linux-kernel - [PATCH] io_uring/rsrc: Simplify buffer cloning by locking both rings

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250115-uring-clone-refactor-v1-1-b2d951577201@google.com>
Date: Wed, 15 Jan 2025 17:25:35 +0100
From: Jann Horn <jannh@...gle.com>
To: Jens Axboe <axboe@...nel.dk>, Pavel Begunkov <asml.silence@...il.com>
Cc: io-uring@...r.kernel.org, linux-kernel@...r.kernel.org, 
 Jann Horn <jannh@...gle.com>
Subject: [PATCH] io_uring/rsrc: Simplify buffer cloning by locking both
 rings

The locking in the buffer cloning code is somewhat complex because it goes
back and forth between locking the source ring and the destination ring.

Make it easier to reason about by locking both rings at the same time.
To avoid ABBA deadlocks, lock the rings in ascending kernel address order,
just like in lock_two_nondirectories().

Signed-off-by: Jann Horn <jannh@...gle.com>
---
Just an idea for how I think io_clone_buffers() could be changed so it
becomes slightly easier to reason about.
I left the out_unlock jump label with its current name for now, though
I guess that should probably be adjusted.
---
 io_uring/rsrc.c | 58 ++++++++++++++++++++++++++++++---------------------------
 1 file changed, 31 insertions(+), 27 deletions(-)

diff --git a/io_uring/rsrc.c b/io_uring/rsrc.c
index 69937d0c94f9518a2fd2cde1e5b2e7139078e1d3..8e26f78230eaaaf7910c1b84a50b40b6ab5fbf16 100644
--- a/io_uring/rsrc.c
+++ b/io_uring/rsrc.c
@@ -924,6 +924,16 @@ int io_import_fixed(int ddir, struct iov_iter *iter,
 	return 0;
 }
 
+/* Lock two rings at once. The rings must be different! */
+static void lock_two_rings(struct io_ring_ctx *ctx1, struct io_ring_ctx *ctx2)
+{
+	if (ctx1 > ctx2)
+		swap(ctx1, ctx2);
+	mutex_lock(&ctx1->uring_lock);
+	mutex_lock_nested(&ctx2->uring_lock, SINGLE_DEPTH_NESTING);
+}
+
+/* Both rings are locked by the caller. */
 static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx,
 			    struct io_uring_clone_buffers *arg)
 {
@@ -938,7 +948,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 	if (ctx->buf_table.nr && !(arg->flags & IORING_REGISTER_DST_REPLACE))
 		return -EBUSY;
 
-	nbufs = READ_ONCE(src_ctx->buf_table.nr);
+	nbufs = src_ctx->buf_table.nr;
 	if (!arg->nr)
 		arg->nr = nbufs;
 	else if (arg->nr > nbufs)
@@ -962,13 +972,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		}
 	}
 
-	/*
-	 * Drop our own lock here. We'll setup the data we need and reference
-	 * the source buffers, then re-grab, check, and assign at the end.
-	 */
-	mutex_unlock(&ctx->uring_lock);
-
-	mutex_lock(&src_ctx->uring_lock);
 	ret = -ENXIO;
 	nbufs = src_ctx->buf_table.nr;
 	if (!nbufs)
@@ -1007,10 +1010,6 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		i++;
 	}
 
-	/* Have a ref on the bufs now, drop src lock and re-grab our own lock */
-	mutex_unlock(&src_ctx->uring_lock);
-	mutex_lock(&ctx->uring_lock);
-
 	/*
 	 * If asked for replace, put the old table. data->nodes[] holds both
 	 * old and new nodes at this point.
@@ -1019,24 +1018,17 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 		io_rsrc_data_free(ctx, &ctx->buf_table);
 
 	/*
-	 * ctx->buf_table should be empty now - either the contents are being
-	 * replaced and we just freed the table, or someone raced setting up
-	 * a buffer table while the clone was happening. If not empty, fall
-	 * through to failure handling.
+	 * ctx->buf_table must be empty now - either the contents are being
+	 * replaced and we just freed the table, or the contents are being
+	 * copied to a ring that does not have buffers yet (checked at function
+	 * entry).
 	 */
-	if (!ctx->buf_table.nr) {
-		ctx->buf_table = data;
-		return 0;
-	}
+	WARN_ON(ctx->buf_table.nr);
+	ctx->buf_table = data;
+	return 0;
 
-	mutex_unlock(&ctx->uring_lock);
-	mutex_lock(&src_ctx->uring_lock);
-	/* someone raced setting up buffers, dump ours */
-	ret = -EBUSY;
 out_unlock:
 	io_rsrc_data_free(ctx, &data);
-	mutex_unlock(&src_ctx->uring_lock);
-	mutex_lock(&ctx->uring_lock);
 	return ret;
 }
 
@@ -1050,6 +1042,7 @@ static int io_clone_buffers(struct io_ring_ctx *ctx, struct io_ring_ctx *src_ctx
 int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 {
 	struct io_uring_clone_buffers buf;
+	struct io_ring_ctx *src_ctx;
 	bool registered_src;
 	struct file *file;
 	int ret;
@@ -1067,7 +1060,18 @@ int io_register_clone_buffers(struct io_ring_ctx *ctx, void __user *arg)
 	file = io_uring_register_get_file(buf.src_fd, registered_src);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
-	ret = io_clone_buffers(ctx, file->private_data, &buf);
+	src_ctx = file->private_data;
+	if (src_ctx == ctx) {
+		ret = -ELOOP;
+		goto out_put;
+	}
+
+	mutex_unlock(&ctx->uring_lock);
+	lock_two_rings(ctx, src_ctx);
+	ret = io_clone_buffers(ctx, src_ctx, &buf);
+	mutex_unlock(&src_ctx->uring_lock);
+
+out_put:
 	if (!registered_src)
 		fput(file);
 	return ret;

---
base-commit: c1c03ee7957ec178756cae09c39d77194e8cddb7
change-id: 20250115-uring-clone-refactor-06ddceddeb00

-- 
Jann Horn <jannh@...gle.com>