mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-30 09:56:40 +07:00
fba2afaaec
This patch series implements the new signalfd() system call. I took part of the original Linus code (and you know how badly it can be broken :), and I added even more breakage ;) Signals are fetched from the same signal queue used by the process, so signalfd will compete with standard kernel delivery in dequeue_signal(). If you want to reliably fetch signals on the signalfd file, you need to block them with sigprocmask(SIG_BLOCK). This seems to be working fine on my Dual Opteron machine. I made a quick test program for it: http://www.xmailserver.org/signafd-test.c The signalfd() system call implements signal delivery into a file descriptor receiver. The signalfd file descriptor if created with the following API: int signalfd(int ufd, const sigset_t *mask, size_t masksize); The "ufd" parameter allows to change an existing signalfd sigmask, w/out going to close/create cycle (Linus idea). Use "ufd" == -1 if you want a brand new signalfd file. The "mask" allows to specify the signal mask of signals that we are interested in. The "masksize" parameter is the size of "mask". The signalfd fd supports the poll(2) and read(2) system calls. The poll(2) will return POLLIN when signals are available to be dequeued. As a direct consequence of supporting the Linux poll subsystem, the signalfd fd can use used together with epoll(2) too. The read(2) system call will return a "struct signalfd_siginfo" structure in the userspace supplied buffer. The return value is the number of bytes copied in the supplied buffer, or -1 in case of error. The read(2) call can also return 0, in case the sighand structure to which the signalfd was attached, has been orphaned. The O_NONBLOCK flag is also supported, and read(2) will return -EAGAIN in case no signal is available. If the size of the buffer passed to read(2) is lower than sizeof(struct signalfd_siginfo), -EINVAL is returned. A read from the signalfd can also return -ERESTARTSYS in case a signal hits the process. The format of the struct signalfd_siginfo is, and the valid fields depends of the (->code & __SI_MASK) value, in the same way a struct siginfo would: struct signalfd_siginfo { __u32 signo; /* si_signo */ __s32 err; /* si_errno */ __s32 code; /* si_code */ __u32 pid; /* si_pid */ __u32 uid; /* si_uid */ __s32 fd; /* si_fd */ __u32 tid; /* si_fd */ __u32 band; /* si_band */ __u32 overrun; /* si_overrun */ __u32 trapno; /* si_trapno */ __s32 status; /* si_status */ __s32 svint; /* si_int */ __u64 svptr; /* si_ptr */ __u64 utime; /* si_utime */ __u64 stime; /* si_stime */ __u64 addr; /* si_addr */ }; [akpm@linux-foundation.org: fix signalfd_copyinfo() on i386] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
375 lines
10 KiB
C
375 lines
10 KiB
C
#ifndef _LINUX_SIGNAL_H
|
|
#define _LINUX_SIGNAL_H
|
|
|
|
#include <asm/signal.h>
|
|
#include <asm/siginfo.h>
|
|
|
|
#ifdef __KERNEL__
|
|
#include <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
|
|
/*
|
|
* Real Time signals may be queued.
|
|
*/
|
|
|
|
struct sigqueue {
|
|
struct list_head list;
|
|
int flags;
|
|
siginfo_t info;
|
|
struct user_struct *user;
|
|
};
|
|
|
|
/* flags values. */
|
|
#define SIGQUEUE_PREALLOC 1
|
|
|
|
struct sigpending {
|
|
struct list_head list;
|
|
sigset_t signal;
|
|
};
|
|
|
|
/*
|
|
* Define some primitives to manipulate sigset_t.
|
|
*/
|
|
|
|
#ifndef __HAVE_ARCH_SIG_BITOPS
|
|
#include <linux/bitops.h>
|
|
|
|
/* We don't use <linux/bitops.h> for these because there is no need to
|
|
be atomic. */
|
|
static inline void sigaddset(sigset_t *set, int _sig)
|
|
{
|
|
unsigned long sig = _sig - 1;
|
|
if (_NSIG_WORDS == 1)
|
|
set->sig[0] |= 1UL << sig;
|
|
else
|
|
set->sig[sig / _NSIG_BPW] |= 1UL << (sig % _NSIG_BPW);
|
|
}
|
|
|
|
static inline void sigdelset(sigset_t *set, int _sig)
|
|
{
|
|
unsigned long sig = _sig - 1;
|
|
if (_NSIG_WORDS == 1)
|
|
set->sig[0] &= ~(1UL << sig);
|
|
else
|
|
set->sig[sig / _NSIG_BPW] &= ~(1UL << (sig % _NSIG_BPW));
|
|
}
|
|
|
|
static inline int sigismember(sigset_t *set, int _sig)
|
|
{
|
|
unsigned long sig = _sig - 1;
|
|
if (_NSIG_WORDS == 1)
|
|
return 1 & (set->sig[0] >> sig);
|
|
else
|
|
return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
|
|
}
|
|
|
|
static inline int sigfindinword(unsigned long word)
|
|
{
|
|
return ffz(~word);
|
|
}
|
|
|
|
#endif /* __HAVE_ARCH_SIG_BITOPS */
|
|
|
|
static inline int sigisemptyset(sigset_t *set)
|
|
{
|
|
extern void _NSIG_WORDS_is_unsupported_size(void);
|
|
switch (_NSIG_WORDS) {
|
|
case 4:
|
|
return (set->sig[3] | set->sig[2] |
|
|
set->sig[1] | set->sig[0]) == 0;
|
|
case 2:
|
|
return (set->sig[1] | set->sig[0]) == 0;
|
|
case 1:
|
|
return set->sig[0] == 0;
|
|
default:
|
|
_NSIG_WORDS_is_unsupported_size();
|
|
return 0;
|
|
}
|
|
}
|
|
|
|
#define sigmask(sig) (1UL << ((sig) - 1))
|
|
|
|
#ifndef __HAVE_ARCH_SIG_SETOPS
|
|
#include <linux/string.h>
|
|
|
|
#define _SIG_SET_BINOP(name, op) \
|
|
static inline void name(sigset_t *r, const sigset_t *a, const sigset_t *b) \
|
|
{ \
|
|
extern void _NSIG_WORDS_is_unsupported_size(void); \
|
|
unsigned long a0, a1, a2, a3, b0, b1, b2, b3; \
|
|
\
|
|
switch (_NSIG_WORDS) { \
|
|
case 4: \
|
|
a3 = a->sig[3]; a2 = a->sig[2]; \
|
|
b3 = b->sig[3]; b2 = b->sig[2]; \
|
|
r->sig[3] = op(a3, b3); \
|
|
r->sig[2] = op(a2, b2); \
|
|
case 2: \
|
|
a1 = a->sig[1]; b1 = b->sig[1]; \
|
|
r->sig[1] = op(a1, b1); \
|
|
case 1: \
|
|
a0 = a->sig[0]; b0 = b->sig[0]; \
|
|
r->sig[0] = op(a0, b0); \
|
|
break; \
|
|
default: \
|
|
_NSIG_WORDS_is_unsupported_size(); \
|
|
} \
|
|
}
|
|
|
|
#define _sig_or(x,y) ((x) | (y))
|
|
_SIG_SET_BINOP(sigorsets, _sig_or)
|
|
|
|
#define _sig_and(x,y) ((x) & (y))
|
|
_SIG_SET_BINOP(sigandsets, _sig_and)
|
|
|
|
#define _sig_nand(x,y) ((x) & ~(y))
|
|
_SIG_SET_BINOP(signandsets, _sig_nand)
|
|
|
|
#undef _SIG_SET_BINOP
|
|
#undef _sig_or
|
|
#undef _sig_and
|
|
#undef _sig_nand
|
|
|
|
#define _SIG_SET_OP(name, op) \
|
|
static inline void name(sigset_t *set) \
|
|
{ \
|
|
extern void _NSIG_WORDS_is_unsupported_size(void); \
|
|
\
|
|
switch (_NSIG_WORDS) { \
|
|
case 4: set->sig[3] = op(set->sig[3]); \
|
|
set->sig[2] = op(set->sig[2]); \
|
|
case 2: set->sig[1] = op(set->sig[1]); \
|
|
case 1: set->sig[0] = op(set->sig[0]); \
|
|
break; \
|
|
default: \
|
|
_NSIG_WORDS_is_unsupported_size(); \
|
|
} \
|
|
}
|
|
|
|
#define _sig_not(x) (~(x))
|
|
_SIG_SET_OP(signotset, _sig_not)
|
|
|
|
#undef _SIG_SET_OP
|
|
#undef _sig_not
|
|
|
|
static inline void sigemptyset(sigset_t *set)
|
|
{
|
|
switch (_NSIG_WORDS) {
|
|
default:
|
|
memset(set, 0, sizeof(sigset_t));
|
|
break;
|
|
case 2: set->sig[1] = 0;
|
|
case 1: set->sig[0] = 0;
|
|
break;
|
|
}
|
|
}
|
|
|
|
static inline void sigfillset(sigset_t *set)
|
|
{
|
|
switch (_NSIG_WORDS) {
|
|
default:
|
|
memset(set, -1, sizeof(sigset_t));
|
|
break;
|
|
case 2: set->sig[1] = -1;
|
|
case 1: set->sig[0] = -1;
|
|
break;
|
|
}
|
|
}
|
|
|
|
/* Some extensions for manipulating the low 32 signals in particular. */
|
|
|
|
static inline void sigaddsetmask(sigset_t *set, unsigned long mask)
|
|
{
|
|
set->sig[0] |= mask;
|
|
}
|
|
|
|
static inline void sigdelsetmask(sigset_t *set, unsigned long mask)
|
|
{
|
|
set->sig[0] &= ~mask;
|
|
}
|
|
|
|
static inline int sigtestsetmask(sigset_t *set, unsigned long mask)
|
|
{
|
|
return (set->sig[0] & mask) != 0;
|
|
}
|
|
|
|
static inline void siginitset(sigset_t *set, unsigned long mask)
|
|
{
|
|
set->sig[0] = mask;
|
|
switch (_NSIG_WORDS) {
|
|
default:
|
|
memset(&set->sig[1], 0, sizeof(long)*(_NSIG_WORDS-1));
|
|
break;
|
|
case 2: set->sig[1] = 0;
|
|
case 1: ;
|
|
}
|
|
}
|
|
|
|
static inline void siginitsetinv(sigset_t *set, unsigned long mask)
|
|
{
|
|
set->sig[0] = ~mask;
|
|
switch (_NSIG_WORDS) {
|
|
default:
|
|
memset(&set->sig[1], -1, sizeof(long)*(_NSIG_WORDS-1));
|
|
break;
|
|
case 2: set->sig[1] = -1;
|
|
case 1: ;
|
|
}
|
|
}
|
|
|
|
#endif /* __HAVE_ARCH_SIG_SETOPS */
|
|
|
|
static inline void init_sigpending(struct sigpending *sig)
|
|
{
|
|
sigemptyset(&sig->signal);
|
|
INIT_LIST_HEAD(&sig->list);
|
|
}
|
|
|
|
extern void flush_sigqueue(struct sigpending *queue);
|
|
|
|
/* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
|
|
static inline int valid_signal(unsigned long sig)
|
|
{
|
|
return sig <= _NSIG ? 1 : 0;
|
|
}
|
|
|
|
extern int next_signal(struct sigpending *pending, sigset_t *mask);
|
|
extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p);
|
|
extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *);
|
|
extern long do_sigpending(void __user *, unsigned long);
|
|
extern int sigprocmask(int, sigset_t *, sigset_t *);
|
|
|
|
struct pt_regs;
|
|
extern int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka, struct pt_regs *regs, void *cookie);
|
|
|
|
extern struct kmem_cache *sighand_cachep;
|
|
|
|
/*
|
|
* In POSIX a signal is sent either to a specific thread (Linux task)
|
|
* or to the process as a whole (Linux thread group). How the signal
|
|
* is sent determines whether it's to one thread or the whole group,
|
|
* which determines which signal mask(s) are involved in blocking it
|
|
* from being delivered until later. When the signal is delivered,
|
|
* either it's caught or ignored by a user handler or it has a default
|
|
* effect that applies to the whole thread group (POSIX process).
|
|
*
|
|
* The possible effects an unblocked signal set to SIG_DFL can have are:
|
|
* ignore - Nothing Happens
|
|
* terminate - kill the process, i.e. all threads in the group,
|
|
* similar to exit_group. The group leader (only) reports
|
|
* WIFSIGNALED status to its parent.
|
|
* coredump - write a core dump file describing all threads using
|
|
* the same mm and then kill all those threads
|
|
* stop - stop all the threads in the group, i.e. TASK_STOPPED state
|
|
*
|
|
* SIGKILL and SIGSTOP cannot be caught, blocked, or ignored.
|
|
* Other signals when not blocked and set to SIG_DFL behaves as follows.
|
|
* The job control signals also have other special effects.
|
|
*
|
|
* +--------------------+------------------+
|
|
* | POSIX signal | default action |
|
|
* +--------------------+------------------+
|
|
* | SIGHUP | terminate |
|
|
* | SIGINT | terminate |
|
|
* | SIGQUIT | coredump |
|
|
* | SIGILL | coredump |
|
|
* | SIGTRAP | coredump |
|
|
* | SIGABRT/SIGIOT | coredump |
|
|
* | SIGBUS | coredump |
|
|
* | SIGFPE | coredump |
|
|
* | SIGKILL | terminate(+) |
|
|
* | SIGUSR1 | terminate |
|
|
* | SIGSEGV | coredump |
|
|
* | SIGUSR2 | terminate |
|
|
* | SIGPIPE | terminate |
|
|
* | SIGALRM | terminate |
|
|
* | SIGTERM | terminate |
|
|
* | SIGCHLD | ignore |
|
|
* | SIGCONT | ignore(*) |
|
|
* | SIGSTOP | stop(*)(+) |
|
|
* | SIGTSTP | stop(*) |
|
|
* | SIGTTIN | stop(*) |
|
|
* | SIGTTOU | stop(*) |
|
|
* | SIGURG | ignore |
|
|
* | SIGXCPU | coredump |
|
|
* | SIGXFSZ | coredump |
|
|
* | SIGVTALRM | terminate |
|
|
* | SIGPROF | terminate |
|
|
* | SIGPOLL/SIGIO | terminate |
|
|
* | SIGSYS/SIGUNUSED | coredump |
|
|
* | SIGSTKFLT | terminate |
|
|
* | SIGWINCH | ignore |
|
|
* | SIGPWR | terminate |
|
|
* | SIGRTMIN-SIGRTMAX | terminate |
|
|
* +--------------------+------------------+
|
|
* | non-POSIX signal | default action |
|
|
* +--------------------+------------------+
|
|
* | SIGEMT | coredump |
|
|
* +--------------------+------------------+
|
|
*
|
|
* (+) For SIGKILL and SIGSTOP the action is "always", not just "default".
|
|
* (*) Special job control effects:
|
|
* When SIGCONT is sent, it resumes the process (all threads in the group)
|
|
* from TASK_STOPPED state and also clears any pending/queued stop signals
|
|
* (any of those marked with "stop(*)"). This happens regardless of blocking,
|
|
* catching, or ignoring SIGCONT. When any stop signal is sent, it clears
|
|
* any pending/queued SIGCONT signals; this happens regardless of blocking,
|
|
* catching, or ignored the stop signal, though (except for SIGSTOP) the
|
|
* default action of stopping the process may happen later or never.
|
|
*/
|
|
|
|
#ifdef SIGEMT
|
|
#define SIGEMT_MASK rt_sigmask(SIGEMT)
|
|
#else
|
|
#define SIGEMT_MASK 0
|
|
#endif
|
|
|
|
#if SIGRTMIN > BITS_PER_LONG
|
|
#define rt_sigmask(sig) (1ULL << ((sig)-1))
|
|
#else
|
|
#define rt_sigmask(sig) sigmask(sig)
|
|
#endif
|
|
#define siginmask(sig, mask) (rt_sigmask(sig) & (mask))
|
|
|
|
#define SIG_KERNEL_ONLY_MASK (\
|
|
rt_sigmask(SIGKILL) | rt_sigmask(SIGSTOP))
|
|
|
|
#define SIG_KERNEL_STOP_MASK (\
|
|
rt_sigmask(SIGSTOP) | rt_sigmask(SIGTSTP) | \
|
|
rt_sigmask(SIGTTIN) | rt_sigmask(SIGTTOU) )
|
|
|
|
#define SIG_KERNEL_COREDUMP_MASK (\
|
|
rt_sigmask(SIGQUIT) | rt_sigmask(SIGILL) | \
|
|
rt_sigmask(SIGTRAP) | rt_sigmask(SIGABRT) | \
|
|
rt_sigmask(SIGFPE) | rt_sigmask(SIGSEGV) | \
|
|
rt_sigmask(SIGBUS) | rt_sigmask(SIGSYS) | \
|
|
rt_sigmask(SIGXCPU) | rt_sigmask(SIGXFSZ) | \
|
|
SIGEMT_MASK )
|
|
|
|
#define SIG_KERNEL_IGNORE_MASK (\
|
|
rt_sigmask(SIGCONT) | rt_sigmask(SIGCHLD) | \
|
|
rt_sigmask(SIGWINCH) | rt_sigmask(SIGURG) )
|
|
|
|
#define sig_kernel_only(sig) \
|
|
(((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_ONLY_MASK))
|
|
#define sig_kernel_coredump(sig) \
|
|
(((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_COREDUMP_MASK))
|
|
#define sig_kernel_ignore(sig) \
|
|
(((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_IGNORE_MASK))
|
|
#define sig_kernel_stop(sig) \
|
|
(((sig) < SIGRTMIN) && siginmask(sig, SIG_KERNEL_STOP_MASK))
|
|
|
|
#define sig_needs_tasklist(sig) ((sig) == SIGCONT)
|
|
|
|
#define sig_user_defined(t, signr) \
|
|
(((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_DFL) && \
|
|
((t)->sighand->action[(signr)-1].sa.sa_handler != SIG_IGN))
|
|
|
|
#define sig_fatal(t, signr) \
|
|
(!siginmask(signr, SIG_KERNEL_IGNORE_MASK|SIG_KERNEL_STOP_MASK) && \
|
|
(t)->sighand->action[(signr)-1].sa.sa_handler == SIG_DFL)
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* _LINUX_SIGNAL_H */
|