d80e731eca
This patch is intentionally incomplete to simplify the review. It ignores ep_unregister_pollwait() which plays with the same wqh. See the next change. epoll assumes that the EPOLL_CTL_ADD'ed file controls everything f_op->poll() needs. In particular it assumes that the wait queue can't go away until eventpoll_release(). This is not true in case of signalfd, the task which does EPOLL_CTL_ADD uses its ->sighand which is not connected to the file. This patch adds the special event, POLLFREE, currently only for epoll. It expects that init_poll_funcptr()'ed hook should do the necessary cleanup. Perhaps it should be defined as EPOLLFREE in eventpoll. __cleanup_sighand() is changed to do wake_up_poll(POLLFREE) if ->signalfd_wqh is not empty, we add the new signalfd_cleanup() helper. ep_poll_callback(POLLFREE) simply does list_del_init(task_list). This make this poll entry inconsistent, but we don't care. If you share epoll fd which contains our sigfd with another process you should blame yourself. signalfd is "really special". I simply do not know how we can define the "right" semantics if it used with epoll. The main problem is, epoll calls signalfd_poll() once to establish the connection with the wait queue, after that signalfd_poll(NULL) returns the different/inconsistent results depending on who does EPOLL_CTL_MOD/signalfd_read/etc. IOW: apart from sigmask, signalfd has nothing to do with the file, it works with the current thread. In short: this patch is the hack which tries to fix the symptoms. It also assumes that nobody can take tasklist_lock under epoll locks, this seems to be true. Note: - we do not have wake_up_all_poll() but wake_up_poll() is fine, poll/epoll doesn't use WQ_FLAG_EXCLUSIVE. - signalfd_cleanup() uses POLLHUP along with POLLFREE, we need a couple of simple changes in eventpoll.c to make sure it can't be "lost". Reported-by: Maxime Bizon <mbizon@freebox.fr> Cc: <stable@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
77 lines
1.6 KiB
C
77 lines
1.6 KiB
C
/*
|
|
* include/linux/signalfd.h
|
|
*
|
|
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
|
|
*
|
|
*/
|
|
|
|
#ifndef _LINUX_SIGNALFD_H
|
|
#define _LINUX_SIGNALFD_H
|
|
|
|
#include <linux/types.h>
|
|
/* For O_CLOEXEC and O_NONBLOCK */
|
|
#include <linux/fcntl.h>
|
|
|
|
/* Flags for signalfd4. */
|
|
#define SFD_CLOEXEC O_CLOEXEC
|
|
#define SFD_NONBLOCK O_NONBLOCK
|
|
|
|
struct signalfd_siginfo {
|
|
__u32 ssi_signo;
|
|
__s32 ssi_errno;
|
|
__s32 ssi_code;
|
|
__u32 ssi_pid;
|
|
__u32 ssi_uid;
|
|
__s32 ssi_fd;
|
|
__u32 ssi_tid;
|
|
__u32 ssi_band;
|
|
__u32 ssi_overrun;
|
|
__u32 ssi_trapno;
|
|
__s32 ssi_status;
|
|
__s32 ssi_int;
|
|
__u64 ssi_ptr;
|
|
__u64 ssi_utime;
|
|
__u64 ssi_stime;
|
|
__u64 ssi_addr;
|
|
__u16 ssi_addr_lsb;
|
|
|
|
/*
|
|
* Pad strcture to 128 bytes. Remember to update the
|
|
* pad size when you add new members. 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[46];
|
|
};
|
|
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#ifdef CONFIG_SIGNALFD
|
|
|
|
/*
|
|
* Deliver the signal to listening signalfd.
|
|
*/
|
|
static inline void signalfd_notify(struct task_struct *tsk, int sig)
|
|
{
|
|
if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh)))
|
|
wake_up(&tsk->sighand->signalfd_wqh);
|
|
}
|
|
|
|
extern void signalfd_cleanup(struct sighand_struct *sighand);
|
|
|
|
#else /* CONFIG_SIGNALFD */
|
|
|
|
static inline void signalfd_notify(struct task_struct *tsk, int sig) { }
|
|
|
|
static inline void signalfd_cleanup(struct sighand_struct *sighand) { }
|
|
|
|
#endif /* CONFIG_SIGNALFD */
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* _LINUX_SIGNALFD_H */
|