SchOS/kernel/net/lwip/netif_eth.c

// SPDX-License-Identifier: Apache-2.0
//
// lwIP network interfaces over the netdev class.
//
// The seam, and it is deliberately driver-agnostic: everything about IP, ARP
// and TCP lives in lwIP, everything about descriptors and registers lives in a
// driver, and this file knows only that a network device can transmit a frame,
// receive a frame and state its MAC address. It was `netif_e1000.c` and called
// `e1000_transmit` directly, which meant the second NIC driver would have
// arrived with a second near-identical copy of this file. See include/netdev.h.
//
// One netif per bound interface, up to NETIF_MAX. Two NICs is an ordinary
// machine -- a laptop with Ethernet and the virtual one QEMU adds is already
// two -- and the limit exists only because a fixed array is simpler than
// allocation for something enumerated once at boot.

#include "types.h"
#include "defs.h"
#include "param.h"
#include "device.h"
#include "netdev.h"

#include "lwip/opt.h"
#include "lwip/netif.h"
#include "lwip/pbuf.h"
#include "lwip/etharp.h"
#include "lwip/ethip6.h"
#include "netif/ethernet.h"

#define ETH_MTU     1500
#define ETH_FRAMESZ 1518        // 1500 payload + 14 header + 4 FCS allowance

struct eth_if {
    struct netif   netif;
    struct device *dev;
    // Frames in and out, for /proc/netif. Counted at this seam rather than in
    // the driver on purpose: a frame the driver received and this file dropped
    // never reached the stack, and a counter one layer down would say it did.
    uint64 rx_frames, tx_frames;
    int    used;
};

static struct eth_if ifs[NETIF_MAX];
static int           nifs;

// One staging buffer each, not one per call: a frame is 1518 bytes and the
// kernel stack is 4096 in total, so a local of this size on a path that is
// several frames deep is exactly the overflow the kstack canary exists to
// catch. Safe as a single static because every caller holds the lwIP lock --
// which is also why one pair serves every interface.
static char txframe[ETH_FRAMESZ];
static char rxframe[ETH_FRAMESZ];

// Send one packet. lwIP hands over a pbuf chain; a driver wants one flat
// buffer, so this walks the chain into txframe.
static err_t
eth_linkoutput(struct netif *netif, struct pbuf *p)
{
    struct eth_if *e = netif->state;

    if (p->tot_len > sizeof(txframe))
        return ERR_IF;

    u16_t off = 0;
    for (struct pbuf *q = p; q != NULL; q = q->next) {
        if (off + q->len > sizeof(txframe))
            return ERR_IF;
        memmove(txframe + off, q->payload, q->len);
        off += q->len;
    }

    // A full transmit ring is congestion, not failure. Reporting ERR_IF would
    // make lwIP drop the segment and wait for a retransmission timer;
    // ERR_WOULDBLOCK lets it try again, which for TCP is the difference between
    // a stall of milliseconds and one of seconds.
    if (netdev_transmit(e->dev, txframe, off) != 0)
        return ERR_WOULDBLOCK;

    e->tx_frames++;
    return ERR_OK;
}

// Bring one interface up. Called by netif_add, once per device.
static err_t
eth_netif_init(struct netif *netif)
{
    struct eth_if *e = netif->state;
    const unsigned char *mac = netdev_mac(e->dev);

    netif->name[0] = 'e';
    netif->name[1] = 'n';
    netif->output     = etharp_output;   // IP -> ARP -> linkoutput
    netif->linkoutput = eth_linkoutput;
    netif->mtu        = ETH_MTU;
    netif->hwaddr_len = 6;
    for (int i = 0; i < 6; i++)
        netif->hwaddr[i] = mac ? mac[i] : 0;
    netif->flags = NETIF_FLAG_BROADCAST | NETIF_FLAG_ETHARP | NETIF_FLAG_LINK_UP;
    return ERR_OK;
}

// Attach one network device. Returns its interface index, or -1.
//
// No address: DHCP fills that in, and an interface that came up with a
// hardcoded one would be wrong on every network but the one it was written on.
int
net_eth_attach(struct device *dev)
{
    ip4_addr_t any;

    if (nifs >= NETIF_MAX || dev == 0)
        return -1;

    struct eth_if *e = &ifs[nifs];
    e->dev  = dev;
    e->used = 1;

    IP4_ADDR(&any, 0, 0, 0, 0);
    if (netif_add(&e->netif, &any, &any, &any, e,
                  eth_netif_init, netif_input) == NULL) {
        e->used = 0;
        return -1;
    }

    // The first one is the default route. With one interface that is the only
    // possible answer; with two it is a policy decision that belongs to a
    // routing table this kernel does not have yet, and picking the first is at
    // least a rule rather than an accident of enumeration order.
    if (nifs == 0)
        netif_set_default(&e->netif);

    netif_set_up(&e->netif);
    if (netdev_link_up(dev))
        netif_set_link_up(&e->netif);
    else
        netif_set_link_down(&e->netif);

    return nifs++;
}

// An interface whose device has gone away.
//
// The missing half of net_eth_attach, and it went missing because nothing had
// ever taken a device back. /dev/pci does: the kernel's e1000 driver hands the
// NIC to a process, and until this existed the interface stayed in lwIP --
// up, holding an address, holding the route to its subnet, and attached to a
// driver that now refuses every frame. Packets went to it and stopped, which
// looks exactly like a driver that is not working.
//
// The slot is left occupied rather than compacted. Interface indices are
// visible in /proc/netif and in the names the stack has already handed out,
// and renumbering them because a device left would be worse than a gap.
int
net_eth_detach(struct device *dev)
{
    int i;

    for (i = 0; i < nifs; i++) {
        if (!ifs[i].used || ifs[i].dev != dev)
            continue;

        // Down first, then out. netif_remove() does stop DHCP and send the
        // release, but a netif removed while still up leaves lwIP's default
        // route pointing at freed storage if this was interface 0.
        netif_set_link_down(&ifs[i].netif);
        netif_set_down(&ifs[i].netif);
        if (netif_default == &ifs[i].netif)
            netif_set_default(NULL);
        netif_remove(&ifs[i].netif);

        ifs[i].used = 0;
        ifs[i].dev  = 0;

        // Something else becomes the default, if anything can. A machine with
        // a second interface should not lose its route because the first one
        // was handed to a driver in a process.
        if (netif_default == NULL) {
            int j;
            for (j = 0; j < nifs; j++)
                if (ifs[j].used) { netif_set_default(&ifs[j].netif); break; }
        }
        return i;
    }
    return -1;
}

int
net_eth_count(void)
{
    return nifs;
}

struct netif *
net_eth_netif(int i)
{
    if (i < 0 || i >= nifs)
        return 0;
    return &ifs[i].netif;
}

struct device *
net_eth_device(int i)
{
    if (i < 0 || i >= nifs)
        return 0;
    return ifs[i].dev;
}

void
net_eth_counts(int i, uint64 *rx, uint64 *tx)
{
    if (i < 0 || i >= nifs) {
        *rx = *tx = 0;
        return;
    }
    *rx = ifs[i].rx_frames;
    *tx = ifs[i].tx_frames;
}

// Take whatever the drivers have and push it into lwIP. Returns how many
// frames moved across all interfaces, so the caller can tell a busy poll from
// an idle one.
//
// Bounded per interface rather than draining: a receive loop with no limit
// starves everything else on a busy network, and the caller comes straight
// back anyway.
int
net_eth_poll(void)
{
    int moved = 0;

    for (int k = 0; k < nifs; k++) {
        struct eth_if *e = &ifs[k];

        for (int i = 0; i < 32; i++) {
            int len = netdev_receive(e->dev, rxframe, sizeof(rxframe));
            if (len <= 0)
                break;

            // PBUF_POOL, so this comes from lwIP's own pool rather than a heap
            // it does not have. A null return means the pool is exhausted,
            // which is a dropped packet -- entirely normal under load, and what
            // the protocol above is designed to survive.
            struct pbuf *p = pbuf_alloc(PBUF_RAW, (u16_t)len, PBUF_POOL);
            if (p == NULL)
                break;

            pbuf_take(p, rxframe, (u16_t)len);

            // netif->input is netif_input, set at netif_add: it dispatches on
            // the Ethernet type. Ownership of the pbuf passes with the call,
            // including when it fails, so there is nothing to free here.
            if (e->netif.input(p, &e->netif) != ERR_OK)
                pbuf_free(p);

            e->rx_frames++;
            moved++;
        }
    }
    return moved;
}