![Davide Libenzi](/assets/img/avatar_default.png)
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>
184 lines
5.1 KiB
C
184 lines
5.1 KiB
C
#ifndef _LINUX__INIT_TASK_H
|
|
#define _LINUX__INIT_TASK_H
|
|
|
|
#include <linux/file.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/irqflags.h>
|
|
#include <linux/utsname.h>
|
|
#include <linux/lockdep.h>
|
|
#include <linux/ipc.h>
|
|
#include <linux/pid_namespace.h>
|
|
|
|
#define INIT_FDTABLE \
|
|
{ \
|
|
.max_fds = NR_OPEN_DEFAULT, \
|
|
.fd = &init_files.fd_array[0], \
|
|
.close_on_exec = (fd_set *)&init_files.close_on_exec_init, \
|
|
.open_fds = (fd_set *)&init_files.open_fds_init, \
|
|
.rcu = RCU_HEAD_INIT, \
|
|
.next = NULL, \
|
|
}
|
|
|
|
#define INIT_FILES \
|
|
{ \
|
|
.count = ATOMIC_INIT(1), \
|
|
.fdt = &init_files.fdtab, \
|
|
.fdtab = INIT_FDTABLE, \
|
|
.file_lock = __SPIN_LOCK_UNLOCKED(init_task.file_lock), \
|
|
.next_fd = 0, \
|
|
.close_on_exec_init = { { 0, } }, \
|
|
.open_fds_init = { { 0, } }, \
|
|
.fd_array = { NULL, } \
|
|
}
|
|
|
|
#define INIT_KIOCTX(name, which_mm) \
|
|
{ \
|
|
.users = ATOMIC_INIT(1), \
|
|
.dead = 0, \
|
|
.mm = &which_mm, \
|
|
.user_id = 0, \
|
|
.next = NULL, \
|
|
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait), \
|
|
.ctx_lock = __SPIN_LOCK_UNLOCKED(name.ctx_lock), \
|
|
.reqs_active = 0U, \
|
|
.max_reqs = ~0U, \
|
|
}
|
|
|
|
#define INIT_MM(name) \
|
|
{ \
|
|
.mm_rb = RB_ROOT, \
|
|
.pgd = swapper_pg_dir, \
|
|
.mm_users = ATOMIC_INIT(2), \
|
|
.mm_count = ATOMIC_INIT(1), \
|
|
.mmap_sem = __RWSEM_INITIALIZER(name.mmap_sem), \
|
|
.page_table_lock = __SPIN_LOCK_UNLOCKED(name.page_table_lock), \
|
|
.mmlist = LIST_HEAD_INIT(name.mmlist), \
|
|
.cpu_vm_mask = CPU_MASK_ALL, \
|
|
}
|
|
|
|
#define INIT_SIGNALS(sig) { \
|
|
.count = ATOMIC_INIT(1), \
|
|
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
|
|
.shared_pending = { \
|
|
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
|
|
.signal = {{0}}}, \
|
|
.posix_timers = LIST_HEAD_INIT(sig.posix_timers), \
|
|
.cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
|
|
.rlim = INIT_RLIMITS, \
|
|
.pgrp = 0, \
|
|
.tty_old_pgrp = NULL, \
|
|
{ .__session = 0}, \
|
|
}
|
|
|
|
extern struct nsproxy init_nsproxy;
|
|
#define INIT_NSPROXY(nsproxy) { \
|
|
.pid_ns = &init_pid_ns, \
|
|
.count = ATOMIC_INIT(1), \
|
|
.nslock = __SPIN_LOCK_UNLOCKED(nsproxy.nslock), \
|
|
.uts_ns = &init_uts_ns, \
|
|
.mnt_ns = NULL, \
|
|
INIT_IPC_NS(ipc_ns) \
|
|
}
|
|
|
|
#define INIT_SIGHAND(sighand) { \
|
|
.count = ATOMIC_INIT(1), \
|
|
.action = { { { .sa_handler = NULL, } }, }, \
|
|
.siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \
|
|
.signalfd_list = LIST_HEAD_INIT(sighand.signalfd_list), \
|
|
}
|
|
|
|
extern struct group_info init_groups;
|
|
|
|
#define INIT_STRUCT_PID { \
|
|
.count = ATOMIC_INIT(1), \
|
|
.nr = 0, \
|
|
/* Don't put this struct pid in pid_hash */ \
|
|
.pid_chain = { .next = NULL, .pprev = NULL }, \
|
|
.tasks = { \
|
|
{ .first = &init_task.pids[PIDTYPE_PID].node }, \
|
|
{ .first = &init_task.pids[PIDTYPE_PGID].node }, \
|
|
{ .first = &init_task.pids[PIDTYPE_SID].node }, \
|
|
}, \
|
|
.rcu = RCU_HEAD_INIT, \
|
|
}
|
|
|
|
#define INIT_PID_LINK(type) \
|
|
{ \
|
|
.node = { \
|
|
.next = NULL, \
|
|
.pprev = &init_struct_pid.tasks[type].first, \
|
|
}, \
|
|
.pid = &init_struct_pid, \
|
|
}
|
|
|
|
/*
|
|
* INIT_TASK is used to set up the first task table, touch at
|
|
* your own risk!. Base=0, limit=0x1fffff (=2MB)
|
|
*/
|
|
#define INIT_TASK(tsk) \
|
|
{ \
|
|
.state = 0, \
|
|
.stack = &init_thread_info, \
|
|
.usage = ATOMIC_INIT(2), \
|
|
.flags = 0, \
|
|
.lock_depth = -1, \
|
|
.prio = MAX_PRIO-20, \
|
|
.static_prio = MAX_PRIO-20, \
|
|
.normal_prio = MAX_PRIO-20, \
|
|
.policy = SCHED_NORMAL, \
|
|
.cpus_allowed = CPU_MASK_ALL, \
|
|
.mm = NULL, \
|
|
.active_mm = &init_mm, \
|
|
.run_list = LIST_HEAD_INIT(tsk.run_list), \
|
|
.ioprio = 0, \
|
|
.time_slice = HZ, \
|
|
.tasks = LIST_HEAD_INIT(tsk.tasks), \
|
|
.ptrace_children= LIST_HEAD_INIT(tsk.ptrace_children), \
|
|
.ptrace_list = LIST_HEAD_INIT(tsk.ptrace_list), \
|
|
.real_parent = &tsk, \
|
|
.parent = &tsk, \
|
|
.children = LIST_HEAD_INIT(tsk.children), \
|
|
.sibling = LIST_HEAD_INIT(tsk.sibling), \
|
|
.group_leader = &tsk, \
|
|
.group_info = &init_groups, \
|
|
.cap_effective = CAP_INIT_EFF_SET, \
|
|
.cap_inheritable = CAP_INIT_INH_SET, \
|
|
.cap_permitted = CAP_FULL_SET, \
|
|
.keep_capabilities = 0, \
|
|
.user = INIT_USER, \
|
|
.comm = "swapper", \
|
|
.thread = INIT_THREAD, \
|
|
.fs = &init_fs, \
|
|
.files = &init_files, \
|
|
.signal = &init_signals, \
|
|
.sighand = &init_sighand, \
|
|
.nsproxy = &init_nsproxy, \
|
|
.pending = { \
|
|
.list = LIST_HEAD_INIT(tsk.pending.list), \
|
|
.signal = {{0}}}, \
|
|
.blocked = {{0}}, \
|
|
.alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
|
|
.journal_info = NULL, \
|
|
.cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
|
|
.fs_excl = ATOMIC_INIT(0), \
|
|
.pi_lock = __SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
|
|
.pids = { \
|
|
[PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
|
|
[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
|
|
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
|
|
}, \
|
|
INIT_TRACE_IRQFLAGS \
|
|
INIT_LOCKDEP \
|
|
}
|
|
|
|
|
|
#define INIT_CPU_TIMERS(cpu_timers) \
|
|
{ \
|
|
LIST_HEAD_INIT(cpu_timers[0]), \
|
|
LIST_HEAD_INIT(cpu_timers[1]), \
|
|
LIST_HEAD_INIT(cpu_timers[2]), \
|
|
}
|
|
|
|
|
|
#endif
|