The patch titled
signal/timer/event: KAIO eventfd support example
has been added to the -mm tree. Its filename is
signal-timer-event-fds-v9-kaio-eventfd-support-example.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: signal/timer/event: KAIO eventfd support example
From: Davide Libenzi <davidel@xxxxxxxxxxxxxxx>
This is an example about how to add eventfd support to the current KAIO code,
in order to enable KAIO to post readiness events to a pollable fd (hence
compatible with POSIX select/poll). The KAIO code simply signals the eventfd
fd when events are ready, and this triggers a POLLIN in the fd. This patch
uses a reserved for future use member of the struct iocb to pass an eventfd
file descriptor, that KAIO will use to post events every time a request
completes. At that point, an aio_getevents() will return the completed result
to a struct io_event. I made a quick test program to verify the patch, and it
runs fine here:
http://www.xmailserver.org/eventfd-aio-test.c
The test program uses poll(2), but it'd, of course, work with select and epoll
too.
This can allow to schedule both block I/O and other poll-able devices
requests, and wait for results using select/poll/epoll. In a typical
scenario, an application would submit KAIO request using aio_submit(), and
will also use epoll_ctl() on the whole other class of devices (that with the
addition of signals, timers and user events, now it's pretty much complete),
and then would:
epoll_wait(...);
for_each_event {
if (curr_event_is_kaiofd) {
aio_getevents();
dispatch_aio_events();
} else {
dispatch_epoll_event();
}
}
Signed-off-by: Davide Libenzi <davidel@xxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/aio.c | 25 +++++++++++++++++++++++++
include/linux/aio.h | 6 ++++++
include/linux/aio_abi.h | 6 +++++-
3 files changed, 36 insertions(+), 1 deletion(-)
diff -puN fs/aio.c~signal-timer-event-fds-v9-kaio-eventfd-support-example fs/aio.c
--- a/fs/aio.c~signal-timer-event-fds-v9-kaio-eventfd-support-example
+++ a/fs/aio.c
@@ -30,6 +30,7 @@
#include <linux/highmem.h>
#include <linux/workqueue.h>
#include <linux/security.h>
+#include <linux/eventfd.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
@@ -419,6 +420,7 @@ static struct kiocb fastcall *__aio_get_
req->private = NULL;
req->ki_iovec = NULL;
INIT_LIST_HEAD(&req->ki_run_list);
+ req->ki_eventfd = ERR_PTR(-EINVAL);
/* Check if the completion queue has enough free space to
* accept an event from this io.
@@ -460,6 +462,8 @@ static inline void really_put_req(struct
{
assert_spin_locked(&ctx->ctx_lock);
+ if (!IS_ERR(req->ki_eventfd))
+ fput(req->ki_eventfd);
if (req->ki_dtor)
req->ki_dtor(req);
if (req->ki_iovec != &req->ki_inline_vec)
@@ -944,6 +948,14 @@ int fastcall aio_complete(struct kiocb *
return 1;
}
+ /*
+ * Check if the user asked us to deliver the result through an
+ * eventfd. The eventfd_signal() function is safe to be called
+ * from IRQ context.
+ */
+ if (!IS_ERR(iocb->ki_eventfd))
+ eventfd_signal(iocb->ki_eventfd, 1);
+
info = &ctx->ring_info;
/* add a completion event to the ring buffer.
@@ -1553,6 +1565,19 @@ int fastcall io_submit_one(struct kioctx
fput(file);
return -EAGAIN;
}
+ if (iocb->aio_resfd != 0) {
+ /*
+ * If the aio_resfd field of the iocb is not zero, get an
+ * instance of the file* now. The file descriptor must be
+ * an eventfd() fd, and will be signaled for each completed
+ * event using the eventfd_signal() function.
+ */
+ req->ki_eventfd = eventfd_fget((int) iocb->aio_resfd);
+ if (IS_ERR(req->ki_eventfd)) {
+ ret = PTR_ERR(req->ki_eventfd);
+ goto out_put_req;
+ }
+ }
req->ki_filp = file;
ret = put_user(req->ki_key, &user_iocb->aio_key);
diff -puN include/linux/aio.h~signal-timer-event-fds-v9-kaio-eventfd-support-example include/linux/aio.h
--- a/include/linux/aio.h~signal-timer-event-fds-v9-kaio-eventfd-support-example
+++ a/include/linux/aio.h
@@ -119,6 +119,12 @@ struct kiocb {
struct list_head ki_list; /* the aio core uses this
* for cancellation */
+
+ /*
+ * If the aio_resfd field of the userspace iocb is not zero,
+ * this is the underlying file* to deliver event to.
+ */
+ struct file *ki_eventfd;
};
#define is_sync_kiocb(iocb) ((iocb)->ki_key == KIOCB_SYNC_KEY)
diff -puN include/linux/aio_abi.h~signal-timer-event-fds-v9-kaio-eventfd-support-example include/linux/aio_abi.h
--- a/include/linux/aio_abi.h~signal-timer-event-fds-v9-kaio-eventfd-support-example
+++ a/include/linux/aio_abi.h
@@ -84,7 +84,11 @@ struct iocb {
/* extra parameters */
__u64 aio_reserved2; /* TODO: use this for a (struct sigevent *) */
- __u64 aio_reserved3;
+ __u32 aio_reserved3;
+ /*
+ * If different from 0, this is an eventfd to deliver AIO results to
+ */
+ __u32 aio_resfd;
}; /* 64 bytes */
#undef IFBIG
_
Patches currently in -mm which might be from davidel@xxxxxxxxxxxxxxx are
origin.patch
epoll-optimizations-and-cleanups.patch
epoll-optimizations-and-cleanups-tidy.patch
signal-timer-event-fds-v9-anonymous-inode-source.patch
signal-timer-event-fds-v9-signalfd-core.patch
signal-timer-event-fds-v9-signalfd-wire-up-i386-arch.patch
signal-timer-event-fds-v9-signalfd-wire-up-x86_64-arch.patch
signal-timer-event-fds-v9-signalfd-compat-code.patch
signal-timer-event-fds-v9-timerfd-core.patch
signal-timer-event-fds-v9-timerfd-wire-up-i386-arch.patch
signal-timer-event-fds-v9-timerfd-wire-up-x86_64-arch.patch
signal-timer-event-fds-v9-timerfd-compat-code.patch
signal-timer-event-fds-v9-eventfd-core.patch
signal-timer-event-fds-v9-eventfd-wire-up-i386-arch.patch
signal-timer-event-fds-v9-eventfd-wire-up-x86_64-arch.patch
signal-timer-event-fds-v9-kaio-eventfd-support-example.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
