signal/timer/event: signalfd core

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>

6 files changed, 102 insertions, 0 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 645b3b528150..bcd01f269f60 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -190,6 +190,7 @@ unifdef-y += errno.h
 unifdef-y += errqueue.h
 unifdef-y += ethtool.h
 unifdef-y += eventpoll.h
+unifdef-y += signalfd.h
 unifdef-y += ext2_fs.h
 unifdef-y += ext3_fs.h
 unifdef-y += fb.h
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 66e2f0a70814..276ccaa2670c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -84,6 +84,7 @@ extern struct nsproxy init_nsproxy;
         .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;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 75f44379b7e9..97c0c7da58ef 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -391,6 +391,7 @@ struct sighand_struct {
         atomic_t                count;
         struct k_sigaction      action[_NSIG];
         spinlock_t              siglock;
+        struct list_head        signalfd_list;
 };
 
 struct pacct_struct {
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 3fa0fab4a04b..9a5eac508e5e 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -233,6 +233,7 @@ 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);
diff --git a/include/linux/signalfd.h b/include/linux/signalfd.h
new file mode 100644
index 000000000000..510429495690
--- /dev/null
+++ b/include/linux/signalfd.h
@@ -0,0 +1,97 @@
+/*
+ *  include/linux/signalfd.h
+ *
+ *  Copyright (C) 2007  Davide Libenzi <davidel@xmailserver.org>
+ *
+ */
+
+#ifndef _LINUX_SIGNALFD_H
+#define _LINUX_SIGNALFD_H
+
+
+struct signalfd_siginfo {
+        __u32 signo;
+        __s32 err;
+        __s32 code;
+        __u32 pid;
+        __u32 uid;
+        __s32 fd;
+        __u32 tid;
+        __u32 band;
+        __u32 overrun;
+        __u32 trapno;
+        __s32 status;
+        __s32 svint;
+        __u64 svptr;
+        __u64 utime;
+        __u64 stime;
+        __u64 addr;
+
+        /*
+         * Pad strcture to 128 bytes. Remember to update the
+         * pad size when you add new memebers. We use a fixed
+         * size structure to avoid compatibility problems with
+         * future versions, and we leave extra space for additional
+         * members. We use fixed size members because this strcture
+         * comes out of a read(2) and we really don't want to have
+         * a compat on read(2).
+         */
+        __u8 __pad[48];
+};
+
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_SIGNALFD
+
+/*
+ * Deliver the signal to listening signalfd. This must be called
+ * with the sighand lock held. Same are the following that end up
+ * calling signalfd_deliver().
+ */
+void signalfd_deliver(struct task_struct *tsk, int sig);
+
+/*
+ * No need to fall inside signalfd_deliver() if no signal listeners
+ * are available.
+ */
+static inline void signalfd_notify(struct task_struct *tsk, int sig)
+{
+        if (unlikely(!list_empty(&tsk->sighand->signalfd_list)))
+                signalfd_deliver(tsk, sig);
+}
+
+/*
+ * The signal -1 is used to notify the signalfd that the sighand
+ * is on its way to be detached.
+ */
+static inline void signalfd_detach_locked(struct task_struct *tsk)
+{
+        if (unlikely(!list_empty(&tsk->sighand->signalfd_list)))
+                signalfd_deliver(tsk, -1);
+}
+
+static inline void signalfd_detach(struct task_struct *tsk)
+{
+        struct sighand_struct *sighand = tsk->sighand;
+
+        if (unlikely(!list_empty(&sighand->signalfd_list))) {
+                spin_lock_irq(&sighand->siglock);
+                signalfd_deliver(tsk, -1);
+                spin_unlock_irq(&sighand->siglock);
+        }
+}
+
+#else /* CONFIG_SIGNALFD */
+
+#define signalfd_deliver(t, s) do { } while (0)
+#define signalfd_notify(t, s) do { } while (0)
+#define signalfd_detach_locked(t) do { } while (0)
+#define signalfd_detach(t) do { } while (0)
+
+#endif /* CONFIG_SIGNALFD */
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_SIGNALFD_H */
+
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 3139f4412297..e049f14a75b7 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -604,6 +604,7 @@ asmlinkage long sys_get_robust_list(int pid,
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
                                     size_t len);
 asmlinkage long sys_getcpu(unsigned __user *cpu, unsigned __user *node, struct getcpu_cache __user *cache);
+asmlinkage long sys_signalfd(int ufd, sigset_t __user *user_mask, size_t sizemask);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);