[PATCH v1 13/15] io_uring: Make remove_ifq_region a delayed work call

[Jonathan Lemon <jonathan.lemon@gmail.com>]

The page backing store should not be removed until all ouststanding
packets are returned.  The packets may be inflight, owned by the
driver or sitting in a socket buffer.

The region holds a reference to the ifq, and when the ifq is
closed, a delayed work item is scheduled which checks that all
pages have been returned.  When complete, then the region releases
the ifq reference so it can be freed.

Currently, the work item will exit and leak pages after a timeout
expires.  This should not happen in normal operation.

Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com>
---
 include/linux/io_uring_types.h |  1 +
 io_uring/zctap.c               | 77 +++++++++++++++++++++++++---------
 2 files changed, 59 insertions(+), 19 deletions(-)

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 39f20344d578..7d9895370875 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -583,6 +583,7 @@ struct io_zctap_ifq {
 	struct io_ring_ctx	*ctx;
 	void			*region;
 	struct ubuf_info	*uarg;
+	refcount_t		refcount;
 	u16			queue_id;
 	u16			id;
 	u16			fill_bgid;
diff --git a/io_uring/zctap.c b/io_uring/zctap.c
index 096b3dd5a8a3..262aa50de8c4 100644
--- a/io_uring/zctap.c
+++ b/io_uring/zctap.c
@@ -19,13 +19,14 @@
 #define NR_ZCTAP_IFQS	1
 
 struct ifq_region {
-	struct io_zctap_ifq	*ifq;		/* only for delayed_work */
-	struct io_mapped_ubuf	*imu;
+	struct io_zctap_ifq	*ifq;
 	int			free_count;
 	int			nr_pages;
 	u16			id;
 
 	spinlock_t		freelist_lock;
+	struct delayed_work	release_work;
+	unsigned long		delay_end;
 
 	struct io_zctap_buf	*buf;
 	u16			freelist[];
@@ -37,6 +38,8 @@ struct io_zctap_ifq_priv {
 	struct ubuf_info	uarg;
 };
 
+static void io_zctap_ifq_put(struct io_zctap_ifq *ifq);
+
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 
 static void zctap_set_page_info(struct page *page, u64 info)
@@ -239,11 +242,30 @@ netdev2device(struct net_device *dev)
 	return dev->dev.parent;			/* from SET_NETDEV_DEV() */
 }
 
-static void io_remove_ifq_region(struct ifq_region *ifr)
+static void io_remove_ifq_region_work(struct work_struct *work)
 {
+	struct ifq_region *ifr = container_of(
+		to_delayed_work(work), struct ifq_region, release_work);
 	struct device *device = netdev2device(ifr->ifq->dev);
 	struct io_zctap_buf *buf;
-	int i;
+	int i, refs, count;
+
+	count = 0;
+	for (i = 0; i < ifr->nr_pages; i++) {
+		buf = &ifr->buf[i];
+		refs = atomic_read(&buf->refcount) & IO_ZCTAP_KREF_MASK;
+		if (refs) {
+			if (time_before(jiffies, ifr->delay_end)) {
+				schedule_delayed_work(&ifr->release_work, HZ);
+				return;
+			}
+			count++;
+		}
+	}
+
+	if (count)
+		pr_debug("freeing ifr with %d/%d outstanding pages\n",
+			 count, ifr->nr_pages);
 
 	for (i = 0; i < ifr->nr_pages; i++) {
 		buf = &ifr->buf[i];
@@ -255,20 +277,28 @@ static void io_remove_ifq_region(struct ifq_region *ifr)
 		put_page(buf->page);
 	}
 
+	io_zctap_ifq_put(ifr->ifq);
 	kvfree(ifr->buf);
 	kvfree(ifr);
 }
 
-static int io_zctap_map_region(struct ifq_region *ifr, struct device *device)
+static void io_remove_ifq_region(struct ifq_region *ifr)
 {
-	struct io_mapped_ubuf *imu;
+	ifr->delay_end = jiffies + HZ * 10;
+	INIT_DELAYED_WORK(&ifr->release_work, io_remove_ifq_region_work);
+	schedule_delayed_work(&ifr->release_work, 0);
+}
+
+static int io_zctap_map_region(struct ifq_region *ifr,
+			       struct io_mapped_ubuf *imu)
+{
+	struct device *device = netdev2device(ifr->ifq->dev);
 	struct io_zctap_buf *buf;
 	struct page *page;
 	dma_addr_t addr;
 	int i, err;
 	u64 info;
 
-	imu = ifr->imu;
 	for (i = 0; i < ifr->nr_pages; i++) {
 		page = imu->bvec[i].bv_page;
 
@@ -302,10 +332,10 @@ static int io_zctap_map_region(struct ifq_region *ifr, struct device *device)
 
 out:
 	while (i--) {
-		page = imu->bvec[i].bv_page;
+		buf = &ifr->buf[i];
+		page = buf->page;
 		set_page_private(page, 0);
 		ClearPagePrivate(page);
-		buf = &ifr->buf[i];
 		dma_unmap_page_attrs(device, buf->dma, PAGE_SIZE,
 				     DMA_BIDIRECTIONAL,
 				     DMA_ATTR_SKIP_CPU_SYNC);
@@ -348,13 +378,12 @@ int io_provide_ifq_region(struct io_zctap_ifq *ifq, u16 id)
 
 	spin_lock_init(&ifr->freelist_lock);
 	ifr->nr_pages = nr_pages;
-	ifr->imu = imu;
 	ifr->free_count = nr_pages;
 	ifr->id = id;
+	ifr->ifq = ifq;
+	ifr->delay_end = 0;
 
-	ifr->ifq = ifq;		/* XXX */
-
-	err = io_zctap_map_region(ifr, netdev2device(ifq->dev));
+	err = io_zctap_map_region(ifr, imu);
 	if (err) {
 		kvfree(ifr->buf);
 		kvfree(ifr);
@@ -362,6 +391,7 @@ int io_provide_ifq_region(struct io_zctap_ifq *ifq, u16 id)
 	}
 
 	ifq->region = ifr;
+	refcount_inc(&ifq->refcount);
 
 	return 0;
 }
@@ -436,15 +466,23 @@ static struct io_zctap_ifq *io_zctap_ifq_alloc(struct io_ring_ctx *ctx)
 	return &priv->ifq;
 }
 
-static void io_zctap_ifq_free(struct io_zctap_ifq *ifq)
+static void io_zctap_ifq_put(struct io_zctap_ifq *ifq)
+{
+	if (!refcount_dec_and_test(&ifq->refcount))
+		return;
+
+	if (ifq->dev)
+		dev_put(ifq->dev);
+	kfree(ifq);
+}
+
+static void io_zctap_ifq_close(struct io_zctap_ifq *ifq)
 {
 	if (ifq->queue_id != -1)
 		io_close_zctap_ifq(ifq, ifq->queue_id);
 	if (ifq->region)
 		io_remove_ifq_region(ifq->region);
-	if (ifq->dev)
-		dev_put(ifq->dev);
-	kfree(ifq);
+	io_zctap_ifq_put(ifq);
 }
 
 int io_register_ifq(struct io_ring_ctx *ctx,
@@ -473,6 +511,7 @@ int io_register_ifq(struct io_ring_ctx *ctx,
 	ifq->fill_bgid = req.fill_bgid;
 	ifq->uarg->callback = io_zctap_ifq_callback;
 	ifq->uarg->flags = SKBFL_ALL_ZEROCOPY | SKBFL_FIXED_FRAG;
+	refcount_set(&ifq->refcount, 1);
 
 	err = -ENODEV;
 	ifq->dev = dev_get_by_index(&init_net, req.ifindex);
@@ -493,7 +532,7 @@ int io_register_ifq(struct io_ring_ctx *ctx,
 	return 0;
 
 out:
-	io_zctap_ifq_free(ifq);
+	io_zctap_ifq_close(ifq);
 	return err;
 }
 
@@ -506,7 +545,7 @@ int io_unregister_zctap_ifq(struct io_ring_ctx *ctx, unsigned long index)
 		return -EINVAL;
 
 	ctx->zctap_ifq = NULL;
-	io_zctap_ifq_free(ifq);
+	io_zctap_ifq_close(ifq);
 
 	return 0;
 }
-- 
2.30.2