ldls: a network, in a process
docs/plan/ldls.md L3a -- the class bridge, and the first of the three pieces
L3 turned out to be.
/dev/netdev is /dev/pci with the arrows reversed. That hands a device to a
process; this lets a process be one. The kernel side is netdev_ops and nothing
else -- transmit, receive, mac, link_up, the same four entries e1000
publishes -- so a process claims the device, supplies a MAC, and from then on
read() gives it frames the stack wants sent and write() hands it frames that
arrived.
cmd/netecho proves it and is deliberately not a driver: no hardware, none
claimed, every frame answered by the program itself. DHCP so the interface
gets an address at all, ARP so the stack can find it, ICMP so it can be
pinged. All built by hand from RFCs 826, 791, 792 and 2131.
# netecho &
netuser: ldls0 is a process now, 2:4c:44:4c:53:1
netecho: I am 10.9.0.1 and will offer 10.9.0.2
netecho: answered DHCP, offering an address
# cat /proc/netif
interface ldls0 driver netuser address 10.9.0.2 gateway 10.9.0.1
# ping 10.9.0.1 3
netecho: answered an ARP
netecho: answered a ping
3 packets transmitted, 3 received, 0% packet loss
The interface got its address by DHCP from a process and then answered ping
from one. lwIP never learns that the thing behind netdev_ops is not a driver,
which is the whole property the bridge exists to have.
It dies the way it should, too. kill the process and link_up() answers false
immediately, so the stack refuses to send -- "ping: sendto: -5" -- rather than
swallowing packets into a driver that is not there. Start another and the
*same* interface comes back, keeping its address. That came free:
netuser_release_all() sits beside pciuser_release_all() in exit() for exactly
the same reason, and the reason is that a process holding a device is one that
may crash.
One thing the kernel needed: netinit() starts DHCP on the devices that exist
when it runs, so an interface created later -- which is how an LDLS-hosted
driver arrives -- would have come up with no address and no way to get one.
net_attach_late() fixes that, and lives in kernel/net/net.c because that is
the only file allowed to include lwIP's headers.
Recorded as not done, because it is not: this proves the bridge, not a driver.
Nothing in that test loads a module. That is why it was done first -- if ping
had not worked here the bridge would be wrong, and now a failure with a real
driver can only be the driver's side. L3b is the SchOS-side host, L3c is the
fifteen symbols for real, and L3 is the two joined.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VQ7Qx8E1q1M1bbCq8QLHS2
This commit is contained in:
Nexoniarz
parent
2d9a0ec6e3
commit
2a441af3c6
14 changed files with 953 additions and 5 deletions
|
|
@ -221,6 +221,7 @@ kmain(uint32 fb_addr)
|
|||
// sinit: kthread_create needs a usable process table. From here on Ctrl-G
|
||||
// on the console answers, with no filesystem mounted and nothing in
|
||||
// userspace started -- which is the whole point of putting it this early.
|
||||
netuser_init();
|
||||
dbg_thread_start();
|
||||
if (boot_verbose) cprintf("verbose boot: dbg thread started\n");
|
||||
mpmain();
|
||||
|
|
|
|||
|
|
@ -121,4 +121,8 @@ struct devsw devsw[] = {
|
|||
// /dev/dbg (major 10) -- ask the kernel a question. Write a line, read the
|
||||
// answer; see include/dbg.h and docs/plan/debugger.md.
|
||||
[10] = { dbg_read, dbg_write },
|
||||
// /dev/netdev (major 11) -- a process, being a network interface. The
|
||||
// reverse of major 9: that hands a device to a process, this lets a process
|
||||
// be one. See include/netuser.h.
|
||||
[11] = { netuser_read, netuser_write, netuser_ready },
|
||||
};
|
||||
|
|
|
|||
414
kernel/dev/netuser.c
Normal file
414
kernel/dev/netuser.c
Normal file
|
|
@ -0,0 +1,414 @@
|
|||
// SPDX-License-Identifier: Apache-2.0
|
||||
//
|
||||
// /dev/netdev -- a network interface whose backend is a process.
|
||||
// See include/netuser.h.
|
||||
//
|
||||
// The shape is `/dev/pci`'s, deliberately, and for the same reasons. One
|
||||
// device, one owner, claimed and released, and the kernel takes it back when
|
||||
// the process dies -- because the process it is handed to is by assumption one
|
||||
// that may crash, which is the entire argument for it being a process.
|
||||
//
|
||||
// What is different is the direction. `/dev/pci` hands a device *to* a
|
||||
// process; this lets a process *be* a device. The kernel is the consumer here
|
||||
// and the process is the driver, so the queues run the other way and the
|
||||
// vtable is ours rather than theirs.
|
||||
|
||||
#include "types.h"
|
||||
#include "defs.h"
|
||||
#include "param.h"
|
||||
#include "spinlock.h"
|
||||
#include "sleeplock.h"
|
||||
#include "fs.h"
|
||||
#include "file.h"
|
||||
#include "errno.h"
|
||||
#include "memlayout.h"
|
||||
#include "mmu.h"
|
||||
#include "proc.h"
|
||||
#include "uaccess.h"
|
||||
#include "device.h"
|
||||
#include "netdev.h"
|
||||
#include "sbuf.h"
|
||||
#include "dbg.h"
|
||||
#include "netuser.h"
|
||||
|
||||
struct frame {
|
||||
int len;
|
||||
uint8 data[NETUSER_MTU];
|
||||
};
|
||||
|
||||
// Two rings. `tx` is what the stack has handed down and the process has not
|
||||
// yet read; `rx` is what the process has written and the stack has not yet
|
||||
// polled. Both are single-producer/single-consumer in practice -- one process
|
||||
// on one side, the network thread on the other -- but the lock is taken
|
||||
// anyway, because "in practice" is not a property the scheduler guarantees.
|
||||
static struct {
|
||||
struct spinlock lock;
|
||||
int inited;
|
||||
|
||||
struct proc *owner;
|
||||
struct device *dev;
|
||||
uint8 mac[6];
|
||||
|
||||
struct frame tx[NETUSER_QLEN];
|
||||
uint tx_head, tx_tail; // monotonic, indexed mod QLEN
|
||||
|
||||
struct frame rx[NETUSER_QLEN];
|
||||
uint rx_head, rx_tail;
|
||||
|
||||
struct netuser_stat st;
|
||||
} nu;
|
||||
|
||||
static void
|
||||
netuser_once(void)
|
||||
{
|
||||
if (!nu.inited) {
|
||||
initlock(&nu.lock, "netuser");
|
||||
nu.inited = 1;
|
||||
}
|
||||
}
|
||||
|
||||
// --- the vtable the kernel sees ---------------------------------------------
|
||||
|
||||
// Queue a frame for the process to read.
|
||||
//
|
||||
// Returns -1 when the ring is full, which netdev.h defines as congestion
|
||||
// rather than failure -- the caller is expected to come back. That matters
|
||||
// here more than it does for real hardware: the "wire" is a process that may
|
||||
// not have been scheduled yet, and treating a full ring as an error would drop
|
||||
// packets every time the machine was busy.
|
||||
static int
|
||||
netuser_transmit(struct device *d, const void *frame, int len)
|
||||
{
|
||||
int rv = 0;
|
||||
|
||||
(void)d;
|
||||
if (len <= 0 || len > NETUSER_MTU)
|
||||
return -1;
|
||||
|
||||
acquire(&nu.lock);
|
||||
if (!nu.owner) {
|
||||
release(&nu.lock);
|
||||
return -1;
|
||||
}
|
||||
if (nu.tx_head - nu.tx_tail >= NETUSER_QLEN) {
|
||||
nu.st.tx_dropped++;
|
||||
rv = -1;
|
||||
} else {
|
||||
struct frame *f = &nu.tx[nu.tx_head % NETUSER_QLEN];
|
||||
memmove(f->data, frame, len);
|
||||
f->len = len;
|
||||
nu.tx_head++;
|
||||
nu.st.tx_frames++;
|
||||
nu.st.tx_bytes += len;
|
||||
}
|
||||
release(&nu.lock);
|
||||
|
||||
if (rv == 0)
|
||||
wakeup(&nu.tx_head);
|
||||
return rv;
|
||||
}
|
||||
|
||||
// Take a frame the process wrote, if there is one. Never blocks: net_eth_poll
|
||||
// calls this in a loop and decides for itself when to stop.
|
||||
static int
|
||||
netuser_receive(struct device *d, void *out, int cap)
|
||||
{
|
||||
int len = 0;
|
||||
|
||||
(void)d;
|
||||
acquire(&nu.lock);
|
||||
if (nu.rx_head != nu.rx_tail) {
|
||||
struct frame *f = &nu.rx[nu.rx_tail % NETUSER_QLEN];
|
||||
len = f->len;
|
||||
if (len > cap)
|
||||
len = cap;
|
||||
memmove(out, f->data, len);
|
||||
nu.rx_tail++;
|
||||
}
|
||||
release(&nu.lock);
|
||||
return len;
|
||||
}
|
||||
|
||||
static const unsigned char *
|
||||
netuser_mac(struct device *d)
|
||||
{
|
||||
(void)d;
|
||||
return nu.mac;
|
||||
}
|
||||
|
||||
// Up exactly while somebody is holding the descriptor.
|
||||
//
|
||||
// This is the honest answer and it is also the useful one: a link that stays
|
||||
// up after its driver died is a link that swallows every packet sent to it.
|
||||
static int
|
||||
netuser_link_up(struct device *d)
|
||||
{
|
||||
(void)d;
|
||||
return nu.owner != 0;
|
||||
}
|
||||
|
||||
static const struct netdev_ops netuser_ops = {
|
||||
.transmit = netuser_transmit,
|
||||
.receive = netuser_receive,
|
||||
.mac = netuser_mac,
|
||||
.link_up = netuser_link_up,
|
||||
};
|
||||
|
||||
// --- claiming and releasing --------------------------------------------------
|
||||
|
||||
static void
|
||||
netuser_drop(void)
|
||||
{
|
||||
// The device stays registered. Removing it would mean unpicking it from
|
||||
// lwIP's interface list, which nothing in that stack supports -- and leaving
|
||||
// it with link_up() answering false is the same thing from the stack's point
|
||||
// of view, without inventing a teardown path nobody else has.
|
||||
nu.owner = 0;
|
||||
nu.tx_head = nu.tx_tail = 0;
|
||||
nu.rx_head = nu.rx_tail = 0;
|
||||
nu.st.attached = 0;
|
||||
}
|
||||
|
||||
static int
|
||||
do_create(uint64 argp)
|
||||
{
|
||||
struct netuser_create c;
|
||||
struct device *d;
|
||||
int first = 0;
|
||||
|
||||
if (copy_from_user(&c, argp, sizeof(c)) < 0)
|
||||
return -EFAULT;
|
||||
|
||||
netuser_once();
|
||||
acquire(&nu.lock);
|
||||
if (nu.owner) {
|
||||
release(&nu.lock);
|
||||
return -EBUSY; // one interface, one process
|
||||
}
|
||||
nu.owner = myproc();
|
||||
for (int i = 0; i < 6; i++)
|
||||
nu.mac[i] = c.mac[i];
|
||||
nu.tx_head = nu.tx_tail = 0;
|
||||
nu.rx_head = nu.rx_tail = 0;
|
||||
nu.st.attached = 1;
|
||||
d = nu.dev;
|
||||
release(&nu.lock);
|
||||
|
||||
// Registered once and reused. A process that comes back after crashing gets
|
||||
// the same interface rather than a second one, which is what makes restart
|
||||
// invisible to anything above -- the same property H2 built for the GPU.
|
||||
if (!d) {
|
||||
c.name[sizeof(c.name) - 1] = 0;
|
||||
d = device_add(c.name[0] ? c.name : "eth", DEVBUS_PLATFORM, DEVCLASS_NET,
|
||||
"netuser");
|
||||
if (!d) {
|
||||
acquire(&nu.lock);
|
||||
netuser_drop();
|
||||
release(&nu.lock);
|
||||
return -ENOSPC;
|
||||
}
|
||||
device_set_desc(d, "a process, acting as a network interface");
|
||||
d->ops = (void *)&netuser_ops;
|
||||
d->priv = 0;
|
||||
nu.dev = d;
|
||||
first = 1;
|
||||
}
|
||||
|
||||
if (first) {
|
||||
// Hand it to the stack. net_attach_late() adds it to lwIP's interface list
|
||||
// *and* starts DHCP on it, which netinit()'s boot-time walk cannot do for
|
||||
// something that did not exist yet -- an interface that only appears once
|
||||
// a program has started would otherwise come up with no address and no way
|
||||
// to ever get one.
|
||||
if (net_attach_late(d) < 0) {
|
||||
cprintf("netuser: the network stack would not take the interface\n");
|
||||
acquire(&nu.lock);
|
||||
netuser_drop();
|
||||
release(&nu.lock);
|
||||
return -ENOSPC;
|
||||
}
|
||||
cprintf("netuser: %s is a process now, %x:%x:%x:%x:%x:%x\n", d->name,
|
||||
nu.mac[0], nu.mac[1], nu.mac[2], nu.mac[3], nu.mac[4], nu.mac[5]);
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int
|
||||
do_release(void)
|
||||
{
|
||||
netuser_once();
|
||||
acquire(&nu.lock);
|
||||
if (nu.owner == myproc())
|
||||
netuser_drop();
|
||||
release(&nu.lock);
|
||||
wakeup(&nu.tx_head);
|
||||
return 0;
|
||||
}
|
||||
|
||||
// Called from exit(), beside pciuser_release_all(), and for the same reason: a
|
||||
// driver that crashed must not leave an interface that claims to be up.
|
||||
void
|
||||
netuser_release_all(struct proc *p)
|
||||
{
|
||||
netuser_once();
|
||||
acquire(&nu.lock);
|
||||
if (nu.owner == p)
|
||||
netuser_drop();
|
||||
release(&nu.lock);
|
||||
wakeup(&nu.tx_head);
|
||||
}
|
||||
|
||||
int
|
||||
netuser_ioctl(uint64 request, uint64 argp)
|
||||
{
|
||||
switch (request) {
|
||||
case NETUSERIOC_CREATE: return do_create(argp);
|
||||
case NETUSERIOC_RELEASE: return do_release();
|
||||
case NETUSERIOC_STAT: {
|
||||
struct netuser_stat s;
|
||||
netuser_once();
|
||||
acquire(&nu.lock);
|
||||
s = nu.st;
|
||||
release(&nu.lock);
|
||||
if (copy_to_user(argp, &s, sizeof(s)) < 0)
|
||||
return -EFAULT;
|
||||
return 0;
|
||||
}
|
||||
default:
|
||||
return -ENOTTY;
|
||||
}
|
||||
}
|
||||
|
||||
// --- the descriptor ----------------------------------------------------------
|
||||
|
||||
// A frame the stack wants sent. Blocks until there is one.
|
||||
int
|
||||
netuser_read(struct inode *ip, uint64 off, char *dst, int n)
|
||||
{
|
||||
struct frame *f;
|
||||
int len;
|
||||
|
||||
(void)off;
|
||||
netuser_once();
|
||||
|
||||
if (nu.owner != myproc())
|
||||
return -EACCES;
|
||||
|
||||
iunlock(ip);
|
||||
acquire(&nu.lock);
|
||||
while (nu.tx_head == nu.tx_tail) {
|
||||
if (myproc()->killed || nu.owner != myproc()) {
|
||||
release(&nu.lock);
|
||||
ilock(ip);
|
||||
return -1;
|
||||
}
|
||||
sleep(&nu.tx_head, &nu.lock);
|
||||
}
|
||||
f = &nu.tx[nu.tx_tail % NETUSER_QLEN];
|
||||
len = f->len;
|
||||
if (len > n)
|
||||
len = n;
|
||||
memmove(dst, f->data, len);
|
||||
nu.tx_tail++;
|
||||
release(&nu.lock);
|
||||
ilock(ip);
|
||||
return len;
|
||||
}
|
||||
|
||||
// A frame that arrived. Handed to the stack at its next poll.
|
||||
int
|
||||
netuser_write(struct inode *ip, uint64 off, char *src, int n)
|
||||
{
|
||||
(void)ip; (void)off;
|
||||
netuser_once();
|
||||
|
||||
if (nu.owner != myproc())
|
||||
return -EACCES;
|
||||
if (n <= 0 || n > NETUSER_MTU)
|
||||
return -EINVAL;
|
||||
|
||||
acquire(&nu.lock);
|
||||
if (nu.rx_head - nu.rx_tail >= NETUSER_QLEN) {
|
||||
// Dropped, and counted. The alternative is blocking the driver until the
|
||||
// stack catches up, which on a receive path means the driver stops reading
|
||||
// its hardware and the hardware drops it instead -- the same packet lost,
|
||||
// further from anything that can say so.
|
||||
nu.st.rx_dropped++;
|
||||
release(&nu.lock);
|
||||
return n;
|
||||
}
|
||||
{
|
||||
struct frame *f = &nu.rx[nu.rx_head % NETUSER_QLEN];
|
||||
memmove(f->data, src, n);
|
||||
f->len = n;
|
||||
nu.rx_head++;
|
||||
nu.st.rx_frames++;
|
||||
nu.st.rx_bytes += n;
|
||||
}
|
||||
release(&nu.lock);
|
||||
return n;
|
||||
}
|
||||
|
||||
// Whether a read would return without blocking, so O_NONBLOCK and poll() work
|
||||
// without the driver growing a flags argument. See struct devsw.
|
||||
int
|
||||
netuser_ready(struct inode *ip)
|
||||
{
|
||||
int r;
|
||||
(void)ip;
|
||||
netuser_once();
|
||||
acquire(&nu.lock);
|
||||
r = (nu.tx_head != nu.tx_tail);
|
||||
release(&nu.lock);
|
||||
return r;
|
||||
}
|
||||
|
||||
// --- what the debugger can be told -------------------------------------------
|
||||
|
||||
static void
|
||||
netuser_dump(struct sbuf *out, const char *arg)
|
||||
{
|
||||
(void)arg;
|
||||
netuser_once();
|
||||
|
||||
acquire(&nu.lock);
|
||||
if (!nu.dev) {
|
||||
sb_puts(out, " (no process has ever claimed /dev/netdev)\n");
|
||||
release(&nu.lock);
|
||||
return;
|
||||
}
|
||||
sb_puts(out, " interface ");
|
||||
sb_puts(out, nu.dev->name);
|
||||
sb_puts(out, nu.owner ? " up, held by pid " : " DOWN, nobody holds it");
|
||||
if (nu.owner)
|
||||
sb_putu(out, nu.owner->pid);
|
||||
sb_putc(out, '\n');
|
||||
|
||||
sb_puts(out, " mac ");
|
||||
for (int i = 0; i < 6; i++) {
|
||||
sb_puthex(out, nu.mac[i], 2);
|
||||
if (i < 5) sb_putc(out, ':');
|
||||
}
|
||||
sb_putc(out, '\n');
|
||||
|
||||
sb_puts(out, "\n tx "); sb_putu(out, nu.st.tx_frames);
|
||||
sb_puts(out, " frames, "); sb_putu(out, nu.st.tx_bytes);
|
||||
sb_puts(out, " bytes, "); sb_putu(out, nu.st.tx_dropped);
|
||||
sb_puts(out, " dropped, "); sb_putu(out, nu.tx_head - nu.tx_tail);
|
||||
sb_puts(out, " waiting to be read\n");
|
||||
|
||||
sb_puts(out, " rx "); sb_putu(out, nu.st.rx_frames);
|
||||
sb_puts(out, " frames, "); sb_putu(out, nu.st.rx_bytes);
|
||||
sb_puts(out, " bytes, "); sb_putu(out, nu.st.rx_dropped);
|
||||
sb_puts(out, " dropped, "); sb_putu(out, nu.rx_head - nu.rx_tail);
|
||||
sb_puts(out, " waiting for the stack\n");
|
||||
release(&nu.lock);
|
||||
}
|
||||
|
||||
void
|
||||
netuser_init(void)
|
||||
{
|
||||
netuser_once();
|
||||
dbg_register("netuser", netuser_dump,
|
||||
"the interface backed by a process, and what has moved");
|
||||
}
|
||||
|
|
@ -89,6 +89,7 @@ static const struct devnode devnodes[] = {
|
|||
{ "fb0", 2, 0, D_ROOT },
|
||||
{ "pci", 9, 0, D_ROOT },
|
||||
{ "dbg", 10, 0, D_ROOT },
|
||||
{ "netdev", 11, 0, D_ROOT },
|
||||
{ "mouse", 3, 1, D_ROOT },
|
||||
|
||||
// Raw disks. Created whether or not a drive is present: opening one with no
|
||||
|
|
|
|||
|
|
@ -177,6 +177,37 @@ htonl_u32(uint v)
|
|||
return ntohl_u32(v);
|
||||
}
|
||||
|
||||
// Attach an interface that appeared after boot.
|
||||
//
|
||||
// netinit() walks the devices that exist when it runs and starts DHCP on each.
|
||||
// An interface created later -- by a process claiming /dev/netdev, which is
|
||||
// how an LDLS-hosted driver arrives -- misses that entirely, and would come up
|
||||
// with no address and no way to ever get one.
|
||||
//
|
||||
// It lives here rather than in kernel/dev/netuser.c because this is the only
|
||||
// file allowed to include lwIP's headers; reaching into the stack from a
|
||||
// device driver would put them on every kernel file's include path. See the
|
||||
// note on /proc/netif in kernel/dev/procfs.c, which is the same rule.
|
||||
int
|
||||
net_attach_late(struct device *d)
|
||||
{
|
||||
int idx;
|
||||
|
||||
if (!net_ready)
|
||||
return -1; // netinit() has not run; it will pick this up
|
||||
|
||||
lwip_sys_lock();
|
||||
idx = net_eth_attach(d);
|
||||
if (idx >= 0)
|
||||
dhcp_start(net_eth_netif(idx));
|
||||
lwip_sys_unlock();
|
||||
|
||||
if (idx >= 0)
|
||||
cprintf("net: %s attached as interface %d, asking for an address\n",
|
||||
d->name, idx);
|
||||
return idx;
|
||||
}
|
||||
|
||||
static void
|
||||
net_thread(void)
|
||||
{
|
||||
|
|
|
|||
|
|
@ -577,6 +577,9 @@ exit(int status)
|
|||
// not keep its hardware locked away from the process that replaces it --
|
||||
// that is the entire point of running drivers outside the kernel.
|
||||
pciuser_release_all(myproc());
|
||||
// And any interface it was acting as. Same reason: a driver that crashed
|
||||
// must not leave a link that claims to be up. See kernel/dev/netuser.c.
|
||||
netuser_release_all(myproc());
|
||||
|
||||
myproc()->xstate = status;
|
||||
|
||||
|
|
|
|||
|
|
@ -18,6 +18,7 @@
|
|||
#include "gfx.h" /* gfx_cols/gfx_rows — TIOCGWINSZ reports them */
|
||||
#include "vt.h" /* the terminals TIOC*/VT_* act on */
|
||||
#include "pciuser.h"
|
||||
#include "netuser.h"
|
||||
|
||||
// -----------------------------------------------------------------------
|
||||
// Linux-ABI-compatible struct stat (x86_64 "struct stat" from
|
||||
|
|
@ -1035,6 +1036,8 @@ addr_t sys_ioctl(void)
|
|||
return input_ioctl(f->ip, (int)request, argp);
|
||||
if (is_dev && f->ip->major == PCIUSER_MAJOR)
|
||||
return pciuser_ioctl(request, argp);
|
||||
if (is_dev && f->ip->major == NETUSER_MAJOR)
|
||||
return netuser_ioctl(request, argp);
|
||||
|
||||
int is_tty = (is_dev && f->ip->major == 1);
|
||||
if (!is_tty) {
|
||||
|
|
|
|||
Loading…
Reference in a new issue