OpenCloudOS-Kernel/include/linux/socket.h

344 lines
11 KiB
C
Raw Normal View History

#ifndef _LINUX_SOCKET_H
#define _LINUX_SOCKET_H
/*
* Desired design of maximum size and alignment (see RFC2553)
*/
#define _K_SS_MAXSIZE 128 /* Implementation specific max size */
#define _K_SS_ALIGNSIZE (__alignof__ (struct sockaddr *))
/* Implementation specific desired alignment */
typedef unsigned short __kernel_sa_family_t;
struct __kernel_sockaddr_storage {
__kernel_sa_family_t ss_family; /* address family */
/* Following field(s) are implementation specific */
char __data[_K_SS_MAXSIZE - sizeof(unsigned short)];
/* space to achieve desired size, */
/* _SS_MAXSIZE value minus size of ss_family */
} __attribute__ ((aligned(_K_SS_ALIGNSIZE))); /* force desired alignment */
#ifdef __KERNEL__
#include <asm/socket.h> /* arch-dependent defines */
#include <linux/sockios.h> /* the SIOCxxx I/O controls */
#include <linux/uio.h> /* iovec support */
#include <linux/types.h> /* pid_t */
#include <linux/compiler.h> /* __user */
struct pid;
struct cred;
#define __sockaddr_check_size(size) \
BUILD_BUG_ON(((size) > sizeof(struct __kernel_sockaddr_storage)))
#ifdef CONFIG_PROC_FS
struct seq_file;
extern void socket_seq_show(struct seq_file *seq);
#endif
typedef __kernel_sa_family_t sa_family_t;
/*
* 1003.1g requires sa_family_t and that sa_data is char.
*/
struct sockaddr {
sa_family_t sa_family; /* address family, AF_xxx */
char sa_data[14]; /* 14 bytes of protocol address */
};
struct linger {
int l_onoff; /* Linger active */
int l_linger; /* How long to linger for */
};
#define sockaddr_storage __kernel_sockaddr_storage
/*
* As we do 4.4BSD message passing we use a 4.4BSD message passing
* system, not 4.3. Thus msg_accrights(len) are now missing. They
* belong in an obscure libc emulation or the bin.
*/
struct msghdr {
void * msg_name; /* Socket name */
int msg_namelen; /* Length of name */
struct iovec * msg_iov; /* Data blocks */
__kernel_size_t msg_iovlen; /* Number of blocks */
void * msg_control; /* Per protocol magic (eg BSD file descriptor passing) */
__kernel_size_t msg_controllen; /* Length of cmsg list */
unsigned msg_flags;
};
/* For recvmmsg/sendmmsg */
struct mmsghdr {
struct msghdr msg_hdr;
unsigned msg_len;
};
/*
* POSIX 1003.1g - ancillary data object information
* Ancillary data consits of a sequence of pairs of
* (cmsghdr, cmsg_data[])
*/
struct cmsghdr {
__kernel_size_t cmsg_len; /* data byte count, including hdr */
int cmsg_level; /* originating protocol */
int cmsg_type; /* protocol-specific type */
};
/*
* Ancillary data object information MACROS
* Table 5-14 of POSIX 1003.1g
*/
#define __CMSG_NXTHDR(ctl, len, cmsg) __cmsg_nxthdr((ctl),(len),(cmsg))
#define CMSG_NXTHDR(mhdr, cmsg) cmsg_nxthdr((mhdr), (cmsg))
#define CMSG_ALIGN(len) ( ((len)+sizeof(long)-1) & ~(sizeof(long)-1) )
#define CMSG_DATA(cmsg) ((void *)((char *)(cmsg) + CMSG_ALIGN(sizeof(struct cmsghdr))))
#define CMSG_SPACE(len) (CMSG_ALIGN(sizeof(struct cmsghdr)) + CMSG_ALIGN(len))
#define CMSG_LEN(len) (CMSG_ALIGN(sizeof(struct cmsghdr)) + (len))
#define __CMSG_FIRSTHDR(ctl,len) ((len) >= sizeof(struct cmsghdr) ? \
(struct cmsghdr *)(ctl) : \
(struct cmsghdr *)NULL)
#define CMSG_FIRSTHDR(msg) __CMSG_FIRSTHDR((msg)->msg_control, (msg)->msg_controllen)
#define CMSG_OK(mhdr, cmsg) ((cmsg)->cmsg_len >= sizeof(struct cmsghdr) && \
(cmsg)->cmsg_len <= (unsigned long) \
((mhdr)->msg_controllen - \
((char *)(cmsg) - (char *)(mhdr)->msg_control)))
/*
* Get the next cmsg header
*
* PLEASE, do not touch this function. If you think, that it is
* incorrect, grep kernel sources and think about consequences
* before trying to improve it.
*
* Now it always returns valid, not truncated ancillary object
* HEADER. But caller still MUST check, that cmsg->cmsg_len is
* inside range, given by msg->msg_controllen before using
* ancillary object DATA. --ANK (980731)
*/
static inline struct cmsghdr * __cmsg_nxthdr(void *__ctl, __kernel_size_t __size,
struct cmsghdr *__cmsg)
{
struct cmsghdr * __ptr;
__ptr = (struct cmsghdr*)(((unsigned char *) __cmsg) + CMSG_ALIGN(__cmsg->cmsg_len));
if ((unsigned long)((char*)(__ptr+1) - (char *) __ctl) > __size)
return (struct cmsghdr *)0;
return __ptr;
}
static inline struct cmsghdr * cmsg_nxthdr (struct msghdr *__msg, struct cmsghdr *__cmsg)
{
return __cmsg_nxthdr(__msg->msg_control, __msg->msg_controllen, __cmsg);
}
/* "Socket"-level control message types: */
#define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */
#define SCM_CREDENTIALS 0x02 /* rw: struct ucred */
[SECURITY]: TCP/UDP getpeersec This patch implements an application of the LSM-IPSec networking controls whereby an application can determine the label of the security association its TCP or UDP sockets are currently connected to via getsockopt and the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of an IPSec security association a particular TCP or UDP socket is using. The application can then use this security context to determine the security context for processing on behalf of the peer at the other end of this connection. In the case of UDP, the security context is for each individual packet. An example application is the inetd daemon, which could be modified to start daemons running at security contexts dependent on the remote client. Patch design approach: - Design for TCP The patch enables the SELinux LSM to set the peer security context for a socket based on the security context of the IPSec security association. The application may retrieve this context using getsockopt. When called, the kernel determines if the socket is a connected (TCP_ESTABLISHED) TCP socket and, if so, uses the dst_entry cache on the socket to retrieve the security associations. If a security association has a security context, the context string is returned, as for UNIX domain sockets. - Design for UDP Unlike TCP, UDP is connectionless. This requires a somewhat different API to retrieve the peer security context. With TCP, the peer security context stays the same throughout the connection, thus it can be retrieved at any time between when the connection is established and when it is torn down. With UDP, each read/write can have different peer and thus the security context might change every time. As a result the security context retrieval must be done TOGETHER with the packet retrieval. The solution is to build upon the existing Unix domain socket API for retrieving user credentials. Linux offers the API for obtaining user credentials via ancillary messages (i.e., out of band/control messages that are bundled together with a normal message). Patch implementation details: - Implementation for TCP The security context can be retrieved by applications using getsockopt with the existing SO_PEERSEC flag. As an example (ignoring error checking): getsockopt(sockfd, SOL_SOCKET, SO_PEERSEC, optbuf, &optlen); printf("Socket peer context is: %s\n", optbuf); The SELinux function, selinux_socket_getpeersec, is extended to check for labeled security associations for connected (TCP_ESTABLISHED == sk->sk_state) TCP sockets only. If so, the socket has a dst_cache of struct dst_entry values that may refer to security associations. If these have security associations with security contexts, the security context is returned. getsockopt returns a buffer that contains a security context string or the buffer is unmodified. - Implementation for UDP To retrieve the security context, the application first indicates to the kernel such desire by setting the IP_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for UDP should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_IP, IP_PASSSEC, &toggle, &toggle_len); recvmsg(sockfd, &msg_hdr, 0); if (msg_hdr.msg_controllen > sizeof(struct cmsghdr)) { cmsg_hdr = CMSG_FIRSTHDR(&msg_hdr); if (cmsg_hdr->cmsg_len <= CMSG_LEN(sizeof(scontext)) && cmsg_hdr->cmsg_level == SOL_IP && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } ip_setsockopt is enhanced with a new socket option IP_PASSSEC to allow a server socket to receive security context of the peer. A new ancillary message type SCM_SECURITY. When the packet is received we get the security context from the sec_path pointer which is contained in the sk_buff, and copy it to the ancillary message space. An additional LSM hook, selinux_socket_getpeersec_udp, is defined to retrieve the security context from the SELinux space. The existing function, selinux_socket_getpeersec does not suit our purpose, because the security context is copied directly to user space, rather than to kernel space. Testing: We have tested the patch by setting up TCP and UDP connections between applications on two machines using the IPSec policies that result in labeled security associations being built. For TCP, we can then extract the peer security context using getsockopt on either end. For UDP, the receiving end can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: James Morris <jmorris@namei.org> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-21 14:41:23 +08:00
#define SCM_SECURITY 0x03 /* rw: security label */
struct ucred {
__u32 pid;
__u32 uid;
__u32 gid;
};
/* Supported address families. */
#define AF_UNSPEC 0
#define AF_UNIX 1 /* Unix domain sockets */
#define AF_LOCAL 1 /* POSIX name for AF_UNIX */
#define AF_INET 2 /* Internet IP Protocol */
#define AF_AX25 3 /* Amateur Radio AX.25 */
#define AF_IPX 4 /* Novell IPX */
#define AF_APPLETALK 5 /* AppleTalk DDP */
#define AF_NETROM 6 /* Amateur Radio NET/ROM */
#define AF_BRIDGE 7 /* Multiprotocol bridge */
#define AF_ATMPVC 8 /* ATM PVCs */
#define AF_X25 9 /* Reserved for X.25 project */
#define AF_INET6 10 /* IP version 6 */
#define AF_ROSE 11 /* Amateur Radio X.25 PLP */
#define AF_DECnet 12 /* Reserved for DECnet project */
#define AF_NETBEUI 13 /* Reserved for 802.2LLC project*/
#define AF_SECURITY 14 /* Security callback pseudo AF */
#define AF_KEY 15 /* PF_KEY key management API */
#define AF_NETLINK 16
#define AF_ROUTE AF_NETLINK /* Alias to emulate 4.4BSD */
#define AF_PACKET 17 /* Packet family */
#define AF_ASH 18 /* Ash */
#define AF_ECONET 19 /* Acorn Econet */
#define AF_ATMSVC 20 /* ATM SVCs */
#define AF_RDS 21 /* RDS sockets */
#define AF_SNA 22 /* Linux SNA Project (nutters!) */
#define AF_IRDA 23 /* IRDA sockets */
#define AF_PPPOX 24 /* PPPoX sockets */
#define AF_WANPIPE 25 /* Wanpipe API Sockets */
#define AF_LLC 26 /* Linux LLC */
#define AF_CAN 29 /* Controller Area Network */
#define AF_TIPC 30 /* TIPC sockets */
#define AF_BLUETOOTH 31 /* Bluetooth sockets */
#define AF_IUCV 32 /* IUCV sockets */
#define AF_RXRPC 33 /* RxRPC sockets */
#define AF_ISDN 34 /* mISDN sockets */
#define AF_PHONET 35 /* Phonet sockets */
#define AF_IEEE802154 36 /* IEEE802154 sockets */
#define AF_CAIF 37 /* CAIF sockets */
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
#define AF_MAX 40 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
#define PF_UNIX AF_UNIX
#define PF_LOCAL AF_LOCAL
#define PF_INET AF_INET
#define PF_AX25 AF_AX25
#define PF_IPX AF_IPX
#define PF_APPLETALK AF_APPLETALK
#define PF_NETROM AF_NETROM
#define PF_BRIDGE AF_BRIDGE
#define PF_ATMPVC AF_ATMPVC
#define PF_X25 AF_X25
#define PF_INET6 AF_INET6
#define PF_ROSE AF_ROSE
#define PF_DECnet AF_DECnet
#define PF_NETBEUI AF_NETBEUI
#define PF_SECURITY AF_SECURITY
#define PF_KEY AF_KEY
#define PF_NETLINK AF_NETLINK
#define PF_ROUTE AF_ROUTE
#define PF_PACKET AF_PACKET
#define PF_ASH AF_ASH
#define PF_ECONET AF_ECONET
#define PF_ATMSVC AF_ATMSVC
#define PF_RDS AF_RDS
#define PF_SNA AF_SNA
#define PF_IRDA AF_IRDA
#define PF_PPPOX AF_PPPOX
#define PF_WANPIPE AF_WANPIPE
#define PF_LLC AF_LLC
#define PF_CAN AF_CAN
#define PF_TIPC AF_TIPC
#define PF_BLUETOOTH AF_BLUETOOTH
#define PF_IUCV AF_IUCV
#define PF_RXRPC AF_RXRPC
#define PF_ISDN AF_ISDN
#define PF_PHONET AF_PHONET
#define PF_IEEE802154 AF_IEEE802154
#define PF_CAIF AF_CAIF
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
#define SOMAXCONN 128
/* Flags we can use with send/ and recv.
Added those for 1003.1g not all are supported yet
*/
#define MSG_OOB 1
#define MSG_PEEK 2
#define MSG_DONTROUTE 4
#define MSG_TRYHARD 4 /* Synonym for MSG_DONTROUTE for DECnet */
#define MSG_CTRUNC 8
#define MSG_PROBE 0x10 /* Do not send. Only probe path f.e. for MTU */
#define MSG_TRUNC 0x20
#define MSG_DONTWAIT 0x40 /* Nonblocking io */
#define MSG_EOR 0x80 /* End of record */
#define MSG_WAITALL 0x100 /* Wait for a full request */
#define MSG_FIN 0x200
#define MSG_SYN 0x400
#define MSG_CONFIRM 0x800 /* Confirm path validity */
#define MSG_RST 0x1000
#define MSG_ERRQUEUE 0x2000 /* Fetch message from error queue */
#define MSG_NOSIGNAL 0x4000 /* Do not generate SIGPIPE */
#define MSG_MORE 0x8000 /* Sender will send more */
#define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */
#define MSG_EOF MSG_FIN
O_CLOEXEC for SCM_RIGHTS Part two in the O_CLOEXEC saga: adding support for file descriptors received through Unix domain sockets. The patch is once again pretty minimal, it introduces a new flag for recvmsg and passes it just like the existing MSG_CMSG_COMPAT flag. I think this bit is not used otherwise but the networking people will know better. This new flag is not recognized by recvfrom and recv. These functions cannot be used for that purpose and the asymmetry this introduces is not worse than the already existing MSG_CMSG_COMPAT situations. The patch must be applied on the patch which introduced O_CLOEXEC. It has to remove static from the new get_unused_fd_flags function but since scm.c cannot live in a module the function still hasn't to be exported. Here's a test program to make sure the code works. It's so much longer than the actual patch... #include <errno.h> #include <error.h> #include <fcntl.h> #include <stdio.h> #include <string.h> #include <unistd.h> #include <sys/socket.h> #include <sys/un.h> #ifndef O_CLOEXEC # define O_CLOEXEC 02000000 #endif #ifndef MSG_CMSG_CLOEXEC # define MSG_CMSG_CLOEXEC 0x40000000 #endif int main (int argc, char *argv[]) { if (argc > 1) { int fd = atol (argv[1]); printf ("child: fd = %d\n", fd); if (fcntl (fd, F_GETFD) == 0 || errno != EBADF) { puts ("file descriptor valid in child"); return 1; } return 0; } struct sockaddr_un sun; strcpy (sun.sun_path, "./testsocket"); sun.sun_family = AF_UNIX; char databuf[] = "hello"; struct iovec iov[1]; iov[0].iov_base = databuf; iov[0].iov_len = sizeof (databuf); union { struct cmsghdr hdr; char bytes[CMSG_SPACE (sizeof (int))]; } buf; struct msghdr msg = { .msg_iov = iov, .msg_iovlen = 1, .msg_control = buf.bytes, .msg_controllen = sizeof (buf) }; struct cmsghdr *cmsg = CMSG_FIRSTHDR (&msg); cmsg->cmsg_level = SOL_SOCKET; cmsg->cmsg_type = SCM_RIGHTS; cmsg->cmsg_len = CMSG_LEN (sizeof (int)); msg.msg_controllen = cmsg->cmsg_len; pid_t child = fork (); if (child == -1) error (1, errno, "fork"); if (child == 0) { int sock = socket (PF_UNIX, SOCK_STREAM, 0); if (sock < 0) error (1, errno, "socket"); if (bind (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0) error (1, errno, "bind"); if (listen (sock, SOMAXCONN) < 0) error (1, errno, "listen"); int conn = accept (sock, NULL, NULL); if (conn == -1) error (1, errno, "accept"); *(int *) CMSG_DATA (cmsg) = sock; if (sendmsg (conn, &msg, MSG_NOSIGNAL) < 0) error (1, errno, "sendmsg"); return 0; } /* For a test suite this should be more robust like a barrier in shared memory. */ sleep (1); int sock = socket (PF_UNIX, SOCK_STREAM, 0); if (sock < 0) error (1, errno, "socket"); if (connect (sock, (struct sockaddr *) &sun, sizeof (sun)) < 0) error (1, errno, "connect"); unlink (sun.sun_path); *(int *) CMSG_DATA (cmsg) = -1; if (recvmsg (sock, &msg, MSG_CMSG_CLOEXEC) < 0) error (1, errno, "recvmsg"); int fd = *(int *) CMSG_DATA (cmsg); if (fd == -1) error (1, 0, "no descriptor received"); char fdname[20]; snprintf (fdname, sizeof (fdname), "%d", fd); execl ("/proc/self/exe", argv[0], fdname, NULL); puts ("execl failed"); return 1; } [akpm@linux-foundation.org: Fix fastcall inconsistency noted by Michael Buesch] [akpm@linux-foundation.org: build fix] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Michael Buesch <mb@bu3sch.de> Cc: Michael Kerrisk <mtk-manpages@gmx.net> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-07-16 14:40:34 +08:00
#define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exit for file
descriptor received through
SCM_RIGHTS */
#if defined(CONFIG_COMPAT)
#define MSG_CMSG_COMPAT 0x80000000 /* This message needs 32 bit fixups */
#else
#define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */
#endif
/* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
#define SOL_IP 0
/* #define SOL_ICMP 1 No-no-no! Due to Linux :-) we cannot use SOL_ICMP=1 */
#define SOL_TCP 6
#define SOL_UDP 17
#define SOL_IPV6 41
#define SOL_ICMPV6 58
#define SOL_SCTP 132
[NET]: Supporting UDP-Lite (RFC 3828) in Linux This is a revision of the previously submitted patch, which alters the way files are organized and compiled in the following manner: * UDP and UDP-Lite now use separate object files * source file dependencies resolved via header files net/ipv{4,6}/udp_impl.h * order of inclusion files in udp.c/udplite.c adapted accordingly [NET/IPv4]: Support for the UDP-Lite protocol (RFC 3828) This patch adds support for UDP-Lite to the IPv4 stack, provided as an extension to the existing UDPv4 code: * generic routines are all located in net/ipv4/udp.c * UDP-Lite specific routines are in net/ipv4/udplite.c * MIB/statistics support in /proc/net/snmp and /proc/net/udplite * shared API with extensions for partial checksum coverage [NET/IPv6]: Extension for UDP-Lite over IPv6 It extends the existing UDPv6 code base with support for UDP-Lite in the same manner as per UDPv4. In particular, * UDPv6 generic and shared code is in net/ipv6/udp.c * UDP-Litev6 specific extensions are in net/ipv6/udplite.c * MIB/statistics support in /proc/net/snmp6 and /proc/net/udplite6 * support for IPV6_ADDRFORM * aligned the coding style of protocol initialisation with af_inet6.c * made the error handling in udpv6_queue_rcv_skb consistent; to return `-1' on error on all error cases * consolidation of shared code [NET]: UDP-Lite Documentation and basic XFRM/Netfilter support The UDP-Lite patch further provides * API documentation for UDP-Lite * basic xfrm support * basic netfilter support for IPv4 and IPv6 (LOG target) Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-11-28 03:10:57 +08:00
#define SOL_UDPLITE 136 /* UDP-Lite (RFC 3828) */
#define SOL_RAW 255
#define SOL_IPX 256
#define SOL_AX25 257
#define SOL_ATALK 258
#define SOL_NETROM 259
#define SOL_ROSE 260
#define SOL_DECNET 261
#define SOL_X25 262
#define SOL_PACKET 263
#define SOL_ATM 264 /* ATM layer (cell level) */
#define SOL_AAL 265 /* ATM Adaption Layer (packet level) */
#define SOL_IRDA 266
#define SOL_NETBEUI 267
#define SOL_LLC 268
#define SOL_DCCP 269
#define SOL_NETLINK 270
#define SOL_TIPC 271
#define SOL_RXRPC 272
#define SOL_PPPOL2TP 273
#define SOL_BLUETOOTH 274
#define SOL_PNPIPE 275
#define SOL_RDS 276
#define SOL_IUCV 277
#define SOL_CAIF 278
#define SOL_ALG 279
/* IPX options */
#define IPX_TYPE 1
extern void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred);
extern int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len);
extern int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov,
int offset, int len);
extern int csum_partial_copy_fromiovecend(unsigned char *kdata,
struct iovec *iov,
int offset,
unsigned int len, __wsum *csump);
extern int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode);
extern int memcpy_toiovec(struct iovec *v, unsigned char *kdata, int len);
extern int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata,
int offset, int len);
extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr *kaddr);
extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
struct timespec;
extern int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
unsigned int flags, struct timespec *timeout);
extern int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg,
unsigned int vlen, unsigned int flags);
#endif /* not kernel and not glibc */
#endif /* _LINUX_SOCKET_H */