Some code in the block layer makes potentially huge allocations. Failure
is not completely unexpected there, so avoid aborting qemu and handle
out-of-memory situations gracefully.

This patch addresses the allocations in the raw-win32 block driver.
Signed-off-by: NKevin Wolf <kwolf@redhat.com>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>

Drop the assumption that we're using the main AioContext for raw-win32.
Convert the aio-win32 code to support detach/attach and replace
qemu_aio_wait() with aio_poll().

The .bdrv_detach/attach_aio_context() interfaces move the aio-win32
event notifier from the old to the new AioContext.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

Each QEMUWin32AIOState event notifier is associated with an AioContext.
Since BlockDriverState instances can use different AioContexts we cannot
continue to use a global QEMUWin32AIOState.

Let each BDRVRawState have its own QEMUWin32AIOState and free it when
BDRVRawState is closed.
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

The io_flush argument to qemu_aio_set_event_notifier() has been removed
since the block layer learnt to drain requests by itself.  Fix the
Windows build for win32-aio.o by updating the
qemu_aio_set_event_notifier() call and dropping win32_aio_flush_cb().
Reviewed-by: NStefan Weil <sw@weilnetz.de>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

This patch is used to remove twice include of "qemu-common.h" in
block/win32-aio.c
Signed-off-by: NQiao Nuohan <qiaonuohan@cn.fujitsu.com>
Reviewed-by: NStefan Weil <sw@weilnetz.de>
Signed-off-by: NMichael Tokarev <mjt@tls.msk.ru>

We have iov_from_buf() and iov_to_buf(), use them instead of
open-coding these in block/win32-aio.c
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

The buffer is allocated for both reads and writes, and obviously it
should be freed even if an error occurs.

Cc: qemu-stable@nongnu.org
Signed-off-by: NKevin Wolf <kwolf@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

Copying data in the right direction really helps a lot!

Cc: qemu-stable@nongnu.org
Signed-off-by: NKevin Wolf <kwolf@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

win32_aio_submit() allocates it with qemu_blockalign(), therefore it
must be freed with qemu_vfree(), not g_free().
Signed-off-by: NMarkus Armbruster <armbru@redhat.com>
Reviewed-by: NKevin Wolf <kwolf@redhat.com>
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>

Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Now that AIOPool no longer keeps a freelist, it isn't really a "pool"
anymore.  Rename it to AIOCBInfo and make it const since it no longer
needs to be modified.
Signed-off-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NKevin Wolf <kwolf@redhat.com>

Versions before gcc-4.6 don't support unnamed fields in initializers
(see http://gcc.gnu.org/bugzilla/show_bug.cgi?id=10676).

Offset and OffsetHigh belong to an unnamed struct which is part of an
unnamed union. Therefore the original code does not work with older
versions of gcc.
Signed-off-by: NStefan Weil <sw@weilnetz.de>
Reviewed-by: NStefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: NKevin Wolf <kwolf@redhat.com>

With the new support for EventNotifiers in the AIO event loop, we
can hook a completion port to every opened file and use asynchronous
I/O on them.

Wine's support is extremely inefficient, also because it really does
the I/O synchronously on regular files. (!)  But it works, and it is
good to keep the Win32 and POSIX ports as similar as possible.
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>