io_uring: fix memory leak when removing provided buffers

When removing provided buffers, io_buffer structs are not being disposed
of, leading to a memory leak. They can't be freed individually, because
they are allocated in page-sized groups. They need to be added to some
free list instead, such as io_buffers_cache. All callers already hold
the lock protecting it, apart from when destroying buffers, so had to
extend the lock there.

Fixes: cc3cec8367cb ("io_uring: speedup provided buffer handling")
Signed-off-by: Wojciech Lukowicz <wlukowicz01@gmail.com>
Link: https://lore.kernel.org/r/20230401195039.404909-2-wlukowicz01@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 722624b6d0dcae61b64c3966260ddc3cae814616..2a8b8c304d2ab1c0f32ece06236145899834c589 100644 (file)
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2789,8 +2789,8 @@ static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
        io_eventfd_unregister(ctx);
        io_alloc_cache_free(&ctx->apoll_cache, io_apoll_cache_free);
        io_alloc_cache_free(&ctx->netmsg_cache, io_netmsg_cache_free);
-       mutex_unlock(&ctx->uring_lock);
        io_destroy_buffers(ctx);
+       mutex_unlock(&ctx->uring_lock);
        if (ctx->sq_creds)
                put_cred(ctx->sq_creds);
        if (ctx->submitter_task)

diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
index 0fdcc0adbdbcc709013a48a6d59899ffd8f02037..a90c820ce99e12e5e72d37dee4fefd2d24665c3a 100644 (file)
--- a/io_uring/kbuf.c
+++ b/io_uring/kbuf.c
@@ -228,11 +228,14 @@ static int __io_remove_buffers(struct io_ring_ctx *ctx,
                return i;
        }
 
+       /* protects io_buffers_cache */
+       lockdep_assert_held(&ctx->uring_lock);
+
        while (!list_empty(&bl->buf_list)) {
                struct io_buffer *nxt;
 
                nxt = list_first_entry(&bl->buf_list, struct io_buffer, list);
-               list_del(&nxt->list);
+               list_move(&nxt->list, &ctx->io_buffers_cache);
                if (++i == nbufs)
                        return i;
                cond_resched();