io-wq relies on a manager thread to create/fork new workers, as needed.
But there's really no strong need for it anymore. We have the following
cases that fork a new worker:

1) Work queue. This is done from the task itself always, and it's trivial
   to create a worker off that path, if needed.

2) All workers have gone to sleep, and we have more work. This is called
   off the sched out path. For this case, use a task_work items to queue
   a fork-worker operation.

3) Hashed work completion. Don't think we need to do anything off this
   case. If need be, it could just use approach 2 as well.

Part of this change is incrementing the running worker count before the
fork, to avoid cases where we observe we need a worker and then queue
creation of one. Then new work comes in, we fork a new one. That last
queue operation should have waited for the previous worker to come up,
it's quite possible we don't even need it. Hence move the worker running
from before we fork it off to more efficiently handle that case.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fork() fails if signal_pending() is true, but there are two conditions
that can lead to that:

1) An actual signal is pending. We want fork to fail for that one, like
   we always have.

2) TIF_NOTIFY_SIGNAL is pending, because the task has pending task_work.
   We don't need to make it fail for that case.

Allow fork() to proceed if just task_work is pending, by changing the
signal_pending() check to task_sigpending().
Signed-off-by: Jens Axboe <axboe@kernel.dk>

This adds two new POLL_ADD flags, IORING_POLL_UPDATE_EVENTS and
IORING_POLL_UPDATE_USER_DATA. As with the other POLL_ADD flag, these are
masked into sqe->len. If set, the POLL_ADD will have the following
behavior:

- sqe->addr must contain the the user_data of the poll request that
  needs to be modified. This field is otherwise invalid for a POLL_ADD
  command.

- If IORING_POLL_UPDATE_EVENTS is set, sqe->poll_events must contain the
  new mask for the existing poll request. There are no checks for whether
  these are identical or not, if a matching poll request is found, then it
  is re-armed with the new mask.

- If IORING_POLL_UPDATE_USER_DATA is set, sqe->off must contain the new
  user_data for the existing poll request.

A POLL_ADD with any of these flags set may complete with any of the
following results:

1) 0, which means that we successfully found the existing poll request
   specified, and performed the re-arm procedure. Any error from that
   re-arm will be exposed as a completion event for that original poll
   request, not for the update request.
2) -ENOENT, if no existing poll request was found with the given
   user_data.
3) -EALREADY, if the existing poll request was already in the process of
   being removed/canceled/completing.
4) -EACCES, if an attempt was made to modify an internal poll request
   (eg not one originally issued ass IORING_OP_POLL_ADD).

The usual -EINVAL cases apply as well, if any invalid fields are set
in the sqe for this command type.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We'll need this helper for another purpose, for now just abstract it
out and have io_poll_cancel() use it for lookups.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

If we hit overflow and fail to allocate an overflow entry for the
completion, terminate the multishot poll mode.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

No functional changes in this patch, just preparation for kill multishot
poll on CQ overflow.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

The default io_uring poll mode is one-shot, where once the event triggers,
the poll command is completed and won't trigger any further events. If
we're doing repeated polling on the same file or socket, then it can be
more efficient to do multishot, where we keep triggering whenever the
event becomes true.

This deviates from the usual norm of having one CQE per SQE submitted. Add
a CQE flag, IORING_CQE_F_MORE, which tells the application to expect
further completion events from the submitted SQE. Right now the only user
of this is POLL_ADD in multishot mode.

Since sqe->poll_events is using the space that we normally use for adding
flags to commands, use sqe->len for the flag space for POLL_ADD. Multishot
mode is selected by setting IORING_POLL_ADD_MULTI in sqe->len. An
application should expect more CQEs for the specificed SQE if the CQE is
flagged with IORING_CQE_F_MORE. In multishot mode, only cancelation or an
error will terminate the poll request, in which case the flag will be
cleared.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We should be including the completion flags for better introspection on
exactly what completion event was logged.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Instead of using a request itself for overflowed CQE stashing, allocate a
separate entry. The disadvantage is that the allocation may fail and it
will be accounted as lost (see rings->cq_overflow), so we lose reliability
in case of memory pressure if the application is driving the CQ ring into
overflow. However, it opens a way for for multiple CQEs per an SQE and
even generating SQE-less CQEs.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
[axboe: use GFP_ATOMIC | __GFP_ACCOUNT]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Instead of masking these in as part of regular POLL_ADD prep, do it in
io_init_poll_iocb(), and include NVAL as that's generally unmaskable,
and RDHUP alongside the HUP that is already set.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Expect read/write to succeed and create a hot path for this case, in
particular hide all error handling with resubmission under a single
check with the desired result.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Move iov_iter_revert() resetting iterator in case of -EIOCBQUEUED into
io_resubmit_prep(), so we don't do heavy revert in hot path, also saves
a couple of checks.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

When reissue_prep failed in io_complete_rw_iopoll(), we change return
code to -EIO to prevent io_iopoll_complete() from doing resubmission.
Mark requests with a new flag (i.e. REQ_F_DONT_REISSUE) instead and
retain the original return value.

It also removes io_rw_reissue() from io_iopoll_complete() that will be
used later.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

file_end_write() is only for regular files, so the function do a couple
of dereferences to get inode and check for it. However, we already have
REQ_F_ISREG at hand, just use it and inline file_end_write().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

current->files are always valid now even for io-wq threads, so kill not
used anymore REQ_F_NO_FILE_TABLE.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

req->work is mostly unused unless it's punted, and io_init_req() is too
hot for fully initialising it. Fortunately, we can skip init work.next
as it's controlled by io-wq, and can not touch work.flags by moving
everything related into io_prep_async_work(). The only field left is
req->work.creds, but there is nothing can be done, keep maintaining it.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Extract a helper for io_work_get_acct() and io_wqe_get_acct() to avoid
duplication.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

struct io_uring_task::sqpoll is not used anymore, kill it
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_match_task() matches all requests with PF_EXITING task, even though
those may be valid requests. It was necessary for SQPOLL cancellation,
but now it kills all requests before exiting via
io_uring_cancel_sqpoll(), so it's not needed.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

REQ_F_LINK_TIMEOUT is a hint that to look for linked timeouts to cancel,
we're leaving it even when it's already fired. Hence don't care to clear
it in io_kill_linked_timeout(), it's safe and is called only once.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Inline io_task_work_add() into io_req_task_work_add(). They both work
with a request, so keeping them separate doesn't make things much more
clear, but merging allows optimise it. Apart from small wins like not
reading req->ctx or not calculating @notify in the hot path, i.e. with
tctx->task_state set, it avoids doing wake_up_process() for every single
add, but only after actually done task_work_add().
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_put_file() doesn't do a good job at generating a good code. Inline
it, so we can check REQ_F_FIXED_FILE first, prioritising FIXED_FILE case
over requests without files, and saving a memory load in that case.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Reshuffle io_dismantle_req() checks to put most of slow path stuff under
a single if.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Inline io_clean_op(), leaving __io_clean_op() but renaming it. This will
be used in following patches.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Both io_req_complete_failed() and __io_req_task_cancel() do the same
thing: set failure flag, put both req refs and emit an CQE. The former
one is a bit more advance as it puts req back into a req cache, so make
it to take over __io_req_task_cancel() and remove the last one.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Add a new helper io_flush_cached_locked_reqs() that splices
locked_free_list to free_list, and does it right doing all sync and
invariant reinit.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We don't care about ret value in io_free_req_deferred(), make the code a
bit more concise.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

One big omission is that io_put_req() haven't been marked inline, and at
least gcc 9 doesn't inline it, not to mention that it's really hot and
extra function call is intolerable, especially when it doesn't put a
final ref.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

There are two problems:
1) we always allocate refnodes in advance and free them if those
haven't been used. It's expensive, takes two allocations, where one of
them is percpu. And it may be pretty common not actually using them.

2) Current API with allocating a refnode and setting some of the fields
is error prone, we don't ever want to have a file node runninng fixed
buffer callback...

Solve both with pre-init/get API. Pre-init just leaves the node for
later if not used, and for get (i.e. io_rsrc_refnode_get()), you need to
explicitly pass all arguments setting callbacks/etc., so it's more
resilient.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Emphasize that return value of io_flush_cached_reqs() depends on number
of requests in the cache. It looks nicer and might help tools from
false-negative analyses.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Move the case of successfully issued request by doing that check first.
It's not much of a difference, just generates slightly better code for
me.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Inline __io_queue_linked_timeout(), we don't need it
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Don't do a function call (io_dismantle_req()) in the middle and place it
to near other function calls, otherwise may lead to excessive register
spilling.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

First of all, w need to set tctx->sqpoll only when we add a new entry
into ->xa, so move it from the hot path. Also extract a hot path for
io_uring_add_task_file() as an inline helper.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Add unlikely annotations, because my compiler pretty much mispredicts
every first check, and apart jumping around in the fast path, it also
generates extra instructions, like in advance setting ret value.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

__tctx_task_work() guarantees that ctx won't be killed while running
task_works, so we can remove now unnecessary ctx pinning for internally
armed polling.
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We can set canceled == true and complete out-of-line, ensure that we catch
that and correctly return -ECANCELED if the poll operation got canceled.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

The correct function is io_iopoll_complete(), which deals with completions
of IOPOLL requests, not io_poll_complete().
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We have to dig quite deep to check for particularly whether or not a
file supports a fast-path nonblock attempt. For fixed files, we can do
this lookup once and cache the state instead.

This adds two new bits to track whether we support async read/write
attempt, and lines up the REQ_F_ISREG bit with those two. The file slot
re-uses the last 3 (or 2, for 32-bit) of the file pointer to cache that
state, and then we mask it in when we go and use a fixed file.
Signed-off-by: Jens Axboe <axboe@kernel.dk>

We don't allow them at registration time, so limit the check for needing
inflight tracking in io_file_get() to the non-fixed path.
Signed-off-by: Jens Axboe <axboe@kernel.dk>