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@xmailserver.org> - Davide Index: linux-2.6.21-rc5.fds/fs/aio.c =================================================================== --- linux-2.6.21-rc5.fds.orig/fs/aio.c 2007-03-31 12:45:30.000000000 -0700 +++ linux-2.6.21-rc5.fds/fs/aio.c 2007-03-31 12:46:31.000000000 -0700 @@ -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> @@ -421,6 +422,7 @@ 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. @@ -462,6 +464,8 @@ { 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) @@ -946,6 +950,14 @@ 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. @@ -1555,6 +1567,19 @@ 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); Index: linux-2.6.21-rc5.fds/include/linux/aio.h =================================================================== --- linux-2.6.21-rc5.fds.orig/include/linux/aio.h 2007-03-31 12:45:30.000000000 -0700 +++ linux-2.6.21-rc5.fds/include/linux/aio.h 2007-03-31 12:46:31.000000000 -0700 @@ -119,6 +119,12 @@ 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) Index: linux-2.6.21-rc5.fds/include/linux/aio_abi.h =================================================================== --- linux-2.6.21-rc5.fds.orig/include/linux/aio_abi.h 2007-03-31 12:45:30.000000000 -0700 +++ linux-2.6.21-rc5.fds/include/linux/aio_abi.h 2007-03-31 12:46:31.000000000 -0700 @@ -84,7 +84,11 @@ /* 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 - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
