OpenCloudOS-Kernel/include/linux/net.h

315 lines
10 KiB
C
Raw Normal View History

/*
* NET An implementation of the SOCKET network access protocol.
* This is the master header file for the Linux NET layer,
* or, in plain English: the networking handling part of the
* kernel.
*
* Version: @(#)net.h 1.0.3 05/25/93
*
* Authors: Orest Zborowski, <obz@Kodak.COM>
* Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#ifndef _LINUX_NET_H
#define _LINUX_NET_H
#include <linux/stringify.h>
#include <linux/random.h>
#include <linux/wait.h>
#include <linux/fcntl.h> /* For O_CLOEXEC and O_NONBLOCK */
#include <linux/kmemcheck.h>
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 19:01:49 +08:00
#include <linux/rcupdate.h>
#include <linux/once.h>
#include <linux/fs.h>
#include <uapi/linux/net.h>
struct poll_table_struct;
struct pipe_inode_info;
struct inode;
struct file;
struct net;
/* Historically, SOCKWQ_ASYNC_NOSPACE & SOCKWQ_ASYNC_WAITDATA were located
* in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
* Eventually all flags will be in sk->sk_wq_flags.
*/
#define SOCKWQ_ASYNC_NOSPACE 0
#define SOCKWQ_ASYNC_WAITDATA 1
#define SOCK_NOSPACE 2
#define SOCK_PASSCRED 3
[AF_UNIX]: Datagram getpeersec This patch implements an API whereby an application can determine the label of its peer's Unix datagram sockets via the auxiliary data mechanism of recvmsg. Patch purpose: This patch enables a security-aware application to retrieve the security context of the peer of a Unix datagram socket. The application can then use this security context to determine the security context for processing on behalf of the peer who sent the packet. Patch design and implementation: The design and implementation is very similar to the UDP case for INET sockets. Basically we 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). To retrieve the security context, the application first indicates to the kernel such desire by setting the SO_PASSSEC option via getsockopt. Then the application retrieves the security context using the auxiliary data mechanism. An example server application for Unix datagram socket should look like this: toggle = 1; toggle_len = sizeof(toggle); setsockopt(sockfd, SOL_SOCKET, SO_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_SOCKET && cmsg_hdr->cmsg_type == SCM_SECURITY) { memcpy(&scontext, CMSG_DATA(cmsg_hdr), sizeof(scontext)); } } sock_setsockopt is enhanced with a new socket option SOCK_PASSSEC to allow a server socket to receive security context of the peer. Testing: We have tested the patch by setting up Unix datagram client and server applications. We verified that the server can retrieve the security context using the auxiliary data mechanism of recvmsg. Signed-off-by: Catherine Zhang <cxzhang@watson.ibm.com> Acked-by: Acked-by: James Morris <jmorris@namei.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 03:27:47 +08:00
#define SOCK_PASSSEC 4
#ifndef ARCH_HAS_SOCKET_TYPES
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:59:25 +08:00
/**
* enum sock_type - Socket types
* @SOCK_STREAM: stream (connection) socket
* @SOCK_DGRAM: datagram (conn.less) socket
* @SOCK_RAW: raw socket
* @SOCK_RDM: reliably-delivered message
* @SOCK_SEQPACKET: sequential packet socket
* @SOCK_DCCP: Datagram Congestion Control Protocol socket
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:59:25 +08:00
* @SOCK_PACKET: linux specific way of getting packets at the dev level.
* For writing rarp and other similar things on the user level.
*
* When adding some new socket type please
* grep ARCH_HAS_SOCKET_TYPE include/asm-* /socket.h, at least MIPS
* overrides this enum for binary compat reasons.
*/
enum sock_type {
SOCK_STREAM = 1,
SOCK_DGRAM = 2,
SOCK_RAW = 3,
SOCK_RDM = 4,
SOCK_SEQPACKET = 5,
SOCK_DCCP = 6,
SOCK_PACKET = 10,
};
#define SOCK_MAX (SOCK_PACKET + 1)
flag parameters: socket and socketpair This patch adds support for flag values which are ORed to the type passwd to socket and socketpair. The additional code is minimal. The flag values in this implementation can and must match the O_* flags. This avoids overhead in the conversion. The internal functions sock_alloc_fd and sock_map_fd get a new parameters and all callers are changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <netinet/in.h> #include <sys/socket.h> #define PORT 57392 /* For Linux these must be the same. */ #define SOCK_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = socket (PF_INET, SOCK_STREAM, 0); if (fd == -1) { puts ("socket(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("socket(0) set close-on-exec flag"); return 1; } close (fd); fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0); if (fd == -1) { puts ("socket(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); int fds[2]; if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1) { puts ("socketpair(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1) { puts ("socketpair(SOCK_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:17 +08:00
/* Mask which covers at least up to SOCK_MASK-1. The
* remaining bits are used as flags. */
#define SOCK_TYPE_MASK 0xf
reintroduce accept4 Introduce a new accept4() system call. The addition of this system call matches analogous changes in 2.6.27 (dup3(), evenfd2(), signalfd4(), inotify_init1(), epoll_create1(), pipe2()) which added new system calls that differed from analogous traditional system calls in adding a flags argument that can be used to access additional functionality. The accept4() system call is exactly the same as accept(), except that it adds a flags bit-mask argument. Two flags are initially implemented. (Most of the new system calls in 2.6.27 also had both of these flags.) SOCK_CLOEXEC causes the close-on-exec (FD_CLOEXEC) flag to be enabled for the new file descriptor returned by accept4(). This is a useful security feature to avoid leaking information in a multithreaded program where one thread is doing an accept() at the same time as another thread is doing a fork() plus exec(). More details here: http://udrepper.livejournal.com/20407.html "Secure File Descriptor Handling", Ulrich Drepper). The other flag is SOCK_NONBLOCK, which causes the O_NONBLOCK flag to be enabled on the new open file description created by accept4(). (This flag is merely a convenience, saving the use of additional calls fcntl(F_GETFL) and fcntl (F_SETFL) to achieve the same result. Here's a test program. Works on x86-32. Should work on x86-64, but I (mtk) don't have a system to hand to test with. It tests accept4() with each of the four possible combinations of SOCK_CLOEXEC and SOCK_NONBLOCK set/clear in 'flags', and verifies that the appropriate flags are set on the file descriptor/open file description returned by accept4(). I tested Ulrich's patch in this thread by applying against 2.6.28-rc2, and it passes according to my test program. /* test_accept4.c Copyright (C) 2008, Linux Foundation, written by Michael Kerrisk <mtk.manpages@gmail.com> Licensed under the GNU GPLv2 or later. */ #define _GNU_SOURCE #include <unistd.h> #include <sys/syscall.h> #include <sys/socket.h> #include <netinet/in.h> #include <stdlib.h> #include <fcntl.h> #include <stdio.h> #include <string.h> #define PORT_NUM 33333 #define die(msg) do { perror(msg); exit(EXIT_FAILURE); } while (0) /**********************************************************************/ /* The following is what we need until glibc gets a wrapper for accept4() */ /* Flags for socket(), socketpair(), accept4() */ #ifndef SOCK_CLOEXEC #define SOCK_CLOEXEC O_CLOEXEC #endif #ifndef SOCK_NONBLOCK #define SOCK_NONBLOCK O_NONBLOCK #endif #ifdef __x86_64__ #define SYS_accept4 288 #elif __i386__ #define USE_SOCKETCALL 1 #define SYS_ACCEPT4 18 #else #error "Sorry -- don't know the syscall # on this architecture" #endif static int accept4(int fd, struct sockaddr *sockaddr, socklen_t *addrlen, int flags) { printf("Calling accept4(): flags = %x", flags); if (flags != 0) { printf(" ("); if (flags & SOCK_CLOEXEC) printf("SOCK_CLOEXEC"); if ((flags & SOCK_CLOEXEC) && (flags & SOCK_NONBLOCK)) printf(" "); if (flags & SOCK_NONBLOCK) printf("SOCK_NONBLOCK"); printf(")"); } printf("\n"); #if USE_SOCKETCALL long args[6]; args[0] = fd; args[1] = (long) sockaddr; args[2] = (long) addrlen; args[3] = flags; return syscall(SYS_socketcall, SYS_ACCEPT4, args); #else return syscall(SYS_accept4, fd, sockaddr, addrlen, flags); #endif } /**********************************************************************/ static int do_test(int lfd, struct sockaddr_in *conn_addr, int closeonexec_flag, int nonblock_flag) { int connfd, acceptfd; int fdf, flf, fdf_pass, flf_pass; struct sockaddr_in claddr; socklen_t addrlen; printf("=======================================\n"); connfd = socket(AF_INET, SOCK_STREAM, 0); if (connfd == -1) die("socket"); if (connect(connfd, (struct sockaddr *) conn_addr, sizeof(struct sockaddr_in)) == -1) die("connect"); addrlen = sizeof(struct sockaddr_in); acceptfd = accept4(lfd, (struct sockaddr *) &claddr, &addrlen, closeonexec_flag | nonblock_flag); if (acceptfd == -1) { perror("accept4()"); close(connfd); return 0; } fdf = fcntl(acceptfd, F_GETFD); if (fdf == -1) die("fcntl:F_GETFD"); fdf_pass = ((fdf & FD_CLOEXEC) != 0) == ((closeonexec_flag & SOCK_CLOEXEC) != 0); printf("Close-on-exec flag is %sset (%s); ", (fdf & FD_CLOEXEC) ? "" : "not ", fdf_pass ? "OK" : "failed"); flf = fcntl(acceptfd, F_GETFL); if (flf == -1) die("fcntl:F_GETFD"); flf_pass = ((flf & O_NONBLOCK) != 0) == ((nonblock_flag & SOCK_NONBLOCK) !=0); printf("nonblock flag is %sset (%s)\n", (flf & O_NONBLOCK) ? "" : "not ", flf_pass ? "OK" : "failed"); close(acceptfd); close(connfd); printf("Test result: %s\n", (fdf_pass && flf_pass) ? "PASS" : "FAIL"); return fdf_pass && flf_pass; } static int create_listening_socket(int port_num) { struct sockaddr_in svaddr; int lfd; int optval; memset(&svaddr, 0, sizeof(struct sockaddr_in)); svaddr.sin_family = AF_INET; svaddr.sin_addr.s_addr = htonl(INADDR_ANY); svaddr.sin_port = htons(port_num); lfd = socket(AF_INET, SOCK_STREAM, 0); if (lfd == -1) die("socket"); optval = 1; if (setsockopt(lfd, SOL_SOCKET, SO_REUSEADDR, &optval, sizeof(optval)) == -1) die("setsockopt"); if (bind(lfd, (struct sockaddr *) &svaddr, sizeof(struct sockaddr_in)) == -1) die("bind"); if (listen(lfd, 5) == -1) die("listen"); return lfd; } int main(int argc, char *argv[]) { struct sockaddr_in conn_addr; int lfd; int port_num; int passed; passed = 1; port_num = (argc > 1) ? atoi(argv[1]) : PORT_NUM; memset(&conn_addr, 0, sizeof(struct sockaddr_in)); conn_addr.sin_family = AF_INET; conn_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK); conn_addr.sin_port = htons(port_num); lfd = create_listening_socket(port_num); if (!do_test(lfd, &conn_addr, 0, 0)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, 0)) passed = 0; if (!do_test(lfd, &conn_addr, 0, SOCK_NONBLOCK)) passed = 0; if (!do_test(lfd, &conn_addr, SOCK_CLOEXEC, SOCK_NONBLOCK)) passed = 0; close(lfd); exit(passed ? EXIT_SUCCESS : EXIT_FAILURE); } [mtk.manpages@gmail.com: rewrote changelog, updated test program] Signed-off-by: Ulrich Drepper <drepper@redhat.com> Tested-by: Michael Kerrisk <mtk.manpages@gmail.com> Acked-by: Michael Kerrisk <mtk.manpages@gmail.com> Cc: <linux-api@vger.kernel.org> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-11-20 07:36:14 +08:00
/* Flags for socket, socketpair, accept4 */
flag parameters: socket and socketpair This patch adds support for flag values which are ORed to the type passwd to socket and socketpair. The additional code is minimal. The flag values in this implementation can and must match the O_* flags. This avoids overhead in the conversion. The internal functions sock_alloc_fd and sock_map_fd get a new parameters and all callers are changed. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <netinet/in.h> #include <sys/socket.h> #define PORT 57392 /* For Linux these must be the same. */ #define SOCK_CLOEXEC O_CLOEXEC int main (void) { int fd; fd = socket (PF_INET, SOCK_STREAM, 0); if (fd == -1) { puts ("socket(0) failed"); return 1; } int coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { puts ("socket(0) set close-on-exec flag"); return 1; } close (fd); fd = socket (PF_INET, SOCK_STREAM|SOCK_CLOEXEC, 0); if (fd == -1) { puts ("socket(SOCK_CLOEXEC) failed"); return 1; } coe = fcntl (fd, F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { puts ("socket(SOCK_CLOEXEC) does not set close-on-exec flag"); return 1; } close (fd); int fds[2]; if (socketpair (PF_UNIX, SOCK_STREAM, 0, fds) == -1) { puts ("socketpair(0) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if (coe & FD_CLOEXEC) { printf ("socketpair(0) set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } if (socketpair (PF_UNIX, SOCK_STREAM|SOCK_CLOEXEC, 0, fds) == -1) { puts ("socketpair(SOCK_CLOEXEC) failed"); return 1; } for (int i = 0; i < 2; ++i) { coe = fcntl (fds[i], F_GETFD); if (coe == -1) { puts ("fcntl failed"); return 1; } if ((coe & FD_CLOEXEC) == 0) { printf ("socketpair(SOCK_CLOEXEC) does not set close-on-exec flag for fds[%d]\n", i); return 1; } close (fds[i]); } puts ("OK"); return 0; } ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Signed-off-by: Ulrich Drepper <drepper@redhat.com> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: Michael Kerrisk <mtk.manpages@googlemail.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Ralf Baechle <ralf@linux-mips.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-24 12:29:17 +08:00
#define SOCK_CLOEXEC O_CLOEXEC
#ifndef SOCK_NONBLOCK
#define SOCK_NONBLOCK O_NONBLOCK
#endif
#endif /* ARCH_HAS_SOCKET_TYPES */
enum sock_shutdown_cmd {
SHUT_RD,
SHUT_WR,
SHUT_RDWR,
};
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 19:01:49 +08:00
struct socket_wq {
/* Note: wait MUST be first field of socket_wq */
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 19:01:49 +08:00
wait_queue_head_t wait;
struct fasync_struct *fasync_list;
unsigned long flags; /* %SOCKWQ_ASYNC_NOSPACE, etc */
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 19:01:49 +08:00
struct rcu_head rcu;
} ____cacheline_aligned_in_smp;
/**
* struct socket - general BSD socket
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:59:25 +08:00
* @state: socket state (%SS_CONNECTED, etc)
* @type: socket type (%SOCK_STREAM, etc)
* @flags: socket flags (%SOCK_NOSPACE, etc)
[PATCH] DocBook: changes and extensions to the kernel documentation I have recompiled Linux kernel 2.6.11.5 documentation for me and our university students again. The documentation could be extended for more sources which are equipped by structured comments for recent 2.6 kernels. I have tried to proceed with that task. I have done that more times from 2.6.0 time and it gets boring to do same changes again and again. Linux kernel compiles after changes for i386 and ARM targets. I have added references to some more files into kernel-api book, I have added some section names as well. So please, check that changes do not break something and that categories are not too much skewed. I have changed kernel-doc to accept "fastcall" and "asmlinkage" words reserved by kernel convention. Most of the other changes are modifications in the comments to make kernel-doc happy, accept some parameters description and do not bail out on errors. Changed <pid> to @pid in the description, moved some #ifdef before comments to correct function to comments bindings, etc. You can see result of the modified documentation build at http://cmp.felk.cvut.cz/~pisa/linux/lkdb-2.6.11.tar.gz Some more sources are ready to be included into kernel-doc generated documentation. Sources has been added into kernel-api for now. Some more section names added and probably some more chaos introduced as result of quick cleanup work. Signed-off-by: Pavel Pisa <pisa@cmp.felk.cvut.cz> Signed-off-by: Martin Waitz <tali@admingilde.org> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-05-01 23:59:25 +08:00
* @ops: protocol specific socket operations
* @file: File back pointer for gc
* @sk: internal networking protocol agnostic socket representation
* @wq: wait queue for several uses
*/
struct socket {
socket_state state;
kmemcheck_bitfield_begin(type);
short type;
kmemcheck_bitfield_end(type);
unsigned long flags;
net: sock_def_readable() and friends RCU conversion sk_callback_lock rwlock actually protects sk->sk_sleep pointer, so we need two atomic operations (and associated dirtying) per incoming packet. RCU conversion is pretty much needed : 1) Add a new structure, called "struct socket_wq" to hold all fields that will need rcu_read_lock() protection (currently: a wait_queue_head_t and a struct fasync_struct pointer). [Future patch will add a list anchor for wakeup coalescing] 2) Attach one of such structure to each "struct socket" created in sock_alloc_inode(). 3) Respect RCU grace period when freeing a "struct socket_wq" 4) Change sk_sleep pointer in "struct sock" by sk_wq, pointer to "struct socket_wq" 5) Change sk_sleep() function to use new sk->sk_wq instead of sk->sk_sleep 6) Change sk_has_sleeper() to wq_has_sleeper() that must be used inside a rcu_read_lock() section. 7) Change all sk_has_sleeper() callers to : - Use rcu_read_lock() instead of read_lock(&sk->sk_callback_lock) - Use wq_has_sleeper() to eventually wakeup tasks. - Use rcu_read_unlock() instead of read_unlock(&sk->sk_callback_lock) 8) sock_wake_async() is modified to use rcu protection as well. 9) Exceptions : macvtap, drivers/net/tun.c, af_unix use integrated "struct socket_wq" instead of dynamically allocated ones. They dont need rcu freeing. Some cleanups or followups are probably needed, (possible sk_callback_lock conversion to a spinlock for example...). Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-04-29 19:01:49 +08:00
struct socket_wq __rcu *wq;
struct file *file;
struct sock *sk;
const struct proto_ops *ops;
};
struct vm_area_struct;
struct page;
struct sockaddr;
struct msghdr;
struct module;
struct sk_buff;
typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
unsigned int, size_t);
struct proto_ops {
int family;
struct module *owner;
int (*release) (struct socket *sock);
int (*bind) (struct socket *sock,
struct sockaddr *myaddr,
int sockaddr_len);
int (*connect) (struct socket *sock,
struct sockaddr *vaddr,
int sockaddr_len, int flags);
int (*socketpair)(struct socket *sock1,
struct socket *sock2);
int (*accept) (struct socket *sock,
struct socket *newsock, int flags);
int (*getname) (struct socket *sock,
struct sockaddr *addr,
int *sockaddr_len, int peer);
unsigned int (*poll) (struct file *file, struct socket *sock,
struct poll_table_struct *wait);
int (*ioctl) (struct socket *sock, unsigned int cmd,
unsigned long arg);
#ifdef CONFIG_COMPAT
int (*compat_ioctl) (struct socket *sock, unsigned int cmd,
unsigned long arg);
#endif
int (*listen) (struct socket *sock, int len);
int (*shutdown) (struct socket *sock, int flags);
int (*setsockopt)(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
int (*getsockopt)(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct socket *sock, int level,
int optname, char __user *optval, unsigned int optlen);
int (*compat_getsockopt)(struct socket *sock, int level,
int optname, char __user *optval, int __user *optlen);
#endif
int (*sendmsg) (struct socket *sock, struct msghdr *m,
size_t total_len);
net: rework recvmsg handler msg_name and msg_namelen logic This patch now always passes msg->msg_namelen as 0. recvmsg handlers must set msg_namelen to the proper size <= sizeof(struct sockaddr_storage) to return msg_name to the user. This prevents numerous uninitialized memory leaks we had in the recvmsg handlers and makes it harder for new code to accidentally leak uninitialized memory. Optimize for the case recvfrom is called with NULL as address. We don't need to copy the address at all, so set it to NULL before invoking the recvmsg handler. We can do so, because all the recvmsg handlers must cope with the case a plain read() is called on them. read() also sets msg_name to NULL. Also document these changes in include/linux/net.h as suggested by David Miller. Changes since RFC: Set msg->msg_name = NULL if user specified a NULL in msg_name but had a non-null msg_namelen in verify_iovec/verify_compat_iovec. This doesn't affect sendto as it would bail out earlier while trying to copy-in the address. It also more naturally reflects the logic by the callers of verify_iovec. With this change in place I could remove " if (!uaddr || msg_sys->msg_namelen == 0) msg->msg_name = NULL ". This change does not alter the user visible error logic as we ignore msg_namelen as long as msg_name is NULL. Also remove two unnecessary curly brackets in ___sys_recvmsg and change comments to netdev style. Cc: David Miller <davem@davemloft.net> Suggested-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-11-21 10:14:22 +08:00
/* Notes for implementing recvmsg:
* ===============================
* msg->msg_namelen should get updated by the recvmsg handlers
* iff msg_name != NULL. It is by default 0 to prevent
* returning uninitialized memory to user space. The recvfrom
* handlers can assume that msg.msg_name is either NULL or has
* a minimum size of sizeof(struct sockaddr_storage).
*/
int (*recvmsg) (struct socket *sock, struct msghdr *m,
size_t total_len, int flags);
int (*mmap) (struct file *file, struct socket *sock,
struct vm_area_struct * vma);
ssize_t (*sendpage) (struct socket *sock, struct page *page,
int offset, size_t size, int flags);
ssize_t (*splice_read)(struct socket *sock, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len, unsigned int flags);
int (*set_peek_off)(struct sock *sk, int val);
int (*peek_len)(struct socket *sock);
int (*read_sock)(struct sock *sk, read_descriptor_t *desc,
sk_read_actor_t recv_actor);
};
#define DECLARE_SOCKADDR(type, dst, src) \
type dst = ({ __sockaddr_check_size(sizeof(*dst)); (type) src; })
struct net_proto_family {
int family;
int (*create)(struct net *net, struct socket *sock,
int protocol, int kern);
struct module *owner;
};
struct iovec;
struct kvec;
enum {
SOCK_WAKE_IO,
SOCK_WAKE_WAITD,
SOCK_WAKE_SPACE,
SOCK_WAKE_URG,
};
int sock_wake_async(struct socket_wq *sk_wq, int how, int band);
int sock_register(const struct net_proto_family *fam);
void sock_unregister(int family);
int __sock_create(struct net *net, int family, int type, int proto,
struct socket **res, int kern);
int sock_create(int family, int type, int proto, struct socket **res);
int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res);
int sock_create_lite(int family, int type, int proto, struct socket **res);
struct socket *sock_alloc(void);
void sock_release(struct socket *sock);
int sock_sendmsg(struct socket *sock, struct msghdr *msg);
int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags);
struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname);
struct socket *sockfd_lookup(int fd, int *err);
struct socket *sock_from_file(struct file *file, int *err);
#define sockfd_put(sock) fput(sock->file)
int net_ratelimit(void);
#define net_ratelimited_function(function, ...) \
do { \
if (net_ratelimit()) \
function(__VA_ARGS__); \
} while (0)
#define net_emerg_ratelimited(fmt, ...) \
net_ratelimited_function(pr_emerg, fmt, ##__VA_ARGS__)
#define net_alert_ratelimited(fmt, ...) \
net_ratelimited_function(pr_alert, fmt, ##__VA_ARGS__)
#define net_crit_ratelimited(fmt, ...) \
net_ratelimited_function(pr_crit, fmt, ##__VA_ARGS__)
#define net_err_ratelimited(fmt, ...) \
net_ratelimited_function(pr_err, fmt, ##__VA_ARGS__)
#define net_notice_ratelimited(fmt, ...) \
net_ratelimited_function(pr_notice, fmt, ##__VA_ARGS__)
#define net_warn_ratelimited(fmt, ...) \
net_ratelimited_function(pr_warn, fmt, ##__VA_ARGS__)
#define net_info_ratelimited(fmt, ...) \
net_ratelimited_function(pr_info, fmt, ##__VA_ARGS__)
#if defined(CONFIG_DYNAMIC_DEBUG)
#define net_dbg_ratelimited(fmt, ...) \
do { \
DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT) && \
net_ratelimit()) \
__dynamic_pr_debug(&descriptor, pr_fmt(fmt), \
##__VA_ARGS__); \
} while (0)
#elif defined(DEBUG)
#define net_dbg_ratelimited(fmt, ...) \
net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
net_dbg_ratelimited: turn into no-op when !DEBUG The pr_debug family of functions turns into a no-op when -DDEBUG is not specified, opting instead to call "no_printk", which gets compiled to a no-op (but retains gcc's nice warnings about printf-style arguments). The problem with net_dbg_ratelimited is that it is defined to be a variant of net_ratelimited_function, which expands to essentially: if (net_ratelimit()) pr_debug(fmt, ...); When DEBUG is not defined, then this becomes, if (net_ratelimit()) ; This seems benign, except it isn't. Firstly, there's the obvious overhead of calling net_ratelimit needlessly, which does quite some book keeping for the rate limiting. Given that the pr_debug and net_dbg_ratelimited family of functions are sprinkled liberally through performance critical code, with developers assuming they'll be compiled out to a no-op most of the time, we certainly do not want this needless book keeping. Secondly, and most visibly, even though no debug message is printed when DEBUG is not defined, if there is a flood of invocations, dmesg winds up peppered with messages such as "net_ratelimit: 320 callbacks suppressed". This is because our aforementioned net_ratelimit() function actually prints this text in some circumstances. It's especially odd to see this when there isn't any other accompanying debug message. So, in sum, it doesn't make sense to have this function's current behavior, and instead it should match what every other debug family of functions in the kernel does with !DEBUG -- nothing. This patch replaces calls to net_dbg_ratelimited when !DEBUG with no_printk, keeping with the idiom of all the other debug print helpers. Also, though not strictly neccessary, it guards the call with an if (0) so that all evaluation of any arguments are sure to be compiled out. Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-08-05 00:26:19 +08:00
#else
#define net_dbg_ratelimited(fmt, ...) \
do { \
if (0) \
no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \
} while (0)
#endif
#define net_get_random_once(buf, nbytes) \
get_random_once((buf), (nbytes))
net: introduce new macro net_get_random_once net_get_random_once is a new macro which handles the initialization of secret keys. It is possible to call it in the fast path. Only the initialization depends on the spinlock and is rather slow. Otherwise it should get used just before the key is used to delay the entropy extration as late as possible to get better randomness. It returns true if the key got initialized. The usage of static_keys for net_get_random_once is a bit uncommon so it needs some further explanation why this actually works: === In the simple non-HAVE_JUMP_LABEL case we actually have === no constrains to use static_key_(true|false) on keys initialized with STATIC_KEY_INIT_(FALSE|TRUE). So this path just expands in favor of the likely case that the initialization is already done. The key is initialized like this: ___done_key = { .enabled = ATOMIC_INIT(0) } The check if (!static_key_true(&___done_key)) \ expands into (pseudo code) if (!likely(___done_key > 0)) , so we take the fast path as soon as ___done_key is increased from the helper function. === If HAVE_JUMP_LABELs are available this depends === on patching of jumps into the prepared NOPs, which is done in jump_label_init at boot-up time (from start_kernel). It is forbidden and dangerous to use net_get_random_once in functions which are called before that! At compilation time NOPs are generated at the call sites of net_get_random_once. E.g. net/ipv6/inet6_hashtable.c:inet6_ehashfn (we need to call net_get_random_once two times in inet6_ehashfn, so two NOPs): 71: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) 76: 0f 1f 44 00 00 nopl 0x0(%rax,%rax,1) Both will be patched to the actual jumps to the end of the function to call __net_get_random_once at boot time as explained above. arch_static_branch is optimized and inlined for false as return value and actually also returns false in case the NOP is placed in the instruction stream. So in the fast case we get a "return false". But because we initialize ___done_key with (enabled != (entries & 1)) this call-site will get patched up at boot thus returning true. The final check looks like this: if (!static_key_true(&___done_key)) \ ___ret = __net_get_random_once(buf, \ expands to if (!!static_key_false(&___done_key)) \ ___ret = __net_get_random_once(buf, \ So we get true at boot time and as soon as static_key_slow_inc is called on the key it will invert the logic and return false for the fast path. static_key_slow_inc will change the branch because it got initialized with .enabled == 0. After static_key_slow_inc is called on the key the branch is replaced with a nop again. === Misc: === The helper defers the increment into a workqueue so we don't have problems calling this code from atomic sections. A seperate boolean (___done) guards the case where we enter net_get_random_once again before the increment happend. Cc: Ingo Molnar <mingo@redhat.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Jason Baron <jbaron@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Eric Dumazet <edumazet@google.com> Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-10-20 03:48:55 +08:00
int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
size_t num, size_t len);
int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
size_t num, size_t len, int flags);
int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen);
int kernel_listen(struct socket *sock, int backlog);
int kernel_accept(struct socket *sock, struct socket **newsock, int flags);
int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
int flags);
int kernel_getsockname(struct socket *sock, struct sockaddr *addr,
int *addrlen);
int kernel_getpeername(struct socket *sock, struct sockaddr *addr,
int *addrlen);
int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval,
int *optlen);
int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval,
unsigned int optlen);
int kernel_sendpage(struct socket *sock, struct page *page, int offset,
size_t size, int flags);
int kernel_sock_ioctl(struct socket *sock, int cmd, unsigned long arg);
int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
#define MODULE_ALIAS_NETPROTO(proto) \
MODULE_ALIAS("net-pf-" __stringify(proto))
#define MODULE_ALIAS_NET_PF_PROTO(pf, proto) \
MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto))
#define MODULE_ALIAS_NET_PF_PROTO_TYPE(pf, proto, type) \
MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \
"-type-" __stringify(type))
#define MODULE_ALIAS_NET_PF_PROTO_NAME(pf, proto, name) \
MODULE_ALIAS("net-pf-" __stringify(pf) "-proto-" __stringify(proto) \
name)
#endif /* _LINUX_NET_H */