The block layer has a couple of cases where it can lose
Force Unit Access semantics when writing a large block of
zeroes, such that the request returns before the zeroes
have been guaranteed to land on underlying media.
SCSI does not support FUA during WRITESAME(10/16); FUA is only
supported if it falls back to WRITE(10/16). But where the
underlying device is new enough to not need a fallback, it
means that any upper layer request with FUA semantics was
silently ignoring BDRV_REQ_FUA.
Conversely, NBD has situations where it can support FUA but not
ZERO_WRITE; when that happens, the generic block layer fallback
to bdrv_driver_pwritev() (or the older bdrv_co_writev() in qemu
2.6) was losing the FUA flag.
The problem of losing flags unrelated to ZERO_WRITE has been
latent in bdrv_co_do_write_zeroes() since commit aa7bfbff, but
back then, it did not matter because there was no FUA flag. It
became observable when commit 93f5e6d8 paved the way for flags
that can impact correctness, when we should have been using
bdrv_co_writev_flags() with modified flags. Compare to commit
9eeb6dd, which got flag manipulation right in
bdrv_co_do_zero_pwritev().
Symptoms: I tested with qemu-io with default writethrough cache
(which is supposed to use FUA semantics on every write), and
targetted an NBD client connected to a server that intentionally
did not advertise NBD_FLAG_SEND_FUA. When doing 'write 0 512',
the NBD client sent two operations (NBD_CMD_WRITE then
NBD_CMD_FLUSH) to get the fallback FUA semantics; but when doing
'write -z 0 512', the NBD client sent only NBD_CMD_WRITE.
The fix is do to a cleanup bdrv_co_flush() at the end of the
operation if any step in the middle relied on a BDS that does
not natively support FUA for that step (note that we don't
need to flush after every operation, if the operation is broken
into chunks based on bounce-buffer sizing). Each BDS gains a
new flag .supported_zero_flags, which parallels the use of
.supported_write_flags but only when accessing a zero write
operation (the flags MUST be different, because of SCSI having
different semantics based on WRITE vs. WRITESAME; and also
because BDRV_REQ_MAY_UNMAP only makes sense on zero writes).
Also fix some documentation to describe -ENOTSUP semantics,
particularly since iscsi depends on those semantics.
Down the road, we may want to add a driver where its
.bdrv_co_pwritev() honors all three of BDRV_REQ_FUA,
BDRV_REQ_ZERO_WRITE, and BDRV_REQ_MAY_UNMAP, and advertise
this via bs->supported_write_flags for blocks opened by that
driver; such a driver should NOT supply .bdrv_co_write_zeroes
nor .supported_zero_flags. But none of the drivers touched
in this patch want to do that (the act of writing zeroes is
different enough from normal writes to deserve a second
callback).
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Pre-patch, .supported_write_flags lives at the driver level, which
means we are blindly declaring that all block devices using a
given driver will either equally support FUA, or that we need a
fallback at the block layer. But there are drivers where FUA
support is a per-block decision: the NBD block driver is dependent
on the remote server advertising NBD_FLAG_SEND_FUA (and has
fallback code to duplicate the flush that the block layer would do
if NBD had not set .supported_write_flags); and the iscsi block
driver is dependent on the mode sense bits advertised by the
underlying device (and is currently silently ignoring FUA requests
if the underlying device does not support FUA).
The fix is to make supported flags as a per-BDS option, set during
.bdrv_open(). This patch moves the variable and fixes NBD and iscsi
to set it only conditionally; later patches will then further
simplify the NBD driver to quit duplicating work done at the block
layer, as well as tackle the fact that SCSI does not support FUA
semantics on WRITESAME(10/16) but only on WRITE(10/16).
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
There is a possibility that qcow2_co_write_zeroes() will be called
with the partial block. This could be synthetically triggered with
qemu-io -c "write -z 32k 4k"
and can happen in the real life in qemu-nbd. The latter happens under
the following conditions:
(1) qemu-nbd is started with --detect-zeroes=on and is connected to the
kernel NBD client
(2) third party program opens kernel NBD device with O_DIRECT
(3) third party program performs write operation with memory buffer
not aligned to the page
In this case qcow2_co_write_zeroes() is unable to perform the operation
and mark entire cluster as zeroed and returns ENOTSUP. Thus the caller
switches to non-optimized version and writes real zeroes to the disk.
The patch creates a shortcut. If the block is read as zeroes, f.e. if
it is unallocated, the request is extended to cover full block.
User-visible situation with this block is not changed. Before the patch
the block is filled in the image with real zeroes. After that patch the
block is marked as zeroed in metadata. Thus any subsequent changes in
backing store chain are not affected.
Kevin, thank you for a cool suggestion.
Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Now that there are no remaining clients, we can drop the
sector-based blk_read(), blk_write(), blk_aio_readv(), and
blk_aio_writev(). Sadly, there are still remaining
sector-based interfaces, such as blk_*discard(), or
blk_write_compressed(); those will have to wait for another
day.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
qemu-io is the last user of several sector-based interfaces.
This patch upgrades to the new interfaces under the hood,
then deletes the resulting dead code. Note that for maximum
back-compat, while the -p option is no longer required to get
blk_pread(), it is still needed to allow for unaligned access;
this is because qemu-iotest 23 relies on qemu-io rejecting
unaligned accesses without -p. A later patch may clean up the
interface to be more user-friendly, but it's better to separate
what's done under the hood from what the user sees.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_read() should die; switch to byte-based
blk_pread() instead.
Add a constant for our magic number 512, to make it obvious
that this size will NOT change even if BDRV_SECTOR_SIZE does,
even though the two happen to be the same for now. Split
assignments from conditionals to keep checkpatch.pl happy.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_read() should die; switch to byte-based
blk_pread() instead.
Add new defines ATAPI_SECTOR_BITS and ATAPI_SECTOR_SIZE to
use anywhere we were previously scaling BDRV_SECTOR_* by 4,
for better legibility.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_read() should die; switch to byte-based
blk_pread() instead.
Likewise for blk_aio_readv() and blk_aio_writev().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
Greatly simplifies the code, now that we let the block layer
take care of alignment and read-modify-write on our behalf :)
In fact, we no longer need to include 'buf' in the migration
stream (although we do have to ensure that the stream remains
compatible).
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
This particular device picks its size during onenand_initfn(),
and can be at most 0x80000000 bytes; therefore, shifting an
'int sec' request to get back to a byte offset should never
overflow 32 bits. But adding assertions to document that point
should not hurt.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
This file is doing some complex computations to map various
flash page sizes (256, 512, and 2048) atop generic uses of
512-byte sector operations. Perhaps someone will want to tidy
up the file for fewer gymnastics in managing addresses and
offsets, and less wasteful visits of 256-byte pages, but it
was out of scope for this series, where I just went with the
mechanical conversion.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; switch to byte-based
blk_pwrite() instead. Likewise for blk_read().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_aio_readv() and blk_aio_writev() should die; switch
to byte-based blk_aio_preadv() and blk_aio_pwritev() instead.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_aio_readv() and blk_aio_writev() should die; switch
to byte-based blk_aio_preadv() and blk_aio_pwritev() instead.
The trace is modified at the same time, and nb_sectors is now
unused. Fix a comment typo while in the vicinity.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_aio_readv() and blk_aio_writev() should die; switch
to byte-based blk_aio_preadv() and blk_aio_pwritev() instead.
As part of the cleanup, scsi_init_iovec() no longer needs to return
a value, and reword a comment.
[ kwolf: Fix read accounting change ]
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_aio_readv() and blk_aio_writev() should die; switch
to byte-based blk_aio_preadv() and blk_aio_pwritev() instead.
The patch had to touch multiple files at once, because dma_blk_io()
takes pointers to the functions, and ide_issue_trim() piggybacks on
the same interface (while ignoring offset under the hood).
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
blk_aio_readv() and blk_aio_writev() are annoying in that they
can't access sub-sector granularity, and cannot pass flags.
Also, they require the caller to pass redundant information
about the size of the I/O (qiov->size in bytes must match
nb_sectors in sectors).
Add new blk_aio_preadv() and blk_aio_pwritev() functions to fix
the flaws. The next few patches will upgrade callers, then
finally delete the old interfaces.
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_write() should die; convert the one-off
variant blk_write_zeroes() to use an offset/count interface
instead. Likewise for blk_co_write_zeroes() and
blk_aio_write_zeroes().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Sector-based blk_read() should die; convert the one-off
variant blk_read_unthrottled().
Signed-off-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
We have several block drivers that understand BDRV_REQ_FUA,
and emulate it in the block layer for the rest by a full flush.
But without a way to actually request BDRV_REQ_FUA during a
pass-through blk_pwrite(), FUA-aware block drivers like NBD are
forced to repeat the emulation logic of a full flush regardless
of whether the backend they are writing to could do it more
efficiently.
This patch just wires up a flags argument; followup patches
will actually make use of it in the NBD driver and in qemu-io.
Signed-off-by: Eric Blake <eblake@redhat.com>
Acked-by: Denis V. Lunev <den@openvz.org>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Vmdk images have metadata to indicate the vmware virtual
hardware version image was created/tested to run with.
Allow users to specify that version via new 'hwversion'
option.
[ kwolf: Adjust qemu-iotests common.filter ]
Signed-off-by: Janne Karhunen <Janne.Karhunen@gmail.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Files with conditional debug statements should ensure that the printf is
always compiled. This prevents bitrot of the format string of the debug
statement. And switch debug output to stderr.
Signed-off-by: Zhou Jie <zhoujie2011@cn.fujitsu.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
There are no block drivers left that implement the old .bdrv_read/write
interface, so it can be removed now. This gets us rid of the
corresponding emulation functions, too.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This doesn't really convert any of the actual vvfat logic to use
vectored I/O (and it's doubtful whether that would make sense), but
instead just adapts the wrappers to the modern interface.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This is a byte granularity version of vmdk_find_index_in_cluster().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This implements .bdrv_co_preadv() for the cloop block driver. While
updating the error paths, change -1 to a valid -errno code.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This implements .bdrv_co_preadv() for the cloop block driver. While
updating the error paths, change -1 to a valid -errno code.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Many parts of the block layer are already byte granularity. The block
driver interface, however, was still missing an interface that allows
making use of this. This patch introduces a new BlockDriver interface,
which is based on coroutines, vectored, has flags and uses a byte
granularity. This is now the preferred interface for new drivers.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
It used to be an internal helper function just for implementing
bdrv_co_do_readv/writev(), but now that it's a public interface, it
deserves a name without "do" in it.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Instead of registering emulation functions as .bdrv_co_writev, just
directly check whether the function is there or not, and use the AIO
interface if it isn't. This makes the read/write functions more
consistent with how things are done in other places (flush, discard,
etc.)
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This is a function that simply calls into the block driver for doing a
write, providing the byte granularity interface we want to eventually
have everywhere, and using whatever interface that driver supports.
This one is a bit more interesting than the version for reads: It adds
support for .bdrv_co_writev_flags() everywhere, so that drivers
implementing this function can drop .bdrv_co_writev() now.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
This is a function that simply calls into the block driver for doing a
read, providing the byte granularity interface we want to eventually
have everywhere, and using whatever interface that driver supports.
For now, this is just a wrapper for calling bs->drv->bdrv_co_readv().
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Replace void* with an opaque LinuxAioState type.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Extract the handling of io_plug "depth" from linux-aio.c and let the
main bdrv_drain loop do nothing but wait on I/O.
Like the two newly introduced functions, bdrv_io_plug and bdrv_io_unplug
now operate on all children. The visit order is now symmetrical between
plug and unplug, making it possible for formats to implement plug/unplug.
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Extract the handling of throttling from bdrv_flush_io_queue. These
new functions will soon become BdrvChildRole callbacks, as they can
be generalized to "beginning of drain" and "end of drain".
Reviewed-by: Alberto Garcia <berto@igalia.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Do not call bdrv_drain_recurse twice in bdrv_co_drain. A small
tweak to the logic in Fam's patch, which is harmless since no
one implements bdrv_drain anyway. But better get it right.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
We want to remove throttled_reqs from block/io.c. This is the easy
part---hide the handling of throttled_reqs during disable/enable of
throttling within throttle-groups.c.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
The return value is unused and I am not sure why it would be useful.
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
We had to disable I/O throttling with synchronous requests because we
didn't use to run timers in nested event loops when the code was
introduced. This isn't true any more, and throttling works just fine
even when using the synchronous API.
The removed code is in fact dead code since commit a8823a3b ('block: Use
blk_co_pwritev() for blk_write()') because I/O throttling can only be
set on the top layer, but BlockBackend always uses the coroutine
interface now instead of using the sync API emulation in block.c.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <1458660792-3035-2-git-send-email-kwolf@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
