If ctx->cached_sq_head < nxt_sq_head, we should add UINT_MAX to tmp, not
tmp_nxt.

Fixes: 5da0fb1a ("io_uring: consider the overflow of sequence for timeout req")
Signed-off-by: Nyangerkun <yangerkun@huawei.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We've got two issues with the non-regular file handling for non-blocking
IO:

1) We don't want to re-do a short read in full for a non-regular file,
   as we can't just read the data again.
2) For non-regular files that don't support non-blocking IO attempts,
   we need to punt to async context even if the file is opened as
   non-blocking. Otherwise the caller always gets -EAGAIN.

Add two new request flags to handle these cases. One is just a cache
of the inode S_ISREG() status, the other tells io_uring that we always
need to punt this request to async context, even if REQ_F_NOWAIT is set.

Cc: stable@vger.kernel.org
Reported-by: NHrvoje Zeba <zeba.hrvoje@gmail.com>
Tested-by: NHrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Now we recalculate the sequence of timeout with 'req->sequence =
ctx->cached_sq_head + count - 1', judge the right place to insert
for timeout_list by compare the number of request we still expected for
completion. But we have not consider about the situation of overflow:

1. ctx->cached_sq_head + count - 1 may overflow. And a bigger count for
the new timeout req can have a small req->sequence.

2. cached_sq_head of now may overflow compare with before req. And it
will lead the timeout req with small req->sequence.

This overflow will lead to the misorder of timeout_list, which can lead
to the wrong order of the completion of timeout_list. Fix it by reuse
req->submit.sequence to store the count, and change the logic of
inserting sort in io_timeout.
Signed-off-by: Nyangerkun <yangerkun@huawei.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We have two ways a request can be deferred:

1) It's a regular request that depends on another one
2) It's a timeout that tracks completions

We have a shared helper to determine whether to defer, and that
attempts to make the right decision based on the request. But we
only have some of this information in the caller. Un-share the
two timeout/defer helpers so the caller can use the right one.

Fixes: 5262f567 ("io_uring: IORING_OP_TIMEOUT support")
Reported-by: Nyangerkun <yangerkun@huawei.com>
Reviewed-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We should not remove the workqueue, we just need to ensure that the
workqueues are synced. The workqueues are torn down on ctx removal.

Cc: stable@vger.kernel.org
Fixes: 6b06314c ("io_uring: add file set registration")
Reported-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Any changes interesting to tasks waiting in io_cqring_wait() are
commited with io_cqring_ev_posted(). However, io_ring_drop_ctx_refs()
also tries to do that but with no reason, that means spurious wakeups
every io_free_req() and io_uring_enter().

Just use percpu_ref_put() instead.
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

io_queue_link_head() accepts @force_nonblock flag, but io_ring_submit()
passes something opposite.

Fixes: c5766668 ("io_uring: optimize submit_and_wait API")
Reported-by: Nkbuild test robot <lkp@intel.com>
Signed-off-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

All system calls use struct __kernel_timespec instead of the old struct
timespec, but this one was just added with the old-style ABI. Change it
now to enforce the use of __kernel_timespec, avoiding ABI confusion and
the need for compat handlers on 32-bit architectures.

Any user space caller will have to use __kernel_timespec now, but this
is unambiguous and works for any C library regardless of the time_t
definition. A nicer way to specify the timeout would have been a less
ambiguous 64-bit nanosecond value, but I suppose it's too late now to
change that as this would impact both 32-bit and 64-bit users.

Fixes: 5262f567 ("io_uring: IORING_OP_TIMEOUT support")
Signed-off-by: NArnd Bergmann <arnd@arndb.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

For batched IO, it's not uncommon for waiters to ask for more than 1
IO to complete before being woken up. This is a problem with
wait_event() since tasks will get woken for every IO that completes,
re-check condition, then go back to sleep. For batch counts on the
order of what you do for high IOPS, that can result in 10s of extra
wakeups for the waiting task.

Add a private wake function that checks for the wake up count criteria
being met before calling autoremove_wake_function(). Pavel reports that
one test case he has runs 40% faster with proper batching of wakeups.
Reported-by: NPavel Begunkov <asml.silence@gmail.com>
Tested-by: NPavel Begunkov <asml.silence@gmail.com>
Reviewed-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Patch series "Make working with compound pages easier", v2.

These three patches add three helpers and convert the appropriate
places to use them.

This patch (of 3):

It's unnecessarily hard to find out the size of a potentially huge page.
Replace 'PAGE_SIZE << compound_order(page)' with page_size(page).

Link: http://lkml.kernel.org/r/20190721104612.19120-2-willy@infradead.orgSigned-off-by: NMatthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: NMichal Hocko <mhocko@suse.com>
Reviewed-by: NAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: NIra Weiny <ira.weiny@intel.com>
Acked-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

After 75b28aff("io_uring: allocate the two rings together"), we compare
sq.head with cached_cq_tail to determine does there any cq invalid.
Actually, we should use cq.head.

Fixes: 75b28aff ("io_uring: allocate the two rings together")
Signed-off-by: Nyangerkun <yangerkun@huawei.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Currently we just -EINVAL a read or write to an fd that isn't backed
by ->read_iter() or ->write_iter(). But we can handle them just fine,
as long as we punt fo async context first.

Implement a simple loop function for doing ->read() or ->write()
instead, and ensure we call it appropriately.
Reported-by: N李通洲 <carter.li@eoitek.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

There's been a few requests for functionality similar to io_getevents()
and epoll_wait(), where the user can specify a timeout for waiting on
events. I deliberately did not add support for this through the system
call initially to avoid overloading the args, but I can see that the use
cases for this are valid.

This adds support for IORING_OP_TIMEOUT. If a user wants to get woken
when waiting for events, simply submit one of these timeout commands
with your wait call (or before). This ensures that the application
sleeping on the CQ ring waiting for events will get woken. The timeout
command is passed in as a pointer to a struct timespec. Timeouts are
relative. The timeout command also includes a way to auto-cancel after
N events has passed.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If preempt isn't enabled in the kernel, we can run into hang issues with
sqthread submissions. Use cond_resched() to play nice instead of
cpu_relax(), if we end up starting the loop and not having any events
pending for submissions.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Sometimes io_get_req will return a NUL, then we need to do the
correct error handling, otherwise it will cause the kernel null
pointer exception.

Fixes: 4fe2c963 ("io_uring: add support for link with drain")
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If we end up getting woken in poll (due to a signal), then we may need
to punt the poll request to an async worker. When we do that, we look up
the list to queue at, deferefencing req->submit.sqe, however that is
only set for requests we initially decided to queue async.

This fixes a crash with poll command usage and wakeups that need to punt
to async context.

Fixes: 54a91f3b ("io_uring: limit parallelism of buffered writes")
Signed-off-by: NJens Axboe <axboe@kernel.dk>

There is a potential dangling pointer problem. we never clean
shadow_req, if there are multiple link lists in this series of
sqes, then the shadow_req will not reallocate, and continue to
use the last one. but in the previous, his memory has been
released, thus forming a dangling pointer. let's clean up him
and make sure that every new link list can reapply for a new
shadow_req.

Fixes: 4fe2c963 ("io_uring: add support for link with drain")
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Just clean up the code, no function changes.
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Some workloads can require far more than 4K oustanding entries. For
example memcached can have ~300K sockets over ~40 cores. Bumping the max
to 32K seems to work pretty well.
Reported-by: NDan Melnic <dmm@fb.com>
Signed-off-by: NDaniel Xu <dxu@dxuuu.xyz>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The way the logic is setup in io_uring_enter() means that you can't wake
up the SQ poller thread while at the same time waiting (or polling) for
completions afterwards. There's no reason for that to be the case.
Reported-by: NLewis Baker <lbaker@fb.com>
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We currently merge async work items if we see a strict sequential hit.
This helps avoid unnecessary workqueue switches when we don't need
them. We can extend this merging to cover cases where it's not a strict
sequential hit, but the IO still fits within the same page. If an
application is doing multiple requests within the same page, we don't
want separate workers waiting on the same page to complete IO. It's much
faster to let the first worker bring in the page, then operate on that
page from the same worker to complete the next request(s).
Reviewed-by: NJeff Moyer <jmoyer@redhat.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

All the popular filesystems need to grab the inode lock for buffered
writes. With io_uring punting buffered writes to async context, we
observe a lot of contention with all workers hamming this mutex.

For buffered writes, we generally don't need a lot of parallelism on
the submission side, as the flushing will take care of that for us.
Hence we don't need a deep queue on the write side, as long as we
can safely punt from the original submission context.

Add a workqueue with a limit of 2 that we can use for buffered writes.
This greatly improves the performance and efficiency of higher queue
depth buffered async writes with io_uring.
Reported-by: NAndres Freund <andres@anarazel.de>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Add a helper for queueing a request for async execution, in preparation
for optimizing it.

No functional change in this patch.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

For some applications that end up using a submit-and-wait type of
approach for certain batches of IO, we can make that a bit more
efficient by allowing the application to block for the last IO
submission. This prevents an async when we don't need it, as the
application will be blocking for the completion event(s) anyway.

Typical use cases are using the liburing
io_uring_submit_and_wait() API, or just using io_uring_enter()
doing both submissions and completions. As a specific example,
RocksDB doing MultiGet() is sped up quite a bit with this
change.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

To support the link with drain, we need to do two parts.

There is an sqes:

    0     1     2     3     4     5     6
 +-----+-----+-----+-----+-----+-----+-----+
 |  N  |  L  |  L  | L+D |  N  |  N  |  N  |
 +-----+-----+-----+-----+-----+-----+-----+

First, we need to ensure that the io before the link is completed,
there is a easy way is set drain flag to the link list's head, so
all subsequent io will be inserted into the defer_list.

	+-----+
    (0) |  N  |
	+-----+
           |          (2)         (3)         (4)
	+-----+     +-----+     +-----+     +-----+
    (1) | L+D | --> |  L  | --> | L+D | --> |  N  |
	+-----+     +-----+     +-----+     +-----+
           |
	+-----+
    (5) |  N  |
	+-----+
           |
	+-----+
    (6) |  N  |
	+-----+

Second, ensure that the following IO will not be completed first,
an easy way is to create a mirror of drain io and insert it into
defer_list, in this way, as long as drain io is not processed, the
following io in the defer_list will not be actively process.

	+-----+
    (0) |  N  |
	+-----+
           |          (2)         (3)         (4)
	+-----+     +-----+     +-----+     +-----+
    (1) | L+D | --> |  L  | --> | L+D | --> |  N  |
	+-----+     +-----+     +-----+     +-----+
           |
	+-----+
   ('3) |  D  |   <== This is a shadow of (3)
	+-----+
           |
	+-----+
    (5) |  N  |
	+-----+
           |
	+-----+
    (6) |  N  |
	+-----+
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Sqo_thread will get sqring in batches, which will cause
ctx->cached_sq_head to be added in batches. if one of these
sqes is set with the DRAIN flag, then he will never get a
chance to process, and finally sqo_thread will not exit.

Fixes: de0617e4 ("io_uring: add support for marking commands as draining")
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

After commit 75b28aff we can get by with just a single mmap to
map both the sq and cq ring. However, userspace doesn't know that.

Add a features variable to io_uring_params, and notify userspace
that the kernel has this ability. This can then be used in liburing
(or in applications directly) to avoid the second mmap.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Both the sq and the cq rings have sizes just over a power of two, and
the sq ring is significantly smaller. By bundling them in a single
alllocation, we get the sq ring for free.

This also means that IORING_OFF_SQ_RING and IORING_OFF_CQ_RING now mean
the same thing. If we indicate this to userspace, we can save a mmap
call.
Signed-off-by: NHristo Venev <hristo@venev.name>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

For pages that were retained via get_user_pages*(), release those pages
via the new put_user_page*() routines, instead of via put_page() or
release_pages().

This is part a tree-wide conversion, as described in commit fc1d8e7c
("mm: introduce put_user_page*(), placeholder versions").

Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-block@vger.kernel.org
Signed-off-by: NJohn Hubbard <jhubbard@nvidia.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

The outer poll loop checks for whether we need to reschedule, and
returns to userspace if we do. However, it's possible to get stuck
in the inner loop as well, if the CPU we are running on needs to
reschedule to finish the IO work.

Add the need_resched() check in the inner loop as well. This fixes
a potential hang if the kernel is configured with
CONFIG_PREEMPT_VOLUNTARY=y.
Reported-by: NSagi Grimberg <sagi@grimberg.me>
Reviewed-by: NSagi Grimberg <sagi@grimberg.me>
Tested-by: NSagi Grimberg <sagi@grimberg.me>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We need to check if we have CQEs pending before starting a poll loop,
as those could be the events we will be spinning for (and hence we'll
find none). This can happen if a CQE triggers an error, or if it is
found by eg an IRQ before we get a chance to find it through polling.
Signed-off-by: NJens Axboe <axboe@kernel.dk>

If a request issue ends up being punted to async context to avoid
blocking, we can get into a situation where the original application
enters the poll loop for that very request before it has been issued.
This should not be an issue, except that the polling will hold the
io_uring uring_ctx mutex for the duration of the poll. When the async
worker has actually issued the request, it needs to acquire this mutex
to add the request to the poll issued list. Since the application
polling is already holding this mutex, the workqueue sleeps on the
mutex forever, and the application thus never gets a chance to poll for
the very request it was interested in.

Fix this by ensuring that the polling drops the uring_ctx occasionally
if it's not making any progress.
Reported-by: NJeffrey M. Birnbaum <jmbnyc@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

This patch may fix two issues:

First, when IOSQE_IO_DRAIN set, the next IOs need to be inserted into
defer list to delay execution, but link io will be actively scheduled to
run by calling io_queue_sqe.

Second, when multiple LINK_IOs are inserted together with defer_list,
the LINK_IO is no longer keep order.

   |-------------|
   |   LINK_IO   |      ----> insert to defer_list  -----------
   |-------------|                                            |
   |   LINK_IO   |      ----> insert to defer_list  ----------|
   |-------------|                                            |
   |   LINK_IO   |      ----> insert to defer_list  ----------|
   |-------------|                                            |
   |   NORMAL_IO |      ----> insert to defer_list  ----------|
   |-------------|                                            |
                                                              |
                              queue_work at same time   <-----|

Fixes: 9e645e11 ("io_uring: add support for sqe links")
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Commit bd11b3a3 ("io_uring: don't use iov_iter_advance() for fixed
buffers") introduced an optimization to avoid using the slow
iov_iter_advance by manually populating the iov_iter iterator in some
cases.

However, the computation of the iterator count field was erroneous: The
first bvec was always accounted for an extent of page size even if the
bvec length was smaller.

In consequence, some I/O operations on fixed buffers were unable to
operate on the full extent of the buffer, consistently skipping some
bytes at the end of it.

Fixes: bd11b3a3 ("io_uring: don't use iov_iter_advance() for fixed buffers")
Cc: stable@vger.kernel.org
Signed-off-by: NAleix Roca Nonell <aleix.rocanonell@bsc.es>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

[root@localhost ~]# ./liburing/test/link

QEMU Standard PC report that:

[   29.379892] CPU: 0 PID: 84 Comm: kworker/u2:2 Not tainted 5.3.0-rc2-00051-g4010b622-dirty #86
[   29.379902] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
[   29.379913] Workqueue: io_ring-wq io_sq_wq_submit_work
[   29.379929] Call Trace:
[   29.379953]  dump_stack+0xa9/0x10e
[   29.379970]  ? io_sq_wq_submit_work+0xbf4/0xe90
[   29.379986]  print_address_description.cold.6+0x9/0x317
[   29.379999]  ? io_sq_wq_submit_work+0xbf4/0xe90
[   29.380010]  ? io_sq_wq_submit_work+0xbf4/0xe90
[   29.380026]  __kasan_report.cold.7+0x1a/0x34
[   29.380044]  ? io_sq_wq_submit_work+0xbf4/0xe90
[   29.380061]  kasan_report+0xe/0x12
[   29.380076]  io_sq_wq_submit_work+0xbf4/0xe90
[   29.380104]  ? io_sq_thread+0xaf0/0xaf0
[   29.380152]  process_one_work+0xb59/0x19e0
[   29.380184]  ? pwq_dec_nr_in_flight+0x2c0/0x2c0
[   29.380221]  worker_thread+0x8c/0xf40
[   29.380248]  ? __kthread_parkme+0xab/0x110
[   29.380265]  ? process_one_work+0x19e0/0x19e0
[   29.380278]  kthread+0x30b/0x3d0
[   29.380292]  ? kthread_create_on_node+0xe0/0xe0
[   29.380311]  ret_from_fork+0x3a/0x50

[   29.380635] Allocated by task 209:
[   29.381255]  save_stack+0x19/0x80
[   29.381268]  __kasan_kmalloc.constprop.6+0xc1/0xd0
[   29.381279]  kmem_cache_alloc+0xc0/0x240
[   29.381289]  io_submit_sqe+0x11bc/0x1c70
[   29.381300]  io_ring_submit+0x174/0x3c0
[   29.381311]  __x64_sys_io_uring_enter+0x601/0x780
[   29.381322]  do_syscall_64+0x9f/0x4d0
[   29.381336]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

[   29.381633] Freed by task 84:
[   29.382186]  save_stack+0x19/0x80
[   29.382198]  __kasan_slab_free+0x11d/0x160
[   29.382210]  kmem_cache_free+0x8c/0x2f0
[   29.382220]  io_put_req+0x22/0x30
[   29.382230]  io_sq_wq_submit_work+0x28b/0xe90
[   29.382241]  process_one_work+0xb59/0x19e0
[   29.382251]  worker_thread+0x8c/0xf40
[   29.382262]  kthread+0x30b/0x3d0
[   29.382272]  ret_from_fork+0x3a/0x50

[   29.382569] The buggy address belongs to the object at ffff888067172140
                which belongs to the cache io_kiocb of size 224
[   29.384692] The buggy address is located 120 bytes inside of
                224-byte region [ffff888067172140, ffff888067172220)
[   29.386723] The buggy address belongs to the page:
[   29.387575] page:ffffea00019c5c80 refcount:1 mapcount:0 mapping:ffff88806ace5180 index:0x0
[   29.387587] flags: 0x100000000000200(slab)
[   29.387603] raw: 0100000000000200 dead000000000100 dead000000000122 ffff88806ace5180
[   29.387617] raw: 0000000000000000 00000000800c000c 00000001ffffffff 0000000000000000
[   29.387624] page dumped because: kasan: bad access detected

[   29.387920] Memory state around the buggy address:
[   29.388771]  ffff888067172080: fb fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc
[   29.390062]  ffff888067172100: fc fc fc fc fc fc fc fc fb fb fb fb fb fb fb fb
[   29.391325] >ffff888067172180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[   29.392578]                                         ^
[   29.393480]  ffff888067172200: fb fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc
[   29.394744]  ffff888067172280: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[   29.396003] ==================================================================
[   29.397260] Disabling lock debugging due to kernel taint

io_sq_wq_submit_work free and read req again.

Cc: Zhengyuan Liu <liuzhengyuan@kylinos.cn>
Cc: linux-block@vger.kernel.org
Cc: stable@vger.kernel.org
Fixes: f7b76ac9 ("io_uring: fix counter inc/dec mismatch in async_list")
Signed-off-by: NJackie Liu <liuyun01@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Daniel reports that when testing an http server that uses io_uring
to poll for incoming connections, sometimes it hard crashes. This is
due to an uninitialized list member for the io_uring request. Normally
this doesn't trigger and none of the test cases caught it.
Reported-by: NDaniel Kozak <kozzi11@gmail.com>
Tested-by: NDaniel Kozak <kozzi11@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

We are using PAGE_SIZE as the unit to determine if the total len in
async_list has exceeded max_pages, it's not fair for smaller io sizes.
For example, if we are doing 1k-size io streams, we will never exceed
max_pages since len >>= PAGE_SHIFT always gets zero. So use original
bytes to make it more accurate.
Signed-off-by: NZhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

Hrvoje reports that when a large fixed buffer is registered and IO is
being done to the latter pages of said buffer, the IO submission time
is much worse:

reading to the start of the buffer: 11238 ns
reading to the end of the buffer:   1039879 ns

In fact, it's worse by two orders of magnitude. The reason for that is
how io_uring figures out how to setup the iov_iter. We point the iter
at the first bvec, and then use iov_iter_advance() to fast-forward to
the offset within that buffer we need.

However, that is abysmally slow, as it entails iterating the bvecs
that we setup as part of buffer registration. There's really no need
to use this generic helper, as we know it's a BVEC type iterator, and
we also know that each bvec is PAGE_SIZE in size, apart from possibly
the first and last. Hence we can just use a shift on the offset to
find the right index, and then adjust the iov_iter appropriately.
After this fix, the timings are:

reading to the start of the buffer: 10135 ns
reading to the end of the buffer:   1377 ns

Or about an 755x improvement for the tail page.
Reported-by: NHrvoje Zeba <zeba.hrvoje@gmail.com>
Tested-by: NHrvoje Zeba <zeba.hrvoje@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

There is a hang issue while using fio to do some basic test. The issue
can be easily reproduced using the below script:

        while true
        do
                fio  --ioengine=io_uring  -rw=write -bs=4k -numjobs=1 \
                     -size=1G -iodepth=64 -name=uring   --filename=/dev/zero
        done

After several minutes (or more), fio would block at
io_uring_enter->io_cqring_wait in order to waiting for previously
committed sqes to be completed and can't return to user anymore until
we send a SIGTERM to fio. After receiving SIGTERM, fio hangs at
io_ring_ctx_wait_and_kill with a backtrace like this:

        [54133.243816] Call Trace:
        [54133.243842]  __schedule+0x3a0/0x790
        [54133.243868]  schedule+0x38/0xa0
        [54133.243880]  schedule_timeout+0x218/0x3b0
        [54133.243891]  ? sched_clock+0x9/0x10
        [54133.243903]  ? wait_for_completion+0xa3/0x130
        [54133.243916]  ? _raw_spin_unlock_irq+0x2c/0x40
        [54133.243930]  ? trace_hardirqs_on+0x3f/0xe0
        [54133.243951]  wait_for_completion+0xab/0x130
        [54133.243962]  ? wake_up_q+0x70/0x70
        [54133.243984]  io_ring_ctx_wait_and_kill+0xa0/0x1d0
        [54133.243998]  io_uring_release+0x20/0x30
        [54133.244008]  __fput+0xcf/0x270
        [54133.244029]  ____fput+0xe/0x10
        [54133.244040]  task_work_run+0x7f/0xa0
        [54133.244056]  do_exit+0x305/0xc40
        [54133.244067]  ? get_signal+0x13b/0xbd0
        [54133.244088]  do_group_exit+0x50/0xd0
        [54133.244103]  get_signal+0x18d/0xbd0
        [54133.244112]  ? _raw_spin_unlock_irqrestore+0x36/0x60
        [54133.244142]  do_signal+0x34/0x720
        [54133.244171]  ? exit_to_usermode_loop+0x7e/0x130
        [54133.244190]  exit_to_usermode_loop+0xc0/0x130
        [54133.244209]  do_syscall_64+0x16b/0x1d0
        [54133.244221]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

The reason is that we had added a req to ctx->pending_async at the very
end, but it didn't get a chance to be processed. How could this happen?

        fio#cpu0                                        wq#cpu1

        io_add_to_prev_work                    io_sq_wq_submit_work

          atomic_read() <<< 1

                                                  atomic_dec_return() << 1->0
                                                  list_empty();    <<< true;

          list_add_tail()
          atomic_read() << 0 or 1?

As atomic_ops.rst states, atomic_read does not guarantee that the
runtime modification by any other thread is visible yet, so we must take
care of that with a proper implicit or explicit memory barrier.

This issue was detected with the help of Jackie's <liuyun01@kylinos.cn>

Fixes: 31b51510 ("io_uring: allow workqueue item to handle multiple buffered requests")
Signed-off-by: NZhengyuan Liu <liuzhengyuan@kylinos.cn>
Signed-off-by: NJens Axboe <axboe@kernel.dk>

task->saved_sigmask and ->restore_sigmask are only used in the ret-from-
syscall paths.  This means that set_user_sigmask() can save ->blocked in
->saved_sigmask and do set_restore_sigmask() to indicate that ->blocked
was modified.

This way the callers do not need 2 sigset_t's passed to set/restore and
restore_user_sigmask() renamed to restore_saved_sigmask_unless() turns
into the trivial helper which just calls restore_saved_sigmask().

Link: http://lkml.kernel.org/r/20190606113206.GA9464@redhat.comSigned-off-by: NOleg Nesterov <oleg@redhat.com>
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Wong <e@80x24.org>
Cc: Jason Baron <jbaron@akamai.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: David Laight <David.Laight@aculab.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>