Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 117 insertions, 0 deletions

diff --git a/io_uring/tw.h b/io_uring/tw.h
new file mode 100644
index 000000000..3ade5ad57
--- /dev/null
+++ b/io_uring/tw.h
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_TW_H
+#define IOU_TW_H
+
+#include <linux/sched.h>
+#include <linux/percpu-refcount.h>
+#include <linux/io_uring_types.h>
+
+#include "mpscq.h"
+
+#define IO_LOCAL_TW_DEFAULT_MAX		20
+
+/*
+ * Terminate the request if either of these conditions are true:
+ *
+ * 1) It's being executed by the original task, but that task is marked
+ *    with PF_EXITING as it's exiting.
+ * 2) PF_KTHREAD is set, in which case the invoker of the task_work is
+ *    our fallback task_work.
+ * 3) The ring has been closed and is going away.
+ */
+static inline bool io_should_terminate_tw(struct io_ring_ctx *ctx)
+{
+	return (current->flags & (PF_EXITING | PF_KTHREAD)) || percpu_ref_is_dying(&ctx->refs);
+}
+
+void io_req_task_work_add_remote(struct io_kiocb *req, unsigned flags);
+void tctx_task_work(struct callback_head *cb);
+void io_tctx_fallback_work(struct work_struct *work);
+int io_run_local_work(struct io_ring_ctx *ctx, int min_events, int max_events);
+int io_run_task_work_sig(struct io_ring_ctx *ctx);
+
+__cold void io_cancel_local_task_work(struct io_ring_ctx *ctx);
+int io_run_local_work_locked(struct io_ring_ctx *ctx, int min_events);
+
+void io_req_local_work_add(struct io_kiocb *req, unsigned flags);
+void io_req_normal_work_add(struct io_kiocb *req);
+void tctx_task_work_run(struct io_uring_task *tctx, unsigned int max_entries, unsigned int *count);
+
+static inline void __io_req_task_work_add(struct io_kiocb *req, unsigned flags)
+{
+	if (req->ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+		io_req_local_work_add(req, flags);
+	else
+		io_req_normal_work_add(req);
+}
+
+static inline void io_req_task_work_add(struct io_kiocb *req)
+{
+	__io_req_task_work_add(req, 0);
+}
+
+static inline int io_run_task_work(void)
+{
+	bool ret = false;
+
+	/*
+	 * Always check-and-clear the task_work notification signal. With how
+	 * signaling works for task_work, we can find it set with nothing to
+	 * run. We need to clear it for that case, like get_signal() does.
+	 */
+	if (test_thread_flag(TIF_NOTIFY_SIGNAL))
+		clear_notify_signal();
+	/*
+	 * PF_IO_WORKER never returns to userspace, so check here if we have
+	 * notify work that needs processing.
+	 */
+	if (current->flags & PF_IO_WORKER) {
+		if (test_thread_flag(TIF_NOTIFY_RESUME)) {
+			__set_current_state(TASK_RUNNING);
+			resume_user_mode_work(NULL);
+		}
+		if (current->io_uring) {
+			unsigned int count = 0;
+
+			__set_current_state(TASK_RUNNING);
+			tctx_task_work_run(current->io_uring, UINT_MAX, &count);
+			if (count)
+				ret = true;
+		}
+	}
+	if (task_work_pending(current)) {
+		__set_current_state(TASK_RUNNING);
+		task_work_run();
+		ret = true;
+	}
+
+	return ret;
+}
+
+static inline bool io_local_work_pending(struct io_ring_ctx *ctx)
+{
+	return !mpscq_empty(&ctx->work_list);
+}
+
+static inline bool io_task_work_pending(struct io_ring_ctx *ctx)
+{
+	return task_work_pending(current) || io_local_work_pending(ctx);
+}
+
+static inline void io_tw_lock(struct io_ring_ctx *ctx, io_tw_token_t tw)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+}
+
+static inline bool io_allowed_defer_tw_run(struct io_ring_ctx *ctx)
+{
+	return likely(ctx->submitter_task == current);
+}
+
+static inline bool io_allowed_run_tw(struct io_ring_ctx *ctx)
+{
+	return likely(!(ctx->flags & IORING_SETUP_DEFER_TASKRUN) ||
+		      ctx->submitter_task == current);
+}
+
+#endif