Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-11 14:42:24 +00:00
Code Issues Packages Projects Releases Wiki Activity
9fcd67d177
linux/include/net/inet_connection_sock.h
David Howells cdfbabfb2f net: Work around lockdep limitation in sockets that use sockets 
Lockdep issues a circular dependency warning when AFS issues an operation
through AF_RXRPC from a context in which the VFS/VM holds the mmap_sem.

The theory lockdep comes up with is as follows:

 (1) If the pagefault handler decides it needs to read pages from AFS, it
     calls AFS with mmap_sem held and AFS begins an AF_RXRPC call, but
     creating a call requires the socket lock:

	mmap_sem must be taken before sk_lock-AF_RXRPC

 (2) afs_open_socket() opens an AF_RXRPC socket and binds it.  rxrpc_bind()
     binds the underlying UDP socket whilst holding its socket lock.
     inet_bind() takes its own socket lock:

	sk_lock-AF_RXRPC must be taken before sk_lock-AF_INET

 (3) Reading from a TCP socket into a userspace buffer might cause a fault
     and thus cause the kernel to take the mmap_sem, but the TCP socket is
     locked whilst doing this:

	sk_lock-AF_INET must be taken before mmap_sem

However, lockdep's theory is wrong in this instance because it deals only
with lock classes and not individual locks.  The AF_INET lock in (2) isn't
really equivalent to the AF_INET lock in (3) as the former deals with a
socket entirely internal to the kernel that never sees userspace.  This is
a limitation in the design of lockdep.

Fix the general case by:

 (1) Double up all the locking keys used in sockets so that one set are
     used if the socket is created by userspace and the other set is used
     if the socket is created by the kernel.

 (2) Store the kern parameter passed to sk_alloc() in a variable in the
     sock struct (sk_kern_sock).  This informs sock_lock_init(),
     sock_init_data() and sk_clone_lock() as to the lock keys to be used.

     Note that the child created by sk_clone_lock() inherits the parent's
     kern setting.

 (3) Add a 'kern' parameter to ->accept() that is analogous to the one
     passed in to ->create() that distinguishes whether kernel_accept() or
     sys_accept4() was the caller and can be passed to sk_alloc().

     Note that a lot of accept functions merely dequeue an already
     allocated socket.  I haven't touched these as the new socket already
     exists before we get the parameter.

     Note also that there are a couple of places where I've made the accepted
     socket unconditionally kernel-based:

	irda_accept()
	rds_rcp_accept_one()
	tcp_accept_from_sock()

     because they follow a sock_create_kern() and accept off of that.

Whilst creating this, I noticed that lustre and ocfs don't create sockets
through sock_create_kern() and thus they aren't marked as for-kernel,
though they appear to be internal.  I wonder if these should do that so
that they use the new set of lock keys.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-03-09 18:23:27 -08:00

322 lines
10 KiB
C
Raw Blame History

/*
* NET Generic infrastructure for INET connection oriented protocols.
*
* Definitions for inet_connection_sock
*
* Authors: Many people, see the TCP sources
*
* From code originally in TCP
*
* 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 _INET_CONNECTION_SOCK_H
#define _INET_CONNECTION_SOCK_H
#include <linux/compiler.h>
#include <linux/string.h>
#include <linux/timer.h>
#include <linux/poll.h>
#include <net/inet_sock.h>
#include <net/request_sock.h>
#define INET_CSK_DEBUG 1
/* Cancel timers, when they are not required. */
#undef INET_CSK_CLEAR_TIMERS
struct inet_bind_bucket;
struct tcp_congestion_ops;
/*
* Pointers to address related TCP functions
* (i.e. things that depend on the address family)
*/
struct inet_connection_sock_af_ops {
int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
void (*send_check)(struct sock *sk, struct sk_buff *skb);
int (*rebuild_header)(struct sock *sk);
void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
int (*conn_request)(struct sock *sk, struct sk_buff *skb);
struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst,
struct request_sock *req_unhash,
bool *own_req);
u16 net_header_len;
u16 net_frag_header_len;
u16 sockaddr_len;
int (*setsockopt)(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen);
int (*getsockopt)(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
#ifdef CONFIG_COMPAT
int (*compat_setsockopt)(struct sock *sk,
int level, int optname,
char __user *optval, unsigned int optlen);
int (*compat_getsockopt)(struct sock *sk,
int level, int optname,
char __user *optval, int __user *optlen);
#endif
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
void (*mtu_reduced)(struct sock *sk);
};
/** inet_connection_sock - INET connection oriented sock
*
* @icsk_accept_queue: FIFO of established children
* @icsk_bind_hash: Bind node
* @icsk_timeout: Timeout
* @icsk_retransmit_timer: Resend (no ack)
* @icsk_rto: Retransmit timeout
* @icsk_pmtu_cookie Last pmtu seen by socket
* @icsk_ca_ops Pluggable congestion control hook
* @icsk_af_ops Operations which are AF_INET{4,6} specific
* @icsk_ca_state: Congestion control state
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
* @icsk_pending: Scheduled timer event
* @icsk_backoff: Backoff
* @icsk_syn_retries: Number of allowed SYN (or equivalent) retries
* @icsk_probes_out: unanswered 0 window probes
* @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options)
* @icsk_ack: Delayed ACK control data
* @icsk_mtup; MTU probing control data
*/
struct inet_connection_sock {
/* inet_sock has to be the first member! */
struct inet_sock icsk_inet;
struct request_sock_queue icsk_accept_queue;
struct inet_bind_bucket *icsk_bind_hash;
unsigned long icsk_timeout;
struct timer_list icsk_retransmit_timer;
struct timer_list icsk_delack_timer;
__u32 icsk_rto;
__u32 icsk_pmtu_cookie;
const struct tcp_congestion_ops *icsk_ca_ops;
const struct inet_connection_sock_af_ops *icsk_af_ops;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state:6,
icsk_ca_setsockopt:1,
icsk_ca_dst_locked:1;
__u8 icsk_retransmits;
__u8 icsk_pending;
__u8 icsk_backoff;
__u8 icsk_syn_retries;
__u8 icsk_probes_out;
__u16 icsk_ext_hdr_len;
struct {
__u8 pending; /* ACK is pending */
__u8 quick; /* Scheduled number of quick acks */
__u8 pingpong; /* The session is interactive */
__u8 blocked; /* Delayed ACK was blocked by socket lock */
__u32 ato; /* Predicted tick of soft clock */
unsigned long timeout; /* Currently scheduled timeout */
__u32 lrcvtime; /* timestamp of last received data packet */
__u16 last_seg_size; /* Size of last incoming segment */
__u16 rcv_mss; /* MSS used for delayed ACK decisions */
} icsk_ack;
struct {
int enabled;
/* Range of MTUs to search */
int search_high;
int search_low;
/* Information on the current probe. */
int probe_size;
u32 probe_timestamp;
} icsk_mtup;
u32 icsk_user_timeout;
u64 icsk_ca_priv[88 / sizeof(u64)];
#define ICSK_CA_PRIV_SIZE (11 * sizeof(u64))
};
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */
#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */
#define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */
static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
{
return (struct inet_connection_sock *)sk;
}
static inline void *inet_csk_ca(const struct sock *sk)
{
return (void *)inet_csk(sk)->icsk_ca_priv;
}
struct sock *inet_csk_clone_lock(const struct sock *sk,
const struct request_sock *req,
const gfp_t priority);
enum inet_csk_ack_state_t {
ICSK_ACK_SCHED = 1,
ICSK_ACK_TIMER = 2,
ICSK_ACK_PUSHED = 4,
ICSK_ACK_PUSHED2 = 8
};
void inet_csk_init_xmit_timers(struct sock *sk,
void (*retransmit_handler)(unsigned long),
void (*delack_handler)(unsigned long),
void (*keepalive_handler)(unsigned long));
void inet_csk_clear_xmit_timers(struct sock *sk);
static inline void inet_csk_schedule_ack(struct sock *sk)
{
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
}
static inline int inet_csk_ack_scheduled(const struct sock *sk)
{
return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
}
static inline void inet_csk_delack_init(struct sock *sk)
{
memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
}
void inet_csk_delete_keepalive_timer(struct sock *sk);
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
#ifdef INET_CSK_DEBUG
extern const char inet_csk_timer_bug_msg[];
#endif
static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
icsk->icsk_pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
#endif
} else if (what == ICSK_TIME_DACK) {
icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
#ifdef INET_CSK_CLEAR_TIMERS
sk_stop_timer(sk, &icsk->icsk_delack_timer);
#endif
}
#ifdef INET_CSK_DEBUG
else {
pr_debug("%s", inet_csk_timer_bug_msg);
}
#endif
}
/*
* Reset the retransmission timer
*/
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
unsigned long when,
const unsigned long max_when)
{
struct inet_connection_sock *icsk = inet_csk(sk);
if (when > max_when) {
#ifdef INET_CSK_DEBUG
pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
sk, what, when, current_text_addr());
#endif
when = max_when;
}
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE ||
what == ICSK_TIME_REO_TIMEOUT) {
icsk->icsk_pending = what;
icsk->icsk_timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
} else if (what == ICSK_TIME_DACK) {
icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
icsk->icsk_ack.timeout = jiffies + when;
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
}
#ifdef INET_CSK_DEBUG
else {
pr_debug("%s", inet_csk_timer_bug_msg);
}
#endif
}
static inline unsigned long
inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
unsigned long max_when)
{
u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;
return (unsigned long)min_t(u64, when, max_when);
}
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
int inet_csk_get_port(struct sock *sk, unsigned short snum);
struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
const struct request_sock *req);
struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
struct sock *newsk,
const struct request_sock *req);
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child);
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
unsigned long timeout);
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
struct request_sock *req,
bool own_req);
static inline void inet_csk_reqsk_queue_added(struct sock *sk)
{
reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
}
static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
{
return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
}
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
}
void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
void inet_csk_destroy_sock(struct sock *sk);
void inet_csk_prepare_forced_close(struct sock *sk);
/*
* LISTEN is a special case for poll..
*/
static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
{
return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
(POLLIN | POLLRDNORM) : 0;
}
int inet_csk_listen_start(struct sock *sk, int backlog);
void inet_csk_listen_stop(struct sock *sk);
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen);
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
#endif /* _INET_CONNECTION_SOCK_H */
Reference in New Issue View Git Blame Copy Permalink