On Tue, Aug 7, 2018 at 5:49 AM, Charles Myers <[email protected]>
wrote:

> libc code is from musl library


Which version? It's not the version we have in musl/, right? So which
version?


> with minor change to prevent partial reads if faster than sender.
>

Is this fixing a bug in musl (in which case you should probably report it
to them), or in OSv?


>
> Signed-off-by: Charles Myers <[email protected]>
> ---
>  Makefile                    |   1 +
>  libc/network/getifaddrs.c   | 392 ++++++++++++++++++++----------
> --------------
>  libc/network/if_nameindex.c | 136 ++++++++++-----
>  libc/network/netlink.c      |  66 ++++++++
>  libc/network/netlink.h      |  94 +++++++++++
>  5 files changed, 435 insertions(+), 254 deletions(-)
>  create mode 100644 libc/network/netlink.c
>  create mode 100644 libc/network/netlink.h
>
> diff --git a/Makefile b/Makefile
> index 49e61b8..d5b6fda 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -1387,6 +1387,7 @@ musl += network/getservbyname.o
>  musl += network/getservbyport_r.o
>  musl += network/getservbyport.o
>  libc += network/getifaddrs.o
> +libc += network/netlink.o
>  libc += network/if_nameindex.o
>  musl += network/if_freenameindex.o
>  libc += network/res_init.o
> diff --git a/libc/network/getifaddrs.c b/libc/network/getifaddrs.c
> index 4cdf4d6..3b92599 100644
> --- a/libc/network/getifaddrs.c
> +++ b/libc/network/getifaddrs.c
> @@ -1,252 +1,216 @@
> -/* (C) 2013 John Spencer. released under musl's standard MIT license. */
> -#undef _GNU_SOURCE
> -#define _GNU_SOURCE
> -#include <ifaddrs.h>
> -#include <stdlib.h>
> -#include <net/if.h> /* IFNAMSIZ, ifreq, ifconf */
> -#include <stdio.h>
> -#include <ctype.h>
> -#include <string.h>
> +//#define _GNU_SOURCE
>  #include <errno.h>
> -#include <arpa/inet.h> /* inet_pton */
> +#include <string.h>
> +#include <stdlib.h>
>  #include <unistd.h>
> -#include <sys/ioctl.h>
> -#include <netpacket/packet.h>
> -#include <net/if_arp.h>
> -
> -typedef union {
> -       struct sockaddr_in6 v6;
> +#include <ifaddrs.h>
> +#include <syscall.h>
> +#include <net/if.h>
> +#include <netinet/in.h>
> +#include "netlink.h"
> +
> +#define IFADDRS_HASH_SIZE 64
> +
> +/* getifaddrs() reports hardware addresses with PF_PACKET that implies
> + * struct sockaddr_ll.  But e.g. Infiniband socket address length is
> + * longer than sockaddr_ll.ssl_addr[8] can hold. Use this hack struct
> + * to extend ssl_addr - callers should be able to still use it. */
> +struct sockaddr_ll_hack {
> +       unsigned short sll_family, sll_protocol;
> +       int sll_ifindex;
> +       unsigned short sll_hatype;
> +       unsigned char sll_pkttype, sll_halen;
> +       unsigned char sll_addr[24];
> +};
> +
> +union sockany {
> +       struct sockaddr sa;
> +       struct sockaddr_ll_hack ll;
>         struct sockaddr_in v4;
> -       struct sockaddr_ll hw;
> -} soa;
> +       struct sockaddr_in6 v6;
> +};
>
> -typedef struct ifaddrs_storage {
> +struct ifaddrs_storage {
>         struct ifaddrs ifa;
> -       soa addr;
> -       soa netmask;
> -       soa dst;
> +       struct ifaddrs_storage *hash_next;
> +       union sockany addr, netmask, ifu;
> +       unsigned int index;
>         char name[IFNAMSIZ+1];
> -} stor;
> -#define next ifa.ifa_next
> +};
>
> -static stor* list_add(stor** list, stor** head, char* ifname)
> -{
> -       stor* curr = calloc(1, sizeof(stor));
> -       if(curr) {
> -               strcpy(curr->name, ifname);
> -               curr->ifa.ifa_name = curr->name;
> -               if(*head) (*head)->next = (struct ifaddrs*) curr;
> -               *head = curr;
> -               if(!*list) *list = curr;
> -       }
> -       return curr;
> -}
> +struct ifaddrs_ctx {
> +       struct ifaddrs_storage *first;
> +       struct ifaddrs_storage *last;
> +       struct ifaddrs_storage *hash[IFADDRS_HASH_SIZE];
> +};
>
>  void freeifaddrs(struct ifaddrs *ifp)
>  {
> -       stor *head = (stor *) ifp;
> -       while(head) {
> -               void *p = head;
> -               head = (stor *) head->next;
> -               free(p);
> +       struct ifaddrs *n;
> +       while (ifp) {
> +               n = ifp->ifa_next;
> +               free(ifp);
> +               ifp = n;
>         }
>  }
>
> -static void ipv6netmask(unsigned prefix_length, struct sockaddr_in6 *sa)
> +static void copy_addr(struct sockaddr **r, int af, union sockany *sa,
> void *addr, size_t addrlen, int ifindex)
>  {
> -       unsigned char* hb = sa->sin6_addr.s6_addr;
> -       unsigned onebytes = prefix_length / 8;
> -       unsigned bits = prefix_length % 8;
> -       unsigned nullbytes = 16 - onebytes;
> -       memset(hb, -1, onebytes);
> -       memset(hb+onebytes, 0, nullbytes);
> -       if(bits) {
> -               unsigned char x = -1;
> -               x <<= 8 - bits;
> -               hb[onebytes] = x;
> +       uint8_t *dst;
> +       int len;
> +
> +       switch (af) {
> +       case AF_INET:
> +               dst = (uint8_t*) &sa->v4.sin_addr;
> +               len = 4;
> +               break;
> +       case AF_INET6:
> +               dst = (uint8_t*) &sa->v6.sin6_addr;
> +               len = 16;
> +               if (IN6_IS_ADDR_LINKLOCAL(addr) ||
> IN6_IS_ADDR_MC_LINKLOCAL(addr))
> +                       sa->v6.sin6_scope_id = ifindex;
> +               break;
> +       default:
> +               return;
>         }
> +       if (addrlen < len) return;
> +       sa->sa.sa_family = af;
> +       memcpy(dst, addr, len);
> +       *r = &sa->sa;
>  }
>
> -static void dealwithipv6(stor **list, stor** head)
> +static void gen_netmask(struct sockaddr **r, int af, union sockany *sa,
> int prefixlen)
>  {
> -       FILE* f = fopen("/proc/net/if_inet6", "r");
> -       /* 00000000000000000000000000000001 01 80 10 80 lo
> -          A                                B  C  D  E  F
> -          all numbers in hex
> -          A = addr B=netlink device#, C=prefix length,
> -          D = scope value (ipv6.h) E = interface flags (rnetlink.h,
> addrconf.c)
> -          F = if name */
> -       char v6conv[32 + 7 + 1], *v6;
> -       char *line, linebuf[512];
> -       if(!f) return;
> -       while((line = fgets(linebuf, sizeof linebuf, f))) {
> -               v6 = v6conv;
> -               size_t i = 0;
> -               for(; i < 8; i++) {
> -                       memcpy(v6, line, 4);
> -                       v6+=4;
> -                       *v6++=':';
> -                       line+=4;
> -               }
> -               --v6; *v6 = 0;
> -               line++;
> -               unsigned b, c, d, e;
> -               char name[IFNAMSIZ+1];
> -               if(5 == sscanf(line, "%x %x %x %x %s", &b, &c, &d, &e,
> name)) {
> -                       struct sockaddr_in6 sa = {0};
> -                       if(1 == inet_pton(AF_INET6, v6conv,
> &sa.sin6_addr)) {
> -                               sa.sin6_family = AF_INET6;
> -                               stor* curr = list_add(list, head, name);
> -                               if(!curr) goto out;
> -                               curr->addr.v6 = sa;
> -                               curr->ifa.ifa_addr = (struct sockaddr*)
> &curr->addr;
> -                               ipv6netmask(c, &sa);
> -                               curr->netmask.v6 = sa;
> -                               curr->ifa.ifa_netmask = (struct sockaddr*)
> &curr->netmask;
> -                               /* find ipv4 struct with the same
> interface name to copy flags */
> -                               stor* scan = *list;
> -                               for(;scan && strcmp(name,
> scan->name);scan=(stor*)scan->next);
> -                               if(scan) curr->ifa.ifa_flags =
> scan->ifa.ifa_flags;
> -                               else curr->ifa.ifa_flags = 0;
> -                       } else errno = 0;
> -               }
> -       }
> -       out:
> -       fclose(f);
> +       uint8_t addr[16] = {0};
> +       int i;
> +
> +       if (prefixlen > 8*sizeof(addr)) prefixlen = 8*sizeof(addr);
> +       i = prefixlen / 8;
> +       memset(addr, 0xff, i);
> +       if (i < sizeof(addr)) addr[i++] = 0xff << (8 - (prefixlen % 8));
> +       copy_addr(r, af, sa, addr, sizeof(addr), 0);
>  }
>
> -int allocate_and_add_ifaddrs(stor **list, stor **head, struct
> if_nameindex *ii)
> +static void copy_lladdr(struct sockaddr **r, union sockany *sa, void
> *addr, size_t addrlen, int ifindex, unsigned short hatype)
>  {
> -       size_t i;
> -       for(i = 0; ii[i].if_index || ii[i].if_name; i++) {
> -               stor* curr = list_add(list, head, ii[i].if_name);
> -               if(!curr) {
> -                       return 0;
> -               }
> -       }
> -       return i;
> +       if (addrlen > sizeof(sa->ll.sll_addr)) return;
> +       sa->ll.sll_family = AF_PACKET;
> +       sa->ll.sll_ifindex = ifindex;
> +       sa->ll.sll_hatype = hatype;
> +       sa->ll.sll_halen = addrlen;
> +       memcpy(sa->ll.sll_addr, addr, addrlen);
> +       *r = &sa->sa;
>  }
>
> -int fill_mac_addrs(int sock, stor *list, struct if_nameindex *ii)
> +static int netlink_msg_to_ifaddr(void *pctx, struct nlmsghdr *h)
>  {
> -       stor *head;
> -       size_t i;
> -
> -       for(head = list, i = 0;
> -           head; head = (stor*)(head->next)) {
> -               struct sockaddr_ll *hw_addr = (struct sockaddr_ll *)
> &head->addr;
> -               head->ifa.ifa_addr = (struct sockaddr*) &head->addr;
> -               struct ifreq req;
> -               int ret;
> -
> -               if (!ii[i].if_name) {
> -                       continue;
> +       struct ifaddrs_ctx *ctx = pctx;
> +       struct ifaddrs_storage *ifs, *ifs0 = NULL;
> +       struct ifinfomsg *ifi = NLMSG_DATA(h);
> +       struct ifaddrmsg *ifa = NLMSG_DATA(h);
> +       struct rtattr *rta;
> +       int stats_len = 0;
> +
> +       if (h->nlmsg_type == RTM_NEWLINK) {
> +               for (rta = NLMSG_RTA(h, sizeof(*ifi)); NLMSG_RTAOK(rta,
> h); rta = RTA_NEXT(rta)) {
> +                       if (rta->rta_type != IFLA_STATS) continue;
> +                       stats_len = RTA_DATALEN(rta);
> +                       break;
>                 }
> -
> -               /* zero the ifreq structure */
> -               memset(&req, 0, sizeof(req));
> -
> -               /* fill in the interface name */
> -               strlcpy(req.ifr_name, ii[i].if_name, IFNAMSIZ);
> -
> -               /* Get the hardware address */
> -               ret = ioctl(sock, SIOCGIFHWADDR, &req);
> -               if (ret == -1) {
> -                       return ret;
> -               }
> -
> -               /* Fill address, index, type, length, familly */
> -               memcpy(hw_addr->sll_addr, req.ifr_hwaddr.sa_data,
> IFHWADDRLEN);
> -               hw_addr->sll_ifindex  = ii[i].if_index;
> -               hw_addr->sll_hatype = ARPHRD_ETHER;
> -               hw_addr->sll_halen  = IFHWADDRLEN;
> -               hw_addr->sll_family = AF_PACKET;
> -
> -               /* Get and fill the address flags */
> -               ret = ioctl(sock, SIOCGIFFLAGS, &req);
> -               if (ret == - 1) {
> -                       return ret;
> -               }
> -               head->ifa.ifa_flags = req.ifr_flags;
> -               i++;
> +       } else {
> +               for (ifs0 = ctx->hash[ifa->ifa_index % IFADDRS_HASH_SIZE];
> ifs0; ifs0 = ifs0->hash_next)
> +                       if (ifs0->index == ifa->ifa_index)
> +                               break;
> +               if (!ifs0) return 0;
>         }
>
> -       return 0;
> -}
> +       ifs = calloc(1, sizeof(struct ifaddrs_storage) + stats_len);
> +       if (ifs == 0) return -1;
>
> -int getifaddrs(struct ifaddrs **ifap)
> -{
> -       stor *list = 0, *head = 0;
> -       struct if_nameindex* ii = if_nameindex();
> -       if(!ii) return -1;
> -       int addr_count;
> -       size_t i;
> -       // allocate and add to the list twice the number of
> -       // interface of ifaddr storage in order to have enough
> -       // for MAC HW addresses that require their own location.
> -       for (i = 0; i < 2; i++) {
> -               addr_count =
> -                       allocate_and_add_ifaddrs(&list, &head, ii);
> -               if (!addr_count) {
> -                       if_freenameindex(ii);
> -                       goto err2;
> -               }
> -       }
> -       if_freenameindex(ii);
> -
> -       int sock = socket(PF_INET, SOCK_DGRAM|SOCK_CLOEXEC, IPPROTO_IP);
> -       if(sock == -1) goto err2;
> -       struct ifreq reqs[32]; /* arbitrary chosen boundary */
> -       struct ifconf conf = {.ifc_len = sizeof reqs, .ifc_req = reqs};
> -       if(-1 == ioctl(sock, SIOCGIFCONF, &conf)) goto err;
> -       size_t reqitems = conf.ifc_len / sizeof(struct ifreq);
> -       int j;
> -       // loop and fill the INET addrs
> -       for(head = list, j = 0; head && j < addr_count; head =
> (stor*)head->next, j++) {
> -               for(i = 0; i < reqitems; i++) {
> -                       // get SIOCGIFADDR of active interfaces.
> -                       if(!strcmp(reqs[i].ifr_name, head->name)) {
> -                               head->addr.v4 = *(struct
> sockaddr_in*)&reqs[i].ifr_addr;
> -                               head->ifa.ifa_addr = (struct sockaddr*)
> &head->addr;
> +       if (h->nlmsg_type == RTM_NEWLINK) {
> +               ifs->index = ifi->ifi_index;
> +               ifs->ifa.ifa_flags = ifi->ifi_flags;
> +
> +               for (rta = NLMSG_RTA(h, sizeof(*ifi)); NLMSG_RTAOK(rta,
> h); rta = RTA_NEXT(rta)) {
> +                       switch (rta->rta_type) {
> +                       case IFLA_IFNAME:
> +                               if (RTA_DATALEN(rta) < sizeof(ifs->name)) {
> +                                       memcpy(ifs->name, RTA_DATA(rta),
> RTA_DATALEN(rta));
> +                                       ifs->ifa.ifa_name = ifs->name;
> +                               }
> +                               break;
> +                       case IFLA_ADDRESS:
> +                               copy_lladdr(&ifs->ifa.ifa_addr,
> &ifs->addr, RTA_DATA(rta), RTA_DATALEN(rta), ifi->ifi_index, ifi->ifi_type);
> +                               break;
> +                       case IFLA_BROADCAST:
> +                               copy_lladdr(&ifs->ifa.ifa_broadaddr,
> &ifs->ifu, RTA_DATA(rta), RTA_DATALEN(rta), ifi->ifi_index, ifi->ifi_type);
> +                               break;
> +                       case IFLA_STATS:
> +                               ifs->ifa.ifa_data = (void*)(ifs+1);
> +                               memcpy(ifs->ifa.ifa_data, RTA_DATA(rta),
> RTA_DATALEN(rta));
>                                 break;
>                         }
>                 }
> -               struct ifreq req;
> -               snprintf(req.ifr_name, sizeof req.ifr_name, "%s",
> head->name);
> -               if(-1 == ioctl(sock, SIOCGIFFLAGS, &req)) goto err;
> -
> -               head->ifa.ifa_flags = req.ifr_flags;
> -               if(head->ifa.ifa_addr) {
> -                       /* or'ing flags with IFF_LOWER_UP on active
> interfaces to mimic glibc */
> -                       head->ifa.ifa_flags |= IFF_LOWER_UP;
> -                       if(-1 == ioctl(sock, SIOCGIFNETMASK, &req)) goto
> err;
> -                       head->netmask.v4 = *(struct
> sockaddr_in*)&req.ifr_netmask;
> -                       head->ifa.ifa_netmask = (struct sockaddr*)
> &head->netmask;
> -
> -                       if(head->ifa.ifa_flags & IFF_POINTOPOINT) {
> -                               if(-1 == ioctl(sock, SIOCGIFDSTADDR,
> &req)) goto err;
> -                               head->dst.v4 = *(struct
> sockaddr_in*)&req.ifr_dstaddr;
> -                       } else {
> -                               if(-1 == ioctl(sock, SIOCGIFBRDADDR,
> &req)) goto err;
> -                               head->dst.v4 = *(struct
> sockaddr_in*)&req.ifr_broadaddr;
> +               if (ifs->ifa.ifa_name) {
> +                       unsigned int bucket = ifs->index %
> IFADDRS_HASH_SIZE;
> +                       ifs->hash_next = ctx->hash[bucket];
> +                       ctx->hash[bucket] = ifs;
> +               }
> +       } else {
> +               ifs->ifa.ifa_name = ifs0->ifa.ifa_name;
> +               ifs->ifa.ifa_flags = ifs0->ifa.ifa_flags;
> +               for (rta = NLMSG_RTA(h, sizeof(*ifa)); NLMSG_RTAOK(rta,
> h); rta = RTA_NEXT(rta)) {
> +                       switch (rta->rta_type) {
> +                       case IFA_ADDRESS:
> +                               /* If ifa_addr is already set we, received
> an IFA_LOCAL before
> +                                * so treat this as destination address */
> +                               if (ifs->ifa.ifa_addr)
> +                                       copy_addr(&ifs->ifa.ifa_dstaddr,
> ifa->ifa_family, &ifs->ifu, RTA_DATA(rta), RTA_DATALEN(rta),
> ifa->ifa_index);
> +                               else
> +                                       copy_addr(&ifs->ifa.ifa_addr,
> ifa->ifa_family, &ifs->addr, RTA_DATA(rta), RTA_DATALEN(rta),
> ifa->ifa_index);
> +                               break;
> +                       case IFA_BROADCAST:
> +                               copy_addr(&ifs->ifa.ifa_broadaddr,
> ifa->ifa_family, &ifs->ifu, RTA_DATA(rta), RTA_DATALEN(rta),
> ifa->ifa_index);
> +                               break;
> +                       case IFA_LOCAL:
> +                               /* If ifa_addr is set and we get
> IFA_LOCAL, assume we have
> +                                * a point-to-point network. Move address
> to correct field. */
> +                               if (ifs->ifa.ifa_addr) {
> +                                       ifs->ifu = ifs->addr;
> +                                       ifs->ifa.ifa_dstaddr = &ifs->
> ifu.sa;
> +                                       memset(&ifs->addr, 0,
> sizeof(ifs->addr));
> +                               }
> +                               copy_addr(&ifs->ifa.ifa_addr,
> ifa->ifa_family, &ifs->addr, RTA_DATA(rta), RTA_DATALEN(rta),
> ifa->ifa_index);
> +                               break;
> +                       case IFA_LABEL:
> +                               if (RTA_DATALEN(rta) < sizeof(ifs->name)) {
> +                                       memcpy(ifs->name, RTA_DATA(rta),
> RTA_DATALEN(rta));
> +                                       ifs->ifa.ifa_name = ifs->name;
> +                               }
> +                               break;
>                         }
> -                       head->ifa.ifa_ifu.ifu_dstaddr = (struct sockaddr*)
> &head->dst;
>                 }
> +               if (ifs->ifa.ifa_addr)
> +                       gen_netmask(&ifs->ifa.ifa_netmask,
> ifa->ifa_family, &ifs->netmask, ifa->ifa_prefixlen);
>         }
> -       if (-1 == fill_mac_addrs(sock, head, ii)) {
> -               goto err;
> +
> +       if (ifs->ifa.ifa_name) {
> +               if (!ctx->first) ctx->first = ifs;
> +               if (ctx->last) ctx->last->ifa.ifa_next = &ifs->ifa;
> +               ctx->last = ifs;
> +       } else {
> +               free(ifs);
>         }
> -       close(sock);
> -       void* last = 0;
> -       for(head = list; head; head=(stor*)head->next) last=head;
> -       head = last;
> -       dealwithipv6(&list, &head);
> -       *ifap = (struct ifaddrs*) list;
>         return 0;
> -       err:
> -       close(sock);
> -       err2:
> -       freeifaddrs((struct ifaddrs*) list);
> -       return -1;
>  }
>
> +int getifaddrs(struct ifaddrs **ifap)
> +{
> +       struct ifaddrs_ctx _ctx, *ctx = &_ctx;
> +       int r;
> +       memset(ctx, 0, sizeof *ctx);
> +       r = __rtnetlink_enumerate(AF_UNSPEC, AF_UNSPEC,
> netlink_msg_to_ifaddr, ctx);
> +       if (r == 0) *ifap = &ctx->first->ifa;
> +       else freeifaddrs(&ctx->first->ifa);
> +       return r;
> +}
> diff --git a/libc/network/if_nameindex.c b/libc/network/if_nameindex.c
> index b0a4f5c..7c36c85 100644
> --- a/libc/network/if_nameindex.c
> +++ b/libc/network/if_nameindex.c
> @@ -1,58 +1,114 @@
> -#define _GNU_SOURCE
> +//#define _GNU_SOURCE
>  #include <net/if.h>
> -#include <stdlib.h>
> -#include <sys/socket.h>
> -#include <sys/ioctl.h>
>  #include <errno.h>
>  #include <unistd.h>
> -#include <sys/syscall.h>
> +#include <stdlib.h>
> +#include <string.h>
> +#include <pthread.h>
> +#include "netlink.h"
>
> -#include <stdio.h>
> +#define IFADDRS_HASH_SIZE 64
>
> -static void *do_nameindex(int s, size_t n)
> -{
> -       size_t i, len, k;
> -       struct ifconf conf;
> -       struct if_nameindex *idx;
> +struct ifnamemap {
> +       unsigned int hash_next;
> +       unsigned int index;
> +       unsigned char namelen;
> +       char name[IFNAMSIZ];
> +};
>
> -       idx = malloc(n * (sizeof(struct if_nameindex)+sizeof(struct
> ifreq)));
> -       if (!idx) return 0;
> +struct ifnameindexctx {
> +       unsigned int num, allocated, str_bytes;
> +       struct ifnamemap *list;
> +       unsigned int hash[IFADDRS_HASH_SIZE];
> +};
>
> -       conf.ifc_buf = (void *)&idx[n];
> -       conf.ifc_len = len = n * sizeof(struct ifreq);
> -       if (ioctl(s, SIOCGIFCONF, &conf) < 0) {
> -               free(idx);
> -               return 0;
> -       }
> -       if (conf.ifc_len == len) {
> -               free(idx);
> -               return (void *)-1;
> +static int netlink_msg_to_nameindex(void *pctx, struct nlmsghdr *h)
> +{
> +       struct ifnameindexctx *ctx = pctx;
> +       struct ifnamemap *map;
> +       struct rtattr *rta;
> +       unsigned int i;
> +       int index, type, namelen, bucket;
> +
> +       if (h->nlmsg_type == RTM_NEWLINK) {
> +               struct ifinfomsg *ifi = NLMSG_DATA(h);
> +               index = ifi->ifi_index;
> +               type = IFLA_IFNAME;
> +               rta = NLMSG_RTA(h, sizeof(*ifi));
> +       } else {
> +               struct ifaddrmsg *ifa = NLMSG_DATA(h);
> +               index = ifa->ifa_index;
> +               type = IFA_LABEL;
> +               rta = NLMSG_RTA(h, sizeof(*ifa));
>         }
> +       for (; NLMSG_RTAOK(rta, h); rta = RTA_NEXT(rta)) {
> +               if (rta->rta_type != type) continue;
> +
> +               namelen = RTA_DATALEN(rta) - 1;
> +               if (namelen > IFNAMSIZ) return 0;
>
> -       n = conf.ifc_len / sizeof(struct ifreq);
> -       for (i=k=0; i<n; i++) {
> -               if (ioctl(s, SIOCGIFINDEX, &conf.ifc_req[i]) < 0) {
> -                       k++;
> -                       continue;
> +               /* suppress duplicates */
> +               bucket = index % IFADDRS_HASH_SIZE;
> +               i = ctx->hash[bucket];
> +               while (i) {
> +                       map = &ctx->list[i-1];
> +                       if (map->index == index &&
> +                           map->namelen == namelen &&
> +                           memcmp(map->name, RTA_DATA(rta), namelen) == 0)
> +                               return 0;
> +                       i = map->hash_next;
>                 }
> -               idx[i-k].if_index = conf.ifc_req[i].ifr_ifindex;
> -               idx[i-k].if_name = conf.ifc_req[i].ifr_name;
> -       }
> -       idx[i-k].if_name = 0;
> -       idx[i-k].if_index = 0;
>
> -       return idx;
> +               if (ctx->num >= ctx->allocated) {
> +                       size_t a = ctx->allocated ? ctx->allocated * 2 + 1
> : 8;
> +                       if (a > SIZE_MAX/sizeof *map) return -1;
> +                       map = realloc(ctx->list, a * sizeof *map);
> +                       if (!map) return -1;
> +                       ctx->list = map;
> +                       ctx->allocated = a;
> +               }
> +               map = &ctx->list[ctx->num];
> +               map->index = index;
> +               map->namelen = namelen;
> +               memcpy(map->name, RTA_DATA(rta), namelen);
> +               ctx->str_bytes += namelen + 1;
> +               ctx->num++;
> +               map->hash_next = ctx->hash[bucket];
> +               ctx->hash[bucket] = ctx->num;
> +               return 0;
> +       }
> +       return 0;
>  }
>
>  struct if_nameindex *if_nameindex()
>  {
> -       size_t n;
> -       void *p = 0;
> -       int s = socket(AF_INET, SOCK_DGRAM|SOCK_CLOEXEC, 0);
> -       if (s>=0) {
> -               for (n=0; (p=do_nameindex(s, n)) == (void *)-1; n++);
> -               __syscall(SYS_close, s);
> +       struct ifnameindexctx _ctx, *ctx = &_ctx;
> +       struct if_nameindex *ifs = 0, *d;
> +       struct ifnamemap *s;
> +       char *p;
> +       int i;
> +       int cs;
> +
> +       pthread_setcancelstate(PTHREAD_CANCEL_DISABLE, &cs);
> +       memset(ctx, 0, sizeof(*ctx));
> +       if (__rtnetlink_enumerate(AF_UNSPEC, AF_INET,
> netlink_msg_to_nameindex, ctx) < 0) goto err;
> +
> +       ifs = malloc(sizeof(struct if_nameindex[ctx->num+1]) +
> ctx->str_bytes);
> +       if (!ifs) goto err;
> +
> +       p = (char*)(ifs + ctx->num + 1);
> +       for (i = ctx->num, d = ifs, s = ctx->list; i; i--, s++, d++) {
> +               d->if_index = s->index;
> +               d->if_name = p;
> +               memcpy(p, s->name, s->namelen);
> +               p += s->namelen;
> +               *p++ = 0;
>         }
> +       d->if_index = 0;
> +       d->if_name = 0;
> +err:
> +       pthread_setcancelstate(cs, 0);
> +       free(ctx->list);
>         errno = ENOBUFS;
> -       return p;
> +       return ifs;
>  }
> diff --git a/libc/network/netlink.c b/libc/network/netlink.c
> new file mode 100644
> index 0000000..ab0437a
> --- /dev/null
> +++ b/libc/network/netlink.c
> @@ -0,0 +1,66 @@
> +#include <errno.h>
> +#include <string.h>
> +#include <syscall.h>
> +#include <sys/socket.h>
> +#include <unistd.h>
> +#include "netlink.h"
> +#include <stdio.h>
> +#include <poll.h>
> +
> +static int __netlink_enumerate(int fd, unsigned int seq, int type, int af,
> +       int (*cb)(void *ctx, struct nlmsghdr *h), void *ctx)
> +{
> +       struct nlmsghdr *h;
> +       union {
> +               uint8_t buf[8192];
> +               struct {
> +                       struct nlmsghdr nlh;
> +                       struct rtgenmsg g;
> +               } req;
> +               struct nlmsghdr reply;
> +       } u;
> +       int r, ret;
> +
> +       memset(&u.req, 0, sizeof(u.req));
> +       u.req.nlh.nlmsg_len = sizeof(u.req);
> +       u.req.nlh.nlmsg_type = type;
> +       u.req.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST;
> +       u.req.nlh.nlmsg_seq = seq;
> +       u.req.g.rtgen_family = af;
> +       r = send(fd, &u.req, sizeof(u.req), 0);
> +       if (r < 0) return r;
> +
> +       while (1) {
> +               r = recv(fd, u.buf, sizeof(u.buf), MSG_DONTWAIT);
> +               if (r <= 0)  {
> +                       /* Wait if recv() timed out because response might
> not be queued in time */
> +                       if (r < 0 && (errno == EAGAIN || errno ==
> EWOULDBLOCK)) {
> +                               struct pollfd pfds[1];
> +                               pfds[0].fd = fd;
> +                               pfds[0].events = POLLIN;
> +                               pfds[0].revents = 0;
> +                               if (poll(pfds, 1, 1000) != 0)
> +                                       continue;
> +                       }
> +                       return -1;
> +               }
> +               for (h = &u.reply; NLMSG_OK(h, (void*)&u.buf[r]); h =
> NLMSG_NEXT(h)) {
> +                       if (h->nlmsg_type == NLMSG_DONE) return 0;
> +                       if (h->nlmsg_type == NLMSG_ERROR) return -1;
> +                       ret = cb(ctx, h);
> +                       if (ret) return ret;
> +               }
> +       }
> +}
> +
> +int __rtnetlink_enumerate(int link_af, int addr_af, int (*cb)(void *ctx,
> struct nlmsghdr *h), void *ctx)
> +{
> +       int fd, r;
> +
> +       fd = socket(PF_NETLINK, SOCK_RAW|SOCK_CLOEXEC, NETLINK_ROUTE);
> +       if (fd < 0) return -1;
> +       r = __netlink_enumerate(fd, 1, RTM_GETLINK, link_af, cb, ctx);
> +       if (!r) r = __netlink_enumerate(fd, 2, RTM_GETADDR, addr_af, cb,
> ctx);
> +       __syscall(SYS_close,fd);
> +       return r;
> +}
> diff --git a/libc/network/netlink.h b/libc/network/netlink.h
> new file mode 100644
> index 0000000..20700ac
> --- /dev/null
> +++ b/libc/network/netlink.h
> @@ -0,0 +1,94 @@
> +#include <stdint.h>
> +
> +/* linux/netlink.h */
>

In the long run, maybe this stuff belongs in include/api/linux/netlink.h;
Don't you also need the same
definitions in the *implementation* of the netlink protocol, not just its
user in libc?
But if this fits your organization and doesn't cause duplication of the
definitions it can stay here for now.

+
> +#define NETLINK_ROUTE 0
> +
> +struct nlmsghdr {
> +       uint32_t        nlmsg_len;
> +       uint16_t        nlmsg_type;
> +       uint16_t        nlmsg_flags;
> +       uint32_t        nlmsg_seq;
> +       uint32_t        nlmsg_pid;
> +};
> +
> +#define NLM_F_REQUEST  1
> +#define NLM_F_MULTI    2
> +#define NLM_F_ACK      4
> +
> +#define NLM_F_ROOT     0x100
> +#define NLM_F_MATCH    0x200
> +#define NLM_F_ATOMIC   0x400
> +#define NLM_F_DUMP     (NLM_F_ROOT|NLM_F_MATCH)
> +
> +#define NLMSG_NOOP     0x1
> +#define NLMSG_ERROR    0x2
> +#define NLMSG_DONE     0x3
> +#define NLMSG_OVERRUN  0x4
> +
> +/* linux/rtnetlink.h */
> +
> +#define RTM_NEWLINK    16
> +#define RTM_GETLINK    18
> +#define RTM_NEWADDR    20
> +#define RTM_GETADDR    22
> +
> +struct rtattr {
> +       unsigned short  rta_len;
> +       unsigned short  rta_type;
> +};
> +
> +struct rtgenmsg {
> +       unsigned char   rtgen_family;
> +};
> +
> +struct ifinfomsg {
> +       unsigned char   ifi_family;
> +       unsigned char   __ifi_pad;
> +       unsigned short  ifi_type;
> +       int             ifi_index;
> +       unsigned        ifi_flags;
> +       unsigned        ifi_change;
> +};
> +
> +/* linux/if_link.h */
> +
> +#define IFLA_ADDRESS   1
> +#define IFLA_BROADCAST 2
> +#define IFLA_IFNAME    3
> +#define IFLA_STATS     7
> +
> +/* linux/if_addr.h */
> +
> +struct ifaddrmsg {
> +       uint8_t         ifa_family;
> +       uint8_t         ifa_prefixlen;
> +       uint8_t         ifa_flags;
> +       uint8_t         ifa_scope;
> +       uint32_t        ifa_index;
> +};
> +
> +#define IFA_ADDRESS    1
> +#define IFA_LOCAL      2
> +#define IFA_LABEL      3
> +#define IFA_BROADCAST  4
> +
> +/* musl */
> +
> +#define NETLINK_ALIGN(len)     (((len)+3) & ~3)
> +#define NLMSG_DATA(nlh)                ((void*)((char*)(nlh)+sizeof(struct
> nlmsghdr)))
> +#define NLMSG_DATALEN(nlh)     ((nlh)->nlmsg_len-sizeof(struct nlmsghdr))
> +#define NLMSG_DATAEND(nlh)     ((char*)(nlh)+(nlh)->nlmsg_len)
> +#define NLMSG_NEXT(nlh)                (struct nlmsghdr*)((char*)(nlh)+
> NETLINK_ALIGN((nlh)->nlmsg_len))
> +#define NLMSG_OK(nlh,end)      ((char*)(end)-(char*)(nlh) >=
> sizeof(struct nlmsghdr))
> +
> +#define RTA_DATA(rta)          ((void*)((char*)(rta)+sizeof(struct
> rtattr)))
> +#define RTA_DATALEN(rta)       ((rta)->rta_len-sizeof(struct rtattr))
> +#define RTA_DATAEND(rta)       ((char*)(rta)+(rta)->rta_len)
> +#define RTA_NEXT(rta)          (struct rtattr*)((char*)(rta)+NETLINK_
> ALIGN((rta)->rta_len))
> +#define RTA_OK(nlh,end)                ((char*)(end)-(char*)(rta) >=
> sizeof(struct rtattr))
> +
> +#define NLMSG_RTA(nlh,len)     ((void*)((char*)(nlh)+sizeof(struct
> nlmsghdr)+NETLINK_ALIGN(len)))
> +#define NLMSG_RTAOK(rta,nlh)   RTA_OK(rta,NLMSG_DATAEND(nlh))
> +
> +int __rtnetlink_enumerate(int link_af, int addr_af, int (*cb)(void *ctx,
> struct nlmsghdr *h), void *ctx);
> --
> 2.7.4
>
> --
> You received this message because you are subscribed to the Google Groups
> "OSv Development" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to [email protected].
> For more options, visit https://groups.google.com/d/optout.
>

-- 
You received this message because you are subscribed to the Google Groups "OSv 
Development" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
For more options, visit https://groups.google.com/d/optout.

Reply via email to