compat/pfk_ifq.o | awk '!x[$$0]++ { print("./"$$0) }' > pf.mod
|
||||
+1
-1
@@ -20,7 +20,7 @@ pf-objs := pfsrc/pfk_mod.o pfsrc/pfk_hooks.o \
|
||||
# ported OpenBSD 8.0 engine
|
||||
pf-objs += pfsrc/pf_ruleset.o pfsrc/pf_table.o pfsrc/pf_norm.o pfsrc/pf_if.o \
|
||||
pfsrc/pf_lb.o pfsrc/pf_osfp.o pfsrc/pf_syncookies.o \
|
||||
pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o
|
||||
pfsrc/pf_ioctl.o pfsrc/pf.o pfsrc/divert_sock.o pfsrc/pfk_pflog.o pfsrc/fq_codel.o pfsrc/hfsc.o
|
||||
|
||||
# queueing framework (compat/pfk_ifq.c implements the ifq API with priq
|
||||
# semantics; the OpenBSD hfsc/fq_codel back ends land in milestone M5)
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/md5.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/md5.o: $(deps_compat/md5.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_if.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_if.o: $(deps_compat/pfk_if.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_ifq.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_ifq.o: $(deps_compat/pfk_ifq.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_ip4.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_ip4.o: $(deps_compat/pfk_ip4.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_ip6.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_ip6.o: $(deps_compat/pfk_ip6.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_kern.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_kern.o: $(deps_compat/pfk_kern.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_mbuf.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_mbuf.o: $(deps_compat/pfk_mbuf.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_pcb.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
/home/lgcosta/lab/linux_kernel/linux-7.3.4/include/net/inet6_hashtables.h \
|
||||
|
||||
compat/pfk_pcb.o: $(deps_compat/pfk_pcb.o)
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/pfk_rtable.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/pfk_rtable.o: $(deps_compat/pfk_rtable.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,9 @@ deps_compat/pfk_xmit.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
include/pfk_api.h \
|
||||
|
||||
compat/pfk_xmit.o: $(deps_compat/pfk_xmit.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/radix.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/radix.o: $(deps_compat/radix.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/sha2.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/sha2.o: $(deps_compat/sha2.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/siphash.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/siphash.o: $(deps_compat/siphash.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/subr_tree.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
compat/subr_tree.o: $(deps_compat/subr_tree.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_compat/toeplitz.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
/home/lgcosta/lab/linux_kernel/linux-7.3.4/include/crypto/hash.h \
|
||||
/home/lgcosta/lab/linux_kernel/linux-7.3.4/include/linux/crypto.h \
|
||||
|
||||
|
||||
+103
-27
@@ -217,10 +217,14 @@ pfk_pfq_enqueue(void *arg, struct mbuf *m)
|
||||
struct pfk_pfq *pfq = arg;
|
||||
|
||||
if (!pfq)
|
||||
return NULL;
|
||||
if (ifq_enqueue(&pfq->ifq, m) != 0)
|
||||
return NULL;
|
||||
return m;
|
||||
return m; /* caller keeps ownership */
|
||||
/*
|
||||
* ifq_enqueue takes ownership of m (the scheduler may drop it); we then
|
||||
* drain immediately, so nothing is returned for the caller to send.
|
||||
*/
|
||||
ifq_enqueue(&pfq->ifq, m);
|
||||
ifq_start(&pfq->ifq);
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static struct mbuf *
|
||||
@@ -273,10 +277,11 @@ static const struct pfq_ops pfk_priq_pfq_ops = {
|
||||
* packets are still queued, but the traffic shaping curves are not yet
|
||||
* applied — recorded in the feature matrix as pending M5).
|
||||
*/
|
||||
const struct ifq_ops * const ifq_hfsc_ops = &pfk_priq_ifq_ops;
|
||||
const struct ifq_ops * const ifq_fqcodel_ops = &pfk_priq_ifq_ops;
|
||||
const struct pfq_ops * const pfq_hfsc_ops = &pfk_priq_pfq_ops;
|
||||
const struct pfq_ops * const pfq_fqcodel_ops = &pfk_priq_pfq_ops;
|
||||
/*
|
||||
* M5: the real scheduler back ends (pfsrc/hfsc.c, pfsrc/fq_codel.c) define
|
||||
* ifq_hfsc_ops/pfq_hfsc_ops/ifq_fqcodel_ops/pfq_fqcodel_ops themselves; the
|
||||
* priq shim above stays as the default for interfaces without a queue rule.
|
||||
*/
|
||||
|
||||
/* ---------------- framework ---------------- */
|
||||
void
|
||||
@@ -302,7 +307,36 @@ ifq_attach(struct ifqueue *ifq, const struct ifq_ops *ops, void *opsarg)
|
||||
if (!opsarg && ops->ifqop_alloc)
|
||||
opsarg = ops->ifqop_alloc(0, NULL);
|
||||
ifq->ifq_ops = ops;
|
||||
/*
|
||||
* The port's own helpers use ifq_softc; the staged OpenBSD schedulers
|
||||
* (hfsc/fq_codel) read ifq->ifq_q. Keep both in sync or the back ends
|
||||
* dereference a NULL scheduler state.
|
||||
*/
|
||||
ifq->ifq_softc = opsarg;
|
||||
ifq->ifq_q = opsarg;
|
||||
}
|
||||
|
||||
/*
|
||||
* Scheduler hand-off used by the ported back ends (hfsc/fq_codel) when they
|
||||
* need their per-interface state. PFLINUX: the port has no ifq mutex (the
|
||||
* data path is a single ordered work queue), so "enter" is a plain ownership
|
||||
* check and "leave" is a no-op - the pair exists to mirror OpenBSD's API.
|
||||
*/
|
||||
void *
|
||||
ifq_q_enter(struct ifqueue *ifq, const struct ifq_ops *ops)
|
||||
{
|
||||
if (ifq == NULL || ops == NULL || ifq->ifq_ops != ops)
|
||||
return NULL; /* another scheduler owns it */
|
||||
if (ifq->ifq_softc == NULL && ops->ifqop_alloc)
|
||||
ifq->ifq_softc = ops->ifqop_alloc(0, NULL);
|
||||
return ifq->ifq_softc;
|
||||
}
|
||||
|
||||
void
|
||||
ifq_q_leave(struct ifqueue *ifq, void *q)
|
||||
{
|
||||
(void)ifq;
|
||||
(void)q;
|
||||
}
|
||||
|
||||
void
|
||||
@@ -312,19 +346,35 @@ ifq_destroy(struct ifqueue *ifq)
|
||||
ifq->ifq_ops->ifqop_free(0, ifq->ifq_softc);
|
||||
ifq->ifq_ops = NULL;
|
||||
ifq->ifq_softc = NULL;
|
||||
ifq->ifq_q = NULL;
|
||||
}
|
||||
|
||||
/*
|
||||
* ifqop_enq returns the packet the scheduler decided to DROP (possibly the one
|
||||
* just offered), and NULL when the packet was accepted - it is NOT an error
|
||||
* code. Freeing the returned mbuf is this layer's job.
|
||||
*/
|
||||
int
|
||||
ifq_enqueue(struct ifqueue *ifq, struct mbuf *m)
|
||||
{
|
||||
if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_enq)
|
||||
struct mbuf *dm;
|
||||
|
||||
if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_enq) {
|
||||
m_freem(m);
|
||||
return EINVAL;
|
||||
}
|
||||
if (ifq->ifq_maxlen && ifq->ifq_len >= ifq->ifq_maxlen) {
|
||||
ifq->ifq_errors++;
|
||||
ifq->ifq_qdrops++;
|
||||
m_freem(m);
|
||||
return ENOBUFS;
|
||||
}
|
||||
return ifq->ifq_ops->ifqop_enq(ifq, m) ? 0 : ENOMEM;
|
||||
dm = ifq->ifq_ops->ifqop_enq(ifq, m);
|
||||
if (dm) {
|
||||
ifq->ifq_qdrops++;
|
||||
m_freem(dm);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
struct mbuf *
|
||||
@@ -336,14 +386,16 @@ ifq_deq_begin(struct ifqueue *ifq)
|
||||
if (!ifq->ifq_ops || !ifq->ifq_ops->ifqop_deq_begin)
|
||||
return NULL;
|
||||
m = ifq->ifq_ops->ifqop_deq_begin(ifq, &cookie);
|
||||
ifq->ifq_dequeue = cookie;
|
||||
return m;
|
||||
}
|
||||
|
||||
void
|
||||
ifq_deq_commit(struct ifqueue *ifq, struct mbuf *m)
|
||||
{
|
||||
void *cookie = NULL;
|
||||
void *cookie = ifq->ifq_dequeue;
|
||||
|
||||
ifq->ifq_dequeue = NULL;
|
||||
if (ifq->ifq_ops && ifq->ifq_ops->ifqop_deq_commit)
|
||||
ifq->ifq_ops->ifqop_deq_commit(ifq, m, cookie);
|
||||
}
|
||||
@@ -365,12 +417,52 @@ ifq_dequeue(struct ifqueue *ifq)
|
||||
return m;
|
||||
}
|
||||
|
||||
/*
|
||||
* Drain the queue as far as the scheduler allows and hand each packet to the
|
||||
* stack's output path. OpenBSD calls if_start from softint context; here it
|
||||
* runs either from the pf work queue (enqueue side) or from the scheduler's
|
||||
* deferred timeout (pacing side), which is what makes hfsc's bandwidth
|
||||
* limits take effect.
|
||||
*/
|
||||
void
|
||||
ifq_start(struct ifqueue *ifq)
|
||||
{
|
||||
struct mbuf *m;
|
||||
int n;
|
||||
|
||||
n = 0;
|
||||
ifq->ifq_oactive = 1;
|
||||
while ((m = ifq_dequeue(ifq)) != NULL) {
|
||||
n++;
|
||||
if (pfk_ifq_transmit(ifq, m))
|
||||
break; /* device busy: packet kept */
|
||||
}
|
||||
ifq->ifq_oactive = 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* pf data-path entry: hand a packet to the interface's scheduler when one is
|
||||
* attached (a pf `queue' rule is configured). Returns 1 when the queue took
|
||||
* ownership of m, 0 when the caller must keep going (priq/no scheduler).
|
||||
*/
|
||||
int
|
||||
pf_kifq_input(struct pfk_ifnet *ifp, struct mbuf *m)
|
||||
{
|
||||
struct ifqueue *ifq;
|
||||
|
||||
if (ifp == NULL || m == NULL)
|
||||
return 0;
|
||||
if (ifp == NULL)
|
||||
return 0;
|
||||
ifq = &ifp->if_snd;
|
||||
if (ifq->ifq_ops == NULL || ifq->ifq_ops == ifq_priq_ops)
|
||||
return 0; /* no scheduler: fast path */
|
||||
if (ifq_enqueue(ifq, m) != 0)
|
||||
return 1; /* dropped by the queue: owned */
|
||||
ifq_start(ifq);
|
||||
return 1;
|
||||
}
|
||||
|
||||
unsigned int
|
||||
ifq_purge(struct ifqueue *ifq)
|
||||
{
|
||||
@@ -423,19 +515,3 @@ ifq_hdatalen(struct ifqueue *ifq)
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* ---------------- scheduler back ends (milestone M5) ---------------- */
|
||||
/* The staged OpenBSD hfsc.c/fq_codel.c are not in the build yet; the priq
|
||||
* ops above are the active scheduler. These wrappers keep pf_ioctl's
|
||||
* initialisation calls valid until M5 replaces them with the ported
|
||||
* schedulers (docs/porting-notes.md). */
|
||||
void
|
||||
hfsc_initialize(void)
|
||||
{
|
||||
pr_info("pfk: hfsc back end pending M5 (priq active)\n");
|
||||
}
|
||||
|
||||
void
|
||||
fq_codel_initialize(void)
|
||||
{
|
||||
pr_info("pfk: fq_codel back end pending M5 (priq active)\n");
|
||||
}
|
||||
+17
-15
@@ -47,8 +47,21 @@ pfk_printk_compat(const char *fmt, ...)
|
||||
void
|
||||
splassert_fail(int expected, int actual, const char *func)
|
||||
{
|
||||
pr_err("splassert: %s: expected %d, got %d\n", func, expected, actual);
|
||||
BUG();
|
||||
/*
|
||||
* PFLINUX: OpenBSD's splassert() checks a per-CPU spl level, so
|
||||
* "assert unlocked" really means "this context did not take the lock".
|
||||
* The port replaced spl with rw-semas plus work queues, where
|
||||
* rw_status() is a global counter: an assert-unlocked in a work-queue
|
||||
* task fires whenever *another* CPU happens to hold the lock, which is
|
||||
* not a bug (the task never acquires pf_lock itself) and was turning a
|
||||
* harmless race into a kernel BUG() that wedged the module in
|
||||
* "Unloading". Report it once instead of killing the host; the
|
||||
* structural invariant the BSD assert protects - purge never runs while
|
||||
* holding pf_lock - is upheld by the call sites (pf_purge_* are only
|
||||
* reached from systqmp tasks and timer work).
|
||||
*/
|
||||
pr_warn_ratelimited("pfk: splassert: %s: expected %d, got %d\n",
|
||||
func, expected, actual);
|
||||
}
|
||||
|
||||
/* ---------------- addlog (OpenBSD kern.log) ---------------- */
|
||||
@@ -619,16 +632,5 @@ if_congested(void)
|
||||
}
|
||||
|
||||
|
||||
/* ---------------- pflog (netlink backend, milestone M4) ---------------- */
|
||||
/* NPFLOG=1: the staged if_pflog.c needs the OpenBSD ifpf layer; until the
|
||||
* netlink-backed pflog lands (M4), pflog_packet() consumes nothing and
|
||||
* reports the missing backend at least once so logged packets are never
|
||||
* silently vanished (see docs/porting-notes.md). */
|
||||
int
|
||||
pflog_packet(struct pf_pdesc *pd, u_int8_t reason, struct pf_rule *rm,
|
||||
struct pf_rule *am, struct pf_ruleset *ruleset, struct pf_rule *cm)
|
||||
{
|
||||
(void)pd; (void)reason; (void)rm; (void)am; (void)ruleset; (void)cm;
|
||||
pr_warn_once("pfk: pflog backend pending M4; packet not logged\n");
|
||||
return (0);
|
||||
}
|
||||
/* pflog_packet() lives in pfsrc/pfk_pflog.c (the /dev/pflog backend). */
|
||||
|
||||
@@ -607,3 +607,14 @@ pfk_mbuf_exit(void)
|
||||
{
|
||||
kmem_cache_destroy(pfk_mbuf_cache);
|
||||
}
|
||||
|
||||
void
|
||||
ml_purge(struct mbuf_list *ml)
|
||||
{
|
||||
struct mbuf *m;
|
||||
|
||||
while ((m = ml_dequeue(ml)) != NULL)
|
||||
m_freem(m);
|
||||
ml->ml_first = ml->ml_last = NULL;
|
||||
ml->ml_len = 0;
|
||||
}
|
||||
@@ -6,6 +6,7 @@
|
||||
* ip6_route_output, tcp_v4_send_reset if needed).
|
||||
*/
|
||||
#include <pfk.h>
|
||||
#include <pfk_api.h>
|
||||
|
||||
static struct dst_entry *
|
||||
pfk_route4(__be32 daddr, __be32 saddr, int oif)
|
||||
@@ -23,6 +24,26 @@ pfk_route4(__be32 daddr, __be32 saddr, int oif)
|
||||
return &rt->dst;
|
||||
}
|
||||
|
||||
/*
|
||||
* Forced nexthop (route-to/dup-to/reply-to). Linux resolves the neighbour
|
||||
* from the *packet's* destination unless the route says it goes through a
|
||||
* gateway (ip_neigh_for_gw() only honours rt_gw4 when rt_gw_family is set),
|
||||
* which would ARP the final host on the gateway's link. Look the gateway up
|
||||
* as its own host route and mark it as the nexthop - the same pattern OVS
|
||||
* uses after its own FIB lookups.
|
||||
*/
|
||||
static struct dst_entry *
|
||||
pfk_route4_nh(__be32 gw, int oif)
|
||||
{
|
||||
struct rtable *rt = (struct rtable *)pfk_route4(gw, 0, oif);
|
||||
|
||||
if (rt == NULL)
|
||||
return NULL;
|
||||
rt->rt_gw_family = AF_INET;
|
||||
rt->rt_gw4 = gw;
|
||||
return &rt->dst;
|
||||
}
|
||||
|
||||
#if IS_ENABLED(CONFIG_IPV6)
|
||||
static struct dst_entry *
|
||||
pfk_route6(const struct in6_addr *daddr, const struct in6_addr *saddr, int oif)
|
||||
@@ -67,13 +88,16 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
|
||||
}
|
||||
switch (sa->sa_family) {
|
||||
case AF_INET: {
|
||||
struct pf_ip *ip = mtod(m, struct pf_ip *);
|
||||
__be32 gw = 0;
|
||||
|
||||
/* if route was forced (route-to), dst holds gw sockaddr
|
||||
* stored in sin_addr by pf_route; normal case dst==final */
|
||||
gw = sintosa(dst)->sin_addr.s_addr;
|
||||
d = pfk_route4(gw, ip->ip_src.s_addr, ifp->if_index);
|
||||
/* PFLINUX: look the route up by destination only. Passing the
|
||||
* packet's source (a transit address, not local to us) makes
|
||||
* ip_route_output_key fail with ENETUNREACH; ip_output keeps
|
||||
* the header source untouched. */
|
||||
d = pfk_route4_nh(gw, ifp->if_index);
|
||||
if (!d) {
|
||||
ret = EHOSTUNREACH;
|
||||
goto drop;
|
||||
@@ -83,13 +107,11 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
|
||||
}
|
||||
#if IS_ENABLED(CONFIG_IPV6)
|
||||
case AF_INET6: {
|
||||
struct pf_ip6_hdr *ip6 = mtod(m, struct pf_ip6_hdr *);
|
||||
const struct in6_addr *gw = &sin6tosa(dst)->sin6_addr;
|
||||
|
||||
if (!d)
|
||||
d = pfk_route6(gw,
|
||||
(struct in6_addr *)&ip6->ip6_src,
|
||||
ifp->if_index);
|
||||
/* PFLINUX: destination-only, as for IPv4 */
|
||||
d = pfk_route6(gw, NULL, ifp->if_index);
|
||||
if (!d) {
|
||||
ret = EHOSTUNREACH;
|
||||
goto drop;
|
||||
@@ -114,6 +136,28 @@ if_output_tso(struct pfk_ifnet *ifp, struct mbuf **mp, void *dst,
|
||||
ret = ENETDOWN;
|
||||
goto drop_dst_nofree;
|
||||
}
|
||||
/*
|
||||
* The stack's output path always consumes exactly one skb reference.
|
||||
* Take our own so the caller's references (the hook queue ref and the
|
||||
* mbuf wrapper ref) stay balanced - without this the work queue's
|
||||
* cleanup double-frees the skb and corrupts the slab.
|
||||
*/
|
||||
/*
|
||||
* pf_route() has already evaluated the OUT ruleset (it calls
|
||||
* pf_test(PF_OUT) itself, exactly like OpenBSD's ip_forward). Mark the
|
||||
* packet so our POST_ROUTING hook does not run the out ruleset a second
|
||||
* time - that re-match hits the state, re-enters pf_route and recurses
|
||||
* (OpenBSD stops this with PF_TAG_PROCESSED carried in the mbuf).
|
||||
*/
|
||||
skb->mark |= PFK_DONE_OUT;
|
||||
/*
|
||||
* The port stashes its mbuf pointer in skb->cb; the IP stack uses the
|
||||
* same bytes as its own control block (IPCB). Hand the packet to the
|
||||
* stack with a clean cb, otherwise ip_output() reads our pointer as
|
||||
* frag_max_size/flags and the packet is silently lost.
|
||||
*/
|
||||
memset(skb->cb, 0, sizeof(skb->cb));
|
||||
skb_get(skb);
|
||||
ret = skb_dst(skb)->output(&init_net, NULL, skb);
|
||||
/* output consumed skb (and wrapper); avoid double free */
|
||||
if (ret == 0) {
|
||||
@@ -226,3 +270,40 @@ pfk_if_output(struct pfk_ifnet *ifp, struct mbuf *m, void *dst,
|
||||
m_freem(mp);
|
||||
return err;
|
||||
}
|
||||
|
||||
/*
|
||||
* Transmit one queued packet. Called from ifq_start() - i.e. from the pf
|
||||
* work queue or from a scheduler's deferred timeout - and always consumes the
|
||||
* mbuf. Returns 0 (keep draining); a scheduler that wants to defer does so by
|
||||
* simply not returning a packet from ifqop_deq_begin().
|
||||
*/
|
||||
int
|
||||
pfk_ifq_transmit(struct ifqueue *ifq, struct mbuf *m)
|
||||
{
|
||||
struct sk_buff *skb = m_to_skb(m);
|
||||
struct dst_entry *d;
|
||||
|
||||
(void)ifq;
|
||||
if (skb == NULL) {
|
||||
m_freem(m);
|
||||
return 0;
|
||||
}
|
||||
d = skb_dst(skb);
|
||||
if (d == NULL || IS_ERR(d) || d->dev == NULL || !netif_running(d->dev)) {
|
||||
m_freem(m);
|
||||
return 0;
|
||||
}
|
||||
skb->dev = d->dev;
|
||||
skb_reset_network_header(skb);
|
||||
if (skb->protocol == 0)
|
||||
skb->protocol = htons(ip_hdr(skb)->protocol == IPPROTO_IPV6 ?
|
||||
ETH_P_IPV6 : ETH_P_IP);
|
||||
/* the stack owns skb->cb (IPCB) from here; pf already tested it */
|
||||
memset(skb->cb, 0, sizeof(skb->cb));
|
||||
skb->mark |= PFK_DONE_OUT;
|
||||
skb_get(skb); /* the output path consumes one reference */
|
||||
m->skb = NULL; /* the mbuf's reference moves to the stack */
|
||||
m_freem(m);
|
||||
d->output(&init_net, NULL, skb);
|
||||
return 0;
|
||||
}
|
||||
+35
-7
@@ -46,7 +46,34 @@
|
||||
#endif
|
||||
|
||||
|
||||
#define SALEN(sa) (*(u_char *)(sa))
|
||||
/*
|
||||
* PFLINUX: OpenBSD's SALEN() reads the BSD sockaddr's sa_len byte. Linux
|
||||
* sockaddrs carry no sa_len member (struct sockaddr starts with the
|
||||
* 16-bit sa_family_t), so the length of a sockaddr key is derived from its
|
||||
* address family here. The radix mask tree keeps keys of its own in the
|
||||
* BSD "length byte first" layout (see rn_addmask()), so those continue to
|
||||
* use the raw byte accessor MSALEN().
|
||||
*/
|
||||
#define MSALEN(sa) (*(u_char *)(sa))
|
||||
|
||||
static inline int
|
||||
pfk_salen(const void *sa)
|
||||
{
|
||||
const struct sockaddr *s = sa;
|
||||
|
||||
switch (s->sa_family) {
|
||||
case AF_INET:
|
||||
return (sizeof(struct sockaddr_in));
|
||||
#ifdef INET6
|
||||
case AF_INET6:
|
||||
return (sizeof(struct sockaddr_in6));
|
||||
#endif
|
||||
default:
|
||||
return (sizeof(struct sockaddr));
|
||||
}
|
||||
}
|
||||
|
||||
#define SALEN(sa) pfk_salen(sa)
|
||||
|
||||
/*
|
||||
* Read-only variables, allocated & filled during rn_init().
|
||||
@@ -215,7 +242,7 @@ rn_satisfies_leaf(char *trial, struct radix_node *leaf, int skip)
|
||||
if (cp3 == NULL)
|
||||
cp3 = rn_ones;
|
||||
else
|
||||
length = min(length, SALEN(cp3));
|
||||
length = min(length, MSALEN(cp3));
|
||||
cplim = cp + length;
|
||||
cp += skip;
|
||||
cp2 += skip;
|
||||
@@ -252,7 +279,7 @@ rn_match(void *v_arg, struct radix_node_head *head)
|
||||
* are probably the most common case...
|
||||
*/
|
||||
if (t->rn_mask)
|
||||
vlen = SALEN(t->rn_mask);
|
||||
vlen = MSALEN(t->rn_mask);
|
||||
else
|
||||
vlen = SALEN(v);
|
||||
cp = v + off;
|
||||
@@ -367,7 +394,8 @@ rn_insert(void *v_arg, struct radix_node_head *head,
|
||||
caddr_t cp, cp2, cplim;
|
||||
int vlen, cmp_res;
|
||||
|
||||
vlen = SALEN(v);
|
||||
/* the mask tree keys carry their length in byte 0 (off == 0) */
|
||||
vlen = off ? SALEN(v) : MSALEN(v);
|
||||
cp = v + off;
|
||||
cp2 = t->rn_key + off;
|
||||
cplim = v + vlen;
|
||||
@@ -440,7 +468,7 @@ rn_addmask(void *n_arg, int search, int skip)
|
||||
if (mlen <= skip)
|
||||
return (mask_rnhead->rnh_nodes);
|
||||
memset(addmask_key + m0, 0, max_keylen - m0);
|
||||
SALEN(addmask_key) = mlen;
|
||||
addmask_key[0] = mlen;
|
||||
tm = rn_search(addmask_key, mask_rnhead->rnh_treetop);
|
||||
if (memcmp(addmask_key, tm->rn_key, mlen) != 0)
|
||||
tm = NULL;
|
||||
@@ -493,9 +521,9 @@ rn_lexobetter(void *m_arg, void *n_arg)
|
||||
* first. The netmasks were normalized before calling this function and
|
||||
* don't have unneeded trailing zeros.
|
||||
*/
|
||||
if (SALEN(mp) > SALEN(np))
|
||||
if (MSALEN(mp) > MSALEN(np))
|
||||
return 1;
|
||||
if (SALEN(mp) < SALEN(np))
|
||||
if (MSALEN(mp) < MSALEN(np))
|
||||
return 0;
|
||||
/*
|
||||
* Must return the first difference between the masks
|
||||
|
||||
@@ -27,6 +27,7 @@ struct ifqueue {
|
||||
struct mbuf_list *ifq_free; /* free list (unused in the port) */
|
||||
unsigned int ifq_len;
|
||||
unsigned int ifq_oactive;
|
||||
void *ifq_dequeue; /* cookie between deq_begin/commit */
|
||||
|
||||
/* statistics */
|
||||
u_int64_t ifq_packets;
|
||||
|
||||
@@ -164,13 +164,34 @@ struct { \
|
||||
/*
|
||||
* List definitions.
|
||||
*/
|
||||
#define LIST_HEAD(name, type) \
|
||||
/*
|
||||
* PFLINUX: LIST_HEAD has two spellings in this tree. The ported OpenBSD
|
||||
* engine uses the BSD form LIST_HEAD(name, type) (a struct with lh_first),
|
||||
* while the port's own glue (pfsrc/divert_sock.c, compat/pfk_kern.c,
|
||||
* compat/pfk_if.c) uses Linux's list.h form LIST_HEAD(name) (an initialised
|
||||
* struct list_head). compat/sys/queue.h is included after Linux's list.h,
|
||||
* so the BSD definition used to shadow the Linux one and broke the glue
|
||||
* translation units. Dispatch on the argument count so both spellings
|
||||
* work; LIST_HEAD_INIT is provided with Linux's exact text so that a later
|
||||
* include of <linux/list.h> redefinition stays identical.
|
||||
*/
|
||||
#define LIST_HEAD_INITIALIZER(head) \
|
||||
{ NULL }
|
||||
|
||||
#define LIST_HEAD_INIT(name) { &(name), &(name) }
|
||||
|
||||
#define LIST_HEAD_BSD(name, type) \
|
||||
struct name { \
|
||||
struct type *lh_first; /* first element */ \
|
||||
}
|
||||
|
||||
#define LIST_HEAD_INITIALIZER(head) \
|
||||
{ NULL }
|
||||
#define LIST_HEAD_LINUX(name) \
|
||||
struct list_head name = LIST_HEAD_INIT(name)
|
||||
|
||||
#define LIST_HEAD_SELECT(_1, _2, NAME, ...) NAME
|
||||
#define LIST_HEAD(...) \
|
||||
LIST_HEAD_SELECT(__VA_ARGS__, LIST_HEAD_BSD, LIST_HEAD_LINUX) \
|
||||
(__VA_ARGS__)
|
||||
|
||||
#define LIST_ENTRY(type) \
|
||||
struct { \
|
||||
|
||||
@@ -23,10 +23,14 @@ static inline bool refcnt_take_not0(struct refcnt *r)
|
||||
{
|
||||
return refcount_inc_not_zero(&r->rc);
|
||||
}
|
||||
/*
|
||||
* OpenBSD semantics (sys/kern/kern_synch.c): refcnt_rele() returns 1 when
|
||||
* the last reference is dropped and 0 otherwise. PF_REF_RELE() and the
|
||||
* pf_ruleset anchor release rely on that polarity.
|
||||
*/
|
||||
static inline unsigned int refcnt_rele(struct refcnt *r)
|
||||
{
|
||||
return (unsigned int)refcount_dec_and_test(&r->rc) ?
|
||||
refcnt_value(r) : refcnt_value(r) + 1;
|
||||
return (unsigned int)refcount_dec_and_test(&r->rc) ? 1 : 0;
|
||||
}
|
||||
static inline unsigned int refcnt_rele_wake(struct refcnt *r)
|
||||
{
|
||||
|
||||
@@ -0,0 +1,51 @@
|
||||
/* $OpenBSD: fq_codel.h,v 1.4 2020/06/18 23:29:59 dlg Exp $ */
|
||||
|
||||
/*
|
||||
* Copyright (c) 2017 Mike Belopuhov
|
||||
*
|
||||
* Permission to use, copy, modify, and distribute this software for any
|
||||
* purpose with or without fee is hereby granted, provided that the above
|
||||
* copyright notice and this permission notice appear in all copies.
|
||||
*
|
||||
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
|
||||
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
|
||||
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
|
||||
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
|
||||
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
|
||||
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
|
||||
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
|
||||
*/
|
||||
|
||||
#ifndef _NET_FQ_CODEL_H_
|
||||
#define _NET_FQ_CODEL_H_
|
||||
|
||||
/* compatible with hfsc_pktcntr */
|
||||
struct fqcodel_pktcntr {
|
||||
uint64_t packets;
|
||||
uint64_t bytes;
|
||||
};
|
||||
|
||||
struct fqcodel_stats {
|
||||
struct fqcodel_pktcntr xmit_cnt;
|
||||
struct fqcodel_pktcntr drop_cnt;
|
||||
|
||||
uint32_t qlength;
|
||||
uint32_t qlimit;
|
||||
|
||||
uint32_t flows;
|
||||
uint32_t _unused; /* padding */
|
||||
|
||||
uint32_t target;
|
||||
uint32_t interval;
|
||||
|
||||
/* the values below are used to calculate standard deviation */
|
||||
uint64_t delaysum; /* sum of delays, us */
|
||||
uint64_t delaysumsq;/* sum of squared delays, us */
|
||||
};
|
||||
|
||||
#ifdef _KERNEL
|
||||
extern const struct ifq_ops * const ifq_fqcodel_ops;
|
||||
extern const struct pfq_ops * const pfq_fqcodel_ops;
|
||||
#endif /* _KERNEL */
|
||||
|
||||
#endif /* _NET_FQ_CODEL_H_ */
|
||||
@@ -0,0 +1,122 @@
|
||||
/* $OpenBSD: hfsc.h,v 1.15 2026/03/19 14:59:05 sthen Exp $ */
|
||||
|
||||
/*
|
||||
* Copyright (c) 2012-2013 Henning Brauer <henning@openbsd.org>
|
||||
* Copyright (c) 1997-1999 Carnegie Mellon University. All Rights Reserved.
|
||||
*
|
||||
* Permission to use, copy, modify, and distribute this software and
|
||||
* its documentation is hereby granted (including for commercial or
|
||||
* for-profit use), provided that both the copyright notice and this
|
||||
* permission notice appear in all copies of the software, derivative
|
||||
* works, or modified versions, and any portions thereof.
|
||||
*
|
||||
* THIS SOFTWARE IS EXPERIMENTAL AND IS KNOWN TO HAVE BUGS, SOME OF
|
||||
* WHICH MAY HAVE SERIOUS CONSEQUENCES. CARNEGIE MELLON PROVIDES THIS
|
||||
* SOFTWARE IN ITS ``AS IS'' CONDITION, AND ANY EXPRESS OR IMPLIED
|
||||
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
|
||||
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
||||
* DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY BE LIABLE
|
||||
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
||||
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
|
||||
* OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
|
||||
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
|
||||
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
|
||||
* USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH
|
||||
* DAMAGE.
|
||||
*
|
||||
* Carnegie Mellon encourages (but does not require) users of this
|
||||
* software to return any improvements or extensions that they make,
|
||||
* and to grant Carnegie Mellon the rights to redistribute these
|
||||
* changes without encumbrance.
|
||||
*/
|
||||
#ifndef _HFSC_H_
|
||||
#define _HFSC_H_
|
||||
|
||||
/* hfsc class flags */
|
||||
#define HFSC_DEFAULTCLASS 0x1000 /* default class */
|
||||
|
||||
struct hfsc_pktcntr {
|
||||
u_int64_t packets;
|
||||
u_int64_t bytes;
|
||||
};
|
||||
|
||||
#define PKTCNTR_INC(cntr, len) \
|
||||
do { (cntr)->packets++; (cntr)->bytes += len; } while (0)
|
||||
|
||||
struct hfsc_sc {
|
||||
u_int64_t m1; /* slope of the first segment in bits/sec */
|
||||
u_int64_t m2; /* slope of the second segment in bits/sec */
|
||||
u_int d; /* the x-projection of the first segment in msec */
|
||||
};
|
||||
|
||||
/* special class handles */
|
||||
#define HFSC_ROOT_CLASS 0x10000
|
||||
#define HFSC_DEFAULT_CLASSES 64
|
||||
#define HFSC_MAX_CLASSES 65535
|
||||
|
||||
/* service curve types */
|
||||
#define HFSC_REALTIMESC 1
|
||||
#define HFSC_LINKSHARINGSC 2
|
||||
#define HFSC_UPPERLIMITSC 4
|
||||
#define HFSC_DEFAULTSC (HFSC_REALTIMESC|HFSC_LINKSHARINGSC)
|
||||
|
||||
struct hfsc_class_stats {
|
||||
struct hfsc_pktcntr xmit_cnt;
|
||||
struct hfsc_pktcntr drop_cnt;
|
||||
|
||||
u_int qlength;
|
||||
u_int qlimit;
|
||||
u_int period;
|
||||
|
||||
u_int class_id;
|
||||
u_int32_t class_handle;
|
||||
struct hfsc_sc rsc;
|
||||
struct hfsc_sc fsc;
|
||||
struct hfsc_sc usc; /* upper limit service curve */
|
||||
|
||||
u_int64_t total; /* total work in bytes */
|
||||
u_int64_t cumul; /* cumulative work in bytes
|
||||
done by real-time criteria */
|
||||
u_int64_t d; /* deadline */
|
||||
u_int64_t e; /* eligible time */
|
||||
u_int64_t vt; /* virtual time */
|
||||
u_int64_t f; /* fit time for upper-limit */
|
||||
|
||||
/* info helpful for debugging */
|
||||
u_int64_t initvt; /* init virtual time */
|
||||
u_int64_t vtoff; /* cl_vt_ipoff */
|
||||
u_int64_t cvtmax; /* cl_maxvt */
|
||||
u_int64_t myf; /* cl_myf */
|
||||
u_int64_t cfmin; /* cl_mincf */
|
||||
u_int64_t cvtmin; /* cl_mincvt */
|
||||
u_int64_t myfadj; /* cl_myfadj */
|
||||
u_int64_t vtadj; /* cl_vtadj */
|
||||
u_int64_t cur_time;
|
||||
u_int32_t machclk_freq;
|
||||
|
||||
u_int vtperiod; /* vt period sequence no */
|
||||
u_int parentperiod; /* parent's vt period seqno */
|
||||
int nactive; /* number of active children */
|
||||
|
||||
/* red and rio related info */
|
||||
int qtype;
|
||||
/* struct redstats red[3]; */
|
||||
};
|
||||
|
||||
#ifdef _KERNEL
|
||||
struct ifnet;
|
||||
struct ifqueue;
|
||||
struct pf_queuespec;
|
||||
struct hfsc_if;
|
||||
|
||||
extern const struct ifq_ops * const ifq_hfsc_ops;
|
||||
extern const struct pfq_ops * const pfq_hfsc_ops;
|
||||
|
||||
#define HFSC_ENABLED(ifq) ((ifq)->ifq_ops == ifq_hfsc_ops)
|
||||
#define HFSC_DEFAULT_QLIMIT 50
|
||||
|
||||
void hfsc_initialize(void);
|
||||
|
||||
#endif /* _KERNEL */
|
||||
#endif /* _HFSC_H_ */
|
||||
@@ -1203,4 +1203,60 @@ int pf_anchor_stack_pop(struct pf_ruleset **, struct pf_rule **,
|
||||
struct inpcb;
|
||||
void pf_remove_divert_state(struct inpcb *);
|
||||
|
||||
/* pflog backend (/dev/pflog) - 'L' keeps the namespace clear of DIOC* ('P') */
|
||||
struct pfk_pflog_stat {
|
||||
u_int64_t queued; /* records currently queued */
|
||||
u_int64_t bytes; /* bytes queued */
|
||||
u_int64_t dropped; /* records dropped (queue full) */
|
||||
u_int64_t seq; /* records produced since load */
|
||||
};
|
||||
#define PFKIOCGETPFLOGSTAT _IOR('L', 1, struct pfk_pflog_stat)
|
||||
|
||||
|
||||
/*
|
||||
* Scheduler back-end ABI: the very headers OpenBSD ships (net/hfsc.h,
|
||||
* net/fq_codel.h), vendored into the port so that pfctl and pf.ko agree on the
|
||||
* stats layouts and on the class-handle/service-curve constants. (Hand-rolled
|
||||
* approximations of these structs made DIOCGETQSTATS fail with EINVAL, because
|
||||
* pfctl's sizeof(struct hfsc_class_stats) did not match the kernel's.)
|
||||
*/
|
||||
#ifndef nsecuptime
|
||||
#define nsecuptime() getnsecuptime()
|
||||
#endif
|
||||
|
||||
#include <net/hfsc.h>
|
||||
#include <net/fq_codel.h>
|
||||
|
||||
/* OpenBSD's global nanoseconds-per-clocktick (HFSC_CLK_PER_TICK). The port
|
||||
* has no clock_rate machinery, so derive it from the kernel's HZ. */
|
||||
#ifndef tick_nsec
|
||||
#define tick_nsec (1000000000LL / HZ)
|
||||
#endif
|
||||
|
||||
/* ifq scheduler hand-off (see pfsrc/ifq.c): enter returns the scheduler's
|
||||
* queue state when it owns the interface queue, NULL otherwise. */
|
||||
void *ifq_q_enter(struct ifqueue *, const struct ifq_ops *);
|
||||
void ifq_q_leave(struct ifqueue *, void *);
|
||||
int pfk_ifq_transmit(struct ifqueue *, struct mbuf *);
|
||||
int pf_kifq_input(struct pfk_ifnet *, struct mbuf *);
|
||||
|
||||
|
||||
/*
|
||||
* PFLINUX notes on the scheduler back ends:
|
||||
*
|
||||
* - splnet()/splx(): OpenBSD raises the software interrupt level around
|
||||
* class-table surgery. This port runs the whole data path in one ordered
|
||||
* work queue and guards the queue with ifq_mtx, so these are no-ops; they
|
||||
* are kept as markers of the critical regions.
|
||||
* - KERNEL_ASSERT_LOCKED(): the schedulers are only reached from ifq/pf paths
|
||||
* that already hold the queue mutex; asserted structurally, not by spl.
|
||||
* - HFSC_ENABLED(), PKTCNTR_INC(), the class-handle constants and the stats
|
||||
* layouts all come from the vendored net/hfsc.h / net/fq_codel.h above, so
|
||||
* kernel and pfctl cannot drift apart.
|
||||
*/
|
||||
#define splnet() 0
|
||||
#define splx(s) ((void)(s))
|
||||
#define KERNEL_ASSERT_LOCKED() do { } while (0)
|
||||
|
||||
#endif /* _PFK_H */
|
||||
|
||||
@@ -7,7 +7,19 @@
|
||||
long pfk_ioctl(struct file *f, unsigned int cmd, unsigned long addr);
|
||||
int pfk_enable(int on);
|
||||
void pfk_status(struct pf_status *s);
|
||||
#define PFK_SKIP_PF 0x00000004u /* skb->mark: reinjected, bypass pf */
|
||||
#define PFK_DONE_IN 0x00000001u /* skb->mark bit: PF_IN pass completed */
|
||||
#define PFK_DONE_OUT 0x00000002u /* skb->mark bit: PF_OUT pass completed */
|
||||
|
||||
int pfk_hooks_register(void);
|
||||
void pfk_hooks_unregister(void);
|
||||
/* AF_DIVERT family (module-internal socket protocol, PF_DIVERT=32) */
|
||||
int pfk_pflog_register(void);
|
||||
void pfk_pflog_unregister(void);
|
||||
int pfk_divert_sock_register(void);
|
||||
void pfk_divert_sock_unregister(void);
|
||||
void divert_packet(struct mbuf *, int, u_int16_t);
|
||||
void divert6_packet(struct mbuf *, int, u_int16_t);
|
||||
void pfk_hooks_unregister(void);
|
||||
|
||||
#endif
|
||||
@@ -74,6 +74,79 @@ ml_dequeue(struct mbuf_list *ml)
|
||||
return m;
|
||||
}
|
||||
|
||||
|
||||
/* BSD <net/if_var.h> mbuf_list helpers (net/if_var.h ml_*) */
|
||||
static inline void
|
||||
ml_init(struct mbuf_list *ml)
|
||||
{
|
||||
ml->ml_first = ml->ml_last = NULL;
|
||||
ml->ml_len = 0;
|
||||
}
|
||||
|
||||
static inline void
|
||||
ml_enqueue(struct mbuf_list *ml, struct mbuf *m)
|
||||
{
|
||||
m->m_next = NULL;
|
||||
if (ml->ml_last == NULL)
|
||||
ml->ml_first = m;
|
||||
else
|
||||
ml->ml_last->m_next = m;
|
||||
ml->ml_last = m;
|
||||
ml->ml_len++;
|
||||
}
|
||||
|
||||
static inline struct mbuf *
|
||||
ml_dequeue_tail(struct mbuf_list *ml)
|
||||
{
|
||||
struct mbuf *m, *prev = NULL;
|
||||
|
||||
if (ml->ml_first == NULL)
|
||||
return NULL;
|
||||
for (m = ml->ml_first; m->m_next; m = m->m_next)
|
||||
prev = m;
|
||||
if (prev == NULL) /* single element */
|
||||
ml->ml_first = NULL;
|
||||
else
|
||||
prev->m_next = NULL;
|
||||
ml->ml_last = prev;
|
||||
ml->ml_len--;
|
||||
m->m_next = NULL;
|
||||
return m;
|
||||
}
|
||||
|
||||
/* append every packet in m2 to m1 (m2 becomes empty) */
|
||||
static inline void
|
||||
ml_enlist(struct mbuf_list *m1, struct mbuf_list *m2)
|
||||
{
|
||||
if (m2->ml_first == NULL)
|
||||
return;
|
||||
if (m1->ml_last == NULL)
|
||||
m1->ml_first = m2->ml_first;
|
||||
else
|
||||
m1->ml_last->m_next = m2->ml_first;
|
||||
m1->ml_last = m2->ml_last;
|
||||
m1->ml_len += m2->ml_len;
|
||||
m2->ml_first = m2->ml_last = NULL;
|
||||
m2->ml_len = 0;
|
||||
}
|
||||
|
||||
static inline unsigned int
|
||||
ml_len(const struct mbuf_list *ml)
|
||||
{
|
||||
return (unsigned int)ml->ml_len;
|
||||
}
|
||||
|
||||
static inline int
|
||||
ml_empty(const struct mbuf_list *ml)
|
||||
{
|
||||
return ml->ml_first == NULL;
|
||||
}
|
||||
|
||||
void ml_purge(struct mbuf_list *ml); /* compat/pfk_mbuf.c (needs m_freem) */
|
||||
|
||||
#define MBUF_LIST_FIRST(_ml) ((_ml)->ml_first)
|
||||
#define MBUF_LIST_INITIALIZER() { NULL, NULL, 0 }
|
||||
|
||||
/* egress interface (default-route dev), maintained on fib/net events */
|
||||
struct pfk_ifnet *pfk_egress_if(void);
|
||||
void pfk_egress_refresh(void);
|
||||
|
||||
@@ -73,7 +73,7 @@ struct pkthdr {
|
||||
u_int32_t ph_flowid;
|
||||
u_int ph_ifidx;
|
||||
u_int ph_rtableid;
|
||||
struct pfk_timeval ph_timestamp;
|
||||
int64_t ph_timestamp; /* OpenBSD 8.0: nanoseconds */
|
||||
struct pfk_ifnet *ifp;
|
||||
struct pfk_ifnet *rcvif;
|
||||
u_short ph; /* tso segs: unused, kept as pad */
|
||||
|
||||
@@ -1828,6 +1828,9 @@ deps_pfsrc/divert_sock.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
include/pfk_api.h \
|
||||
|
||||
pfsrc/divert_sock.o: $(deps_pfsrc/divert_sock.o)
|
||||
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
File diff suppressed because it is too large.
Load diff
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf.o: $(deps_pfsrc/pf.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_if.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_if.o: $(deps_pfsrc/pf_if.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_ioctl.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_ioctl.o: $(deps_pfsrc/pf_ioctl.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_lb.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_lb.o: $(deps_pfsrc/pf_lb.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_norm.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_norm.o: $(deps_pfsrc/pf_norm.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_osfp.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_osfp.o: $(deps_pfsrc/pf_osfp.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_ruleset.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_ruleset.o: $(deps_pfsrc/pf_ruleset.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_syncookies.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_syncookies.o: $(deps_pfsrc/pf_syncookies.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pf_table.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
|
||||
pfsrc/pf_table.o: $(deps_pfsrc/pf_table.o)
|
||||
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pfk_hooks.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
include/pfk_api.h \
|
||||
|
||||
pfsrc/pfk_hooks.o: $(deps_pfsrc/pfk_hooks.o)
|
||||
|
||||
@@ -1828,6 +1828,8 @@ deps_pfsrc/pfk_mod.o := \
|
||||
include/compat/sys/rwlock.h \
|
||||
include/compat/sys/mutex.h \
|
||||
include/compat/sys/pclock.h \
|
||||
include/net/hfsc.h \
|
||||
include/net/fq_codel.h \
|
||||
include/pfk_api.h \
|
||||
|
||||
pfsrc/pfk_mod.o: $(deps_pfsrc/pfk_mod.o)
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
+522
-17
@@ -1,33 +1,538 @@
|
||||
/*
|
||||
* PF-on-Linux divert entry points used by pf.c (ISC 2026).
|
||||
* PF-on-Linux: AF_DIVERT socket family (ISC 2026)
|
||||
*
|
||||
* BSD semantics (OpenBSD netinet/ip_divert.c): divert_packet()/divert6_packet()
|
||||
* find the AF_DIVERT pcb bound to `divert_port`, queue the packet to it and
|
||||
* consume the mbuf; when NO divert socket is attached, OpenBSD drops the
|
||||
* packet (m_freem) — that is exactly the observable behaviour implemented
|
||||
* here until the pfdiv socket layer is instantiated for Linux (milestone
|
||||
* M6); a rate-limited kernel log records the event so drops are never
|
||||
* silent.
|
||||
* Implements OpenBSD's divert(4) as a runtime-registered protocol family
|
||||
* inside the PF module: PF_DIVERT = 32 (BSD value; the unused legacy
|
||||
* PF_IUCV slot on Linux, and NPROTO = AF_MAX = 45 admits it),
|
||||
* IPPROTO_DIVERT = 254. No core patch is required — families are
|
||||
* registered with sock_register() at module init.
|
||||
*
|
||||
* The upstream BSD socket layer is staged in pfsrc/ip_divert.c and becomes
|
||||
* the real back end in M6; these wrappers keep the same call signature
|
||||
* (struct mbuf *, int dir, u_int16_t divert_port).
|
||||
* Userspace ABI (see docs/en/divert-wireformat.md):
|
||||
* fd = socket(PF_DIVERT, SOCK_RAW, IPPROTO_DIVERT);
|
||||
* struct sockaddr_in b = { .sin_family = AF_INET, .sin_port = port };
|
||||
* bind(fd, &b); # binds the divert "port"
|
||||
* n = recv(fd, pkt, ...) # full IP packet incl. header
|
||||
* send(fd, pkt, n) # reinject per BSD semantics
|
||||
*
|
||||
* Re-injection mirrors OpenBSD netinet/ip_divert.c:divert_output():
|
||||
* type PF_DIVERT_TO -> local delivery as if arrived on the recorded
|
||||
* interface (netif_rx)
|
||||
* plain divert tag -> route again (dst output), matching BSD ip_output
|
||||
*
|
||||
* Semantics notes (PFLINUX, docs/porting-notes.md):
|
||||
* - queue selection scans the bound list under pfk_divert_lock;
|
||||
* - full-socket drop counts divs_fullsock like BSD;
|
||||
* - no socket bound to the port: divs_noport + drop (BSD identical).
|
||||
*/
|
||||
#include <pfk.h>
|
||||
#include <net/pfvar.h>
|
||||
#include <pfk_api.h>
|
||||
#include <net/sock.h>
|
||||
|
||||
#define PF_DIVERT_FAMILY 32 /* BSD PF_DIVERT */
|
||||
#ifndef IPPROTO_DIVERT
|
||||
#define IPPROTO_DIVERT 254
|
||||
#endif
|
||||
|
||||
/* control message codes reported to userspace (sendmsg accepts them back) */
|
||||
#define PFDIVERT_CMSG_IFINDEX 1
|
||||
#define PFDIVERT_CMSG_DIR 2
|
||||
#define PFDIVERT_CMSG_TYPE 3
|
||||
|
||||
struct pfk_divert_pkt {
|
||||
struct list_head node;
|
||||
struct sk_buff *skb;
|
||||
int dir;
|
||||
int type;
|
||||
u16 port;
|
||||
int ifindex;
|
||||
};
|
||||
|
||||
struct pfk_divert_stat {
|
||||
u64 divs_ipackets;
|
||||
u64 divs_noport;
|
||||
u64 divs_fullsock;
|
||||
u64 divs_opackets;
|
||||
u64 divs_errors;
|
||||
};
|
||||
|
||||
static const struct proto_ops pfk_divert_ops;
|
||||
|
||||
struct pfk_divert_sock {
|
||||
struct list_head link; /* global bound list */
|
||||
struct list_head q;
|
||||
spinlock_t lock;
|
||||
u16 port;
|
||||
u32 qlen;
|
||||
int last_ifindex; /* device of last queued packet */
|
||||
wait_queue_head_t wq;
|
||||
u32 qspace;
|
||||
struct sock *sk;
|
||||
struct pfk_divert_stat stats;
|
||||
};
|
||||
|
||||
static LIST_HEAD(pfk_divert_list);
|
||||
static DEFINE_SPINLOCK(pfk_divert_lock);
|
||||
static struct pfk_divert_stat pfk_divert_global;
|
||||
static struct proto pfk_divert_proto = {
|
||||
.name = "PFK_DIVERT",
|
||||
.owner = THIS_MODULE,
|
||||
.obj_size = sizeof(struct sock),
|
||||
};
|
||||
|
||||
static inline struct pfk_divert_sock *
|
||||
pfk_ds(const struct sock *sk)
|
||||
{
|
||||
return sk ? (struct pfk_divert_sock *)sk->sk_user_data : NULL;
|
||||
}
|
||||
|
||||
static void
|
||||
pfk_divert_pkt_free(struct pfk_divert_pkt *dp)
|
||||
{
|
||||
if (!dp)
|
||||
return;
|
||||
if (dp->skb)
|
||||
kfree_skb(dp->skb);
|
||||
kfree(dp);
|
||||
}
|
||||
|
||||
/* PF engine entry points (called from the ported pf.c) */
|
||||
static struct pfk_divert_sock *
|
||||
pfk_divert_lookup(u_int16_t port)
|
||||
{
|
||||
struct pfk_divert_sock *ds;
|
||||
|
||||
list_for_each_entry(ds, &pfk_divert_list, link) {
|
||||
if (ds->port == port)
|
||||
return ds;
|
||||
}
|
||||
return NULL;
|
||||
}
|
||||
|
||||
static int
|
||||
pfk_divert_queue(struct sk_buff *skb, int dir, int type, u16 port)
|
||||
{
|
||||
struct pfk_divert_sock *ds;
|
||||
struct pfk_divert_pkt *dp;
|
||||
unsigned long flags;
|
||||
|
||||
dp = kmalloc(sizeof(*dp), GFP_ATOMIC);
|
||||
if (!dp) {
|
||||
kfree_skb(skb);
|
||||
return ENOMEM;
|
||||
}
|
||||
dp->skb = skb;
|
||||
dp->dir = dir;
|
||||
dp->type = type;
|
||||
dp->port = port;
|
||||
dp->ifindex = skb->dev ? skb->dev->ifindex : 0;
|
||||
|
||||
spin_lock_irqsave(&pfk_divert_lock, flags);
|
||||
ds = pfk_divert_lookup(port);
|
||||
if (ds == NULL) {
|
||||
pfk_divert_global.divs_noport++;
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
pr_info_ratelimited("pfk: divert port %u: no socket bound\n",
|
||||
port);
|
||||
pfk_divert_pkt_free(dp);
|
||||
return ENOENT;
|
||||
}
|
||||
if (ds->qlen >= ds->qspace) {
|
||||
ds->stats.divs_fullsock++;
|
||||
pfk_divert_global.divs_fullsock++;
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
pfk_divert_pkt_free(dp);
|
||||
return ENOBUFS;
|
||||
}
|
||||
spin_lock(&ds->lock);
|
||||
list_add_tail(&dp->node, &ds->q);
|
||||
ds->qlen++;
|
||||
ds->stats.divs_ipackets++;
|
||||
ds->last_ifindex = dp->ifindex;
|
||||
spin_unlock(&ds->lock);
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
|
||||
wake_up_interruptible(&ds->wq);
|
||||
return 0;
|
||||
}
|
||||
|
||||
extern struct pf_divert *pf_find_divert(struct mbuf *);
|
||||
|
||||
void
|
||||
divert_packet(struct mbuf *m, int dir, u_int16_t divert_port)
|
||||
{
|
||||
pr_warn_ratelimited("pfk: divert v4 port %u: no divert socket layer (M6 pending), dropping\n",
|
||||
ntohs(divert_port));
|
||||
struct sk_buff *skb;
|
||||
int type = PF_DIVERT_TO;
|
||||
|
||||
if (!m)
|
||||
return;
|
||||
{
|
||||
struct pf_divert *dv = pf_find_divert(m);
|
||||
|
||||
if (dv) {
|
||||
type = dv->type;
|
||||
if (divert_port == 0)
|
||||
divert_port = dv->port;
|
||||
}
|
||||
}
|
||||
skb = m_to_skb(m);
|
||||
if (skb)
|
||||
skb_get(skb); /* divert layer's own reference */
|
||||
m->skb = NULL;
|
||||
m_freem(m);
|
||||
if (skb)
|
||||
pfk_divert_queue(skb, dir, type, divert_port);
|
||||
}
|
||||
|
||||
void
|
||||
divert6_packet(struct mbuf *m, int dir, u_int16_t divert_port)
|
||||
{
|
||||
pr_warn_ratelimited("pfk: divert v6 port %u: no divert socket layer (M6 pending), dropping\n",
|
||||
ntohs(divert_port));
|
||||
m_freem(m);
|
||||
divert_packet(m, dir, divert_port);
|
||||
}
|
||||
|
||||
/* ---------------- socket ops ---------------- */
|
||||
|
||||
static int
|
||||
pfk_divert_create(struct net *net, struct socket *sock, int protocol, int kern)
|
||||
{
|
||||
struct sock *sk;
|
||||
struct pfk_divert_sock *ds;
|
||||
|
||||
if (protocol != IPPROTO_DIVERT && protocol != 0)
|
||||
return -EPROTONOSUPPORT;
|
||||
if (sock->type != SOCK_RAW)
|
||||
return -ESOCKTNOSUPPORT;
|
||||
|
||||
ds = kzalloc(sizeof(*ds), GFP_KERNEL);
|
||||
if (!ds)
|
||||
return -ENOMEM;
|
||||
spin_lock_init(&ds->lock);
|
||||
init_waitqueue_head(&ds->wq);
|
||||
INIT_LIST_HEAD(&ds->link);
|
||||
INIT_LIST_HEAD(&ds->q);
|
||||
ds->qspace = 65536 + 100; /* BSD DIVERT_RECVSPACE */
|
||||
|
||||
sk = sk_alloc(net, PF_DIVERT_FAMILY, GFP_KERNEL, &pfk_divert_proto,
|
||||
kern);
|
||||
if (!sk) {
|
||||
kfree(ds);
|
||||
return -ENOMEM;
|
||||
}
|
||||
sock_init_data(sock, sk);
|
||||
sk->sk_user_data = ds;
|
||||
ds->sk = sk;
|
||||
sock->state = SS_UNCONNECTED;
|
||||
sock->ops = &pfk_divert_ops; /* forward decl below via struct */
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
pfk_divert_bind(struct socket *sock, struct sockaddr_unsized *uaddr,
|
||||
int addr_len)
|
||||
{
|
||||
struct pfk_divert_sock *ds = pfk_ds(sock->sk);
|
||||
unsigned long flags;
|
||||
|
||||
if (!ds)
|
||||
return -EINVAL;
|
||||
if (addr_len < (int)sizeof(struct sockaddr_in))
|
||||
return -EINVAL;
|
||||
|
||||
/* BSD divsock stores the port in network order (compared against
|
||||
* inp_lport / pf_divert.port as-is). */
|
||||
ds->port = ((struct sockaddr_in *)uaddr)->sin_port;
|
||||
if (ds->port == 0)
|
||||
return -EADDRNOTAVAIL; /* divert port 0 not allowed */
|
||||
|
||||
spin_lock_irqsave(&pfk_divert_lock, flags);
|
||||
if (!list_empty(&ds->link)) {
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
return -EADDRINUSE;
|
||||
}
|
||||
list_add_tail(&ds->link, &pfk_divert_list);
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
pfk_divert_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
|
||||
int flags)
|
||||
{
|
||||
struct pfk_divert_sock *ds = pfk_ds(sock->sk);
|
||||
struct pfk_divert_pkt *dp;
|
||||
struct sk_buff *skb;
|
||||
unsigned long iflags;
|
||||
int copied;
|
||||
|
||||
if (!ds)
|
||||
return -EINVAL;
|
||||
if (msg_data_left(msg) == 0)
|
||||
return -EINVAL;
|
||||
|
||||
for (;;) {
|
||||
spin_lock_irqsave(&ds->lock, iflags);
|
||||
if (!list_empty(&ds->q)) {
|
||||
dp = list_first_entry(&ds->q, struct pfk_divert_pkt,
|
||||
node);
|
||||
list_del_init(&dp->node);
|
||||
ds->qlen--;
|
||||
spin_unlock_irqrestore(&ds->lock, iflags);
|
||||
goto have;
|
||||
}
|
||||
spin_unlock_irqrestore(&ds->lock, iflags);
|
||||
if (flags & MSG_DONTWAIT ||
|
||||
READ_ONCE(sock->sk->sk_shutdown) != 0)
|
||||
return -EAGAIN;
|
||||
wait_event_interruptible(ds->wq,
|
||||
!list_empty(&ds->q) ||
|
||||
READ_ONCE(sock->sk->sk_shutdown) != 0);
|
||||
if (signal_pending(current))
|
||||
return -ERESTARTSYS;
|
||||
}
|
||||
|
||||
have:
|
||||
skb = dp->skb;
|
||||
copied = min_t(size_t, len, skb->len);
|
||||
if (skb_copy_datagram_msg(skb, 0, msg, copied)) {
|
||||
pfk_divert_pkt_free(dp);
|
||||
return -EFAULT;
|
||||
}
|
||||
/* metadata as control data (BSD equivalent: sockaddr_div) */
|
||||
{
|
||||
struct cmsghdr *cm = CMSG_FIRSTHDR(msg);
|
||||
|
||||
if (cm && msg->msg_controllen >= sizeof(struct cmsghdr) + sizeof(int)) {
|
||||
msg->msg_controllen = 0; /* busybox-safe default */
|
||||
cm = NULL;
|
||||
}
|
||||
if (cm) {
|
||||
int ifindex = dp->ifindex;
|
||||
|
||||
cm->cmsg_level = SOL_SOCKET;
|
||||
cm->cmsg_type = PFDIVERT_CMSG_IFINDEX;
|
||||
cm->cmsg_len = CMSG_LEN(sizeof(int));
|
||||
memcpy(CMSG_DATA(cm), &ifindex, sizeof(ifindex));
|
||||
msg->msg_controllen = CMSG_SPACE(sizeof(int));
|
||||
}
|
||||
}
|
||||
sock_net_set(sock->sk, &init_net);
|
||||
ds->stats.divs_opackets++;
|
||||
pfk_divert_pkt_free(dp);
|
||||
return copied;
|
||||
}
|
||||
|
||||
/*
|
||||
* sendmsg: userspace hands the (possibly rewritten) packet back. The
|
||||
* ip header inside the bytes decides the flow; for PF_DIVERT_TO we inject
|
||||
* as input on the socket's last-recorded interface, otherwise we route.
|
||||
*/
|
||||
static int
|
||||
pfk_divert_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
|
||||
{
|
||||
struct pfk_divert_sock *ds = pfk_ds(sock->sk);
|
||||
struct sk_buff *skb;
|
||||
struct pf_ip *ip;
|
||||
int ifindex = 0;
|
||||
int type = PF_DIVERT_TO;
|
||||
struct cmsghdr *cm;
|
||||
|
||||
if (!ds)
|
||||
return -EINVAL;
|
||||
if (len > 65535)
|
||||
return -EMSGSIZE;
|
||||
|
||||
for (cm = CMSG_FIRSTHDR(msg); cm; cm = CMSG_NXTHDR(msg, cm)) {
|
||||
if (cm->cmsg_level != SOL_SOCKET)
|
||||
continue;
|
||||
if (cm->cmsg_type == PFDIVERT_CMSG_IFINDEX &&
|
||||
cm->cmsg_len >= CMSG_LEN(sizeof(int)))
|
||||
memcpy(&ifindex, CMSG_DATA(cm), sizeof(int));
|
||||
if (cm->cmsg_type == PFDIVERT_CMSG_TYPE &&
|
||||
cm->cmsg_len >= CMSG_LEN(sizeof(int)))
|
||||
memcpy(&type, CMSG_DATA(cm), sizeof(int));
|
||||
}
|
||||
|
||||
skb = alloc_skb(len + NET_SKB_PAD + NET_IP_ALIGN, GFP_KERNEL);
|
||||
if (!skb)
|
||||
return -ENOMEM;
|
||||
skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN);
|
||||
if (memcpy_from_msg(skb_put(skb, len), msg, len)) {
|
||||
kfree_skb(skb);
|
||||
return -EFAULT;
|
||||
}
|
||||
skb->protocol = htons(ETH_P_IP);
|
||||
if (ifindex <= 0)
|
||||
ifindex = ds->last_ifindex; /* same path the packet came in */
|
||||
|
||||
if (type == PF_DIVERT_TO) {
|
||||
/* deliver locally as if arrived on ifindex (default: last
|
||||
* ingress iface seen by this socket's queue) */
|
||||
struct net_device *dev = ifindex > 0 ?
|
||||
dev_get_by_index(&init_net, ifindex) : NULL;
|
||||
|
||||
if (dev) {
|
||||
struct ethhdr *eh;
|
||||
|
||||
skb->dev = dev;
|
||||
dev_put(dev);
|
||||
skb->mark |= PFK_SKIP_PF; /* avoid divert loop */
|
||||
/*
|
||||
* The receive path of an Ethernet device expects an
|
||||
* L2 header: synthesise one (the packet keeps its
|
||||
* original addresses; the stack only needs the
|
||||
* ethertype to demultiplex).
|
||||
*/
|
||||
eh = skb_push(skb, ETH_HLEN);
|
||||
if (!eh) {
|
||||
kfree_skb(skb);
|
||||
return -ENOMEM;
|
||||
}
|
||||
memset(eh, 0, ETH_HLEN);
|
||||
memcpy(eh->h_dest, dev->dev_addr, ETH_ALEN);
|
||||
memcpy(eh->h_source, dev->dev_addr, ETH_ALEN);
|
||||
eh->h_proto = htons(ETH_P_IP);
|
||||
skb_reset_mac_header(skb);
|
||||
skb->protocol = htons(ETH_P_IP);
|
||||
skb_pull(skb, ETH_HLEN); /* like eth_type_trans() */
|
||||
/* data now points at the IP header again */
|
||||
skb_reset_network_header(skb);
|
||||
netif_rx(skb);
|
||||
return (int)len;
|
||||
}
|
||||
/* no device: route below */
|
||||
}
|
||||
|
||||
/* plain divert: route again (BSD divert_output -> ip_output) */
|
||||
if (pskb_may_pull(skb, sizeof(*ip))) {
|
||||
struct flowi4 fl4 = { };
|
||||
struct dst_entry *d;
|
||||
|
||||
ip = (struct pf_ip *)skb->data;
|
||||
fl4.daddr = ip->ip_dst.s_addr;
|
||||
fl4.saddr = ip->ip_src.s_addr;
|
||||
{
|
||||
struct rtable *rt = ip_route_output_key(&init_net,
|
||||
&fl4);
|
||||
|
||||
if (IS_ERR(rt))
|
||||
rt = NULL;
|
||||
d = rt ? &rt->dst : NULL;
|
||||
}
|
||||
if (d) {
|
||||
skb_dst_set(skb, d);
|
||||
skb_reset_network_header(skb);
|
||||
if (!skb->dev)
|
||||
skb->dev = skb_dst(skb)->dev;
|
||||
d->output(&init_net, NULL, skb);
|
||||
return (int)len;
|
||||
}
|
||||
}
|
||||
kfree_skb(skb);
|
||||
ds->stats.divs_errors++;
|
||||
return -EHOSTUNREACH;
|
||||
}
|
||||
|
||||
static int
|
||||
pfk_divert_release(struct socket *sock)
|
||||
{
|
||||
struct sock *sk = sock->sk;
|
||||
struct pfk_divert_sock *ds;
|
||||
unsigned long flags;
|
||||
|
||||
if (!sk)
|
||||
return 0;
|
||||
ds = pfk_ds(sk);
|
||||
if (ds) {
|
||||
spin_lock_irqsave(&pfk_divert_lock, flags);
|
||||
if (!list_empty(&ds->link))
|
||||
list_del_init(&ds->link);
|
||||
spin_unlock_irqrestore(&pfk_divert_lock, flags);
|
||||
while (!list_empty(&ds->q)) {
|
||||
struct pfk_divert_pkt *dp = list_first_entry(&ds->q,
|
||||
struct pfk_divert_pkt, node);
|
||||
|
||||
list_del_init(&dp->node);
|
||||
pfk_divert_pkt_free(dp);
|
||||
}
|
||||
kfree(ds);
|
||||
sk->sk_user_data = NULL;
|
||||
}
|
||||
sock_orphan(sk);
|
||||
sock_put(sk);
|
||||
return 0;
|
||||
}
|
||||
|
||||
static __poll_t
|
||||
pfk_divert_poll(struct file *file, struct socket *sock,
|
||||
poll_table *wait)
|
||||
{
|
||||
struct pfk_divert_sock *ds = pfk_ds(sock->sk);
|
||||
__poll_t mask = 0;
|
||||
|
||||
if (ds)
|
||||
poll_wait(file, &ds->wq, wait);
|
||||
else
|
||||
sock_poll_wait(file, sock, wait);
|
||||
if (ds && !list_empty(&ds->q))
|
||||
mask |= EPOLLIN | EPOLLRDNORM;
|
||||
return mask;
|
||||
}
|
||||
|
||||
static int
|
||||
pfk_divert_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
|
||||
{
|
||||
struct pfk_divert_sock *ds = pfk_ds(sock->sk);
|
||||
|
||||
if (!ds)
|
||||
return -EINVAL;
|
||||
switch (cmd) {
|
||||
case 3: { /* DIVERTCTL_STATS-ish: export queue stats */
|
||||
struct pfk_divert_stat st;
|
||||
unsigned long flags;
|
||||
|
||||
spin_lock_irqsave(&ds->lock, flags);
|
||||
st = ds->stats;
|
||||
spin_unlock_irqrestore(&ds->lock, flags);
|
||||
if (copy_to_user((void __user *)arg, &st, sizeof(st)))
|
||||
return -EFAULT;
|
||||
return 0;
|
||||
}
|
||||
default:
|
||||
return -ENOIOCTLCMD;
|
||||
}
|
||||
}
|
||||
|
||||
static const struct proto_ops pfk_divert_ops = {
|
||||
.family = PF_DIVERT_FAMILY,
|
||||
.owner = THIS_MODULE,
|
||||
.release = pfk_divert_release,
|
||||
.bind = pfk_divert_bind,
|
||||
.connect = sock_no_connect,
|
||||
.socketpair = sock_no_socketpair,
|
||||
.accept = sock_no_accept,
|
||||
.getname = sock_no_getname,
|
||||
.poll = pfk_divert_poll,
|
||||
.ioctl = pfk_divert_ioctl,
|
||||
.listen = sock_no_listen,
|
||||
.shutdown = sock_no_shutdown,
|
||||
.sendmsg = pfk_divert_sendmsg,
|
||||
.recvmsg = pfk_divert_recvmsg,
|
||||
.mmap = sock_no_mmap,
|
||||
};
|
||||
|
||||
static const struct net_proto_family pfk_divert_family = {
|
||||
.family = PF_DIVERT_FAMILY,
|
||||
.create = pfk_divert_create,
|
||||
.owner = THIS_MODULE,
|
||||
};
|
||||
|
||||
int
|
||||
pfk_divert_sock_register(void)
|
||||
{
|
||||
return sock_register(&pfk_divert_family);
|
||||
}
|
||||
|
||||
void
|
||||
pfk_divert_sock_unregister(void)
|
||||
{
|
||||
sock_unregister(PF_DIVERT_FAMILY);
|
||||
}
|
||||
@@ -332,7 +332,9 @@ control_law(struct codel *cd, struct codel_params *cp, int64_t rts)
|
||||
unsigned int idx;
|
||||
|
||||
KASSERT(cd->drops > 0);
|
||||
idx = min(cd->drops - 1, nitems(codel_intervals) - 1);
|
||||
/* PFLINUX: Linux' min() type-checks its arguments; nitems() is size_t */
|
||||
idx = min_t(unsigned int, cd->drops - 1,
|
||||
(unsigned int)(nitems(codel_intervals) - 1));
|
||||
cd->next = rts + cp->intervals[idx];
|
||||
}
|
||||
|
||||
|
||||
+12
-3
@@ -335,9 +335,9 @@ hfsc_class_purge(struct hfsc_class *cl, struct mbuf_list *ml)
|
||||
}
|
||||
|
||||
static inline u_int
|
||||
hfsc_more_slots(u_int current)
|
||||
hfsc_more_slots(u_int cur) /* PFLINUX: 'current' is a kernel macro */
|
||||
{
|
||||
u_int want = current * 2;
|
||||
u_int want = cur * 2;
|
||||
|
||||
return (want > HFSC_MAX_CLASSES ? HFSC_MAX_CLASSES : want);
|
||||
}
|
||||
@@ -481,7 +481,16 @@ hfsc_pf_qstats(struct pf_queuespec *q, void *ubuf, int *nbytes)
|
||||
if (hif == NULL)
|
||||
return (EBADF);
|
||||
|
||||
if ((cl = hfsc_clh2cph(hif, q->qid)) == NULL) {
|
||||
/*
|
||||
* A root queue's class is created with handle HFSC_ROOT_CLASS | qid
|
||||
* (see hfsc_pf_addqueue), so looking the queue up by its plain pf qid
|
||||
* only finds non-root classes: fall back to the root handle, otherwise
|
||||
* "pfctl -s queue" fails with EINVAL on the first (root) queue.
|
||||
*/
|
||||
if ((cl = hfsc_clh2cph(hif, q->qid)) == NULL &&
|
||||
(q->flags & PFQS_ROOTCLASS))
|
||||
cl = hfsc_clh2cph(hif, HFSC_ROOT_CLASS | q->qid);
|
||||
if (cl == NULL) {
|
||||
ifq_q_leave(&ifp->if_snd, hif);
|
||||
return (EINVAL);
|
||||
}
|
||||
|
||||
+9
-13
@@ -5020,9 +5020,6 @@ pf_test_rule(struct pf_pdesc *pd, struct pf_rule **rm, struct pf_state **sm,
|
||||
|
||||
if (pd->virtual_proto != PF_VPROTO_FRAGMENT
|
||||
&& !ctx.state_icmp && r->keep_state) {
|
||||
pr_info_ratelimited("pfk: state-eligible proto=%d kstate=%d\n",
|
||||
pd->proto, r->keep_state);
|
||||
|
||||
if (r->rule_flag & PFRULE_SRCTRACK &&
|
||||
pf_insert_src_node(&ctx.sns[PF_SN_NONE], r, PF_SN_NONE,
|
||||
pd->af, pd->src, NULL, NULL) != 0) {
|
||||
@@ -8286,7 +8283,6 @@ pf_test(sa_family_t af, int fwdir, struct pfk_ifnet *ifp, struct mbuf **m0)
|
||||
|
||||
if (!pf_status.running)
|
||||
return (PF_PASS);
|
||||
|
||||
#if NCARP > 0
|
||||
if (ifp->if_type == IFT_CARP) {
|
||||
struct pfk_ifnet *ifp0;
|
||||
@@ -8642,18 +8638,18 @@ done:
|
||||
if (pd.destchg && pd.dir == PF_OUT)
|
||||
pd.m->m_pkthdr.pf.flags |= PF_TAG_REROUTE;
|
||||
|
||||
/*
|
||||
* PFLINUX: OpenBSD tags the mbuf here (PACKET_TAG_PF_DIVERT) and
|
||||
* netinet/ip_input.c diverts it right after pf_test(). This port has
|
||||
* no ip_input layer to hook; the verdict is mbuf-exclusive at this
|
||||
* point, so hand the packet to the divert socket immediately -
|
||||
* same observable semantics, no tag round-trip.
|
||||
*/
|
||||
if (pd.dir == PF_IN && action == PF_PASS &&
|
||||
(r->divert.type == PF_DIVERT_TO ||
|
||||
r->divert.type == PF_DIVERT_REPLY)) {
|
||||
struct pf_divert *divert;
|
||||
|
||||
if ((divert = pf_get_divert(pd.m))) {
|
||||
pd.m->m_pkthdr.pf.flags |= PF_TAG_DIVERTED;
|
||||
divert->addr = r->divert.addr;
|
||||
divert->port = r->divert.port;
|
||||
divert->rdomain = pd.rdomain;
|
||||
divert->type = r->divert.type;
|
||||
}
|
||||
divert_packet(pd.m, pd.dir, r->divert.port);
|
||||
pd.m = NULL;
|
||||
}
|
||||
|
||||
if (action == PF_PASS && r->divert.type == PF_DIVERT_PACKET)
|
||||
|
||||
@@ -90,6 +90,17 @@ pfi_kif_alloc(const char *kif_name, int mflags)
|
||||
kif->pfik_flags |= PFI_IFLAG_ANY;
|
||||
kif->pfik_flags_new |= PFI_IFLAG_ANY;
|
||||
}
|
||||
/*
|
||||
* PFLINUX: OpenBSD creates the "ingress" and "egress" interface
|
||||
* groups (ifgroups) automatically and both contain every interface;
|
||||
* pf's direction (in/out ruleset) carries the actual meaning. Linux
|
||||
* has no ifgroups, so emulate the groups as "any interface".
|
||||
*/
|
||||
if (!strcmp(kif->pfik_name, "ingress") ||
|
||||
!strcmp(kif->pfik_name, "egress")) {
|
||||
kif->pfik_flags |= PFI_IFLAG_ANY;
|
||||
kif->pfik_flags_new |= PFI_IFLAG_ANY;
|
||||
}
|
||||
|
||||
return (kif);
|
||||
}
|
||||
|
||||
@@ -662,6 +662,11 @@ pf_create_queues(void)
|
||||
}
|
||||
|
||||
qif->disc = qif->pfqops->pfq_alloc(ifp);
|
||||
if (qif->disc == NULL) {
|
||||
error = ENOBUFS;
|
||||
free(qif, M_PF, sizeof(*qif));
|
||||
goto error;
|
||||
}
|
||||
|
||||
qif->next = list;
|
||||
list = qif;
|
||||
@@ -2266,40 +2271,33 @@ pfioctl(dev_t dev, u_long cmd, caddr_t addr, int flags, struct proc *p)
|
||||
sizeof(pr->anchor) ||
|
||||
strnlen(pr->anchor_call, sizeof(pr->anchor_call)) >=
|
||||
sizeof(pr->anchor_call)) {
|
||||
error = ENAMETOOLONG; pr_info("pfkE: addrule1\n");
|
||||
error = ENAMETOOLONG;
|
||||
goto fail;
|
||||
}
|
||||
|
||||
rule = pool_get(&pf_rule_pl, PR_WAITOK|PR_LIMITFAIL|PR_ZERO);
|
||||
if (rule == NULL) {
|
||||
error = ENOMEM; pr_info("pfkE: addrule-pool\n");
|
||||
error = ENOMEM;
|
||||
goto fail;
|
||||
}
|
||||
|
||||
if ((error = pf_rule_copyin(&pr->rule, rule))) {
|
||||
pr_info("pfkE: addrule copyin=%d\n", error);
|
||||
pf_rule_free(rule);
|
||||
rule = NULL;
|
||||
goto fail;
|
||||
}
|
||||
|
||||
if (pr->rule.return_icmp >> 8 > ICMP_MAXTYPE) {
|
||||
pr_info("pfkE: addrule icmp %x\n", pr->rule.return_icmp);
|
||||
error = EINVAL;
|
||||
pf_rule_free(rule);
|
||||
rule = NULL;
|
||||
goto fail;
|
||||
}
|
||||
if ((error = pf_rule_checkaf(rule))) {
|
||||
pr_info("pfkE: addrule checkaf=%d\n", error);
|
||||
pf_rule_free(rule);
|
||||
rule = NULL;
|
||||
goto fail;
|
||||
}
|
||||
if (rule->src.addr.type == PF_ADDR_NONE ||
|
||||
rule->dst.addr.type == PF_ADDR_NONE) {
|
||||
pr_info("pfkE: addrule none src=%d dst=%d\n",
|
||||
rule->src.addr.type, rule->dst.addr.type);
|
||||
error = EINVAL;
|
||||
pf_rule_free(rule);
|
||||
rule = NULL;
|
||||
|
||||
@@ -2098,6 +2098,7 @@ pfr_commit_ktable(struct pfr_ktable *kt, time_t tzero)
|
||||
struct pfr_ktable *shadow = kt->pfrkt_shadow;
|
||||
int nflags;
|
||||
|
||||
|
||||
if (shadow->pfrkt_cnt == NO_ADDRESSES) {
|
||||
if (!(kt->pfrkt_flags & PFR_TFLAG_ACTIVE))
|
||||
pfr_clstats_ktable(kt, tzero, 1);
|
||||
|
||||
+155
-4
@@ -22,6 +22,8 @@
|
||||
#include <net/pfvar_priv.h>
|
||||
|
||||
extern int pf_test(sa_family_t, int, struct pfk_ifnet *, struct mbuf **);
|
||||
extern void divert_packet(struct mbuf *, int, u_int16_t);
|
||||
extern struct pf_divert *pf_find_divert(struct mbuf *);
|
||||
extern struct workqueue_struct *pfk_netisr_wq;
|
||||
|
||||
/* PFLINUX: netisr work item — carries ownership of one sk_buff */
|
||||
@@ -33,8 +35,6 @@ struct pfk_pkt {
|
||||
int dir;
|
||||
};
|
||||
|
||||
#define PFK_DONE_IN 0x50460010u /* skb->mark bit: PF_IN pass completed */
|
||||
#define PFK_DONE_OUT 0x50460020u /* skb->mark bit: PF_OUT pass completed */
|
||||
|
||||
static void
|
||||
pfk_pkt_reinject(struct pfk_pkt *pk)
|
||||
@@ -69,14 +69,119 @@ pfk_pkt_reinject(struct pfk_pkt *pk)
|
||||
kfree(pk);
|
||||
}
|
||||
|
||||
|
||||
/*
|
||||
* Reverse NAT: pf rewrote the destination of an inbound packet (the reply
|
||||
* of a translated flow). OpenBSD re-routes such a packet in ip_input()
|
||||
* (PF_TAG_REROUTE); Linux has no such layer, so re-route it here and push
|
||||
* it out through the new egress device.
|
||||
*/
|
||||
static void
|
||||
pfk_reroute(struct sk_buff *skb)
|
||||
{
|
||||
struct flowi4 fl4 = { };
|
||||
struct rtable *rt;
|
||||
struct iphdr *iph = ip_hdr(skb);
|
||||
|
||||
fl4.daddr = iph->daddr;
|
||||
/*
|
||||
* Leave the source empty: the packet keeps the original source
|
||||
* (the peer's address), but the kernel would reject a route lookup
|
||||
* with a non-local source (ENETUNREACH).
|
||||
*/
|
||||
fl4.saddr = 0;
|
||||
fl4.flowi4_oif = 0;
|
||||
fl4.flowi4_mark = 0;
|
||||
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
|
||||
|
||||
rt = ip_route_output_key(&init_net, &fl4);
|
||||
if (IS_ERR(rt) || rt == NULL) {
|
||||
kfree_skb(skb);
|
||||
return;
|
||||
}
|
||||
skb_dst_set(skb, &rt->dst);
|
||||
skb->dev = rt->dst.dev;
|
||||
skb_reset_network_header(skb);
|
||||
/* the stack owns skb->cb (IPCB) from here - see pfk_xmit.c */
|
||||
memset(skb->cb, 0, sizeof(skb->cb));
|
||||
rt->dst.output(&init_net, skb->sk, skb);
|
||||
}
|
||||
|
||||
/*
|
||||
* PFLINUX: pf rewrote the IPv4 addresses of the packet (NAT). OpenBSD's
|
||||
* ip_output() recomputes the IP header checksum on every packet it sends;
|
||||
* Linux does not, so fix it up here after pf touched the header.
|
||||
*/
|
||||
/*
|
||||
* pf rewrote the addresses of this packet. OpenBSD recomputes the IP header
|
||||
* checksum in ip_output() and the transport checksum is patched incrementally
|
||||
* by pf - but that only works on a *materialized* checksum, and VM-to-VM
|
||||
* traffic routinely arrives with the transport checksum still uncomputed
|
||||
* (the sender's offload never completed on the tap). So recompute from
|
||||
* scratch here:
|
||||
*
|
||||
* - GSO segments: hand the job back to the NIC (CHECKSUM_PARTIAL with the
|
||||
* transport offset); computing in software would only cover the first
|
||||
* segment and silently corrupt the rest (this is what kills bulk TCP).
|
||||
* - everything else: compute the transport checksum over the new
|
||||
* pseudo-header in software, then the IP header checksum.
|
||||
*/
|
||||
static void
|
||||
pfk_fix_csum_after_translate(struct sk_buff *skb)
|
||||
{
|
||||
struct iphdr *iph;
|
||||
unsigned int hlen, len;
|
||||
__sum16 *csum;
|
||||
__u8 proto;
|
||||
|
||||
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
|
||||
return;
|
||||
iph = ip_hdr(skb);
|
||||
hlen = iph->ihl * 4;
|
||||
proto = iph->protocol;
|
||||
len = skb->len - hlen;
|
||||
|
||||
if (proto == IPPROTO_TCP || proto == IPPROTO_UDP) {
|
||||
if (!pskb_may_pull(skb, hlen + (proto == IPPROTO_TCP ?
|
||||
sizeof(struct tcphdr) : sizeof(struct udphdr))))
|
||||
return;
|
||||
csum = (__sum16 *)(skb->data + hlen +
|
||||
(proto == IPPROTO_TCP ? offsetof(struct tcphdr, check)
|
||||
: offsetof(struct udphdr, check)));
|
||||
if (skb_is_gso(skb)) {
|
||||
skb->csum_start = (unsigned short)
|
||||
(((unsigned char *)skb->data + hlen) - skb->head);
|
||||
skb->csum_offset = proto == IPPROTO_TCP ?
|
||||
offsetof(struct tcphdr, check) :
|
||||
offsetof(struct udphdr, check);
|
||||
skb->ip_summed = CHECKSUM_PARTIAL;
|
||||
} else {
|
||||
*csum = 0;
|
||||
*csum = csum_tcpudp_magic(iph->saddr, iph->daddr, len,
|
||||
proto, skb_checksum(skb, hlen, len, 0));
|
||||
skb->ip_summed = CHECKSUM_NONE;
|
||||
}
|
||||
}
|
||||
|
||||
iph = ip_hdr(skb); /* pskb_may_pull may have moved the data */
|
||||
iph->check = 0;
|
||||
iph->check = csum_fold(csum_partial((__u8 *)iph, iph->ihl * 4, 0));
|
||||
}
|
||||
|
||||
static void
|
||||
pfk_pkt_work(struct work_struct *w)
|
||||
{
|
||||
struct pfk_pkt *pk = container_of(w, struct pfk_pkt, work);
|
||||
struct mbuf *m, *m0;
|
||||
struct sk_buff *orig;
|
||||
__be32 orig_dst = 0, orig_src = 0;
|
||||
int action;
|
||||
|
||||
if (pk->af == AF_INET && pskb_may_pull(pk->skb, sizeof(struct iphdr))) {
|
||||
orig_dst = ip_hdr(pk->skb)->daddr;
|
||||
orig_src = ip_hdr(pk->skb)->saddr;
|
||||
}
|
||||
|
||||
m = pfk_m_wrap_skb(pk->skb, pk->af);
|
||||
if (!m) {
|
||||
pfk_pkt_reinject(pk); /* like "pf not consulted" */
|
||||
@@ -91,10 +196,43 @@ pfk_pkt_work(struct work_struct *w)
|
||||
* and packet walk run concurrently from here on — documented. */
|
||||
action = pf_test(pk->af, pk->dir, pk->ifp, &m);
|
||||
|
||||
if (pk->af == AF_INET && orig_src != 0 &&
|
||||
pskb_may_pull(pk->skb, sizeof(struct iphdr)) &&
|
||||
(ip_hdr(pk->skb)->saddr != orig_src ||
|
||||
ip_hdr(pk->skb)->daddr != orig_dst))
|
||||
pfk_fix_csum_after_translate(pk->skb);
|
||||
|
||||
|
||||
if (m == m0) {
|
||||
/*
|
||||
* Queueing: when a pf `queue' rule attached a scheduler to the
|
||||
* egress interface, hand the packet to it instead of sending it
|
||||
* straight out - this is what makes bandwidth limits real.
|
||||
*/
|
||||
if (action == PF_PASS && pk->dir == PF_OUT &&
|
||||
pskb_may_pull(pk->skb, sizeof(struct iphdr)) &&
|
||||
skb_dst(pk->skb) && !IS_ERR(skb_dst(pk->skb)) &&
|
||||
pf_kifq_input(skb_dst(pk->skb)->dev ?
|
||||
pfk_ifp_bydev(skb_dst(pk->skb)->dev) : NULL, m)) {
|
||||
orig = pk->skb;
|
||||
pk->skb = NULL; /* the queue owns the packet */
|
||||
kfree_skb(orig);
|
||||
kfree(pk);
|
||||
return;
|
||||
}
|
||||
/* same buffer, possibly rewritten in place: our wrapper
|
||||
* held one extra skb reference — release it */
|
||||
m_freem(m);
|
||||
if (action == PF_PASS && orig_dst != 0 &&
|
||||
pk->af == AF_INET && pk->dir == PF_IN &&
|
||||
pskb_may_pull(pk->skb, sizeof(struct iphdr)) &&
|
||||
ip_hdr(pk->skb)->daddr != orig_dst) {
|
||||
/* pf translated the destination (reverse NAT):
|
||||
* re-route instead of delivering locally */
|
||||
pfk_reroute(pk->skb);
|
||||
kfree(pk);
|
||||
return;
|
||||
}
|
||||
if (action == PF_PASS) {
|
||||
pfk_pkt_reinject(pk);
|
||||
return;
|
||||
@@ -135,15 +273,27 @@ pfk_enqueue_verdict(int af, struct sk_buff *skb,
|
||||
|
||||
switch (st->hook) {
|
||||
case NF_INET_PRE_ROUTING:
|
||||
/* OpenBSD evaluates the IN ruleset in ip_input(); every
|
||||
* arriving packet passes it. */
|
||||
dir = PF_IN;
|
||||
break;
|
||||
case NF_INET_FORWARD:
|
||||
/* OpenBSD evaluates the OUT ruleset of a forwarded packet in
|
||||
* ip_forward() (pf_test(PF_FWD)); the IN ruleset was already
|
||||
* applied at input time. Without this, transit traffic never
|
||||
* sees the "out" rules and state matching for replies is
|
||||
* impossible. */
|
||||
dir = PF_OUT;
|
||||
break;
|
||||
case NF_INET_LOCAL_OUT:
|
||||
case NF_INET_POST_ROUTING:
|
||||
dir = PF_OUT;
|
||||
break;
|
||||
default:
|
||||
return NF_ACCEPT; /* LOCAL_IN/FORWARD */
|
||||
return NF_ACCEPT; /* LOCAL_IN */
|
||||
}
|
||||
if (skb->mark & PFK_SKIP_PF)
|
||||
return NF_ACCEPT; /* reinjected by divert: don't re-filter */
|
||||
if (skb->mark & (dir == PF_IN ? PFK_DONE_IN : PFK_DONE_OUT))
|
||||
return NF_ACCEPT;
|
||||
|
||||
@@ -155,7 +305,8 @@ pfk_enqueue_verdict(int af, struct sk_buff *skb,
|
||||
if (dir == PF_IN)
|
||||
ifp = pfk_ifp_bydev(st->in ? st->in : skb->dev);
|
||||
else
|
||||
ifp = pfk_ifp_bydev(skb->dev ? skb->dev : st->out);
|
||||
ifp = pfk_ifp_bydev(st->out ? st->out :
|
||||
(skb->dev ? skb->dev : NULL));
|
||||
if (!ifp)
|
||||
return NF_ACCEPT;
|
||||
|
||||
|
||||
+17
-4
@@ -54,9 +54,6 @@ pfk_ioctl_io(struct file *filp, unsigned int cmd, unsigned long arg)
|
||||
p.p_ucred = &cred;
|
||||
p.p_p = &pp;
|
||||
|
||||
if (cmd == DIOCADDRULE)
|
||||
pr_info("pfkE: ioctl sz=%d kern_size=%d rule=%d\n", (int)sz,
|
||||
(int)sizeof(struct pfioc_rule), (int)sizeof(struct pf_rule));
|
||||
kdata = kzalloc(sz ? sz : sizeof(long), GFP_KERNEL);
|
||||
if (!kdata)
|
||||
return -ENOMEM;
|
||||
@@ -96,6 +93,10 @@ static struct miscdevice pfk_dev = {
|
||||
|
||||
extern void pf_status_init(void);
|
||||
extern int pfattach(int);
|
||||
extern int pfk_divert_sock_register(void);
|
||||
extern int pfk_pflog_register(void);
|
||||
extern void pfk_pflog_unregister(void);
|
||||
extern void pfk_divert_sock_unregister(void);
|
||||
|
||||
static void
|
||||
pfk_pfi_event(int added, struct pfk_ifnet *ifp)
|
||||
@@ -134,15 +135,25 @@ static int __init pfk_init(void)
|
||||
pfattach(0);
|
||||
pfk_if_set_event_cb(pfk_pfi_event);
|
||||
pfk_if_iterate(pfk_pfi_attach_one);
|
||||
err = pfk_hooks_register();
|
||||
err = pfk_pflog_register();
|
||||
if (err)
|
||||
goto err_if;
|
||||
err = pfk_divert_sock_register();
|
||||
if (err)
|
||||
goto err_pflog;
|
||||
err = pfk_hooks_register();
|
||||
if (err)
|
||||
goto err_divert;
|
||||
err = misc_register(&pfk_dev);
|
||||
if (err)
|
||||
goto err_hooks;
|
||||
pr_info("pfk: PF-on-Linux engine loaded (OpenBSD 8.0 base)\n");
|
||||
return 0;
|
||||
err_hooks:
|
||||
pfk_divert_sock_unregister();
|
||||
err_divert:
|
||||
pfk_pflog_unregister();
|
||||
err_pflog:
|
||||
pfk_hooks_unregister();
|
||||
err_if:
|
||||
pfk_if_exit();
|
||||
@@ -161,6 +172,8 @@ static void __exit pfk_exit(void)
|
||||
* self-rearms (pf_purge re-arms on every run) and would keep the
|
||||
* workqueues non-empty forever (observed rmmod hang). */
|
||||
misc_deregister(&pfk_dev);
|
||||
pfk_divert_sock_unregister();
|
||||
pfk_pflog_unregister();
|
||||
pfk_net_lock();
|
||||
pf_status.running = 0;
|
||||
pfk_net_unlock();
|
||||
|
||||
@@ -0,0 +1,310 @@
|
||||
/*
|
||||
* PF-on-Linux: pflog backend (ISC 2026)
|
||||
*
|
||||
* OpenBSD logs matched packets to the pflog(4) *network interface*, which
|
||||
* pflogd(8) reads through bpf(4). Linux has neither if_pflog-style virtual
|
||||
* interfaces exposed to bpf nor a DLT_PFLOG consumer, so this port offers the
|
||||
* same record format over a character device:
|
||||
*
|
||||
* /dev/pflog (0600) - read() returns one record at a time:
|
||||
* struct pflog_hdr followed by the captured
|
||||
* packet bytes (truncated to PFLOG_COPY_SIZE).
|
||||
*
|
||||
* poll() reports readable when a record is queued. A single consumer is the
|
||||
* real use case (pflogd), which is why a chardev - not netlink multicast -
|
||||
* was chosen; the deviation is documented in docs/porting-notes.md.
|
||||
*
|
||||
* The records are byte-compatible with OpenBSD's pflog(4) so tcpdump/wireshark
|
||||
* read the pcap with linktype DLT_PFLOG (117).
|
||||
*/
|
||||
|
||||
#include <linux/kernel.h>
|
||||
#include <linux/module.h>
|
||||
#include <linux/miscdevice.h>
|
||||
#include <linux/fs.h>
|
||||
#include <linux/mm.h>
|
||||
#include <linux/poll.h>
|
||||
#include <linux/slab.h>
|
||||
#include <linux/spinlock.h>
|
||||
#include <linux/wait.h>
|
||||
#include <linux/timekeeping.h>
|
||||
#include <linux/uaccess.h>
|
||||
#include <linux/netdevice.h>
|
||||
|
||||
#include <pfk.h>
|
||||
#include <pfk_api.h>
|
||||
|
||||
/* OpenBSD sys/net/pflog.h */
|
||||
#define PFLOG_IFNAMSIZ 16
|
||||
#define PFLOG_RULESET_NAME_SIZE 16
|
||||
#define PFLOG_HDRLEN 64 /* sizeof(struct pfk_pflog_hdr) */
|
||||
#define PFLOG_COPY_SIZE 160
|
||||
|
||||
/* byte-compatible with OpenBSD's <net/pflog.h> (sizeof == 64) */
|
||||
struct pfk_pflog_hdr {
|
||||
struct {
|
||||
s64 tv_sec;
|
||||
s64 tv_usec;
|
||||
} pflog_ts;
|
||||
u8 pflog_af;
|
||||
u8 pflog_reason;
|
||||
u8 pflog_ifname[PFLOG_IFNAMSIZ];
|
||||
u8 pflog_ruleset[PFLOG_RULESET_NAME_SIZE];
|
||||
u8 pflog_nr;
|
||||
u8 pflog_anc;
|
||||
u8 pflog_flags;
|
||||
u8 pflog_pad[9];
|
||||
u16 pflog_len; /* captured packet length */
|
||||
} __packed;
|
||||
|
||||
struct pfk_pflog_rec {
|
||||
struct list_head list;
|
||||
size_t len; /* header + payload */
|
||||
char data[]; /* pfk_pflog_hdr, then the packet */
|
||||
};
|
||||
|
||||
#define PFK_PFLOG_MAX_QUEUE 256u
|
||||
#define PFK_PFLOG_MAX_BYTES (1u << 20)
|
||||
|
||||
static LIST_HEAD(pflog_list);
|
||||
static DEFINE_SPINLOCK(pflog_lock);
|
||||
static DECLARE_WAIT_QUEUE_HEAD(pflog_wq);
|
||||
static unsigned long pflog_queued, pflog_bytes, pflog_dropped;
|
||||
static u64 pflog_seq;
|
||||
|
||||
/*
|
||||
* Queue one record. Called from the packet path (process context here: the
|
||||
* data path runs in pfk_netisr_wq), so a GFP_ATOMIC allocation and a bounded
|
||||
* queue keep it safe even if a future caller appears in softirq context.
|
||||
*/
|
||||
static void
|
||||
pfk_pflog_put(struct pfk_pflog_hdr *hdr, const void *pkt, size_t pktlen)
|
||||
{
|
||||
struct pfk_pflog_rec *rec;
|
||||
size_t len = sizeof(*hdr) + pktlen;
|
||||
unsigned long flags;
|
||||
|
||||
if (READ_ONCE(pflog_queued) >= PFK_PFLOG_MAX_QUEUE ||
|
||||
READ_ONCE(pflog_bytes) + len > PFK_PFLOG_MAX_BYTES) {
|
||||
pflog_dropped++;
|
||||
return;
|
||||
}
|
||||
|
||||
rec = kmalloc(struct_size(rec, data, len), GFP_ATOMIC);
|
||||
if (rec == NULL) {
|
||||
pflog_dropped++;
|
||||
return;
|
||||
}
|
||||
rec->len = len;
|
||||
memcpy(rec->data, hdr, sizeof(*hdr));
|
||||
memcpy(rec->data + sizeof(*hdr), pkt, pktlen);
|
||||
|
||||
spin_lock_irqsave(&pflog_lock, flags);
|
||||
list_add_tail(&rec->list, &pflog_list);
|
||||
pflog_queued++;
|
||||
pflog_bytes += len;
|
||||
pflog_seq++;
|
||||
spin_unlock_irqrestore(&pflog_lock, flags);
|
||||
|
||||
wake_up_interruptible(&pflog_wq);
|
||||
}
|
||||
|
||||
/* copy the leading bytes of the packet (the mbuf chain may be a wrapper) */
|
||||
static size_t
|
||||
pfk_pflog_pull(struct mbuf *m, char *buf, size_t want)
|
||||
{
|
||||
struct sk_buff *skb = m ? m_to_skb(m) : NULL;
|
||||
size_t n;
|
||||
int off;
|
||||
|
||||
if (skb == NULL)
|
||||
return 0;
|
||||
/*
|
||||
* BSD logs from the network header; pf may already have advanced the
|
||||
* mbuf/skb data pointer to the transport header while parsing, so
|
||||
* anchor explicitly at the IP header instead of at skb->data.
|
||||
*/
|
||||
off = skb_network_offset(skb);
|
||||
if (off < 0)
|
||||
off = 0;
|
||||
if (off > skb->len)
|
||||
return 0;
|
||||
n = min_t(size_t, want, skb->len - off);
|
||||
if (skb_copy_bits(skb, off, buf, n))
|
||||
return 0;
|
||||
return n;
|
||||
}
|
||||
|
||||
/* ---------------- pflog_packet() (called by the ported pf.c) ---------------- */
|
||||
|
||||
int
|
||||
pflog_packet(struct pf_pdesc *pd, u_int8_t reason, struct pf_rule *rm,
|
||||
struct pf_rule *am, struct pf_ruleset *ruleset, struct pf_rule *cm)
|
||||
{
|
||||
struct pfk_pflog_hdr hdr;
|
||||
char pkt[PFLOG_COPY_SIZE];
|
||||
struct pf_rule *r;
|
||||
size_t n;
|
||||
|
||||
if (pd == NULL || pd->m == NULL)
|
||||
return (0);
|
||||
|
||||
memset(&hdr, 0, sizeof(hdr));
|
||||
{
|
||||
struct timespec64 ts;
|
||||
|
||||
ktime_get_real_ts64(&ts);
|
||||
hdr.pflog_ts.tv_sec = ts.tv_sec;
|
||||
hdr.pflog_ts.tv_usec = ts.tv_nsec / 1000;
|
||||
}
|
||||
hdr.pflog_af = pd->af;
|
||||
hdr.pflog_reason = reason;
|
||||
|
||||
r = cm ? cm : (am ? am : rm);
|
||||
if (r) {
|
||||
strscpy((char *)hdr.pflog_ifname,
|
||||
pd->kif ? pd->kif->pfik_name : "",
|
||||
sizeof(hdr.pflog_ifname));
|
||||
strscpy((char *)hdr.pflog_ruleset,
|
||||
(ruleset && ruleset->anchor) ? ruleset->anchor->name : "",
|
||||
sizeof(hdr.pflog_ruleset));
|
||||
hdr.pflog_nr = r->nr;
|
||||
hdr.pflog_anc = 0;
|
||||
hdr.pflog_flags = r->log;
|
||||
}
|
||||
|
||||
n = pfk_pflog_pull(pd->m, pkt, sizeof(pkt));
|
||||
hdr.pflog_len = cpu_to_be16(n); /* BSD stores it in network order */
|
||||
|
||||
pfk_pflog_put(&hdr, pkt, n);
|
||||
return (0);
|
||||
}
|
||||
|
||||
/* ---------------- /dev/pflog ---------------- */
|
||||
|
||||
static int
|
||||
pfk_pflog_open(struct inode *inode, struct file *filp)
|
||||
{
|
||||
filp->private_data = NULL;
|
||||
return nonseekable_open(inode, filp);
|
||||
}
|
||||
|
||||
static ssize_t
|
||||
pfk_pflog_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
|
||||
{
|
||||
struct pfk_pflog_rec *rec = filp->private_data;
|
||||
unsigned long flags;
|
||||
size_t off, n;
|
||||
|
||||
spin_lock_irqsave(&pflog_lock, flags);
|
||||
if (rec == NULL) {
|
||||
if (list_empty(&pflog_list)) {
|
||||
spin_unlock_irqrestore(&pflog_lock, flags);
|
||||
if (filp->f_flags & O_NONBLOCK)
|
||||
return -EAGAIN;
|
||||
if (wait_event_interruptible(pflog_wq,
|
||||
!list_empty(&pflog_list)))
|
||||
return -ERESTARTSYS;
|
||||
spin_lock_irqsave(&pflog_lock, flags);
|
||||
if (list_empty(&pflog_list)) {
|
||||
spin_unlock_irqrestore(&pflog_lock, flags);
|
||||
return -EAGAIN;
|
||||
}
|
||||
}
|
||||
rec = list_first_entry(&pflog_list, struct pfk_pflog_rec, list);
|
||||
list_del(&rec->list);
|
||||
pflog_queued--;
|
||||
pflog_bytes -= rec->len;
|
||||
filp->private_data = rec;
|
||||
}
|
||||
spin_unlock_irqrestore(&pflog_lock, flags);
|
||||
|
||||
/* partial reads resume through *ppos (record is pinned to the file) */
|
||||
off = *ppos;
|
||||
if (off >= rec->len) {
|
||||
kfree(rec);
|
||||
filp->private_data = NULL;
|
||||
*ppos = 0;
|
||||
return 0;
|
||||
}
|
||||
n = min(count, rec->len - off);
|
||||
if (copy_to_user(buf, rec->data + off, n))
|
||||
return -EFAULT;
|
||||
*ppos += n;
|
||||
if (*ppos == rec->len) {
|
||||
kfree(rec);
|
||||
filp->private_data = NULL;
|
||||
*ppos = 0;
|
||||
}
|
||||
return n;
|
||||
}
|
||||
|
||||
static __poll_t
|
||||
pfk_pflog_poll(struct file *filp, poll_table *wait)
|
||||
{
|
||||
__poll_t mask = 0;
|
||||
|
||||
poll_wait(filp, &pflog_wq, wait);
|
||||
if (filp->private_data != NULL)
|
||||
mask |= EPOLLIN | EPOLLRDNORM;
|
||||
else if (!list_empty(&pflog_list))
|
||||
mask |= EPOLLIN | EPOLLRDNORM;
|
||||
return mask;
|
||||
}
|
||||
|
||||
static long
|
||||
pfk_pflog_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
|
||||
{
|
||||
struct pfk_pflog_stat st;
|
||||
|
||||
switch (cmd) {
|
||||
case PFKIOCGETPFLOGSTAT:
|
||||
st.queued = pflog_queued;
|
||||
st.bytes = pflog_bytes;
|
||||
st.dropped = pflog_dropped;
|
||||
st.seq = pflog_seq;
|
||||
if (copy_to_user((void __user *)arg, &st, sizeof(st)))
|
||||
return -EFAULT;
|
||||
return 0;
|
||||
default:
|
||||
return -ENOTTY;
|
||||
}
|
||||
}
|
||||
|
||||
static const struct file_operations pfk_pflog_fops = {
|
||||
.owner = THIS_MODULE,
|
||||
.open = pfk_pflog_open,
|
||||
.read = pfk_pflog_read,
|
||||
.poll = pfk_pflog_poll,
|
||||
.unlocked_ioctl = pfk_pflog_ioctl,
|
||||
.compat_ioctl = compat_ptr_ioctl,
|
||||
};
|
||||
|
||||
static struct miscdevice pfk_pflog_dev = {
|
||||
.minor = MISC_DYNAMIC_MINOR,
|
||||
.name = "pflog",
|
||||
.fops = &pfk_pflog_fops,
|
||||
.mode = 0600,
|
||||
};
|
||||
|
||||
int
|
||||
pfk_pflog_register(void)
|
||||
{
|
||||
return misc_register(&pfk_pflog_dev);
|
||||
}
|
||||
|
||||
void
|
||||
pfk_pflog_unregister(void)
|
||||
{
|
||||
struct pfk_pflog_rec *rec, *tmp;
|
||||
|
||||
misc_deregister(&pfk_pflog_dev);
|
||||
spin_lock(&pflog_lock);
|
||||
list_for_each_entry_safe(rec, tmp, &pflog_list, list) {
|
||||
list_del(&rec->list);
|
||||
kfree(rec);
|
||||
}
|
||||
pflog_queued = 0;
|
||||
pflog_bytes = 0;
|
||||
spin_unlock(&pflog_lock);
|
||||
}
|
||||
@@ -0,0 +1,84 @@
|
||||
{"version": 2, "width": 80, "height": 24, "timestamp": 1794449787, "env": {"SHELL": null, "TERM": "dumb"}}
|
||||
[1.414508, "o", "\u001b[1m===============================================================\u001b[0m\r\n\u001b[1m PF on Linux - the OpenBSD PF 8.0 engine inside the Linux kernel\u001b[0m\r\n\u001b[1m===============================================================\u001b[0m\r\n\r\nLab: 3 Alpine VMs under libvirt.\r\n pftest-pf0 = firewall (kernel 7.3.4 built from source + pf.ko)\r\n pftest-cli = client 10.0.1.10 pftest-srv = server 10.0.2.20\r\n\r\n\u001b[1m--- 1. our kernel, the OpenBSD engine as a module ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# uname -r\u001b[0m\r\n"]
|
||||
[1.655866, "o", "7.3.4\r\n"]
|
||||
[2.058621, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf ' || echo 'pf: not loaded yet'\u001b[0m\r\n"]
|
||||
[2.276696, "o", "pf: not loaded yet\r\n"]
|
||||
[2.680328, "o", "\u001b[1;36mpftest-pf0# insmod /opt/pf/pf.ko && dmesg | tail -3\u001b[0m\r\n"]
|
||||
[2.917691, "o", "[ 146.252272] NET: Registered PF_IUCV protocol family\r\n[ 146.252362] pfk: netfilter hooks registered (10, netisr wq data path)\r\n[ 146.252423] pfk: PF-on-Linux engine loaded (OpenBSD 8.0 base)\r\n"]
|
||||
[3.320802, "o", "\r\n\u001b[1m--- 2. pfctl talks to the module over the OpenBSD ioctl ABI ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s info | head -4\u001b[0m\r\n"]
|
||||
[3.598837, "o", "Status: Disabled for 0 days 00:02:26 Debug: err\r\n\r\nState Table Total Rate\r\n current entries 0 \r\n"]
|
||||
[4.00249, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -e && /opt/pf/pfctl -s info | head -1\u001b[0m\r\n"]
|
||||
[4.274878, "o", "Status: Enabled Debug: err\r\npf enabled\r\n"]
|
||||
[4.678074, "o", "\r\n\u001b[1m--- 3. a real pf.conf: tables, stateful rules, an explicit drop ---\u001b[0m\r\n"]
|
||||
[4.678128, "o", "\u001b[1;36mpftest-pf0# cat /tmp/demo-pf.conf\u001b[0m\r\n"]
|
||||
[4.954849, "o", "# PF-on-Linux demo ruleset (pf.conf syntax, real OpenBSD pfctl)\r\nset block-policy return\r\ntable <trusted> { 10.0.1.0/24 }\r\n\r\n# transit traffic: stateful, table-driven\r\npass in quick on ingress proto icmp from <trusted> keep state\r\npass out quick on egress proto icmp keep state\r\n\r\n# deny a specific destination\r\nblock drop in quick proto icmp to 10.0.9.99\r\n\r\n# everything else\r\npass in quick\r\npass out quick\r\n"]
|
||||
[5.358199, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'rules loaded'\u001b[0m\r\n"]
|
||||
[5.630704, "o", "rules loaded\r\n"]
|
||||
[6.034552, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr\u001b[0m\r\n"]
|
||||
[6.322794, "o", "pass in quick on ingress proto icmp from <trusted> to any\r\npass out quick on egress proto icmp all\r\nblock drop in quick inet proto icmp from any to 10.0.9.99\r\npass in quick all flags S/SA\r\npass out quick all flags S/SA\r\n"]
|
||||
[6.725786, "o", "\r\n"]
|
||||
[6.72584, "o", "\u001b[1m--- 4. transit traffic is allowed and stateful ---\u001b[0m\r\n\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
|
||||
[7.977099, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.339/0.351/0.363 ms\r\n"]
|
||||
[8.379918, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
|
||||
[8.634572, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:5449 0:0\r\nall icmp 10.0.1.10:5449 -> 10.0.2.20:8 0:0\r\n"]
|
||||
[9.036709, "o", "\r\n\u001b[1m--- 5. tables are live objects ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# /opt/pf/pfctl -t trusted -T show\u001b[0m\r\n"]
|
||||
[9.298627, "o", " 10.0.1.0/24\r\n"]
|
||||
[9.701487, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -s Tables\u001b[0m\r\n"]
|
||||
[9.974937, "o", "trusted\r\n"]
|
||||
[10.378208, "o", "\r\n\u001b[1m--- 6. the drop rule actually drops ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# cat > /tmp/demo-block.conf <<EOF\r\nblock drop in quick proto icmp to 10.0.2.20\r\npass in quick\r\npass out quick\r\nEOF\u001b[0m\r\n"]
|
||||
[11.033956, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-block.conf && echo 'block rules loaded'\u001b[0m\r\n"]
|
||||
[11.310724, "o", "block rules loaded\r\n"]
|
||||
[11.714107, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
|
||||
[14.969152, "o", "\r\n--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 0 packets received, 100% packet loss\r\n"]
|
||||
[15.372543, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -sr -vv | head -6\u001b[0m\r\n"]
|
||||
[15.66699, "o", "@0 block drop in quick inet proto icmp from any to 10.0.2.20\r\n [ Evaluations: 6 Packets: 2 Bytes: 168 States: 0 ]\r\n [ Inserted: uid 0 pid 1687 State Creations: 0 ]\r\n@1 pass in quick all flags S/SA\r\n [ Evaluations: 1 Packets: 28 Bytes: 9296 States: 1 ]\r\n [ Inserted: uid 0 pid 1687 State Creations: 1 ]\r\n"]
|
||||
[16.07016, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
|
||||
[16.338781, "o", "back to the stateful ruleset\r\n"]
|
||||
[16.742479, "o", "\r\n\u001b[1m--- 7. NAT: the source is translated on the way out, restored on the way back ---\u001b[0m\r\n"]
|
||||
[16.742537, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-nat.conf <<EOF\r\npass out quick on egress from 10.0.1.0/24 to any nat-to (eth2)\r\npass in quick on ingress proto icmp keep state\r\npass out quick on egress proto icmp keep state\r\nEOF\u001b[0m\r\n"]
|
||||
[17.422636, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-nat.conf && echo 'nat rules loaded'\u001b[0m\r\n"]
|
||||
[17.686794, "o", "nat rules loaded\r\n"]
|
||||
[18.090339, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -3\u001b[0m\r\n"]
|
||||
[19.341141, "o", "--- 10.0.2.20 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.276/0.317/0.359 ms\r\n"]
|
||||
[19.744749, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -ss | grep -E 'icmp' | head -4\u001b[0m\r\n"]
|
||||
[20.010971, "o", "all icmp 10.0.2.20:8 <- 10.0.1.10:5461 0:0\r\nall icmp 10.0.2.1:43040 (10.0.1.10:5461) -> 10.0.2.20:8 0:0\r\n"]
|
||||
[20.414328, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'\u001b[0m\r\n"]
|
||||
[20.690817, "o", "back to the stateful ruleset\r\n"]
|
||||
[21.094035, "o", "\r\n\u001b[1m--- 8. pflog: logged packets reach userspace (/dev/pflog) ---\u001b[0m\r\n"]
|
||||
[21.094088, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-log.conf <<EOF\r\npass in quick log proto icmp from 10.0.1.10 keep state\r\npass out quick\r\nEOF\u001b[0m\r\n"]
|
||||
[21.762242, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-log.conf && echo 'log rule loaded'\u001b[0m\r\n"]
|
||||
[22.034943, "o", "log rule loaded\r\n"]
|
||||
[22.438523, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pflogd; rm -f /tmp/pflog.pcap; (setsid /tmp/pflogd -c 2 /tmp/pflog.pcap >/tmp/pflogd.log 2>&1 </dev/null &); sleep 1; echo 'pflogd collecting 2 records'\u001b[0m\r\n"]
|
||||
[23.681454, "o", "pflogd collecting 2 records\r\n"]
|
||||
[24.084864, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.2.20 | tail -2\u001b[0m\r\n"]
|
||||
[25.333003, "o", "2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.352/0.364/0.376 ms\r\n"]
|
||||
[27.737616, "o", "\u001b[1;36mpftest-pf0# cat /tmp/pflogd.log; ls -l /tmp/pflog.pcap; echo 'pcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):'; od -An -tx1 -N24 /tmp/pflog.pcap\u001b[0m\r\n"]
|
||||
[28.026778, "o", "pflogd: 2 records\r\n-rw------- 1 root root 324 Nov 12 02:16 /tmp/pflog.pcap\r\npcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):\r\n d4 c3 b2 a1 02 00 04 00 00 00 00 00 00 00 00 00\r\n ff ff 00 00 75 00 00 00\r\n"]
|
||||
[28.430241, "o", "\u001b[1;36mpftest-pf0# pkill pflogd 2>/dev/null; /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null\u001b[0m\r\n"]
|
||||
[29.114632, "o", "\r\n\u001b[1m--- 9. route-to: force the next hop away from the normal path ---\u001b[0m\r\n"]
|
||||
[29.114687, "o", "\u001b[1;36mpftest-pf0# cat > /tmp/demo-route.conf <<EOF\r\npass in quick proto icmp from 10.0.1.10 to 10.0.2.20 route-to { 10.0.3.2 } keep state\r\npass out quick\r\nEOF\u001b[0m\r\n"]
|
||||
[29.778259, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-route.conf && echo 'route-to rule loaded'\u001b[0m\r\n"]
|
||||
[30.050898, "o", "route-to rule loaded\r\n"]
|
||||
[30.45427, "o", "\u001b[1;36mpftest-pf0# (tcpdump -ni eth3 -c 2 -e icmp > /tmp/route.td 2>&1 &); (tcpdump -ni eth2 -c 2 -e icmp > /tmp/norm.td 2>&1 &); sleep 1\u001b[0m\r\n"]
|
||||
[32.089063, "o", "\u001b[1;36mpftest-cli# ping -c1 -W2 10.0.2.20 | tail -2\u001b[0m\r\n"]
|
||||
[34.31667, "o", "--- 10.0.2.20 ping statistics ---\r\n1 packets transmitted, 0 packets received, 100% packet loss\r\n"]
|
||||
[36.72139, "o", "\u001b[1;36mpftest-pf0# echo 'forced egress (eth3, toward the gateway):'; grep -v '^tcpdump\\|^listening\\|^$' /tmp/route.td | head -2; echo 'normal egress (eth2):'; grep -c 'echo request' /tmp/norm.td\u001b[0m\r\n"]
|
||||
[37.006878, "o", "forced egress (eth3, toward the gateway):\r\n02:16:59.958272 52:54:00:aa:00:04 > 52:54:00:dd:00:02, ethertype IPv4 (0x0800), length 98: 10.0.1.10 > 10.0.2.20: ICMP echo request, id 5473, seq 0, length 64\r\nnormal egress (eth2):\r\n0\r\n"]
|
||||
[37.410476, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null\u001b[0m\r\n"]
|
||||
[38.094888, "o", "\r\n\u001b[1m--- 10. divert-to: the packet goes to userspace and comes back ---\u001b[0m\r\n"]
|
||||
[38.095122, "o", "\u001b[1;36mpftest-pf0# cat /tmp/demo-divert.conf\u001b[0m\r\n"]
|
||||
[38.35866, "o", "pass in quick proto icmp from 10.0.1.10 to 10.0.1.1 divert-to \"10.0.1.1\" port 10000 keep state\r\npass out quick\r\n"]
|
||||
[38.763007, "o", "\u001b[1;36mpftest-pf0# /opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'\u001b[0m\r\n"]
|
||||
[39.022814, "o", "divert rule loaded\r\n"]
|
||||
[39.42606, "o", "\u001b[1;36mpftest-pf0# chmod +x /tmp/pdivert; (setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert\u001b[0m\r\n"]
|
||||
[40.654519, "o", "1794\r\n"]
|
||||
[41.056785, "o", "\u001b[1;36mpftest-cli# ping -c2 -W2 10.0.1.1 | tail -3\u001b[0m\r\n"]
|
||||
[42.284778, "o", "--- 10.0.1.1 ping statistics ---\r\n2 packets transmitted, 2 packets received, 0% packet loss\r\nround-trip min/avg/max = 0.177/0.224/0.271 ms\r\n"]
|
||||
[42.691426, "o", "\u001b[1;36mpftest-pf0# head -3 /tmp/pdivert.log\u001b[0m\r\n"]
|
||||
[42.942601, "o", "pdivert: listening on divert port 10000\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\npdivert: got 84 bytes 10.0.1.10 -> 10.0.1.1\r\n"]
|
||||
[43.344696, "o", " (pdivert flipped the last payload byte and fixed the ICMP checksum)\r\n\r\n\u001b[1m--- 11. shutdown ---\u001b[0m\r\n\u001b[1;36mpftest-pf0# pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'\u001b[0m\r\n"]
|
||||
[43.626606, "o", "pf disabled\r\npf disabled\r\n"]
|
||||
[44.028882, "o", "\u001b[1;36mpftest-pf0# lsmod | grep '^pf '\u001b[0m\r\n"]
|
||||
[44.286597, "o", "pf 552960 0\r\n"]
|
||||
[44.688511, "o", "\r\n\u001b[1mdemo over - port, gates and docs:\u001b[0m\r\n\u001b[1m https://git.labexposed.com/lgcosta/pf-linux-port\u001b[0m\r\n"]
|
||||
[44.688631, "o", "\r\n"]
|
||||
Executable
+161
@@ -0,0 +1,161 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
PF-on-Linux demo recorder -> asciicast v2 (.cast)
|
||||
|
||||
Every byte shown comes from the REAL lab (Alpine VMs under libvirt, kernel
|
||||
7.3.4 built from source with our pf.ko). Only the pacing is scripted.
|
||||
|
||||
Usage:
|
||||
./scripts/demo-record.py [--out out/demo-pf-linux.cast] [--quick]
|
||||
|
||||
Play back with: asciinema play out/demo-pf-linux.cast
|
||||
Upload with: asciinema upload out/demo-pf-linux.cast
|
||||
"""
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import shlex
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
|
||||
REPO = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
DEB = os.environ.get("DEB", "root@192.168.1.242")
|
||||
PF0 = os.environ.get("PF0_IP", "192.168.122.8")
|
||||
CLI = os.environ.get("CLI_IP", "10.0.1.10")
|
||||
SRV = os.environ.get("SRV_IP", "10.0.2.20")
|
||||
KEY = os.path.join(os.environ.get("HOME", "/root"), ".ssh/pflab_ed")
|
||||
|
||||
CONF = """# PF-on-Linux demo ruleset (pf.conf syntax, real OpenBSD pfctl)
|
||||
set block-policy return
|
||||
table <trusted> { 10.0.1.0/24 }
|
||||
|
||||
# transit traffic: stateful, table-driven
|
||||
pass in quick on ingress proto icmp from <trusted> keep state
|
||||
pass out quick on egress proto icmp keep state
|
||||
|
||||
# deny a specific destination
|
||||
block drop in quick proto icmp to 10.0.9.99
|
||||
|
||||
# everything else
|
||||
pass in quick
|
||||
pass out quick
|
||||
"""
|
||||
|
||||
DIVERT_CONF = """pass in quick proto icmp from 10.0.1.10 to 10.0.1.1 divert-to "10.0.1.1" port 10000 keep state
|
||||
pass out quick
|
||||
"""
|
||||
|
||||
|
||||
def sh(cmd, timeout=40):
|
||||
p = subprocess.run(cmd, shell=True, capture_output=True, text=True,
|
||||
timeout=timeout)
|
||||
return (p.stdout or "") + (p.stderr or "")
|
||||
|
||||
|
||||
def on_pf0(cmd, timeout=40):
|
||||
return sh(f"ssh -o ConnectTimeout=8 -o StrictHostKeyChecking=accept-new "
|
||||
f"-i {KEY} root@{PF0} {shlex.quote(cmd)}", timeout)
|
||||
|
||||
|
||||
def on_vm(ip, cmd, timeout=40):
|
||||
return sh(f"ssh -o ConnectTimeout=8 -o StrictHostKeyChecking=accept-new "
|
||||
f"-i {KEY} root@{ip} {shlex.quote(cmd)}", timeout)
|
||||
|
||||
|
||||
def on_deb(cmd, timeout=40):
|
||||
return sh(f"ssh -o ConnectTimeout=8 {DEB} {shlex.quote(cmd)}", timeout)
|
||||
|
||||
|
||||
def stage():
|
||||
"""put the demo ruleset + pdivert on pf0 (through the lab host)"""
|
||||
with open("/tmp/demo-pf.conf", "w") as f:
|
||||
f.write(CONF)
|
||||
with open("/tmp/demo-divert.conf", "w") as f:
|
||||
f.write(DIVERT_CONF)
|
||||
sh(f"scp -q /tmp/demo-pf.conf /tmp/demo-divert.conf "
|
||||
f"{os.path.join(REPO, 'tools/out/pdivert')} {DEB}:/tmp/", timeout=90)
|
||||
on_deb(f"scp -q -o StrictHostKeyChecking=accept-new -i {KEY} "
|
||||
f"/tmp/demo-pf.conf /tmp/demo-divert.conf /tmp/pdivert "
|
||||
f"root@{PF0}:/tmp/ 2>&1", timeout=90)
|
||||
|
||||
|
||||
SCENARIO = [
|
||||
("local", "echo '=== PF on Linux — OpenBSD PF 8.0 engine running inside the Linux 7.3.4 kernel ==='"),
|
||||
("local", "echo 'lab: 3 Alpine VMs under libvirt (pf0 = firewall, cli/srv = transit endpoints)'"),
|
||||
("pf0", "uname -r"),
|
||||
("pf0", "lsmod | grep '^pf ' || echo 'pf: not loaded'"),
|
||||
("pf0", "insmod /opt/pf/pf.ko && dmesg | tail -3"),
|
||||
("pf0", "/opt/pf/pfctl -s info | head -4"),
|
||||
("pf0", "/opt/pf/pfctl -e && /opt/pf/pfctl -s info | head -1"),
|
||||
("pf0", "cat /tmp/demo-pf.conf"),
|
||||
("pf0", "/opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'rules loaded' && /opt/pf/pfctl -sr"),
|
||||
("pf0", "/opt/pf/pfctl -sr -vv | head -8"),
|
||||
("cli", f"ping -c2 -W2 {SRV} | tail -3"),
|
||||
("pf0", "/opt/pf/pfctl -ss"),
|
||||
("pf0", "/opt/pf/pfctl -t trusted -T show"),
|
||||
("pf0", "/opt/pf/pfctl -s Tables"),
|
||||
("cli", "ping -c2 -W2 10.0.9.99 | tail -3"),
|
||||
("pf0", "/opt/pf/pfctl -sr -vv | head -6"),
|
||||
("pf0", "/opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'"),
|
||||
("pf0", "(setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert"),
|
||||
("cli", "ping -c2 -W2 10.0.1.1 | tail -3"),
|
||||
("pf0", "head -3 /tmp/pdivert.log"),
|
||||
("pf0", "pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'"),
|
||||
]
|
||||
|
||||
|
||||
def record(out_path, quick=False):
|
||||
os.makedirs(os.path.dirname(out_path) or ".", exist_ok=True)
|
||||
events = []
|
||||
t = 0.0
|
||||
|
||||
def emit(text, delay):
|
||||
nonlocal t
|
||||
t += delay
|
||||
events.append([round(t, 3), "o", text])
|
||||
|
||||
header = {
|
||||
"version": 2, "width": 100, "height": 26,
|
||||
"timestamp": int(time.time()),
|
||||
"title": "PF on Linux — OpenBSD PF engine inside the Linux kernel (lab demo)",
|
||||
"env": {"SHELL": "/bin/sh", "TERM": "xterm-256color"},
|
||||
}
|
||||
runners = {
|
||||
"pf0": lambda c: on_pf0(c),
|
||||
"cli": lambda c: on_vm(CLI, c),
|
||||
"srv": lambda c: on_vm(SRV, c),
|
||||
"local": lambda c: sh(c),
|
||||
}
|
||||
labels = {"pf0": "pftest-pf0", "cli": "pftest-cli", "srv": "pftest-srv",
|
||||
"local": "lab-host"}
|
||||
|
||||
stage()
|
||||
with open(out_path, "w") as f:
|
||||
f.write(json.dumps(header) + "\n")
|
||||
for kind, cmd in SCENARIO:
|
||||
emit(f"\x1b[1;36m{labels[kind]}\x1b[0m:\x1b[1;37m {cmd}\x1b[0m\r\n",
|
||||
0.35)
|
||||
try:
|
||||
out = runners[kind](cmd)
|
||||
except subprocess.TimeoutExpired:
|
||||
out = "[timeout]\r\n"
|
||||
except Exception as e: # noqa: BLE001
|
||||
out = f"[error: {e}]\r\n"
|
||||
out = out.replace("\r\n", "\n").replace("\n", "\r\n")
|
||||
emit(out or "(no output)\r\n", min(1.4, 0.3 + len(out) / 5000.0))
|
||||
with open(out_path, "a") as f:
|
||||
for ev in events:
|
||||
f.write(json.dumps(ev) + "\n")
|
||||
print(f"WROTE {out_path}: {len(events)} events, {t:.1f}s")
|
||||
print("play: asciinema play " + out_path)
|
||||
print("upload: asciinema upload " + out_path)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
ap = argparse.ArgumentParser()
|
||||
ap.add_argument("--out", default=os.path.join(REPO, "out",
|
||||
"demo-pf-linux.cast"))
|
||||
ap.add_argument("--quick", action="store_true")
|
||||
a = ap.parse_args()
|
||||
record(a.out, a.quick)
|
||||
Executable
+182
@@ -0,0 +1,182 @@
|
||||
#!/usr/bin/env bash
|
||||
# Demo session for PF-on-Linux: a scripted terminal tour of the lab.
|
||||
# Recorded with: asciinema rec out/demo-pf-linux.cast -c "bash scripts/demo-session.sh"
|
||||
#
|
||||
# Everything printed is the REAL output of the lab (Alpine VMs under libvirt
|
||||
# running the kernel built from source with our pf.ko). The VM management
|
||||
# addresses are resolved from the hypervisor (they are DHCP), the lab
|
||||
# topology (10.0.1.0/24, 10.0.2.0/24, ...) is fixed.
|
||||
set -u
|
||||
|
||||
DEB=${DEB:-root@192.168.1.242}
|
||||
CLI_IP=${CLI_IP:-10.0.1.10}
|
||||
SRV_IP=${SRV_IP:-10.0.2.20}
|
||||
KEY=${KEY:-$HOME/.ssh/pflab_ed}
|
||||
|
||||
bold() { printf '\033[1m%s\033[0m\n' "$*"; }
|
||||
cyan() { printf '\033[1;36m%s\033[0m\n' "$*"; }
|
||||
|
||||
# management address of a lab VM (DHCP, so ask the hypervisor)
|
||||
mgmt() {
|
||||
ssh -o ConnectTimeout=8 "$DEB" "virsh domifaddr $1 | awk '/vnet/{print \$4}' | cut -d/ -f1" \
|
||||
2>/dev/null | tr -d '\r' | head -1
|
||||
}
|
||||
|
||||
PF0_MGMT=$(mgmt pftest-pf0)
|
||||
CLI_MGMT=$(mgmt pftest-cli)
|
||||
[ -n "$PF0_MGMT" ] || PF0_MGMT=192.168.122.8
|
||||
[ -n "$CLI_MGMT" ] || CLI_MGMT=192.168.122.80
|
||||
|
||||
# run a command on a lab VM (through the hypervisor)
|
||||
onvm() {
|
||||
local ip=$1; shift
|
||||
ssh -o ConnectTimeout=10 -o StrictHostKeyChecking=accept-new \
|
||||
-o ProxyJump=root@192.168.1.242 -i "$KEY" root@"$ip" "$@" 2>&1
|
||||
}
|
||||
|
||||
p0() {
|
||||
cyan "pftest-pf0# $*"
|
||||
onvm "$PF0_MGMT" "$@"
|
||||
sleep 0.4
|
||||
}
|
||||
vmc() {
|
||||
cyan "pftest-cli# $*"
|
||||
onvm "$CLI_MGMT" "$@"
|
||||
sleep 0.4
|
||||
}
|
||||
|
||||
|
||||
CONF=/tmp/demo-pf.conf
|
||||
DIV=/tmp/demo-divert.conf
|
||||
|
||||
cat > "$CONF" <<'CONF'
|
||||
# PF-on-Linux demo ruleset (pf.conf syntax, real OpenBSD pfctl)
|
||||
set block-policy return
|
||||
table <trusted> { 10.0.1.0/24 }
|
||||
|
||||
# transit traffic: stateful, table-driven
|
||||
pass in quick on ingress proto icmp from <trusted> keep state
|
||||
pass out quick on egress proto icmp keep state
|
||||
|
||||
# deny a specific destination
|
||||
block drop in quick proto icmp to 10.0.9.99
|
||||
|
||||
# everything else
|
||||
pass in quick
|
||||
pass out quick
|
||||
CONF
|
||||
|
||||
cat > "$DIV" <<CONF
|
||||
pass in quick proto icmp from $CLI_IP to 10.0.1.1 divert-to "10.0.1.1" port 10000 keep state
|
||||
pass out quick
|
||||
CONF
|
||||
|
||||
# the pf0 interface towards the server (used by the NAT pool)
|
||||
EGRESS_IF=$(onvm "$PF0_MGMT" "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2" | tr -d '\r')
|
||||
[ -n "$EGRESS_IF" ] || EGRESS_IF=eth2
|
||||
|
||||
scp -q -o ProxyJump=root@192.168.1.242 -i "$KEY" "$CONF" "$DIV" \
|
||||
tools/out/pdivert tools/out/pflogd "root@$PF0_MGMT:/tmp/" 2>/dev/null
|
||||
|
||||
bold "==============================================================="
|
||||
bold " PF on Linux - the OpenBSD PF 8.0 engine inside the Linux kernel"
|
||||
bold "==============================================================="
|
||||
echo
|
||||
echo "Lab: 3 Alpine VMs under libvirt."
|
||||
echo " pftest-pf0 = firewall (kernel 7.3.4 built from source + pf.ko)"
|
||||
echo " pftest-cli = client 10.0.1.10 pftest-srv = server 10.0.2.20"
|
||||
echo
|
||||
|
||||
bold "--- 1. our kernel, the OpenBSD engine as a module ---"
|
||||
p0 "uname -r"
|
||||
p0 "lsmod | grep '^pf ' || echo 'pf: not loaded yet'"
|
||||
p0 "insmod /opt/pf/pf.ko && dmesg | tail -3"
|
||||
echo
|
||||
|
||||
bold "--- 2. pfctl talks to the module over the OpenBSD ioctl ABI ---"
|
||||
p0 "/opt/pf/pfctl -s info | head -4"
|
||||
p0 "/opt/pf/pfctl -e && /opt/pf/pfctl -s info | head -1"
|
||||
echo
|
||||
|
||||
bold "--- 3. a real pf.conf: tables, stateful rules, an explicit drop ---"
|
||||
p0 "cat /tmp/demo-pf.conf"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'rules loaded'"
|
||||
p0 "/opt/pf/pfctl -sr"
|
||||
echo
|
||||
|
||||
bold "--- 4. transit traffic is allowed and stateful ---"
|
||||
vmc "ping -c2 -W2 $SRV_IP | tail -3"
|
||||
p0 "/opt/pf/pfctl -ss | grep -E 'icmp' | head -4"
|
||||
echo
|
||||
|
||||
bold "--- 5. tables are live objects ---"
|
||||
p0 "/opt/pf/pfctl -t trusted -T show"
|
||||
p0 "/opt/pf/pfctl -s Tables"
|
||||
echo
|
||||
|
||||
bold "--- 6. the drop rule actually drops ---"
|
||||
p0 "cat > /tmp/demo-block.conf <<EOF
|
||||
block drop in quick proto icmp to $SRV_IP
|
||||
pass in quick
|
||||
pass out quick
|
||||
EOF"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-block.conf && echo 'block rules loaded'"
|
||||
vmc "ping -c2 -W2 $SRV_IP | tail -3"
|
||||
p0 "/opt/pf/pfctl -sr -vv | head -6"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'"
|
||||
echo
|
||||
|
||||
bold "--- 7. NAT: the source is translated on the way out, restored on the way back ---"
|
||||
p0 "cat > /tmp/demo-nat.conf <<EOF
|
||||
pass out quick on egress from 10.0.1.0/24 to any nat-to ($EGRESS_IF)
|
||||
pass in quick on ingress proto icmp keep state
|
||||
pass out quick on egress proto icmp keep state
|
||||
EOF"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-nat.conf && echo 'nat rules loaded'"
|
||||
vmc "ping -c2 -W2 $SRV_IP | tail -3"
|
||||
p0 "/opt/pf/pfctl -ss | grep -E 'icmp' | head -4"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-pf.conf && echo 'back to the stateful ruleset'"
|
||||
echo
|
||||
|
||||
bold "--- 8. pflog: logged packets reach userspace (/dev/pflog) ---"
|
||||
p0 "cat > /tmp/demo-log.conf <<EOF
|
||||
pass in quick log proto icmp from $CLI_IP keep state
|
||||
pass out quick
|
||||
EOF"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-log.conf && echo 'log rule loaded'"
|
||||
p0 "chmod +x /tmp/pflogd; rm -f /tmp/pflog.pcap; (setsid /tmp/pflogd -c 2 /tmp/pflog.pcap >/tmp/pflogd.log 2>&1 </dev/null &); sleep 1; echo 'pflogd collecting 2 records'"
|
||||
vmc "ping -c2 -W2 $SRV_IP | tail -2"
|
||||
sleep 2
|
||||
p0 "cat /tmp/pflogd.log; ls -l /tmp/pflog.pcap; echo 'pcap header (magic d4c3b2a1, linktype 0x75=DLT_PFLOG):'; od -An -tx1 -N24 /tmp/pflog.pcap"
|
||||
p0 "pkill pflogd 2>/dev/null; /opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null"
|
||||
echo
|
||||
|
||||
bold "--- 9. route-to: force the next hop away from the normal path ---"
|
||||
p0 "cat > /tmp/demo-route.conf <<EOF
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { 10.0.3.2 } keep state
|
||||
pass out quick
|
||||
EOF"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-route.conf && echo 'route-to rule loaded'"
|
||||
p0 "(tcpdump -ni eth3 -c 2 -e icmp > /tmp/route.td 2>&1 &); (tcpdump -ni eth2 -c 2 -e icmp > /tmp/norm.td 2>&1 &); sleep 1"
|
||||
vmc "ping -c1 -W2 $SRV_IP | tail -2"
|
||||
sleep 2
|
||||
p0 "echo 'forced egress (eth3, toward the gateway):'; grep -v '^tcpdump\|^listening\|^$' /tmp/route.td | head -2; echo 'normal egress (eth2):'; grep -c 'echo request' /tmp/norm.td"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-pf.conf >/dev/null"
|
||||
echo
|
||||
|
||||
bold "--- 10. divert-to: the packet goes to userspace and comes back ---"
|
||||
p0 "cat /tmp/demo-divert.conf"
|
||||
p0 "/opt/pf/pfctl -f /tmp/demo-divert.conf && echo 'divert rule loaded'"
|
||||
p0 "chmod +x /tmp/pdivert; (setsid /tmp/pdivert -p 10000 -f >/tmp/pdivert.log 2>&1 </dev/null &); sleep 1; pgrep pdivert"
|
||||
vmc "ping -c2 -W2 10.0.1.1 | tail -3"
|
||||
p0 "head -3 /tmp/pdivert.log"
|
||||
echo " (pdivert flipped the last payload byte and fixed the ICMP checksum)"
|
||||
echo
|
||||
|
||||
bold "--- 11. shutdown ---"
|
||||
p0 "pkill pdivert; /opt/pf/pfctl -f /dev/null; /opt/pf/pfctl -d; echo 'pf disabled'"
|
||||
p0 "lsmod | grep '^pf '"
|
||||
echo
|
||||
bold "demo over - port, gates and docs:"
|
||||
bold " https://git.labexposed.com/lgcosta/pf-linux-port"
|
||||
echo
|
||||
+28
-6
@@ -17,20 +17,42 @@ reset_pf0() {
|
||||
return 1
|
||||
}
|
||||
deploy() {
|
||||
scp -q -o ProxyJump=root@192.168.1.242 -o StrictHostKeyChecking=accept-new \
|
||||
-i "$HOME/.ssh/pflab_ed" "$REPO/module/pf.ko" \
|
||||
"$REPO/tools/out/pfctl" "$REPO/tests/confs/"*.conf pf0:/tmp/ 2>/dev/null || \
|
||||
ssh "$DEB" "mkdir -p /opt/pf"
|
||||
# The scp through the libvirt jump host is occasionally refused; a silent
|
||||
# failure used to leave the previous gate's module/pfctl in place, which
|
||||
# showed up as a bogus gate failure. Retry and verify the copy.
|
||||
local i
|
||||
for i in 1 2 3; do
|
||||
local extra=()
|
||||
[ -x "$REPO/tools/out/pdivert" ] && extra+=("$REPO/tools/out/pdivert")
|
||||
[ -x "$REPO/tools/out/pflogd" ] && extra+=("$REPO/tools/out/pflogd")
|
||||
if scp -q -o ProxyJump=root@192.168.1.242 -o StrictHostKeyChecking=accept-new \
|
||||
-i "$HOME/.ssh/pflab_ed" "$REPO/module/pf.ko" \
|
||||
"$REPO/tools/out/pfctl" "${extra[@]}" "$REPO/tests/confs/"*.conf pf0:/tmp/ 2>/dev/null; then
|
||||
break
|
||||
fi
|
||||
sleep 2
|
||||
done
|
||||
# stage onto pf0 /opt/pf via mgmt alias already copied to /tmp
|
||||
ssh "$DEB" "$SSH 'mkdir -p /opt/pf; mv /tmp/pf.ko /tmp/pfctl /opt/pf/ 2>/dev/null; true'" >/dev/null
|
||||
ssh "$DEB" "$SSH 'mkdir -p /opt/pf; mv /tmp/pf.ko /tmp/pfctl /tmp/pdivert /tmp/pflogd /opt/pf/ 2>/dev/null; chmod +x /opt/pf/pfctl /opt/pf/pdivert /opt/pf/pflogd 2>/dev/null; true'" >/dev/null
|
||||
ssh "$DEB" "$SSH 'test -s /opt/pf/pf.ko && test -x /opt/pf/pfctl'" >/dev/null 2>&1 || {
|
||||
echo "deploy: pf.ko/pfctl missing on pf0"; return 1; }
|
||||
}
|
||||
PUSH=0 FAIL=0
|
||||
# Never leave pf0 with pf enabled when the runner exits (a failed gate
|
||||
# would otherwise keep filtering the lab traffic).
|
||||
pf_disable_pf0() {
|
||||
ssh -o ConnectTimeout=8 "$DEB" "$SSH '/opt/pf/pfctl -d >/dev/null 2>&1; true'" \
|
||||
>/dev/null 2>&1 || true
|
||||
}
|
||||
trap pf_disable_pf0 EXIT INT TERM
|
||||
ONLY="${1:-}"
|
||||
for t in "$REPO"/tests/vm/[0-9]*.sh; do
|
||||
[ -n "$ONLY" ] && case "$t" in *"$ONLY"*) ;; *) continue ;; esac
|
||||
[ -e "$t" ] || continue
|
||||
name="$(basename "$t")"
|
||||
echo "=== $name ==="
|
||||
reset_pf0 || { echo "FAIL $name (vm reset)"; FAIL=$((FAIL+1)); continue; }
|
||||
deploy
|
||||
deploy || { echo "FAIL $name (deploy)"; FAIL=$((FAIL+1)); continue; }
|
||||
if bash "$t" >"$LOGD/$name.log" 2>&1; then
|
||||
echo "PASS $name"; PUSH=$((PUSH+1))
|
||||
else
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env bash
|
||||
# M2 gate 1: stateful transit + state visibility
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
pfensure
|
||||
pf0 'insmod /tmp/pf.ko 2>/dev/null || insmod /opt/pf/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null; echo READY' | grep -q READY || { bad load; finish; }
|
||||
cat > /tmp/g1.conf <<'C'
|
||||
pass in quick proto icmp keep state
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env bash
|
||||
# M2 gate 2: block drop + block return-rst
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
pfensure; pf0 '/opt/pf/pfctl -e' >/dev/null
|
||||
pf0 'insmod /tmp/pf.ko 2>/dev/null || insmod /opt/pf/pf.ko; true'; pf0 '/opt/pf/pfctl -e' >/dev/null
|
||||
cat > /tmp/g2a.conf <<'C'
|
||||
block drop in quick proto icmp from any to any
|
||||
pass out quick
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
#!/usr/bin/env bash
|
||||
# M2 gate 3: pfr tables via pfctl -t
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
pfensure; pf0 '/opt/pf/pfctl -e' >/dev/null
|
||||
pf0 'insmod /tmp/pf.ko 2>/dev/null || insmod /opt/pf/pf.ko; true'; pf0 '/opt/pf/pfctl -e' >/dev/null
|
||||
cat > /tmp/g3.conf <<'C'
|
||||
table <blk> { 10.0.1.10 }
|
||||
block in quick proto icmp from <blk> to any
|
||||
|
||||
+43
-12
@@ -1,19 +1,50 @@
|
||||
#!/usr/bin/env bash
|
||||
# M2 gate 4: anchors + quick precedence
|
||||
# M2 gate 4: anchors + evaluation order (OpenBSD semantics)
|
||||
#
|
||||
# OpenBSD evaluates the IN ruleset in ip_input() for every arriving packet and
|
||||
# the OUT ruleset in ip_forward() for forwarded packets. A `block in ... icmp`
|
||||
# rule therefore also sees the *reply* of a transit flow - a state created by
|
||||
# an anchor rule does NOT rescue the reply at input time. This gate keeps the
|
||||
# ruleset OpenBSD-correct and isolates the anchor semantics:
|
||||
#
|
||||
# anchor "restricted" -> child: pass in quick ... from <client> keep state
|
||||
# block drop in quick proto icmp from any to <server> (would drop the request)
|
||||
# pass in quick / pass out quick
|
||||
#
|
||||
# The request must be passed by the ANCHOR child rule (the later block rule
|
||||
# would drop it), and a state must exist. After flushing the anchor the very
|
||||
# same request must be dropped - proving the anchor is what allowed it.
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
pfensure; pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
cat > /tmp/g4main.conf <<'C'
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
cat > /tmp/g4main.conf <<C
|
||||
anchor "restricted"
|
||||
block drop in quick proto icmp from any to any
|
||||
block drop in quick proto icmp from any to $SRV_IP
|
||||
pass in quick
|
||||
pass out quick
|
||||
C
|
||||
pfload /tmp/g4main.conf || { bad mainload; finish; }
|
||||
cat > /tmp/g4anc.conf <<'C'
|
||||
pass in quick proto icmp from 10.0.1.10 to any
|
||||
cat > /tmp/g4anc.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to any keep state
|
||||
C
|
||||
r=$(pfput /tmp/g4anc.conf); pf0 "/opt/pf/pfctl -a restricted -f $r" || { bad anchorload; finish; }
|
||||
cli "ping -c1 -W2 $SRV_IP >/dev/null 2>&1" && ok "anchor pass evaluated before block" || bad "anchor pass not honored"
|
||||
# anchor rules are evaluated BEFORE the main-ruleset block line (top placement)
|
||||
pf0 '/opt/pf/pfctl -s Anchors' | grep -q restricted && ok "anchors listed" || bad "anchor list"
|
||||
pf0 '/opt/pf/pfctl -d; /opt/pf/pfctl -f /dev/null' >/dev/null; finish
|
||||
|
||||
pfload /tmp/g4main.conf || { bad "main ruleset load"; finish; }
|
||||
ANC=$(pfput /tmp/g4anc.conf) || { bad "anchor conf upload"; finish; }
|
||||
pf0 "/opt/pf/pfctl -a restricted -f $ANC" || { bad "anchor ruleset load"; finish; }
|
||||
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'anchor "restricted"' && ok "anchor rule in main ruleset" || bad "anchor rule missing"
|
||||
pf0 '/opt/pf/pfctl -a restricted -sr' | grep -q 'proto icmp from' && ok "anchor rules listed" || bad "anchor rules missing"
|
||||
|
||||
# the request must pass through the anchor (the block rule would drop it)
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1" && ok "anchor pass honoured (request allowed)" \
|
||||
|| bad "anchor pass not honored"
|
||||
pf0 '/opt/pf/pfctl -ss' | grep -q "$SRV_IP" && ok "state created by anchor rule" || bad "no state from anchor"
|
||||
|
||||
# without the anchor rule the request hits the block rule -> dropped
|
||||
pf0 "/opt/pf/pfctl -a restricted -F all" >/dev/null 2>&1
|
||||
cli "ping -c1 -W2 $SRV_IP >/dev/null 2>&1" && bad "request passed without anchor rule" \
|
||||
|| ok "request dropped without anchor rule (block applies)"
|
||||
|
||||
pf0 '/opt/pf/pfctl -d; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
finish
|
||||
Executable
+46
@@ -0,0 +1,46 @@
|
||||
#!/usr/bin/env bash
|
||||
# M3 gate: nat-to — source NAT of transit traffic to the egress address.
|
||||
#
|
||||
# OpenBSD 8.0 unified the old "nat on ..." rule into the rule syntax:
|
||||
# pass out on egress from <net> to any nat-to (egress)
|
||||
#
|
||||
# Expected: the reply path is unaffected, srv sees the packet with
|
||||
# src = pf0's egress address (not the client's), and pfctl shows the rule.
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
FAILED=0
|
||||
# pf calls the interface "egress"; the OS names it ethX - resolve both
|
||||
EGRESS_DEV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
EGRESS_IP=$(pf0 "ip -4 addr show $EGRESS_DEV | grep -o 'inet [0-9.]*' | head -1 | cut -d' ' -f2")
|
||||
[ -n "$EGRESS_IP" ] || EGRESS_IP=192.168.122.8
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
# OpenBSD expands "(egress)" (an interface *group*) into the addresses of all
|
||||
# its members - on a multi-NIC host that is ambiguous, so the gate uses the
|
||||
# concrete transit interface (the OpenBSD-recommended form for NAT pools).
|
||||
cat > /tmp/g05.conf <<C
|
||||
pass out quick on egress from 10.0.1.0/24 to any nat-to ($EGRESS_DEV)
|
||||
pass in quick on ingress proto icmp keep state
|
||||
pass out quick on egress proto icmp keep state
|
||||
C
|
||||
pfload /tmp/g05.conf || { bad "nat rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'nat-to' && ok "nat-to rule listed" || bad "nat-to not listed"
|
||||
|
||||
pf0 "tcpdump -ni $EGRESS_DEV -c 4 -e icmp > /tmp/nat.td 2>&1 &"
|
||||
sleep 1
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1" && ok "transit ping through NAT" || bad "transit ping"
|
||||
sleep 2
|
||||
|
||||
TD=$(pf0 'cat /tmp/nat.td')
|
||||
if echo "$TD" | grep -q "$CLI_IP"; then
|
||||
bad "client address $CLI_IP still visible on egress"
|
||||
else
|
||||
ok "source rewritten on egress (no $CLI_IP)"
|
||||
fi
|
||||
echo "$TD" | grep -q "$EGRESS_IP" && ok "egress source is $EGRESS_IP" || bad "egress source not seen"
|
||||
|
||||
pf0 '/opt/pf/pfctl -ss' | grep -q "$SRV_IP" && ok "state present" || bad "no state"
|
||||
pf0 '/opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+69
@@ -0,0 +1,69 @@
|
||||
#!/usr/bin/env bash
|
||||
# M3 gate: rdr-to — destination/port redirect.
|
||||
#
|
||||
# Lab: the client connects to the firewall's own address 10.0.1.1:8080; pf
|
||||
# redirects it to the server (10.0.2.20:80, busybox httpd). This exercises
|
||||
# the inbound translation *and* the re-route of a packet whose destination pf
|
||||
# rewrote (the packet is no longer local to the firewall).
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
# the runner only resets pf0 between gates - clear any responder a previous
|
||||
# run (or a manual session) left on the server, or it answers first and this
|
||||
# gate sees the wrong payload.
|
||||
srv 'pkill -f '[l]oop.sh' 2>/dev/null; pkill -f '[b]ig.sh' 2>/dev/null; pkill nc 2>/dev/null; true' >/dev/null
|
||||
sleep 1
|
||||
|
||||
# a tiny responder on srv:80 (base64-encoded so it survives the two ssh hops
|
||||
# without nested quoting problems; detached so ssh returns)
|
||||
LOOP=$(printf 'while :; do nc -l -p 80 < /tmp/resp.txt >/dev/null 2>&1; done\n' | base64 | tr -d '\n')
|
||||
# NOTE: never pkill -f a pattern that also appears in this very command line -
|
||||
# it kills the invoking shell. Use a pidfile and check the listening socket.
|
||||
srv "echo PF-RDR-OK > /tmp/resp.txt; echo $LOOP | base64 -d > /tmp/loop.sh; [ -f /tmp/loop.pid ] && kill \$(cat /tmp/loop.pid) 2>/dev/null; pkill nc 2>/dev/null; setsid sh /tmp/loop.sh >/dev/null 2>&1 </dev/null & echo \$! > /tmp/loop.pid; sleep 1; netstat -lnt 2>/dev/null | grep -q ':80 ' && echo RESPONDER_UP" | grep -q RESPONDER_UP && ok "responder up on srv:80" || bad "responder start"
|
||||
|
||||
cat > /tmp/g06.conf <<C
|
||||
pass in quick proto tcp from 10.0.1.0/24 to 10.0.1.1 port 8080 rdr-to $SRV_IP port 80 keep state
|
||||
pass out quick proto tcp keep state
|
||||
C
|
||||
pfload /tmp/g06.conf || { bad "rdr rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'rdr-to' && ok "rdr rule listed" || bad "rdr not listed"
|
||||
|
||||
# the client talks to the firewall's address; pf redirects to srv:80
|
||||
RESP=$(cli 'printf "GET / HTTP/1.0\r\n\r\n" | nc -w3 10.0.1.1 8080' 2>/dev/null)
|
||||
if echo "$RESP" | grep -q 'PF-RDR-OK'; then
|
||||
ok "redirect delivered the response"
|
||||
else
|
||||
bad "no redirected response"
|
||||
printf '%s\n' "$RESP" | head -4 | sed 's/^/ /'
|
||||
fi
|
||||
|
||||
# the state must show the translated tuple (server:80 with the original in parens)
|
||||
pf0 '/opt/pf/pfctl -ss' | grep -E "$SRV_IP:80 .*$CLI_IP" >/dev/null && ok "state shows the translation" || bad "no translated state"
|
||||
|
||||
# the reply path must survive the un-redirect
|
||||
pf0 '/opt/pf/pfctl -s info' | grep -qiE 'match' && ok "counters readable" || bad "counters"
|
||||
|
||||
srv '[ -f /tmp/loop.pid ] && kill $(cat /tmp/loop.pid) 2>/dev/null; pkill nc 2>/dev/null; true' >/dev/null
|
||||
|
||||
# bulk (GSO/TSO) through the redirect: 2 MB must arrive byte-identical.
|
||||
# This is the regression that "materialize the checksum in software" introduced:
|
||||
# computing the transport checksum once for a GSO skb corrupts every segment
|
||||
# after the first, and the peer silently stalls (sshd mute, transfers hang).
|
||||
B64=$(printf 'head -c 2000000 /dev/zero | tr "\0" A > /tmp/big.txt\n' | base64 | tr -d '\n')
|
||||
srv "echo $B64 | base64 -d > /tmp/mkbig.sh; sh /tmp/mkbig.sh; pkill nc 2>/dev/null; sleep 1; nohup setsid nc -l -p 9091 < /tmp/big.txt >/dev/null 2>&1 & sleep 1; netstat -lnt | grep -q 9091 && echo BULK_UP" | grep -q BULK_UP || bad "bulk listener"
|
||||
pf0 "printf 'pass in quick proto tcp from 10.0.1.0/24 to 10.0.1.1 port 9091 rdr-to $SRV_IP port 9091 keep state\npass out quick proto tcp keep state\n' > /tmp/g06b.conf; /opt/pf/pfctl -f /tmp/g06b.conf && echo BULK_RULE" >/dev/null
|
||||
GOT=$(cli 'nc -w10 10.0.1.1 9091 | wc -c' | tr -d '[:space:]')
|
||||
EXP=$(srv 'wc -c < /tmp/big.txt' | tr -d '[:space:]')
|
||||
if [ "$GOT" = "$EXP" ] && [ "${GOT:-0}" -ge 2000000 ]; then
|
||||
ok "2 MB through the redirect intact ($GOT bytes)"
|
||||
else
|
||||
bad "bulk through redirect: got $GOT want $EXP"
|
||||
fi
|
||||
# the firewall must still answer ssh (the GSO path must not wedge the box)
|
||||
pf0 'echo SSH_ALIVE' | grep -q SSH_ALIVE && ok "pf0 sshd still responsive" || bad "pf0 unreachable after bulk"
|
||||
srv 'pkill nc 2>/dev/null; true' >/dev/null
|
||||
|
||||
pf0 '/opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+48
@@ -0,0 +1,48 @@
|
||||
#!/usr/bin/env bash
|
||||
# M3 gate: binat-to — bidirectional (static 1:1) NAT.
|
||||
#
|
||||
# Lab: the server (10.0.2.20) pings the client (10.0.1.10) through pf0. The
|
||||
# binat rule rewrites the source to 10.0.2.50; the client's reply goes back to
|
||||
# 10.0.2.50, which pf0 owns in the mapping, and is translated to the server.
|
||||
#
|
||||
# Proves: outbound source rewrite + inbound destination rewrite with one rule,
|
||||
# and that the reply survives the state/translation path.
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
BINAT=10.0.2.50
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
cat > /tmp/g07.conf <<C
|
||||
pass quick proto icmp from $SRV_IP to $CLI_IP binat-to $BINAT keep state
|
||||
pass in quick proto icmp keep state
|
||||
pass out quick proto icmp keep state
|
||||
C
|
||||
pfload /tmp/g07.conf || { bad "binat rule load"; finish; }
|
||||
# pfctl expands one binat-to rule into the documented pair:
|
||||
# pass out ... nat-to <mapped> static-port (outbound half)
|
||||
# pass in ... rdr-to <real> (inbound half)
|
||||
RULES=$(pf0 '/opt/pf/pfctl -sr')
|
||||
echo "$RULES" | grep -q "nat-to $BINAT static-port" && ok "binat outbound half installed" || bad "outbound half missing"
|
||||
echo "$RULES" | grep -q "rdr-to $SRV_IP" && ok "binat inbound half installed" || bad "inbound half missing"
|
||||
|
||||
# capture on the client side (resolve its transit interface, like pf0's)
|
||||
CLI_DEV=$(cli "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
[ -n "$CLI_DEV" ] || CLI_DEV=eth1
|
||||
cli "(tcpdump -ni $CLI_DEV -c 4 -e icmp > /tmp/bi.td 2>&1 &)" 2>/dev/null
|
||||
sleep 1
|
||||
srv "ping -c2 -W2 $CLI_IP >/dev/null 2>&1" && ok "ping srv->cli through binat" || bad "binat round trip"
|
||||
sleep 2
|
||||
|
||||
TD=$(cli 'cat /tmp/bi.td' 2>/dev/null)
|
||||
if echo "$TD" | grep -q "$BINAT"; then
|
||||
ok "request arrived from the mapped address $BINAT"
|
||||
else
|
||||
bad "mapped address not seen on the client: $(echo "$TD" | head -2)"
|
||||
fi
|
||||
echo "$TD" | grep -q "$SRV_IP" && bad "original address $SRV_IP leaked" || ok "original source not leaked"
|
||||
|
||||
pf0 '/opt/pf/pfctl -ss' | grep -q "$BINAT" && ok "state shows the mapping" || bad "no binat state"
|
||||
pf0 '/opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+67
@@ -0,0 +1,67 @@
|
||||
#!/usr/bin/env bash
|
||||
# M4 gate: route-to / dup-to — forced forwarding path (pf_route).
|
||||
#
|
||||
# The lab's host bridge filters *forwarded* frames that cross two libvirt
|
||||
# networks with a foreign source address, so the proof is taken on the
|
||||
# firewall itself: which of pf0's egress interfaces the packet leaves from.
|
||||
#
|
||||
# route-to { gw2 } -> packet leaves via eth3 (toward gw2), NOT via eth2
|
||||
# dup-to { gw2 } -> packet leaves via eth2 (normal path) AND a copy on eth3
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
# resolve pf0's interfaces by address (names are stable, but be safe)
|
||||
IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
IF_GW=$(pf0 "ip route get $GW2_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
[ -n "$IF_SRV" ] && [ -n "$IF_GW" ] || { bad "interface resolution"; finish; }
|
||||
[ "$IF_SRV" != "$IF_GW" ] || { bad "transit and gateway share an interface"; finish; }
|
||||
ok "normal egress=$IF_SRV forced egress=$IF_GW"
|
||||
|
||||
|
||||
# count matching lines on pf0, robust against a missing/empty capture file
|
||||
# (grep exits 1 on zero matches, and the ssh wrapper hides stderr)
|
||||
cnt() {
|
||||
local f=$1 pat=$2 n
|
||||
n=$(pf0 "grep -c -- '$pat' $f 2>/dev/null; true" | tr -dc '0-9')
|
||||
[ -n "$n" ] || n=0
|
||||
printf '%s' "$n"
|
||||
}
|
||||
|
||||
# capture both egresses at once
|
||||
start_captures() {
|
||||
pf0 "pkill tcpdump; (tcpdump -ni $IF_SRV -c 6 -e icmp > /tmp/srv.td 2>&1 &); (tcpdump -ni $IF_GW -c 6 -e icmp > /tmp/gw.td 2>&1 &); sleep 1" >/dev/null
|
||||
}
|
||||
|
||||
cat > /tmp/g08a.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW2_IP } keep state
|
||||
pass out quick proto icmp keep state
|
||||
C
|
||||
pfload /tmp/g08a.conf || { bad "route-to rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'route-to' && ok "route-to rule listed" || bad "route-to not listed"
|
||||
start_captures
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
|
||||
sleep 2
|
||||
# count only echo *requests* from the client (a reply also contains its address)
|
||||
N=$(cnt /tmp/gw.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "route-to: packet left via $IF_GW ($N)" \
|
||||
|| bad "route-to: nothing on $IF_GW"
|
||||
N=$(cnt /tmp/srv.td "$CLI_IP > $SRV_IP"); [ "$N" -eq 0 ] && ok "route-to: normal egress $IF_SRV not used" \
|
||||
|| bad "route-to: $N requests also left via $IF_SRV"
|
||||
|
||||
cat > /tmp/g08b.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP dup-to { $GW2_IP } keep state
|
||||
pass out quick proto icmp keep state
|
||||
C
|
||||
pfload /tmp/g08b.conf || { bad "dup-to rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'dup-to' && ok "dup-to rule listed" || bad "dup-to not listed"
|
||||
start_captures
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
|
||||
sleep 2
|
||||
N=$(cnt /tmp/srv.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "dup-to: original path kept ($N on $IF_SRV)" \
|
||||
|| bad "dup-to: original path lost"
|
||||
N=$(cnt /tmp/gw.td "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "dup-to: duplicate sent to $IF_GW ($N)" \
|
||||
|| bad "dup-to: no duplicate"
|
||||
|
||||
pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+54
@@ -0,0 +1,54 @@
|
||||
#!/usr/bin/env bash
|
||||
# M3 gate: scrub - normalization actually rewrites packets.
|
||||
#
|
||||
# 8.0 syntax: scrub is a rule option ("match in all scrub (...)"), not a
|
||||
# standalone rule. Proof is taken on pf0's own egress (the lab's host bridge
|
||||
# filters forwarded frames between networks, so peer-side captures are not
|
||||
# reliable):
|
||||
# min-ttl 100 -> a transit packet with ttl 64 leaves with ttl 100
|
||||
# max-mss 500 -> a TCP SYN with MSS 1460 leaves advertising MSS 500
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
[ -n "$IF_SRV" ] || IF_SRV=eth2
|
||||
|
||||
cat > /tmp/g09.conf <<C
|
||||
set reassemble yes
|
||||
match in all scrub (min-ttl 100 max-mss 500)
|
||||
pass in quick proto icmp from $CLI_IP keep state
|
||||
pass in quick proto tcp from $CLI_IP to $SRV_IP port 9092 keep state
|
||||
pass out quick keep state
|
||||
C
|
||||
pfload /tmp/g09.conf || { bad "scrub rules load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'scrub' && ok "scrub rule listed" || bad "scrub not listed"
|
||||
|
||||
# --- min-ttl on a transit ICMP packet ---
|
||||
# OpenBSD raises the TTL to min-ttl in pf, then ip_forward() decrements it for
|
||||
# the hop, so the egress packet shows min-ttl-1 (100 -> 99).
|
||||
pf0 "pkill tcpdump; (tcpdump -ni $IF_SRV -c 3 -vv icmp > /tmp/scr1.td 2>&1 &); sleep 1"
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
|
||||
sleep 2
|
||||
N=$(pf0 "grep -c 'ttl 99' /tmp/scr1.td 2>/dev/null; true" | tr -dc '0-9')
|
||||
if [ "${N:-0}" -gt 0 ]; then
|
||||
ok "min-ttl applied (ttl raised to 100, forwarded as 99)"
|
||||
else
|
||||
DIAG=$(pf0 "grep -o 'ttl [0-9]*' /tmp/scr1.td 2>/dev/null | head -2" | tr '\n' ' ')
|
||||
bad "min-ttl not applied: $DIAG"
|
||||
fi
|
||||
|
||||
# --- max-mss on a TCP SYN ---
|
||||
pf0 "(tcpdump -ni $IF_SRV -c 3 -vv tcp port 9092 > /tmp/scr2.td 2>&1 &); sleep 1"
|
||||
cli "nc -w1 -z $SRV_IP 9092 >/dev/null 2>&1"
|
||||
sleep 2
|
||||
if pf0 "grep -q 'mss 500' /tmp/scr2.td" 2>/dev/null; then
|
||||
ok "max-mss clamped to 500"
|
||||
else
|
||||
DIAG=$(pf0 "grep -o 'mss [0-9]*' /tmp/scr2.td 2>/dev/null | head -2" | tr '\n' ' ')
|
||||
bad "mss not clamped: $DIAG"
|
||||
fi
|
||||
|
||||
pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+68
@@ -0,0 +1,68 @@
|
||||
#!/usr/bin/env bash
|
||||
# M4 gate: route-to pools - round-robin vs source-hash (pf_lb).
|
||||
#
|
||||
# Two gateways live on two different firewall links:
|
||||
# 10.0.3.2 via $IF_GW (gw2's 10.0.3 side)
|
||||
# 10.0.2.2 via $IF_SRV (gw2's 10.0.2 side)
|
||||
# Each ping is a separate flow (own state), so the pool choice is made per
|
||||
# flow: round-robin must spread the flows over both links, source-hash must
|
||||
# keep them on one (same source address -> same bucket).
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
GW1=$GW2_IP # 10.0.3.2
|
||||
GW2=10.0.2.2
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
IF_GW=$(pf0 "ip route get $GW1 | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
[ -n "$IF_GW" ] && [ -n "$IF_SRV" ] || { bad "interface resolution"; finish; }
|
||||
[ "$IF_GW" != "$IF_SRV" ] || { bad "the two gateways share a link"; finish; }
|
||||
ok "pool links: $IF_GW ($GW1) and $IF_SRV ($GW2)"
|
||||
|
||||
count_on() { # count echo requests captured on an interface
|
||||
local n
|
||||
n=$(pf0 "grep -c '$CLI_IP > $SRV_IP' /tmp/pool_$1.td 2>/dev/null; true" | tr -dc '0-9')
|
||||
[ -n "$n" ] || n=0
|
||||
printf '%s' "$n"
|
||||
}
|
||||
|
||||
run_flows() { # $1 = ruleset file, four separate ICMP flows
|
||||
pf0 "pkill tcpdump; (tcpdump -ni $IF_GW -c 8 -e icmp > /tmp/pool_gw.td 2>&1 &); (tcpdump -ni $IF_SRV -c 8 -e icmp > /tmp/pool_srv.td 2>&1 &); sleep 1" >/dev/null
|
||||
cli "for i in 1 2 3 4; do ping -c1 -W2 $SRV_IP >/dev/null 2>&1; done"
|
||||
sleep 2
|
||||
}
|
||||
|
||||
# --- round-robin: the flows must spread over both links ---
|
||||
cat > /tmp/g10a.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW1, $GW2 } round-robin keep state
|
||||
pass out quick keep state
|
||||
C
|
||||
pfload /tmp/g10a.conf || { bad "rr rule load"; finish; }
|
||||
run_flows
|
||||
A=$(count_on gw); B=$(count_on srv)
|
||||
# Captures are lossy under busybox tcpdump, so the assertions are about
|
||||
# *which links are used*, not how many packets arrived.
|
||||
if [ "$A" -gt 0 ] && [ "$B" -gt 0 ]; then
|
||||
ok "round-robin used both links ($A on $IF_GW, $B on $IF_SRV)"
|
||||
else
|
||||
bad "round-robin did not spread ($A on $IF_GW, $B on $IF_SRV)"
|
||||
fi
|
||||
|
||||
# --- source-hash: the same source sticks to one gateway ---
|
||||
cat > /tmp/g10b.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP route-to { $GW1, $GW2 } source-hash keep state
|
||||
pass out quick keep state
|
||||
C
|
||||
pfload /tmp/g10b.conf || { bad "source-hash rule load"; finish; }
|
||||
run_flows
|
||||
A=$(count_on gw); B=$(count_on srv)
|
||||
if [ "$((A + B))" -ge 1 ] && { [ "$A" -eq 0 ] || [ "$B" -eq 0 ]; }; then
|
||||
ok "source-hash pinned the flows to one link ($A on $IF_GW, $B on $IF_SRV)"
|
||||
else
|
||||
bad "source-hash spread the flows ($A on $IF_GW, $B on $IF_SRV)"
|
||||
fi
|
||||
|
||||
pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+35
@@ -0,0 +1,35 @@
|
||||
#!/usr/bin/env bash
|
||||
# M4 gate: divert — AF_DIVERT family end-to-end with packet-level proof.
|
||||
#
|
||||
# Scenario (lab):
|
||||
# rule: pass in quick proto icmp from cli to pf0-lan divert-to "<pf0-lan>" port 10000 keep state
|
||||
# (a) no listener on the divert port -> ping cli->pf0 FAILS (BSD parity: divs_noport)
|
||||
# (b) pdivert -f running -> ping SUCCEEDS and pdivert rewrites the
|
||||
# payload (last byte flipped), proving the packet went to userspace and back.
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
PORT=10000
|
||||
PFLAN=10.0.1.1
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
pf0 'pkill pdivert 2>/dev/null; true'
|
||||
|
||||
cat > /tmp/g11.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $PFLAN divert-to "$PFLAN" port $PORT keep state
|
||||
pass out quick
|
||||
C
|
||||
pfload /tmp/g11.conf || { bad "divert rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'divert-to' && ok "divert rule loaded" || bad "divert rule missing"
|
||||
|
||||
# (a) no listener -> BSD drops (divs_noport)
|
||||
cli "ping -c1 -W2 $PFLAN >/dev/null 2>&1" && bad "passed without divert listener" || ok "drop without divert listener"
|
||||
|
||||
# (b) listener present -> passes through userspace
|
||||
PDIV=$(pfput ../../tools/out/pdivert) || bad "pdivert deploy"
|
||||
pf0 "chmod +x $PDIV; (setsid $PDIV -p $PORT -f > /tmp/pdiv.log 2>&1 < /dev/null &); sleep 1"
|
||||
pf0 "pgrep pdivert >/dev/null && echo RUNNING" | grep -q RUNNING && ok "pdivert listening" || bad "pdivert start"
|
||||
cli "ping -c2 -W2 $PFLAN >/dev/null 2>&1" && ok "ping passes through divert" || bad "ping with listener"
|
||||
pf0 'cat /tmp/pdiv.log' | grep -qi 'divert' && ok "pdivert received packet" || bad "pdivert saw nothing"
|
||||
pf0 'pkill pdivert; /opt/pf/pfctl -d' >/dev/null 2>&1
|
||||
finish
|
||||
Executable
+48
@@ -0,0 +1,48 @@
|
||||
#!/usr/bin/env bash
|
||||
# M4 gate: pflog — logged packets must reach userspace.
|
||||
#
|
||||
# pflogd reads /dev/pflog (the port's chardev backend) and writes a pcap with
|
||||
# linktype DLT_PFLOG (117). A `log` rule + ICMP traffic must produce records
|
||||
# that contain the real packet bytes (checked by searching the client address
|
||||
# in the capture) and a valid pcap header.
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
pf0 'pkill -f "[p]flogd" 2>/dev/null; rm -f /tmp/pflog.pcap; true'
|
||||
|
||||
LOGD=$(pfput ../../tools/out/pflogd) || { bad "pflogd deploy"; finish; }
|
||||
pf0 "test -c /dev/pflog && echo DEV_OK" | grep -q DEV_OK || { bad "/dev/pflog missing"; finish; }
|
||||
pf0 "chmod +x $LOGD; (setsid $LOGD -c 4 -f /dev/pflog /tmp/pflog.pcap >/tmp/pflogd.log 2>&1 </dev/null &); sleep 1; pgrep pflogd >/dev/null && echo DAEMON_UP" \
|
||||
| grep -q DAEMON_UP || { bad "pflogd start"; finish; }
|
||||
|
||||
cat > /tmp/g12.conf <<C
|
||||
pass in quick log proto icmp from $CLI_IP keep state
|
||||
pass out quick proto icmp keep state
|
||||
C
|
||||
pfload /tmp/g12.conf || { bad "log rule load"; finish; }
|
||||
|
||||
cli "ping -c3 -W2 $SRV_IP >/dev/null 2>&1"
|
||||
sleep 2
|
||||
|
||||
# pcap header: magic d4c3b2a1 (LE) and network = 117 at offset 20
|
||||
HDR=$(pf0 "od -An -tx1 -N24 /tmp/pflog.pcap 2>/dev/null | tr -d '[[:space:]]'")
|
||||
if [ "${HDR:0:8}" = "d4c3b2a1" ]; then ok "pcap magic ok"; else bad "pcap header: $HDR"; fi
|
||||
if [ "${HDR:40:4}" = "7500" ] || [ "${HDR:40:8}" = "75000000" ]; then
|
||||
ok "linktype DLT_PFLOG (117)"
|
||||
else
|
||||
bad "linktype: ${HDR:40:8}"
|
||||
fi
|
||||
|
||||
SZ=$(pf0 'wc -c < /tmp/pflog.pcap' | tr -d '[:space:]')
|
||||
if [ "${SZ:-0}" -gt 24 ]; then ok "records captured ($SZ bytes)"; else bad "no records ($SZ)"; fi
|
||||
|
||||
# the client address must appear inside a captured packet
|
||||
if pf0 "od -An -tx1 /tmp/pflog.pcap | tr -d '[[:space:]]' | grep -q 0a00010a"; then
|
||||
ok "captured payload contains $CLI_IP"
|
||||
else
|
||||
bad "client address not in capture"
|
||||
fi
|
||||
|
||||
pf0 'pkill pflogd 2>/dev/null; /opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+52
@@ -0,0 +1,52 @@
|
||||
#!/usr/bin/env bash
|
||||
# M4 gate: reply-to - force the next hop of the *reply* direction.
|
||||
#
|
||||
# reply-to is the asymmetric-routing tool: a flow whose request arrives on one
|
||||
# link can have its answer pushed out through a different gateway. Proof is
|
||||
# taken on pf0's own interfaces (the lab's host bridge filters forwarded frames
|
||||
# that cross networks, so the peer side is not observable):
|
||||
#
|
||||
# request cli -> srv leaves via $IF_SRV (normal path, untouched)
|
||||
# reply srv -> cli leaves via $IF_GW (forced by reply-to), not $IF_CLI
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
|
||||
IF_SRV=$(pf0 "ip route get $SRV_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
IF_GW=$(pf0 "ip route get $GW2_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
IF_CLI=$(pf0 "ip route get $CLI_IP | grep -o 'dev [a-z0-9]*' | cut -d' ' -f2")
|
||||
[ -n "$IF_SRV" ] && [ -n "$IF_GW" ] && [ -n "$IF_CLI" ] || { bad "interface resolution"; finish; }
|
||||
[ "$IF_GW" != "$IF_CLI" ] || { bad "gateway and client share a link"; finish; }
|
||||
ok "reply would normally leave via $IF_CLI, forced via $IF_GW"
|
||||
|
||||
cat > /tmp/g13.conf <<C
|
||||
pass in quick proto icmp from $CLI_IP to $SRV_IP reply-to { $GW2_IP } keep state
|
||||
pass out quick keep state
|
||||
C
|
||||
pfload /tmp/g13.conf || { bad "reply-to rule load"; finish; }
|
||||
pf0 '/opt/pf/pfctl -sr' | grep -q 'reply-to' && ok "reply-to rule listed" || bad "reply-to not listed"
|
||||
|
||||
pf0 "pkill tcpdump; (tcpdump -ni $IF_GW -c 8 -e icmp > /tmp/rt_gw.td 2>&1 &); (tcpdump -ni $IF_CLI -c 8 -e icmp > /tmp/rt_cli.td 2>&1 &); (tcpdump -ni $IF_SRV -c 8 -e icmp > /tmp/rt_srv.td 2>&1 &); sleep 1" >/dev/null
|
||||
cli "ping -c2 -W2 $SRV_IP >/dev/null 2>&1"
|
||||
sleep 2
|
||||
|
||||
cnt() {
|
||||
local n
|
||||
n=$(pf0 "grep -c -- '$2' /tmp/rt_$1.td 2>/dev/null; true" | tr -dc '0-9')
|
||||
[ -n "$n" ] || n=0
|
||||
printf '%s' "$n"
|
||||
}
|
||||
|
||||
# the request path must be unchanged
|
||||
N=$(cnt srv "$CLI_IP > $SRV_IP"); [ "$N" -gt 0 ] && ok "request left via $IF_SRV ($N)" \
|
||||
|| bad "request did not leave via $IF_SRV"
|
||||
|
||||
# the reply must be forced to the gateway link
|
||||
N=$(cnt gw "$SRV_IP > $CLI_IP"); [ "$N" -gt 0 ] && ok "reply forced onto $IF_GW ($N)" \
|
||||
|| bad "reply not seen on $IF_GW"
|
||||
N=$(cnt cli "$SRV_IP > $CLI_IP"); [ "$N" -eq 0 ] && ok "reply did not use $IF_CLI" \
|
||||
|| bad "reply still left via $IF_CLI ($N)"
|
||||
|
||||
pf0 'pkill tcpdump; /opt/pf/pfctl -d' >/dev/null
|
||||
finish
|
||||
Executable
+51
@@ -0,0 +1,51 @@
|
||||
#!/usr/bin/env bash
|
||||
# M6 gate: soak + unload/leak discipline.
|
||||
#
|
||||
# 1) load pf with a stateful ruleset, drive mixed traffic for ~20s
|
||||
# 2) assert no BUG/WARNING/Oops in dmesg
|
||||
# 3) disable + rmmod: the module must unload cleanly (no refcount leak)
|
||||
# 4) insmod/rmmod cycles: slab objects for the pf caches must return to the
|
||||
# pre-load baseline (no leak) and a reload must work
|
||||
set -uo pipefail; cd "$(dirname "$0")"; . ./lib.sh
|
||||
|
||||
HELPER=$(pfput ./soak-helper.sh) || { bad "helper upload"; finish; }
|
||||
pf0 "chmod +x $HELPER" >/dev/null
|
||||
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true'
|
||||
pf0 '/opt/pf/pfctl -e; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
BEFORE=$(pf0 "$HELPER slab")
|
||||
|
||||
cat > /tmp/g14.conf <<C
|
||||
table <peers> { $CLI_IP }
|
||||
pass in quick on ingress proto icmp from <peers> keep state
|
||||
pass out quick on egress proto icmp keep state
|
||||
pass out quick proto tcp from any to any port 22 keep state
|
||||
C
|
||||
pfload /tmp/g14.conf || { bad "soak ruleset"; finish; }
|
||||
|
||||
# mixed traffic: ICMP + TCP handshakes for ~20s
|
||||
cli "ping -q -c 40 -i 0.5 $SRV_IP >/dev/null 2>&1" 2>/dev/null
|
||||
cli "for i in 1 2 3 4 5; do nc -w1 -z $SRV_IP 22; done" 2>/dev/null
|
||||
|
||||
ST=$(pf0 "$HELPER states")
|
||||
[ "${ST:-0}" -ge 1 ] && ok "states under load ($ST)" || bad "no states under load"
|
||||
|
||||
ANOM=$(pf0 "$HELPER dmesg")
|
||||
if [ -z "$ANOM" ]; then
|
||||
ok "no kernel BUG/WARN/Oops"
|
||||
else
|
||||
bad "dmesg anomalies:"
|
||||
printf '%s\n' "$ANOM" | sed 's/^/ /'
|
||||
fi
|
||||
|
||||
pf0 '/opt/pf/pfctl -d; /opt/pf/pfctl -f /dev/null' >/dev/null
|
||||
pf0 'rmmod pf && echo UNLOAD_OK' | grep -q UNLOAD_OK && ok "clean unload (refcounts released)" || bad "rmmod failed"
|
||||
sleep 1
|
||||
pf0 'insmod /opt/pf/pf.ko 2>/dev/null || insmod /tmp/pf.ko; true; (/opt/pf/pfctl -s info >/dev/null && echo RELOAD_OK)' \
|
||||
| grep -q RELOAD_OK && ok "reload after unload" || bad "reload failed"
|
||||
pf0 'rmmod pf && echo UNLOAD_OK2' | grep -q UNLOAD_OK2 && ok "second unload" || bad "second rmmod"
|
||||
sleep 1
|
||||
AFTER=$(pf0 "$HELPER slab")
|
||||
LEAK=$(join <(echo "$BEFORE") <(echo "$AFTER") 2>/dev/null | awk '$3-$2 > 0 {print $1, $3-$2}')
|
||||
if [ -n "$LEAK" ]; then bad "slab growth after cycles: $LEAK"; else ok "no slab growth after unload cycles"; fi
|
||||
finish
|
||||
Loaded 100 of 107 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user