io_uring/zcrx: add ctx pointer to zcrx

zcrx will need to have a pointer to an owning ctx to communicate
different events. Reference the ctx while it's attached to zcrx, and
rely on zcrx termination to drop the ctx to avoid circular ref deps.

Co-developed-by: Vishwanath Seshagiri <vishs@meta.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Vishwanath Seshagiri <vishs@meta.com>
Link: https://patch.msgid.link/b60514b3d1bd92f571e3bd91751166f8c3599256.1779189667.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 34 insertions, 8 deletions

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 7ac9eb6a0934..1e194de7d6d2 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -44,6 +44,17 @@ static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *nio
 	return container_of(owner, struct io_zcrx_area, nia);
 }
 
+static bool zcrx_set_ring_ctx(struct io_zcrx_ifq *zcrx,
+			      struct io_ring_ctx *ctx)
+{
+	guard(spinlock_bh)(&zcrx->ctx_lock);
+	if (zcrx->master_ctx)
+		return false;
+	percpu_ref_get(&ctx->refs);
+	zcrx->master_ctx = ctx;
+	return true;
+}
+
 static inline struct page *io_zcrx_iov_page(const struct net_iov *niov)
 {
 	struct io_zcrx_area *area = io_zcrx_iov_to_area(niov);
@@ -529,6 +540,7 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
 		return NULL;
 
 	ifq->if_rxq = -1;
+	spin_lock_init(&ifq->ctx_lock);
 	spin_lock_init(&ifq->rq.lock);
 	mutex_init(&ifq->pp_lock);
 	refcount_set(&ifq->refs, 1);
@@ -578,6 +590,8 @@ static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
 		return;
 	if (WARN_ON_ONCE(ifq->netdev != NULL))
 		return;
+	if (WARN_ON_ONCE(ifq->master_ctx))
+		return;
 
 	if (ifq->area)
 		io_zcrx_free_area(ifq, ifq->area);
@@ -654,17 +668,24 @@ static void io_zcrx_scrub(struct io_zcrx_ifq *ifq)
 	}
 }
 
-static void zcrx_unregister_user(struct io_zcrx_ifq *ifq)
+static void zcrx_unregister_user(struct io_zcrx_ifq *ifq, struct io_ring_ctx *ctx)
 {
+	scoped_guard(spinlock_bh, &ifq->ctx_lock) {
+		if (ctx && ifq->master_ctx == ctx) {
+			ifq->master_ctx = NULL;
+			percpu_ref_put(&ctx->refs);
+		}
+	}
+
 	if (refcount_dec_and_test(&ifq->user_refs)) {
 		io_close_queue(ifq);
 		io_zcrx_scrub(ifq);
 	}
 }
 
-static void zcrx_unregister(struct io_zcrx_ifq *ifq)
+static void zcrx_unregister(struct io_zcrx_ifq *ifq, struct io_ring_ctx *ctx)
 {
-	zcrx_unregister_user(ifq);
+	zcrx_unregister_user(ifq, ctx);
 	io_put_zcrx_ifq(ifq);
 }
 
@@ -684,7 +705,7 @@ static int zcrx_box_release(struct inode *inode, struct file *file)
 
 	if (WARN_ON_ONCE(!ifq))
 		return -EFAULT;
-	zcrx_unregister(ifq);
+	zcrx_unregister(ifq, NULL);
 	return 0;
 }
 
@@ -709,7 +730,7 @@ static int zcrx_export(struct io_ring_ctx *ctx, struct io_zcrx_ifq *ifq,
 	file = anon_inode_create_getfile("[zcrx]", &zcrx_box_fops,
 					 ifq, O_CLOEXEC, NULL);
 	if (IS_ERR(file)) {
-		zcrx_unregister(ifq);
+		zcrx_unregister(ifq, NULL);
 		return PTR_ERR(file);
 	}
 
@@ -785,7 +806,7 @@ err_xa_erase:
 	scoped_guard(mutex, &ctx->mmap_lock)
 		xa_erase(&ctx->zcrx_ctxs, id);
 err:
-	zcrx_unregister(ifq);
+	zcrx_unregister(ifq, ctx);
 	return ret;
 }
 
@@ -930,12 +951,14 @@ int io_register_zcrx(struct io_ring_ctx *ctx,
 		ret = -EFAULT;
 		goto err;
 	}
+
+	zcrx_set_ring_ctx(ifq, ctx);
 	return 0;
 err:
 	scoped_guard(mutex, &ctx->mmap_lock)
 		xa_erase(&ctx->zcrx_ctxs, id);
 ifq_free:
-	zcrx_unregister(ifq);
+	zcrx_unregister(ifq, ctx);
 	return ret;
 }
 
@@ -965,7 +988,7 @@ void io_terminate_zcrx(struct io_ring_ctx *ctx)
 			break;
 		set_zcrx_entry_mark(ctx, id);
 		id++;
-		zcrx_unregister_user(ifq);
+		zcrx_unregister_user(ifq, ctx);
 	}
 }
 
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 75e0a4e6ef6e..76389a5dd50f 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -72,6 +72,9 @@ struct io_zcrx_ifq {
 	 */
 	struct mutex			pp_lock;
 	struct io_mapped_region		rq_region;
+
+	spinlock_t			ctx_lock;
+	struct io_ring_ctx		*master_ctx;
 };
 
 #if defined(CONFIG_IO_URING_ZCRX)