From 7a074e96dee62586c935c80cecd931431bfdd0be Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 2 May 2018 19:51:00 +0200
Subject: aio: implement io_pgetevents
This is the io_getevents equivalent of ppoll/pselect and allows to
properly mix signals and aio completions (especially with IOCB_CMD_POLL)
and atomically executes the following sequence:
sigset_t origmask;
pthread_sigmask(SIG_SETMASK, &sigmask, &origmask);
ret = io_getevents(ctx, min_nr, nr, events, timeout);
pthread_sigmask(SIG_SETMASK, &origmask, NULL);
Note that unlike many other signal related calls we do not pass a sigmask
size, as that would get us to 7 arguments, which aren't easily supported
by the syscall infrastructure. It seems a lot less painful to just add a
new syscall variant in the unlikely case we're going to increase the
sigset size.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
include/uapi/linux/aio_abi.h | 6 ++++++
1 file changed, 6 insertions(+)
(limited to 'include/uapi/linux')
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index a04adbc70ddf..2c0a3415beee 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -29,6 +29,7 @@
#include <linux/types.h>
#include <linux/fs.h>
+#include <linux/signal.h>
#include <asm/byteorder.h>
typedef __kernel_ulong_t aio_context_t;
@@ -108,5 +109,10 @@ struct iocb {
#undef IFBIG
#undef IFLITTLE
+struct __aio_sigset {
+ sigset_t __user *sigmask;
+ size_t sigsetsize;
+};
+
#endif /* __LINUX__AIO_ABI_H */
--
cgit v1.2.3
From ee219b946e4bf7df2d2c68dfaae1bdaa360ec2ea Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 23 May 2018 17:42:59 +0200
Subject: uapi: turn __poll_t sparse checks on by default
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
include/uapi/linux/types.h | 4 ----
1 file changed, 4 deletions(-)
(limited to 'include/uapi/linux')
diff --git a/include/uapi/linux/types.h b/include/uapi/linux/types.h
index cd4f0b897a48..2fce8b6876e9 100644
--- a/include/uapi/linux/types.h
+++ b/include/uapi/linux/types.h
@@ -49,11 +49,7 @@ typedef __u32 __bitwise __wsum;
#define __aligned_be64 __be64 __attribute__((aligned(8)))
#define __aligned_le64 __le64 __attribute__((aligned(8)))
-#ifdef __CHECK_POLL
typedef unsigned __bitwise __poll_t;
-#else
-typedef unsigned __poll_t;
-#endif
#endif /* __ASSEMBLY__ */
#endif /* _UAPI_LINUX_TYPES_H */
--
cgit v1.2.3
From 2c14fa838cbefc23cf1c73ca167ed85b274b2913 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 20 Mar 2018 16:34:36 +0100
Subject: aio: implement IOCB_CMD_POLL
Simple one-shot poll through the io_submit() interface. To poll for
a file descriptor the application should submit an iocb of type
IOCB_CMD_POLL. It will poll the fd for the events specified in the
the first 32 bits of the aio_buf field of the iocb.
Unlike poll or epoll without EPOLLONESHOT this interface always works
in one shot mode, that is once the iocb is completed, it will have to be
resubmitted.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
---
fs/aio.c | 134 ++++++++++++++++++++++++++++++++++++++++++-
include/uapi/linux/aio_abi.h | 6 +-
2 files changed, 135 insertions(+), 5 deletions(-)
(limited to 'include/uapi/linux')
diff --git a/fs/aio.c b/fs/aio.c
index 0633cf3b325c..bd711cfa4a1f 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
* Implements an efficient asynchronous io interface.
*
* Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright 2018 Christoph Hellwig.
*
* See ../COPYING for licensing terms.
*/
@@ -164,10 +165,22 @@ struct fsync_iocb {
bool datasync;
};
+struct poll_iocb {
+ struct file *file;
+ __poll_t events;
+ struct wait_queue_head *head;
+
+ union {
+ struct wait_queue_entry wait;
+ struct work_struct work;
+ };
+};
+
struct aio_kiocb {
union {
struct kiocb rw;
struct fsync_iocb fsync;
+ struct poll_iocb poll;
};
struct kioctx *ki_ctx;
@@ -1558,7 +1571,6 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes ||
iocb->aio_rw_flags))
return -EINVAL;
-
req->file = fget(iocb->aio_fildes);
if (unlikely(!req->file))
return -EBADF;
@@ -1573,6 +1585,124 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
return -EIOCBQUEUED;
}
+/* need to use list_del_init so we can check if item was present */
+static inline bool __aio_poll_remove(struct poll_iocb *req)
+{
+ if (list_empty(&req->wait.entry))
+ return false;
+ list_del_init(&req->wait.entry);
+ return true;
+}
+
+static inline void __aio_poll_complete(struct poll_iocb *req, __poll_t mask)
+{
+ struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+ struct file *file = req->file;
+
+ aio_complete(iocb, mangle_poll(mask), 0);
+ fput(file);
+}
+
+static void aio_poll_work(struct work_struct *work)
+{
+ struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+
+ __aio_poll_complete(req, req->events);
+}
+
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+ struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+ struct poll_iocb *req = &aiocb->poll;
+ struct wait_queue_head *head = req->head;
+ bool found = false;
+
+ spin_lock(&head->lock);
+ found = __aio_poll_remove(req);
+ spin_unlock(&head->lock);
+
+ if (found) {
+ req->events = 0;
+ INIT_WORK(&req->work, aio_poll_work);
+ schedule_work(&req->work);
+ }
+ return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+ struct file *file = req->file;
+ __poll_t mask = key_to_poll(key);
+
+ assert_spin_locked(&req->head->lock);
+
+ /* for instances that support it check for an event match first: */
+ if (mask && !(mask & req->events))
+ return 0;
+
+ mask = file->f_op->poll_mask(file, req->events);
+ if (!mask)
+ return 0;
+
+ __aio_poll_remove(req);
+
+ req->events = mask;
+ INIT_WORK(&req->work, aio_poll_work);
+ schedule_work(&req->work);
+ return 1;
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+ struct kioctx *ctx = aiocb->ki_ctx;
+ struct poll_iocb *req = &aiocb->poll;
+ __poll_t mask;
+
+ /* reject any unknown events outside the normal event mask. */
+ if ((u16)iocb->aio_buf != iocb->aio_buf)
+ return -EINVAL;
+ /* reject fields that are not defined for poll */
+ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+ return -EINVAL;
+
+ req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+ req->file = fget(iocb->aio_fildes);
+ if (unlikely(!req->file))
+ return -EBADF;
+ if (!file_has_poll_mask(req->file))
+ goto out_fail;
+
+ req->head = req->file->f_op->get_poll_head(req->file, req->events);
+ if (!req->head)
+ goto out_fail;
+ if (IS_ERR(req->head)) {
+ mask = EPOLLERR;
+ goto done;
+ }
+
+ init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+ aiocb->ki_cancel = aio_poll_cancel;
+
+ spin_lock_irq(&ctx->ctx_lock);
+ spin_lock(&req->head->lock);
+ mask = req->file->f_op->poll_mask(req->file, req->events);
+ if (!mask) {
+ __add_wait_queue(req->head, &req->wait);
+ list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+ }
+ spin_unlock(&req->head->lock);
+ spin_unlock_irq(&ctx->ctx_lock);
+done:
+ if (mask)
+ __aio_poll_complete(req, mask);
+ return -EIOCBQUEUED;
+out_fail:
+ fput(req->file);
+ return -EINVAL; /* same as no support for IOCB_CMD_POLL */
+}
+
static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
{
@@ -1641,6 +1771,8 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
break;
case IOCB_CMD_FDSYNC:
ret = aio_fsync(&req->fsync, iocb, true);
+ case IOCB_CMD_POLL:
+ ret = aio_poll(req, iocb);
break;
default:
pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode);
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index 2c0a3415beee..ed0185945bb2 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -39,10 +39,8 @@ enum {
IOCB_CMD_PWRITE = 1,
IOCB_CMD_FSYNC = 2,
IOCB_CMD_FDSYNC = 3,
- /* These two are experimental.
- * IOCB_CMD_PREADX = 4,
- * IOCB_CMD_POLL = 5,
- */
+ /* 4 was the experimental IOCB_CMD_PREADX */
+ IOCB_CMD_POLL = 5,
IOCB_CMD_NOOP = 6,
IOCB_CMD_PREADV = 7,
IOCB_CMD_PWRITEV = 8,
--
cgit v1.2.3