/* * 32bit Socket syscall emulation. Based on arch/sparc64/kernel/sys_sparc32.c. * * Copyright (C) 2000 VA Linux Co * Copyright (C) 2000 Don Dugger <n0ano@valinux.com> * Copyright (C) 1999 Arun Sharma <arun.sharma@intel.com> * Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz) * Copyright (C) 1997 David S. Miller (davem@caip.rutgers.edu) * Copyright (C) 2000 Hewlett-Packard Co. * Copyright (C) 2000 David Mosberger-Tang <davidm@hpl.hp.com> * Copyright (C) 2000,2001 Andi Kleen, SuSE Labs */ #include <linux/kernel.h> #include <linux/fs.h> #include <linux/types.h> #include <linux/file.h> #include <linux/icmpv6.h> #include <linux/socket.h> #include <linux/syscalls.h> #include <linux/filter.h> #include <linux/compat.h> #include <linux/netfilter_ipv4/ip_tables.h> #include <linux/security.h> #include <net/scm.h> #include <net/sock.h> #include <asm/uaccess.h> #include <net/compat.h> static inline int iov_from_user_compat_to_kern(struct iovec *kiov, struct compat_iovec __user *uiov32, int niov) { int tot_len = 0; while (niov > 0) { compat_uptr_t buf; compat_size_t len; if (get_user(len, &uiov32->iov_len) || get_user(buf, &uiov32->iov_base)) { tot_len = -EFAULT; break; } tot_len += len; kiov->iov_base = compat_ptr(buf); kiov->iov_len = (__kernel_size_t) len; uiov32++; kiov++; niov--; } return tot_len; } int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg) { compat_uptr_t tmp1, tmp2, tmp3; if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || __get_user(tmp1, &umsg->msg_name) || __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || __get_user(tmp2, &umsg->msg_iov) || __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) || __get_user(tmp3, &umsg->msg_control) || __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) return -EFAULT; kmsg->msg_name = compat_ptr(tmp1); kmsg->msg_iov = compat_ptr(tmp2); kmsg->msg_control = compat_ptr(tmp3); return 0; } /* I've named the args so it is easy to tell whose space the pointers are in. */ int verify_compat_iovec(struct msghdr *kern_msg, struct iovec *kern_iov, char *kern_address, int mode) { int tot_len; if (kern_msg->msg_namelen) { if (mode==VERIFY_READ) { int err = move_addr_to_kernel(kern_msg->msg_name, kern_msg->msg_namelen, kern_address); if (err < 0) return err; } kern_msg->msg_name = kern_address; } else kern_msg->msg_name = NULL; tot_len = iov_from_user_compat_to_kern(kern_iov, (struct compat_iovec __user *)kern_msg->msg_iov, kern_msg->msg_iovlen); if (tot_len >= 0) kern_msg->msg_iov = kern_iov; return tot_len; } /* Bleech... */ #define CMSG_COMPAT_ALIGN(len) ALIGN((len), sizeof(s32)) #define CMSG_COMPAT_DATA(cmsg) \ ((void __user *)((char __user *)(cmsg) + CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)))) #define CMSG_COMPAT_SPACE(len) \ (CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)) + CMSG_COMPAT_ALIGN(len)) #define CMSG_COMPAT_LEN(len) \ (CMSG_COMPAT_ALIGN(sizeof(struct compat_cmsghdr)) + (len)) #define CMSG_COMPAT_FIRSTHDR(msg) \ (((msg)->msg_controllen) >= sizeof(struct compat_cmsghdr) ? \ (struct compat_cmsghdr __user *)((msg)->msg_control) : \ (struct compat_cmsghdr __user *)NULL) #define CMSG_COMPAT_OK(ucmlen, ucmsg, mhdr) \ ((ucmlen) >= sizeof(struct compat_cmsghdr) && \ (ucmlen) <= (unsigned long) \ ((mhdr)->msg_controllen - \ ((char *)(ucmsg) - (char *)(mhdr)->msg_control))) static inline struct compat_cmsghdr __user *cmsg_compat_nxthdr(struct msghdr *msg, struct compat_cmsghdr __user *cmsg, int cmsg_len) { char __user *ptr = (char __user *)cmsg + CMSG_COMPAT_ALIGN(cmsg_len); if ((unsigned long)(ptr + 1 - (char __user *)msg->msg_control) > msg->msg_controllen) return NULL; return (struct compat_cmsghdr __user *)ptr; } /* There is a lot of hair here because the alignment rules (and * thus placement) of cmsg headers and length are different for * 32-bit apps. -DaveM */ int cmsghdr_from_user_compat_to_kern(struct msghdr *kmsg, struct sock *sk, unsigned char *stackbuf, int stackbuf_size) { struct compat_cmsghdr __user *ucmsg; struct cmsghdr *kcmsg, *kcmsg_base; compat_size_t ucmlen; __kernel_size_t kcmlen, tmp; int err = -EFAULT; kcmlen = 0; kcmsg_base = kcmsg = (struct cmsghdr *)stackbuf; ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg); while (ucmsg != NULL) { if (get_user(ucmlen, &ucmsg->cmsg_len)) return -EFAULT; /* Catch bogons. */ if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg)) return -EINVAL; tmp = ((ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg))) + CMSG_ALIGN(sizeof(struct cmsghdr))); tmp = CMSG_ALIGN(tmp); kcmlen += tmp; ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); } if (kcmlen == 0) return -EINVAL; /* The kcmlen holds the 64-bit version of the control length. * It may not be modified as we do not stick it into the kmsg * until we have successfully copied over all of the data * from the user. */ if (kcmlen > stackbuf_size) kcmsg_base = kcmsg = sock_kmalloc(sk, kcmlen, GFP_KERNEL); if (kcmsg == NULL) return -ENOBUFS; /* Now copy them over neatly. */ memset(kcmsg, 0, kcmlen); ucmsg = CMSG_COMPAT_FIRSTHDR(kmsg); while (ucmsg != NULL) { if (__get_user(ucmlen, &ucmsg->cmsg_len)) goto Efault; if (!CMSG_COMPAT_OK(ucmlen, ucmsg, kmsg)) goto Einval; tmp = ((ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg))) + CMSG_ALIGN(sizeof(struct cmsghdr))); if ((char *)kcmsg_base + kcmlen - (char *)kcmsg < CMSG_ALIGN(tmp)) goto Einval; kcmsg->cmsg_len = tmp; tmp = CMSG_ALIGN(tmp); if (__get_user(kcmsg->cmsg_level, &ucmsg->cmsg_level) || __get_user(kcmsg->cmsg_type, &ucmsg->cmsg_type) || copy_from_user(CMSG_DATA(kcmsg), CMSG_COMPAT_DATA(ucmsg), (ucmlen - CMSG_COMPAT_ALIGN(sizeof(*ucmsg))))) goto Efault; /* Advance. */ kcmsg = (struct cmsghdr *)((char *)kcmsg + tmp); ucmsg = cmsg_compat_nxthdr(kmsg, ucmsg, ucmlen); } /* Ok, looks like we made it. Hook it up and return success. */ kmsg->msg_control = kcmsg_base; kmsg->msg_controllen = kcmlen; return 0; Einval: err = -EINVAL; Efault: if (kcmsg_base != (struct cmsghdr *)stackbuf) sock_kfree_s(sk, kcmsg_base, kcmlen); return err; } int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *data) { struct compat_timeval ctv; struct compat_timespec cts; struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { kmsg->msg_flags |= MSG_CTRUNC; return 0; /* XXX: return error? check spec. */ } if (level == SOL_SOCKET && type == SO_TIMESTAMP) { struct timeval *tv = (struct timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; data = &ctv; len = sizeof(ctv); } if (level == SOL_SOCKET && type == SO_TIMESTAMPNS) { struct timespec *ts = (struct timespec *)data; cts.tv_sec = ts->tv_sec; cts.tv_nsec = ts->tv_nsec; data = &cts; len = sizeof(cts); } cmlen = CMSG_COMPAT_LEN(len); if (kmsg->msg_controllen < cmlen) { kmsg->msg_flags |= MSG_CTRUNC; cmlen = kmsg->msg_controllen; } cmhdr.cmsg_level = level; cmhdr.cmsg_type = type; cmhdr.cmsg_len = cmlen; if (copy_to_user(cm, &cmhdr, sizeof cmhdr)) return -EFAULT; if (copy_to_user(CMSG_COMPAT_DATA(cm), data, cmlen - sizeof(struct compat_cmsghdr))) return -EFAULT; cmlen = CMSG_COMPAT_SPACE(len); kmsg->msg_control += cmlen; kmsg->msg_controllen -= cmlen; return 0; } void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; int fdmax = (kmsg->msg_controllen - sizeof(struct compat_cmsghdr)) / sizeof(int); int fdnum = scm->fp->count; struct file **fp = scm->fp->fp; int __user *cmfptr; int err = 0, i; if (fdnum < fdmax) fdmax = fdnum; for (i = 0, cmfptr = (int __user *) CMSG_COMPAT_DATA(cm); i < fdmax; i++, cmfptr++) { int new_fd; err = security_file_receive(fp[i]); if (err) break; err = get_unused_fd(); if (err < 0) break; new_fd = err; err = put_user(new_fd, cmfptr); if (err) { put_unused_fd(new_fd); break; } /* Bump the usage count and install the file. */ get_file(fp[i]); fd_install(new_fd, fp[i]); } if (i > 0) { int cmlen = CMSG_COMPAT_LEN(i * sizeof(int)); err = put_user(SOL_SOCKET, &cm->cmsg_level); if (!err) err = put_user(SCM_RIGHTS, &cm->cmsg_type); if (!err) err = put_user(cmlen, &cm->cmsg_len); if (!err) { cmlen = CMSG_COMPAT_SPACE(i * sizeof(int)); kmsg->msg_control += cmlen; kmsg->msg_controllen -= cmlen; } } if (i < fdnum) kmsg->msg_flags |= MSG_CTRUNC; /* * All of the files that fit in the message have had their * usage counts incremented, so we just free the list. */ __scm_destroy(scm); } /* * For now, we assume that the compatibility and native version * of struct ipt_entry are the same - sfr. FIXME */ struct compat_ipt_replace { char name[IPT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_IP_NUMHOOKS]; u32 underflow[NF_IP_NUMHOOKS]; u32 num_counters; compat_uptr_t counters; /* struct ipt_counters * */ struct ipt_entry entries[0]; }; static int do_netfilter_replace(int fd, int level, int optname, char __user *optval, int optlen) { struct compat_ipt_replace __user *urepl; struct ipt_replace __user *repl_nat; char name[IPT_TABLE_MAXNAMELEN]; u32 origsize, tmp32, num_counters; unsigned int repl_nat_size; int ret; int i; compat_uptr_t ucntrs; urepl = (struct compat_ipt_replace __user *)optval; if (get_user(origsize, &urepl->size)) return -EFAULT; /* Hack: Causes ipchains to give correct error msg --RR */ if (optlen != sizeof(*urepl) + origsize) return -ENOPROTOOPT; /* XXX Assumes that size of ipt_entry is the same both in * native and compat environments. */ repl_nat_size = sizeof(*repl_nat) + origsize; repl_nat = compat_alloc_user_space(repl_nat_size); ret = -EFAULT; if (put_user(origsize, &repl_nat->size)) goto out; if (!access_ok(VERIFY_READ, urepl, optlen) || !access_ok(VERIFY_WRITE, repl_nat, optlen)) goto out; if (__copy_from_user(name, urepl->name, sizeof(urepl->name)) || __copy_to_user(repl_nat->name, name, sizeof(repl_nat->name))) goto out; if (__get_user(tmp32, &urepl->valid_hooks) || __put_user(tmp32, &repl_nat->valid_hooks)) goto out; if (__get_user(tmp32, &urepl->num_entries) || __put_user(tmp32, &repl_nat->num_entries)) goto out; if (__get_user(num_counters, &urepl->num_counters) || __put_user(num_counters, &repl_nat->num_counters)) goto out; if (__get_user(ucntrs, &urepl->counters) || __put_user(compat_ptr(ucntrs), &repl_nat->counters)) goto out; if (__copy_in_user(&repl_nat->entries[0], &urepl->entries[0], origsize)) goto out; for (i = 0; i < NF_IP_NUMHOOKS; i++) { if (__get_user(tmp32, &urepl->hook_entry[i]) || __put_user(tmp32, &repl_nat->hook_entry[i]) || __get_user(tmp32, &urepl->underflow[i]) || __put_user(tmp32, &repl_nat->underflow[i])) goto out; } /* * Since struct ipt_counters just contains two u_int64_t members * we can just do the access_ok check here and pass the (converted) * pointer into the standard syscall. We hope that the pointer is * not misaligned ... */ if (!access_ok(VERIFY_WRITE, compat_ptr(ucntrs), num_counters * sizeof(struct ipt_counters))) goto out; ret = sys_setsockopt(fd, level, optname, (char __user *)repl_nat, repl_nat_size); out: return ret; } /* * A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; static int do_set_attach_filter(struct socket *sock, int level, int optname, char __user *optval, int optlen) { struct compat_sock_fprog __user *fprog32 = (struct compat_sock_fprog __user *)optval; struct sock_fprog __user *kfprog = compat_alloc_user_space(sizeof(struct sock_fprog)); compat_uptr_t ptr; u16 len; if (!access_ok(VERIFY_READ, fprog32, sizeof(*fprog32)) || !access_ok(VERIFY_WRITE, kfprog, sizeof(struct sock_fprog)) || __get_user(len, &fprog32->len) || __get_user(ptr, &fprog32->filter) || __put_user(len, &kfprog->len) || __put_user(compat_ptr(ptr), &kfprog->filter)) return -EFAULT; return sock_setsockopt(sock, level, optname, (char __user *)kfprog, sizeof(struct sock_fprog)); } static int do_set_sock_timeout(struct socket *sock, int level, int optname, char __user *optval, int optlen) { struct compat_timeval __user *up = (struct compat_timeval __user *) optval; struct timeval ktime; mm_segment_t old_fs; int err; if (optlen < sizeof(*up)) return -EINVAL; if (!access_ok(VERIFY_READ, up, sizeof(*up)) || __get_user(ktime.tv_sec, &up->tv_sec) || __get_user(ktime.tv_usec, &up->tv_usec)) return -EFAULT; old_fs = get_fs(); set_fs(KERNEL_DS); err = sock_setsockopt(sock, level, optname, (char *) &ktime, sizeof(ktime)); set_fs(old_fs); return err; } static int compat_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { if (optname == SO_ATTACH_FILTER) return do_set_attach_filter(sock, level, optname, optval, optlen); if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) return do_set_sock_timeout(sock, level, optname, optval, optlen); return sock_setsockopt(sock, level, optname, optval, optlen); } asmlinkage long compat_sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { int err; struct socket *sock; if (level == SOL_IPV6 && optname == IPT_SO_SET_REPLACE) return do_netfilter_replace(fd, level, optname, optval, optlen); if (optlen < 0) return -EINVAL; if ((sock = sockfd_lookup(fd, &err))!=NULL) { err = security_socket_setsockopt(sock,level,optname); if (err) { sockfd_put(sock); return err; } if (level == SOL_SOCKET) err = compat_sock_setsockopt(sock, level, optname, optval, optlen); else if (sock->ops->compat_setsockopt) err = sock->ops->compat_setsockopt(sock, level, optname, optval, optlen); else err = sock->ops->setsockopt(sock, level, optname, optval, optlen); sockfd_put(sock); } return err; } static int do_get_sock_timeout(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { struct compat_timeval __user *up; struct timeval ktime; mm_segment_t old_fs; int len, err; up = (struct compat_timeval __user *) optval; if (get_user(len, optlen)) return -EFAULT; if (len < sizeof(*up)) return -EINVAL; len = sizeof(ktime); old_fs = get_fs(); set_fs(KERNEL_DS); err = sock_getsockopt(sock, level, optname, (char *) &ktime, &len); set_fs(old_fs); if (!err) { if (put_user(sizeof(*up), optlen) || !access_ok(VERIFY_WRITE, up, sizeof(*up)) || __put_user(ktime.tv_sec, &up->tv_sec) || __put_user(ktime.tv_usec, &up->tv_usec)) err = -EFAULT; } return err; } static int compat_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) return do_get_sock_timeout(sock, level, optname, optval, optlen); return sock_getsockopt(sock, level, optname, optval, optlen); } int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct compat_timeval __user *ctv = (struct compat_timeval __user*) userstamp; int err = -ENOENT; struct timeval tv; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk); tv = ktime_to_timeval(sk->sk_stamp); if (tv.tv_sec == -1) return err; if (tv.tv_sec == 0) { sk->sk_stamp = ktime_get_real(); tv = ktime_to_timeval(sk->sk_stamp); } err = 0; if (put_user(tv.tv_sec, &ctv->tv_sec) || put_user(tv.tv_usec, &ctv->tv_usec)) err = -EFAULT; return err; } EXPORT_SYMBOL(compat_sock_get_timestamp); int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp) { struct compat_timespec __user *ctv = (struct compat_timespec __user*) userstamp; int err = -ENOENT; struct timespec ts; if (!sock_flag(sk, SOCK_TIMESTAMP)) sock_enable_timestamp(sk); ts = ktime_to_timespec(sk->sk_stamp); if (ts.tv_sec == -1) return err; if (ts.tv_sec == 0) { sk->sk_stamp = ktime_get_real(); ts = ktime_to_timespec(sk->sk_stamp); } err = 0; if (put_user(ts.tv_sec, &ctv->tv_sec) || put_user(ts.tv_nsec, &ctv->tv_nsec)) err = -EFAULT; return err; } EXPORT_SYMBOL(compat_sock_get_timestampns); asmlinkage long compat_sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { int err; struct socket *sock; if ((sock = sockfd_lookup(fd, &err))!=NULL) { err = security_socket_getsockopt(sock, level, optname); if (err) { sockfd_put(sock); return err; } if (level == SOL_SOCKET) err = compat_sock_getsockopt(sock, level, optname, optval, optlen); else if (sock->ops->compat_getsockopt) err = sock->ops->compat_getsockopt(sock, level, optname, optval, optlen); else err = sock->ops->getsockopt(sock, level, optname, optval, optlen); sockfd_put(sock); } return err; } /* Argument list sizes for compat_sys_socketcall */ #define AL(x) ((x) * sizeof(u32)) static unsigned char nas[18]={AL(0),AL(3),AL(3),AL(3),AL(2),AL(3), AL(3),AL(3),AL(4),AL(4),AL(4),AL(6), AL(6),AL(2),AL(5),AL(5),AL(3),AL(3)}; #undef AL asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg, unsigned flags) { return sys_sendmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg, unsigned int flags) { return sys_recvmsg(fd, (struct msghdr __user *)msg, flags | MSG_CMSG_COMPAT); } asmlinkage long compat_sys_socketcall(int call, u32 __user *args) { int ret; u32 a[6]; u32 a0, a1; if (call < SYS_SOCKET || call > SYS_RECVMSG) return -EINVAL; if (copy_from_user(a, args, nas[call])) return -EFAULT; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: ret = sys_socket(a0, a1, a[2]); break; case SYS_BIND: ret = sys_bind(a0, compat_ptr(a1), a[2]); break; case SYS_CONNECT: ret = sys_connect(a0, compat_ptr(a1), a[2]); break; case SYS_LISTEN: ret = sys_listen(a0, a1); break; case SYS_ACCEPT: ret = sys_accept(a0, compat_ptr(a1), compat_ptr(a[2])); break; case SYS_GETSOCKNAME: ret = sys_getsockname(a0, compat_ptr(a1), compat_ptr(a[2])); break; case SYS_GETPEERNAME: ret = sys_getpeername(a0, compat_ptr(a1), compat_ptr(a[2])); break; case SYS_SOCKETPAIR: ret = sys_socketpair(a0, a1, a[2], compat_ptr(a[3])); break; case SYS_SEND: ret = sys_send(a0, compat_ptr(a1), a[2], a[3]); break; case SYS_SENDTO: ret = sys_sendto(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), a[5]); break; case SYS_RECV: ret = sys_recv(a0, compat_ptr(a1), a[2], a[3]); break; case SYS_RECVFROM: ret = sys_recvfrom(a0, compat_ptr(a1), a[2], a[3], compat_ptr(a[4]), compat_ptr(a[5])); break; case SYS_SHUTDOWN: ret = sys_shutdown(a0,a1); break; case SYS_SETSOCKOPT: ret = compat_sys_setsockopt(a0, a1, a[2], compat_ptr(a[3]), a[4]); break; case SYS_GETSOCKOPT: ret = compat_sys_getsockopt(a0, a1, a[2], compat_ptr(a[3]), compat_ptr(a[4])); break; case SYS_SENDMSG: ret = compat_sys_sendmsg(a0, compat_ptr(a1), a[2]); break; case SYS_RECVMSG: ret = compat_sys_recvmsg(a0, compat_ptr(a1), a[2]); break; default: ret = -EINVAL; break; } return ret; }