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, 973 insertions, 0 deletions

diff --git a/io_uring/poll.c b/io_uring/poll.c
new file mode 100644
index 000000000..5447a7c24
--- /dev/null
+++ b/io_uring/poll.c
@@ -0,0 +1,973 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/hashtable.h>
+#include <linux/io_uring.h>
+
+#include <trace/events/io_uring.h>
+
+#include <uapi/linux/io_uring.h>
+
+#include "io_uring.h"
+#include "alloc_cache.h"
+#include "refs.h"
+#include "napi.h"
+#include "opdef.h"
+#include "kbuf.h"
+#include "poll.h"
+#include "cancel.h"
+
+struct io_poll_update {
+	struct file			*file;
+	u64				old_user_data;
+	u64				new_user_data;
+	__poll_t			events;
+	bool				update_events;
+	bool				update_user_data;
+};
+
+struct io_poll_table {
+	struct poll_table_struct pt;
+	struct io_kiocb *req;
+	int nr_entries;
+	int error;
+	bool owning;
+	/* output value, set only if arm poll returns >0 */
+	__poll_t result_mask;
+};
+
+#define IO_POLL_CANCEL_FLAG	BIT(31)
+#define IO_POLL_RETRY_FLAG	BIT(30)
+#define IO_POLL_REF_MASK	GENMASK(29, 0)
+
+/*
+ * We usually have 1-2 refs taken, 128 is more than enough and we want to
+ * maximise the margin between this amount and the moment when it overflows.
+ */
+#define IO_POLL_REF_BIAS	128
+
+#define IO_WQE_F_DOUBLE		1
+
+static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+			void *key);
+
+static inline struct io_kiocb *wqe_to_req(struct wait_queue_entry *wqe)
+{
+	unsigned long priv = (unsigned long)wqe->private;
+
+	return (struct io_kiocb *)(priv & ~IO_WQE_F_DOUBLE);
+}
+
+static inline bool wqe_is_double(struct wait_queue_entry *wqe)
+{
+	unsigned long priv = (unsigned long)wqe->private;
+
+	return priv & IO_WQE_F_DOUBLE;
+}
+
+static bool io_poll_get_ownership_slowpath(struct io_kiocb *req)
+{
+	int v;
+
+	/*
+	 * poll_refs are already elevated and we don't have much hope for
+	 * grabbing the ownership. Instead of incrementing set a retry flag
+	 * to notify the loop that there might have been some change.
+	 */
+	v = atomic_fetch_or(IO_POLL_RETRY_FLAG, &req->poll_refs);
+	if (v & IO_POLL_REF_MASK)
+		return false;
+	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
+}
+
+/*
+ * If refs part of ->poll_refs (see IO_POLL_REF_MASK) is 0, it's free. We can
+ * bump it and acquire ownership. It's disallowed to modify requests while not
+ * owning it, that prevents from races for enqueueing task_work's and b/w
+ * arming poll and wakeups.
+ */
+static inline bool io_poll_get_ownership(struct io_kiocb *req)
+{
+	if (unlikely((unsigned int)atomic_read(&req->poll_refs) >= IO_POLL_REF_BIAS))
+		return io_poll_get_ownership_slowpath(req);
+	return !(atomic_fetch_inc(&req->poll_refs) & IO_POLL_REF_MASK);
+}
+
+static void io_poll_mark_cancelled(struct io_kiocb *req)
+{
+	atomic_or(IO_POLL_CANCEL_FLAG, &req->poll_refs);
+}
+
+static struct io_poll *io_poll_get_double(struct io_kiocb *req)
+{
+	/* pure poll stashes this in ->async_data, poll driven retry elsewhere */
+	if (req->opcode == IORING_OP_POLL_ADD)
+		return req->async_data;
+	return req->apoll->double_poll;
+}
+
+static struct io_poll *io_poll_get_single(struct io_kiocb *req)
+{
+	if (req->opcode == IORING_OP_POLL_ADD)
+		return io_kiocb_to_cmd(req, struct io_poll);
+	return &req->apoll->poll;
+}
+
+static void io_poll_req_insert(struct io_kiocb *req)
+{
+	struct io_hash_table *table = &req->ctx->cancel_table;
+	u32 index = hash_long(req->cqe.user_data, table->hash_bits);
+
+	lockdep_assert_held(&req->ctx->uring_lock);
+
+	hlist_add_head(&req->hash_node, &table->hbs[index].list);
+}
+
+static void io_init_poll_iocb(struct io_poll *poll, __poll_t events)
+{
+	poll->head = NULL;
+#define IO_POLL_UNMASK	(EPOLLERR|EPOLLHUP|EPOLLNVAL|EPOLLRDHUP)
+	/* mask in events that we always want/need */
+	poll->events = events | IO_POLL_UNMASK;
+	INIT_LIST_HEAD(&poll->wait.entry);
+	init_waitqueue_func_entry(&poll->wait, io_poll_wake);
+}
+
+static void io_poll_remove_waitq(struct io_poll *poll)
+{
+	/*
+	 * If the waitqueue is being freed early but someone is already holds
+	 * ownership over it, we have to tear down the request as best we can.
+	 * That means immediately removing the request from its waitqueue and
+	 * preventing all further accesses to the waitqueue via the request.
+	 */
+	list_del_init(&poll->wait.entry);
+
+	/*
+	 * Careful: this *must* be the last step, since as soon as req->head is
+	 * NULL'ed out, the request can be completed and freed, since
+	 * io_poll_remove_entry() will no longer need to take the waitqueue
+	 * lock.
+	 */
+	smp_store_release(&poll->head, NULL);
+}
+
+static inline void io_poll_remove_entry(struct io_poll *poll)
+{
+	struct wait_queue_head *head = smp_load_acquire(&poll->head);
+
+	if (head) {
+		spin_lock_irq(&head->lock);
+		io_poll_remove_waitq(poll);
+		spin_unlock_irq(&head->lock);
+	}
+}
+
+static void io_poll_remove_entries(struct io_kiocb *req)
+{
+	/*
+	 * Nothing to do if neither of those flags are set. Avoid dipping
+	 * into the poll/apoll/double cachelines if we can.
+	 */
+	if (!(req->flags & (REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL)))
+		return;
+
+	/*
+	 * While we hold the waitqueue lock and the waitqueue is nonempty,
+	 * wake_up_pollfree() will wait for us.  However, taking the waitqueue
+	 * lock in the first place can race with the waitqueue being freed.
+	 *
+	 * We solve this as eventpoll does: by taking advantage of the fact that
+	 * all users of wake_up_pollfree() will RCU-delay the actual free.  If
+	 * we enter rcu_read_lock() and see that the pointer to the queue is
+	 * non-NULL, we can then lock it without the memory being freed out from
+	 * under us.
+	 *
+	 * Keep holding rcu_read_lock() as long as we hold the queue lock, in
+	 * case the caller deletes the entry from the queue, leaving it empty.
+	 * In that case, only RCU prevents the queue memory from being freed.
+	 */
+	rcu_read_lock();
+	if (req->flags & REQ_F_SINGLE_POLL)
+		io_poll_remove_entry(io_poll_get_single(req));
+	if (req->flags & REQ_F_DOUBLE_POLL)
+		io_poll_remove_entry(io_poll_get_double(req));
+	rcu_read_unlock();
+}
+
+enum {
+	IOU_POLL_DONE = 0,
+	IOU_POLL_NO_ACTION = 1,
+	IOU_POLL_REMOVE_POLL_USE_RES = 2,
+	IOU_POLL_REISSUE = 3,
+	IOU_POLL_REQUEUE = 4,
+};
+
+static void __io_poll_execute(struct io_kiocb *req, int mask, unsigned tw_flags)
+{
+	unsigned flags = tw_flags;
+
+	io_req_set_res(req, mask, 0);
+	req->io_task_work.func = io_poll_task_func;
+
+	trace_io_uring_task_add(req, mask);
+
+	if (!(req->flags & REQ_F_POLL_NO_LAZY))
+		flags |= IOU_F_TWQ_LAZY_WAKE;
+	__io_req_task_work_add(req, flags);
+}
+
+static inline void io_poll_execute(struct io_kiocb *req, int res,
+				   unsigned tw_flags)
+{
+	if (io_poll_get_ownership(req))
+		__io_poll_execute(req, res, tw_flags);
+}
+
+/*
+ * All poll tw should go through this. Checks for poll events, manages
+ * references, does rewait, etc.
+ *
+ * Returns a negative error on failure. IOU_POLL_NO_ACTION when no action
+ * require, which is either spurious wakeup or multishot CQE is served.
+ * IOU_POLL_DONE when it's done with the request, then the mask is stored in
+ * req->cqe.res. IOU_POLL_REMOVE_POLL_USE_RES indicates to remove multishot
+ * poll and that the result is stored in req->cqe.
+ */
+static int io_poll_check_events(struct io_kiocb *req, io_tw_token_t tw)
+{
+	int v;
+
+	if (unlikely(tw.cancel))
+		return -ECANCELED;
+
+	do {
+		v = atomic_read(&req->poll_refs);
+
+		if (unlikely(v != 1)) {
+			/* tw should be the owner and so have some refs */
+			if (WARN_ON_ONCE(!(v & IO_POLL_REF_MASK)))
+				return IOU_POLL_NO_ACTION;
+			if (v & IO_POLL_CANCEL_FLAG)
+				return -ECANCELED;
+			/*
+			 * cqe.res contains only events of the first wake up
+			 * and all others are to be lost. Redo vfs_poll() to get
+			 * up to date state.
+			 */
+			if ((v & IO_POLL_REF_MASK) != 1)
+				req->cqe.res = 0;
+
+			if (v & IO_POLL_RETRY_FLAG) {
+				req->cqe.res = 0;
+				/*
+				 * We won't find new events that came in between
+				 * vfs_poll and the ref put unless we clear the
+				 * flag in advance.
+				 */
+				atomic_andnot(IO_POLL_RETRY_FLAG, &req->poll_refs);
+				v &= ~IO_POLL_RETRY_FLAG;
+			}
+			v &= IO_POLL_REF_MASK;
+		}
+
+		/* the mask was stashed in __io_poll_execute */
+		if (!req->cqe.res) {
+			__poll_t events = req->apoll_events;
+			struct poll_table_struct pt = { ._key = events };
+
+			req->cqe.res = vfs_poll(req->file, &pt) & events;
+			/*
+			 * We got woken with a mask, but someone else got to
+			 * it first. The above vfs_poll() doesn't add us back
+			 * to the waitqueue, so if we get nothing back, we
+			 * should be safe and attempt a reissue.
+			 */
+			if (unlikely(!req->cqe.res)) {
+				/* Multishot armed need not reissue */
+				if (!(events & EPOLLONESHOT))
+					continue;
+				return IOU_POLL_REISSUE;
+			}
+		}
+		if (req->apoll_events & EPOLLONESHOT)
+			return IOU_POLL_DONE;
+
+		/* multishot, just fill a CQE and proceed */
+		if (!(req->flags & REQ_F_APOLL_MULTISHOT)) {
+			__poll_t mask = mangle_poll(req->cqe.res &
+						    req->apoll_events);
+
+			if (!io_req_post_cqe(req, mask, IORING_CQE_F_MORE)) {
+				io_req_set_res(req, mask, 0);
+				return IOU_POLL_REMOVE_POLL_USE_RES;
+			}
+		} else {
+			int ret;
+
+			/* multiple refs and HUP, ensure we loop once more */
+			if ((req->cqe.res & (POLLHUP | POLLRDHUP)) && v != 1)
+				v--;
+
+			ret = io_poll_issue(req, tw);
+			if (ret == IOU_COMPLETE)
+				return IOU_POLL_REMOVE_POLL_USE_RES;
+			else if (ret == IOU_REQUEUE)
+				return IOU_POLL_REQUEUE;
+			if (ret != IOU_RETRY && ret < 0)
+				return ret;
+		}
+
+		/* force the next iteration to vfs_poll() */
+		req->cqe.res = 0;
+
+		/*
+		 * Release all references, retry if someone tried to restart
+		 * task_work while we were executing it.
+		 */
+	} while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
+
+	io_napi_add(req);
+	return IOU_POLL_NO_ACTION;
+}
+
+void io_poll_task_func(struct io_tw_req tw_req, io_tw_token_t tw)
+{
+	struct io_kiocb *req = tw_req.req;
+	int ret;
+
+	ret = io_poll_check_events(req, tw);
+	if (ret == IOU_POLL_NO_ACTION) {
+		return;
+	} else if (ret == IOU_POLL_REQUEUE) {
+		__io_poll_execute(req, 0, 0);
+		return;
+	}
+	io_poll_remove_entries(req);
+	/* task_work always has ->uring_lock held */
+	hash_del(&req->hash_node);
+
+	if (req->opcode == IORING_OP_POLL_ADD) {
+		if (ret == IOU_POLL_DONE) {
+			struct io_poll *poll;
+
+			poll = io_kiocb_to_cmd(req, struct io_poll);
+			req->cqe.res = mangle_poll(req->cqe.res & poll->events);
+		} else if (ret == IOU_POLL_REISSUE) {
+			io_req_task_submit(tw_req, tw);
+			return;
+		} else if (ret != IOU_POLL_REMOVE_POLL_USE_RES) {
+			req->cqe.res = ret;
+			req_set_fail(req);
+		}
+
+		io_req_set_res(req, req->cqe.res, 0);
+		io_req_task_complete(tw_req, tw);
+	} else {
+		io_tw_lock(req->ctx, tw);
+
+		if (ret == IOU_POLL_REMOVE_POLL_USE_RES)
+			io_req_task_complete(tw_req, tw);
+		else if (ret == IOU_POLL_DONE || ret == IOU_POLL_REISSUE)
+			io_req_task_submit(tw_req, tw);
+		else
+			io_req_defer_failed(req, ret);
+	}
+}
+
+static void io_poll_cancel_req(struct io_kiocb *req)
+{
+	io_poll_mark_cancelled(req);
+	/* kick tw, which should complete the request */
+	io_poll_execute(req, 0, 0);
+}
+
+#define IO_ASYNC_POLL_COMMON	(EPOLLONESHOT | EPOLLPRI)
+
+static __cold int io_pollfree_wake(struct io_kiocb *req, struct io_poll *poll)
+{
+	io_poll_mark_cancelled(req);
+	/* we have to kick tw in case it's not already */
+	io_poll_execute(req, 0, IOU_F_TWQ_IN_WAKE);
+	io_poll_remove_waitq(poll);
+	return 1;
+}
+
+static int io_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+			void *key)
+{
+	struct io_kiocb *req = wqe_to_req(wait);
+	struct io_poll *poll = container_of(wait, struct io_poll, wait);
+	__poll_t mask = key_to_poll(key);
+
+	if (unlikely(mask & POLLFREE))
+		return io_pollfree_wake(req, poll);
+
+	/* for instances that support it check for an event match first */
+	if (mask && !(mask & (poll->events & ~IO_ASYNC_POLL_COMMON)))
+		return 0;
+
+	if (io_poll_get_ownership(req)) {
+		/*
+		 * If we trigger a multishot poll off our own wakeup path,
+		 * disable multishot as there is a circular dependency between
+		 * CQ posting and triggering the event.
+		 */
+		if (mask & EPOLL_URING_WAKE) {
+			poll->events |= EPOLLONESHOT;
+			req->apoll_events |= EPOLLONESHOT;
+		}
+
+		/* optional, saves extra locking for removal in tw handler */
+		if (mask && poll->events & EPOLLONESHOT) {
+			io_poll_remove_waitq(poll);
+			if (wqe_is_double(wait))
+				req->flags &= ~REQ_F_DOUBLE_POLL;
+			else
+				req->flags &= ~REQ_F_SINGLE_POLL;
+		}
+		__io_poll_execute(req, mask, IOU_F_TWQ_IN_WAKE);
+	}
+	return 1;
+}
+
+/* fails only when polling is already completing by the first entry */
+static bool io_poll_double_prepare(struct io_kiocb *req)
+{
+	struct wait_queue_head *head;
+	struct io_poll *poll = io_poll_get_single(req);
+
+	/* head is RCU protected, see io_poll_remove_entries() comments */
+	rcu_read_lock();
+	head = smp_load_acquire(&poll->head);
+	/*
+	 * poll arm might not hold ownership and so race for req->flags with
+	 * io_poll_wake(). There is only one poll entry queued, serialise with
+	 * it by taking its head lock. As we're still arming the tw hanlder
+	 * is not going to be run, so there are no races with it.
+	 */
+	if (head) {
+		spin_lock_irq(&head->lock);
+		req->flags |= REQ_F_DOUBLE_POLL;
+		if (req->opcode == IORING_OP_POLL_ADD)
+			req->flags |= REQ_F_ASYNC_DATA;
+		spin_unlock_irq(&head->lock);
+	}
+	rcu_read_unlock();
+	return !!head;
+}
+
+static void __io_queue_proc(struct io_poll *poll, struct io_poll_table *pt,
+			    struct wait_queue_head *head,
+			    struct io_poll **poll_ptr)
+{
+	struct io_kiocb *req = pt->req;
+	unsigned long wqe_private = (unsigned long) req;
+
+	/*
+	 * The file being polled uses multiple waitqueues for poll handling
+	 * (e.g. one for read, one for write). Setup a separate io_poll
+	 * if this happens.
+	 */
+	if (unlikely(pt->nr_entries)) {
+		struct io_poll *first = poll;
+
+		/* double add on the same waitqueue head, ignore */
+		if (first->head == head)
+			return;
+		/* already have a 2nd entry, fail a third attempt */
+		if (*poll_ptr) {
+			if ((*poll_ptr)->head == head)
+				return;
+			pt->error = -EINVAL;
+			return;
+		}
+
+		poll = kmalloc_obj(*poll, GFP_ATOMIC);
+		if (!poll) {
+			pt->error = -ENOMEM;
+			return;
+		}
+
+		/* mark as double wq entry */
+		wqe_private |= IO_WQE_F_DOUBLE;
+		io_init_poll_iocb(poll, first->events);
+		if (!io_poll_double_prepare(req)) {
+			/* the request is completing, just back off */
+			kfree(poll);
+			return;
+		}
+		*poll_ptr = poll;
+	} else {
+		/* fine to modify, there is no poll queued to race with us */
+		req->flags |= REQ_F_SINGLE_POLL;
+	}
+
+	pt->nr_entries++;
+	poll->head = head;
+	poll->wait.private = (void *) wqe_private;
+
+	if (poll->events & EPOLLEXCLUSIVE) {
+		add_wait_queue_exclusive(head, &poll->wait);
+	} else {
+		add_wait_queue(head, &poll->wait);
+	}
+}
+
+static void io_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+			       struct poll_table_struct *p)
+{
+	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+	struct io_poll *poll = io_kiocb_to_cmd(pt->req, struct io_poll);
+
+	__io_queue_proc(poll, pt, head,
+			(struct io_poll **) &pt->req->async_data);
+}
+
+static bool io_poll_can_finish_inline(struct io_kiocb *req,
+				      struct io_poll_table *pt)
+{
+	return pt->owning || io_poll_get_ownership(req);
+}
+
+static void io_poll_add_hash(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	io_poll_req_insert(req);
+	io_ring_submit_unlock(ctx, issue_flags);
+}
+
+/*
+ * Returns 0 when it's handed over for polling. The caller owns the requests if
+ * it returns non-zero, but otherwise should not touch it. Negative values
+ * contain an error code. When the result is >0, the polling has completed
+ * inline and ipt.result_mask is set to the mask.
+ */
+static int __io_arm_poll_handler(struct io_kiocb *req,
+				 struct io_poll *poll,
+				 struct io_poll_table *ipt, __poll_t mask,
+				 unsigned issue_flags)
+{
+	INIT_HLIST_NODE(&req->hash_node);
+	io_init_poll_iocb(poll, mask);
+	poll->file = req->file;
+	req->apoll_events = poll->events;
+
+	ipt->pt._key = mask;
+	ipt->req = req;
+	ipt->error = 0;
+	ipt->nr_entries = 0;
+	/*
+	 * Polling is either completed here or via task_work, so if we're in the
+	 * task context we're naturally serialised with tw by merit of running
+	 * the same task. When it's io-wq, take the ownership to prevent tw
+	 * from running. However, when we're in the task context, skip taking
+	 * it as an optimisation.
+	 *
+	 * Note: even though the request won't be completed/freed, without
+	 * ownership we still can race with io_poll_wake().
+	 * io_poll_can_finish_inline() tries to deal with that.
+	 */
+	ipt->owning = issue_flags & IO_URING_F_UNLOCKED;
+	atomic_set(&req->poll_refs, (int)ipt->owning);
+
+	/*
+	 * Exclusive waits may only wake a limited amount of entries
+	 * rather than all of them, this may interfere with lazy
+	 * wake if someone does wait(events > 1). Ensure we don't do
+	 * lazy wake for those, as we need to process each one as they
+	 * come in.
+	 */
+	if (poll->events & EPOLLEXCLUSIVE)
+		req->flags |= REQ_F_POLL_NO_LAZY;
+
+	mask = vfs_poll(req->file, &ipt->pt) & poll->events;
+
+	if (unlikely(ipt->error || !ipt->nr_entries)) {
+		io_poll_remove_entries(req);
+
+		if (!io_poll_can_finish_inline(req, ipt)) {
+			io_poll_mark_cancelled(req);
+			return 0;
+		} else if (mask && (poll->events & EPOLLET)) {
+			ipt->result_mask = mask;
+			return 1;
+		}
+		return ipt->error ?: -EINVAL;
+	}
+
+	if (mask &&
+	   ((poll->events & (EPOLLET|EPOLLONESHOT)) == (EPOLLET|EPOLLONESHOT))) {
+		if (!io_poll_can_finish_inline(req, ipt)) {
+			io_poll_add_hash(req, issue_flags);
+			return 0;
+		}
+		io_poll_remove_entries(req);
+		ipt->result_mask = mask;
+		/* no one else has access to the req, forget about the ref */
+		return 1;
+	}
+
+	io_poll_add_hash(req, issue_flags);
+
+	if (mask && (poll->events & EPOLLET) &&
+	    io_poll_can_finish_inline(req, ipt)) {
+		__io_poll_execute(req, mask, 0);
+		return 0;
+	}
+	io_napi_add(req);
+
+	if (ipt->owning) {
+		/*
+		 * Try to release ownership. If we see a change of state, e.g.
+		 * poll was waken up, queue up a tw, it'll deal with it.
+		 */
+		if (atomic_cmpxchg(&req->poll_refs, 1, 0) != 1)
+			__io_poll_execute(req, 0, 0);
+	}
+	return 0;
+}
+
+static void io_async_queue_proc(struct file *file, struct wait_queue_head *head,
+			       struct poll_table_struct *p)
+{
+	struct io_poll_table *pt = container_of(p, struct io_poll_table, pt);
+	struct async_poll *apoll = pt->req->apoll;
+
+	__io_queue_proc(&apoll->poll, pt, head, &apoll->double_poll);
+}
+
+/*
+ * We can't reliably detect loops in repeated poll triggers and issue
+ * subsequently failing. But rather than fail these immediately, allow a
+ * certain amount of retries before we give up. Given that this condition
+ * should _rarely_ trigger even once, we should be fine with a larger value.
+ */
+#define APOLL_MAX_RETRY		128
+
+static struct async_poll *io_req_alloc_apoll(struct io_kiocb *req,
+					     unsigned issue_flags)
+{
+	struct io_ring_ctx *ctx = req->ctx;
+	struct async_poll *apoll;
+
+	if (req->flags & REQ_F_POLLED) {
+		apoll = req->apoll;
+		kfree(apoll->double_poll);
+	} else {
+		if (!(issue_flags & IO_URING_F_UNLOCKED))
+			apoll = io_cache_alloc(&ctx->apoll_cache, GFP_ATOMIC);
+		else
+			apoll = kmalloc_obj(*apoll, GFP_ATOMIC);
+		if (!apoll)
+			return NULL;
+		apoll->poll.retries = APOLL_MAX_RETRY;
+	}
+	apoll->double_poll = NULL;
+	req->apoll = apoll;
+	if (unlikely(!--apoll->poll.retries))
+		return NULL;
+	return apoll;
+}
+
+int io_arm_apoll(struct io_kiocb *req, unsigned issue_flags, __poll_t mask)
+{
+	struct async_poll *apoll;
+	struct io_poll_table ipt;
+	int ret;
+
+	mask |= EPOLLET;
+	if (!io_file_can_poll(req))
+		return IO_APOLL_ABORTED;
+	if (!(req->flags & REQ_F_APOLL_MULTISHOT))
+		mask |= EPOLLONESHOT;
+
+	apoll = io_req_alloc_apoll(req, issue_flags);
+	if (!apoll)
+		return IO_APOLL_ABORTED;
+	req->flags &= ~(REQ_F_SINGLE_POLL | REQ_F_DOUBLE_POLL);
+	req->flags |= REQ_F_POLLED;
+	ipt.pt._qproc = io_async_queue_proc;
+
+	ret = __io_arm_poll_handler(req, &apoll->poll, &ipt, mask, issue_flags);
+	if (ret)
+		return ret > 0 ? IO_APOLL_READY : IO_APOLL_ABORTED;
+	trace_io_uring_poll_arm(req, mask, apoll->poll.events);
+	return IO_APOLL_OK;
+}
+
+int io_arm_poll_handler(struct io_kiocb *req, unsigned issue_flags)
+{
+	const struct io_issue_def *def = &io_issue_defs[req->opcode];
+	__poll_t mask = POLLPRI | POLLERR;
+
+	if (!def->pollin && !def->pollout)
+		return IO_APOLL_ABORTED;
+	if (!io_file_can_poll(req))
+		return IO_APOLL_ABORTED;
+
+	if (def->pollin) {
+		mask |= EPOLLIN | EPOLLRDNORM;
+
+		/* If reading from MSG_ERRQUEUE using recvmsg, ignore POLLIN */
+		if (req->flags & REQ_F_CLEAR_POLLIN)
+			mask &= ~EPOLLIN;
+	} else {
+		mask |= EPOLLOUT | EPOLLWRNORM;
+	}
+	if (def->poll_exclusive)
+		mask |= EPOLLEXCLUSIVE;
+
+	return io_arm_apoll(req, issue_flags, mask);
+}
+
+/*
+ * Returns true if we found and killed one or more poll requests
+ */
+__cold bool io_poll_remove_all(struct io_ring_ctx *ctx, struct io_uring_task *tctx,
+			       bool cancel_all)
+{
+	unsigned nr_buckets = 1U << ctx->cancel_table.hash_bits;
+	struct hlist_node *tmp;
+	struct io_kiocb *req;
+	bool found = false;
+	int i;
+
+	lockdep_assert_held(&ctx->uring_lock);
+
+	for (i = 0; i < nr_buckets; i++) {
+		struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+
+		hlist_for_each_entry_safe(req, tmp, &hb->list, hash_node) {
+			if (io_match_task_safe(req, tctx, cancel_all)) {
+				hlist_del_init(&req->hash_node);
+				io_poll_cancel_req(req);
+				found = true;
+			}
+		}
+	}
+	return found;
+}
+
+static struct io_kiocb *io_poll_find(struct io_ring_ctx *ctx, bool poll_only,
+				     struct io_cancel_data *cd)
+{
+	struct io_kiocb *req;
+	u32 index = hash_long(cd->data, ctx->cancel_table.hash_bits);
+	struct io_hash_bucket *hb = &ctx->cancel_table.hbs[index];
+
+	hlist_for_each_entry(req, &hb->list, hash_node) {
+		if (cd->data != req->cqe.user_data)
+			continue;
+		if (poll_only && req->opcode != IORING_OP_POLL_ADD)
+			continue;
+		if (cd->flags & IORING_ASYNC_CANCEL_ALL) {
+			if (io_cancel_match_sequence(req, cd->seq))
+				continue;
+		}
+		return req;
+	}
+	return NULL;
+}
+
+static struct io_kiocb *io_poll_file_find(struct io_ring_ctx *ctx,
+					  struct io_cancel_data *cd)
+{
+	unsigned nr_buckets = 1U << ctx->cancel_table.hash_bits;
+	struct io_kiocb *req;
+	int i;
+
+	for (i = 0; i < nr_buckets; i++) {
+		struct io_hash_bucket *hb = &ctx->cancel_table.hbs[i];
+
+		hlist_for_each_entry(req, &hb->list, hash_node) {
+			if (io_cancel_req_match(req, cd))
+				return req;
+		}
+	}
+	return NULL;
+}
+
+static int io_poll_disarm(struct io_kiocb *req)
+{
+	if (!req)
+		return -ENOENT;
+	if (!io_poll_get_ownership(req))
+		return -EALREADY;
+	io_poll_remove_entries(req);
+	hash_del(&req->hash_node);
+	return 0;
+}
+
+static int __io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd)
+{
+	struct io_kiocb *req;
+
+	if (cd->flags & (IORING_ASYNC_CANCEL_FD | IORING_ASYNC_CANCEL_OP |
+			 IORING_ASYNC_CANCEL_ANY))
+		req = io_poll_file_find(ctx, cd);
+	else
+		req = io_poll_find(ctx, false, cd);
+
+	if (req) {
+		io_poll_cancel_req(req);
+		return 0;
+	}
+	return -ENOENT;
+}
+
+int io_poll_cancel(struct io_ring_ctx *ctx, struct io_cancel_data *cd,
+		   unsigned issue_flags)
+{
+	int ret;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	ret = __io_poll_cancel(ctx, cd);
+	io_ring_submit_unlock(ctx, issue_flags);
+	return ret;
+}
+
+static __poll_t io_poll_parse_events(const struct io_uring_sqe *sqe,
+				     unsigned int flags)
+{
+	u32 events;
+
+	events = READ_ONCE(sqe->poll32_events);
+#ifdef __BIG_ENDIAN
+	events = swahw32(events);
+#endif
+	if (!(flags & IORING_POLL_ADD_MULTI))
+		events |= EPOLLONESHOT;
+	if (!(flags & IORING_POLL_ADD_LEVEL))
+		events |= EPOLLET;
+	return demangle_poll(events) |
+		(events & (EPOLLEXCLUSIVE|EPOLLONESHOT|EPOLLET));
+}
+
+int io_poll_remove_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_poll_update *upd = io_kiocb_to_cmd(req, struct io_poll_update);
+	u32 flags;
+
+	if (sqe->buf_index || sqe->splice_fd_in)
+		return -EINVAL;
+	flags = READ_ONCE(sqe->len);
+	if (flags & ~(IORING_POLL_UPDATE_EVENTS | IORING_POLL_UPDATE_USER_DATA |
+		      IORING_POLL_ADD_MULTI))
+		return -EINVAL;
+	/* meaningless without update */
+	if (flags == IORING_POLL_ADD_MULTI)
+		return -EINVAL;
+
+	upd->old_user_data = READ_ONCE(sqe->addr);
+	upd->update_events = flags & IORING_POLL_UPDATE_EVENTS;
+	upd->update_user_data = flags & IORING_POLL_UPDATE_USER_DATA;
+
+	upd->new_user_data = READ_ONCE(sqe->off);
+	if (!upd->update_user_data && upd->new_user_data)
+		return -EINVAL;
+	if (upd->update_events)
+		upd->events = io_poll_parse_events(sqe, flags);
+	else if (sqe->poll32_events)
+		return -EINVAL;
+
+	return 0;
+}
+
+int io_poll_add_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
+{
+	struct io_poll *poll = io_kiocb_to_cmd(req, struct io_poll);
+	u32 flags;
+
+	if (sqe->buf_index || sqe->off || sqe->addr)
+		return -EINVAL;
+	flags = READ_ONCE(sqe->len);
+	if (flags & ~IORING_POLL_ADD_MULTI)
+		return -EINVAL;
+	if ((flags & IORING_POLL_ADD_MULTI) && (req->flags & REQ_F_CQE_SKIP))
+		return -EINVAL;
+
+	poll->events = io_poll_parse_events(sqe, flags);
+	return 0;
+}
+
+int io_poll_add(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_poll *poll = io_kiocb_to_cmd(req, struct io_poll);
+	struct io_poll_table ipt;
+	int ret;
+
+	ipt.pt._qproc = io_poll_queue_proc;
+
+	ret = __io_arm_poll_handler(req, poll, &ipt, poll->events, issue_flags);
+	if (ret > 0) {
+		io_req_set_res(req, ipt.result_mask, 0);
+		return IOU_COMPLETE;
+	}
+	return ret ?: IOU_ISSUE_SKIP_COMPLETE;
+}
+
+int io_poll_remove(struct io_kiocb *req, unsigned int issue_flags)
+{
+	struct io_poll_update *poll_update = io_kiocb_to_cmd(req, struct io_poll_update);
+	struct io_ring_ctx *ctx = req->ctx;
+	struct io_cancel_data cd = { .ctx = ctx, .data = poll_update->old_user_data, };
+	struct io_kiocb *preq;
+	int ret2, ret = 0;
+
+	io_ring_submit_lock(ctx, issue_flags);
+	preq = io_poll_find(ctx, true, &cd);
+	ret2 = io_poll_disarm(preq);
+	if (ret2) {
+		ret = ret2;
+		goto out;
+	}
+	if (WARN_ON_ONCE(preq->opcode != IORING_OP_POLL_ADD)) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	if (poll_update->update_events || poll_update->update_user_data) {
+		/* only mask one event flags, keep behavior flags */
+		if (poll_update->update_events) {
+			struct io_poll *poll = io_kiocb_to_cmd(preq, struct io_poll);
+
+			poll->events &= ~0xffff;
+			poll->events |= poll_update->events & 0xffff;
+			poll->events |= IO_POLL_UNMASK;
+		}
+		if (poll_update->update_user_data)
+			preq->cqe.user_data = poll_update->new_user_data;
+
+		ret2 = io_poll_add(preq, issue_flags & ~IO_URING_F_UNLOCKED);
+		/* successfully updated, don't complete poll request */
+		if (ret2 == IOU_ISSUE_SKIP_COMPLETE)
+			goto out;
+		/* request completed as part of the update, complete it */
+		else if (ret2 == IOU_COMPLETE)
+			goto complete;
+	}
+
+	io_req_set_res(preq, -ECANCELED, 0);
+complete:
+	if (preq->cqe.res < 0)
+		req_set_fail(preq);
+	preq->io_task_work.func = io_req_task_complete;
+	io_req_task_work_add(preq);
+out:
+	io_ring_submit_unlock(ctx, issue_flags);
+	if (ret < 0) {
+		req_set_fail(req);
+		return ret;
+	}
+	/* complete update request, we're done with it */
+	io_req_set_res(req, ret, 0);
+	return IOU_COMPLETE;
+}