From 216578e55ac932cf5e348d9e65d8e129fc9e34cc Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Tue, 13 Oct 2020 09:44:00 +0100 Subject: [PATCH] io_uring: fix REQ_F_COMP_LOCKED by killing it REQ_F_COMP_LOCKED is used and implemented in a buggy way. The problem is that the flag is set before io_put_req() but not cleared after, and if that wasn't the final reference, the request will be freed with the flag set from some other context, which may not hold a spinlock. That means possible races with removing linked timeouts and unsynchronised completion (e.g. access to CQ). Instead of fixing REQ_F_COMP_LOCKED, kill the flag and use task_work_add() to move such requests to a fresh context to free from it, as was done with __io_free_req_finish(). Signed-off-by: Pavel Begunkov Signed-off-by: Jens Axboe --- fs/io_uring.c | 149 +++++++++++++++++++++++--------------------------- 1 file changed, 69 insertions(+), 80 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 0680fa385353..641d869d96ee 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -574,7 +574,6 @@ enum { REQ_F_NOWAIT_BIT, REQ_F_LINK_TIMEOUT_BIT, REQ_F_ISREG_BIT, - REQ_F_COMP_LOCKED_BIT, REQ_F_NEED_CLEANUP_BIT, REQ_F_POLLED_BIT, REQ_F_BUFFER_SELECTED_BIT, @@ -613,8 +612,6 @@ enum { REQ_F_LINK_TIMEOUT = BIT(REQ_F_LINK_TIMEOUT_BIT), /* regular file */ REQ_F_ISREG = BIT(REQ_F_ISREG_BIT), - /* completion under lock */ - REQ_F_COMP_LOCKED = BIT(REQ_F_COMP_LOCKED_BIT), /* needs cleanup */ REQ_F_NEED_CLEANUP = BIT(REQ_F_NEED_CLEANUP_BIT), /* already went through poll handler */ @@ -963,8 +960,8 @@ static void __io_complete_rw(struct io_kiocb *req, long res, long res2, struct io_comp_state *cs); static void io_cqring_fill_event(struct io_kiocb *req, long res); static void io_put_req(struct io_kiocb *req); +static void io_put_req_deferred(struct io_kiocb *req, int nr); static void io_double_put_req(struct io_kiocb *req); -static void __io_double_put_req(struct io_kiocb *req); static struct io_kiocb *io_prep_linked_timeout(struct io_kiocb *req); static void __io_queue_linked_timeout(struct io_kiocb *req); static void io_queue_linked_timeout(struct io_kiocb *req); @@ -1316,9 +1313,8 @@ static void io_kill_timeout(struct io_kiocb *req) atomic_set(&req->ctx->cq_timeouts, atomic_read(&req->ctx->cq_timeouts) + 1); list_del_init(&req->timeout.list); - req->flags |= REQ_F_COMP_LOCKED; io_cqring_fill_event(req, 0); - io_put_req(req); + io_put_req_deferred(req, 1); } } @@ -1369,8 +1365,7 @@ static void __io_queue_deferred(struct io_ring_ctx *ctx) if (link) { __io_queue_linked_timeout(link); /* drop submission reference */ - link->flags |= REQ_F_COMP_LOCKED; - io_put_req(link); + io_put_req_deferred(link, 1); } kfree(de); } while (!list_empty(&ctx->defer_list)); @@ -1597,13 +1592,19 @@ static void io_submit_flush_completions(struct io_comp_state *cs) req = list_first_entry(&cs->list, struct io_kiocb, compl.list); list_del(&req->compl.list); __io_cqring_fill_event(req, req->result, req->compl.cflags); - if (!(req->flags & REQ_F_LINK_HEAD)) { - req->flags |= REQ_F_COMP_LOCKED; - io_put_req(req); - } else { + + /* + * io_free_req() doesn't care about completion_lock unless one + * of these flags is set. REQ_F_WORK_INITIALIZED is in the list + * because of a potential deadlock with req->work.fs->lock + */ + if (req->flags & (REQ_F_FAIL_LINK|REQ_F_LINK_TIMEOUT + |REQ_F_WORK_INITIALIZED)) { spin_unlock_irq(&ctx->completion_lock); io_put_req(req); spin_lock_irq(&ctx->completion_lock); + } else { + io_put_req(req); } } io_commit_cqring(ctx); @@ -1702,10 +1703,14 @@ static void io_dismantle_req(struct io_kiocb *req) io_req_clean_work(req); } -static void __io_free_req_finish(struct io_kiocb *req) +static void __io_free_req(struct io_kiocb *req) { - struct io_uring_task *tctx = req->task->io_uring; - struct io_ring_ctx *ctx = req->ctx; + struct io_uring_task *tctx; + struct io_ring_ctx *ctx; + + io_dismantle_req(req); + tctx = req->task->io_uring; + ctx = req->ctx; atomic_long_inc(&tctx->req_complete); if (tctx->in_idle) @@ -1719,33 +1724,6 @@ static void __io_free_req_finish(struct io_kiocb *req) percpu_ref_put(&ctx->refs); } -static void io_req_task_file_table_put(struct callback_head *cb) -{ - struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); - - io_dismantle_req(req); - __io_free_req_finish(req); -} - -static void __io_free_req(struct io_kiocb *req) -{ - if (!(req->flags & REQ_F_COMP_LOCKED)) { - io_dismantle_req(req); - __io_free_req_finish(req); - } else { - int ret; - - init_task_work(&req->task_work, io_req_task_file_table_put); - ret = task_work_add(req->task, &req->task_work, TWA_RESUME); - if (unlikely(ret)) { - struct task_struct *tsk; - - tsk = io_wq_get_task(req->ctx->io_wq); - task_work_add(tsk, &req->task_work, 0); - } - } -} - static bool io_link_cancel_timeout(struct io_kiocb *req) { struct io_timeout_data *io = req->async_data; @@ -1754,11 +1732,10 @@ static bool io_link_cancel_timeout(struct io_kiocb *req) ret = hrtimer_try_to_cancel(&io->timer); if (ret != -1) { - req->flags |= REQ_F_COMP_LOCKED; io_cqring_fill_event(req, -ECANCELED); io_commit_cqring(ctx); req->flags &= ~REQ_F_LINK_HEAD; - io_put_req(req); + io_put_req_deferred(req, 1); return true; } @@ -1785,17 +1762,12 @@ static bool __io_kill_linked_timeout(struct io_kiocb *req) static void io_kill_linked_timeout(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; bool wake_ev; - if (!(req->flags & REQ_F_COMP_LOCKED)) { - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - wake_ev = __io_kill_linked_timeout(req); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } else { - wake_ev = __io_kill_linked_timeout(req); - } + spin_lock_irqsave(&ctx->completion_lock, flags); + wake_ev = __io_kill_linked_timeout(req); + spin_unlock_irqrestore(&ctx->completion_lock, flags); if (wake_ev) io_cqring_ev_posted(ctx); @@ -1835,27 +1807,29 @@ static void __io_fail_links(struct io_kiocb *req) trace_io_uring_fail_link(req, link); io_cqring_fill_event(link, -ECANCELED); - link->flags |= REQ_F_COMP_LOCKED; - __io_double_put_req(link); + + /* + * It's ok to free under spinlock as they're not linked anymore, + * but avoid REQ_F_WORK_INITIALIZED because it may deadlock on + * work.fs->lock. + */ + if (link->flags & REQ_F_WORK_INITIALIZED) + io_put_req_deferred(link, 2); + else + io_double_put_req(link); } io_commit_cqring(ctx); - io_cqring_ev_posted(ctx); } static void io_fail_links(struct io_kiocb *req) { struct io_ring_ctx *ctx = req->ctx; + unsigned long flags; - if (!(req->flags & REQ_F_COMP_LOCKED)) { - unsigned long flags; - - spin_lock_irqsave(&ctx->completion_lock, flags); - __io_fail_links(req); - spin_unlock_irqrestore(&ctx->completion_lock, flags); - } else { - __io_fail_links(req); - } + spin_lock_irqsave(&ctx->completion_lock, flags); + __io_fail_links(req); + spin_unlock_irqrestore(&ctx->completion_lock, flags); io_cqring_ev_posted(ctx); } @@ -2069,6 +2043,34 @@ static void io_put_req(struct io_kiocb *req) io_free_req(req); } +static void io_put_req_deferred_cb(struct callback_head *cb) +{ + struct io_kiocb *req = container_of(cb, struct io_kiocb, task_work); + + io_free_req(req); +} + +static void io_free_req_deferred(struct io_kiocb *req) +{ + int ret; + + init_task_work(&req->task_work, io_put_req_deferred_cb); + ret = io_req_task_work_add(req, true); + if (unlikely(ret)) { + struct task_struct *tsk; + + tsk = io_wq_get_task(req->ctx->io_wq); + task_work_add(tsk, &req->task_work, 0); + wake_up_process(tsk); + } +} + +static inline void io_put_req_deferred(struct io_kiocb *req, int refs) +{ + if (refcount_sub_and_test(refs, &req->refs)) + io_free_req_deferred(req); +} + static struct io_wq_work *io_steal_work(struct io_kiocb *req) { struct io_kiocb *nxt; @@ -2085,17 +2087,6 @@ static struct io_wq_work *io_steal_work(struct io_kiocb *req) return nxt ? &nxt->work : NULL; } -/* - * Must only be used if we don't need to care about links, usually from - * within the completion handling itself. - */ -static void __io_double_put_req(struct io_kiocb *req) -{ - /* drop both submit and complete references */ - if (refcount_sub_and_test(2, &req->refs)) - __io_free_req(req); -} - static void io_double_put_req(struct io_kiocb *req) { /* drop both submit and complete references */ @@ -5127,9 +5118,8 @@ static bool io_poll_remove_one(struct io_kiocb *req) if (do_complete) { io_cqring_fill_event(req, -ECANCELED); io_commit_cqring(req->ctx); - req->flags |= REQ_F_COMP_LOCKED; req_set_fail_links(req); - io_put_req(req); + io_put_req_deferred(req, 1); } return do_complete; @@ -5311,9 +5301,8 @@ static int __io_timeout_cancel(struct io_kiocb *req) list_del_init(&req->timeout.list); req_set_fail_links(req); - req->flags |= REQ_F_COMP_LOCKED; io_cqring_fill_event(req, -ECANCELED); - io_put_req(req); + io_put_req_deferred(req, 1); return 0; }