net: the socket layer stops saying yes to things it did not do, and ping works
setsockopt was `return 0;` and getsockopt wrote a zero for whatever was asked. The comment said it was so a server setting SO_REUSEADDR and treating failure as fatal would not fail. That trade is the wrong way round: a caller told "no" adapts, a caller told "yes" changes its behaviour on the strength of it -- sets SO_RCVTIMEO and then blocks forever in a read it believes will time out, sets TCP_NODELAY and reports latency numbers that measure Nagle. The failure is silent, remote from the call, and indistinguishable from a bug in the stack. Six options are honoured now and everything else is ENOPROTOOPT. SO_REUSEADDR, SO_KEEPALIVE, SO_BROADCAST and TCP_NODELAY reach lwIP's pcb; SO_SNDBUF/SO_RCVBUF are accepted and report the real size on read. SO_REUSEADDR is implemented rather than refused precisely because of the original comment's concern -- it is the one option a server really does set and really does check. accept4 becomes its own table entry rather than an alias for accept. It has to be: accept takes three arguments, so a shared handler reading a fourth register reads whatever the caller last left there and invents a SOCK_NONBLOCK out of stack litter. SOCK_CLOEXEC and SOCK_NONBLOCK are now honoured by socket(), socketpair() and accept4() -- a dropped CLOEXEC leaks a listening socket across every exec, and a dropped NONBLOCK has the caller block forever in what it believes is a poll loop. ICMP ping sockets: socket(AF_INET, SOCK_DGRAM, IPPROTO_ICMP), on lwIP's raw API, with the callback stripping the variable-length IP header. Only echo replies are eaten, and that restriction is load-bearing -- raw_input runs before lwIP's own icmp_input, so consuming every ICMP message would swallow the echo *requests* and this machine would silently stop answering pings from outside. Loopback, so 127.0.0.1 is a real destination. LWIP_NETIF_LOOPBACK is the half that is easy to miss: without it a packet addressed to an interface's own address goes out of the wire and never comes back. With NO_SYS=1 nothing drains the loopback queue, so the network thread calls netif_poll_all(). cmd/ping is first-party rather than toybox's, and the reason is a limitation not a preference: toybox reads replies with recvmsg(2) and wants the TTL through an IP_RECVTTL control message, and SchOS has neither. recvmsg is item 1 of docs/plan/foundations.md, where it is wanted for SCM_RIGHTS anyway, and should not be rushed to make one applet run. Two bugs found on the way. Every AF_INET socket failed with ENFILE until DHCP bound, because inet_new() demanded an *address* before handing out a socket and reported it as "file table overflow"; net_is_ready() (lwIP up) is now distinct from net_is_up() (DHCP bound). And that bug was hiding a bad test: socktest asserted "AF_INET is refused, not faked", true when written, false since AF_INET landed, and green the whole time because the suite runs before DHCP binds and the ENFILE made the refusal look real. Fixing the kernel is what turned it red. Verified: ping to 127.0.0.1, localhost, the gateway, 1.1.1.1 and 9.9.9.9, all 0% loss; socktest ALL CHECKS PASSED with ten new checks, including a setsockopt round trip and an unknown option that must be refused -- a permissive stub cannot pass both at once. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01VQ7Qx8E1q1M1bbCq8QLHS2
This commit is contained in:
Nexoniarz
parent
fc0a7c6f4e
commit
c362e308d0
13 changed files with 903 additions and 36 deletions
|
|
@ -62,6 +62,9 @@
|
|||
#include "lwip/opt.h"
|
||||
#include "lwip/tcp.h"
|
||||
#include "lwip/udp.h"
|
||||
#include "lwip/raw.h"
|
||||
#include "lwip/icmp.h"
|
||||
#include "lwip/prot/ip4.h"
|
||||
#include "lwip/ip_addr.h"
|
||||
#include "lwip/pbuf.h"
|
||||
|
||||
|
|
@ -84,9 +87,11 @@ struct dgram {
|
|||
struct inet_sock {
|
||||
int inuse;
|
||||
int type; // SOCK_STREAM or SOCK_DGRAM
|
||||
int proto; // 0, or IPPROTO_ICMP for a ping socket
|
||||
|
||||
struct tcp_pcb *tpcb;
|
||||
struct udp_pcb *upcb;
|
||||
struct raw_pcb *rpcb; // SOCK_DGRAM + IPPROTO_ICMP
|
||||
|
||||
// Receive ring. lwIP hands over pbufs from the network thread; a reader
|
||||
// drains bytes. Full means the sender is told to back off, which for TCP is
|
||||
|
|
@ -399,6 +404,77 @@ inet_udp_recv_cb(void *arg, struct udp_pcb *pcb, struct pbuf *p,
|
|||
net_wake();
|
||||
}
|
||||
|
||||
// ICMP, for ping sockets.
|
||||
//
|
||||
// Linux calls these "ping sockets": SOCK_DGRAM with IPPROTO_ICMP, giving an
|
||||
// unprivileged process the one thing raw sockets were used for. The contract is
|
||||
// that the caller reads and writes the ICMP message alone, and the kernel deals
|
||||
// with the IP header -- which is why this strips it on the way in, where
|
||||
// lwIP's raw layer hands over a pbuf that starts at the IP header.
|
||||
//
|
||||
// **Only echo replies are eaten.** raw_input runs before lwIP's own
|
||||
// icmp_input, so a callback that returned 1 for everything would swallow the
|
||||
// echo *requests* too and this machine would silently stop answering pings
|
||||
// from outside. Returning 0 leaves the packet for lwIP, which is exactly what
|
||||
// should happen to every ICMP message we did not ask for.
|
||||
//
|
||||
// No matching against the echo id: a reply goes to every open ICMP socket.
|
||||
// Linux rewrites the id per socket and filters on it, which matters when two
|
||||
// processes ping at once; with one ping at a time the difference is invisible,
|
||||
// and a socket that sees a reply to somebody else's request will read a
|
||||
// sequence number it never sent and ignore it.
|
||||
static u8_t
|
||||
inet_icmp_recv_cb(void *arg, struct raw_pcb *pcb, struct pbuf *p,
|
||||
const ip_addr_t *addr)
|
||||
{
|
||||
struct inet_sock *is = arg;
|
||||
(void)pcb;
|
||||
|
||||
if (is == 0 || p == NULL)
|
||||
return 0;
|
||||
|
||||
// The IP header is variable length: IHL counts 32-bit words.
|
||||
if (p->tot_len < sizeof(struct ip_hdr))
|
||||
return 0;
|
||||
struct ip_hdr *ih = (struct ip_hdr *)p->payload;
|
||||
u16_t hlen = (u16_t)(IPH_HL(ih) * 4);
|
||||
if (hlen < sizeof(struct ip_hdr) || p->tot_len < hlen + 8)
|
||||
return 0;
|
||||
|
||||
// Type 0 is ICMP Echo Reply. Everything else -- including the requests this
|
||||
// host must keep answering -- is left for lwIP.
|
||||
u8_t type;
|
||||
if (pbuf_copy_partial(p, &type, 1, hlen) != 1 || type != 0)
|
||||
return 0;
|
||||
|
||||
u16_t icmplen = (u16_t)(p->tot_len - hlen);
|
||||
|
||||
if (icmplen <= rx_space(is) && dq_used(is) < NDGRAM) {
|
||||
struct dgram *d = &is->dq[is->dhead % NDGRAM];
|
||||
d->addr = addr ? ip4_addr_get_u32(ip_2_ip4(addr)) : 0;
|
||||
d->port = 0; // ICMP has no ports
|
||||
d->len = icmplen;
|
||||
is->dhead++;
|
||||
|
||||
// Copy the ICMP message out, skipping the IP header, across whatever pbuf
|
||||
// chain it arrived in.
|
||||
u16_t off = hlen;
|
||||
while (off < p->tot_len) {
|
||||
char tmp[64];
|
||||
u16_t want = (u16_t)(p->tot_len - off);
|
||||
if (want > sizeof(tmp)) want = sizeof(tmp);
|
||||
if (pbuf_copy_partial(p, tmp, want, off) != want)
|
||||
break;
|
||||
rx_put(is, tmp, want);
|
||||
off = (u16_t)(off + want);
|
||||
}
|
||||
}
|
||||
|
||||
pbuf_free(p);
|
||||
net_wake();
|
||||
return 1; // eaten
|
||||
}
|
||||
|
||||
/* ------------------------------------------------------------------ */
|
||||
/* Allocation */
|
||||
/* ------------------------------------------------------------------ */
|
||||
|
|
@ -422,11 +498,13 @@ inet_alloc(int type)
|
|||
/* ------------------------------------------------------------------ */
|
||||
|
||||
void *
|
||||
inet_new(int type)
|
||||
inet_new(int type, int proto)
|
||||
{
|
||||
if (type != SOCK_STREAM && type != SOCK_DGRAM)
|
||||
return 0;
|
||||
if (!net_is_up())
|
||||
// Ready, not *up*: see net_is_ready() in kernel/net/net.c. Requiring an
|
||||
// address here made every socket() fail until DHCP answered.
|
||||
if (!net_is_ready())
|
||||
return 0;
|
||||
|
||||
lwip_sys_lock();
|
||||
|
|
@ -435,8 +513,21 @@ inet_new(int type)
|
|||
lwip_sys_unlock();
|
||||
return 0;
|
||||
}
|
||||
is->proto = proto;
|
||||
|
||||
if (type == SOCK_STREAM) {
|
||||
if (proto == IPPROTO_ICMP) {
|
||||
// A ping socket. raw_new registers for one IP protocol number; the
|
||||
// callback below filters to echo replies so lwIP keeps answering the
|
||||
// requests this host receives. See inet_icmp_recv_cb.
|
||||
is->rpcb = raw_new(IP_PROTO_ICMP);
|
||||
if (is->rpcb == 0) {
|
||||
is->inuse = 0;
|
||||
lwip_sys_unlock();
|
||||
return 0;
|
||||
}
|
||||
raw_recv(is->rpcb, inet_icmp_recv_cb, is);
|
||||
raw_bind(is->rpcb, IP_ANY_TYPE);
|
||||
} else if (type == SOCK_STREAM) {
|
||||
is->tpcb = tcp_new();
|
||||
if (is->tpcb == 0) {
|
||||
is->inuse = 0;
|
||||
|
|
@ -480,6 +571,58 @@ inet_bind(void *h, uint32 addr, uint16 port)
|
|||
return e == ERR_OK ? 0 : -EINVAL;
|
||||
}
|
||||
|
||||
// Apply a socket option to the lwIP pcb behind this handle.
|
||||
//
|
||||
// Only the four that lwIP can genuinely honour. Everything else is refused by
|
||||
// the caller (kernel/sys/sys_net.c) before it reaches here, so this never has
|
||||
// to pretend.
|
||||
//
|
||||
// Called with the option already recorded on the struct socket, so a flag set
|
||||
// before bind() is not lost: lwIP's pcb exists from inet_new() onwards, which
|
||||
// is early enough for all four, but recording it there as well means
|
||||
// getsockopt has one answer and not two.
|
||||
int
|
||||
inet_setopt(void *h, int level, int name, int val)
|
||||
{
|
||||
struct inet_sock *is = h;
|
||||
|
||||
lwip_sys_lock();
|
||||
if (level == SOL_SOCKET) {
|
||||
struct ip_pcb *p = (is->type == SOCK_STREAM) ? (struct ip_pcb *)is->tpcb
|
||||
: (struct ip_pcb *)is->upcb;
|
||||
if (p == 0) { lwip_sys_unlock(); return -EINVAL; }
|
||||
switch (name) {
|
||||
case SO_REUSEADDR:
|
||||
if (val) ip_set_option(p, SOF_REUSEADDR);
|
||||
else ip_reset_option(p, SOF_REUSEADDR);
|
||||
break;
|
||||
case SO_KEEPALIVE:
|
||||
if (val) ip_set_option(p, SOF_KEEPALIVE);
|
||||
else ip_reset_option(p, SOF_KEEPALIVE);
|
||||
break;
|
||||
case SO_BROADCAST:
|
||||
if (val) ip_set_option(p, SOF_BROADCAST);
|
||||
else ip_reset_option(p, SOF_BROADCAST);
|
||||
break;
|
||||
default:
|
||||
lwip_sys_unlock();
|
||||
return -ENOPROTOOPT;
|
||||
}
|
||||
} else if (level == IPPROTO_TCP && name == TCP_NODELAY) {
|
||||
if (is->type != SOCK_STREAM || is->tpcb == 0) {
|
||||
lwip_sys_unlock();
|
||||
return -EINVAL;
|
||||
}
|
||||
if (val) tcp_nagle_disable(is->tpcb);
|
||||
else tcp_nagle_enable(is->tpcb);
|
||||
} else {
|
||||
lwip_sys_unlock();
|
||||
return -ENOPROTOOPT;
|
||||
}
|
||||
lwip_sys_unlock();
|
||||
return 0;
|
||||
}
|
||||
|
||||
int
|
||||
inet_listen(void *h, int backlog)
|
||||
{
|
||||
|
|
@ -653,6 +796,38 @@ inet_sendto(void *h, char *buf, int n, uint addr, ushort port)
|
|||
if (n <= 0)
|
||||
return 0;
|
||||
|
||||
// ICMP. The caller hands over the ICMP message alone -- header, checksum and
|
||||
// payload -- and lwIP puts the IP header on the front, which is what makes
|
||||
// this a ping socket rather than a raw one.
|
||||
//
|
||||
// PBUF_IP rather than PBUF_TRANSPORT for the headroom: the IP header is what
|
||||
// goes in front here, and asking for transport headroom would have lwIP
|
||||
// reallocate to make room for it.
|
||||
if (is->proto == IPPROTO_ICMP) {
|
||||
if (is->rpcb == 0)
|
||||
return -ENOTCONN;
|
||||
if (addr == 0)
|
||||
return -EDESTADDRREQ;
|
||||
|
||||
lwip_sys_lock();
|
||||
struct pbuf *p = pbuf_alloc(PBUF_IP, (u16_t)n, PBUF_RAM);
|
||||
if (p == 0) {
|
||||
lwip_sys_unlock();
|
||||
return -ENOBUFS;
|
||||
}
|
||||
pbuf_take(p, buf, (u16_t)n);
|
||||
|
||||
ip_addr_t ip;
|
||||
ip_addr_set_ip4_u32(&ip, addr);
|
||||
err_t e = raw_sendto(is->rpcb, p, &ip);
|
||||
|
||||
pbuf_free(p);
|
||||
lwip_sys_unlock();
|
||||
if (e == ERR_OK)
|
||||
return n;
|
||||
return e == ERR_RTE ? -ENETUNREACH : -EIO;
|
||||
}
|
||||
|
||||
if (is->type == SOCK_DGRAM) {
|
||||
lwip_sys_lock();
|
||||
struct pbuf *p = pbuf_alloc(PBUF_TRANSPORT, (u16_t)n, PBUF_RAM);
|
||||
|
|
@ -793,6 +968,11 @@ inet_close(void *h)
|
|||
udp_remove(is->upcb);
|
||||
is->upcb = 0;
|
||||
}
|
||||
if (is->rpcb) {
|
||||
raw_recv(is->rpcb, 0, 0);
|
||||
raw_remove(is->rpcb);
|
||||
is->rpcb = 0;
|
||||
}
|
||||
is->inuse = 0;
|
||||
lwip_sys_unlock();
|
||||
}
|
||||
|
|
|
|||
|
|
@ -49,6 +49,18 @@
|
|||
#define LWIP_ETHERNET 1
|
||||
#define LWIP_ICMP 1
|
||||
#define LWIP_RAW 1
|
||||
|
||||
// A loopback interface, so 127.0.0.1 is a real destination rather than an
|
||||
// address with no route. lwip_init() creates it; nothing else has to.
|
||||
//
|
||||
// LWIP_NETIF_LOOPBACK is the other half and is easy to miss: without it a
|
||||
// packet addressed to an interface's *own* address goes out of the wire and
|
||||
// never comes back. With NO_SYS=1 there is no thread to drain the loopback
|
||||
// queue either, so netif_poll_all() is called from the network thread -- see
|
||||
// kernel/net/net.c.
|
||||
#define LWIP_HAVE_LOOPIF 1
|
||||
#define LWIP_NETIF_LOOPBACK 1
|
||||
#define LWIP_LOOPBACK_MAX_PBUFS 8
|
||||
#define LWIP_UDP 1
|
||||
#define LWIP_TCP 1
|
||||
#define LWIP_DHCP 1
|
||||
|
|
|
|||
|
|
@ -25,6 +25,7 @@ int memcmp(const void *, const void *, unsigned long);
|
|||
void *memmove(void *, const void *, unsigned long);
|
||||
void *memset(void *, int, unsigned long);
|
||||
int strlen(const char *);
|
||||
int strcmp(const char *, const char *);
|
||||
int strncmp(const char *, const char *, unsigned long);
|
||||
char *strncpy(char *, const char *, int);
|
||||
|
||||
|
|
|
|||
|
|
@ -55,12 +55,29 @@ static int net_started;
|
|||
// something true to say rather than reporting 0.0.0.0 forever.
|
||||
static int net_bound;
|
||||
|
||||
// Set once lwIP is initialised and this thread is running its timers. Distinct
|
||||
// from net_bound, and the distinction is not academic: inet_new() used to
|
||||
// require an *address* before it would hand out a socket, so every AF_INET
|
||||
// socket() failed until DHCP answered -- reported as ENFILE, which sends you to
|
||||
// look at the file table. It is also simply wrong for 127.0.0.1, which needs no
|
||||
// lease and no NIC.
|
||||
//
|
||||
// Creating a socket is not the same as having somewhere to send: a bind or a
|
||||
// connect with no route fails on its own, with an error that says so.
|
||||
static int net_ready;
|
||||
|
||||
int
|
||||
net_is_up(void)
|
||||
{
|
||||
return net_bound;
|
||||
}
|
||||
|
||||
int
|
||||
net_is_ready(void)
|
||||
{
|
||||
return net_ready;
|
||||
}
|
||||
|
||||
static void
|
||||
net_thread(void)
|
||||
{
|
||||
|
|
@ -69,6 +86,9 @@ net_thread(void)
|
|||
// before there is a process context means doing it somewhere that cannot
|
||||
// sleep if the allocator ever needs to.
|
||||
lwip_sys_init();
|
||||
// From here a socket can be created: the pools exist and the timers are
|
||||
// about to run. An address may still be minutes away, or never arrive.
|
||||
net_ready = 1;
|
||||
|
||||
lwip_sys_lock();
|
||||
lwip_init();
|
||||
|
|
@ -111,6 +131,10 @@ net_thread(void)
|
|||
lwip_sys_lock();
|
||||
moved = net_eth_poll();
|
||||
sys_check_timeouts();
|
||||
// Loopback has no driver and no interrupt: a packet sent to 127.0.0.1
|
||||
// sits on the loopif's queue until something drains it. With NO_SYS=1
|
||||
// that something is this thread.
|
||||
netif_poll_all();
|
||||
|
||||
// Report each address once, when it first arrives. Anyone who has spent
|
||||
// an evening wondering whether the guest has an address at all wants
|
||||
|
|
|
|||
|
|
@ -159,6 +159,88 @@ sockdup(struct socket *s)
|
|||
release(&stab.lock);
|
||||
}
|
||||
|
||||
// ---------------------------------------------------------------------------
|
||||
// Socket options
|
||||
//
|
||||
// Only the options that are genuinely honoured appear here; everything else is
|
||||
// answered ENOPROTOOPT by the switch's default. That is deliberate and it is a
|
||||
// change of policy: both calls used to succeed unconditionally, which is the
|
||||
// worst of the three possible answers. A caller told "no" adapts; a caller told
|
||||
// "yes" falsely proceeds on the strength of it -- setting SO_RCVTIMEO and then
|
||||
// blocking forever in a read it believes will time out.
|
||||
//
|
||||
// The flags are recorded here as well as pushed into lwIP so that getsockopt
|
||||
// has one answer rather than two, and so that an AF_UNIX socket -- which has no
|
||||
// pcb and for which none of these mean anything -- can still give back what was
|
||||
// set, as POSIX requires.
|
||||
int
|
||||
sockopt_set(struct socket *s, int level, int name, int val)
|
||||
{
|
||||
int r = 0;
|
||||
|
||||
acquire(&stab.lock);
|
||||
if (level == SOL_SOCKET) {
|
||||
switch (name) {
|
||||
case SO_REUSEADDR: s->o_reuseaddr = !!val; break;
|
||||
case SO_KEEPALIVE: s->o_keepalive = !!val; break;
|
||||
case SO_BROADCAST: s->o_broadcast = !!val; break;
|
||||
// Accepted and left at the size we have. Not the same lie as before:
|
||||
// Linux is explicitly free to clamp these, and sockopt_get below reports
|
||||
// the real figure rather than the requested one.
|
||||
case SO_SNDBUF:
|
||||
case SO_RCVBUF: release(&stab.lock); return 0;
|
||||
default: release(&stab.lock); return -ENOPROTOOPT;
|
||||
}
|
||||
} else if (level == IPPROTO_TCP && name == TCP_NODELAY) {
|
||||
if (s->type != SOCK_STREAM) { release(&stab.lock); return -EINVAL; }
|
||||
s->o_nodelay = !!val;
|
||||
} else {
|
||||
release(&stab.lock);
|
||||
return -ENOPROTOOPT;
|
||||
}
|
||||
int inet = (s->domain == AF_INET);
|
||||
void *h = s->inet;
|
||||
release(&stab.lock);
|
||||
|
||||
// Outside the table lock: inet_setopt takes the lwIP lock, which is a
|
||||
// sleeplock, and the same ordering rule the rest of this file follows.
|
||||
if (inet && h)
|
||||
r = inet_setopt(h, level, name, val);
|
||||
return r;
|
||||
}
|
||||
|
||||
int
|
||||
sockopt_get(struct socket *s, int level, int name, int *out)
|
||||
{
|
||||
int r = 0;
|
||||
|
||||
acquire(&stab.lock);
|
||||
if (level == IPPROTO_TCP && name == TCP_NODELAY) {
|
||||
*out = s->o_nodelay;
|
||||
} else if (level != SOL_SOCKET) {
|
||||
r = -ENOPROTOOPT;
|
||||
} else {
|
||||
switch (name) {
|
||||
case SO_TYPE: *out = s->type; break;
|
||||
case SO_ACCEPTCONN: *out = (s->state == SS_LISTENING); break;
|
||||
case SO_REUSEADDR: *out = s->o_reuseaddr; break;
|
||||
case SO_KEEPALIVE: *out = s->o_keepalive; break;
|
||||
case SO_BROADCAST: *out = s->o_broadcast; break;
|
||||
// The real buffer, not a number somebody asked for.
|
||||
case SO_SNDBUF:
|
||||
case SO_RCVBUF: *out = SOCKBUF; break;
|
||||
// An honest zero rather than the blanket one it replaces: connect() here
|
||||
// is blocking and reports failure as its own return value, so there is no
|
||||
// deferred error for SO_ERROR to carry. It becomes a real field the day a
|
||||
// non-blocking connect exists.
|
||||
case SO_ERROR: *out = 0; break;
|
||||
default: r = -ENOPROTOOPT; break;
|
||||
}
|
||||
}
|
||||
release(&stab.lock);
|
||||
return r;
|
||||
}
|
||||
|
||||
const char *
|
||||
sockname(struct socket *s)
|
||||
{
|
||||
|
|
@ -254,7 +336,7 @@ sockwrite(struct socket *s, char *addr, int n)
|
|||
// ---------------------------------------------------------------------------
|
||||
|
||||
struct socket *
|
||||
socknew(int domain, int type)
|
||||
socknew(int domain, int type, int proto)
|
||||
{
|
||||
struct socket *s;
|
||||
|
||||
|
|
@ -276,7 +358,7 @@ socknew(int domain, int type)
|
|||
if(domain == AF_INET){
|
||||
// Outside the table lock: inet_new takes the lwIP lock, which is a
|
||||
// sleeplock, and sleeping while holding a spinlock is a panic.
|
||||
s->inet = inet_new(type);
|
||||
s->inet = inet_new(type, proto);
|
||||
if(s->inet == 0){
|
||||
sockclose(s);
|
||||
return 0;
|
||||
|
|
|
|||
Loading…
Reference in a new issue