Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 586 insertions, 0 deletions

diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
new file mode 100644
index 000000000..896aab1ed
--- /dev/null
+++ b/io_uring/io_uring.h
@@ -0,0 +1,586 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef IOU_CORE_H
+#define IOU_CORE_H
+
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/lockdep.h>
+#include <linux/resume_user_mode.h>
+#include <linux/poll.h>
+#include <linux/io_uring_types.h>
+#include <uapi/linux/eventpoll.h>
+#include "alloc_cache.h"
+#include "io-wq.h"
+#include "slist.h"
+#include "tw.h"
+#include "opdef.h"
+
+#ifndef CREATE_TRACE_POINTS
+#include <trace/events/io_uring.h>
+#endif
+
+struct io_rings_layout {
+	/* size of CQ + headers + SQ offset array */
+	size_t rings_size;
+	size_t sq_size;
+
+	size_t sq_array_offset;
+};
+
+struct io_ctx_config {
+	struct io_uring_params p;
+	struct io_rings_layout layout;
+	struct io_uring_params __user *uptr;
+};
+
+#define IORING_FEAT_FLAGS (IORING_FEAT_SINGLE_MMAP |\
+			IORING_FEAT_NODROP |\
+			IORING_FEAT_SUBMIT_STABLE |\
+			IORING_FEAT_RW_CUR_POS |\
+			IORING_FEAT_CUR_PERSONALITY |\
+			IORING_FEAT_FAST_POLL |\
+			IORING_FEAT_POLL_32BITS |\
+			IORING_FEAT_SQPOLL_NONFIXED |\
+			IORING_FEAT_EXT_ARG |\
+			IORING_FEAT_NATIVE_WORKERS |\
+			IORING_FEAT_RSRC_TAGS |\
+			IORING_FEAT_CQE_SKIP |\
+			IORING_FEAT_LINKED_FILE |\
+			IORING_FEAT_REG_REG_RING |\
+			IORING_FEAT_RECVSEND_BUNDLE |\
+			IORING_FEAT_MIN_TIMEOUT |\
+			IORING_FEAT_RW_ATTR |\
+			IORING_FEAT_NO_IOWAIT)
+
+#define IORING_SETUP_FLAGS (IORING_SETUP_IOPOLL |\
+			IORING_SETUP_SQPOLL |\
+			IORING_SETUP_SQ_AFF |\
+			IORING_SETUP_CQSIZE |\
+			IORING_SETUP_CLAMP |\
+			IORING_SETUP_ATTACH_WQ |\
+			IORING_SETUP_R_DISABLED |\
+			IORING_SETUP_SUBMIT_ALL |\
+			IORING_SETUP_COOP_TASKRUN |\
+			IORING_SETUP_TASKRUN_FLAG |\
+			IORING_SETUP_SQE128 |\
+			IORING_SETUP_CQE32 |\
+			IORING_SETUP_SINGLE_ISSUER |\
+			IORING_SETUP_DEFER_TASKRUN |\
+			IORING_SETUP_NO_MMAP |\
+			IORING_SETUP_REGISTERED_FD_ONLY |\
+			IORING_SETUP_NO_SQARRAY |\
+			IORING_SETUP_HYBRID_IOPOLL |\
+			IORING_SETUP_CQE_MIXED |\
+			IORING_SETUP_SQE_MIXED |\
+			IORING_SETUP_SQ_REWIND)
+
+#define IORING_ENTER_FLAGS (IORING_ENTER_GETEVENTS |\
+			IORING_ENTER_SQ_WAKEUP |\
+			IORING_ENTER_SQ_WAIT |\
+			IORING_ENTER_EXT_ARG |\
+			IORING_ENTER_REGISTERED_RING |\
+			IORING_ENTER_ABS_TIMER |\
+			IORING_ENTER_EXT_ARG_REG |\
+			IORING_ENTER_NO_IOWAIT)
+
+
+#define SQE_VALID_FLAGS (IOSQE_FIXED_FILE |\
+			IOSQE_IO_DRAIN |\
+			IOSQE_IO_LINK |\
+			IOSQE_IO_HARDLINK |\
+			IOSQE_ASYNC |\
+			IOSQE_BUFFER_SELECT |\
+			IOSQE_CQE_SKIP_SUCCESS)
+
+#define IO_REQ_LINK_FLAGS (REQ_F_LINK | REQ_F_HARDLINK)
+
+/*
+ * Complaint timeout for io_uring cancelation exits, and for io-wq exit
+ * worker waiting.
+ */
+#define IO_URING_EXIT_WAIT_MAX	(HZ * 60 * 5)
+
+enum {
+	IOU_COMPLETE		= 0,
+
+	IOU_ISSUE_SKIP_COMPLETE	= -EIOCBQUEUED,
+
+	/*
+	 * The request has more work to do and should be retried. io_uring will
+	 * attempt to wait on the file for eligible opcodes, but otherwise
+	 * it'll be handed to iowq for blocking execution. It works for normal
+	 * requests as well as for the multi shot mode.
+	 */
+	IOU_RETRY		= -EAGAIN,
+
+	/*
+	 * Requeue the task_work to restart operations on this request. The
+	 * actual value isn't important, should just be not an otherwise
+	 * valid error code, yet less than -MAX_ERRNO and valid internally.
+	 */
+	IOU_REQUEUE		= -3072,
+};
+
+struct io_defer_entry {
+	struct list_head	list;
+	struct io_kiocb		*req;
+};
+
+struct io_wait_queue {
+	struct wait_queue_entry wq;
+	struct io_ring_ctx *ctx;
+	unsigned cq_tail;
+	unsigned cq_min_tail;
+	unsigned nr_timeouts;
+	int hit_timeout;
+	ktime_t min_timeout;
+	ktime_t timeout;
+	struct hrtimer t;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	ktime_t napi_busy_poll_dt;
+	bool napi_prefer_busy_poll;
+#endif
+};
+
+static inline struct io_rings *io_get_rings(struct io_ring_ctx *ctx)
+{
+	return rcu_dereference_check(ctx->rings_rcu,
+			lockdep_is_held(&ctx->uring_lock) ||
+			lockdep_is_held(&ctx->completion_lock));
+}
+
+static inline bool io_should_wake(struct io_wait_queue *iowq)
+{
+	struct io_ring_ctx *ctx = iowq->ctx;
+	struct io_rings *rings;
+	int dist;
+
+	guard(rcu)();
+	rings = io_get_rings(ctx);
+
+	/*
+	 * Wake up if we have enough events, or if a timeout occurred since we
+	 * started waiting. For timeouts, we always want to return to userspace,
+	 * regardless of event count.
+	 */
+	dist = READ_ONCE(rings->cq.tail) - (int) iowq->cq_tail;
+	return dist >= 0 || atomic_read(&ctx->cq_timeouts) != iowq->nr_timeouts;
+}
+
+#define IORING_MAX_ENTRIES	32768
+#define IORING_MAX_CQ_ENTRIES	(2 * IORING_MAX_ENTRIES)
+
+int io_prepare_config(struct io_ctx_config *config);
+
+bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow, bool cqe32);
+void io_req_defer_failed(struct io_kiocb *req, s32 res);
+bool io_post_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
+void io_add_aux_cqe(struct io_ring_ctx *ctx, u64 user_data, s32 res, u32 cflags);
+bool io_req_post_cqe(struct io_kiocb *req, s32 res, u32 cflags);
+bool io_req_post_cqe32(struct io_kiocb *req, struct io_uring_cqe src_cqe[2]);
+void __io_commit_cqring_flush(struct io_ring_ctx *ctx);
+
+unsigned io_linked_nr(struct io_kiocb *req);
+void io_req_track_inflight(struct io_kiocb *req);
+struct file *io_file_get_normal(struct io_kiocb *req, int fd);
+struct file *io_file_get_fixed(struct io_kiocb *req, int fd,
+			       unsigned issue_flags);
+struct file *io_uring_ctx_get_file(unsigned int fd, bool registered);
+
+void io_req_task_queue(struct io_kiocb *req);
+void io_req_task_complete(struct io_tw_req tw_req, io_tw_token_t tw);
+void io_req_task_queue_fail(struct io_kiocb *req, int ret);
+void io_req_task_submit(struct io_tw_req tw_req, io_tw_token_t tw);
+__cold void io_uring_drop_tctx_refs(struct task_struct *task);
+
+int io_ring_add_registered_file(struct io_uring_task *tctx, struct file *file,
+				     int start, int end);
+void io_queue_iowq(struct io_kiocb *req);
+
+int io_poll_issue(struct io_kiocb *req, io_tw_token_t tw);
+int io_submit_sqes(struct io_ring_ctx *ctx, unsigned int nr);
+int io_do_iopoll(struct io_ring_ctx *ctx, bool force_nonspin);
+__cold void io_iopoll_try_reap_events(struct io_ring_ctx *ctx);
+void __io_submit_flush_completions(struct io_ring_ctx *ctx);
+
+struct io_wq_work *io_wq_free_work(struct io_wq_work *work);
+void io_wq_submit_work(struct io_wq_work *work);
+
+void io_free_req(struct io_kiocb *req);
+void io_queue_next(struct io_kiocb *req);
+void io_task_refs_refill(struct io_uring_task *tctx);
+bool __io_alloc_req_refill(struct io_ring_ctx *ctx);
+
+void io_activate_pollwq(struct io_ring_ctx *ctx);
+void io_restriction_clone(struct io_restriction *dst, struct io_restriction *src);
+void io_poison_req(struct io_kiocb *req);
+
+static inline void io_lockdep_assert_cq_locked(struct io_ring_ctx *ctx)
+{
+#if defined(CONFIG_PROVE_LOCKING)
+	lockdep_assert(in_task());
+
+	if (ctx->flags & IORING_SETUP_DEFER_TASKRUN)
+		lockdep_assert_held(&ctx->uring_lock);
+
+	if (ctx->flags & IORING_SETUP_IOPOLL) {
+		lockdep_assert_held(&ctx->uring_lock);
+	} else if (!(ctx->int_flags & IO_RING_F_TASK_COMPLETE)) {
+		lockdep_assert_held(&ctx->completion_lock);
+	} else if (ctx->submitter_task) {
+		/*
+		 * ->submitter_task may be NULL and we can still post a CQE,
+		 * if the ring has been setup with IORING_SETUP_R_DISABLED.
+		 * Not from an SQE, as those cannot be submitted, but via
+		 * updating tagged resources.
+		 */
+		if (!percpu_ref_is_dying(&ctx->refs))
+			lockdep_assert(current == ctx->submitter_task);
+	}
+#endif
+}
+
+static inline bool io_is_compat(struct io_ring_ctx *ctx)
+{
+	return IS_ENABLED(CONFIG_COMPAT) && unlikely(ctx->int_flags & IO_RING_F_COMPAT);
+}
+
+static inline void io_submit_flush_completions(struct io_ring_ctx *ctx)
+{
+	if (!wq_list_empty(&ctx->submit_state.compl_reqs) ||
+	    ctx->submit_state.cq_flush)
+		__io_submit_flush_completions(ctx);
+}
+
+#define io_for_each_link(pos, head) \
+	for (pos = (head); pos; pos = pos->link)
+
+static inline bool io_get_cqe_overflow(struct io_ring_ctx *ctx,
+					struct io_uring_cqe **ret,
+					bool overflow, bool cqe32)
+{
+	io_lockdep_assert_cq_locked(ctx);
+
+	if (unlikely(ctx->cqe_sentinel - ctx->cqe_cached < (cqe32 + 1))) {
+		if (unlikely(!io_cqe_cache_refill(ctx, overflow, cqe32)))
+			return false;
+	}
+	*ret = ctx->cqe_cached;
+	ctx->cached_cq_tail++;
+	ctx->cqe_cached++;
+	if (ctx->flags & IORING_SETUP_CQE32) {
+		ctx->cqe_cached++;
+	} else if (cqe32 && ctx->flags & IORING_SETUP_CQE_MIXED) {
+		ctx->cqe_cached++;
+		ctx->cached_cq_tail++;
+	}
+	WARN_ON_ONCE(ctx->cqe_cached > ctx->cqe_sentinel);
+	return true;
+}
+
+static inline bool io_get_cqe(struct io_ring_ctx *ctx, struct io_uring_cqe **ret,
+				bool cqe32)
+{
+	return io_get_cqe_overflow(ctx, ret, false, cqe32);
+}
+
+static inline bool io_defer_get_uncommited_cqe(struct io_ring_ctx *ctx,
+					       struct io_uring_cqe **cqe_ret)
+{
+	io_lockdep_assert_cq_locked(ctx);
+
+	ctx->submit_state.cq_flush = true;
+	return io_get_cqe(ctx, cqe_ret, ctx->flags & IORING_SETUP_CQE_MIXED);
+}
+
+static __always_inline bool io_fill_cqe_req(struct io_ring_ctx *ctx,
+					    struct io_kiocb *req)
+{
+	bool is_cqe32 = req->cqe.flags & IORING_CQE_F_32;
+	struct io_uring_cqe *cqe;
+
+	/*
+	 * If we can't get a cq entry, userspace overflowed the submission
+	 * (by quite a lot).
+	 */
+	if (unlikely(!io_get_cqe(ctx, &cqe, is_cqe32)))
+		return false;
+
+	memcpy(cqe, &req->cqe, sizeof(*cqe));
+	if (ctx->flags & IORING_SETUP_CQE32 || is_cqe32) {
+		memcpy(cqe->big_cqe, &req->big_cqe, sizeof(*cqe));
+		memset(&req->big_cqe, 0, sizeof(req->big_cqe));
+	}
+
+	if (trace_io_uring_complete_enabled())
+		trace_call__io_uring_complete(req->ctx, req, cqe);
+	return true;
+}
+
+static inline void req_set_fail(struct io_kiocb *req)
+{
+	req->flags |= REQ_F_FAIL;
+	if (req->flags & REQ_F_CQE_SKIP) {
+		req->flags &= ~REQ_F_CQE_SKIP;
+		req->flags |= REQ_F_SKIP_LINK_CQES;
+	}
+}
+
+static inline void io_req_set_res(struct io_kiocb *req, s32 res, u32 cflags)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags;
+}
+
+static inline u32 ctx_cqe32_flags(struct io_ring_ctx *ctx)
+{
+	if (ctx->flags & IORING_SETUP_CQE_MIXED)
+		return IORING_CQE_F_32;
+	return 0;
+}
+
+static inline void io_req_set_res32(struct io_kiocb *req, s32 res, u32 cflags,
+				    __u64 extra1, __u64 extra2)
+{
+	req->cqe.res = res;
+	req->cqe.flags = cflags | ctx_cqe32_flags(req->ctx);
+	req->big_cqe.extra1 = extra1;
+	req->big_cqe.extra2 = extra2;
+}
+
+static inline void *io_uring_alloc_async_data(struct io_alloc_cache *cache,
+					      struct io_kiocb *req)
+{
+	if (cache) {
+		req->async_data = io_cache_alloc(cache, GFP_KERNEL);
+	} else {
+		const struct io_issue_def *def = &io_issue_defs[req->opcode];
+
+		WARN_ON_ONCE(!def->async_size);
+		req->async_data = kmalloc(def->async_size, GFP_KERNEL);
+	}
+	if (req->async_data)
+		req->flags |= REQ_F_ASYNC_DATA;
+	return req->async_data;
+}
+
+static inline bool req_has_async_data(struct io_kiocb *req)
+{
+	return req->flags & REQ_F_ASYNC_DATA;
+}
+
+static inline void io_req_async_data_clear(struct io_kiocb *req,
+					   io_req_flags_t extra_flags)
+{
+	req->flags &= ~(REQ_F_ASYNC_DATA|extra_flags);
+	req->async_data = NULL;
+}
+
+static inline void io_req_async_data_free(struct io_kiocb *req)
+{
+	kfree(req->async_data);
+	io_req_async_data_clear(req, 0);
+}
+
+static inline void io_put_file(struct io_kiocb *req)
+{
+	if (!(req->flags & REQ_F_FIXED_FILE) && req->file)
+		fput(req->file);
+}
+
+static inline void io_ring_submit_unlock(struct io_ring_ctx *ctx,
+					 unsigned issue_flags)
+{
+	lockdep_assert_held(&ctx->uring_lock);
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
+		mutex_unlock(&ctx->uring_lock);
+}
+
+static inline void io_ring_submit_lock(struct io_ring_ctx *ctx,
+				       unsigned issue_flags)
+{
+	/*
+	 * "Normal" inline submissions always hold the uring_lock, since we
+	 * grab it from the system call. Same is true for the SQPOLL offload.
+	 * The only exception is when we've detached the request and issue it
+	 * from an async worker thread, grab the lock for that case.
+	 */
+	if (unlikely(issue_flags & IO_URING_F_UNLOCKED))
+		mutex_lock(&ctx->uring_lock);
+	lockdep_assert_held(&ctx->uring_lock);
+}
+
+static inline void io_commit_cqring(struct io_ring_ctx *ctx)
+{
+	/* order cqe stores with ring update */
+	smp_store_release(&ctx->rings->cq.tail, ctx->cached_cq_tail);
+}
+
+static inline void __io_wq_wake(struct wait_queue_head *wq)
+{
+	/*
+	 *
+	 * Pass in EPOLLIN|EPOLL_URING_WAKE as the poll wakeup key. The latter
+	 * set in the mask so that if we recurse back into our own poll
+	 * waitqueue handlers, we know we have a dependency between eventfd or
+	 * epoll and should terminate multishot poll at that point.
+	 */
+	if (wq_has_sleeper(wq))
+		__wake_up(wq, TASK_NORMAL, 0, poll_to_key(EPOLL_URING_WAKE | EPOLLIN));
+}
+
+static inline void io_poll_wq_wake(struct io_ring_ctx *ctx)
+{
+	__io_wq_wake(&ctx->poll_wq);
+}
+
+static inline void io_cqring_wake(struct io_ring_ctx *ctx)
+{
+	/*
+	 * Trigger waitqueue handler on all waiters on our waitqueue. This
+	 * won't necessarily wake up all the tasks, io_should_wake() will make
+	 * that decision.
+	 */
+
+	__io_wq_wake(&ctx->cq_wait);
+}
+
+static inline bool __io_sqring_full(struct io_ring_ctx *ctx)
+{
+	struct io_rings *r = io_get_rings(ctx);
+
+	/*
+	 * SQPOLL must use the actual sqring head, as using the cached_sq_head
+	 * is race prone if the SQPOLL thread has grabbed entries but not yet
+	 * committed them to the ring. For !SQPOLL, this doesn't matter, but
+	 * since this helper is just used for SQPOLL sqring waits (or POLLOUT),
+	 * just read the actual sqring head unconditionally.
+	 */
+	return READ_ONCE(r->sq.tail) - READ_ONCE(r->sq.head) == ctx->sq_entries;
+}
+
+static inline bool io_sqring_full(struct io_ring_ctx *ctx)
+{
+	guard(rcu)();
+	return __io_sqring_full(ctx);
+}
+
+static inline unsigned int __io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	struct io_rings *rings = io_get_rings(ctx);
+	unsigned int entries;
+
+	/* make sure SQ entry isn't read before tail */
+	entries = smp_load_acquire(&rings->sq.tail) - ctx->cached_sq_head;
+	return min(entries, ctx->sq_entries);
+}
+
+static inline unsigned int io_sqring_entries(struct io_ring_ctx *ctx)
+{
+	guard(rcu)();
+	return __io_sqring_entries(ctx);
+}
+
+/*
+ * Don't complete immediately but use deferred completion infrastructure.
+ * Protected by ->uring_lock and can only be used either with
+ * IO_URING_F_COMPLETE_DEFER or inside a tw handler holding the mutex.
+ */
+static inline void io_req_complete_defer(struct io_kiocb *req)
+	__must_hold(&req->ctx->uring_lock)
+{
+	struct io_submit_state *state = &req->ctx->submit_state;
+
+	lockdep_assert_held(&req->ctx->uring_lock);
+
+	wq_list_add_tail(&req->comp_list, &state->compl_reqs);
+}
+
+#define SHOULD_FLUSH_MASK	(IO_RING_F_OFF_TIMEOUT_USED | \
+				 IO_RING_F_HAS_EVFD | IO_RING_F_POLL_ACTIVATED)
+
+static inline void io_commit_cqring_flush(struct io_ring_ctx *ctx)
+{
+	if (unlikely(data_race(ctx->int_flags) & SHOULD_FLUSH_MASK))
+		__io_commit_cqring_flush(ctx);
+}
+
+static inline void io_get_task_refs(int nr)
+{
+	struct io_uring_task *tctx = current->io_uring;
+
+	tctx->cached_refs -= nr;
+	if (unlikely(tctx->cached_refs < 0))
+		io_task_refs_refill(tctx);
+}
+
+static inline bool io_req_cache_empty(struct io_ring_ctx *ctx)
+{
+	return !ctx->submit_state.free_list.next;
+}
+
+extern struct kmem_cache *req_cachep;
+
+static inline struct io_kiocb *io_extract_req(struct io_ring_ctx *ctx)
+{
+	struct io_kiocb *req;
+
+	req = container_of(ctx->submit_state.free_list.next, struct io_kiocb, comp_list);
+	wq_stack_extract(&ctx->submit_state.free_list);
+	return req;
+}
+
+static inline bool io_alloc_req(struct io_ring_ctx *ctx, struct io_kiocb **req)
+{
+	if (unlikely(io_req_cache_empty(ctx))) {
+		if (!__io_alloc_req_refill(ctx))
+			return false;
+	}
+	*req = io_extract_req(ctx);
+	return true;
+}
+
+static inline void io_req_queue_tw_complete(struct io_kiocb *req, s32 res)
+{
+	io_req_set_res(req, res, 0);
+	req->io_task_work.func = io_req_task_complete;
+	io_req_task_work_add(req);
+}
+
+static inline bool io_file_can_poll(struct io_kiocb *req)
+{
+	if (req->flags & REQ_F_CAN_POLL)
+		return true;
+	if (req->file && file_can_poll(req->file)) {
+		req->flags |= REQ_F_CAN_POLL;
+		return true;
+	}
+	return false;
+}
+
+static inline bool io_is_uring_cmd(const struct io_kiocb *req)
+{
+	return req->opcode == IORING_OP_URING_CMD ||
+	       req->opcode == IORING_OP_URING_CMD128;
+}
+
+static inline ktime_t io_get_time(struct io_ring_ctx *ctx)
+{
+	if (ctx->clockid == CLOCK_MONOTONIC)
+		return ktime_get();
+
+	return ktime_get_with_offset(ctx->clock_offset);
+}
+
+enum {
+	IO_CHECK_CQ_OVERFLOW_BIT,
+	IO_CHECK_CQ_DROPPED_BIT,
+};
+
+static inline bool io_has_work(struct io_ring_ctx *ctx)
+{
+	return test_bit(IO_CHECK_CQ_OVERFLOW_BIT, &ctx->check_cq) ||
+	       io_local_work_pending(ctx);
+}
+#endif