io_uring: apply max_workers limit to all future users

Currently, IORING_REGISTER_IOWQ_MAX_WORKERS applies only to the task
that issued it, it's unexpected for users. If one task creates a ring,
limits workers and then passes it to another task the limit won't be
applied to the other task.

Another pitfall is that a task should either create a ring or submit at
least one request for IORING_REGISTER_IOWQ_MAX_WORKERS to work at all,
furher complicating the picture.

Change the API, save the limits and apply to all future users. Note, it
should be done first before giving away the ring or submitting new
requests otherwise the result is not guaranteed.

Fixes: 2e480058ddc2 ("io-wq: provide a way to limit max number of workers")
Link: https://github.com/axboe/liburing/issues/460
Reported-by: Beld Zhang <beldzhang@gmail.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/51d0bae97180e08ab722c0d5c93e7439cfb6f697.1634683237.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/fs/io_uring.c b/fs/io_uring.c
index e68d278..e8b71f1 100644 (file)
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -456,6 +456,8 @@ struct io_ring_ctx {
                struct work_struct              exit_work;
                struct list_head                tctx_list;
                struct completion               ref_comp;
+               u32                             iowq_limits[2];
+               bool                            iowq_limits_set;
        };
 };
 
@@ -9638,7 +9640,16 @@ static int __io_uring_add_tctx_node(struct io_ring_ctx *ctx)
                ret = io_uring_alloc_task_context(current, ctx);
                if (unlikely(ret))
                        return ret;
+
                tctx = current->io_uring;
+               if (ctx->iowq_limits_set) {
+                       unsigned int limits[2] = { ctx->iowq_limits[0],
+                                                  ctx->iowq_limits[1], };
+
+                       ret = io_wq_max_workers(tctx->io_wq, limits);
+                       if (ret)
+                               return ret;
+               }
        }
        if (!xa_load(&tctx->xa, (unsigned long)ctx)) {
                node = kmalloc(sizeof(*node), GFP_KERNEL);
@@ -10674,13 +10685,19 @@ static int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
                tctx = current->io_uring;
        }
 
-       ret = -EINVAL;
-       if (!tctx || !tctx->io_wq)
-               goto err;
+       BUILD_BUG_ON(sizeof(new_count) != sizeof(ctx->iowq_limits));
 
-       ret = io_wq_max_workers(tctx->io_wq, new_count);
-       if (ret)
-               goto err;
+       memcpy(ctx->iowq_limits, new_count, sizeof(new_count));
+       ctx->iowq_limits_set = true;
+
+       ret = -EINVAL;
+       if (tctx && tctx->io_wq) {
+               ret = io_wq_max_workers(tctx->io_wq, new_count);
+               if (ret)
+                       goto err;
+       } else {
+               memset(new_count, 0, sizeof(new_count));
+       }
 
        if (sqd) {
                mutex_unlock(&sqd->lock);