a48e42920f
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>
304 lines
10 KiB
C
304 lines
10 KiB
C
/*
|
|
* 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>
|
|
#include <linux/rcupdate.h>
|
|
#include <uapi/linux/net.h>
|
|
|
|
struct poll_table_struct;
|
|
struct pipe_inode_info;
|
|
struct inode;
|
|
struct file;
|
|
struct net;
|
|
|
|
#define SOCK_ASYNC_NOSPACE 0
|
|
#define SOCK_ASYNC_WAITDATA 1
|
|
#define SOCK_NOSPACE 2
|
|
#define SOCK_PASSCRED 3
|
|
#define SOCK_PASSSEC 4
|
|
#define SOCK_EXTERNALLY_ALLOCATED 5
|
|
|
|
#ifndef ARCH_HAS_SOCKET_TYPES
|
|
/**
|
|
* 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
|
|
* @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)
|
|
/* Mask which covers at least up to SOCK_MASK-1. The
|
|
* remaining bits are used as flags. */
|
|
#define SOCK_TYPE_MASK 0xf
|
|
|
|
/* Flags for socket, socketpair, accept4 */
|
|
#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,
|
|
};
|
|
|
|
struct socket_wq {
|
|
/* Note: wait MUST be first field of socket_wq */
|
|
wait_queue_head_t wait;
|
|
struct fasync_struct *fasync_list;
|
|
struct rcu_head rcu;
|
|
} ____cacheline_aligned_in_smp;
|
|
|
|
/**
|
|
* struct socket - general BSD socket
|
|
* @state: socket state (%SS_CONNECTED, etc)
|
|
* @type: socket type (%SOCK_STREAM, etc)
|
|
* @flags: socket flags (%SOCK_ASYNC_NOSPACE, etc)
|
|
* @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;
|
|
|
|
struct socket_wq __rcu *wq;
|
|
|
|
struct file *file;
|
|
struct sock *sk;
|
|
const struct proto_ops *ops;
|
|
};
|
|
|
|
struct vm_area_struct;
|
|
struct page;
|
|
struct kiocb;
|
|
struct sockaddr;
|
|
struct msghdr;
|
|
struct module;
|
|
|
|
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 kiocb *iocb, struct socket *sock,
|
|
struct msghdr *m, size_t total_len);
|
|
int (*recvmsg) (struct kiocb *iocb, 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);
|
|
void (*set_peek_off)(struct sock *sk, int val);
|
|
};
|
|
|
|
#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 *sk, 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(int family, int type, int proto, struct socket **res);
|
|
int sock_create_lite(int family, int type, int proto, struct socket **res);
|
|
void sock_release(struct socket *sock);
|
|
int sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len);
|
|
int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
|
|
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__)
|
|
#define net_dbg_ratelimited(fmt, ...) \
|
|
net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
|
|
|
|
#define net_random() prandom_u32()
|
|
#define net_srandom(seed) prandom_seed((__force u32)(seed))
|
|
|
|
bool __net_get_random_once(void *buf, int nbytes, bool *done,
|
|
struct static_key *done_key);
|
|
|
|
#ifdef HAVE_JUMP_LABEL
|
|
#define ___NET_RANDOM_STATIC_KEY_INIT ((struct static_key) \
|
|
{ .enabled = ATOMIC_INIT(0), .entries = (void *)1 })
|
|
#else /* !HAVE_JUMP_LABEL */
|
|
#define ___NET_RANDOM_STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
|
|
#endif /* HAVE_JUMP_LABEL */
|
|
|
|
/* BE CAREFUL: this function is not interrupt safe */
|
|
#define net_get_random_once(buf, nbytes) \
|
|
({ \
|
|
bool ___ret = false; \
|
|
static bool ___done = false; \
|
|
static struct static_key ___done_key = \
|
|
___NET_RANDOM_STATIC_KEY_INIT; \
|
|
if (!static_key_true(&___done_key)) \
|
|
___ret = __net_get_random_once(buf, \
|
|
nbytes, \
|
|
&___done, \
|
|
&___done_key); \
|
|
___ret; \
|
|
})
|
|
|
|
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 */
|