Re: [RFC PATCH]vhost-blk: In-kernel accelerator for virtio blockdevice

From: Liu Yuan
Date: Tue Aug 09 2011 - 22:20:06 EST

On 08/09/2011 01:16 AM, Badari Pulavarty wrote:
On 8/8/2011 12:31 AM, Liu Yuan wrote:
On 08/08/2011 01:04 PM, Badari Pulavarty wrote:
On 8/7/2011 6:35 PM, Liu Yuan wrote:
On 08/06/2011 02:02 AM, Badari Pulavarty wrote:
On 8/5/2011 4:04 AM, Liu Yuan wrote:
On 08/05/2011 05:58 AM, Badari Pulavarty wrote:
Hi Liu Yuan,

I started testing your patches. I applied your kernel patch to 3.0
and applied QEMU to latest git.

I passed 6 blockdevices from the host to guest (4 vcpu, 4GB RAM).
I ran simple "dd" read tests from the guest on all block devices
(with various blocksizes, iflag=direct).

Unfortunately, system doesn't stay up. I immediately get into
panic on the host. I didn't get time to debug the problem. Wondering
if you have seen this issue before and/or you have new patchset
to try ?

Let me know.

Thanks,
Badari


Okay, it is actually a bug pointed out by MST on the other thread, that it needs a mutex for completion thread.

Now would you please this attachment?This patch only applies to kernel part, on top of v1 kernel patch.

This patch mainly moves completion thread into vhost thread as a function. As a result, both requests submitting and completion signalling is in the same thread.

Yuan

Unfortunately, "dd" tests (4 out of 6) in the guest hung. I see following messages

virtio_blk virtio2: requests: id 0 is not a head !
virtio_blk virtio3: requests: id 1 is not a head !
virtio_blk virtio5: requests: id 1 is not a head !
virtio_blk virtio1: requests: id 1 is not a head !

I still see host panics. I will collect the host panic and see if its still same or not.

Thanks,
Badari


Would you please show me how to reproduce it step by step? I tried dd with two block device attached, but didn't get hung nor panic.

Yuan

I did 6 "dd"s on 6 block devices..

dd if=/dev/vdb of=/dev/null bs=1M iflag=direct &
dd if=/dev/vdc of=/dev/null bs=1M iflag=direct &
dd if=/dev/vdd of=/dev/null bs=1M iflag=direct &
dd if=/dev/vde of=/dev/null bs=1M iflag=direct &
dd if=/dev/vdf of=/dev/null bs=1M iflag=direct &
dd if=/dev/vdg of=/dev/null bs=1M iflag=direct &

I can reproduce the problem with in 3 minutes :(

Thanks,
Badari


Ah...I made an embarrassing mistake that I tried to 'free()' an kmem_cache object.

Would you please revert the vblk-for-kernel-2 patch and apply the new one attached in this letter?

Hmm.. My version of the code seems to have kzalloc() for used_info. I don't have a version
that is using kmem_cache_alloc(). Would it be possible for you to send out complete patch
(with all the fixes applied) for me to try ? This will avoid all the confusion ..

Thanks,
Badari


Okay, please apply the attached patch to the vanilla kernel. :)

Thanks,
Yuan
diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile
index 72dd020..31f8b2e 100644
--- a/drivers/vhost/Makefile
+++ b/drivers/vhost/Makefile
@@ -1,2 +1,5 @@
obj-$(CONFIG_VHOST_NET) += vhost_net.o
+obj-m += vhost_blk.o
+
vhost_net-y := vhost.o net.o
+vhost_blk-y := vhost.o blk.o
diff --git a/drivers/vhost/blk.c b/drivers/vhost/blk.c
new file mode 100644
index 0000000..c372011
--- /dev/null
+++ b/drivers/vhost/blk.c
@@ -0,0 +1,530 @@
+/* Copyright (C) 2011 Taobao, Inc.
+ * Author: Liu Yuan <tailai.ly@xxxxxxxxxx>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Vhost-blk driver is an in-kernel accelerator, intercepting the
+ * IO requests from KVM virtio-capable guests. It is based on the
+ * vhost infrastructure.
+ */
+
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/virtio_net.h>
+#include <linux/vhost.h>
+#include <linux/eventfd.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/virtio_blk.h>
+#include <linux/file.h>
+#include <linux/mmu_context.h>
+#include <linux/kthread.h>
+#include <linux/anon_inodes.h>
+#include <linux/syscalls.h>
+#include <linux/blkdev.h>
+
+#include "vhost.h"
+
+#define DEBUG 0
+
+#if DEBUG > 0
+#define dprintk printk
+#else
+#define dprintk(x...) do { ; } while (0)
+#endif
+
+enum {
+ virtqueue_max = 1,
+};
+
+#define MAX_EVENTS 128
+
+struct vhost_blk {
+ struct vhost_virtqueue vq;
+ struct vhost_dev dev;
+ int should_stop;
+ struct kioctx *ioctx;
+ struct eventfd_ctx *ectx;
+ struct file *efile;
+ struct task_struct *worker;
+ struct vhost_poll poll;
+};
+
+struct used_info {
+ void *status;
+ int head;
+ int len;
+};
+
+static struct io_event events[MAX_EVENTS];
+
+static struct kmem_cache *used_info_cachep;
+
+static void blk_flush(struct vhost_blk *blk)
+{
+ vhost_poll_flush(&blk->vq.poll);
+ vhost_poll_flush(&blk->poll);
+}
+
+static long blk_set_features(struct vhost_blk *blk, u64 features)
+{
+ blk->dev.acked_features = features;
+ return 0;
+}
+
+static void blk_stop(struct vhost_blk *blk)
+{
+ struct vhost_virtqueue *vq = &blk->vq;
+ struct file *f;
+
+ mutex_lock(&vq->mutex);
+ f = rcu_dereference_protected(vq->private_data,
+ lockdep_is_held(&vq->mutex));
+ rcu_assign_pointer(vq->private_data, NULL);
+ mutex_unlock(&vq->mutex);
+
+ if (f)
+ fput(f);
+}
+
+static long blk_set_backend(struct vhost_blk *blk, struct vhost_vring_file *backend)
+{
+ int idx = backend->index;
+ struct vhost_virtqueue *vq = &blk->vq;
+ struct file *file, *oldfile;
+ int ret;
+
+ mutex_lock(&blk->dev.mutex);
+ ret = vhost_dev_check_owner(&blk->dev);
+ if (ret)
+ goto err_dev;
+ if (idx >= virtqueue_max) {
+ ret = -ENOBUFS;
+ goto err_dev;
+ }
+
+ mutex_lock(&vq->mutex);
+
+ if (!vhost_vq_access_ok(vq)) {
+ ret = -EFAULT;
+ goto err_vq;
+ }
+
+ file = fget(backend->fd);
+ if (IS_ERR(file)) {
+ ret = PTR_ERR(file);
+ goto err_vq;
+ }
+
+ oldfile = rcu_dereference_protected(vq->private_data,
+ lockdep_is_held(&vq->mutex));
+ if (file != oldfile)
+ rcu_assign_pointer(vq->private_data, file);
+
+ mutex_unlock(&vq->mutex);
+
+ if (oldfile) {
+ blk_flush(blk);
+ fput(oldfile);
+ }
+
+ mutex_unlock(&blk->dev.mutex);
+ return 0;
+err_vq:
+ mutex_unlock(&vq->mutex);
+err_dev:
+ mutex_unlock(&blk->dev.mutex);
+ return ret;
+}
+
+static long blk_reset_owner(struct vhost_blk *b)
+{
+ int ret;
+
+ mutex_lock(&b->dev.mutex);
+ ret = vhost_dev_check_owner(&b->dev);
+ if (ret)
+ goto err;
+ blk_stop(b);
+ blk_flush(b);
+ ret = vhost_dev_reset_owner(&b->dev);
+err:
+ mutex_unlock(&b->dev.mutex);
+ return ret;
+}
+
+static int kernel_io_setup(unsigned nr_events, struct kioctx **ioctx)
+{
+ int ret = 0;
+ *ioctx = ioctx_alloc(nr_events);
+ if (IS_ERR(ioctx))
+ ret = PTR_ERR(ioctx);
+ return ret;
+}
+
+static inline int kernel_read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event *event,
+ struct timespec *ts)
+{
+ mm_segment_t old_fs;
+ int ret;
+
+ old_fs = get_fs();
+ set_fs(get_ds());
+ ret = read_events(ctx, min_nr, nr, event, ts);
+ set_fs(old_fs);
+
+ return ret;
+}
+
+static inline ssize_t io_event_ret(struct io_event *ev)
+{
+ return (ssize_t)(((uint64_t)ev->res2 << 32) | ev->res);
+}
+
+static inline void aio_prep_req(struct kiocb *iocb, struct eventfd_ctx *ectx, struct file *file,
+ struct iovec *iov, int nvecs, u64 offset, int opcode, struct used_info *ui)
+{
+ iocb->ki_filp = file;
+ iocb->ki_eventfd = ectx;
+ iocb->ki_pos = offset;
+ iocb->ki_buf = (void *)iov;
+ iocb->ki_left = iocb->ki_nbytes = nvecs;
+ iocb->ki_opcode = opcode;
+ iocb->ki_obj.user = ui;
+}
+
+static inline int kernel_io_submit(struct vhost_blk *blk, struct iovec *iov, u64 nvecs, loff_t pos, int opcode, int head, int len)
+{
+ int ret = -EAGAIN;
+ struct kiocb *req;
+ struct kioctx *ioctx = blk->ioctx;
+ struct used_info *ui = kmem_cache_zalloc(used_info_cachep, GFP_KERNEL);
+ struct file *f = blk->vq.private_data;
+
+ try_get_ioctx(ioctx);
+ atomic_long_inc_not_zero(&f->f_count);
+ eventfd_ctx_get(blk->ectx);
+
+
+ req = aio_get_req(ioctx); /* return 2 refs of req*/
+ if (unlikely(!req))
+ goto out;
+
+ ui->head = head;
+ ui->status = blk->vq.iov[nvecs + 1].iov_base;
+ ui->len = len;
+ aio_prep_req(req, blk->ectx, f, iov, nvecs, pos, opcode, ui);
+
+ ret = aio_setup_iocb(req, 0);
+ if (unlikely(ret))
+ goto out_put_req;
+
+ spin_lock_irq(&ioctx->ctx_lock);
+ if (unlikely(ioctx->dead)) {
+ spin_unlock_irq(&ioctx->ctx_lock);
+ ret = -EINVAL;
+ goto out_put_req;
+ }
+
+ aio_run_iocb(req);
+ if (!list_empty(&ioctx->run_list)) {
+ while (__aio_run_iocbs(ioctx))
+ ;
+ }
+ spin_unlock_irq(&ioctx->ctx_lock);
+
+ aio_put_req(req);
+ put_ioctx(blk->ioctx);
+
+ return ret;
+
+out_put_req:
+ aio_put_req(req);
+ aio_put_req(req);
+out:
+ put_ioctx(blk->ioctx);
+ return ret;
+}
+
+static long vhost_blk_ioctl(struct file *f, unsigned int ioctl,
+ unsigned long arg)
+{
+ struct vhost_blk *blk = f->private_data;
+ struct vhost_vring_file backend;
+ u64 features = VHOST_BLK_FEATURES;
+ int ret = -EFAULT;
+
+ switch (ioctl) {
+ case VHOST_NET_SET_BACKEND:
+ if(copy_from_user(&backend, (void __user *)arg, sizeof backend))
+ break;
+ ret = blk_set_backend(blk, &backend);
+ break;
+ case VHOST_GET_FEATURES:
+ features = VHOST_BLK_FEATURES;
+ if (copy_to_user((void __user *)arg , &features, sizeof features))
+ break;
+ ret = 0;
+ break;
+ case VHOST_SET_FEATURES:
+ if (copy_from_user(&features, (void __user *)arg, sizeof features))
+ break;
+ if (features & ~VHOST_BLK_FEATURES) {
+ ret = -EOPNOTSUPP;
+ break;
+ }
+ ret = blk_set_features(blk, features);
+ break;
+ case VHOST_RESET_OWNER:
+ ret = blk_reset_owner(blk);
+ break;
+ default:
+ mutex_lock(&blk->dev.mutex);
+ ret = vhost_dev_ioctl(&blk->dev, ioctl, arg);
+ blk_flush(blk);
+ mutex_unlock(&blk->dev.mutex);
+ break;
+ }
+ return ret;
+}
+
+#define BLK_HDR 0
+#define BLK_HDR_LEN 16
+
+static inline int do_request(struct vhost_virtqueue *vq, struct virtio_blk_outhdr *hdr,
+ u64 nr_vecs, int head)
+{
+ struct file *f = vq->private_data;
+ struct vhost_blk *blk = container_of(vq->dev, struct vhost_blk, dev);
+ struct iovec *iov = &vq->iov[BLK_HDR + 1];
+ loff_t pos = hdr->sector << 9;
+ int ret = 0, len = 0, status;
+ // int i;
+
+ dprintk("sector %llu, num %lu, type %d\n", hdr->sector, iov->iov_len / 512, hdr->type);
+ //Guest virtio-blk driver dosen't use len currently.
+ //for (i = 0; i < nr_vecs; i++) {
+ // len += iov[i].iov_len;
+ //}
+ switch (hdr->type) {
+ case VIRTIO_BLK_T_OUT:
+ kernel_io_submit(blk, iov, nr_vecs, pos, IOCB_CMD_PWRITEV, head, len);
+ break;
+ case VIRTIO_BLK_T_IN:
+ kernel_io_submit(blk, iov, nr_vecs, pos, IOCB_CMD_PREADV, head, len);
+ break;
+ case VIRTIO_BLK_T_FLUSH:
+ ret = vfs_fsync(f, 1);
+ /* fall through */
+ case VIRTIO_BLK_T_GET_ID:
+ status = ret < 0 ? VIRTIO_BLK_S_IOERR :VIRTIO_BLK_S_OK;
+ if ((vq->iov[nr_vecs + 1].iov_len != 1))
+ BUG();
+
+ if (copy_to_user(vq->iov[nr_vecs + 1].iov_base, &status, sizeof status)) {
+ vq_err(vq, "%s failed to write status!\n", __func__);
+ vhost_discard_vq_desc(vq, 1);
+ ret = -EFAULT;
+ break;
+ }
+
+ vhost_add_used_and_signal(&blk->dev, vq, head, ret);
+ break;
+ default:
+ pr_info("%s, unsupported request type %d\n", __func__, hdr->type);
+ vhost_discard_vq_desc(vq, 1);
+ ret = -EFAULT;
+ break;
+ }
+ return ret;
+}
+
+static inline void handle_kick(struct vhost_blk *blk)
+{
+ struct vhost_virtqueue *vq = &blk->vq;
+ struct virtio_blk_outhdr hdr;
+ u64 nr_vecs;
+ int in, out, head;
+ struct blk_plug plug;
+
+ mutex_lock(&vq->mutex);
+ vhost_disable_notify(&blk->dev, vq);
+
+ blk_start_plug(&plug);
+ for (;;) {
+ head = vhost_get_vq_desc(&blk->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in, NULL, NULL);
+ /* No awailable descriptors from Guest? */
+ if (head == vq->num) {
+ if (unlikely(vhost_enable_notify(&blk->dev, vq))) {
+ vhost_disable_notify(&blk->dev, vq);
+ continue;
+ }
+ break;
+ }
+ if (unlikely(head < 0))
+ break;
+
+ dprintk("head %d, in %d, out %d\n", head, in, out);
+ if(unlikely(vq->iov[BLK_HDR].iov_len != BLK_HDR_LEN)) {
+ vq_err(vq, "%s bad block header lengh!\n", __func__);
+ vhost_discard_vq_desc(vq, 1);
+ break;
+ }
+
+ if (copy_from_user(&hdr, vq->iov[BLK_HDR].iov_base, sizeof hdr)) {
+ vq_err(vq, "%s failed to get block header!\n", __func__);
+ vhost_discard_vq_desc(vq, 1);
+ break;
+ }
+
+ if (hdr.type == VIRTIO_BLK_T_IN || hdr.type == VIRTIO_BLK_T_GET_ID)
+ nr_vecs = in - 1;
+ else
+ nr_vecs = out - 1;
+
+ if (do_request(vq, &hdr, nr_vecs, head) < 0)
+ break;
+ }
+ blk_finish_plug(&plug);
+ mutex_unlock(&vq->mutex);
+}
+
+static void handle_guest_kick(struct vhost_work *work)
+{
+ struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, poll.work);
+ struct vhost_blk *blk = container_of(vq->dev, struct vhost_blk, dev);
+ handle_kick(blk);
+}
+
+static void handle_completion(struct vhost_work* work)
+{
+ struct vhost_blk *blk = container_of(work, struct vhost_blk, poll.work);
+ struct vhost_virtqueue *vq = &blk->vq;
+ struct timespec ts = { 0 };
+ int ret, i, nr;
+ u64 count;
+
+ mutex_lock(&vq->mutex);
+ do {
+ ret = eventfd_ctx_read(blk->ectx, 1, &count);
+ } while (unlikely(ret == -ERESTARTSYS));
+
+ do {
+ nr = kernel_read_events(blk->ioctx, count, MAX_EVENTS, events, &ts);
+ } while (unlikely(nr == -EINTR));
+ dprintk("%s, count %llu, nr %d\n", __func__, count, nr);
+
+ if (unlikely(nr <= 0)) {
+ mutex_unlock(&vq->mutex);
+ return;
+ }
+
+ for (i = 0; i < nr; i++) {
+ struct used_info *u = (struct used_info *)events[i].obj;
+ int len, status;
+
+ dprintk("%s, head %d complete in %d\n", __func__, u->head, i);
+ len = io_event_ret(&events[i]);
+ //status = u->len == len ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR;
+ status = len > 0 ? VIRTIO_BLK_S_OK : VIRTIO_BLK_S_IOERR;
+ if (copy_to_user(u->status, &status, sizeof status)) {
+ vq_err(&blk->vq, "%s failed to write status\n", __func__);
+ BUG(); /* FIXME: maybe a bit radical? */
+ }
+ vhost_add_used(&blk->vq, u->head, u->len);
+ kmem_cache_free(used_info_cachep, u);
+ }
+
+ vhost_signal(&blk->dev, &blk->vq);
+ mutex_unlock(&vq->mutex);
+}
+
+static void eventfd_setup(struct vhost_blk *blk)
+{
+ blk->efile = eventfd_file_create(0, 0);
+ blk->ectx = eventfd_ctx_fileget(blk->efile);
+ vhost_poll_init(&blk->poll, handle_completion, POLLIN, &blk->dev);
+ vhost_poll_start(&blk->poll, blk->efile);
+}
+
+static int vhost_blk_open(struct inode *inode, struct file *f)
+{
+ int ret = -ENOMEM;
+ struct vhost_blk *blk = kmalloc(sizeof *blk, GFP_KERNEL);
+ if (!blk)
+ goto err;
+
+ blk->vq.handle_kick = handle_guest_kick;
+ ret = vhost_dev_init(&blk->dev, &blk->vq, virtqueue_max);
+ if (ret < 0)
+ goto err_init;
+
+ ret = kernel_io_setup(MAX_EVENTS, &blk->ioctx);
+ if (ret < 0)
+ goto err_io_setup;
+
+ eventfd_setup(blk);
+ f->private_data = blk;
+ used_info_cachep = KMEM_CACHE(used_info, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+ return ret;
+err_init:
+err_io_setup:
+ kfree(blk);
+err:
+ return ret;
+}
+
+static void eventfd_destroy(struct vhost_blk *blk)
+{
+ eventfd_ctx_put(blk->ectx);
+ fput(blk->efile);
+}
+
+static int vhost_blk_release(struct inode *inode, struct file *f)
+{
+ struct vhost_blk *blk = f->private_data;
+
+ blk_stop(blk);
+ blk_flush(blk);
+ vhost_dev_cleanup(&blk->dev);
+ /* Yet another flush? See comments in vhost_net_release() */
+ blk_flush(blk);
+ eventfd_destroy(blk);
+ kfree(blk);
+
+ return 0;
+}
+
+const static struct file_operations vhost_blk_fops = {
+ .owner = THIS_MODULE,
+ .release = vhost_blk_release,
+ .open = vhost_blk_open,
+ .unlocked_ioctl = vhost_blk_ioctl,
+ .llseek = noop_llseek,
+};
+
+
+static struct miscdevice vhost_blk_misc = {
+ 234,
+ "vhost-blk",
+ &vhost_blk_fops,
+};
+
+int vhost_blk_init(void)
+{
+ return misc_register(&vhost_blk_misc);
+}
+void vhost_blk_exit(void)
+{
+ misc_deregister(&vhost_blk_misc);
+}
+
+module_init(vhost_blk_init);
+module_exit(vhost_blk_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Liu Yuan");
+MODULE_DESCRIPTION("Host kernel accelerator for virtio_blk");
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 8e03379..9e17152 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -12,6 +12,7 @@
#include <linux/virtio_config.h>
#include <linux/virtio_ring.h>
#include <asm/atomic.h>
+#include <linux/virtio_blk.h>

struct vhost_device;

@@ -174,6 +175,16 @@ enum {
(1ULL << VHOST_F_LOG_ALL) |
(1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
(1ULL << VIRTIO_NET_F_MRG_RXBUF),
+
+ VHOST_BLK_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+ (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+ (1ULL << VIRTIO_RING_F_EVENT_IDX) |
+ (1ULL << VIRTIO_BLK_F_SEG_MAX) |
+ (1ULL << VIRTIO_BLK_F_GEOMETRY) |
+ (1ULL << VIRTIO_BLK_F_TOPOLOGY) |
+ (1ULL << VIRTIO_BLK_F_SCSI) |
+ (1ULL << VIRTIO_BLK_F_BLK_SIZE),
+
};

static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
diff --git a/fs/aio.c b/fs/aio.c
index e29ec48..534d396 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -215,7 +215,7 @@ static void ctx_rcu_free(struct rcu_head *head)
* Called when the last user of an aio context has gone away,
* and the struct needs to be freed.
*/
-static void __put_ioctx(struct kioctx *ctx)
+void __put_ioctx(struct kioctx *ctx)
{
BUG_ON(ctx->reqs_active);

@@ -227,29 +227,12 @@ static void __put_ioctx(struct kioctx *ctx)
pr_debug("__put_ioctx: freeing %p\n", ctx);
call_rcu(&ctx->rcu_head, ctx_rcu_free);
}
-
-static inline void get_ioctx(struct kioctx *kioctx)
-{
- BUG_ON(atomic_read(&kioctx->users) <= 0);
- atomic_inc(&kioctx->users);
-}
-
-static inline int try_get_ioctx(struct kioctx *kioctx)
-{
- return atomic_inc_not_zero(&kioctx->users);
-}
-
-static inline void put_ioctx(struct kioctx *kioctx)
-{
- BUG_ON(atomic_read(&kioctx->users) <= 0);
- if (unlikely(atomic_dec_and_test(&kioctx->users)))
- __put_ioctx(kioctx);
-}
+EXPORT_SYMBOL(__put_ioctx);

/* ioctx_alloc
* Allocates and initializes an ioctx. Returns an ERR_PTR if it failed.
*/
-static struct kioctx *ioctx_alloc(unsigned nr_events)
+struct kioctx *ioctx_alloc(unsigned nr_events)
{
struct mm_struct *mm;
struct kioctx *ctx;
@@ -327,6 +310,7 @@ out_freectx:
dprintk("aio: error allocating ioctx %p\n", ctx);
return ctx;
}
+EXPORT_SYMBOL(ioctx_alloc);

/* aio_cancel_all
* Cancels all outstanding aio requests on an aio context. Used
@@ -437,7 +421,7 @@ void exit_aio(struct mm_struct *mm)
* This prevents races between the aio code path referencing the
* req (after submitting it) and aio_complete() freeing the req.
*/
-static struct kiocb *__aio_get_req(struct kioctx *ctx)
+struct kiocb *__aio_get_req(struct kioctx *ctx)
{
struct kiocb *req = NULL;
struct aio_ring *ring;
@@ -480,7 +464,7 @@ static struct kiocb *__aio_get_req(struct kioctx *ctx)
return req;
}

-static inline struct kiocb *aio_get_req(struct kioctx *ctx)
+struct kiocb *aio_get_req(struct kioctx *ctx)
{
struct kiocb *req;
/* Handle a potential starvation case -- should be exceedingly rare as
@@ -494,6 +478,7 @@ static inline struct kiocb *aio_get_req(struct kioctx *ctx)
}
return req;
}
+EXPORT_SYMBOL(aio_get_req);

static inline void really_put_req(struct kioctx *ctx, struct kiocb *req)
{
@@ -659,7 +644,7 @@ static inline int __queue_kicked_iocb(struct kiocb *iocb)
* simplifies the coding of individual aio operations as
* it avoids various potential races.
*/
-static ssize_t aio_run_iocb(struct kiocb *iocb)
+ssize_t aio_run_iocb(struct kiocb *iocb)
{
struct kioctx *ctx = iocb->ki_ctx;
ssize_t (*retry)(struct kiocb *);
@@ -753,6 +738,7 @@ out:
}
return ret;
}
+EXPORT_SYMBOL(aio_run_iocb);

/*
* __aio_run_iocbs:
@@ -761,7 +747,7 @@ out:
* Assumes it is operating within the aio issuer's mm
* context.
*/
-static int __aio_run_iocbs(struct kioctx *ctx)
+int __aio_run_iocbs(struct kioctx *ctx)
{
struct kiocb *iocb;
struct list_head run_list;
@@ -784,6 +770,7 @@ static int __aio_run_iocbs(struct kioctx *ctx)
return 1;
return 0;
}
+EXPORT_SYMBOL(__aio_run_iocbs);

static void aio_queue_work(struct kioctx * ctx)
{
@@ -1074,7 +1061,7 @@ static inline void clear_timeout(struct aio_timeout *to)
del_singleshot_timer_sync(&to->timer);
}

-static int read_events(struct kioctx *ctx,
+int read_events(struct kioctx *ctx,
long min_nr, long nr,
struct io_event __user *event,
struct timespec __user *timeout)
@@ -1190,11 +1177,12 @@ out:
destroy_timer_on_stack(&to.timer);
return i ? i : ret;
}
+EXPORT_SYMBOL(read_events);

/* Take an ioctx and remove it from the list of ioctx's. Protects
* against races with itself via ->dead.
*/
-static void io_destroy(struct kioctx *ioctx)
+void io_destroy(struct kioctx *ioctx)
{
struct mm_struct *mm = current->mm;
int was_dead;
@@ -1221,6 +1209,7 @@ static void io_destroy(struct kioctx *ioctx)
wake_up_all(&ioctx->wait);
put_ioctx(ioctx); /* once for the lookup */
}
+EXPORT_SYMBOL(io_destroy);

/* sys_io_setup:
* Create an aio_context capable of receiving at least nr_events.
@@ -1423,7 +1412,7 @@ static ssize_t aio_setup_single_vector(struct kiocb *kiocb)
* Performs the initial checks and aio retry method
* setup for the kiocb at the time of io submission.
*/
-static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
+ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)
{
struct file *file = kiocb->ki_filp;
ssize_t ret = 0;
@@ -1513,6 +1502,7 @@ static ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat)

return 0;
}
+EXPORT_SYMBOL(aio_setup_iocb);

static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
struct iocb *iocb, bool compat)
diff --git a/fs/eventfd.c b/fs/eventfd.c
index d9a5917..6343bc9 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -406,6 +406,7 @@ struct file *eventfd_file_create(unsigned int count, int flags)

return file;
}
+EXPORT_SYMBOL_GPL(eventfd_file_create);

SYSCALL_DEFINE2(eventfd2, unsigned int, count, int, flags)
{
diff --git a/include/linux/aio.h b/include/linux/aio.h
index 7a8db41..d63bc04 100644
--- a/include/linux/aio.h
+++ b/include/linux/aio.h
@@ -214,6 +214,37 @@ struct mm_struct;
extern void exit_aio(struct mm_struct *mm);
extern long do_io_submit(aio_context_t ctx_id, long nr,
struct iocb __user *__user *iocbpp, bool compat);
+extern void __put_ioctx(struct kioctx *ctx);
+extern struct kioctx *ioctx_alloc(unsigned nr_events);
+extern struct kiocb *aio_get_req(struct kioctx *ctx);
+extern ssize_t aio_run_iocb(struct kiocb *iocb);
+extern int __aio_run_iocbs(struct kioctx *ctx);
+extern int read_events(struct kioctx *ctx,
+ long min_nr, long nr,
+ struct io_event __user *event,
+ struct timespec __user *timeout);
+extern void io_destroy(struct kioctx *ioctx);
+extern ssize_t aio_setup_iocb(struct kiocb *kiocb, bool compat);
+extern void __put_ioctx(struct kioctx *ctx);
+
+static inline void get_ioctx(struct kioctx *kioctx)
+{
+ BUG_ON(atomic_read(&kioctx->users) <= 0);
+ atomic_inc(&kioctx->users);
+}
+
+static inline int try_get_ioctx(struct kioctx *kioctx)
+{
+ return atomic_inc_not_zero(&kioctx->users);
+}
+
+static inline void put_ioctx(struct kioctx *kioctx)
+{
+ BUG_ON(atomic_read(&kioctx->users) <= 0);
+ if (unlikely(atomic_dec_and_test(&kioctx->users)))
+ __put_ioctx(kioctx);
+}
+
#else
static inline ssize_t wait_on_sync_kiocb(struct kiocb *iocb) { return 0; }
static inline int aio_put_req(struct kiocb *iocb) { return 0; }