diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-03 06:22:12 +0200 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-04-03 06:22:12 +0200 |
commit | 642e7fd23353e22290e3d51719fcb658dc252342 (patch) | |
tree | 93688d5ff15836d8e5b0e097748f7fabb13a303a /net/socket.c | |
parent | bitmap: fix memset optimization on big-endian systems (diff) | |
parent | bpf: whitelist all syscalls for error injection (diff) | |
download | linux-642e7fd23353e22290e3d51719fcb658dc252342.tar.xz linux-642e7fd23353e22290e3d51719fcb658dc252342.zip |
Merge branch 'syscalls-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux
Pull removal of in-kernel calls to syscalls from Dominik Brodowski:
"System calls are interaction points between userspace and the kernel.
Therefore, system call functions such as sys_xyzzy() or
compat_sys_xyzzy() should only be called from userspace via the
syscall table, but not from elsewhere in the kernel.
At least on 64-bit x86, it will likely be a hard requirement from
v4.17 onwards to not call system call functions in the kernel: It is
better to use use a different calling convention for system calls
there, where struct pt_regs is decoded on-the-fly in a syscall wrapper
which then hands processing over to the actual syscall function. This
means that only those parameters which are actually needed for a
specific syscall are passed on during syscall entry, instead of
filling in six CPU registers with random user space content all the
time (which may cause serious trouble down the call chain). Those
x86-specific patches will be pushed through the x86 tree in the near
future.
Moreover, rules on how data may be accessed may differ between kernel
data and user data. This is another reason why calling sys_xyzzy() is
generally a bad idea, and -- at most -- acceptable in arch-specific
code.
This patchset removes all in-kernel calls to syscall functions in the
kernel with the exception of arch/. On top of this, it cleans up the
three places where many syscalls are referenced or prototyped, namely
kernel/sys_ni.c, include/linux/syscalls.h and include/linux/compat.h"
* 'syscalls-next' of git://git.kernel.org/pub/scm/linux/kernel/git/brodo/linux: (109 commits)
bpf: whitelist all syscalls for error injection
kernel/sys_ni: remove {sys_,sys_compat} from cond_syscall definitions
kernel/sys_ni: sort cond_syscall() entries
syscalls/x86: auto-create compat_sys_*() prototypes
syscalls: sort syscall prototypes in include/linux/compat.h
net: remove compat_sys_*() prototypes from net/compat.h
syscalls: sort syscall prototypes in include/linux/syscalls.h
kexec: move sys_kexec_load() prototype to syscalls.h
x86/sigreturn: use SYSCALL_DEFINE0
x86: fix sys_sigreturn() return type to be long, not unsigned long
x86/ioport: add ksys_ioperm() helper; remove in-kernel calls to sys_ioperm()
mm: add ksys_readahead() helper; remove in-kernel calls to sys_readahead()
mm: add ksys_mmap_pgoff() helper; remove in-kernel calls to sys_mmap_pgoff()
mm: add ksys_fadvise64_64() helper; remove in-kernel call to sys_fadvise64_64()
fs: add ksys_fallocate() wrapper; remove in-kernel calls to sys_fallocate()
fs: add ksys_p{read,write}64() helpers; remove in-kernel calls to syscalls
fs: add ksys_truncate() wrapper; remove in-kernel calls to sys_truncate()
fs: add ksys_sync_file_range helper(); remove in-kernel calls to syscall
kernel: add ksys_setsid() helper; remove in-kernel call to sys_setsid()
kernel: add ksys_unshare() helper; remove in-kernel calls to sys_unshare()
...
Diffstat (limited to 'net/socket.c')
-rw-r--r-- | net/socket.c | 234 |
1 files changed, 161 insertions, 73 deletions
diff --git a/net/socket.c b/net/socket.c index 08847c3b8c39..4ba9fc631c43 100644 --- a/net/socket.c +++ b/net/socket.c @@ -1332,7 +1332,7 @@ int sock_create_kern(struct net *net, int family, int type, int protocol, struct } EXPORT_SYMBOL(sock_create_kern); -SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) +int __sys_socket(int family, int type, int protocol) { int retval; struct socket *sock; @@ -1359,12 +1359,16 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } +SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) +{ + return __sys_socket(family, type, protocol); +} + /* * Create a pair of connected sockets. */ -SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, - int __user *, usockvec) +int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; @@ -1449,6 +1453,12 @@ out: return err; } +SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, + int __user *, usockvec) +{ + return __sys_socketpair(family, type, protocol, usockvec); +} + /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. @@ -1457,7 +1467,7 @@ out: * the protocol layer (having also checked the address is ok). */ -SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) +int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; @@ -1480,13 +1490,18 @@ SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) return err; } +SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) +{ + return __sys_bind(fd, umyaddr, addrlen); +} + /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ -SYSCALL_DEFINE2(listen, int, fd, int, backlog) +int __sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; @@ -1507,6 +1522,11 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) return err; } +SYSCALL_DEFINE2(listen, int, fd, int, backlog) +{ + return __sys_listen(fd, backlog); +} + /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new @@ -1519,8 +1539,8 @@ SYSCALL_DEFINE2(listen, int, fd, int, backlog) * clean when we restucture accept also. */ -SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, - int __user *, upeer_addrlen, int, flags) +int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, + int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; @@ -1599,10 +1619,16 @@ out_fd: goto out_put; } +SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, + int __user *, upeer_addrlen, int, flags) +{ + return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); +} + SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { - return sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); + return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* @@ -1617,8 +1643,7 @@ SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, * include the -EINPROGRESS status for such sockets. */ -SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, - int, addrlen) +int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; @@ -1644,13 +1669,19 @@ out: return err; } +SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, + int, addrlen) +{ + return __sys_connect(fd, uservaddr, addrlen); +} + /* * Get the local address ('name') of a socket object. Move the obtained * name to user space. */ -SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, - int __user *, usockaddr_len) +int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; @@ -1675,13 +1706,19 @@ out: return err; } +SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) +{ + return __sys_getsockname(fd, usockaddr, usockaddr_len); +} + /* * Get the remote address ('name') of a socket object. Move the obtained * name to user space. */ -SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, - int __user *, usockaddr_len) +int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, + int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; @@ -1706,15 +1743,19 @@ SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, return err; } +SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, + int __user *, usockaddr_len) +{ + return __sys_getpeername(fd, usockaddr, usockaddr_len); +} + /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ - -SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, - unsigned int, flags, struct sockaddr __user *, addr, - int, addr_len) +int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, + struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; @@ -1752,6 +1793,13 @@ out: return err; } +SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, + unsigned int, flags, struct sockaddr __user *, addr, + int, addr_len) +{ + return __sys_sendto(fd, buff, len, flags, addr, addr_len); +} + /* * Send a datagram down a socket. */ @@ -1759,7 +1807,7 @@ out: SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { - return sys_sendto(fd, buff, len, flags, NULL, 0); + return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* @@ -1767,10 +1815,8 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ - -SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, - unsigned int, flags, struct sockaddr __user *, addr, - int __user *, addr_len) +int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, + struct sockaddr __user *addr, int __user *addr_len) { struct socket *sock; struct iovec iov; @@ -1810,6 +1856,13 @@ out: return err; } +SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, + unsigned int, flags, struct sockaddr __user *, addr, + int __user *, addr_len) +{ + return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); +} + /* * Receive a datagram from a socket. */ @@ -1817,7 +1870,7 @@ out: SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { - return sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); + return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } /* @@ -1825,8 +1878,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, * to pass the user mode parameter for the protocols to sort out. */ -SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, - char __user *, optval, int, optlen) +static int __sys_setsockopt(int fd, int level, int optname, + char __user *optval, int optlen) { int err, fput_needed; struct socket *sock; @@ -1854,13 +1907,19 @@ out_put: return err; } +SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, + char __user *, optval, int, optlen) +{ + return __sys_setsockopt(fd, level, optname, optval, optlen); +} + /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ -SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, - char __user *, optval, int __user *, optlen) +static int __sys_getsockopt(int fd, int level, int optname, + char __user *optval, int __user *optlen) { int err, fput_needed; struct socket *sock; @@ -1885,11 +1944,17 @@ out_put: return err; } +SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, + char __user *, optval, int __user *, optlen) +{ + return __sys_getsockopt(fd, level, optname, optval, optlen); +} + /* * Shutdown a socket. */ -SYSCALL_DEFINE2(shutdown, int, fd, int, how) +int __sys_shutdown(int fd, int how) { int err, fput_needed; struct socket *sock; @@ -1904,6 +1969,11 @@ SYSCALL_DEFINE2(shutdown, int, fd, int, how) return err; } +SYSCALL_DEFINE2(shutdown, int, fd, int, how) +{ + return __sys_shutdown(fd, how); +} + /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ @@ -2067,12 +2137,16 @@ out_freeiov: * BSD sendmsg interface */ -long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags) +long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, + bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -2086,9 +2160,7 @@ out: SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_sendmsg(fd, msg, flags); + return __sys_sendmsg(fd, msg, flags, true); } /* @@ -2096,7 +2168,7 @@ SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, - unsigned int flags) + unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err, datagrams; struct socket *sock; @@ -2106,6 +2178,9 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, struct used_address used_address; unsigned int oflags = flags; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; + if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; @@ -2162,9 +2237,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_sendmmsg(fd, mmsg, vlen, flags); + return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, @@ -2237,12 +2310,16 @@ out_freeiov: * BSD recvmsg interface */ -long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned flags) +long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, + bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; + if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) + return -EINVAL; + sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; @@ -2257,9 +2334,7 @@ out: SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { - if (flags & MSG_CMSG_COMPAT) - return -EINVAL; - return __sys_recvmsg(fd, msg, flags); + return __sys_recvmsg(fd, msg, flags, true); } /* @@ -2375,9 +2450,9 @@ out_put: return datagrams; } -SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, - unsigned int, vlen, unsigned int, flags, - struct timespec __user *, timeout) +static int do_sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, + unsigned int vlen, unsigned int flags, + struct timespec __user *timeout) { int datagrams; struct timespec timeout_sys; @@ -2400,6 +2475,13 @@ SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, return datagrams; } +SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, + unsigned int, vlen, unsigned int, flags, + struct timespec __user *, timeout) +{ + return do_sys_recvmmsg(fd, mmsg, vlen, flags, timeout); +} + #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) @@ -2447,76 +2529,82 @@ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) switch (call) { case SYS_SOCKET: - err = sys_socket(a0, a1, a[2]); + err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: - err = sys_bind(a0, (struct sockaddr __user *)a1, a[2]); + err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: - err = sys_connect(a0, (struct sockaddr __user *)a1, a[2]); + err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: - err = sys_listen(a0, a1); + err = __sys_listen(a0, a1); break; case SYS_ACCEPT: - err = sys_accept4(a0, (struct sockaddr __user *)a1, - (int __user *)a[2], 0); + err = __sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = - sys_getsockname(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + __sys_getsockname(a0, (struct sockaddr __user *)a1, + (int __user *)a[2]); break; case SYS_GETPEERNAME: err = - sys_getpeername(a0, (struct sockaddr __user *)a1, - (int __user *)a[2]); + __sys_getpeername(a0, (struct sockaddr __user *)a1, + (int __user *)a[2]); break; case SYS_SOCKETPAIR: - err = sys_socketpair(a0, a1, a[2], (int __user *)a[3]); + err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: - err = sys_send(a0, (void __user *)a1, a[2], a[3]); + err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], + NULL, 0); break; case SYS_SENDTO: - err = sys_sendto(a0, (void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], a[5]); + err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: - err = sys_recv(a0, (void __user *)a1, a[2], a[3]); + err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], + NULL, NULL); break; case SYS_RECVFROM: - err = sys_recvfrom(a0, (void __user *)a1, a[2], a[3], - (struct sockaddr __user *)a[4], - (int __user *)a[5]); + err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], + (struct sockaddr __user *)a[4], + (int __user *)a[5]); break; case SYS_SHUTDOWN: - err = sys_shutdown(a0, a1); + err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: - err = sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); + err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], + a[4]); break; case SYS_GETSOCKOPT: err = - sys_getsockopt(a0, a1, a[2], (char __user *)a[3], - (int __user *)a[4]); + __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], + (int __user *)a[4]); break; case SYS_SENDMSG: - err = sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2]); + err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, + a[2], true); break; case SYS_SENDMMSG: - err = sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3]); + err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], + a[3], true); break; case SYS_RECVMSG: - err = sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2]); + err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, + a[2], true); break; case SYS_RECVMMSG: - err = sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], - (struct timespec __user *)a[4]); + err = do_sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], + a[3], (struct timespec __user *)a[4]); break; case SYS_ACCEPT4: - err = sys_accept4(a0, (struct sockaddr __user *)a1, - (int __user *)a[2], a[3]); + err = __sys_accept4(a0, (struct sockaddr __user *)a1, + (int __user *)a[2], a[3]); break; default: err = -EINVAL; |