aboutsummaryrefslogtreecommitdiffstats
path: root/fs/eventpoll.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/eventpoll.c')
-rw-r--r--fs/eventpoll.c75
1 files changed, 59 insertions, 16 deletions
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1c8b5567080..9fec1836057 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -38,6 +38,8 @@
#include <asm/io.h>
#include <asm/mman.h>
#include <linux/atomic.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
/*
* LOCKING:
@@ -783,8 +785,34 @@ static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
return pollflags != -1 ? pollflags : 0;
}
+#ifdef CONFIG_PROC_FS
+static int ep_show_fdinfo(struct seq_file *m, struct file *f)
+{
+ struct eventpoll *ep = f->private_data;
+ struct rb_node *rbp;
+ int ret = 0;
+
+ mutex_lock(&ep->mtx);
+ for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+ struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
+
+ ret = seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+ epi->ffd.fd, epi->event.events,
+ (long long)epi->event.data);
+ if (ret)
+ break;
+ }
+ mutex_unlock(&ep->mtx);
+
+ return ret;
+}
+#endif
+
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
+#ifdef CONFIG_PROC_FS
+ .show_fdinfo = ep_show_fdinfo,
+#endif
.release = ep_eventpoll_release,
.poll = ep_eventpoll_poll,
.llseek = noop_llseek,
@@ -1285,7 +1313,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
* otherwise we might miss an event that happens between the
* f_op->poll() call and the new event set registering.
*/
- epi->event.events = event->events;
+ epi->event.events = event->events; /* need barrier below */
pt._key = event->events;
epi->event.data = event->data; /* protected by mtx */
if (epi->event.events & EPOLLWAKEUP) {
@@ -1296,6 +1324,26 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_even
}
/*
+ * The following barrier has two effects:
+ *
+ * 1) Flush epi changes above to other CPUs. This ensures
+ * we do not miss events from ep_poll_callback if an
+ * event occurs immediately after we call f_op->poll().
+ * We need this because we did not take ep->lock while
+ * changing epi above (but ep_poll_callback does take
+ * ep->lock).
+ *
+ * 2) We also need to ensure we do not miss _past_ events
+ * when calling f_op->poll(). This barrier also
+ * pairs with the barrier in wq_has_sleeper (see
+ * comments for wq_has_sleeper).
+ *
+ * This barrier will now guarantee ep_poll_callback or f_op->poll
+ * (or both) will notice the readiness of an item.
+ */
+ smp_mb();
+
+ /*
* Get current event bits. We can safely use the file* here because
* its usage count has been increased by the caller of this function.
*/
@@ -1654,8 +1702,8 @@ SYSCALL_DEFINE1(epoll_create1, int, flags)
error = PTR_ERR(file);
goto out_free_fd;
}
- fd_install(fd, file);
ep->file = file;
+ fd_install(fd, file);
return fd;
out_free_fd:
@@ -1810,7 +1858,7 @@ SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout)
{
int error;
- struct file *file;
+ struct fd f;
struct eventpoll *ep;
/* The maximum number of event must be greater than zero */
@@ -1818,38 +1866,33 @@ SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
return -EINVAL;
/* Verify that the area passed by the user is writeable */
- if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event))) {
- error = -EFAULT;
- goto error_return;
- }
+ if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event)))
+ return -EFAULT;
/* Get the "struct file *" for the eventpoll file */
- error = -EBADF;
- file = fget(epfd);
- if (!file)
- goto error_return;
+ f = fdget(epfd);
+ if (!f.file)
+ return -EBADF;
/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
error = -EINVAL;
- if (!is_file_epoll(file))
+ if (!is_file_epoll(f.file))
goto error_fput;
/*
* At this point it is safe to assume that the "private_data" contains
* our own data structure.
*/
- ep = file->private_data;
+ ep = f.file->private_data;
/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);
error_fput:
- fput(file);
-error_return:
-
+ fdput(f);
return error;
}