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>

4 files changed, 37 insertions, 5 deletions

diff --git a/kernel/exit.c b/kernel/exit.c
index e93691e9b325..c6d14b8008dd 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -24,6 +24,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/ptrace.h>
 #include <linux/profile.h>
+#include <linux/signalfd.h>
 #include <linux/mount.h>
 #include <linux/proc_fs.h>
 #include <linux/kthread.h>
@@ -83,6 +84,14 @@ static void __exit_signal(struct task_struct *tsk)
         sighand = rcu_dereference(tsk->sighand);
         spin_lock(&sighand->siglock);
 
+        /*
+         * Notify that this sighand has been detached. This must
+         * be called with the tsk->sighand lock held. Also, this
+         * access tsk->sighand internally, so it must be called
+         * before tsk->sighand is reset.
+         */
+        signalfd_detach_locked(tsk);
+
         posix_cpu_timers_exit(tsk);
         if (atomic_dec_and_test(&sig->count))
                 posix_cpu_timers_exit_group(tsk);
diff --git a/kernel/fork.c b/kernel/fork.c
index 083bf8953ce8..49530e40ea8b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1422,12 +1422,15 @@ long do_fork(unsigned long clone_flags,
 #define ARCH_MIN_MMSTRUCT_ALIGN 0
 #endif
 
-static void sighand_ctor(void *data, struct kmem_cache *cachep, unsigned long flags)
+static void sighand_ctor(void *data, struct kmem_cache *cachep,
+                        unsigned long flags)
 {
         struct sighand_struct *sighand = data;
 
-        if (flags & SLAB_CTOR_CONSTRUCTOR)
+        if (flags & SLAB_CTOR_CONSTRUCTOR) {
                 spin_lock_init(&sighand->siglock);
+                INIT_LIST_HEAD(&sighand->signalfd_list);
+        }
 }
 
 void __init proc_caches_init(void)
@@ -1453,7 +1456,6 @@ void __init proc_caches_init(void)
                         SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL);
 }
 
-
 /*
  * Check constraints on flags passed to the unshare system call and
  * force unsharing of additional process context as appropriate.
diff --git a/kernel/signal.c b/kernel/signal.c
index 2ac3a668d9dd..34b7d6abce8f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -21,6 +21,7 @@
 #include <linux/syscalls.h>
 #include <linux/ptrace.h>
 #include <linux/signal.h>
+#include <linux/signalfd.h>
 #include <linux/capability.h>
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
@@ -113,8 +114,7 @@ void recalc_sigpending(void)
 
 /* Given the mask, find the first available signal that should be serviced. */
 
-static int
-next_signal(struct sigpending *pending, sigset_t *mask)
+int next_signal(struct sigpending *pending, sigset_t *mask)
 {
         unsigned long i, *s, *m, x;
         int sig = 0;
@@ -630,6 +630,12 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
         int ret = 0;
 
         /*
+         * Deliver the signal to listening signalfds. This must be called
+         * with the sighand lock held.
+         */
+        signalfd_notify(t, sig);
+
+        /*
          * fast-pathed signals for kernel-internal things like SIGSTOP
          * or SIGKILL.
          */
@@ -1280,6 +1286,11 @@ int send_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
                 ret = 1;
                 goto out;
         }
+        /*
+         * Deliver the signal to listening signalfds. This must be called
+         * with the sighand lock held.
+         */
+        signalfd_notify(p, sig);
 
         list_add_tail(&q->list, &p->pending.list);
         sigaddset(&p->pending.signal, sig);
@@ -1323,6 +1334,11 @@ send_group_sigqueue(int sig, struct sigqueue *q, struct task_struct *p)
                 q->info.si_overrun++;
                 goto out;
         } 
+        /*
+         * Deliver the signal to listening signalfds. This must be called
+         * with the sighand lock held.
+         */
+        signalfd_notify(p, sig);
 
         /*
          * Put this signal on the shared-pending queue.
@@ -1983,6 +1999,8 @@ int copy_siginfo_to_user(siginfo_t __user *to, siginfo_t *from)
         /*
          * If you change siginfo_t structure, please be sure
          * this code is fixed accordingly.
+         * Please remember to update the signalfd_copyinfo() function
+         * inside fs/signalfd.c too, in case siginfo_t changes.
          * It should never copy any pad contained in the structure
          * to avoid security leaks, but must copy the generic
          * 3 ints plus the relevant union member.
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d7306d0f3dfc..807e9bb8fcdb 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -141,3 +141,6 @@ cond_syscall(compat_sys_migrate_pages);
 cond_syscall(sys_bdflush);
 cond_syscall(sys_ioprio_set);
 cond_syscall(sys_ioprio_get);
+
+/* New file descriptors */
+cond_syscall(sys_signalfd);