Compare commits

..

59 Commits

Author SHA1 Message Date
Michael Roth
db51dfc1fc Update version for 2.5.1.1 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com
2016-05-09 11:55:58 -05:00
Michael S. Tsirkin
5b7236f725 cadence_uart: bounds check write offset
cadence_uart_init() initializes an I/O memory region of size 0x1000
bytes.  However in uart_write(), the 'offset' parameter (offset within
region) is divided by 4 and then used to index the array 'r' of size
CADENCE_UART_R_MAX which is much smaller: (0x48/4).  If 'offset>>=2'
exceeds CADENCE_UART_R_MAX, this will cause an out-of-bounds memory
write where the offset and the value are controlled by guest.

This will corrupt QEMU memory, in most situations this causes the vm to
crash.

Fix by checking the offset against the array size.

Cc: qemu-stable@nongnu.org
Reported-by: 李强 <liqiang6-s@360.cn>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Alistair Francis <alistair.francis@xilinx.com>
Message-id: 20160418100735.GA517@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 5eb0b194e9)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-09 11:55:58 -05:00
Gerd Hoffmann
0bcdb632f8 Revert "ehci: make idt processing more robust"
This reverts commit 156a2e4dbf.

Breaks FreeBSD.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit a49923d283)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 22:37:18 -05:00
Gerd Hoffmann
706bab670b ehci: apply limit to iTD/sidt descriptors
Commit "156a2e4 ehci: make idt processing more robust" tries to avoid a
DoS by the guest (create a circular iTD queue and let qemu ehci
emulation run in circles forever).  Unfortunately this has two problems:
First it misses the case of siTDs, and second it reportedly breaks
FreeBSD.

So lets go for a different approach: just count the number of iTDs and
siTDs we have seen per frame and apply a limit.  That should really
catch all cases now.

Reported-by: 杜少博 <dushaobo@360.cn>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 1ae3f2f178)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 22:37:09 -05:00
Gerd Hoffmann
44b86aa32e vga: make sure vga register setup for vbe stays intact (CVE-2016-3712).
Call vbe_update_vgaregs() when the guest touches GFX, SEQ or CRT
registers, to make sure the vga registers will always have the
values needed by vbe mode.  This makes sure the sanity checks
applied by vbe_fixup_regs() are effective.

Without this guests can muck with shift_control, can turn on planar
vga modes or text mode emulation while VBE is active, making qemu
take code paths meant for CGA compatibility, but with the very
large display widths and heigts settable using VBE registers.

Which is good for one or another buffer overflow.  Not that
critical as they typically read overflows happening somewhere
in the display code.  So guests can DoS by crashing qemu with a
segfault, but it is probably not possible to break out of the VM.

Fixes: CVE-2016-3712
Reported-by: Zuozhi Fzz <zuozhi.fzz@alibaba-inc.com>
Reported-by: P J P <ppandit@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 20:56:43 -05:00
Gerd Hoffmann
a6e5e5dd4b vga: update vga register setup on vbe changes
Call the new vbe_update_vgaregs() function on vbe configuration
changes, to make sure vga registers are up-to-date.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 20:56:40 -05:00
Gerd Hoffmann
2f2f74e87c vga: factor out vga register setup
When enabling vbe mode qemu will setup a bunch of vga registers to make
sure the vga emulation operates in correct mode for a linear
framebuffer.  Move that code to a separate function so we can call it
from other places too.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 20:56:38 -05:00
Gerd Hoffmann
46aff2c7e9 vga: add vbe_enabled() helper
Makes code a bit easier to read.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 20:56:34 -05:00
Gerd Hoffmann
4f0323d26c vga: fix banked access bounds checking (CVE-2016-3710)
vga allows banked access to video memory using the window at 0xa00000
and it supports a different access modes with different address
calculations.

The VBE bochs extentions support banked access too, using the
VBE_DISPI_INDEX_BANK register.  The code tries to take the different
address calculations into account and applies different limits to
VBE_DISPI_INDEX_BANK depending on the current access mode.

Which is probably effective in stopping misprogramming by accident.
But from a security point of view completely useless as an attacker
can easily change access modes after setting the bank register.

Drop the bogus check, add range checks to vga_mem_{readb,writeb}
instead.

Fixes: CVE-2016-3710
Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-05-08 20:56:30 -05:00
Michael Roth
a58047f7fb Update version for 2.5.1 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-29 15:47:56 -05:00
Denis V. Lunev
5f409b108f hyperv: cpu hotplug fix with HyperV enabled
With Hyper-V enabled CPU hotplug stops working. The CPU appears
in device manager on Windows but does not appear in peformance
monitor and control panel.

The root of the problem is the following. Windows checks
HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE bit in CPUID. The
presence of this bit is enough to cure the situation.

The bit should be set when CPU hotplug is allowed for HyperV VM.
The check that hot_add_cpu callback is defined is enough from the
protocol point of view. Though this callback is defined almost
always thus there is no need to export that knowledge in the
other way.

Signed-off-by: Denis V. Lunev <den@openvz.org>
Reviewed-by: Roman Kagan <rkagan@virtuozzo.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
CC: "Andreas Färber" <afaerber@suse.de>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit 4467c6c118)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 18:02:30 -05:00
Fam Zheng
078de11898 vmdk: Fix converting to streamOptimized
Commit d62d9dc4b8 lifted streamOptimized images's version to 3, but we
now refuse to open version 3 images read-write.  We need to make
streamOptimized an exception to allow converting to it. This fixes the
accidentally broken iotests case 059 for the same reason.

Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 3db1d98a20)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:41:10 -05:00
Fam Zheng
acea76c162 vmdk: Create streamOptimized as version 3
VMware products accept only version 3 for streamOptimized, let's bump
the version.

Reported-by: Radoslav Gerganov <rgerganov@vmware.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit d62d9dc4b8)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:41:04 -05:00
Prasad J Pandit
80b6e5723f usb: check USB configuration descriptor object
When processing remote NDIS control message packets, the USB Net
device emulator checks to see if the USB configuration descriptor
object is of RNDIS type(2). But it does not check if it is null,
which leads to a null dereference error. Add check to avoid it.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-id: 1455188480-14688-1-git-send-email-ppandit@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 80eecda8e5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:56 -05:00
Prasad J Pandit
9bddb45dbc usb: check RNDIS message length
When processing remote NDIS control message packets, the USB Net
device emulator uses a fixed length(4096) data buffer. The incoming
packet length could exceed this limit. Add a check to avoid it.

Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-id: 1455648821-17340-2-git-send-email-ppandit@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 64c9bc181f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:52 -05:00
Prasad J Pandit
e3a2cdfcb5 usb: check RNDIS buffer offsets & length
When processing remote NDIS control message packets,
the USB Net device emulator uses a fixed length(4096) data buffer.
The incoming informationBufferOffset & Length combination could
overflow and cross that range. Check control message buffer
offsets and length to avoid it.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-id: 1455648821-17340-3-git-send-email-ppandit@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit fe3c546c5f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:46 -05:00
Prasad J Pandit
4dcd2f13b1 usb: check page select value while processing iTD
While processing isochronous transfer descriptors(iTD), the page
select(PG) field value could lead to an OOB read access. Add
check to avoid it.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-id: 1453233406-12165-1-git-send-email-ppandit@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 49d925ce50)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:40 -05:00
Prasad J Pandit
38e09211b6 net: ne2000: fix bounds check in ioport operations
While doing ioport r/w operations, ne2000 device emulation suffers
from OOB r/w errors. Update respective array bounds check to avoid
OOB access.

Reported-by: Ling Liu <liuling-it@360.cn>
Cc: qemu-stable@nongnu.org
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit aa7f9966df)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:34 -05:00
Prasad J Pandit
d0ee85b4e4 net: check packet payload length
While computing IP checksum, 'net_checksum_calculate' reads
payload length from the packet. It could exceed the given 'data'
buffer size. Add a check to avoid it.

Reported-by: Liu Ling <liuling-it@360.cn>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 362786f14a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:27 -05:00
Prasad J Pandit
4f046a6ba1 ide: ahci: reset ncq object to unused on error
When processing NCQ commands, AHCI device emulation prepares a
NCQ transfer object; To which an aio control block(aiocb) object
is assigned in 'execute_ncq_command'. In case, when the NCQ
command is invalid, the 'aiocb' object is not assigned, and NCQ
transfer object is left as 'used'. This leads to a use after
free kind of error in 'bdrv_aio_cancel_async' via 'ahci_reset_port'.
Reset NCQ transfer object to 'unused' to avoid it.

[Maintainer edit: s/ACHI/AHCI/ in the commit message. --js]

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 1452282511-4116-1-git-send-email-ppandit@redhat.com
Signed-off-by: John Snow <jsnow@redhat.com>
(cherry picked from commit 4ab0359a8a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:40:20 -05:00
P J P
b47809c6b3 i386: avoid null pointer dereference
Hello,

A null pointer dereference issue was reported by Mr Ling Liu, CC'd here. It
occurs while doing I/O port write operations via hmp interface. In that,
'current_cpu' remains null as it is not called from cpu_exec loop, which
results in the said issue.

Below is a proposed (tested)patch to fix this issue; Does it look okay?

===
From ae88a4947fab9a148cd794f8ad2d812e7f5a1d0f Mon Sep 17 00:00:00 2001
From: Prasad J Pandit <pjp@fedoraproject.org>
Date: Fri, 18 Dec 2015 11:16:07 +0530
Subject: [PATCH] i386: avoid null pointer dereference

When I/O port write operation is called from hmp interface,
'current_cpu' remains null, as it is not called from cpu_exec()
loop. This leads to a null pointer dereference in vapic_write
routine. Add check to avoid it.

Reported-by: Ling Liu <liuling-it@360.cn>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <alpine.LFD.2.20.1512181129320.9805@wniryva>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: P J P <ppandit@redhat.com>
(cherry picked from commit 4c1396cb57)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:39:27 -05:00
Wolfgang Bumiller
24fe899c3c hmp: fix sendkey out of bounds write (CVE-2015-8619)
When processing 'sendkey' command, hmp_sendkey routine null
terminates the 'keyname_buf' array. This results in an OOB
write issue, if 'keyname_len' was to fall outside of
'keyname_buf' array.

Since the keyname's length is known the keyname_buf can be
removed altogether by adding a length parameter to
index_from_key() and using it for the error output as well.

Reported-by: Ling Liu <liuling-it@360.cn>
Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Message-Id: <20160113080958.GA18934@olga>
[Comparison with "<" dumbed down, test for junk after strtoul()
tweaked]
Signed-off-by: Markus Armbruster <armbru@redhat.com>

(cherry picked from commit 64ffbe04ea)

Conflicts:
	hmp.c

*removed dependency on 7fb1cf16

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:38:16 -05:00
John Snow
aaf4fb6afb ahci: Do not unmap NULL addresses
Definitely don't try to unmap a garbage address.

Reported-by: Zuozhi fzz <zuozhi.fzz@alibaba-inc.com>
Signed-off-by: John Snow <jsnow@redhat.com>
Message-id: 1454103689-13042-2-git-send-email-jsnow@redhat.com
(cherry picked from commit 99b4cb7106)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:35:36 -05:00
Greg Kurz
a2ae168821 migration: allow machine to enforce configuration section migration
Migration of pseries-2.3 doesn't have configuration section. Unfortunately,
QEMU 2.4/2.4.1/2.5 are buggy and always stream and expect the configuration
section, and break migration both ways.

This patch introduces a property which allows to enforce a configuration
section for machines who don't have one.

It can be set at startup:

-machine enforce-config-section=on

or later from the QEMU monitor:

qom-set /machine enforce-config-section on

It is up to the tooling to set or unset this property according to the
version of the QEMU at the other end of the pipe.

Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 902c053d83)

Conflicts:
	qemu-options.hx

* removed context dependency on 87252e1b
* added to provide 2.5<->2.5.1 migration compat option for
  pseries-2.3 machines

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-22 17:20:12 -05:00
Marcel Apfelbaum
bad094d524 vl.c: Fix regression in machine error message
Commit e1ce0c3cb (vl.c: fix regression when reading machine type
from config file) fixed the error message when the machine type
was supplied inside the config file. However now the option name
is not displayed correctly if the error happens when the machine
is specified at command line.

Running
    ./x86_64-softmmu/qemu-system-x86_64 -M q35-1.5 -redir tcp:8022::22
will result in the error message:
    qemu-system-x86_64: -redir tcp:8022::22: unsupported machine type
    Use -machine help to list supported machines

Fixed it by restoring the error location and also extracted the code
dealing with machine options into a separate function.

Reported-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <1455303747-19776-2-git-send-email-ehabkost@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 34f405ae6d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 18:21:32 -05:00
Alberto Garcia
4b0b1ec8e0 quorum: Fix crash in quorum_aio_cb()
quorum_aio_cb() emits the QUORUM_REPORT_BAD event if there's
an I/O error in a Quorum child. However sacb->aiocb must be
correctly initialized for this to happen. read_quorum_children() and
read_fifo_child() are not doing this, which results in a QEMU crash.

Signed-off-by: Alberto Garcia <berto@igalia.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Message-id: 8138570d071ba7e25db3736979234a1fd71dbd05.1457610443.git.berto@igalia.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit b9c600d207)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 18:18:19 -05:00
Peter Maydell
cab1cc7245 target-arm: Make reserved ranges in ID_AA64* spaces RAZ, not UNDEF
The v8 ARM ARM defines that unused spaces in the ID_AA64* system
register ranges are Reserved and must RAZ, rather than being UNDEF.
Implement this.

In particular, ARM v8.2 adds a new feature register ID_AA64MMFR2,
and newer versions of the Linux kernel will attempt to read this,
which causes them not to boot up on versions of QEMU missing this fix.

Since the encoding .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 6
is actually defined in ARMv8 (as ID_MMFR4), we give it an entry in
the ARMCPU struct so CPUs can override it, though since none do
this too will just RAZ.

Cc: qemu-stable@nongnu.org
Reported-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 1455890863-11203-1-git-send-email-peter.maydell@linaro.org
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Tested-by: Alex Bennée <alex.bennee@linaro.org>
(cherry picked from commit e20d84c140)

Conflicts:
	target-arm/helper.c

* remove context dep on 4054bfa9

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:48:45 -05:00
Michael S. Tsirkin
9ae02175b4 vhost-user: don't merge regions with different fds
vhost currently merges regions with contiguious virtual and physical
addresses.  This breaks for vhost-user since that also needs fds to
match.

Add a vhost_ops entry to compare the fds for vhost-user only.

Cc: qemu-stable@nongnu.org
Cc: Victor Kaplansky <victork@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit ffe42cc14c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:36:07 -05:00
Laszlo Ersek
30929793b0 fw_cfg: unbreak migration compatibility for 2.4 and earlier machines
When I reviewed Marc's fw_cfg DMA patches, I completely missed that the
way we set dma_enabled would break migration.

Gerd explained the right way (see reference below): dma_enabled should be
set to true by default, and only true->false transitions should be
possible:

- when the user requests that with

    -global fw_cfg_mem.dma_enabled=off

  or

   -global fw_cfg_io.dma_enabled=off

  as appropriate for the platform,

- when HW_COMPAT_2_4 dictates it,

- when board code initializes fw_cfg without requesting DMA support.

Cc: Marc Marí <markmb@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Alexandre DERUMIER <aderumier@odiso.com>
Cc: qemu-stable@nongnu.org
Ref: http://thread.gmane.org/gmane.comp.emulators.qemu/390272/focus=391042
Ref: https://bugs.launchpad.net/qemu/+bug/1536487
Suggested-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Message-id: 1455823860-22268-1-git-send-email-lersek@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit e6915b5f3a)

Conflicts:
	include/hw/compat.h

* remove cosmetic dep on c9c0afbb

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:33:59 -05:00
Marcel Apfelbaum
c5c9841ce8 hw/virtio: group virtio flags into an enum
Minimizes the possibility to assign
the same bit to different features.

Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit fc1769b758)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:25:13 -05:00
Marcel Apfelbaum
6b62303eb8 hw/virtio: fix double use of a virtio flag
Commits 1811e64c and a6df8adf use the same virtio feature bit 4
for different features.

Fix it by using different bits.

Reported-by: Laurent Vivier <lvivier@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 631a438755)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:24:57 -05:00
Greg Kurz
c06f342009 spapr: skip configuration section during migration of older machines
Since QEMU 2.4, we have a configuration section in the migration stream.
This must be skipped for older machines, like it is already done for x86.

This patch fixes the migration of pseries-2.3 from/to QEMU 2.3, but it
breaks migration of the same machine from/to QEMU 2.4/2.4.1/2.5. We do
that anyway because QEMU 2.3 is likely to be more widely deployed than
newer QEMU versions.

Fixes: 61964c23e5
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 09b5e30da5)

Conflicts:
	hw/ppc/spapr.c

*remove dep on 5013c5474

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 17:17:33 -05:00
Laszlo Ersek
cb873eaa6d e1000: eliminate infinite loops on out-of-bounds transfer start
The start_xmit() and e1000_receive_iov() functions implement DMA transfers
iterating over a set of descriptors that the guest's e1000 driver
prepares:

- the TDLEN and RDLEN registers store the total size of the descriptor
  area,

- while the TDH and RDH registers store the offset (in whole tx / rx
  descriptors) into the area where the transfer is supposed to start.

Each time a descriptor is processed, the TDH and RDH register is bumped
(as appropriate for the transfer direction).

QEMU already contains logic to deal with bogus transfers submitted by the
guest:

- Normally, the transmit case wants to increase TDH from its initial value
  to TDT. (TDT is allowed to be numerically smaller than the initial TDH
  value; wrapping at or above TDLEN bytes to zero is normal.) The failsafe
  that QEMU currently has here is a check against reaching the original
  TDH value again -- a complete wraparound, which should never happen.

- In the receive case RDH is increased from its initial value until
  "total_size" bytes have been received; preferably in a single step, or
  in "s->rxbuf_size" byte steps, if the latter is smaller. However, null
  RX descriptors are skipped without receiving data, while RDH is
  incremented just the same. QEMU tries to prevent an infinite loop
  (processing only null RX descriptors) by detecting whether RDH assumes
  its original value during the loop. (Again, wrapping from RDLEN to 0 is
  normal.)

What both directions miss is that the guest could program TDLEN and RDLEN
so low, and the initial TDH and RDH so high, that these registers will
immediately be truncated to zero, and then never reassume their initial
values in the loop -- a full wraparound will never occur.

The condition that expresses this is:

  xdh_start >= s->mac_reg[XDLEN] / sizeof(desc)

i.e., TDH or RDH start out after the last whole rx or tx descriptor that
fits into the TDLEN or RDLEN sized area.

This condition could be checked before we enter the loops, but
pci_dma_read() / pci_dma_write() knows how to fill in buffers safely for
bogus DMA addresses, so we just extend the existing failsafes with the
above condition.

This is CVE-2016-1981.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Petr Matousek <pmatouse@redhat.com>
Cc: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Cc: Prasad Pandit <ppandit@redhat.com>
Cc: Michael Roth <mdroth@linux.vnet.ibm.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: qemu-stable@nongnu.org
RHBZ: https://bugzilla.redhat.com/show_bug.cgi?id=1296044
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit dd793a7488)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:55:27 -05:00
Jeff Cody
4853a5a80f block: qemu-iotests - add test for snapshot, commit, snapshot bug
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 2dbc05efba2f683cb3aaf71aaa9b776ebf7ec57c.1454376655.git.jcody@redhat.com
Reviewed-by: Max Reitz <mreitz@redhat.com>
[Moved test number from 143 to 144]
Signed-off-by: Max Reitz <mreitz@redhat.com>

(cherry picked from commit 8983b670f6)

Conflicts:
	tests/qemu-iotests/group

*removed context dependencies on newer test groups

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:53:35 -05:00
Jeff Cody
a375e0b03e block: set device_list.tqe_prev to NULL on BDS removal
This fixes a regression introduced with commit 3f09bfbc7.  Multiple
bugs arise in conjunction with live snapshots and mirroring operations
(which include active layer commit).

After a live snapshot occurs, the active layer and the base layer both
have a non-NULL tqe_prev field in the device_list, although the base
node's tqe_prev field points to a NULL entry.  This non-NULL tqe_prev
field occurs after the bdrv_append() in the external snapshot calls
change_parent_backing_link().

In change_parent_backing_link(), when the previous active layer is
removed from device_list, the device_list.tqe_prev pointer is not
set to NULL.

The operating scheme in the block layer is to indicate that a BDS belongs
in the bdrv_states device_list iff the device_list.tqe_prev pointer
is non-NULL.

This patch does two things:

1.) Introduces a new block layer helper bdrv_device_remove() to remove a
    BDS from the device_list, and
2.) uses that new API, which also fixes the regression once used in
    change_parent_backing_link().

Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 0cd51e11c0666c04ddb7c05293fe94afeb551e89.1454376655.git.jcody@redhat.com
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit f8aa905a4f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:51:48 -05:00
Eric Blake
a38a283fc7 qmp: Fix reference-counting of qnull on empty output visit
Commit 6c2f9a15 ensured that we would not return NULL when the
caller used an output visitor but had nothing to visit. But
in doing so, it added a FIXME about a reference count leak
that could abort qemu in the (unlikely) case of SIZE_MAX such
visits (more plausible on 32-bit).  (Although that commit
suggested we might fix it in time for 2.5, we ran out of time;
fortunately, it is unlikely enough to bite that it was not
worth worrying about during the 2.5 release.)

This fixes things by documenting the internal contracts, and
explaining why the internal function can return NULL and only
the public facing interface needs to worry about qnull(),
thus avoiding over-referencing the qnull_ global object.

It does not, however, fix the stupidity of the stack mixing
up two separate pieces of information; add a FIXME to explain
that issue, which will be fixed shortly in a future patch.

Signed-off-by: Eric Blake <eblake@redhat.com>
Cc: qemu-stable@nongnu.org
Message-Id: <1454075341-13658-25-git-send-email-eblake@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit a861564015)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:50:34 -05:00
Dr. David Alan Gilbert
225d50fbb1 cpus: use broadcast on qemu_pause_cond
Jiri saw a hang on pause_all_vcpus called from postcopy_start,
where the cpus are all apparently stopped ('stopped' flag set)
but pause_all_vcpus is still stuck on a cond_wait on qemu_paused_cond.
We suspect this is happening if a qmp_stop is called at about the
same time as the postcopy code calls that pause_all_vcpus;
although they both should have the main lock held, Paolo spotted
the cond_wait unlocks the global lock so perhaps they both
could end up waiting at the same time?

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reported-by: Jiri Denemark <jdenemar@redhat.com>
Message-Id: <1453716498-27238-1-git-send-email-dgilbert@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 96bce6831b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:47:04 -05:00
Gabriel L. Somlo
020282d3e6 fw_cfg: avoid calculating invalid current entry pointer
When calculating a pointer to the currently selected fw_cfg item, the
following is used:

  FWCfgEntry *e = &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];

When s->cur_entry is FW_CFG_INVALID, we are calculating the address of
a non-existent element in s->entries[arch][...], which is undefined.

This patch ensures the resulting entry pointer is set to NULL whenever
s->cur_entry is FW_CFG_INVALID.

Reported-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Gabriel Somlo <somlo@cmu.edu>
Message-id: 1446733972-1602-5-git-send-email-somlo@cmu.edu
Cc: Marc Marí <markmb@redhat.com>
Signed-off-by: Gabriel Somlo <somlo@cmu.edu>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 66f8fd9dda)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:45:24 -05:00
Halil Pasic
091af18104 s390x/css: fix control flags during csch
From the beginning, css support contained an error in csch handling:
instead of setting the clear bit in the function control bits twice, we
need to set the clear pending bit in the activity control bits. Let's
fix this.

Cc: qemu-stable@nongnu.org
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Halil Pasic <pasic@linux.vnet.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 4c6bf79a22)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:42:26 -05:00
Pierre Morel
d98392379a s390x/ioinst: set type and len for SEI response
If no event information is pending, the return code
is set to 0x0005 and the length of the response is
set to 8 bytes.

Signed-off-by: Pierre Morel <pmorel@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Song Shan Gong <gongss@linux.vnet.ibm.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit f70202be53)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:42:13 -05:00
Christian Borntraeger
643c8d8ec1 block/raw-posix: avoid bogus fixup for cylinders on DASD disks
large volume DASD that have > 64k cylinders do claim to have
0xFFFE cylinders as special value in the old 16 bit field. We
want to pass this "token" along to the guest, instead of
calculating the real number. Otherwise qemu might fail with
"cyls must be between 1 and 65535"

Cc: qemu-stable@nongnu.org
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 972b543c6b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:41:43 -05:00
Gerd Hoffmann
3ede27db32 ehci: update irq on reset
After clearing the status register we also have to update the irq line
status.  Otherwise a irq which happends to be pending at reset time
causes a interrupt storm.  And the guest can't stop as the status
register doesn't indicate any pending interrupt.

Both NetBSD and FreeBSD hang on shutdown because of that.

Cc: qemu-stable@nongnu.org
Reported-by: Andrey Korolyov <andrey@xdel.ru>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1453203884-4125-1-git-send-email-kraxel@redhat.com
(cherry picked from commit 5a8660741a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:41:14 -05:00
Laurent Vivier
9849b1912f net: set endianness on all backend devices
commit 5be7d9f1b1
       vhost-net: tell tap backend about the vnet endianness

makes vhost net to set the endianness of the device, but only for
the first device.

In case of multiqueue, we have multiple devices... This patch sets the
endianness for all the devices of the interface.

Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit a407644079)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:36:19 -05:00
Prasad J Pandit
fe90bdc25b net: ne2000: check ring buffer control registers
Ne2000 NIC uses ring buffer of NE2000_MEM_SIZE(49152)
bytes to process network packets. Registers PSTART & PSTOP
define ring buffer size & location. Setting these registers
to invalid values could lead to infinite loop or OOB r/w
access issues. Add check to avoid it.

Reported-by: Yang Hongke <yanghongke@huawei.com>
Tested-by: Yang Hongke <yanghongke@huawei.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 415ab35a44)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:34:56 -05:00
Li Zhijian
aaa5271327 net/filter: fix nf->netdev_id leak
Cc: Jason Wang <jasowang@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 671f66f87f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:34:23 -05:00
Li Zhijian
abda95cb01 net/dump: fix nfds->filename leak
Cc: Jason Wang <jasowang@redhat.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit b50c7d452f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:34:15 -05:00
Max Reitz
6a49a71cc6 blockdev: Fix 'change' for slot devices
'change' and related operations did not work when used on guest devices
featuring removable media but no actual tray, because
blk_dev_is_tray_open() always returned false for them and the
blockdev-{insert,remove}-medium commands required it to return true.

Fix this by making blockdev-{insert,remove}-medium work on tray-less
devices. Also, blockdev-{open,close}-tray are now explicitly no-ops when
invoked on such devices, and blk_dev_change_media_cb() is instead
called by blockdev-{insert,remove}-medium (for tray-less devices only).

Reported-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable <qemu-stable@nongnu.org>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Alberto Garcia <berto@igalia.com>
Message-id: 1454096953-31773-3-git-send-email-mreitz@redhat.com
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit 12c7ec87a7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:23:54 -05:00
Max Reitz
e1a8a09124 block: Add blk_dev_has_tray()
Pull out the check whether a block device has a tray from
blk_dev_is_tray_open() into its own function so both attributes (whether
there is a tray vs. whether that tray is open) can be queried
independently.

Cc: qemu-stable <qemu-stable@nongnu.org>
Signed-off-by: Max Reitz <mreitz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Alberto Garcia <berto@igalia.com>
Message-id: 1454096953-31773-2-git-send-email-mreitz@redhat.com
(cherry picked from commit 8f3a73bc57)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-17 16:23:28 -05:00
Prasad J Pandit
7a2c1c8e66 net: rocker: fix an incorrect array bounds check
While processing transmit(tx) descriptors in 'tx_consume' routine
the switch emulator suffers from an off-by-one error, if a
descriptor was to have more than allowed(ROCKER_TX_FRAGS_MAX=16)
fragments. Fix an incorrect bounds check to avoid it.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 007cd223de)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:39:32 -05:00
Marc-André Lureau
702a8d165c ivshmem: remove redundant assignment, fix crash with msi=off
Fix crash when msi=false introduced in 660c97ee (msi_vectors is NULL in
this case)

Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 47213eb110)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:35:51 -05:00
Marc-André Lureau
3e96d5dcf2 ivshmem: no need for opaque argument
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 2c64846972)
*context dependency for 47213eb
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:35:25 -05:00
P J P
16a2875735 scsi: initialise info object with appropriate size
While processing controller 'CTRL_GET_INFO' command, the routine
'megasas_ctrl_get_info' overflows the '&info' object size. Use its
appropriate size to null initialise it.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Message-Id: <alpine.LFD.2.20.1512211501420.22471@wniryva>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: P J P <ppandit@redhat.com>
(cherry picked from commit 36fef36b91)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:21:11 -05:00
Greg Kurz
4588b0d856 virtio-9p: use accessor to get thread_pool
The aio_context_new() function does not allocate a thread pool. This is
deferred to the first call to the aio_get_thread_pool() accessor. It is
hence forbidden to access the thread_pool field directly, as it may be
NULL. The accessor *must* be used always.

Fixes: ebac1202c9
Reviewed-by: Michael Tokarev <mjt@tls.msk.ru>
Tested-by: Michael Tokarev <mjt@tls.msk.ru>
Cc: qemu-stable@nongnu.org
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
(cherry picked from commit 4b3a4f2d45)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:20:55 -05:00
Stefano Stabellini
ff083d3c3b xenfb: avoid reading twice the same fields from the shared page
Reading twice the same field could give the guest an attack of
opportunity. In the case of event->type, gcc could compile the switch
statement into a jump table, effectively ending up reading the type
field multiple times.

This is part of XSA-155.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
(cherry picked from commit 7ea11bf376)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:20:35 -05:00
Stefano Stabellini
4d59e78dfe xen/blkif: Avoid double access to src->nr_segments
src is stored in shared memory and src->nr_segments is dereferenced
twice at the end of the function.  If a compiler decides to compile this
into two separate memory accesses then the size limitation could be
bypassed.

Fix it by removing the double access to src->nr_segments.

This is part of XSA-155.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
(cherry picked from commit f9e98e5d7a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:20:17 -05:00
Peter Maydell
52a7b27947 configure: Fix shell syntax to placate OpenBSD's pdksh
Unfortunately the OpenBSD pdksh does not like brackets inside
the right part of a ${variable+word} parameter expansion:

  $ echo "${a+($b)}"
  ksh: ${a+($b)}": bad substitution

though both bash and dash accept them. In any case this line
was causing odd output in the case where nettle is not present:
  nettle    no ()

(because if nettle is not present then $nettle will be "no",
not a null string or unset).

Rewrite it to just use an if.

This bug was originally introduced in becaeb726 and was present
in the 2.4.0 release.

Fixes: https://bugs.launchpad.net/qemu/+bug/1525682
Reported-by: Dmitrij D. Czarkoff
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 1450105357-8516-1-git-send-email-peter.maydell@linaro.org
(cherry picked from commit 18f49881cf)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:19:47 -05:00
Greg Kurz
d4aed70099 target-ppc: kvm: fix floating point registers sync on little-endian hosts
On VSX capable CPUs, the 32 FP registers are mapped to the high-bits
of the 32 first VSX registers. So if you have:

VSR31 = (uint128) 0x0102030405060708090a0b0c0d0e0f00

then

FPR31 = (uint64) 0x0102030405060708

The kernel stores the VSX registers in the fp_state struct following the
host endian element ordering.

On big-endian:

fp_state.fpr[31][0] = 0x0102030405060708
fp_state.fpr[31][1] = 0x090a0b0c0d0e0f00

On little-endian:

fp_state.fpr[31][0] = 0x090a0b0c0d0e0f00
fp_state.fpr[31][1] = 0x0102030405060708

The KVM_GET_ONE_REG and KVM_SET_ONE_REG ioctls preserve this ordering, but
QEMU considers it as big-endian and always copies element [0] to the
fpr[] array and element [1] to the vsr[] array. This does not work with
little-endian hosts, and you will get:

(qemu) p $f31
0x90a0b0c0d0e0f00

instead of:

(qemu) p $f31
0x102030405060708

This patch fixes the element ordering for little-endian hosts.

Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 3a4b791b4c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:10:47 -05:00
P J P
42ae4a3c61 net: vmxnet3: avoid memory leakage in activate_device
Vmxnet3 device emulator does not check if the device is active
before activating it, also it did not free the transmit & receive
buffers while deactivating the device, thus resulting in memory
leakage on the host. This patch fixes both these issues to avoid
host memory leakage.

Reported-by: Qinghao Tang <luodalongde@gmail.com>
Reviewed-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit aa4a3dce1c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:08:24 -05:00
Gerd Hoffmann
0d335804e3 ehci: make idt processing more robust
Make ehci_process_itd return an error in case we didn't do any actual
iso transfer because we've found no active transaction.  That'll avoid
ehci happily run in circles forever if the guest builds a loop out of
idts.

This is CVE-2015-8558.

Cc: qemu-stable@nongnu.org
Reported-by: Qinghao Tang <luodalongde@gmail.com>
Tested-by: P J P <ppandit@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 156a2e4dbf)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2016-03-15 12:07:11 -05:00
2226 changed files with 46311 additions and 91206 deletions

View File

@@ -1,38 +1,9 @@
sudo: false
language: c
python:
- "2.4"
compiler:
- gcc
- clang
cache: ccache
addons:
apt:
packages:
- libaio-dev
- libattr1-dev
- libbrlapi-dev
- libcap-ng-dev
- libgnutls-dev
- libgtk-3-dev
- libiscsi-dev
- liblttng-ust-dev
- libncurses5-dev
- libnss3-dev
- libpixman-1-dev
- libpng12-dev
- librados-dev
- libsdl1.2-dev
- libseccomp-dev
- libspice-protocol-dev
- libspice-server-dev
- libssh2-1-dev
- liburcu-dev
- libusb-1.0-0-dev
- libvte-2.90-dev
- sparse
- uuid-dev
notifications:
irc:
channels:
@@ -41,16 +12,29 @@ notifications:
on_failure: always
env:
global:
- TEST_CMD="make check"
- TEST_CMD=""
- EXTRA_CONFIG=""
# Development packages, EXTRA_PKGS saved for additional builds
- CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
- NET_PKGS="libseccomp-dev libgnutls-dev libssh2-1-dev libspice-server-dev libspice-protocol-dev libnss3-dev"
- GUI_PKGS="libgtk-3-dev libvte-2.90-dev libsdl1.2-dev libpng12-dev libpixman-1-dev"
- EXTRA_PKGS=""
matrix:
# Group major targets together with their linux-user counterparts
- TARGETS=alpha-softmmu,alpha-linux-user,cris-softmmu,cris-linux-user,m68k-softmmu,m68k-linux-user,microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
- TARGETS=alpha-softmmu,alpha-linux-user
- TARGETS=arm-softmmu,arm-linux-user,armeb-linux-user,aarch64-softmmu,aarch64-linux-user
- TARGETS=cris-softmmu,cris-linux-user
- TARGETS=i386-softmmu,i386-linux-user,x86_64-softmmu,x86_64-linux-user
- TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu,mips-linux-user,mips64-linux-user,mips64el-linux-user,mipsel-linux-user,mipsn32-linux-user,mipsn32el-linux-user
- TARGETS=or32-softmmu,or32-linux-user,ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,ppc-linux-user,ppc64-linux-user,ppc64abi32-linux-user,ppc64le-linux-user
- TARGETS=s390x-softmmu,s390x-linux-user,sh4-softmmu,sh4eb-softmmu,sh4-linux-user,sh4eb-linux-user,sparc-softmmu,sparc64-softmmu,sparc-linux-user,sparc32plus-linux-user,sparc64-linux-user,unicore32-softmmu,unicore32-linux-user
- TARGETS=m68k-softmmu,m68k-linux-user
- TARGETS=microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
- TARGETS=mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu
- TARGETS=mips-linux-user,mips64-linux-user,mips64el-linux-user,mipsel-linux-user,mipsn32-linux-user,mipsn32el-linux-user
- TARGETS=or32-softmmu,or32-linux-user
- TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,ppc-linux-user,ppc64-linux-user,ppc64abi32-linux-user,ppc64le-linux-user
- TARGETS=s390x-softmmu,s390x-linux-user
- TARGETS=sh4-softmmu,sh4eb-softmmu,sh4-linux-user sh4eb-linux-user
- TARGETS=sparc-softmmu,sparc64-softmmu,sparc-linux-user,sparc32plus-linux-user,sparc64-linux-user
- TARGETS=unicore32-softmmu,unicore32-linux-user
# Group remaining softmmu only targets into one build
- TARGETS=lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
git:
@@ -59,6 +43,8 @@ git:
before_install:
- wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
- git submodule update --init --recursive
- sudo apt-get update -qq
- sudo apt-get install -qq ${CORE_PKGS} ${NET_PKGS} ${GUI_PKGS} ${EXTRA_PKGS}
before_script:
- ./configure --target-list=${TARGETS} --enable-debug-tcg ${EXTRA_CONFIG}
script:
@@ -66,59 +52,44 @@ script:
matrix:
# We manually include a number of additional build for non-standard bits
include:
# Make check target (we only do this once)
- env:
- TARGETS=alpha-softmmu,arm-softmmu,aarch64-softmmu,cris-softmmu,i386-softmmu,x86_64-softmmu,m68k-softmmu,microblaze-softmmu,microblazeel-softmmu,mips-softmmu,mips64-softmmu,mips64el-softmmu,mipsel-softmmu,or32-softmmu,ppc-softmmu,ppc64-softmmu,ppcemb-softmmu,s390x-softmmu,sh4-softmmu,sh4eb-softmmu,sparc-softmmu,sparc64-softmmu,unicore32-softmmu,unicore32-linux-user,lm32-softmmu,moxie-softmmu,tricore-softmmu,xtensa-softmmu,xtensaeb-softmmu
TEST_CMD="make check"
compiler: gcc
# Debug related options
- env: TARGETS=x86_64-softmmu
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-debug"
compiler: gcc
# We currently disable "make check"
- env: TARGETS=alpha-softmmu
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-debug --enable-tcg-interpreter"
TEST_CMD=""
compiler: gcc
# Disable a few of the optional features
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--disable-linux-aio --disable-cap-ng --disable-attr --disable-brlapi --disable-uuid --disable-libusb"
# All the extra -dev packages
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_PKGS="libaio-dev libcap-ng-dev libattr1-dev libbrlapi-dev uuid-dev libusb-1.0.0-dev"
compiler: gcc
# Currently configure doesn't force --disable-pie
- env: TARGETS=x86_64-softmmu
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-gprof --enable-gcov --disable-pie"
compiler: gcc
# Sparse
- env: TARGETS=x86_64-softmmu
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_PKGS="sparse"
EXTRA_CONFIG="--enable-sparse"
compiler: gcc
# Modules
- env: TARGETS=arm-softmmu,x86_64-softmmu
# All the trace backends (apart from dtrace)
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=stderr"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=simple"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=ftrace"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
EXTRA_CONFIG="--enable-trace-backends=ust"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-modules"
compiler: gcc
# All the trace backends (apart from dtrace)
- env: TARGETS=i386-softmmu
EXTRA_CONFIG="--enable-trace-backends=log"
compiler: gcc
# We currently disable "make check" (until 41fc57e44ed regression fixed)
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=simple"
TEST_CMD=""
compiler: gcc
# We currently disable "make check"
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=ftrace"
TEST_CMD=""
compiler: gcc
# We currently disable "make check"
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=ust"
TEST_CMD=""
compiler: gcc
# All the co-routine backends (apart from windows)
# We currently disable "make check"
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--with-coroutine=gthread"
TEST_CMD=""
compiler: gcc
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--with-coroutine=ucontext"
compiler: gcc
- env: TARGETS=x86_64-softmmu
EXTRA_CONFIG="--with-coroutine=sigaltstack"
compiler: gcc

55
HACKING
View File

@@ -157,58 +157,3 @@ painful. These are:
* you may assume that integers are 2s complement representation
* you may assume that right shift of a signed integer duplicates
the sign bit (ie it is an arithmetic shift, not a logical shift)
7. Error handling and reporting
7.1 Reporting errors to the human user
Do not use printf(), fprintf() or monitor_printf(). Instead, use
error_report() or error_vreport() from error-report.h. This ensures the
error is reported in the right place (current monitor or stderr), and in
a uniform format.
Use error_printf() & friends to print additional information.
error_report() prints the current location. In certain common cases
like command line parsing, the current location is tracked
automatically. To manipulate it manually, use the loc_*() from
error-report.h.
7.2 Propagating errors
An error can't always be reported to the user right where it's detected,
but often needs to be propagated up the call chain to a place that can
handle it. This can be done in various ways.
The most flexible one is Error objects. See error.h for usage
information.
Use the simplest suitable method to communicate success / failure to
callers. Stick to common methods: non-negative on success / -1 on
error, non-negative / -errno, non-null / null, or Error objects.
Example: when a function returns a non-null pointer on success, and it
can fail only in one way (as far as the caller is concerned), returning
null on failure is just fine, and certainly simpler and a lot easier on
the eyes than propagating an Error object through an Error ** parameter.
Example: when a function's callers need to report details on failure
only the function really knows, use Error **, and set suitable errors.
Do not report an error to the user when you're also returning an error
for somebody else to handle. Leave the reporting to the place that
consumes the error returned.
7.3 Handling errors
Calling exit() is fine when handling configuration errors during
startup. It's problematic during normal operation. In particular,
monitor commands should never exit().
Do not call exit() or abort() to handle an error that can be triggered
by the guest (e.g., some unimplemented corner case in guest code
translation or device emulation). Guests should not be able to
terminate QEMU.
Note that &error_fatal is just another way to exit(1), and &error_abort
is just another way to abort().

View File

@@ -52,11 +52,6 @@ General Project Administration
------------------------------
M: Peter Maydell <peter.maydell@linaro.org>
All patches CC here
L: qemu-devel@nongnu.org
F: *
F: */
Responsible Disclosure, Reporting Security Issues
------------------------------
W: http://wiki.qemu.org/SecurityProcess
@@ -84,13 +79,6 @@ F: include/exec/exec-all.h
F: include/exec/helper*.h
F: include/exec/tb-hash.h
FPU emulation
M: Aurelien Jarno <aurelien@aurel32.net>
M: Peter Maydell <peter.maydell@linaro.org>
S: Odd Fixes
F: fpu/
F: include/fpu/
Alpha
M: Richard Henderson <rth@twiddle.net>
S: Maintained
@@ -234,7 +222,6 @@ L: kvm@vger.kernel.org
S: Supported
F: kvm-*
F: */kvm.*
F: include/sysemu/kvm*.h
ARM
M: Peter Maydell <peter.maydell@linaro.org>
@@ -286,12 +273,9 @@ F: */xen*
F: hw/char/xen_console.c
F: hw/display/xenfb.c
F: hw/net/xen_nic.c
F: hw/block/xen_*
F: hw/xen/
F: hw/xenpv/
F: hw/i386/xen/
F: include/hw/xen/
F: include/sysemu/xen-mapcache.h
Hosts:
------
@@ -364,7 +348,6 @@ M: Dmitry Solodkiy <d.solodkiy@samsung.com>
L: qemu-arm@nongnu.org
S: Maintained
F: hw/*/exynos*
F: include/hw/arm/exynos4210.h
Calxeda Highbank
M: Rob Herring <robh@kernel.org>
@@ -392,7 +375,6 @@ L: qemu-arm@nongnu.org
S: Odd fixes
F: hw/*/imx*
F: hw/arm/kzm.c
F: include/hw/arm/fsl-imx31.h
Integrator CP
M: Peter Maydell <peter.maydell@linaro.org>
@@ -435,7 +417,6 @@ F: hw/arm/spitz.c
F: hw/arm/tosa.c
F: hw/arm/z2.c
F: hw/*/pxa2xx*
F: include/hw/arm/pxa.h
Stellaris
M: Peter Maydell <peter.maydell@linaro.org>
@@ -606,7 +587,7 @@ F: hw/ppc/prep.c
F: hw/pci-host/prep.[hc]
F: hw/isa/pc87312.[hc]
sPAPR
sPAPR (pseries)
M: David Gibson <david@gibson.dropbear.id.au>
M: Alexander Graf <agraf@suse.de>
L: qemu-ppc@nongnu.org
@@ -657,6 +638,12 @@ F: hw/*/grlib*
S390 Machines
-------------
S390 Virtio
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: hw/s390x/s390-*.c
X: hw/s390x/*pci*.[hc]
S390 Virtio-ccw
M: Cornelia Huck <cornelia.huck@de.ibm.com>
M: Christian Borntraeger <borntraeger@de.ibm.com>
@@ -664,6 +651,7 @@ M: Alexander Graf <agraf@suse.de>
S: Supported
F: hw/char/sclp*.[hc]
F: hw/s390x/
X: hw/s390x/s390-virtio-bus.[ch]
F: include/hw/s390x/
F: pc-bios/s390-ccw/
F: hw/watchdog/wdt_diag288.c
@@ -717,12 +705,6 @@ F: hw/timer/hpet*
F: hw/timer/i8254*
F: hw/timer/mc146818rtc*
Machine core
M: Eduardo Habkost <ehabkost@redhat.com>
M: Marcel Apfelbaum <marcel@redhat.com>
S: Supported
F: hw/core/machine.c
F: include/hw/boards.h
Xtensa Machines
---------------
@@ -771,7 +753,6 @@ OMAP
M: Peter Maydell <peter.maydell@linaro.org>
S: Maintained
F: hw/*/omap*
F: include/hw/arm/omap.h
IPack
M: Alberto Garcia <berto@igalia.com>
@@ -857,10 +838,6 @@ M: Gerd Hoffmann <kraxel@redhat.com>
S: Maintained
F: hw/usb/*
F: tests/usb-*-test.c
F: docs/usb2.txt
F: docs/usb-storage.txt
F: include/hw/usb.h
F: include/hw/usb/
USB (serial adapter)
M: Gerd Hoffmann <kraxel@redhat.com>
@@ -872,7 +849,6 @@ VFIO
M: Alex Williamson <alex.williamson@redhat.com>
S: Supported
F: hw/vfio/*
F: include/hw/vfio/
vhost
M: Michael S. Tsirkin <mst@redhat.com>
@@ -884,7 +860,6 @@ M: Michael S. Tsirkin <mst@redhat.com>
S: Supported
F: hw/*/virtio*
F: net/vhost-user.c
F: include/hw/virtio/
virtio-9p
M: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
@@ -930,7 +905,6 @@ M: Amit Shah <amit.shah@redhat.com>
S: Supported
F: hw/virtio/virtio-rng.c
F: include/hw/virtio/virtio-rng.h
F: include/sysemu/rng*.h
F: backends/rng*.c
nvme
@@ -967,13 +941,6 @@ M: Jiri Pirko <jiri@resnulli.us>
S: Maintained
F: hw/net/rocker/
NVDIMM
M: Xiao Guangrong <guangrong.xiao@linux.intel.com>
S: Maintained
F: hw/acpi/nvdimm.c
F: hw/mem/nvdimm.c
F: include/hw/mem/nvdimm.h
Subsystems
----------
Audio
@@ -1062,8 +1029,7 @@ Device Tree
M: Peter Crosthwaite <crosthwaite.peter@gmail.com>
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: device_tree.c
F: include/sysemu/device_tree.h
F: device_tree.[ch]
Error reporting
M: Markus Armbruster <armbru@redhat.com>
@@ -1094,7 +1060,6 @@ SPICE
M: Gerd Hoffmann <kraxel@redhat.com>
S: Supported
F: include/ui/qemu-spice.h
F: include/ui/spice-display.h
F: ui/spice-*.c
F: audio/spiceaudio.c
F: hw/display/qxl*
@@ -1103,7 +1068,6 @@ Graphics
M: Gerd Hoffmann <kraxel@redhat.com>
S: Odd Fixes
F: ui/
F: include/ui/
Cocoa graphics
M: Andreas Färber <andreas.faerber@web.de>
@@ -1131,7 +1095,6 @@ Network device backends
M: Jason Wang <jasowang@redhat.com>
S: Maintained
F: net/
F: include/net/
T: git git://github.com/jasowang/qemu.git net
Netmap network backend
@@ -1145,9 +1108,8 @@ F: net/netmap.c
Network Block Device (NBD)
M: Paolo Bonzini <pbonzini@redhat.com>
S: Odd Fixes
F: block/nbd*
F: nbd/
F: include/block/nbd*
F: block/nbd.c
F: nbd.*
F: qemu-nbd.c
T: git git://github.com/bonzini/qemu.git nbd-next
@@ -1227,12 +1189,9 @@ F: scripts/qmp/
T: git git://repo.or.cz/qemu/armbru.git qapi-next
SLIRP
M: Samuel Thibault <samuel.thibault@ens-lyon.org>
M: Jan Kiszka <jan.kiszka@siemens.com>
S: Maintained
F: slirp/
F: net/slirp.c
F: include/net/slirp.h
T: git git://git.kiszka.org/qemu.git queues/slirp
Tracing
@@ -1257,7 +1216,6 @@ F: include/migration/
F: migration/
F: scripts/vmstate-static-checker.py
F: tests/vmstate-static-checker-data/
F: docs/migration.txt
Seccomp
M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
@@ -1285,30 +1243,6 @@ S: Odd fixes
F: util/buffer.c
F: include/qemu/buffer.h
I/O Channels
M: Daniel P. Berrange <berrange@redhat.com>
S: Maintained
F: io/
F: include/io/
F: tests/test-io-*
Sockets
M: Daniel P. Berrange <berrange@redhat.com>
M: Gerd Hoffmann <kraxel@redhat.com>
M: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: include/qemu/sockets.h
F: util/qemu-sockets.c
Throttling infrastructure
M: Alberto Garcia <berto@igalia.com>
S: Supported
F: block/throttle-groups.c
F: include/block/throttle-groups.h
F: include/qemu/throttle.h
F: util/throttle.c
L: qemu-block@nongnu.org
Usermode Emulation
------------------
Overall
@@ -1549,7 +1483,6 @@ M: Denis V. Lunev <den@openvz.org>
L: qemu-block@nongnu.org
S: Supported
F: block/parallels.c
F: docs/specs/parallels.txt
qed
M: Stefan Hajnoczi <stefanha@redhat.com>
@@ -1604,12 +1537,6 @@ L: qemu-block@nongnu.org
S: Supported
F: tests/image-fuzzer/
Build and test automation
-------------------------
M: Alex Bennée <alex.bennee@linaro.org>
L: qemu-devel@nongnu.org
S: Supported
F: .travis.yml
Documentation
-------------

View File

@@ -159,7 +159,6 @@ dummy := $(call unnest-vars,, \
crypto-obj-y \
crypto-aes-obj-y \
qom-obj-y \
io-obj-y \
common-obj-y \
common-obj-m)
@@ -179,7 +178,6 @@ SOFTMMU_SUBDIR_RULES=$(filter %-softmmu,$(SUBDIR_RULES))
$(SOFTMMU_SUBDIR_RULES): $(block-obj-y)
$(SOFTMMU_SUBDIR_RULES): $(crypto-obj-y)
$(SOFTMMU_SUBDIR_RULES): $(io-obj-y)
$(SOFTMMU_SUBDIR_RULES): config-all-devices.mak
subdir-%:
@@ -234,13 +232,13 @@ util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
qemu-img.o: qemu-img-cmds.h
qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o libqemuutil.a libqemustub.a
qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/9p-marshal.o fsdev/9p-iov-marshal.o libqemuutil.a libqemustub.a
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/virtio-9p-marshal.o libqemuutil.a libqemustub.a
fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx
@@ -271,9 +269,7 @@ $(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
qapi-modules = $(SRC_PATH)/qapi-schema.json $(SRC_PATH)/qapi/common.json \
$(SRC_PATH)/qapi/block.json $(SRC_PATH)/qapi/block-core.json \
$(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json \
$(SRC_PATH)/qapi/crypto.json $(SRC_PATH)/qapi/rocker.json \
$(SRC_PATH)/qapi/trace.json
$(SRC_PATH)/qapi/event.json $(SRC_PATH)/qapi/introspect.json
qapi-types.c qapi-types.h :\
$(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
@@ -329,7 +325,7 @@ ifneq ($(EXESUF),)
qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI)
endif
ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) libqemuutil.a libqemustub.a
ivshmem-client$(EXESUF): $(ivshmem-client-obj-y)
$(call LINK, $^)
ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) libqemuutil.a libqemustub.a
$(call LINK, $^)
@@ -391,7 +387,7 @@ bepo cz
ifdef INSTALL_BLOBS
BLOBS=bios.bin bios-256k.bin sgabios.bin vgabios.bin vgabios-cirrus.bin \
vgabios-stdvga.bin vgabios-vmware.bin vgabios-qxl.bin vgabios-virtio.bin \
acpi-dsdt.aml \
acpi-dsdt.aml q35-acpi-dsdt.aml \
ppc_rom.bin openbios-sparc32 openbios-sparc64 openbios-ppc QEMU,tcx.bin QEMU,cgthree.bin \
pxe-e1000.rom pxe-eepro100.rom pxe-ne2k_pci.rom \
pxe-pcnet.rom pxe-rtl8139.rom pxe-virtio.rom \
@@ -400,6 +396,7 @@ efi-pcnet.rom efi-rtl8139.rom efi-virtio.rom \
qemu-icon.bmp qemu_logo_no_text.svg \
bamboo.dtb petalogix-s3adsp1800.dtb petalogix-ml605.dtb \
multiboot.bin linuxboot.bin kvmvapic.bin \
s390-zipl.rom \
s390-ccw.img \
spapr-rtas.bin slof.bin \
palcode-clipper \

View File

@@ -8,8 +8,7 @@ util-obj-y += qmp-introspect.o qapi-types.o qapi-visit.o qapi-event.o
# block-obj-y is code used by both qemu system emulation and qemu-img
block-obj-y = async.o thread-pool.o
block-obj-y += nbd/
block-obj-y += block.o blockjob.o
block-obj-y += nbd.o block.o blockjob.o
block-obj-y += main-loop.o iohandler.o qemu-timer.o
block-obj-$(CONFIG_POSIX) += aio-posix.o
block-obj-$(CONFIG_WIN32) += aio-win32.o
@@ -29,11 +28,6 @@ crypto-aes-obj-y = crypto/
qom-obj-y = qom/
#######################################################################
# io-obj-y is code used by both qemu system emulation and qemu-img
io-obj-y = io/
######################################################################
# Target independent part of system emulation. The long term path is to
# suppress *all* target specific code in case of system emulation, i.e. a
@@ -89,6 +83,7 @@ endif
#######################################################################
# Target-independent parts used in system and user emulation
common-obj-y += qemu-log.o
common-obj-y += tcg-runtime.o
common-obj-y += hw/
common-obj-y += qom/

View File

@@ -176,7 +176,6 @@ dummy := $(call unnest-vars,.., \
crypto-obj-y \
crypto-aes-obj-y \
qom-obj-y \
io-obj-y \
common-obj-y \
common-obj-m)
target-obj-y := $(target-obj-y-save)
@@ -186,7 +185,6 @@ all-obj-y += $(qom-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
all-obj-$(CONFIG_USER_ONLY) += $(crypto-aes-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)
$(QEMU_PROG_BUILD): config-devices.mak

View File

@@ -1 +1 @@
2.5.50
2.5.1.1

View File

@@ -23,7 +23,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "sysemu/accel.h"
#include "hw/boards.h"
#include "qemu-common.h"

View File

@@ -13,7 +13,6 @@
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/queue.h"

View File

@@ -15,7 +15,6 @@
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/queue.h"

View File

@@ -21,7 +21,7 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <stdint.h>
#include "sysemu/sysemu.h"
#include "sysemu/arch_init.h"
#include "hw/pci/pci.h"
@@ -258,7 +258,9 @@ void do_acpitable_option(const QemuOpts *opts)
acpi_table_add(opts, &err);
if (err) {
error_reportf_err(err, "Wrong acpi table provided: ");
error_report("Wrong acpi table provided: %s",
error_get_pretty(err));
error_free(err);
exit(1);
}
#endif

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/aio.h"
#include "block/thread-pool.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <alsa/asoundlib.h>
#include "qemu-common.h"
#include "qemu/main-loop.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "hw/hw.h"
#include "audio.h"
#include "monitor/monitor.h"
@@ -1807,6 +1806,9 @@ static void audio_init (void)
atexit (audio_atexit);
s->ts = timer_new_ns(QEMU_CLOCK_VIRTUAL, audio_timer, s);
if (!s->ts) {
hw_error("Could not create audio timer\n");
}
audio_process_options ("AUDIO", audio_options);
@@ -1857,8 +1859,12 @@ static void audio_init (void)
if (!done) {
done = !audio_driver_init (s, &no_audio_driver);
assert(done);
dolog("warning: Using timer based audio emulation\n");
if (!done) {
hw_error("Could not initialize audio subsystem\n");
}
else {
dolog ("warning: Using timer based audio emulation\n");
}
}
if (conf.period.hertz <= 0) {

View File

@@ -24,6 +24,7 @@
#ifndef QEMU_AUDIO_H
#define QEMU_AUDIO_H
#include "config-host.h"
#include "qemu/queue.h"
typedef void (*audio_callback_fn) (void *opaque, int avail);

View File

@@ -1,4 +1,3 @@
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "audio.h"

View File

@@ -1,6 +1,5 @@
/* public domain */
#include "qemu/osdep.h"
#include "qemu-common.h"
#define AUDIO_CAP "win-int"

View File

@@ -22,8 +22,8 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <CoreAudio/CoreAudio.h>
#include <string.h> /* strerror */
#include <pthread.h> /* pthread_X */
#include "qemu-common.h"
@@ -32,10 +32,6 @@
#define AUDIO_CAP "coreaudio"
#include "audio_int.h"
#ifndef MAC_OS_X_VERSION_10_6
#define MAC_OS_X_VERSION_10_6 1060
#endif
static int isAtexit;
typedef struct {
@@ -49,233 +45,11 @@ typedef struct coreaudioVoiceOut {
AudioDeviceID outputDeviceID;
UInt32 audioDevicePropertyBufferFrameSize;
AudioStreamBasicDescription outputStreamBasicDescription;
AudioDeviceIOProcID ioprocid;
int live;
int decr;
int rpos;
} coreaudioVoiceOut;
#if MAC_OS_X_VERSION_MAX_ALLOWED >= MAC_OS_X_VERSION_10_6
/* The APIs used here only become available from 10.6 */
static OSStatus coreaudio_get_voice(AudioDeviceID *id)
{
UInt32 size = sizeof(*id);
AudioObjectPropertyAddress addr = {
kAudioHardwarePropertyDefaultOutputDevice,
kAudioObjectPropertyScopeGlobal,
kAudioObjectPropertyElementMaster
};
return AudioObjectGetPropertyData(kAudioObjectSystemObject,
&addr,
0,
NULL,
&size,
id);
}
static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
AudioValueRange *framerange)
{
UInt32 size = sizeof(*framerange);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyBufferFrameSizeRange,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectGetPropertyData(id,
&addr,
0,
NULL,
&size,
framerange);
}
static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
{
UInt32 size = sizeof(*framesize);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyBufferFrameSize,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectGetPropertyData(id,
&addr,
0,
NULL,
&size,
framesize);
}
static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
{
UInt32 size = sizeof(*framesize);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyBufferFrameSize,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectSetPropertyData(id,
&addr,
0,
NULL,
size,
framesize);
}
static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
AudioStreamBasicDescription *d)
{
UInt32 size = sizeof(*d);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyStreamFormat,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectGetPropertyData(id,
&addr,
0,
NULL,
&size,
d);
}
static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
AudioStreamBasicDescription *d)
{
UInt32 size = sizeof(*d);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyStreamFormat,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectSetPropertyData(id,
&addr,
0,
NULL,
size,
d);
}
static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
{
UInt32 size = sizeof(*result);
AudioObjectPropertyAddress addr = {
kAudioDevicePropertyDeviceIsRunning,
kAudioDevicePropertyScopeOutput,
kAudioObjectPropertyElementMaster
};
return AudioObjectGetPropertyData(id,
&addr,
0,
NULL,
&size,
result);
}
#else
/* Legacy versions of functions using deprecated APIs */
static OSStatus coreaudio_get_voice(AudioDeviceID *id)
{
UInt32 size = sizeof(*id);
return AudioHardwareGetProperty(
kAudioHardwarePropertyDefaultOutputDevice,
&size,
id);
}
static OSStatus coreaudio_get_framesizerange(AudioDeviceID id,
AudioValueRange *framerange)
{
UInt32 size = sizeof(*framerange);
return AudioDeviceGetProperty(
id,
0,
0,
kAudioDevicePropertyBufferFrameSizeRange,
&size,
framerange);
}
static OSStatus coreaudio_get_framesize(AudioDeviceID id, UInt32 *framesize)
{
UInt32 size = sizeof(*framesize);
return AudioDeviceGetProperty(
id,
0,
false,
kAudioDevicePropertyBufferFrameSize,
&size,
framesize);
}
static OSStatus coreaudio_set_framesize(AudioDeviceID id, UInt32 *framesize)
{
UInt32 size = sizeof(*framesize);
return AudioDeviceSetProperty(
id,
NULL,
0,
false,
kAudioDevicePropertyBufferFrameSize,
size,
framesize);
}
static OSStatus coreaudio_get_streamformat(AudioDeviceID id,
AudioStreamBasicDescription *d)
{
UInt32 size = sizeof(*d);
return AudioDeviceGetProperty(
id,
0,
false,
kAudioDevicePropertyStreamFormat,
&size,
d);
}
static OSStatus coreaudio_set_streamformat(AudioDeviceID id,
AudioStreamBasicDescription *d)
{
UInt32 size = sizeof(*d);
return AudioDeviceSetProperty(
id,
0,
0,
0,
kAudioDevicePropertyStreamFormat,
size,
d);
}
static OSStatus coreaudio_get_isrunning(AudioDeviceID id, UInt32 *result)
{
UInt32 size = sizeof(*result);
return AudioDeviceGetProperty(
id,
0,
0,
kAudioDevicePropertyDeviceIsRunning,
&size,
result);
}
#endif
static void coreaudio_logstatus (OSStatus status)
{
const char *str = "BUG";
@@ -370,7 +144,10 @@ static inline UInt32 isPlaying (AudioDeviceID outputDeviceID)
{
OSStatus status;
UInt32 result = 0;
status = coreaudio_get_isrunning(outputDeviceID, &result);
UInt32 propertySize = sizeof(outputDeviceID);
status = AudioDeviceGetProperty(
outputDeviceID, 0, 0,
kAudioDevicePropertyDeviceIsRunning, &propertySize, &result);
if (status != kAudioHardwareNoError) {
coreaudio_logerr(status,
"Could not determine whether Device is playing\n");
@@ -511,6 +288,7 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
{
OSStatus status;
coreaudioVoiceOut *core = (coreaudioVoiceOut *) hw;
UInt32 propertySize;
int err;
const char *typ = "playback";
AudioValueRange frameRange;
@@ -525,7 +303,12 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
audio_pcm_init_info (&hw->info, as);
status = coreaudio_get_voice(&core->outputDeviceID);
/* open default output device */
propertySize = sizeof(core->outputDeviceID);
status = AudioHardwareGetProperty(
kAudioHardwarePropertyDefaultOutputDevice,
&propertySize,
&core->outputDeviceID);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ,
"Could not get default output Device\n");
@@ -537,8 +320,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
}
/* get minimum and maximum buffer frame sizes */
status = coreaudio_get_framesizerange(core->outputDeviceID,
&frameRange);
propertySize = sizeof(frameRange);
status = AudioDeviceGetProperty(
core->outputDeviceID,
0,
0,
kAudioDevicePropertyBufferFrameSizeRange,
&propertySize,
&frameRange);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ,
"Could not get device buffer frame range\n");
@@ -558,8 +347,15 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
}
/* set Buffer Frame Size */
status = coreaudio_set_framesize(core->outputDeviceID,
&core->audioDevicePropertyBufferFrameSize);
propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
status = AudioDeviceSetProperty(
core->outputDeviceID,
NULL,
0,
false,
kAudioDevicePropertyBufferFrameSize,
propertySize,
&core->audioDevicePropertyBufferFrameSize);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ,
"Could not set device buffer frame size %" PRIu32 "\n",
@@ -568,8 +364,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
}
/* get Buffer Frame Size */
status = coreaudio_get_framesize(core->outputDeviceID,
&core->audioDevicePropertyBufferFrameSize);
propertySize = sizeof(core->audioDevicePropertyBufferFrameSize);
status = AudioDeviceGetProperty(
core->outputDeviceID,
0,
false,
kAudioDevicePropertyBufferFrameSize,
&propertySize,
&core->audioDevicePropertyBufferFrameSize);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ,
"Could not get device buffer frame size\n");
@@ -578,8 +380,14 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
hw->samples = conf->nbuffers * core->audioDevicePropertyBufferFrameSize;
/* get StreamFormat */
status = coreaudio_get_streamformat(core->outputDeviceID,
&core->outputStreamBasicDescription);
propertySize = sizeof(core->outputStreamBasicDescription);
status = AudioDeviceGetProperty(
core->outputDeviceID,
0,
false,
kAudioDevicePropertyStreamFormat,
&propertySize,
&core->outputStreamBasicDescription);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ,
"Could not get Device Stream properties\n");
@@ -589,8 +397,15 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
/* set Samplerate */
core->outputStreamBasicDescription.mSampleRate = (Float64) as->freq;
status = coreaudio_set_streamformat(core->outputDeviceID,
&core->outputStreamBasicDescription);
propertySize = sizeof(core->outputStreamBasicDescription);
status = AudioDeviceSetProperty(
core->outputDeviceID,
0,
0,
0,
kAudioDevicePropertyStreamFormat,
propertySize,
&core->outputStreamBasicDescription);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ, "Could not set samplerate %d\n",
as->freq);
@@ -599,12 +414,8 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
}
/* set Callback */
core->ioprocid = NULL;
status = AudioDeviceCreateIOProcID(core->outputDeviceID,
audioDeviceIOProc,
hw,
&core->ioprocid);
if (status != kAudioHardwareNoError || core->ioprocid == NULL) {
status = AudioDeviceAddIOProc(core->outputDeviceID, audioDeviceIOProc, hw);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ, "Could not set IOProc\n");
core->outputDeviceID = kAudioDeviceUnknown;
return -1;
@@ -612,10 +423,10 @@ static int coreaudio_init_out(HWVoiceOut *hw, struct audsettings *as,
/* start Playback */
if (!isPlaying(core->outputDeviceID)) {
status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
if (status != kAudioHardwareNoError) {
coreaudio_logerr2 (status, typ, "Could not start playback\n");
AudioDeviceDestroyIOProcID(core->outputDeviceID, core->ioprocid);
AudioDeviceRemoveIOProc(core->outputDeviceID, audioDeviceIOProc);
core->outputDeviceID = kAudioDeviceUnknown;
return -1;
}
@@ -633,15 +444,15 @@ static void coreaudio_fini_out (HWVoiceOut *hw)
if (!isAtexit) {
/* stop playback */
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID, core->ioprocid);
status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not stop playback\n");
}
}
/* remove callback */
status = AudioDeviceDestroyIOProcID(core->outputDeviceID,
core->ioprocid);
status = AudioDeviceRemoveIOProc(core->outputDeviceID,
audioDeviceIOProc);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not remove IOProc\n");
}
@@ -664,7 +475,7 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
case VOICE_ENABLE:
/* start playback */
if (!isPlaying(core->outputDeviceID)) {
status = AudioDeviceStart(core->outputDeviceID, core->ioprocid);
status = AudioDeviceStart(core->outputDeviceID, audioDeviceIOProc);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not resume playback\n");
}
@@ -675,8 +486,7 @@ static int coreaudio_ctl_out (HWVoiceOut *hw, int cmd, ...)
/* stop playback */
if (!isAtexit) {
if (isPlaying(core->outputDeviceID)) {
status = AudioDeviceStop(core->outputDeviceID,
core->ioprocid);
status = AudioDeviceStop(core->outputDeviceID, audioDeviceIOProc);
if (status != kAudioHardwareNoError) {
coreaudio_logerr (status, "Could not pause playback\n");
}

View File

@@ -26,7 +26,6 @@
* SEAL 1.07 by Carlos 'pel' Hasan was used as documentation
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "audio.h"

View File

@@ -22,7 +22,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "audio.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "audio.h"
#include "qemu/timer.h"

View File

@@ -21,8 +21,9 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <stdlib.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/ioctl.h>
#include <sys/soundcard.h>
#include "qemu-common.h"

View File

@@ -1,5 +1,4 @@
/* public domain */
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "audio.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <SDL.h>
#include <SDL_thread.h>
#include "qemu-common.h"

View File

@@ -17,7 +17,6 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "hw/hw.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "hw/hw.h"
#include "qemu/timer.h"
#include "audio.h"

View File

@@ -1,4 +1,3 @@
#include "qemu/osdep.h"
#include "hw/hw.h"
#include "monitor/monitor.h"
#include "qemu/error-report.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#include "qemu/timer.h"
@@ -567,7 +566,6 @@ static CharDriverState *chr_baum_init(const char *id,
ChardevReturn *ret,
Error **errp)
{
ChardevCommon *common = backend->u.braille;
BaumDriverState *baum;
CharDriverState *chr;
brlapi_handle_t *handle;
@@ -578,12 +576,8 @@ static CharDriverState *chr_baum_init(const char *id,
#endif
int tty;
chr = qemu_chr_alloc(common, errp);
if (!chr) {
return NULL;
}
baum = g_malloc0(sizeof(BaumDriverState));
baum->chr = chr;
baum->chr = chr = qemu_chr_alloc();
chr->opaque = baum;
chr->chr_write = baum_write;

View File

@@ -9,7 +9,6 @@
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/hostmem.h"
#include "sysemu/sysemu.h"

View File

@@ -9,7 +9,6 @@
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/hostmem.h"
#include "qom/object_interfaces.h"

View File

@@ -9,7 +9,6 @@
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/hostmem.h"
#include "hw/boards.h"
#include "qapi/visitor.h"
@@ -27,18 +26,18 @@ QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
#endif
static void
host_memory_backend_get_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
host_memory_backend_get_size(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint64_t value = backend->size;
visit_type_size(v, name, &value, errp);
visit_type_size(v, &value, name, errp);
}
static void
host_memory_backend_set_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
host_memory_backend_set_size(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
Error *local_err = NULL;
@@ -49,7 +48,7 @@ host_memory_backend_set_size(Object *obj, Visitor *v, const char *name,
goto out;
}
visit_type_size(v, name, &value, &local_err);
visit_type_size(v, &value, name, &local_err);
if (local_err) {
goto out;
}
@@ -64,8 +63,8 @@ out:
}
static void
host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
host_memory_backend_get_host_nodes(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint16List *host_nodes = NULL;
@@ -92,18 +91,18 @@ host_memory_backend_get_host_nodes(Object *obj, Visitor *v, const char *name,
node = &(*node)->next;
} while (true);
visit_type_uint16List(v, name, &host_nodes, errp);
visit_type_uint16List(v, &host_nodes, name, errp);
}
static void
host_memory_backend_set_host_nodes(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
host_memory_backend_set_host_nodes(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
#ifdef CONFIG_NUMA
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
uint16List *l = NULL;
visit_type_uint16List(v, name, &l, errp);
visit_type_uint16List(v, &l, name, errp);
while (l) {
bitmap_set(backend->host_nodes, l->value, 1);

View File

@@ -21,7 +21,7 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <stdlib.h>
#include "qemu-common.h"
#include "sysemu/char.h"
#include "ui/console.h"
@@ -68,13 +68,9 @@ static CharDriverState *qemu_chr_open_msmouse(const char *id,
ChardevReturn *ret,
Error **errp)
{
ChardevCommon *common = backend->u.msmouse;
CharDriverState *chr;
chr = qemu_chr_alloc(common, errp);
if (!chr) {
return NULL;
}
chr = qemu_chr_alloc();
chr->chr_write = msmouse_chr_write;
chr->chr_close = msmouse_chr_close;
chr->explicit_be_open = true;

View File

@@ -10,7 +10,6 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/rng.h"
#include "sysemu/char.h"
#include "qapi/qmp/qerror.h"
@@ -25,12 +24,33 @@ typedef struct RngEgd
CharDriverState *chr;
char *chr_name;
GSList *requests;
} RngEgd;
static void rng_egd_request_entropy(RngBackend *b, RngRequest *req)
typedef struct RngRequest
{
EntropyReceiveFunc *receive_entropy;
uint8_t *data;
void *opaque;
size_t offset;
size_t size;
} RngRequest;
static void rng_egd_request_entropy(RngBackend *b, size_t size,
EntropyReceiveFunc *receive_entropy,
void *opaque)
{
RngEgd *s = RNG_EGD(b);
size_t size = req->size;
RngRequest *req;
req = g_malloc(sizeof(*req));
req->offset = 0;
req->size = size;
req->receive_entropy = receive_entropy;
req->opaque = opaque;
req->data = g_malloc(req->size);
while (size > 0) {
uint8_t header[2];
@@ -44,15 +64,24 @@ static void rng_egd_request_entropy(RngBackend *b, RngRequest *req)
size -= len;
}
s->requests = g_slist_append(s->requests, req);
}
static void rng_egd_free_request(RngRequest *req)
{
g_free(req->data);
g_free(req);
}
static int rng_egd_chr_can_read(void *opaque)
{
RngEgd *s = RNG_EGD(opaque);
RngRequest *req;
GSList *i;
int size = 0;
QSIMPLEQ_FOREACH(req, &s->parent.requests, next) {
for (i = s->requests; i; i = i->next) {
RngRequest *req = i->data;
size += req->size - req->offset;
}
@@ -64,8 +93,8 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
RngEgd *s = RNG_EGD(opaque);
size_t buf_offset = 0;
while (size > 0 && !QSIMPLEQ_EMPTY(&s->parent.requests)) {
RngRequest *req = QSIMPLEQ_FIRST(&s->parent.requests);
while (size > 0 && s->requests) {
RngRequest *req = s->requests->data;
int len = MIN(size, req->size - req->offset);
memcpy(req->data + req->offset, buf + buf_offset, len);
@@ -74,13 +103,38 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
size -= len;
if (req->offset == req->size) {
s->requests = g_slist_remove_link(s->requests, s->requests);
req->receive_entropy(req->opaque, req->data, req->size);
rng_backend_finalize_request(&s->parent, req);
rng_egd_free_request(req);
}
}
}
static void rng_egd_free_requests(RngEgd *s)
{
GSList *i;
for (i = s->requests; i; i = i->next) {
rng_egd_free_request(i->data);
}
g_slist_free(s->requests);
s->requests = NULL;
}
static void rng_egd_cancel_requests(RngBackend *b)
{
RngEgd *s = RNG_EGD(b);
/* We simply delete the list of pending requests. If there is data in the
* queue waiting to be read, this is okay, because there will always be
* more data than we requested originally
*/
rng_egd_free_requests(s);
}
static void rng_egd_opened(RngBackend *b, Error **errp)
{
RngEgd *s = RNG_EGD(b);
@@ -149,6 +203,8 @@ static void rng_egd_finalize(Object *obj)
}
g_free(s->chr_name);
rng_egd_free_requests(s);
}
static void rng_egd_class_init(ObjectClass *klass, void *data)
@@ -156,6 +212,7 @@ static void rng_egd_class_init(ObjectClass *klass, void *data)
RngBackendClass *rbc = RNG_BACKEND_CLASS(klass);
rbc->request_entropy = rng_egd_request_entropy;
rbc->cancel_requests = rng_egd_cancel_requests;
rbc->opened = rng_egd_opened;
}

View File

@@ -10,7 +10,6 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/rng-random.h"
#include "sysemu/rng.h"
#include "qapi/qmp/qerror.h"
@@ -22,6 +21,10 @@ struct RndRandom
int fd;
char *filename;
EntropyReceiveFunc *receive_func;
void *opaque;
size_t size;
};
/**
@@ -34,35 +37,36 @@ struct RndRandom
static void entropy_available(void *opaque)
{
RndRandom *s = RNG_RANDOM(opaque);
uint8_t buffer[s->size];
ssize_t len;
while (!QSIMPLEQ_EMPTY(&s->parent.requests)) {
RngRequest *req = QSIMPLEQ_FIRST(&s->parent.requests);
ssize_t len;
len = read(s->fd, req->data, req->size);
if (len < 0 && errno == EAGAIN) {
return;
}
g_assert(len != -1);
req->receive_entropy(req->opaque, req->data, len);
rng_backend_finalize_request(&s->parent, req);
len = read(s->fd, buffer, s->size);
if (len < 0 && errno == EAGAIN) {
return;
}
g_assert(len != -1);
s->receive_func(s->opaque, buffer, len);
s->receive_func = NULL;
/* We've drained all requests, the fd handler can be reset. */
qemu_set_fd_handler(s->fd, NULL, NULL, NULL);
}
static void rng_random_request_entropy(RngBackend *b, RngRequest *req)
static void rng_random_request_entropy(RngBackend *b, size_t size,
EntropyReceiveFunc *receive_entropy,
void *opaque)
{
RndRandom *s = RNG_RANDOM(b);
if (QSIMPLEQ_EMPTY(&s->parent.requests)) {
/* If there are no pending requests yet, we need to
* install our fd handler. */
qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
if (s->receive_func) {
s->receive_func(s->opaque, NULL, 0);
}
s->receive_func = receive_entropy;
s->opaque = opaque;
s->size = size;
qemu_set_fd_handler(s->fd, entropy_available, NULL, s);
}
static void rng_random_opened(RngBackend *b, Error **errp)

View File

@@ -10,7 +10,6 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/rng.h"
#include "qapi/qmp/qerror.h"
#include "qom/object_interfaces.h"
@@ -20,20 +19,18 @@ void rng_backend_request_entropy(RngBackend *s, size_t size,
void *opaque)
{
RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
RngRequest *req;
if (k->request_entropy) {
req = g_malloc(sizeof(*req));
k->request_entropy(s, size, receive_entropy, opaque);
}
}
req->offset = 0;
req->size = size;
req->receive_entropy = receive_entropy;
req->opaque = opaque;
req->data = g_malloc(req->size);
void rng_backend_cancel_requests(RngBackend *s)
{
RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
k->request_entropy(s, req);
QSIMPLEQ_INSERT_TAIL(&s->requests, req, next);
if (k->cancel_requests) {
k->cancel_requests(s);
}
}
@@ -75,48 +72,14 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
s->opened = true;
}
static void rng_backend_free_request(RngRequest *req)
{
g_free(req->data);
g_free(req);
}
static void rng_backend_free_requests(RngBackend *s)
{
RngRequest *req, *next;
QSIMPLEQ_FOREACH_SAFE(req, &s->requests, next, next) {
rng_backend_free_request(req);
}
QSIMPLEQ_INIT(&s->requests);
}
void rng_backend_finalize_request(RngBackend *s, RngRequest *req)
{
QSIMPLEQ_REMOVE(&s->requests, req, RngRequest, next);
rng_backend_free_request(req);
}
static void rng_backend_init(Object *obj)
{
RngBackend *s = RNG_BACKEND(obj);
QSIMPLEQ_INIT(&s->requests);
object_property_add_bool(obj, "opened",
rng_backend_prop_get_opened,
rng_backend_prop_set_opened,
NULL);
}
static void rng_backend_finalize(Object *obj)
{
RngBackend *s = RNG_BACKEND(obj);
rng_backend_free_requests(s);
}
static void rng_backend_class_init(ObjectClass *oc, void *data)
{
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
@@ -129,7 +92,6 @@ static const TypeInfo rng_backend_info = {
.parent = TYPE_OBJECT,
.instance_size = sizeof(RngBackend),
.instance_init = rng_backend_init,
.instance_finalize = rng_backend_finalize,
.class_size = sizeof(RngBackendClass),
.class_init = rng_backend_class_init,
.abstract = true,

View File

@@ -23,7 +23,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/char.h"

View File

@@ -12,7 +12,6 @@
* Based on backends/rng.c by Anthony Liguori
*/
#include "qemu/osdep.h"
#include "sysemu/tpm_backend.h"
#include "qapi/qmp/qerror.h"
#include "sysemu/tpm.h"

View File

@@ -24,7 +24,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "exec/cpu-common.h"
#include "sysemu/kvm.h"

972
block.c

File diff suppressed because it is too large Load Diff

View File

@@ -20,7 +20,7 @@ block-obj-$(CONFIG_RBD) += rbd.o
block-obj-$(CONFIG_GLUSTERFS) += gluster.o
block-obj-$(CONFIG_ARCHIPELAGO) += archipelago.o
block-obj-$(CONFIG_LIBSSH2) += ssh.o
block-obj-y += accounting.o dirty-bitmap.o
block-obj-y += accounting.o
block-obj-y += write-threshold.o
common-obj-y += stream.o

View File

@@ -23,7 +23,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/accounting.h"
#include "block/block_int.h"
#include "qemu/timer.h"

View File

@@ -50,7 +50,6 @@
*
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/error-report.h"
@@ -60,6 +59,7 @@
#include "qapi/qmp/qjson.h"
#include "qemu/atomic.h"
#include <inttypes.h>
#include <xseg/xseg.h>
#include <xseg/protocol.h>

View File

@@ -11,7 +11,9 @@
*
*/
#include "qemu/osdep.h"
#include <stdio.h>
#include <errno.h>
#include <unistd.h>
#include "trace.h"
#include "block/block.h"
@@ -20,9 +22,11 @@
#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
#include "sysemu/block-backend.h"
#include "qemu/bitmap.h"
#define BACKUP_CLUSTER_SIZE_DEFAULT (1 << 16)
#define BACKUP_CLUSTER_BITS 16
#define BACKUP_CLUSTER_SIZE (1 << BACKUP_CLUSTER_BITS)
#define BACKUP_SECTORS_PER_CLUSTER (BACKUP_CLUSTER_SIZE / BDRV_SECTOR_SIZE)
#define SLICE_TIME 100000000ULL /* ns */
typedef struct CowRequest {
@@ -43,17 +47,10 @@ typedef struct BackupBlockJob {
BlockdevOnError on_target_error;
CoRwlock flush_rwlock;
uint64_t sectors_read;
unsigned long *done_bitmap;
int64_t cluster_size;
HBitmap *bitmap;
QLIST_HEAD(, CowRequest) inflight_reqs;
} BackupBlockJob;
/* Size of a cluster in sectors, instead of bytes. */
static inline int64_t cluster_size_sectors(BackupBlockJob *job)
{
return job->cluster_size / BDRV_SECTOR_SIZE;
}
/* See if in-flight requests overlap and wait for them to complete */
static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
int64_t start,
@@ -102,14 +99,13 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
QEMUIOVector bounce_qiov;
void *bounce_buffer = NULL;
int ret = 0;
int64_t sectors_per_cluster = cluster_size_sectors(job);
int64_t start, end;
int n;
qemu_co_rwlock_rdlock(&job->flush_rwlock);
start = sector_num / sectors_per_cluster;
end = DIV_ROUND_UP(sector_num + nb_sectors, sectors_per_cluster);
start = sector_num / BACKUP_SECTORS_PER_CLUSTER;
end = DIV_ROUND_UP(sector_num + nb_sectors, BACKUP_SECTORS_PER_CLUSTER);
trace_backup_do_cow_enter(job, start, sector_num, nb_sectors);
@@ -117,19 +113,19 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
cow_request_begin(&cow_request, job, start, end);
for (; start < end; start++) {
if (test_bit(start, job->done_bitmap)) {
if (hbitmap_get(job->bitmap, start)) {
trace_backup_do_cow_skip(job, start);
continue; /* already copied */
}
trace_backup_do_cow_process(job, start);
n = MIN(sectors_per_cluster,
n = MIN(BACKUP_SECTORS_PER_CLUSTER,
job->common.len / BDRV_SECTOR_SIZE -
start * sectors_per_cluster);
start * BACKUP_SECTORS_PER_CLUSTER);
if (!bounce_buffer) {
bounce_buffer = qemu_blockalign(bs, job->cluster_size);
bounce_buffer = qemu_blockalign(bs, BACKUP_CLUSTER_SIZE);
}
iov.iov_base = bounce_buffer;
iov.iov_len = n * BDRV_SECTOR_SIZE;
@@ -137,10 +133,10 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
if (is_write_notifier) {
ret = bdrv_co_readv_no_serialising(bs,
start * sectors_per_cluster,
start * BACKUP_SECTORS_PER_CLUSTER,
n, &bounce_qiov);
} else {
ret = bdrv_co_readv(bs, start * sectors_per_cluster, n,
ret = bdrv_co_readv(bs, start * BACKUP_SECTORS_PER_CLUSTER, n,
&bounce_qiov);
}
if (ret < 0) {
@@ -153,11 +149,11 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
if (buffer_is_zero(iov.iov_base, iov.iov_len)) {
ret = bdrv_co_write_zeroes(job->target,
start * sectors_per_cluster,
start * BACKUP_SECTORS_PER_CLUSTER,
n, BDRV_REQ_MAY_UNMAP);
} else {
ret = bdrv_co_writev(job->target,
start * sectors_per_cluster, n,
start * BACKUP_SECTORS_PER_CLUSTER, n,
&bounce_qiov);
}
if (ret < 0) {
@@ -168,7 +164,7 @@ static int coroutine_fn backup_do_cow(BlockDriverState *bs,
goto out;
}
set_bit(start, job->done_bitmap);
hbitmap_set(job->bitmap, start, 1);
/* Publish progress, guest I/O counts as progress too. Note that the
* offset field is an opaque progress value, it is not a disk offset.
@@ -328,22 +324,21 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
int64_t cluster;
int64_t end;
int64_t last_cluster = -1;
int64_t sectors_per_cluster = cluster_size_sectors(job);
BlockDriverState *bs = job->common.bs;
HBitmapIter hbi;
granularity = bdrv_dirty_bitmap_granularity(job->sync_bitmap);
clusters_per_iter = MAX((granularity / job->cluster_size), 1);
clusters_per_iter = MAX((granularity / BACKUP_CLUSTER_SIZE), 1);
bdrv_dirty_iter_init(job->sync_bitmap, &hbi);
/* Find the next dirty sector(s) */
while ((sector = hbitmap_iter_next(&hbi)) != -1) {
cluster = sector / sectors_per_cluster;
cluster = sector / BACKUP_SECTORS_PER_CLUSTER;
/* Fake progress updates for any clusters we skipped */
if (cluster != last_cluster + 1) {
job->common.offset += ((cluster - last_cluster - 1) *
job->cluster_size);
BACKUP_CLUSTER_SIZE);
}
for (end = cluster + clusters_per_iter; cluster < end; cluster++) {
@@ -351,8 +346,8 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
if (yield_and_check(job)) {
return ret;
}
ret = backup_do_cow(bs, cluster * sectors_per_cluster,
sectors_per_cluster, &error_is_read,
ret = backup_do_cow(bs, cluster * BACKUP_SECTORS_PER_CLUSTER,
BACKUP_SECTORS_PER_CLUSTER, &error_is_read,
false);
if ((ret < 0) &&
backup_error_action(job, error_is_read, -ret) ==
@@ -364,17 +359,17 @@ static int coroutine_fn backup_run_incremental(BackupBlockJob *job)
/* If the bitmap granularity is smaller than the backup granularity,
* we need to advance the iterator pointer to the next cluster. */
if (granularity < job->cluster_size) {
bdrv_set_dirty_iter(&hbi, cluster * sectors_per_cluster);
if (granularity < BACKUP_CLUSTER_SIZE) {
bdrv_set_dirty_iter(&hbi, cluster * BACKUP_SECTORS_PER_CLUSTER);
}
last_cluster = cluster - 1;
}
/* Play some final catchup with the progress meter */
end = DIV_ROUND_UP(job->common.len, job->cluster_size);
end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
if (last_cluster + 1 < end) {
job->common.offset += ((end - last_cluster - 1) * job->cluster_size);
job->common.offset += ((end - last_cluster - 1) * BACKUP_CLUSTER_SIZE);
}
return ret;
@@ -391,16 +386,15 @@ static void coroutine_fn backup_run(void *opaque)
.notify = backup_before_write_notify,
};
int64_t start, end;
int64_t sectors_per_cluster = cluster_size_sectors(job);
int ret = 0;
QLIST_INIT(&job->inflight_reqs);
qemu_co_rwlock_init(&job->flush_rwlock);
start = 0;
end = DIV_ROUND_UP(job->common.len, job->cluster_size);
end = DIV_ROUND_UP(job->common.len, BACKUP_CLUSTER_SIZE);
job->done_bitmap = bitmap_new(end);
job->bitmap = hbitmap_alloc(end, 0);
bdrv_set_enable_write_cache(target, true);
if (target->blk) {
@@ -435,7 +429,7 @@ static void coroutine_fn backup_run(void *opaque)
/* Check to see if these blocks are already in the
* backing file. */
for (i = 0; i < sectors_per_cluster;) {
for (i = 0; i < BACKUP_SECTORS_PER_CLUSTER;) {
/* bdrv_is_allocated() only returns true/false based
* on the first set of sectors it comes across that
* are are all in the same state.
@@ -444,8 +438,8 @@ static void coroutine_fn backup_run(void *opaque)
* needed but at some point that is always the case. */
alloced =
bdrv_is_allocated(bs,
start * sectors_per_cluster + i,
sectors_per_cluster - i, &n);
start * BACKUP_SECTORS_PER_CLUSTER + i,
BACKUP_SECTORS_PER_CLUSTER - i, &n);
i += n;
if (alloced == 1 || n == 0) {
@@ -460,8 +454,8 @@ static void coroutine_fn backup_run(void *opaque)
}
}
/* FULL sync mode we copy the whole drive. */
ret = backup_do_cow(bs, start * sectors_per_cluster,
sectors_per_cluster, &error_is_read, false);
ret = backup_do_cow(bs, start * BACKUP_SECTORS_PER_CLUSTER,
BACKUP_SECTORS_PER_CLUSTER, &error_is_read, false);
if (ret < 0) {
/* Depending on error action, fail now or retry cluster */
BlockErrorAction action =
@@ -481,7 +475,7 @@ static void coroutine_fn backup_run(void *opaque)
/* wait until pending backup_do_cow() calls have completed */
qemu_co_rwlock_wrlock(&job->flush_rwlock);
qemu_co_rwlock_unlock(&job->flush_rwlock);
g_free(job->done_bitmap);
hbitmap_free(job->bitmap);
if (target->blk) {
blk_iostatus_disable(target->blk);
@@ -502,8 +496,6 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
BlockJobTxn *txn, Error **errp)
{
int64_t len;
BlockDriverInfo bdi;
int ret;
assert(bs);
assert(target);
@@ -573,32 +565,14 @@ void backup_start(BlockDriverState *bs, BlockDriverState *target,
goto error;
}
bdrv_op_block_all(target, job->common.blocker);
job->on_source_error = on_source_error;
job->on_target_error = on_target_error;
job->target = target;
job->sync_mode = sync_mode;
job->sync_bitmap = sync_mode == MIRROR_SYNC_MODE_INCREMENTAL ?
sync_bitmap : NULL;
/* If there is no backing file on the target, we cannot rely on COW if our
* backup cluster size is smaller than the target cluster size. Even for
* targets with a backing file, try to avoid COW if possible. */
ret = bdrv_get_info(job->target, &bdi);
if (ret < 0 && !target->backing) {
error_setg_errno(errp, -ret,
"Couldn't determine the cluster size of the target image, "
"which has no backing file");
error_append_hint(errp,
"Aborting, since this may create an unusable destination image\n");
goto error;
} else if (ret < 0 && target->backing) {
/* Not fatal; just trudge on ahead. */
job->cluster_size = BACKUP_CLUSTER_SIZE_DEFAULT;
} else {
job->cluster_size = MAX(BACKUP_CLUSTER_SIZE_DEFAULT, bdi.cluster_size);
}
bdrv_op_block_all(target, job->common.blocker);
job->common.len = len;
job->common.co = qemu_coroutine_create(backup_run);
block_job_txn_add_job(txn, &job->common);

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/config-file.h"
#include "block/block_int.h"
@@ -37,7 +36,7 @@ typedef struct BDRVBlkdebugState {
int state;
int new_state;
QLIST_HEAD(, BlkdebugRule) rules[BLKDBG__MAX];
QLIST_HEAD(, BlkdebugRule) rules[BLKDBG_EVENT_MAX];
QSIMPLEQ_HEAD(, BlkdebugRule) active_rules;
QLIST_HEAD(, BlkdebugSuspendedReq) suspended_reqs;
} BDRVBlkdebugState;
@@ -65,7 +64,7 @@ enum {
};
typedef struct BlkdebugRule {
BlkdebugEvent event;
BlkDebugEvent event;
int action;
int state;
union {
@@ -144,12 +143,69 @@ static QemuOptsList *config_groups[] = {
NULL
};
static int get_event_by_name(const char *name, BlkdebugEvent *event)
static const char *event_names[BLKDBG_EVENT_MAX] = {
[BLKDBG_L1_UPDATE] = "l1_update",
[BLKDBG_L1_GROW_ALLOC_TABLE] = "l1_grow.alloc_table",
[BLKDBG_L1_GROW_WRITE_TABLE] = "l1_grow.write_table",
[BLKDBG_L1_GROW_ACTIVATE_TABLE] = "l1_grow.activate_table",
[BLKDBG_L2_LOAD] = "l2_load",
[BLKDBG_L2_UPDATE] = "l2_update",
[BLKDBG_L2_UPDATE_COMPRESSED] = "l2_update_compressed",
[BLKDBG_L2_ALLOC_COW_READ] = "l2_alloc.cow_read",
[BLKDBG_L2_ALLOC_WRITE] = "l2_alloc.write",
[BLKDBG_READ_AIO] = "read_aio",
[BLKDBG_READ_BACKING_AIO] = "read_backing_aio",
[BLKDBG_READ_COMPRESSED] = "read_compressed",
[BLKDBG_WRITE_AIO] = "write_aio",
[BLKDBG_WRITE_COMPRESSED] = "write_compressed",
[BLKDBG_VMSTATE_LOAD] = "vmstate_load",
[BLKDBG_VMSTATE_SAVE] = "vmstate_save",
[BLKDBG_COW_READ] = "cow_read",
[BLKDBG_COW_WRITE] = "cow_write",
[BLKDBG_REFTABLE_LOAD] = "reftable_load",
[BLKDBG_REFTABLE_GROW] = "reftable_grow",
[BLKDBG_REFTABLE_UPDATE] = "reftable_update",
[BLKDBG_REFBLOCK_LOAD] = "refblock_load",
[BLKDBG_REFBLOCK_UPDATE] = "refblock_update",
[BLKDBG_REFBLOCK_UPDATE_PART] = "refblock_update_part",
[BLKDBG_REFBLOCK_ALLOC] = "refblock_alloc",
[BLKDBG_REFBLOCK_ALLOC_HOOKUP] = "refblock_alloc.hookup",
[BLKDBG_REFBLOCK_ALLOC_WRITE] = "refblock_alloc.write",
[BLKDBG_REFBLOCK_ALLOC_WRITE_BLOCKS] = "refblock_alloc.write_blocks",
[BLKDBG_REFBLOCK_ALLOC_WRITE_TABLE] = "refblock_alloc.write_table",
[BLKDBG_REFBLOCK_ALLOC_SWITCH_TABLE] = "refblock_alloc.switch_table",
[BLKDBG_CLUSTER_ALLOC] = "cluster_alloc",
[BLKDBG_CLUSTER_ALLOC_BYTES] = "cluster_alloc_bytes",
[BLKDBG_CLUSTER_FREE] = "cluster_free",
[BLKDBG_FLUSH_TO_OS] = "flush_to_os",
[BLKDBG_FLUSH_TO_DISK] = "flush_to_disk",
[BLKDBG_PWRITEV_RMW_HEAD] = "pwritev_rmw.head",
[BLKDBG_PWRITEV_RMW_AFTER_HEAD] = "pwritev_rmw.after_head",
[BLKDBG_PWRITEV_RMW_TAIL] = "pwritev_rmw.tail",
[BLKDBG_PWRITEV_RMW_AFTER_TAIL] = "pwritev_rmw.after_tail",
[BLKDBG_PWRITEV] = "pwritev",
[BLKDBG_PWRITEV_ZERO] = "pwritev_zero",
[BLKDBG_PWRITEV_DONE] = "pwritev_done",
[BLKDBG_EMPTY_IMAGE_PREPARE] = "empty_image_prepare",
};
static int get_event_by_name(const char *name, BlkDebugEvent *event)
{
int i;
for (i = 0; i < BLKDBG__MAX; i++) {
if (!strcmp(BlkdebugEvent_lookup[i], name)) {
for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
if (!strcmp(event_names[i], name)) {
*event = i;
return 0;
}
@@ -168,7 +224,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
struct add_rule_data *d = opaque;
BDRVBlkdebugState *s = d->s;
const char* event_name;
BlkdebugEvent event;
BlkDebugEvent event;
struct BlkdebugRule *rule;
/* Find the right event for the rule */
@@ -508,7 +564,7 @@ static void blkdebug_close(BlockDriverState *bs)
BlkdebugRule *rule, *next;
int i;
for (i = 0; i < BLKDBG__MAX; i++) {
for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
remove_rule(rule);
}
@@ -571,13 +627,13 @@ static bool process_rule(BlockDriverState *bs, struct BlkdebugRule *rule,
return injected;
}
static void blkdebug_debug_event(BlockDriverState *bs, BlkdebugEvent event)
static void blkdebug_debug_event(BlockDriverState *bs, BlkDebugEvent event)
{
BDRVBlkdebugState *s = bs->opaque;
struct BlkdebugRule *rule, *next;
bool injected;
assert((int)event >= 0 && event < BLKDBG__MAX);
assert((int)event >= 0 && event < BLKDBG_EVENT_MAX);
injected = false;
s->new_state = s->state;
@@ -592,7 +648,7 @@ static int blkdebug_debug_breakpoint(BlockDriverState *bs, const char *event,
{
BDRVBlkdebugState *s = bs->opaque;
struct BlkdebugRule *rule;
BlkdebugEvent blkdebug_event;
BlkDebugEvent blkdebug_event;
if (get_event_by_name(event, &blkdebug_event) < 0) {
return -ENOENT;
@@ -634,7 +690,7 @@ static int blkdebug_debug_remove_breakpoint(BlockDriverState *bs,
BlkdebugRule *rule, *next;
int i, ret = -ENOENT;
for (i = 0; i < BLKDBG__MAX; i++) {
for (i = 0; i < BLKDBG_EVENT_MAX; i++) {
QLIST_FOREACH_SAFE(rule, &s->rules[i], next, next) {
if (rule->action == ACTION_SUSPEND &&
!strcmp(rule->options.suspend.tag, tag)) {
@@ -675,15 +731,17 @@ static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
return bdrv_truncate(bs->file->bs, offset);
}
static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
static void blkdebug_refresh_filename(BlockDriverState *bs)
{
QDict *opts;
const QDictEntry *e;
bool force_json = false;
for (e = qdict_first(options); e; e = qdict_next(options, e)) {
for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
if (strcmp(qdict_entry_key(e), "config") &&
strcmp(qdict_entry_key(e), "x-image"))
strcmp(qdict_entry_key(e), "x-image") &&
strcmp(qdict_entry_key(e), "image") &&
strncmp(qdict_entry_key(e), "image.", strlen("image.")))
{
force_json = true;
break;
@@ -699,7 +757,7 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
if (!force_json && bs->file->bs->exact_filename[0]) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"blkdebug:%s:%s",
qdict_get_try_str(options, "config") ?: "",
qdict_get_try_str(bs->options, "config") ?: "",
bs->file->bs->exact_filename);
}
@@ -709,8 +767,11 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
QINCREF(bs->file->bs->full_open_options);
qdict_put_obj(opts, "image", QOBJECT(bs->file->bs->full_open_options));
for (e = qdict_first(options); e; e = qdict_next(options, e)) {
if (strcmp(qdict_entry_key(e), "x-image")) {
for (e = qdict_first(bs->options); e; e = qdict_next(bs->options, e)) {
if (strcmp(qdict_entry_key(e), "x-image") &&
strcmp(qdict_entry_key(e), "image") &&
strncmp(qdict_entry_key(e), "image.", strlen("image.")))
{
qobject_incref(qdict_entry_value(e));
qdict_put_obj(opts, qdict_entry_key(e), qdict_entry_value(e));
}
@@ -719,12 +780,6 @@ static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
bs->full_open_options = opts;
}
static int blkdebug_reopen_prepare(BDRVReopenState *reopen_state,
BlockReopenQueue *queue, Error **errp)
{
return 0;
}
static BlockDriver bdrv_blkdebug = {
.format_name = "blkdebug",
.protocol_name = "blkdebug",
@@ -733,7 +788,6 @@ static BlockDriver bdrv_blkdebug = {
.bdrv_parse_filename = blkdebug_parse_filename,
.bdrv_file_open = blkdebug_open,
.bdrv_close = blkdebug_close,
.bdrv_reopen_prepare = blkdebug_reopen_prepare,
.bdrv_getlength = blkdebug_getlength,
.bdrv_truncate = blkdebug_truncate,
.bdrv_refresh_filename = blkdebug_refresh_filename,

View File

@@ -7,7 +7,7 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include <stdarg.h>
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "block/block_int.h"
#include "qapi/qmp/qdict.h"
@@ -307,7 +307,7 @@ static void blkverify_attach_aio_context(BlockDriverState *bs,
bdrv_attach_aio_context(s->test_file->bs, new_context);
}
static void blkverify_refresh_filename(BlockDriverState *bs, QDict *options)
static void blkverify_refresh_filename(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;

View File

@@ -10,7 +10,6 @@
* or later. See the COPYING.LIB file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/block-backend.h"
#include "block/block_int.h"
#include "block/blockjob.h"
@@ -49,10 +48,6 @@ struct BlockBackend {
BlockdevOnError on_read_error, on_write_error;
bool iostatus_enabled;
BlockDeviceIoStatus iostatus;
bool allow_write_beyond_eof;
NotifierList remove_bs_notifiers, insert_bs_notifiers;
};
typedef struct BlockBackendAIOCB {
@@ -103,8 +98,6 @@ BlockBackend *blk_new(const char *name, Error **errp)
blk = g_new0(BlockBackend, 1);
blk->name = g_strdup(name);
blk->refcnt = 1;
notifier_list_init(&blk->remove_bs_notifiers);
notifier_list_init(&blk->insert_bs_notifiers);
QTAILQ_INSERT_TAIL(&blk_backends, blk, link);
return blk;
}
@@ -168,10 +161,11 @@ static void blk_delete(BlockBackend *blk)
assert(!blk->refcnt);
assert(!blk->dev);
if (blk->bs) {
blk_remove_bs(blk);
assert(blk->bs->blk == blk);
blk->bs->blk = NULL;
bdrv_unref(blk->bs);
blk->bs = NULL;
}
assert(QLIST_EMPTY(&blk->remove_bs_notifiers.notifiers));
assert(QLIST_EMPTY(&blk->insert_bs_notifiers.notifiers));
if (blk->root_state.throttle_state) {
g_free(blk->root_state.throttle_group);
throttle_group_unref(blk->root_state.throttle_state);
@@ -225,21 +219,6 @@ void blk_unref(BlockBackend *blk)
}
}
void blk_remove_all_bs(void)
{
BlockBackend *blk;
QTAILQ_FOREACH(blk, &blk_backends, link) {
AioContext *ctx = blk_get_aio_context(blk);
aio_context_acquire(ctx);
if (blk->bs) {
blk_remove_bs(blk);
}
aio_context_release(ctx);
}
}
/*
* Return the BlockBackend after @blk.
* If @blk is null, return the first one.
@@ -365,10 +344,6 @@ void blk_hide_on_behalf_of_hmp_drive_del(BlockBackend *blk)
*/
void blk_remove_bs(BlockBackend *blk)
{
assert(blk->bs->blk == blk);
notifier_list_notify(&blk->remove_bs_notifiers, blk);
blk_update_root_state(blk);
blk->bs->blk = NULL;
@@ -385,8 +360,6 @@ void blk_insert_bs(BlockBackend *blk, BlockDriverState *bs)
bdrv_ref(bs);
blk->bs = bs;
bs->blk = blk;
notifier_list_notify(&blk->insert_bs_notifiers, blk);
}
/*
@@ -581,11 +554,6 @@ void blk_iostatus_set_err(BlockBackend *blk, int error)
}
}
void blk_set_allow_write_beyond_eof(BlockBackend *blk, bool allow)
{
blk->allow_write_beyond_eof = allow;
}
static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
size_t size)
{
@@ -599,19 +567,17 @@ static int blk_check_byte_request(BlockBackend *blk, int64_t offset,
return -ENOMEDIUM;
}
len = blk_getlength(blk);
if (len < 0) {
return len;
}
if (offset < 0) {
return -EIO;
}
if (!blk->allow_write_beyond_eof) {
len = blk_getlength(blk);
if (len < 0) {
return len;
}
if (offset > len || len - offset < size) {
return -EIO;
}
if (offset > len || len - offset < size) {
return -EIO;
}
return 0;
@@ -1065,21 +1031,11 @@ int blk_get_max_transfer_length(BlockBackend *blk)
}
}
int blk_get_max_iov(BlockBackend *blk)
{
return blk->bs->bl.max_iov;
}
void blk_set_guest_block_size(BlockBackend *blk, int align)
{
blk->guest_block_size = align;
}
void *blk_try_blockalign(BlockBackend *blk, size_t size)
{
return qemu_try_blockalign(blk ? blk->bs : NULL, size);
}
void *blk_blockalign(BlockBackend *blk, size_t size)
{
return qemu_blockalign(blk ? blk->bs : NULL, size);
@@ -1159,14 +1115,11 @@ void blk_remove_aio_context_notifier(BlockBackend *blk,
}
}
void blk_add_remove_bs_notifier(BlockBackend *blk, Notifier *notify)
void blk_add_close_notifier(BlockBackend *blk, Notifier *notify)
{
notifier_list_add(&blk->remove_bs_notifiers, notify);
}
void blk_add_insert_bs_notifier(BlockBackend *blk, Notifier *notify)
{
notifier_list_add(&blk->insert_bs_notifiers, notify);
if (blk->bs) {
bdrv_add_close_notifier(blk->bs, notify);
}
}
void blk_io_plug(BlockBackend *blk)

View File

@@ -22,7 +22,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/module.h"

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/module.h"

View File

@@ -12,7 +12,6 @@
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"

View File

@@ -21,13 +21,11 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "block/block_int.h"
#include "qapi/qmp/qbool.h"
#include "qapi/qmp/qstring.h"
#include "crypto/secret.h"
#include <curl/curl.h>
// #define DEBUG_CURL
@@ -79,10 +77,6 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
#define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
#define CURL_BLOCK_OPT_TIMEOUT "timeout"
#define CURL_BLOCK_OPT_COOKIE "cookie"
#define CURL_BLOCK_OPT_USERNAME "username"
#define CURL_BLOCK_OPT_PASSWORD_SECRET "password-secret"
#define CURL_BLOCK_OPT_PROXY_USERNAME "proxy-username"
#define CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET "proxy-password-secret"
struct BDRVCURLState;
@@ -125,10 +119,6 @@ typedef struct BDRVCURLState {
char *cookie;
bool accept_range;
AioContext *aio_context;
char *username;
char *password;
char *proxyusername;
char *proxypassword;
} BDRVCURLState;
static void curl_clean_state(CURLState *s);
@@ -428,21 +418,6 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
if (s->username) {
curl_easy_setopt(state->curl, CURLOPT_USERNAME, s->username);
}
if (s->password) {
curl_easy_setopt(state->curl, CURLOPT_PASSWORD, s->password);
}
if (s->proxyusername) {
curl_easy_setopt(state->curl,
CURLOPT_PROXYUSERNAME, s->proxyusername);
}
if (s->proxypassword) {
curl_easy_setopt(state->curl,
CURLOPT_PROXYPASSWORD, s->proxypassword);
}
/* Restrict supported protocols to avoid security issues in the more
* obscure protocols. For example, do not allow POP3/SMTP/IMAP see
* CVE-2013-0249.
@@ -549,31 +524,10 @@ static QemuOptsList runtime_opts = {
.type = QEMU_OPT_STRING,
.help = "Pass the cookie or list of cookies with each request"
},
{
.name = CURL_BLOCK_OPT_USERNAME,
.type = QEMU_OPT_STRING,
.help = "Username for HTTP auth"
},
{
.name = CURL_BLOCK_OPT_PASSWORD_SECRET,
.type = QEMU_OPT_STRING,
.help = "ID of secret used as password for HTTP auth",
},
{
.name = CURL_BLOCK_OPT_PROXY_USERNAME,
.type = QEMU_OPT_STRING,
.help = "Username for HTTP proxy auth"
},
{
.name = CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET,
.type = QEMU_OPT_STRING,
.help = "ID of secret used as password for HTTP proxy auth",
},
{ /* end of list */ }
},
};
static int curl_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
@@ -584,7 +538,6 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
const char *file;
const char *cookie;
double d;
const char *secretid;
static int inited = 0;
@@ -626,26 +579,6 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
goto out_noclean;
}
s->username = g_strdup(qemu_opt_get(opts, CURL_BLOCK_OPT_USERNAME));
secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PASSWORD_SECRET);
if (secretid) {
s->password = qcrypto_secret_lookup_as_utf8(secretid, errp);
if (!s->password) {
goto out_noclean;
}
}
s->proxyusername = g_strdup(
qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_USERNAME));
secretid = qemu_opt_get(opts, CURL_BLOCK_OPT_PROXY_PASSWORD_SECRET);
if (secretid) {
s->proxypassword = qcrypto_secret_lookup_as_utf8(secretid, errp);
if (!s->proxypassword) {
goto out_noclean;
}
}
if (!inited) {
curl_global_init(CURL_GLOBAL_ALL);
inited = 1;

View File

@@ -1,387 +0,0 @@
/*
* Block Dirty Bitmap
*
* Copyright (c) 2016 Red Hat. Inc
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "config-host.h"
#include "qemu-common.h"
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
/**
* A BdrvDirtyBitmap can be in three possible states:
* (1) successor is NULL and disabled is false: full r/w mode
* (2) successor is NULL and disabled is true: read only mode ("disabled")
* (3) successor is set: frozen mode.
* A frozen bitmap cannot be renamed, deleted, anonymized, cleared, set,
* or enabled. A frozen bitmap can only abdicate() or reclaim().
*/
struct BdrvDirtyBitmap {
HBitmap *bitmap; /* Dirty sector bitmap implementation */
BdrvDirtyBitmap *successor; /* Anonymous child; implies frozen status */
char *name; /* Optional non-empty unique ID */
int64_t size; /* Size of the bitmap (Number of sectors) */
bool disabled; /* Bitmap is read-only */
QLIST_ENTRY(BdrvDirtyBitmap) list;
};
BdrvDirtyBitmap *bdrv_find_dirty_bitmap(BlockDriverState *bs, const char *name)
{
BdrvDirtyBitmap *bm;
assert(name);
QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
if (bm->name && !strcmp(name, bm->name)) {
return bm;
}
}
return NULL;
}
void bdrv_dirty_bitmap_make_anon(BdrvDirtyBitmap *bitmap)
{
assert(!bdrv_dirty_bitmap_frozen(bitmap));
g_free(bitmap->name);
bitmap->name = NULL;
}
BdrvDirtyBitmap *bdrv_create_dirty_bitmap(BlockDriverState *bs,
uint32_t granularity,
const char *name,
Error **errp)
{
int64_t bitmap_size;
BdrvDirtyBitmap *bitmap;
uint32_t sector_granularity;
assert((granularity & (granularity - 1)) == 0);
if (name && bdrv_find_dirty_bitmap(bs, name)) {
error_setg(errp, "Bitmap already exists: %s", name);
return NULL;
}
sector_granularity = granularity >> BDRV_SECTOR_BITS;
assert(sector_granularity);
bitmap_size = bdrv_nb_sectors(bs);
if (bitmap_size < 0) {
error_setg_errno(errp, -bitmap_size, "could not get length of device");
errno = -bitmap_size;
return NULL;
}
bitmap = g_new0(BdrvDirtyBitmap, 1);
bitmap->bitmap = hbitmap_alloc(bitmap_size, ctz32(sector_granularity));
bitmap->size = bitmap_size;
bitmap->name = g_strdup(name);
bitmap->disabled = false;
QLIST_INSERT_HEAD(&bs->dirty_bitmaps, bitmap, list);
return bitmap;
}
bool bdrv_dirty_bitmap_frozen(BdrvDirtyBitmap *bitmap)
{
return bitmap->successor;
}
bool bdrv_dirty_bitmap_enabled(BdrvDirtyBitmap *bitmap)
{
return !(bitmap->disabled || bitmap->successor);
}
DirtyBitmapStatus bdrv_dirty_bitmap_status(BdrvDirtyBitmap *bitmap)
{
if (bdrv_dirty_bitmap_frozen(bitmap)) {
return DIRTY_BITMAP_STATUS_FROZEN;
} else if (!bdrv_dirty_bitmap_enabled(bitmap)) {
return DIRTY_BITMAP_STATUS_DISABLED;
} else {
return DIRTY_BITMAP_STATUS_ACTIVE;
}
}
/**
* Create a successor bitmap destined to replace this bitmap after an operation.
* Requires that the bitmap is not frozen and has no successor.
*/
int bdrv_dirty_bitmap_create_successor(BlockDriverState *bs,
BdrvDirtyBitmap *bitmap, Error **errp)
{
uint64_t granularity;
BdrvDirtyBitmap *child;
if (bdrv_dirty_bitmap_frozen(bitmap)) {
error_setg(errp, "Cannot create a successor for a bitmap that is "
"currently frozen");
return -1;
}
assert(!bitmap->successor);
/* Create an anonymous successor */
granularity = bdrv_dirty_bitmap_granularity(bitmap);
child = bdrv_create_dirty_bitmap(bs, granularity, NULL, errp);
if (!child) {
return -1;
}
/* Successor will be on or off based on our current state. */
child->disabled = bitmap->disabled;
/* Install the successor and freeze the parent */
bitmap->successor = child;
return 0;
}
/**
* For a bitmap with a successor, yield our name to the successor,
* delete the old bitmap, and return a handle to the new bitmap.
*/
BdrvDirtyBitmap *bdrv_dirty_bitmap_abdicate(BlockDriverState *bs,
BdrvDirtyBitmap *bitmap,
Error **errp)
{
char *name;
BdrvDirtyBitmap *successor = bitmap->successor;
if (successor == NULL) {
error_setg(errp, "Cannot relinquish control if "
"there's no successor present");
return NULL;
}
name = bitmap->name;
bitmap->name = NULL;
successor->name = name;
bitmap->successor = NULL;
bdrv_release_dirty_bitmap(bs, bitmap);
return successor;
}
/**
* In cases of failure where we can no longer safely delete the parent,
* we may wish to re-join the parent and child/successor.
* The merged parent will be un-frozen, but not explicitly re-enabled.
*/
BdrvDirtyBitmap *bdrv_reclaim_dirty_bitmap(BlockDriverState *bs,
BdrvDirtyBitmap *parent,
Error **errp)
{
BdrvDirtyBitmap *successor = parent->successor;
if (!successor) {
error_setg(errp, "Cannot reclaim a successor when none is present");
return NULL;
}
if (!hbitmap_merge(parent->bitmap, successor->bitmap)) {
error_setg(errp, "Merging of parent and successor bitmap failed");
return NULL;
}
bdrv_release_dirty_bitmap(bs, successor);
parent->successor = NULL;
return parent;
}
/**
* Truncates _all_ bitmaps attached to a BDS.
*/
void bdrv_dirty_bitmap_truncate(BlockDriverState *bs)
{
BdrvDirtyBitmap *bitmap;
uint64_t size = bdrv_nb_sectors(bs);
QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
assert(!bdrv_dirty_bitmap_frozen(bitmap));
hbitmap_truncate(bitmap->bitmap, size);
bitmap->size = size;
}
}
static void bdrv_do_release_matching_dirty_bitmap(BlockDriverState *bs,
BdrvDirtyBitmap *bitmap,
bool only_named)
{
BdrvDirtyBitmap *bm, *next;
QLIST_FOREACH_SAFE(bm, &bs->dirty_bitmaps, list, next) {
if ((!bitmap || bm == bitmap) && (!only_named || bm->name)) {
assert(!bdrv_dirty_bitmap_frozen(bm));
QLIST_REMOVE(bm, list);
hbitmap_free(bm->bitmap);
g_free(bm->name);
g_free(bm);
if (bitmap) {
return;
}
}
}
}
void bdrv_release_dirty_bitmap(BlockDriverState *bs, BdrvDirtyBitmap *bitmap)
{
bdrv_do_release_matching_dirty_bitmap(bs, bitmap, false);
}
/**
* Release all named dirty bitmaps attached to a BDS (for use in bdrv_close()).
* There must not be any frozen bitmaps attached.
*/
void bdrv_release_named_dirty_bitmaps(BlockDriverState *bs)
{
bdrv_do_release_matching_dirty_bitmap(bs, NULL, true);
}
void bdrv_disable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
{
assert(!bdrv_dirty_bitmap_frozen(bitmap));
bitmap->disabled = true;
}
void bdrv_enable_dirty_bitmap(BdrvDirtyBitmap *bitmap)
{
assert(!bdrv_dirty_bitmap_frozen(bitmap));
bitmap->disabled = false;
}
BlockDirtyInfoList *bdrv_query_dirty_bitmaps(BlockDriverState *bs)
{
BdrvDirtyBitmap *bm;
BlockDirtyInfoList *list = NULL;
BlockDirtyInfoList **plist = &list;
QLIST_FOREACH(bm, &bs->dirty_bitmaps, list) {
BlockDirtyInfo *info = g_new0(BlockDirtyInfo, 1);
BlockDirtyInfoList *entry = g_new0(BlockDirtyInfoList, 1);
info->count = bdrv_get_dirty_count(bm);
info->granularity = bdrv_dirty_bitmap_granularity(bm);
info->has_name = !!bm->name;
info->name = g_strdup(bm->name);
info->status = bdrv_dirty_bitmap_status(bm);
entry->value = info;
*plist = entry;
plist = &entry->next;
}
return list;
}
int bdrv_get_dirty(BlockDriverState *bs, BdrvDirtyBitmap *bitmap,
int64_t sector)
{
if (bitmap) {
return hbitmap_get(bitmap->bitmap, sector);
} else {
return 0;
}
}
/**
* Chooses a default granularity based on the existing cluster size,
* but clamped between [4K, 64K]. Defaults to 64K in the case that there
* is no cluster size information available.
*/
uint32_t bdrv_get_default_bitmap_granularity(BlockDriverState *bs)
{
BlockDriverInfo bdi;
uint32_t granularity;
if (bdrv_get_info(bs, &bdi) >= 0 && bdi.cluster_size > 0) {
granularity = MAX(4096, bdi.cluster_size);
granularity = MIN(65536, granularity);
} else {
granularity = 65536;
}
return granularity;
}
uint32_t bdrv_dirty_bitmap_granularity(BdrvDirtyBitmap *bitmap)
{
return BDRV_SECTOR_SIZE << hbitmap_granularity(bitmap->bitmap);
}
void bdrv_dirty_iter_init(BdrvDirtyBitmap *bitmap, HBitmapIter *hbi)
{
hbitmap_iter_init(hbi, bitmap->bitmap, 0);
}
void bdrv_set_dirty_bitmap(BdrvDirtyBitmap *bitmap,
int64_t cur_sector, int nr_sectors)
{
assert(bdrv_dirty_bitmap_enabled(bitmap));
hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
}
void bdrv_reset_dirty_bitmap(BdrvDirtyBitmap *bitmap,
int64_t cur_sector, int nr_sectors)
{
assert(bdrv_dirty_bitmap_enabled(bitmap));
hbitmap_reset(bitmap->bitmap, cur_sector, nr_sectors);
}
void bdrv_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap **out)
{
assert(bdrv_dirty_bitmap_enabled(bitmap));
if (!out) {
hbitmap_reset_all(bitmap->bitmap);
} else {
HBitmap *backup = bitmap->bitmap;
bitmap->bitmap = hbitmap_alloc(bitmap->size,
hbitmap_granularity(backup));
*out = backup;
}
}
void bdrv_undo_clear_dirty_bitmap(BdrvDirtyBitmap *bitmap, HBitmap *in)
{
HBitmap *tmp = bitmap->bitmap;
assert(bdrv_dirty_bitmap_enabled(bitmap));
bitmap->bitmap = in;
hbitmap_free(tmp);
}
void bdrv_set_dirty(BlockDriverState *bs, int64_t cur_sector,
int nr_sectors)
{
BdrvDirtyBitmap *bitmap;
QLIST_FOREACH(bitmap, &bs->dirty_bitmaps, list) {
if (!bdrv_dirty_bitmap_enabled(bitmap)) {
continue;
}
hbitmap_set(bitmap->bitmap, cur_sector, nr_sectors);
}
}
/**
* Advance an HBitmapIter to an arbitrary offset.
*/
void bdrv_set_dirty_iter(HBitmapIter *hbi, int64_t offset)
{
assert(hbi->hb);
hbitmap_iter_init(hbi, hbi->hb, offset);
}
int64_t bdrv_get_dirty_count(BdrvDirtyBitmap *bitmap)
{
return hbitmap_count(bitmap->bitmap);
}

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/bswap.h"

View File

@@ -7,7 +7,6 @@
* See the COPYING file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include <glusterfs/api/glfs.h>
#include "block/block_int.h"
#include "qemu/uri.h"

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "sysemu/block-backend.h"
#include "block/blockjob.h"
@@ -167,13 +166,9 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.max_transfer_length = bs->file->bs->bl.max_transfer_length;
bs->bl.min_mem_alignment = bs->file->bs->bl.min_mem_alignment;
bs->bl.opt_mem_alignment = bs->file->bs->bl.opt_mem_alignment;
bs->bl.max_iov = bs->file->bs->bl.max_iov;
} else {
bs->bl.min_mem_alignment = 512;
bs->bl.opt_mem_alignment = getpagesize();
/* Safe default since most protocols use readv()/writev()/etc */
bs->bl.max_iov = IOV_MAX;
}
if (bs->backing) {
@@ -194,9 +189,6 @@ void bdrv_refresh_limits(BlockDriverState *bs, Error **errp)
bs->bl.min_mem_alignment =
MAX(bs->bl.min_mem_alignment,
bs->backing->bs->bl.min_mem_alignment);
bs->bl.max_iov =
MIN(bs->bl.max_iov,
bs->backing->bs->bl.max_iov);
}
/* Then let the driver override it */
@@ -301,7 +293,6 @@ void bdrv_drain_all(void)
if (bs->job) {
block_job_pause(bs->job);
}
bdrv_drain_recurse(bs);
aio_context_release(aio_context);
if (!g_slist_find(aio_ctxs, aio_context)) {
@@ -665,7 +656,6 @@ int bdrv_write_zeroes(BlockDriverState *bs, int64_t sector_num,
int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
{
int64_t target_sectors, ret, nb_sectors, sector_num = 0;
BlockDriverState *file;
int n;
target_sectors = bdrv_nb_sectors(bs);
@@ -678,7 +668,7 @@ int bdrv_make_zero(BlockDriverState *bs, BdrvRequestFlags flags)
if (nb_sectors <= 0) {
return 0;
}
ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n, &file);
ret = bdrv_get_block_status(bs, sector_num, nb_sectors, &n);
if (ret < 0) {
error_report("error getting block status at sector %" PRId64 ": %s",
sector_num, strerror(-ret));
@@ -1303,7 +1293,6 @@ static int coroutine_fn bdrv_co_do_pwritev(BlockDriverState *bs,
if (bs->read_only) {
return -EPERM;
}
assert(!(bs->open_flags & BDRV_O_INACTIVE));
ret = bdrv_check_byte_request(bs, offset, bytes);
if (ret < 0) {
@@ -1468,7 +1457,6 @@ int bdrv_flush_all(void)
typedef struct BdrvCoGetBlockStatusData {
BlockDriverState *bs;
BlockDriverState *base;
BlockDriverState **file;
int64_t sector_num;
int nb_sectors;
int *pnum;
@@ -1490,14 +1478,10 @@ typedef struct BdrvCoGetBlockStatusData {
*
* 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
* beyond the end of the disk image it will be clamped.
*
* If returned value is positive and BDRV_BLOCK_OFFSET_VALID bit is set, 'file'
* points to the BDS which the sector range is allocated in.
*/
static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
int64_t total_sectors;
int64_t n;
@@ -1527,9 +1511,7 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
return ret;
}
*file = NULL;
ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum,
file);
ret = bs->drv->bdrv_co_get_block_status(bs, sector_num, nb_sectors, pnum);
if (ret < 0) {
*pnum = 0;
return ret;
@@ -1538,7 +1520,7 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
if (ret & BDRV_BLOCK_RAW) {
assert(ret & BDRV_BLOCK_OFFSET_VALID);
return bdrv_get_block_status(bs->file->bs, ret >> BDRV_SECTOR_BITS,
*pnum, pnum, file);
*pnum, pnum);
}
if (ret & (BDRV_BLOCK_DATA | BDRV_BLOCK_ZERO)) {
@@ -1555,14 +1537,13 @@ static int64_t coroutine_fn bdrv_co_get_block_status(BlockDriverState *bs,
}
}
if (*file && *file != bs &&
if (bs->file &&
(ret & BDRV_BLOCK_DATA) && !(ret & BDRV_BLOCK_ZERO) &&
(ret & BDRV_BLOCK_OFFSET_VALID)) {
BlockDriverState *file2;
int file_pnum;
ret2 = bdrv_co_get_block_status(*file, ret >> BDRV_SECTOR_BITS,
*pnum, &file_pnum, &file2);
ret2 = bdrv_co_get_block_status(bs->file->bs, ret >> BDRV_SECTOR_BITS,
*pnum, &file_pnum);
if (ret2 >= 0) {
/* Ignore errors. This is just providing extra information, it
* is useful but not necessary.
@@ -1587,15 +1568,14 @@ static int64_t coroutine_fn bdrv_co_get_block_status_above(BlockDriverState *bs,
BlockDriverState *base,
int64_t sector_num,
int nb_sectors,
int *pnum,
BlockDriverState **file)
int *pnum)
{
BlockDriverState *p;
int64_t ret = 0;
assert(bs != base);
for (p = bs; p != base; p = backing_bs(p)) {
ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum, file);
ret = bdrv_co_get_block_status(p, sector_num, nb_sectors, pnum);
if (ret < 0 || ret & BDRV_BLOCK_ALLOCATED) {
break;
}
@@ -1614,8 +1594,7 @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque)
data->ret = bdrv_co_get_block_status_above(data->bs, data->base,
data->sector_num,
data->nb_sectors,
data->pnum,
data->file);
data->pnum);
data->done = true;
}
@@ -1627,14 +1606,12 @@ static void coroutine_fn bdrv_get_block_status_above_co_entry(void *opaque)
int64_t bdrv_get_block_status_above(BlockDriverState *bs,
BlockDriverState *base,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
Coroutine *co;
BdrvCoGetBlockStatusData data = {
.bs = bs,
.base = base,
.file = file,
.sector_num = sector_num,
.nb_sectors = nb_sectors,
.pnum = pnum,
@@ -1658,19 +1635,16 @@ int64_t bdrv_get_block_status_above(BlockDriverState *bs,
int64_t bdrv_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
return bdrv_get_block_status_above(bs, backing_bs(bs),
sector_num, nb_sectors, pnum, file);
sector_num, nb_sectors, pnum);
}
int coroutine_fn bdrv_is_allocated(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, int *pnum)
{
BlockDriverState *file;
int64_t ret = bdrv_get_block_status(bs, sector_num, nb_sectors, pnum,
&file);
int64_t ret = bdrv_get_block_status(bs, sector_num, nb_sectors, pnum);
if (ret < 0) {
return ret;
}
@@ -1908,8 +1882,7 @@ static int multiwrite_merge(BlockDriverState *bs, BlockRequest *reqs,
merge = 1;
}
if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 >
bs->bl.max_iov) {
if (reqs[outidx].qiov->niov + reqs[i].qiov->niov + 1 > IOV_MAX) {
merge = 0;
}
@@ -2480,7 +2453,6 @@ int coroutine_fn bdrv_co_discard(BlockDriverState *bs, int64_t sector_num,
} else if (bs->read_only) {
return -EPERM;
}
assert(!(bs->open_flags & BDRV_O_INACTIVE));
/* Do nothing if disabled. */
if (!(bs->open_flags & BDRV_O_UNMAP)) {
@@ -2642,11 +2614,10 @@ int bdrv_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
bdrv_co_ioctl_entry(&data);
} else {
Coroutine *co = qemu_coroutine_create(bdrv_co_ioctl_entry);
qemu_coroutine_enter(co, &data);
while (data.ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(bs), true);
}
}
while (data.ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(bs), true);
}
return data.ret;
}

View File

@@ -23,7 +23,7 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "config-host.h"
#include <poll.h>
#include <math.h>
@@ -39,7 +39,6 @@
#include "sysemu/sysemu.h"
#include "qmp-commands.h"
#include "qapi/qmp/qstring.h"
#include "crypto/secret.h"
#include <iscsi/iscsi.h>
#include <iscsi/scsi-lowlevel.h>
@@ -533,8 +532,7 @@ static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
IscsiLun *iscsilun = bs->opaque;
struct scsi_get_lba_status *lbas = NULL;
@@ -626,9 +624,6 @@ out:
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
}
if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID) {
*file = bs;
}
return ret;
}
@@ -655,8 +650,7 @@ static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
!iscsi_allocationmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
int64_t ret;
int pnum;
BlockDriverState *file;
ret = iscsi_co_get_block_status(bs, sector_num, INT_MAX, &pnum, &file);
ret = iscsi_co_get_block_status(bs, sector_num, INT_MAX, &pnum);
if (ret < 0) {
return ret;
}
@@ -1081,8 +1075,6 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
QemuOpts *opts;
const char *user = NULL;
const char *password = NULL;
const char *secretid;
char *secret = NULL;
list = qemu_find_opts("iscsi");
if (!list) {
@@ -1102,20 +1094,8 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
return;
}
secretid = qemu_opt_get(opts, "password-secret");
password = qemu_opt_get(opts, "password");
if (secretid && password) {
error_setg(errp, "'password' and 'password-secret' properties are "
"mutually exclusive");
return;
}
if (secretid) {
secret = qcrypto_secret_lookup_as_utf8(secretid, errp);
if (!secret) {
return;
}
password = secret;
} else if (!password) {
if (!password) {
error_setg(errp, "CHAP username specified but no password was given");
return;
}
@@ -1123,8 +1103,6 @@ static void parse_chap(struct iscsi_context *iscsi, const char *target,
if (iscsi_set_initiator_username_pwd(iscsi, user, password)) {
error_setg(errp, "Failed to set initiator username and password");
}
g_free(secret);
}
static void parse_header_digest(struct iscsi_context *iscsi, const char *target,
@@ -1265,13 +1243,8 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
iscsilun->lbprz = !!rc16->lbprz;
iscsilun->use_16_for_rw = (rc16->returned_lba > 0xffffffff);
}
break;
}
if (task != NULL && task->status == SCSI_STATUS_CHECK_CONDITION
&& task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
break;
}
/* Fall through and try READ CAPACITY(10) instead. */
break;
case TYPE_ROM:
task = iscsi_readcapacity10_sync(iscsilun->iscsi, iscsilun->lun, 0, 0);
if (task != NULL && task->status == SCSI_STATUS_GOOD) {
@@ -1297,7 +1270,7 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
&& retries-- > 0);
if (task == NULL || task->status != SCSI_STATUS_GOOD) {
error_setg(errp, "iSCSI: failed to send readcapacity10/16 command");
error_setg(errp, "iSCSI: failed to send readcapacity10 command.");
} else if (!iscsilun->block_size ||
iscsilun->block_size % BDRV_SECTOR_SIZE) {
error_setg(errp, "iSCSI: the target returned an invalid "
@@ -1874,11 +1847,6 @@ static QemuOptsList qemu_iscsi_opts = {
.name = "password",
.type = QEMU_OPT_STRING,
.help = "password for CHAP authentication to target",
},{
.name = "password-secret",
.type = QEMU_OPT_STRING,
.help = "ID of the secret providing password for CHAP "
"authentication to target",
},{
.name = "header-digest",
.type = QEMU_OPT_STRING,

View File

@@ -7,7 +7,6 @@
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/aio.h"
#include "qemu/queue.h"

View File

@@ -11,7 +11,6 @@
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "block/blockjob.h"
#include "block/block_int.h"
@@ -19,7 +18,6 @@
#include "qapi/qmp/qerror.h"
#include "qemu/ratelimit.h"
#include "qemu/bitmap.h"
#include "qemu/error-report.h"
#define SLICE_TIME 100000000ULL /* ns */
#define MAX_IN_FLIGHT 16
@@ -47,6 +45,7 @@ typedef struct MirrorBlockJob {
BlockdevOnError on_source_error, on_target_error;
bool synced;
bool should_complete;
int64_t sector_num;
int64_t granularity;
size_t buf_size;
int64_t bdev_length;
@@ -63,8 +62,6 @@ typedef struct MirrorBlockJob {
int ret;
bool unmap;
bool waiting_for_io;
int target_cluster_sectors;
int max_iov;
} MirrorBlockJob;
typedef struct MirrorOp {
@@ -160,85 +157,113 @@ static void mirror_read_complete(void *opaque, int ret)
mirror_write_complete, op);
}
/* Round sector_num and/or nb_sectors to target cluster if COW is needed, and
* return the offset of the adjusted tail sector against original. */
static int mirror_cow_align(MirrorBlockJob *s,
int64_t *sector_num,
int *nb_sectors)
{
bool need_cow;
int ret = 0;
int chunk_sectors = s->granularity >> BDRV_SECTOR_BITS;
int64_t align_sector_num = *sector_num;
int align_nb_sectors = *nb_sectors;
int max_sectors = chunk_sectors * s->max_iov;
need_cow = !test_bit(*sector_num / chunk_sectors, s->cow_bitmap);
need_cow |= !test_bit((*sector_num + *nb_sectors - 1) / chunk_sectors,
s->cow_bitmap);
if (need_cow) {
bdrv_round_to_clusters(s->target, *sector_num, *nb_sectors,
&align_sector_num, &align_nb_sectors);
}
if (align_nb_sectors > max_sectors) {
align_nb_sectors = max_sectors;
if (need_cow) {
align_nb_sectors = QEMU_ALIGN_DOWN(align_nb_sectors,
s->target_cluster_sectors);
}
}
ret = align_sector_num + align_nb_sectors - (*sector_num + *nb_sectors);
*sector_num = align_sector_num;
*nb_sectors = align_nb_sectors;
assert(ret >= 0);
return ret;
}
static inline void mirror_wait_for_io(MirrorBlockJob *s)
{
assert(!s->waiting_for_io);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
/* Submit async read while handling COW.
* Returns: nb_sectors if no alignment is necessary, or
* (new_end - sector_num) if tail is rounded up or down due to
* alignment or buffer limit.
*/
static int mirror_do_read(MirrorBlockJob *s, int64_t sector_num,
int nb_sectors)
static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
BlockDriverState *source = s->common.bs;
int sectors_per_chunk, nb_chunks;
int ret = nb_sectors;
int nb_sectors, sectors_per_chunk, nb_chunks;
int64_t end, sector_num, next_chunk, next_sector, hbitmap_next_sector;
uint64_t delay_ns = 0;
MirrorOp *op;
int pnum;
int64_t ret;
s->sector_num = hbitmap_iter_next(&s->hbi);
if (s->sector_num < 0) {
bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
s->sector_num = hbitmap_iter_next(&s->hbi);
trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
assert(s->sector_num >= 0);
}
hbitmap_next_sector = s->sector_num;
sector_num = s->sector_num;
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
end = s->bdev_length / BDRV_SECTOR_SIZE;
/* We can only handle as much as buf_size at a time. */
nb_sectors = MIN(s->buf_size >> BDRV_SECTOR_BITS, nb_sectors);
assert(nb_sectors);
/* Extend the QEMUIOVector to include all adjacent blocks that will
* be copied in this operation.
*
* We have to do this if we have no backing file yet in the destination,
* and the cluster size is very large. Then we need to do COW ourselves.
* The first time a cluster is copied, copy it entirely. Note that,
* because both the granularity and the cluster size are powers of two,
* the number of sectors to copy cannot exceed one cluster.
*
* We also want to extend the QEMUIOVector to include more adjacent
* dirty blocks if possible, to limit the number of I/O operations and
* run efficiently even with a small granularity.
*/
nb_chunks = 0;
nb_sectors = 0;
next_sector = sector_num;
next_chunk = sector_num / sectors_per_chunk;
if (s->cow_bitmap) {
ret += mirror_cow_align(s, &sector_num, &nb_sectors);
}
assert(nb_sectors << BDRV_SECTOR_BITS <= s->buf_size);
/* The sector range must meet granularity because:
* 1) Caller passes in aligned values;
* 2) mirror_cow_align is used only when target cluster is larger. */
assert(!(nb_sectors % sectors_per_chunk));
assert(!(sector_num % sectors_per_chunk));
nb_chunks = nb_sectors / sectors_per_chunk;
while (s->buf_free_count < nb_chunks) {
/* Wait for I/O to this cluster (from a previous iteration) to be done. */
while (test_bit(next_chunk, s->in_flight_bitmap)) {
trace_mirror_yield_in_flight(s, sector_num, s->in_flight);
mirror_wait_for_io(s);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
do {
int added_sectors, added_chunks;
if (!bdrv_get_dirty(source, s->dirty_bitmap, next_sector) ||
test_bit(next_chunk, s->in_flight_bitmap)) {
assert(nb_sectors > 0);
break;
}
added_sectors = sectors_per_chunk;
if (s->cow_bitmap && !test_bit(next_chunk, s->cow_bitmap)) {
bdrv_round_to_clusters(s->target,
next_sector, added_sectors,
&next_sector, &added_sectors);
/* On the first iteration, the rounding may make us copy
* sectors before the first dirty one.
*/
if (next_sector < sector_num) {
assert(nb_sectors == 0);
sector_num = next_sector;
next_chunk = next_sector / sectors_per_chunk;
}
}
added_sectors = MIN(added_sectors, end - (sector_num + nb_sectors));
added_chunks = (added_sectors + sectors_per_chunk - 1) / sectors_per_chunk;
/* When doing COW, it may happen that there is not enough space for
* a full cluster. Wait if that is the case.
*/
while (nb_chunks == 0 && s->buf_free_count < added_chunks) {
trace_mirror_yield_buf_busy(s, nb_chunks, s->in_flight);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
if (s->buf_free_count < nb_chunks + added_chunks) {
trace_mirror_break_buf_busy(s, nb_chunks, s->in_flight);
break;
}
if (IOV_MAX < nb_chunks + added_chunks) {
trace_mirror_break_iov_max(s, nb_chunks, added_chunks);
break;
}
/* We have enough free space to copy these sectors. */
bitmap_set(s->in_flight_bitmap, next_chunk, added_chunks);
nb_sectors += added_sectors;
nb_chunks += added_chunks;
next_sector += added_sectors;
next_chunk += added_chunks;
if (!s->synced && s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
}
} while (delay_ns == 0 && next_sector < end);
/* Allocate a MirrorOp that is used as an AIO callback. */
op = g_new(MirrorOp, 1);
op->s = s;
@@ -249,151 +274,47 @@ static int mirror_do_read(MirrorBlockJob *s, int64_t sector_num,
* from s->buf_free.
*/
qemu_iovec_init(&op->qiov, nb_chunks);
next_sector = sector_num;
while (nb_chunks-- > 0) {
MirrorBuffer *buf = QSIMPLEQ_FIRST(&s->buf_free);
size_t remaining = nb_sectors * BDRV_SECTOR_SIZE - op->qiov.size;
size_t remaining = (nb_sectors * BDRV_SECTOR_SIZE) - op->qiov.size;
QSIMPLEQ_REMOVE_HEAD(&s->buf_free, next);
s->buf_free_count--;
qemu_iovec_add(&op->qiov, buf, MIN(s->granularity, remaining));
/* Advance the HBitmapIter in parallel, so that we do not examine
* the same sector twice.
*/
if (next_sector > hbitmap_next_sector
&& bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
hbitmap_next_sector = hbitmap_iter_next(&s->hbi);
}
next_sector += sectors_per_chunk;
}
bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num, nb_sectors);
/* Copy the dirty cluster. */
s->in_flight++;
s->sectors_in_flight += nb_sectors;
trace_mirror_one_iteration(s, sector_num, nb_sectors);
bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
mirror_read_complete, op);
return ret;
}
static void mirror_do_zero_or_discard(MirrorBlockJob *s,
int64_t sector_num,
int nb_sectors,
bool is_discard)
{
MirrorOp *op;
/* Allocate a MirrorOp that is used as an AIO callback. The qiov is zeroed
* so the freeing in mirror_iteration_done is nop. */
op = g_new0(MirrorOp, 1);
op->s = s;
op->sector_num = sector_num;
op->nb_sectors = nb_sectors;
s->in_flight++;
s->sectors_in_flight += nb_sectors;
if (is_discard) {
bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
mirror_write_complete, op);
} else {
ret = bdrv_get_block_status_above(source, NULL, sector_num,
nb_sectors, &pnum);
if (ret < 0 || pnum < nb_sectors ||
(ret & BDRV_BLOCK_DATA && !(ret & BDRV_BLOCK_ZERO))) {
bdrv_aio_readv(source, sector_num, &op->qiov, nb_sectors,
mirror_read_complete, op);
} else if (ret & BDRV_BLOCK_ZERO) {
bdrv_aio_write_zeroes(s->target, sector_num, op->nb_sectors,
s->unmap ? BDRV_REQ_MAY_UNMAP : 0,
mirror_write_complete, op);
}
}
static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
{
BlockDriverState *source = s->common.bs;
int64_t sector_num;
uint64_t delay_ns = 0;
/* At least the first dirty chunk is mirrored in one iteration. */
int nb_chunks = 1;
int64_t end = s->bdev_length / BDRV_SECTOR_SIZE;
int sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
sector_num = hbitmap_iter_next(&s->hbi);
if (sector_num < 0) {
bdrv_dirty_iter_init(s->dirty_bitmap, &s->hbi);
sector_num = hbitmap_iter_next(&s->hbi);
trace_mirror_restart_iter(s, bdrv_get_dirty_count(s->dirty_bitmap));
assert(sector_num >= 0);
}
/* Find the number of consective dirty chunks following the first dirty
* one, and wait for in flight requests in them. */
while (nb_chunks * sectors_per_chunk < (s->buf_size >> BDRV_SECTOR_BITS)) {
int64_t hbitmap_next;
int64_t next_sector = sector_num + nb_chunks * sectors_per_chunk;
int64_t next_chunk = next_sector / sectors_per_chunk;
if (next_sector >= end ||
!bdrv_get_dirty(source, s->dirty_bitmap, next_sector)) {
break;
}
if (test_bit(next_chunk, s->in_flight_bitmap)) {
if (nb_chunks > 0) {
break;
}
trace_mirror_yield_in_flight(s, next_sector, s->in_flight);
mirror_wait_for_io(s);
/* Now retry. */
} else {
hbitmap_next = hbitmap_iter_next(&s->hbi);
assert(hbitmap_next == next_sector);
nb_chunks++;
}
}
/* Clear dirty bits before querying the block status, because
* calling bdrv_get_block_status_above could yield - if some blocks are
* marked dirty in this window, we need to know.
*/
bdrv_reset_dirty_bitmap(s->dirty_bitmap, sector_num,
nb_chunks * sectors_per_chunk);
bitmap_set(s->in_flight_bitmap, sector_num / sectors_per_chunk, nb_chunks);
while (nb_chunks > 0 && sector_num < end) {
int ret;
int io_sectors;
BlockDriverState *file;
enum MirrorMethod {
MIRROR_METHOD_COPY,
MIRROR_METHOD_ZERO,
MIRROR_METHOD_DISCARD
} mirror_method = MIRROR_METHOD_COPY;
assert(!(sector_num % sectors_per_chunk));
ret = bdrv_get_block_status_above(source, NULL, sector_num,
nb_chunks * sectors_per_chunk,
&io_sectors, &file);
if (ret < 0) {
io_sectors = nb_chunks * sectors_per_chunk;
}
io_sectors -= io_sectors % sectors_per_chunk;
if (io_sectors < sectors_per_chunk) {
io_sectors = sectors_per_chunk;
} else if (ret >= 0 && !(ret & BDRV_BLOCK_DATA)) {
int64_t target_sector_num;
int target_nb_sectors;
bdrv_round_to_clusters(s->target, sector_num, io_sectors,
&target_sector_num, &target_nb_sectors);
if (target_sector_num == sector_num &&
target_nb_sectors == io_sectors) {
mirror_method = ret & BDRV_BLOCK_ZERO ?
MIRROR_METHOD_ZERO :
MIRROR_METHOD_DISCARD;
}
}
switch (mirror_method) {
case MIRROR_METHOD_COPY:
io_sectors = mirror_do_read(s, sector_num, io_sectors);
break;
case MIRROR_METHOD_ZERO:
mirror_do_zero_or_discard(s, sector_num, io_sectors, false);
break;
case MIRROR_METHOD_DISCARD:
mirror_do_zero_or_discard(s, sector_num, io_sectors, true);
break;
default:
abort();
}
assert(io_sectors);
sector_num += io_sectors;
nb_chunks -= io_sectors / sectors_per_chunk;
delay_ns += ratelimit_calculate_delay(&s->limit, io_sectors);
} else {
assert(!(ret & BDRV_BLOCK_DATA));
bdrv_aio_discard(s->target, sector_num, op->nb_sectors,
mirror_write_complete, op);
}
return delay_ns;
}
@@ -418,7 +339,9 @@ static void mirror_free_init(MirrorBlockJob *s)
static void mirror_drain(MirrorBlockJob *s)
{
while (s->in_flight > 0) {
mirror_wait_for_io(s);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
}
}
@@ -447,22 +370,11 @@ static void mirror_exit(BlockJob *job, void *opaque)
if (s->to_replace) {
to_replace = s->to_replace;
}
/* This was checked in mirror_start_job(), but meanwhile one of the
* nodes could have been newly attached to a BlockBackend. */
if (to_replace->blk && s->target->blk) {
error_report("block job: Can't create node with two BlockBackends");
data->ret = -EINVAL;
goto out;
}
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
bdrv_replace_in_backing_chain(to_replace, s->target);
}
out:
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
@@ -492,7 +404,6 @@ static void coroutine_fn mirror_run(void *opaque)
checking for a NULL string */
int ret = 0;
int n;
int target_cluster_size = BDRV_SECTOR_SIZE;
if (block_job_is_cancelled(&s->common)) {
goto immediate_exit;
@@ -522,16 +433,16 @@ static void coroutine_fn mirror_run(void *opaque)
*/
bdrv_get_backing_filename(s->target, backing_filename,
sizeof(backing_filename));
if (!bdrv_get_info(s->target, &bdi) && bdi.cluster_size) {
target_cluster_size = bdi.cluster_size;
if (backing_filename[0] && !s->target->backing) {
ret = bdrv_get_info(s->target, &bdi);
if (ret < 0) {
goto immediate_exit;
}
if (s->granularity < bdi.cluster_size) {
s->buf_size = MAX(s->buf_size, bdi.cluster_size);
s->cow_bitmap = bitmap_new(length);
}
}
if (backing_filename[0] && !s->target->backing
&& s->granularity < target_cluster_size) {
s->buf_size = MAX(s->buf_size, target_cluster_size);
s->cow_bitmap = bitmap_new(length);
}
s->target_cluster_sectors = target_cluster_size >> BDRV_SECTOR_BITS;
s->max_iov = MIN(s->common.bs->bl.max_iov, s->target->bl.max_iov);
end = s->bdev_length / BDRV_SECTOR_SIZE;
s->buf = qemu_try_blockalign(bs, s->buf_size);
@@ -606,7 +517,9 @@ static void coroutine_fn mirror_run(void *opaque)
if (s->in_flight == MAX_IN_FLIGHT || s->buf_free_count == 0 ||
(cnt == 0 && s->in_flight > 0)) {
trace_mirror_yield(s, s->in_flight, s->buf_free_count, cnt);
mirror_wait_for_io(s);
s->waiting_for_io = true;
qemu_coroutine_yield();
s->waiting_for_io = false;
continue;
} else if (cnt != 0) {
delay_ns = mirror_iteration(s);
@@ -727,7 +640,7 @@ static void mirror_complete(BlockJob *job, Error **errp)
Error *local_err = NULL;
int ret;
ret = bdrv_open_backing_file(s->target, NULL, "backing", &local_err);
ret = bdrv_open_backing_file(s->target, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return;
@@ -792,7 +705,6 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
bool is_none_mode, BlockDriverState *base)
{
MirrorBlockJob *s;
BlockDriverState *replaced_bs;
if (granularity == 0) {
granularity = bdrv_get_default_bitmap_granularity(target);
@@ -816,21 +728,6 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
buf_size = DEFAULT_MIRROR_BUF_SIZE;
}
/* We can't support this case as long as the block layer can't handle
* multiple BlockBackends per BlockDriverState. */
if (replaces) {
replaced_bs = bdrv_lookup_bs(replaces, replaces, errp);
if (replaced_bs == NULL) {
return;
}
} else {
replaced_bs = bs;
}
if (replaced_bs->blk && target->blk) {
error_setg(errp, "Can't create node with two BlockBackends");
return;
}
s = block_job_create(driver, bs, speed, cb, opaque, errp);
if (!s) {
return;

View File

@@ -26,8 +26,8 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "nbd-client.h"
#include "qemu/sockets.h"
#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
#define INDEX_TO_HANDLE(bs, index) ((index) ^ ((uint64_t)(intptr_t)bs))
@@ -47,21 +47,13 @@ static void nbd_teardown_connection(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
if (!client->ioc) { /* Already closed */
return;
}
/* finish any pending coroutines */
qio_channel_shutdown(client->ioc,
QIO_CHANNEL_SHUTDOWN_BOTH,
NULL);
shutdown(client->sock, 2);
nbd_recv_coroutines_enter_all(client);
nbd_client_detach_aio_context(bs);
object_unref(OBJECT(client->sioc));
client->sioc = NULL;
object_unref(OBJECT(client->ioc));
client->ioc = NULL;
closesocket(client->sock);
client->sock = -1;
}
static void nbd_reply_ready(void *opaque)
@@ -71,16 +63,12 @@ static void nbd_reply_ready(void *opaque)
uint64_t i;
int ret;
if (!s->ioc) { /* Already closed */
return;
}
if (s->reply.handle == 0) {
/* No reply already in flight. Fetch a header. It is possible
* that another thread has done the same thing in parallel, so
* the socket is not readable anymore.
*/
ret = nbd_receive_reply(s->ioc, &s->reply);
ret = nbd_receive_reply(s->sock, &s->reply);
if (ret == -EAGAIN) {
return;
}
@@ -131,35 +119,32 @@ static int nbd_co_send_request(BlockDriverState *bs,
}
}
g_assert(qemu_in_coroutine());
assert(i < MAX_NBD_REQUESTS);
request->handle = INDEX_TO_HANDLE(s, i);
if (!s->ioc) {
qemu_co_mutex_unlock(&s->send_mutex);
return -EPIPE;
}
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(bs);
aio_set_fd_handler(aio_context, s->sioc->fd, false,
aio_set_fd_handler(aio_context, s->sock, false,
nbd_reply_ready, nbd_restart_write, bs);
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (!s->is_unix) {
socket_set_cork(s->sock, 1);
}
rc = nbd_send_request(s->sock, request);
if (rc >= 0) {
ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov,
offset, request->len, 0);
ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
offset, request->len);
if (ret != request->len) {
rc = -EIO;
}
}
qio_channel_set_cork(s->ioc, false);
if (!s->is_unix) {
socket_set_cork(s->sock, 0);
}
} else {
rc = nbd_send_request(s->ioc, request);
rc = nbd_send_request(s->sock, request);
}
aio_set_fd_handler(aio_context, s->sioc->fd, false,
aio_set_fd_handler(aio_context, s->sock, false,
nbd_reply_ready, NULL, bs);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
@@ -176,13 +161,12 @@ static void nbd_co_receive_reply(NbdClientSession *s,
* peek at the next reply and avoid yielding if it's ours? */
qemu_coroutine_yield();
*reply = s->reply;
if (reply->handle != request->handle ||
!s->ioc) {
if (reply->handle != request->handle) {
reply->error = EIO;
} else {
if (qiov && reply->error == 0) {
ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov,
offset, request->len, 1);
ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
offset, request->len);
if (ret != request->len) {
reply->error = EIO;
}
@@ -365,14 +349,14 @@ int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
void nbd_client_detach_aio_context(BlockDriverState *bs)
{
aio_set_fd_handler(bdrv_get_aio_context(bs),
nbd_get_client_session(bs)->sioc->fd,
nbd_get_client_session(bs)->sock,
false, NULL, NULL, NULL);
}
void nbd_client_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sioc->fd,
aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sock,
false, nbd_reply_ready, NULL, bs);
}
@@ -385,20 +369,16 @@ void nbd_client_close(BlockDriverState *bs)
.len = 0
};
if (client->ioc == NULL) {
if (client->sock == -1) {
return;
}
nbd_send_request(client->ioc, &request);
nbd_send_request(client->sock, &request);
nbd_teardown_connection(bs);
}
int nbd_client_init(BlockDriverState *bs,
QIOChannelSocket *sioc,
const char *export,
QCryptoTLSCreds *tlscreds,
const char *hostname,
int nbd_client_init(BlockDriverState *bs, int sock, const char *export,
Error **errp)
{
NbdClientSession *client = nbd_get_client_session(bs);
@@ -406,32 +386,22 @@ int nbd_client_init(BlockDriverState *bs,
/* NBD handshake */
logout("session init %s\n", export);
qio_channel_set_blocking(QIO_CHANNEL(sioc), true, NULL);
ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
&client->nbdflags,
tlscreds, hostname,
&client->ioc,
&client->size, errp);
qemu_set_block(sock);
ret = nbd_receive_negotiate(sock, export,
&client->nbdflags, &client->size, errp);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
closesocket(sock);
return ret;
}
qemu_co_mutex_init(&client->send_mutex);
qemu_co_mutex_init(&client->free_sema);
client->sioc = sioc;
object_ref(OBJECT(client->sioc));
if (!client->ioc) {
client->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(client->ioc));
}
client->sock = sock;
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
qemu_set_nonblock(sock);
nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
logout("Established connection with NBD server\n");

View File

@@ -4,7 +4,6 @@
#include "qemu-common.h"
#include "block/nbd.h"
#include "block/block_int.h"
#include "io/channel-socket.h"
/* #define DEBUG_NBD */
@@ -18,8 +17,7 @@
#define MAX_NBD_REQUESTS 16
typedef struct NbdClientSession {
QIOChannelSocket *sioc; /* The master data channel */
QIOChannel *ioc; /* The current I/O channel which may differ (eg TLS) */
int sock;
uint32_t nbdflags;
off_t size;
@@ -36,11 +34,7 @@ typedef struct NbdClientSession {
NbdClientSession *nbd_get_client_session(BlockDriverState *bs);
int nbd_client_init(BlockDriverState *bs,
QIOChannelSocket *sock,
const char *export_name,
QCryptoTLSCreds *tlscreds,
const char *hostname,
int nbd_client_init(BlockDriverState *bs, int sock, const char *export_name,
Error **errp);
void nbd_client_close(BlockDriverState *bs);

View File

@@ -26,16 +26,18 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/nbd-client.h"
#include "qemu/uri.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qemu/sockets.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qmp/qint.h"
#include "qapi/qmp/qstring.h"
#include <sys/types.h>
#include <unistd.h>
#define EN_OPTSTR ":exportname="
@@ -204,20 +206,18 @@ static SocketAddress *nbd_config(BDRVNBDState *s, QDict *options, char **export,
saddr = g_new0(SocketAddress, 1);
if (qdict_haskey(options, "path")) {
UnixSocketAddress *q_unix;
saddr->type = SOCKET_ADDRESS_KIND_UNIX;
q_unix = saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
q_unix->path = g_strdup(qdict_get_str(options, "path"));
saddr->u.q_unix = g_new0(UnixSocketAddress, 1);
saddr->u.q_unix->path = g_strdup(qdict_get_str(options, "path"));
qdict_del(options, "path");
} else {
InetSocketAddress *inet;
saddr->type = SOCKET_ADDRESS_KIND_INET;
inet = saddr->u.inet = g_new0(InetSocketAddress, 1);
inet->host = g_strdup(qdict_get_str(options, "host"));
saddr->u.inet = g_new0(InetSocketAddress, 1);
saddr->u.inet->host = g_strdup(qdict_get_str(options, "host"));
if (!qdict_get_try_str(options, "port")) {
inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
saddr->u.inet->port = g_strdup_printf("%d", NBD_DEFAULT_PORT);
} else {
inet->port = g_strdup(qdict_get_str(options, "port"));
saddr->u.inet->port = g_strdup(qdict_get_str(options, "port"));
}
qdict_del(options, "host");
qdict_del(options, "port");
@@ -239,113 +239,55 @@ NbdClientSession *nbd_get_client_session(BlockDriverState *bs)
return &s->client;
}
static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
Error **errp)
static int nbd_establish_connection(BlockDriverState *bs,
SocketAddress *saddr,
Error **errp)
{
QIOChannelSocket *sioc;
Error *local_err = NULL;
BDRVNBDState *s = bs->opaque;
int sock;
sioc = qio_channel_socket_new();
sock = socket_connect(saddr, errp, NULL, NULL);
qio_channel_socket_connect_sync(sioc,
saddr,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
return NULL;
if (sock < 0) {
logout("Failed to establish connection to NBD server\n");
return -EIO;
}
qio_channel_set_delay(QIO_CHANNEL(sioc), false);
if (!s->client.is_unix) {
socket_set_nodelay(sock);
}
return sioc;
return sock;
}
static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp)
{
Object *obj;
QCryptoTLSCreds *creds;
obj = object_resolve_path_component(
object_get_objects_root(), id);
if (!obj) {
error_setg(errp, "No TLS credentials with id '%s'",
id);
return NULL;
}
creds = (QCryptoTLSCreds *)
object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS);
if (!creds) {
error_setg(errp, "Object with id '%s' is not TLS credentials",
id);
return NULL;
}
if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) {
error_setg(errp,
"Expecting TLS credentials with a client endpoint");
return NULL;
}
object_ref(obj);
return creds;
}
static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVNBDState *s = bs->opaque;
char *export = NULL;
QIOChannelSocket *sioc = NULL;
int result, sock;
SocketAddress *saddr;
const char *tlscredsid;
QCryptoTLSCreds *tlscreds = NULL;
const char *hostname = NULL;
int ret = -EINVAL;
/* Pop the config into our state object. Exit if invalid. */
saddr = nbd_config(s, options, &export, errp);
if (!saddr) {
goto error;
}
tlscredsid = g_strdup(qdict_get_try_str(options, "tls-creds"));
if (tlscredsid) {
qdict_del(options, "tls-creds");
tlscreds = nbd_get_tls_creds(tlscredsid, errp);
if (!tlscreds) {
goto error;
}
if (saddr->type != SOCKET_ADDRESS_KIND_INET) {
error_setg(errp, "TLS only supported over IP sockets");
goto error;
}
hostname = saddr->u.inet->host;
return -EINVAL;
}
/* establish TCP connection, return error if it fails
* TODO: Configurable retry-until-timeout behaviour.
*/
sioc = nbd_establish_connection(saddr, errp);
if (!sioc) {
ret = -ECONNREFUSED;
goto error;
sock = nbd_establish_connection(bs, saddr, errp);
qapi_free_SocketAddress(saddr);
if (sock < 0) {
g_free(export);
return sock;
}
/* NBD handshake */
ret = nbd_client_init(bs, sioc, export,
tlscreds, hostname, errp);
error:
if (sioc) {
object_unref(OBJECT(sioc));
}
if (tlscreds) {
object_unref(OBJECT(tlscreds));
}
qapi_free_SocketAddress(saddr);
result = nbd_client_init(bs, sock, export, errp);
g_free(export);
return ret;
return result;
}
static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
@@ -400,14 +342,13 @@ static void nbd_attach_aio_context(BlockDriverState *bs,
nbd_client_attach_aio_context(bs, new_context);
}
static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
static void nbd_refresh_filename(BlockDriverState *bs)
{
QDict *opts = qdict_new();
const char *path = qdict_get_try_str(options, "path");
const char *host = qdict_get_try_str(options, "host");
const char *port = qdict_get_try_str(options, "port");
const char *export = qdict_get_try_str(options, "export");
const char *tlscreds = qdict_get_try_str(options, "tls-creds");
const char *path = qdict_get_try_str(bs->options, "path");
const char *host = qdict_get_try_str(bs->options, "host");
const char *port = qdict_get_try_str(bs->options, "port");
const char *export = qdict_get_try_str(bs->options, "export");
qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("nbd")));
@@ -442,9 +383,6 @@ static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
if (export) {
qdict_put_obj(opts, "export", QOBJECT(qstring_from_str(export)));
}
if (tlscreds) {
qdict_put_obj(opts, "tls-creds", QOBJECT(qstring_from_str(tlscreds)));
}
bs->full_open_options = opts;
}

View File

@@ -22,7 +22,7 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "config-host.h"
#include <poll.h>
#include "qemu-common.h"
@@ -36,7 +36,6 @@
#include <nfsc/libnfs.h>
#define QEMU_NFS_MAX_READAHEAD_SIZE 1048576
#define QEMU_NFS_MAX_DEBUG_LEVEL 2
typedef struct NFSClient {
struct nfs_context *context;
@@ -334,17 +333,6 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
val = QEMU_NFS_MAX_READAHEAD_SIZE;
}
nfs_set_readahead(client->context, val);
#endif
#ifdef LIBNFS_FEATURE_DEBUG
} else if (!strcmp(qp->p[i].name, "debug")) {
/* limit the maximum debug level to avoid potential flooding
* of our log files. */
if (val > QEMU_NFS_MAX_DEBUG_LEVEL) {
error_report("NFS Warning: Limiting NFS debug level"
" to %d", QEMU_NFS_MAX_DEBUG_LEVEL);
val = QEMU_NFS_MAX_DEBUG_LEVEL;
}
nfs_set_debug(client->context, val);
#endif
} else {
error_setg(errp, "Unknown NFS parameter name: %s",

View File

@@ -10,7 +10,6 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "block/block_int.h"
#define NULL_OPT_LATENCY "latency-ns"

View File

@@ -27,10 +27,8 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include "qemu/bitmap.h"
#include "qapi/util.h"
@@ -63,7 +61,7 @@ typedef struct ParallelsHeader {
typedef enum ParallelsPreallocMode {
PRL_PREALLOC_MODE_FALLOCATE = 0,
PRL_PREALLOC_MODE_TRUNCATE = 1,
PRL_PREALLOC_MODE__MAX = 2,
PRL_PREALLOC_MODE_MAX = 2,
} ParallelsPreallocMode;
static const char *prealloc_mode_lookup[] = {
@@ -262,7 +260,7 @@ static coroutine_fn int parallels_co_flush_to_os(BlockDriverState *bs)
static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
BDRVParallelsState *s = bs->opaque;
int64_t offset;
@@ -275,7 +273,6 @@ static int64_t coroutine_fn parallels_co_get_block_status(BlockDriverState *bs,
return 0;
}
*file = bs->file->bs;
return (offset << BDRV_SECTOR_BITS) |
BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
}
@@ -462,7 +459,7 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
int64_t total_size, cl_size;
uint8_t tmp[BDRV_SECTOR_SIZE];
Error *local_err = NULL;
BlockBackend *file;
BlockDriverState *file;
uint32_t bat_entries, bat_sectors;
ParallelsHeader header;
int ret;
@@ -478,17 +475,14 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
return ret;
}
file = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (file == NULL) {
file = NULL;
ret = bdrv_open(&file, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return -EIO;
return ret;
}
blk_set_allow_write_beyond_eof(file, true);
ret = blk_truncate(file, 0);
ret = bdrv_truncate(file, 0);
if (ret < 0) {
goto exit;
}
@@ -512,18 +506,18 @@ static int parallels_create(const char *filename, QemuOpts *opts, Error **errp)
memset(tmp, 0, sizeof(tmp));
memcpy(tmp, &header, sizeof(header));
ret = blk_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE);
ret = bdrv_pwrite(file, 0, tmp, BDRV_SECTOR_SIZE);
if (ret < 0) {
goto exit;
}
ret = blk_write_zeroes(file, 1, bat_sectors - 1, 0);
ret = bdrv_write_zeroes(file, 1, bat_sectors - 1, 0);
if (ret < 0) {
goto exit;
}
ret = 0;
done:
blk_unref(file);
bdrv_unref(file);
return ret;
exit:
@@ -666,7 +660,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
s->prealloc_size = MAX(s->tracks, s->prealloc_size >> BDRV_SECTOR_BITS);
buf = qemu_opt_get_del(opts, PARALLELS_OPT_PREALLOC_MODE);
s->prealloc_mode = qapi_enum_parse(prealloc_mode_lookup, buf,
PRL_PREALLOC_MODE__MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
PRL_PREALLOC_MODE_MAX, PRL_PREALLOC_MODE_FALLOCATE, &local_err);
g_free(buf);
if (local_err != NULL) {
goto fail_options;

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/qapi.h"
#include "block/block_int.h"
#include "block/throttle-groups.h"
@@ -92,26 +91,6 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs, Error **errp)
info->has_iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->iops_wr_max = cfg.buckets[THROTTLE_OPS_WRITE].max;
info->has_bps_max_length = info->has_bps_max;
info->bps_max_length =
cfg.buckets[THROTTLE_BPS_TOTAL].burst_length;
info->has_bps_rd_max_length = info->has_bps_rd_max;
info->bps_rd_max_length =
cfg.buckets[THROTTLE_BPS_READ].burst_length;
info->has_bps_wr_max_length = info->has_bps_wr_max;
info->bps_wr_max_length =
cfg.buckets[THROTTLE_BPS_WRITE].burst_length;
info->has_iops_max_length = info->has_iops_max;
info->iops_max_length =
cfg.buckets[THROTTLE_OPS_TOTAL].burst_length;
info->has_iops_rd_max_length = info->has_iops_rd_max;
info->iops_rd_max_length =
cfg.buckets[THROTTLE_OPS_READ].burst_length;
info->has_iops_wr_max_length = info->has_iops_wr_max;
info->iops_wr_max_length =
cfg.buckets[THROTTLE_OPS_WRITE].burst_length;
info->has_iops_size = cfg.op_size;
info->iops_size = cfg.op_size;
@@ -231,13 +210,11 @@ void bdrv_query_image_info(BlockDriverState *bs,
Error *err = NULL;
ImageInfo *info;
aio_context_acquire(bdrv_get_aio_context(bs));
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
goto out;
return;
}
info = g_new0(ImageInfo, 1);
@@ -268,18 +245,15 @@ void bdrv_query_image_info(BlockDriverState *bs,
info->has_backing_filename = true;
bdrv_get_full_backing_filename(bs, backing_filename2, PATH_MAX, &err);
if (err) {
/* Can't reconstruct the full backing filename, so we must omit
* this field and apply a Best Effort to this query. */
error_propagate(errp, err);
qapi_free_ImageInfo(info);
g_free(backing_filename2);
backing_filename2 = NULL;
error_free(err);
err = NULL;
return;
}
/* Always report the full_backing_filename if present, even if it's the
* same as backing_filename. That they are same is useful info. */
if (backing_filename2) {
info->full_backing_filename = g_strdup(backing_filename2);
if (strcmp(backing_filename, backing_filename2) != 0) {
info->full_backing_filename =
g_strdup(backing_filename2);
info->has_full_backing_filename = true;
}
@@ -305,13 +279,10 @@ void bdrv_query_image_info(BlockDriverState *bs,
default:
error_propagate(errp, err);
qapi_free_ImageInfo(info);
goto out;
return;
}
*p_info = info;
out:
aio_context_release(bdrv_get_aio_context(bs));
}
/* @p_info will be set only on success. */
@@ -325,7 +296,7 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
info->locked = blk_dev_is_medium_locked(blk);
info->removable = blk_dev_has_removable_media(blk);
if (blk_dev_has_tray(blk)) {
if (blk_dev_has_removable_media(blk)) {
info->has_tray_open = true;
info->tray_open = blk_dev_is_tray_open(blk);
}
@@ -355,116 +326,100 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
qapi_free_BlockInfo(info);
}
static BlockStats *bdrv_query_stats(BlockBackend *blk,
const BlockDriverState *bs,
bool query_backing);
static void bdrv_query_blk_stats(BlockStats *s, BlockBackend *blk)
static BlockStats *bdrv_query_stats(const BlockDriverState *bs,
bool query_backing)
{
BlockAcctStats *stats = blk_get_stats(blk);
BlockAcctTimedStats *ts = NULL;
BlockStats *s;
s->has_device = true;
s->device = g_strdup(blk_name(blk));
s = g_malloc0(sizeof(*s));
s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
s->stats->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
if (s->stats->has_idle_time_ns) {
s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
if (bdrv_get_device_name(bs)[0]) {
s->has_device = true;
s->device = g_strdup(bdrv_get_device_name(bs));
}
s->stats->account_invalid = stats->account_invalid;
s->stats->account_failed = stats->account_failed;
while ((ts = block_acct_interval_next(stats, ts))) {
BlockDeviceTimedStatsList *timed_stats =
g_malloc0(sizeof(*timed_stats));
BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
timed_stats->next = s->stats->timed_stats;
timed_stats->value = dev_stats;
s->stats->timed_stats = timed_stats;
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
dev_stats->min_rd_latency_ns = timed_average_min(rd);
dev_stats->max_rd_latency_ns = timed_average_max(rd);
dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
dev_stats->min_wr_latency_ns = timed_average_min(wr);
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
dev_stats->avg_rd_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
}
}
static void bdrv_query_bds_stats(BlockStats *s, const BlockDriverState *bs,
bool query_backing)
{
if (bdrv_get_node_name(bs)[0]) {
s->has_node_name = true;
s->node_name = g_strdup(bdrv_get_node_name(bs));
}
s->stats = g_malloc0(sizeof(*s->stats));
if (bs->blk) {
BlockAcctStats *stats = blk_get_stats(bs->blk);
BlockAcctTimedStats *ts = NULL;
s->stats->rd_bytes = stats->nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = stats->nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = stats->nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = stats->nr_ops[BLOCK_ACCT_WRITE];
s->stats->failed_rd_operations = stats->failed_ops[BLOCK_ACCT_READ];
s->stats->failed_wr_operations = stats->failed_ops[BLOCK_ACCT_WRITE];
s->stats->failed_flush_operations = stats->failed_ops[BLOCK_ACCT_FLUSH];
s->stats->invalid_rd_operations = stats->invalid_ops[BLOCK_ACCT_READ];
s->stats->invalid_wr_operations = stats->invalid_ops[BLOCK_ACCT_WRITE];
s->stats->invalid_flush_operations =
stats->invalid_ops[BLOCK_ACCT_FLUSH];
s->stats->rd_merged = stats->merged[BLOCK_ACCT_READ];
s->stats->wr_merged = stats->merged[BLOCK_ACCT_WRITE];
s->stats->flush_operations = stats->nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = stats->total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = stats->total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = stats->total_time_ns[BLOCK_ACCT_FLUSH];
s->stats->has_idle_time_ns = stats->last_access_time_ns > 0;
if (s->stats->has_idle_time_ns) {
s->stats->idle_time_ns = block_acct_idle_time_ns(stats);
}
s->stats->account_invalid = stats->account_invalid;
s->stats->account_failed = stats->account_failed;
while ((ts = block_acct_interval_next(stats, ts))) {
BlockDeviceTimedStatsList *timed_stats =
g_malloc0(sizeof(*timed_stats));
BlockDeviceTimedStats *dev_stats = g_malloc0(sizeof(*dev_stats));
timed_stats->next = s->stats->timed_stats;
timed_stats->value = dev_stats;
s->stats->timed_stats = timed_stats;
TimedAverage *rd = &ts->latency[BLOCK_ACCT_READ];
TimedAverage *wr = &ts->latency[BLOCK_ACCT_WRITE];
TimedAverage *fl = &ts->latency[BLOCK_ACCT_FLUSH];
dev_stats->interval_length = ts->interval_length;
dev_stats->min_rd_latency_ns = timed_average_min(rd);
dev_stats->max_rd_latency_ns = timed_average_max(rd);
dev_stats->avg_rd_latency_ns = timed_average_avg(rd);
dev_stats->min_wr_latency_ns = timed_average_min(wr);
dev_stats->max_wr_latency_ns = timed_average_max(wr);
dev_stats->avg_wr_latency_ns = timed_average_avg(wr);
dev_stats->min_flush_latency_ns = timed_average_min(fl);
dev_stats->max_flush_latency_ns = timed_average_max(fl);
dev_stats->avg_flush_latency_ns = timed_average_avg(fl);
dev_stats->avg_rd_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_READ);
dev_stats->avg_wr_queue_depth =
block_acct_queue_depth(ts, BLOCK_ACCT_WRITE);
}
}
s->stats->wr_highest_offset = bs->wr_highest_offset;
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_stats(NULL, bs->file->bs, query_backing);
s->parent = bdrv_query_stats(bs->file->bs, query_backing);
}
if (query_backing && bs->backing) {
s->has_backing = true;
s->backing = bdrv_query_stats(NULL, bs->backing->bs, query_backing);
}
}
static BlockStats *bdrv_query_stats(BlockBackend *blk,
const BlockDriverState *bs,
bool query_backing)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
s->stats = g_malloc0(sizeof(*s->stats));
if (blk) {
bdrv_query_blk_stats(s, blk);
}
if (bs) {
bdrv_query_bds_stats(s, bs, query_backing);
s->backing = bdrv_query_stats(bs->backing->bs, query_backing);
}
return s;
@@ -493,38 +448,22 @@ BlockInfoList *qmp_query_block(Error **errp)
return head;
}
static bool next_query_bds(BlockBackend **blk, BlockDriverState **bs,
bool query_nodes)
{
if (query_nodes) {
*bs = bdrv_next_node(*bs);
return !!*bs;
}
*blk = blk_next(*blk);
*bs = *blk ? blk_bs(*blk) : NULL;
return !!*blk;
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
/* Just to be safe if query_nodes is not always initialized */
query_nodes = has_query_nodes && query_nodes;
while (next_query_bds(&blk, &bs, query_nodes)) {
while ((bs = query_nodes ? bdrv_next_node(bs) : bdrv_next(bs))) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk ? blk_get_aio_context(blk)
: bdrv_get_aio_context(bs);
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_stats(blk, bs, !query_nodes);
info->value = bdrv_query_stats(bs, !query_nodes);
aio_context_release(ctx);
*p_next = info;
@@ -649,7 +588,7 @@ static void dump_qlist(fprintf_function func_fprintf, void *f, int indentation,
int i = 0;
for (entry = qlist_first(list); entry; entry = qlist_next(entry), i++) {
QType type = qobject_type(entry->value);
qtype_code type = qobject_type(entry->value);
bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
const char *format = composite ? "%*s[%i]:\n" : "%*s[%i]: ";
@@ -667,7 +606,7 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
const QDictEntry *entry;
for (entry = qdict_first(dict); entry; entry = qdict_next(dict, entry)) {
QType type = qobject_type(entry->value);
qtype_code type = qobject_type(entry->value);
bool composite = (type == QTYPE_QDICT || type == QTYPE_QLIST);
const char *format = composite ? "%*s%s:\n" : "%*s%s: ";
char key[strlen(entry->key) + 1];
@@ -693,7 +632,7 @@ void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
QmpOutputVisitor *ov = qmp_output_visitor_new();
QObject *obj, *data;
visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), NULL, &info_spec,
visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
&error_abort);
obj = qmp_output_get_qobject(ov);
assert(qobject_type(obj) == QTYPE_QDICT);
@@ -737,10 +676,7 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
if (info->has_backing_filename) {
func_fprintf(f, "backing file: %s", info->backing_filename);
if (!info->has_full_backing_filename) {
func_fprintf(f, " (cannot determine actual path)");
} else if (strcmp(info->backing_filename,
info->full_backing_filename) != 0) {
if (info->has_full_backing_filename) {
func_fprintf(f, " (actual path: %s)", info->full_backing_filename);
}
func_fprintf(f, "\n");

View File

@@ -21,10 +21,8 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include <zlib.h>
#include "qapi/qmp/qerror.h"
@@ -490,7 +488,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
}
static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
BDRVQcowState *s = bs->opaque;
int index_in_cluster, n;
@@ -511,7 +509,6 @@ static int64_t coroutine_fn qcow_co_get_block_status(BlockDriverState *bs,
return BDRV_BLOCK_DATA;
}
cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
*file = bs->file->bs;
return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | cluster_offset;
}
@@ -781,7 +778,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
int flags = 0;
Error *local_err = NULL;
int ret;
BlockBackend *qcow_blk;
BlockDriverState *qcow_bs;
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
@@ -797,18 +794,15 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
goto cleanup;
}
qcow_blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (qcow_blk == NULL) {
qcow_bs = NULL;
ret = bdrv_open(&qcow_bs, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto cleanup;
}
blk_set_allow_write_beyond_eof(qcow_blk, true);
ret = blk_truncate(qcow_blk, 0);
ret = bdrv_truncate(qcow_bs, 0);
if (ret < 0) {
goto exit;
}
@@ -848,13 +842,13 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
}
/* write all the data */
ret = blk_pwrite(qcow_blk, 0, &header, sizeof(header));
ret = bdrv_pwrite(qcow_bs, 0, &header, sizeof(header));
if (ret != sizeof(header)) {
goto exit;
}
if (backing_file) {
ret = blk_pwrite(qcow_blk, sizeof(header),
ret = bdrv_pwrite(qcow_bs, sizeof(header),
backing_file, backing_filename_len);
if (ret != backing_filename_len) {
goto exit;
@@ -864,7 +858,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
tmp = g_malloc0(BDRV_SECTOR_SIZE);
for (i = 0; i < ((sizeof(uint64_t)*l1_size + BDRV_SECTOR_SIZE - 1)/
BDRV_SECTOR_SIZE); i++) {
ret = blk_pwrite(qcow_blk, header_size +
ret = bdrv_pwrite(qcow_bs, header_size +
BDRV_SECTOR_SIZE*i, tmp, BDRV_SECTOR_SIZE);
if (ret != BDRV_SECTOR_SIZE) {
g_free(tmp);
@@ -875,7 +869,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
g_free(tmp);
ret = 0;
exit:
blk_unref(qcow_blk);
bdrv_unref(qcow_bs);
cleanup:
g_free(backing_file);
return ret;

View File

@@ -23,7 +23,7 @@
*/
/* Needed for CONFIG_MADVISE */
#include "qemu/osdep.h"
#include "config-host.h"
#if defined(CONFIG_MADVISE) || defined(CONFIG_POSIX_MADVISE)
#include <sys/mman.h>
@@ -31,6 +31,7 @@
#include "block/block_int.h"
#include "qemu-common.h"
#include "qemu/osdep.h"
#include "qcow2.h"
#include "trace.h"

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <zlib.h>
#include "qemu-common.h"
@@ -1642,8 +1641,7 @@ fail:
static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
int l1_size, int64_t *visited_l1_entries,
int64_t l1_entries,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque)
BlockDriverAmendStatusCB *status_cb)
{
BDRVQcow2State *s = bs->opaque;
bool is_active_l1 = (l1_table == s->l1_table);
@@ -1669,7 +1667,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
/* unallocated */
(*visited_l1_entries)++;
if (status_cb) {
status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
status_cb(bs, *visited_l1_entries, l1_entries);
}
continue;
}
@@ -1806,7 +1804,7 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
(*visited_l1_entries)++;
if (status_cb) {
status_cb(bs, *visited_l1_entries, l1_entries, cb_opaque);
status_cb(bs, *visited_l1_entries, l1_entries);
}
}
@@ -1830,8 +1828,7 @@ fail:
* qcow2 version which doesn't yet support metadata zero clusters.
*/
int qcow2_expand_zero_clusters(BlockDriverState *bs,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque)
BlockDriverAmendStatusCB *status_cb)
{
BDRVQcow2State *s = bs->opaque;
uint64_t *l1_table = NULL;
@@ -1848,7 +1845,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
&visited_l1_entries, l1_entries,
status_cb, cb_opaque);
status_cb);
if (ret < 0) {
goto fail;
}
@@ -1884,7 +1881,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
ret = expand_zero_clusters_in_l1(bs, l1_table, s->snapshots[i].l1_size,
&visited_l1_entries, l1_entries,
status_cb, cb_opaque);
status_cb);
if (ret < 0) {
goto fail;
}

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "block/qcow2.h"
@@ -1346,9 +1345,6 @@ static int inc_refcounts(BlockDriverState *bs,
if (refcount == s->refcount_max) {
fprintf(stderr, "ERROR: overflow cluster offset=0x%" PRIx64
"\n", cluster_offset);
fprintf(stderr, "Use qemu-img amend to increase the refcount entry "
"width or qemu-img convert to create a clean copy if the "
"image cannot be opened for writing\n");
res->corruptions++;
continue;
}
@@ -2471,450 +2467,3 @@ int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
return 0;
}
/* A pointer to a function of this type is given to walk_over_reftable(). That
* function will create refblocks and pass them to a RefblockFinishOp once they
* are completed (@refblock). @refblock_empty is set if the refblock is
* completely empty.
*
* Along with the refblock, a corresponding reftable entry is passed, in the
* reftable @reftable (which may be reallocated) at @reftable_index.
*
* @allocated should be set to true if a new cluster has been allocated.
*/
typedef int (RefblockFinishOp)(BlockDriverState *bs, uint64_t **reftable,
uint64_t reftable_index, uint64_t *reftable_size,
void *refblock, bool refblock_empty,
bool *allocated, Error **errp);
/**
* This "operation" for walk_over_reftable() allocates the refblock on disk (if
* it is not empty) and inserts its offset into the new reftable. The size of
* this new reftable is increased as required.
*/
static int alloc_refblock(BlockDriverState *bs, uint64_t **reftable,
uint64_t reftable_index, uint64_t *reftable_size,
void *refblock, bool refblock_empty, bool *allocated,
Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int64_t offset;
if (!refblock_empty && reftable_index >= *reftable_size) {
uint64_t *new_reftable;
uint64_t new_reftable_size;
new_reftable_size = ROUND_UP(reftable_index + 1,
s->cluster_size / sizeof(uint64_t));
if (new_reftable_size > QCOW_MAX_REFTABLE_SIZE / sizeof(uint64_t)) {
error_setg(errp,
"This operation would make the refcount table grow "
"beyond the maximum size supported by QEMU, aborting");
return -ENOTSUP;
}
new_reftable = g_try_realloc(*reftable, new_reftable_size *
sizeof(uint64_t));
if (!new_reftable) {
error_setg(errp, "Failed to increase reftable buffer size");
return -ENOMEM;
}
memset(new_reftable + *reftable_size, 0,
(new_reftable_size - *reftable_size) * sizeof(uint64_t));
*reftable = new_reftable;
*reftable_size = new_reftable_size;
}
if (!refblock_empty && !(*reftable)[reftable_index]) {
offset = qcow2_alloc_clusters(bs, s->cluster_size);
if (offset < 0) {
error_setg_errno(errp, -offset, "Failed to allocate refblock");
return offset;
}
(*reftable)[reftable_index] = offset;
*allocated = true;
}
return 0;
}
/**
* This "operation" for walk_over_reftable() writes the refblock to disk at the
* offset specified by the new reftable's entry. It does not modify the new
* reftable or change any refcounts.
*/
static int flush_refblock(BlockDriverState *bs, uint64_t **reftable,
uint64_t reftable_index, uint64_t *reftable_size,
void *refblock, bool refblock_empty, bool *allocated,
Error **errp)
{
BDRVQcow2State *s = bs->opaque;
int64_t offset;
int ret;
if (reftable_index < *reftable_size && (*reftable)[reftable_index]) {
offset = (*reftable)[reftable_index];
ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
if (ret < 0) {
error_setg_errno(errp, -ret, "Overlap check failed");
return ret;
}
ret = bdrv_pwrite(bs->file->bs, offset, refblock, s->cluster_size);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to write refblock");
return ret;
}
} else {
assert(refblock_empty);
}
return 0;
}
/**
* This function walks over the existing reftable and every referenced refblock;
* if @new_set_refcount is non-NULL, it is called for every refcount entry to
* create an equal new entry in the passed @new_refblock. Once that
* @new_refblock is completely filled, @operation will be called.
*
* @status_cb and @cb_opaque are used for the amend operation's status callback.
* @index is the index of the walk_over_reftable() calls and @total is the total
* number of walk_over_reftable() calls per amend operation. Both are used for
* calculating the parameters for the status callback.
*
* @allocated is set to true if a new cluster has been allocated.
*/
static int walk_over_reftable(BlockDriverState *bs, uint64_t **new_reftable,
uint64_t *new_reftable_index,
uint64_t *new_reftable_size,
void *new_refblock, int new_refblock_size,
int new_refcount_bits,
RefblockFinishOp *operation, bool *allocated,
Qcow2SetRefcountFunc *new_set_refcount,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque, int index, int total,
Error **errp)
{
BDRVQcow2State *s = bs->opaque;
uint64_t reftable_index;
bool new_refblock_empty = true;
int refblock_index;
int new_refblock_index = 0;
int ret;
for (reftable_index = 0; reftable_index < s->refcount_table_size;
reftable_index++)
{
uint64_t refblock_offset = s->refcount_table[reftable_index]
& REFT_OFFSET_MASK;
status_cb(bs, (uint64_t)index * s->refcount_table_size + reftable_index,
(uint64_t)total * s->refcount_table_size, cb_opaque);
if (refblock_offset) {
void *refblock;
if (offset_into_cluster(s, refblock_offset)) {
qcow2_signal_corruption(bs, true, -1, -1, "Refblock offset %#"
PRIx64 " unaligned (reftable index: %#"
PRIx64 ")", refblock_offset,
reftable_index);
error_setg(errp,
"Image is corrupt (unaligned refblock offset)");
return -EIO;
}
ret = qcow2_cache_get(bs, s->refcount_block_cache, refblock_offset,
&refblock);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to retrieve refblock");
return ret;
}
for (refblock_index = 0; refblock_index < s->refcount_block_size;
refblock_index++)
{
uint64_t refcount;
if (new_refblock_index >= new_refblock_size) {
/* new_refblock is now complete */
ret = operation(bs, new_reftable, *new_reftable_index,
new_reftable_size, new_refblock,
new_refblock_empty, allocated, errp);
if (ret < 0) {
qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
return ret;
}
(*new_reftable_index)++;
new_refblock_index = 0;
new_refblock_empty = true;
}
refcount = s->get_refcount(refblock, refblock_index);
if (new_refcount_bits < 64 && refcount >> new_refcount_bits) {
uint64_t offset;
qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
offset = ((reftable_index << s->refcount_block_bits)
+ refblock_index) << s->cluster_bits;
error_setg(errp, "Cannot decrease refcount entry width to "
"%i bits: Cluster at offset %#" PRIx64 " has a "
"refcount of %" PRIu64, new_refcount_bits,
offset, refcount);
return -EINVAL;
}
if (new_set_refcount) {
new_set_refcount(new_refblock, new_refblock_index++,
refcount);
} else {
new_refblock_index++;
}
new_refblock_empty = new_refblock_empty && refcount == 0;
}
qcow2_cache_put(bs, s->refcount_block_cache, &refblock);
} else {
/* No refblock means every refcount is 0 */
for (refblock_index = 0; refblock_index < s->refcount_block_size;
refblock_index++)
{
if (new_refblock_index >= new_refblock_size) {
/* new_refblock is now complete */
ret = operation(bs, new_reftable, *new_reftable_index,
new_reftable_size, new_refblock,
new_refblock_empty, allocated, errp);
if (ret < 0) {
return ret;
}
(*new_reftable_index)++;
new_refblock_index = 0;
new_refblock_empty = true;
}
if (new_set_refcount) {
new_set_refcount(new_refblock, new_refblock_index++, 0);
} else {
new_refblock_index++;
}
}
}
}
if (new_refblock_index > 0) {
/* Complete the potentially existing partially filled final refblock */
if (new_set_refcount) {
for (; new_refblock_index < new_refblock_size;
new_refblock_index++)
{
new_set_refcount(new_refblock, new_refblock_index, 0);
}
}
ret = operation(bs, new_reftable, *new_reftable_index,
new_reftable_size, new_refblock, new_refblock_empty,
allocated, errp);
if (ret < 0) {
return ret;
}
(*new_reftable_index)++;
}
status_cb(bs, (uint64_t)(index + 1) * s->refcount_table_size,
(uint64_t)total * s->refcount_table_size, cb_opaque);
return 0;
}
int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque, Error **errp)
{
BDRVQcow2State *s = bs->opaque;
Qcow2GetRefcountFunc *new_get_refcount;
Qcow2SetRefcountFunc *new_set_refcount;
void *new_refblock = qemu_blockalign(bs->file->bs, s->cluster_size);
uint64_t *new_reftable = NULL, new_reftable_size = 0;
uint64_t *old_reftable, old_reftable_size, old_reftable_offset;
uint64_t new_reftable_index = 0;
uint64_t i;
int64_t new_reftable_offset = 0, allocated_reftable_size = 0;
int new_refblock_size, new_refcount_bits = 1 << refcount_order;
int old_refcount_order;
int walk_index = 0;
int ret;
bool new_allocation;
assert(s->qcow_version >= 3);
assert(refcount_order >= 0 && refcount_order <= 6);
/* see qcow2_open() */
new_refblock_size = 1 << (s->cluster_bits - (refcount_order - 3));
new_get_refcount = get_refcount_funcs[refcount_order];
new_set_refcount = set_refcount_funcs[refcount_order];
do {
int total_walks;
new_allocation = false;
/* At least we have to do this walk and the one which writes the
* refblocks; also, at least we have to do this loop here at least
* twice (normally), first to do the allocations, and second to
* determine that everything is correctly allocated, this then makes
* three walks in total */
total_walks = MAX(walk_index + 2, 3);
/* First, allocate the structures so they are present in the refcount
* structures */
ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
&new_reftable_size, NULL, new_refblock_size,
new_refcount_bits, &alloc_refblock,
&new_allocation, NULL, status_cb, cb_opaque,
walk_index++, total_walks, errp);
if (ret < 0) {
goto done;
}
new_reftable_index = 0;
if (new_allocation) {
if (new_reftable_offset) {
qcow2_free_clusters(bs, new_reftable_offset,
allocated_reftable_size * sizeof(uint64_t),
QCOW2_DISCARD_NEVER);
}
new_reftable_offset = qcow2_alloc_clusters(bs, new_reftable_size *
sizeof(uint64_t));
if (new_reftable_offset < 0) {
error_setg_errno(errp, -new_reftable_offset,
"Failed to allocate the new reftable");
ret = new_reftable_offset;
goto done;
}
allocated_reftable_size = new_reftable_size;
}
} while (new_allocation);
/* Second, write the new refblocks */
ret = walk_over_reftable(bs, &new_reftable, &new_reftable_index,
&new_reftable_size, new_refblock,
new_refblock_size, new_refcount_bits,
&flush_refblock, &new_allocation, new_set_refcount,
status_cb, cb_opaque, walk_index, walk_index + 1,
errp);
if (ret < 0) {
goto done;
}
assert(!new_allocation);
/* Write the new reftable */
ret = qcow2_pre_write_overlap_check(bs, 0, new_reftable_offset,
new_reftable_size * sizeof(uint64_t));
if (ret < 0) {
error_setg_errno(errp, -ret, "Overlap check failed");
goto done;
}
for (i = 0; i < new_reftable_size; i++) {
cpu_to_be64s(&new_reftable[i]);
}
ret = bdrv_pwrite(bs->file->bs, new_reftable_offset, new_reftable,
new_reftable_size * sizeof(uint64_t));
for (i = 0; i < new_reftable_size; i++) {
be64_to_cpus(&new_reftable[i]);
}
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to write the new reftable");
goto done;
}
/* Empty the refcount cache */
ret = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret < 0) {
error_setg_errno(errp, -ret, "Failed to flush the refblock cache");
goto done;
}
/* Update the image header to point to the new reftable; this only updates
* the fields which are relevant to qcow2_update_header(); other fields
* such as s->refcount_table or s->refcount_bits stay stale for now
* (because we have to restore everything if qcow2_update_header() fails) */
old_refcount_order = s->refcount_order;
old_reftable_size = s->refcount_table_size;
old_reftable_offset = s->refcount_table_offset;
s->refcount_order = refcount_order;
s->refcount_table_size = new_reftable_size;
s->refcount_table_offset = new_reftable_offset;
ret = qcow2_update_header(bs);
if (ret < 0) {
s->refcount_order = old_refcount_order;
s->refcount_table_size = old_reftable_size;
s->refcount_table_offset = old_reftable_offset;
error_setg_errno(errp, -ret, "Failed to update the qcow2 header");
goto done;
}
/* Now update the rest of the in-memory information */
old_reftable = s->refcount_table;
s->refcount_table = new_reftable;
s->refcount_bits = 1 << refcount_order;
s->refcount_max = UINT64_C(1) << (s->refcount_bits - 1);
s->refcount_max += s->refcount_max - 1;
s->refcount_block_bits = s->cluster_bits - (refcount_order - 3);
s->refcount_block_size = 1 << s->refcount_block_bits;
s->get_refcount = new_get_refcount;
s->set_refcount = new_set_refcount;
/* For cleaning up all old refblocks and the old reftable below the "done"
* label */
new_reftable = old_reftable;
new_reftable_size = old_reftable_size;
new_reftable_offset = old_reftable_offset;
done:
if (new_reftable) {
/* On success, new_reftable actually points to the old reftable (and
* new_reftable_size is the old reftable's size); but that is just
* fine */
for (i = 0; i < new_reftable_size; i++) {
uint64_t offset = new_reftable[i] & REFT_OFFSET_MASK;
if (offset) {
qcow2_free_clusters(bs, offset, s->cluster_size,
QCOW2_DISCARD_OTHER);
}
}
g_free(new_reftable);
if (new_reftable_offset > 0) {
qcow2_free_clusters(bs, new_reftable_offset,
new_reftable_size * sizeof(uint64_t),
QCOW2_DISCARD_OTHER);
}
}
qemu_vfree(new_refblock);
return ret;
}

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "block/qcow2.h"

View File

@@ -21,10 +21,8 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include <zlib.h>
#include "block/qcow2.h"
@@ -1142,7 +1140,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
}
/* Clear unknown autoclear feature bits */
if (!bs->read_only && !(flags & BDRV_O_INACTIVE) && s->autoclear_features) {
if (!bs->read_only && !(flags & BDRV_O_INCOMING) && s->autoclear_features) {
s->autoclear_features = 0;
ret = qcow2_update_header(bs);
if (ret < 0) {
@@ -1155,7 +1153,7 @@ static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
qemu_co_mutex_init(&s->lock);
/* Repair image if dirty */
if (!(flags & (BDRV_O_CHECK | BDRV_O_INACTIVE)) && !bs->read_only &&
if (!(flags & (BDRV_O_CHECK | BDRV_O_INCOMING)) && !bs->read_only &&
(s->incompatible_features & QCOW2_INCOMPAT_DIRTY)) {
BdrvCheckResult result = {0};
@@ -1284,54 +1282,8 @@ static void qcow2_reopen_abort(BDRVReopenState *state)
g_free(state->opaque);
}
static void qcow2_join_options(QDict *options, QDict *old_options)
{
bool has_new_overlap_template =
qdict_haskey(options, QCOW2_OPT_OVERLAP) ||
qdict_haskey(options, QCOW2_OPT_OVERLAP_TEMPLATE);
bool has_new_total_cache_size =
qdict_haskey(options, QCOW2_OPT_CACHE_SIZE);
bool has_all_cache_options;
/* New overlap template overrides all old overlap options */
if (has_new_overlap_template) {
qdict_del(old_options, QCOW2_OPT_OVERLAP);
qdict_del(old_options, QCOW2_OPT_OVERLAP_TEMPLATE);
qdict_del(old_options, QCOW2_OPT_OVERLAP_MAIN_HEADER);
qdict_del(old_options, QCOW2_OPT_OVERLAP_ACTIVE_L1);
qdict_del(old_options, QCOW2_OPT_OVERLAP_ACTIVE_L2);
qdict_del(old_options, QCOW2_OPT_OVERLAP_REFCOUNT_TABLE);
qdict_del(old_options, QCOW2_OPT_OVERLAP_REFCOUNT_BLOCK);
qdict_del(old_options, QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE);
qdict_del(old_options, QCOW2_OPT_OVERLAP_INACTIVE_L1);
qdict_del(old_options, QCOW2_OPT_OVERLAP_INACTIVE_L2);
}
/* New total cache size overrides all old options */
if (qdict_haskey(options, QCOW2_OPT_CACHE_SIZE)) {
qdict_del(old_options, QCOW2_OPT_L2_CACHE_SIZE);
qdict_del(old_options, QCOW2_OPT_REFCOUNT_CACHE_SIZE);
}
qdict_join(options, old_options, false);
/*
* If after merging all cache size options are set, an old total size is
* overwritten. Do keep all options, however, if all three are new. The
* resulting error message is what we want to happen.
*/
has_all_cache_options =
qdict_haskey(options, QCOW2_OPT_CACHE_SIZE) ||
qdict_haskey(options, QCOW2_OPT_L2_CACHE_SIZE) ||
qdict_haskey(options, QCOW2_OPT_REFCOUNT_CACHE_SIZE);
if (has_all_cache_options && !has_new_total_cache_size) {
qdict_del(options, QCOW2_OPT_CACHE_SIZE);
}
}
static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
BDRVQcow2State *s = bs->opaque;
uint64_t cluster_offset;
@@ -1350,7 +1302,6 @@ static int64_t coroutine_fn qcow2_co_get_block_status(BlockDriverState *bs,
!s->cipher) {
index_in_cluster = sector_num & (s->cluster_sectors - 1);
cluster_offset |= (index_in_cluster << BDRV_SECTOR_BITS);
*file = bs->file->bs;
status |= BDRV_BLOCK_OFFSET_VALID | cluster_offset;
}
if (ret == QCOW2_CLUSTER_ZERO) {
@@ -1688,32 +1639,6 @@ fail:
return ret;
}
static int qcow2_inactivate(BlockDriverState *bs)
{
BDRVQcow2State *s = bs->opaque;
int ret, result = 0;
ret = qcow2_cache_flush(bs, s->l2_table_cache);
if (ret) {
result = ret;
error_report("Failed to flush the L2 table cache: %s",
strerror(-ret));
}
ret = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret) {
result = ret;
error_report("Failed to flush the refcount block cache: %s",
strerror(-ret));
}
if (result == 0) {
qcow2_mark_clean(bs);
}
return result;
}
static void qcow2_close(BlockDriverState *bs)
{
BDRVQcow2State *s = bs->opaque;
@@ -1721,8 +1646,24 @@ static void qcow2_close(BlockDriverState *bs)
/* else pre-write overlap checks in cache_destroy may crash */
s->l1_table = NULL;
if (!(s->flags & BDRV_O_INACTIVE)) {
qcow2_inactivate(bs);
if (!(bs->open_flags & BDRV_O_INCOMING)) {
int ret1, ret2;
ret1 = qcow2_cache_flush(bs, s->l2_table_cache);
ret2 = qcow2_cache_flush(bs, s->refcount_block_cache);
if (ret1) {
error_report("Failed to flush the L2 table cache: %s",
strerror(-ret1));
}
if (ret2) {
error_report("Failed to flush the refcount block cache: %s",
strerror(-ret2));
}
if (!ret1 && !ret2) {
qcow2_mark_clean(bs);
}
}
cache_clean_timer_del(bs);
@@ -1766,24 +1707,21 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
bdrv_invalidate_cache(bs->file->bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
bs->drv = NULL;
return;
}
memset(s, 0, sizeof(BDRVQcow2State));
options = qdict_clone_shallow(bs->options);
flags &= ~BDRV_O_INACTIVE;
ret = qcow2_open(bs, options, flags, &local_err);
QDECREF(options);
if (local_err) {
error_propagate(errp, local_err);
error_prepend(errp, "Could not reopen qcow2 layer: ");
bs->drv = NULL;
error_setg(errp, "Could not reopen qcow2 layer: %s",
error_get_pretty(local_err));
error_free(local_err);
return;
} else if (ret < 0) {
error_setg_errno(errp, -ret, "Could not reopen qcow2 layer");
bs->drv = NULL;
return;
}
@@ -1911,33 +1849,31 @@ int qcow2_update_header(BlockDriverState *bs)
}
/* Feature table */
if (s->qcow_version >= 3) {
Qcow2Feature features[] = {
{
.type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
.bit = QCOW2_INCOMPAT_DIRTY_BITNR,
.name = "dirty bit",
},
{
.type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
.bit = QCOW2_INCOMPAT_CORRUPT_BITNR,
.name = "corrupt bit",
},
{
.type = QCOW2_FEAT_TYPE_COMPATIBLE,
.bit = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
.name = "lazy refcounts",
},
};
Qcow2Feature features[] = {
{
.type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
.bit = QCOW2_INCOMPAT_DIRTY_BITNR,
.name = "dirty bit",
},
{
.type = QCOW2_FEAT_TYPE_INCOMPATIBLE,
.bit = QCOW2_INCOMPAT_CORRUPT_BITNR,
.name = "corrupt bit",
},
{
.type = QCOW2_FEAT_TYPE_COMPATIBLE,
.bit = QCOW2_COMPAT_LAZY_REFCOUNTS_BITNR,
.name = "lazy refcounts",
},
};
ret = header_ext_add(buf, QCOW2_EXT_MAGIC_FEATURE_TABLE,
features, sizeof(features), buflen);
if (ret < 0) {
goto fail;
}
buf += ret;
buflen -= ret;
ret = header_ext_add(buf, QCOW2_EXT_MAGIC_FEATURE_TABLE,
features, sizeof(features), buflen);
if (ret < 0) {
goto fail;
}
buf += ret;
buflen -= ret;
/* Keep unknown header extensions */
QLIST_FOREACH(uext, &s->unknown_header_ext, next) {
@@ -2098,7 +2034,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
* 2 GB for 64k clusters, and we don't want to have a 2 GB initial file
* size for any qcow2 image.
*/
BlockBackend *blk;
BlockDriverState* bs;
QCowHeader *header;
uint64_t* refcount_table;
Error *local_err = NULL;
@@ -2173,16 +2109,14 @@ static int qcow2_create2(const char *filename, int64_t total_size,
return ret;
}
blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
bs = NULL;
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return -EIO;
return ret;
}
blk_set_allow_write_beyond_eof(blk, true);
/* Write the header */
QEMU_BUILD_BUG_ON((1 << MIN_CLUSTER_BITS) < sizeof(*header));
header = g_malloc0(cluster_size);
@@ -2210,7 +2144,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
cpu_to_be64(QCOW2_COMPAT_LAZY_REFCOUNTS);
}
ret = blk_pwrite(blk, 0, header, cluster_size);
ret = bdrv_pwrite(bs, 0, header, cluster_size);
g_free(header);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not write qcow2 header");
@@ -2220,7 +2154,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
/* Write a refcount table with one refcount block */
refcount_table = g_malloc0(2 * cluster_size);
refcount_table[0] = cpu_to_be64(2 * cluster_size);
ret = blk_pwrite(blk, cluster_size, refcount_table, 2 * cluster_size);
ret = bdrv_pwrite(bs, cluster_size, refcount_table, 2 * cluster_size);
g_free(refcount_table);
if (ret < 0) {
@@ -2228,8 +2162,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
goto out;
}
blk_unref(blk);
blk = NULL;
bdrv_unref(bs);
bs = NULL;
/*
* And now open the image and make it consistent first (i.e. increase the
@@ -2238,16 +2172,15 @@ static int qcow2_create2(const char *filename, int64_t total_size,
*/
options = qdict_new();
qdict_put(options, "driver", qstring_from_str("qcow2"));
blk = blk_new_open("image-qcow2", filename, NULL, options,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
&local_err);
if (blk == NULL) {
ret = bdrv_open(&bs, filename, NULL, options,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto out;
}
ret = qcow2_alloc_clusters(blk_bs(blk), 3 * cluster_size);
ret = qcow2_alloc_clusters(bs, 3 * cluster_size);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not allocate clusters for qcow2 "
"header and refcount table");
@@ -2258,15 +2191,8 @@ static int qcow2_create2(const char *filename, int64_t total_size,
abort();
}
/* Create a full header (including things like feature table) */
ret = qcow2_update_header(blk_bs(blk));
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not update qcow2 header");
goto out;
}
/* Okay, now that we have a valid image, let's give it the right size */
ret = blk_truncate(blk, total_size);
ret = bdrv_truncate(bs, total_size);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not resize image");
goto out;
@@ -2274,7 +2200,7 @@ static int qcow2_create2(const char *filename, int64_t total_size,
/* Want a backing file? There you go.*/
if (backing_file) {
ret = bdrv_change_backing_file(blk_bs(blk), backing_file, backing_format);
ret = bdrv_change_backing_file(bs, backing_file, backing_format);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not assign backing file '%s' "
"with format '%s'", backing_file, backing_format);
@@ -2284,9 +2210,9 @@ static int qcow2_create2(const char *filename, int64_t total_size,
/* And if we're supposed to preallocate metadata, do that now */
if (prealloc != PREALLOC_MODE_OFF) {
BDRVQcow2State *s = blk_bs(blk)->opaque;
BDRVQcow2State *s = bs->opaque;
qemu_co_mutex_lock(&s->lock);
ret = preallocate(blk_bs(blk));
ret = preallocate(bs);
qemu_co_mutex_unlock(&s->lock);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not preallocate metadata");
@@ -2294,25 +2220,24 @@ static int qcow2_create2(const char *filename, int64_t total_size,
}
}
blk_unref(blk);
blk = NULL;
bdrv_unref(bs);
bs = NULL;
/* Reopen the image without BDRV_O_NO_FLUSH to flush it before returning */
options = qdict_new();
qdict_put(options, "driver", qstring_from_str("qcow2"));
blk = blk_new_open("image-flush", filename, NULL, options,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
&local_err);
if (blk == NULL) {
ret = bdrv_open(&bs, filename, NULL, options,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_BACKING,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EIO;
goto out;
}
ret = 0;
out:
if (blk) {
blk_unref(blk);
if (bs) {
bdrv_unref(bs);
}
return ret;
}
@@ -2344,7 +2269,7 @@ static int qcow2_create(const char *filename, QemuOpts *opts, Error **errp)
DEFAULT_CLUSTER_SIZE);
buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
@@ -2832,10 +2757,6 @@ static ImageInfoSpecific *qcow2_get_specific_info(BlockDriverState *bs)
.has_corrupt = true,
.refcount_bits = s->refcount_bits,
};
} else {
/* if this assertion fails, this probably means a new version was
* added without having it covered here */
assert(false);
}
return spec_info;
@@ -2903,7 +2824,7 @@ static int qcow2_load_vmstate(BlockDriverState *bs, uint8_t *buf,
* have to be removed.
*/
static int qcow2_downgrade(BlockDriverState *bs, int target_version,
BlockDriverAmendStatusCB *status_cb, void *cb_opaque)
BlockDriverAmendStatusCB *status_cb)
{
BDRVQcow2State *s = bs->opaque;
int current_version = s->qcow_version;
@@ -2918,7 +2839,13 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
}
if (s->refcount_order != 4) {
error_report("compat=0.10 requires refcount_bits=16");
/* we would have to convert the image to a refcount_order == 4 image
* here; however, since qemu (at the time of writing this) does not
* support anything different than 4 anyway, there is no point in doing
* so right now; however, we should error out (if qemu supports this in
* the future and this code has not been adapted) */
error_report("qcow2_downgrade: Image refcount orders other than 4 are "
"currently not supported.");
return -ENOTSUP;
}
@@ -2946,7 +2873,7 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
/* clearing autoclear features is trivial */
s->autoclear_features = 0;
ret = qcow2_expand_zero_clusters(bs, status_cb, cb_opaque);
ret = qcow2_expand_zero_clusters(bs, status_cb);
if (ret < 0) {
return ret;
}
@@ -2960,79 +2887,8 @@ static int qcow2_downgrade(BlockDriverState *bs, int target_version,
return 0;
}
typedef enum Qcow2AmendOperation {
/* This is the value Qcow2AmendHelperCBInfo::last_operation will be
* statically initialized to so that the helper CB can discern the first
* invocation from an operation change */
QCOW2_NO_OPERATION = 0,
QCOW2_CHANGING_REFCOUNT_ORDER,
QCOW2_DOWNGRADING,
} Qcow2AmendOperation;
typedef struct Qcow2AmendHelperCBInfo {
/* The code coordinating the amend operations should only modify
* these four fields; the rest will be managed by the CB */
BlockDriverAmendStatusCB *original_status_cb;
void *original_cb_opaque;
Qcow2AmendOperation current_operation;
/* Total number of operations to perform (only set once) */
int total_operations;
/* The following fields are managed by the CB */
/* Number of operations completed */
int operations_completed;
/* Cumulative offset of all completed operations */
int64_t offset_completed;
Qcow2AmendOperation last_operation;
int64_t last_work_size;
} Qcow2AmendHelperCBInfo;
static void qcow2_amend_helper_cb(BlockDriverState *bs,
int64_t operation_offset,
int64_t operation_work_size, void *opaque)
{
Qcow2AmendHelperCBInfo *info = opaque;
int64_t current_work_size;
int64_t projected_work_size;
if (info->current_operation != info->last_operation) {
if (info->last_operation != QCOW2_NO_OPERATION) {
info->offset_completed += info->last_work_size;
info->operations_completed++;
}
info->last_operation = info->current_operation;
}
assert(info->total_operations > 0);
assert(info->operations_completed < info->total_operations);
info->last_work_size = operation_work_size;
current_work_size = info->offset_completed + operation_work_size;
/* current_work_size is the total work size for (operations_completed + 1)
* operations (which includes this one), so multiply it by the number of
* operations not covered and divide it by the number of operations
* covered to get a projection for the operations not covered */
projected_work_size = current_work_size * (info->total_operations -
info->operations_completed - 1)
/ (info->operations_completed + 1);
info->original_status_cb(bs, info->offset_completed + operation_offset,
current_work_size + projected_work_size,
info->original_cb_opaque);
}
static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque)
BlockDriverAmendStatusCB *status_cb)
{
BDRVQcow2State *s = bs->opaque;
int old_version = s->qcow_version, new_version = old_version;
@@ -3042,10 +2898,8 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
const char *compat = NULL;
uint64_t cluster_size = s->cluster_size;
bool encrypt;
int refcount_bits = s->refcount_bits;
int ret;
QemuOptDesc *desc = opts->list->desc;
Qcow2AmendHelperCBInfo helper_cb_info;
while (desc && desc->name) {
if (!qemu_opt_find(opts, desc->name)) {
@@ -3063,11 +2917,11 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
} else if (!strcmp(compat, "1.1")) {
new_version = 3;
} else {
error_report("Unknown compatibility level %s", compat);
fprintf(stderr, "Unknown compatibility level %s.\n", compat);
return -EINVAL;
}
} else if (!strcmp(desc->name, BLOCK_OPT_PREALLOC)) {
error_report("Cannot change preallocation mode");
fprintf(stderr, "Cannot change preallocation mode.\n");
return -ENOTSUP;
} else if (!strcmp(desc->name, BLOCK_OPT_SIZE)) {
new_size = qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 0);
@@ -3080,74 +2934,47 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
!!s->cipher);
if (encrypt != !!s->cipher) {
error_report("Changing the encryption flag is not supported");
fprintf(stderr, "Changing the encryption flag is not "
"supported.\n");
return -ENOTSUP;
}
} else if (!strcmp(desc->name, BLOCK_OPT_CLUSTER_SIZE)) {
cluster_size = qemu_opt_get_size(opts, BLOCK_OPT_CLUSTER_SIZE,
cluster_size);
if (cluster_size != s->cluster_size) {
error_report("Changing the cluster size is not supported");
fprintf(stderr, "Changing the cluster size is not "
"supported.\n");
return -ENOTSUP;
}
} else if (!strcmp(desc->name, BLOCK_OPT_LAZY_REFCOUNTS)) {
lazy_refcounts = qemu_opt_get_bool(opts, BLOCK_OPT_LAZY_REFCOUNTS,
lazy_refcounts);
} else if (!strcmp(desc->name, BLOCK_OPT_REFCOUNT_BITS)) {
refcount_bits = qemu_opt_get_number(opts, BLOCK_OPT_REFCOUNT_BITS,
refcount_bits);
if (refcount_bits <= 0 || refcount_bits > 64 ||
!is_power_of_2(refcount_bits))
{
error_report("Refcount width must be a power of two and may "
"not exceed 64 bits");
return -EINVAL;
}
error_report("Cannot change refcount entry width");
return -ENOTSUP;
} else {
/* if this point is reached, this probably means a new option was
/* if this assertion fails, this probably means a new option was
* added without having it covered here */
abort();
assert(false);
}
desc++;
}
helper_cb_info = (Qcow2AmendHelperCBInfo){
.original_status_cb = status_cb,
.original_cb_opaque = cb_opaque,
.total_operations = (new_version < old_version)
+ (s->refcount_bits != refcount_bits)
};
/* Upgrade first (some features may require compat=1.1) */
if (new_version > old_version) {
s->qcow_version = new_version;
ret = qcow2_update_header(bs);
if (ret < 0) {
s->qcow_version = old_version;
return ret;
}
}
if (s->refcount_bits != refcount_bits) {
int refcount_order = ctz32(refcount_bits);
Error *local_error = NULL;
if (new_version < 3 && refcount_bits != 16) {
error_report("Different refcount widths than 16 bits require "
"compatibility level 1.1 or above (use compat=1.1 or "
"greater)");
return -EINVAL;
}
helper_cb_info.current_operation = QCOW2_CHANGING_REFCOUNT_ORDER;
ret = qcow2_change_refcount_order(bs, refcount_order,
&qcow2_amend_helper_cb,
&helper_cb_info, &local_error);
if (ret < 0) {
error_report_err(local_error);
return ret;
if (new_version != old_version) {
if (new_version > old_version) {
/* Upgrade */
s->qcow_version = new_version;
ret = qcow2_update_header(bs);
if (ret < 0) {
s->qcow_version = old_version;
return ret;
}
} else {
ret = qcow2_downgrade(bs, new_version, status_cb);
if (ret < 0) {
return ret;
}
}
}
@@ -3162,9 +2989,9 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
if (s->use_lazy_refcounts != lazy_refcounts) {
if (lazy_refcounts) {
if (new_version < 3) {
error_report("Lazy refcounts only supported with compatibility "
"level 1.1 and above (use compat=1.1 or greater)");
if (s->qcow_version < 3) {
fprintf(stderr, "Lazy refcounts only supported with compatibility "
"level 1.1 and above (use compat=1.1 or greater)\n");
return -EINVAL;
}
s->compatible_features |= QCOW2_COMPAT_LAZY_REFCOUNTS;
@@ -3198,16 +3025,6 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
}
}
/* Downgrade last (so unsupported features can be removed before) */
if (new_version < old_version) {
helper_cb_info.current_operation = QCOW2_DOWNGRADING;
ret = qcow2_downgrade(bs, new_version, &qcow2_amend_helper_cb,
&helper_cb_info);
if (ret < 0) {
return ret;
}
}
return 0;
}
@@ -3328,7 +3145,6 @@ BlockDriver bdrv_qcow2 = {
.bdrv_reopen_prepare = qcow2_reopen_prepare,
.bdrv_reopen_commit = qcow2_reopen_commit,
.bdrv_reopen_abort = qcow2_reopen_abort,
.bdrv_join_options = qcow2_join_options,
.bdrv_create = qcow2_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_co_get_block_status = qcow2_co_get_block_status,
@@ -3360,7 +3176,6 @@ BlockDriver bdrv_qcow2 = {
.bdrv_refresh_limits = qcow2_refresh_limits,
.bdrv_invalidate_cache = qcow2_invalidate_cache,
.bdrv_inactivate = qcow2_inactivate,
.create_opts = &qcow2_create_opts,
.bdrv_check = qcow2_check,

View File

@@ -529,10 +529,6 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
int qcow2_pre_write_overlap_check(BlockDriverState *bs, int ign, int64_t offset,
int64_t size);
int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque, Error **errp);
/* qcow2-cluster.c functions */
int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
bool exact_size);
@@ -557,8 +553,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
int qcow2_expand_zero_clusters(BlockDriverState *bs,
BlockDriverAmendStatusCB *status_cb,
void *cb_opaque);
BlockDriverAmendStatusCB *status_cb);
/* qcow2-snapshot.c functions */
int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);

View File

@@ -11,7 +11,6 @@
*
*/
#include "qemu/osdep.h"
#include "qed.h"
typedef struct {

View File

@@ -12,7 +12,6 @@
*
*/
#include "qemu/osdep.h"
#include "qed.h"
/**

View File

@@ -11,7 +11,6 @@
*
*/
#include "qemu/osdep.h"
#include "qed.h"
void *gencb_alloc(size_t len, BlockCompletionFunc *cb, void *opaque)

View File

@@ -50,7 +50,6 @@
* table will be deleted in favor of the existing cache entry.
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "qed.h"

View File

@@ -12,7 +12,6 @@
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "qed.h"

View File

@@ -12,13 +12,11 @@
*
*/
#include "qemu/osdep.h"
#include "qemu/timer.h"
#include "trace.h"
#include "qed.h"
#include "qapi/qmp/qerror.h"
#include "migration/migration.h"
#include "sysemu/block-backend.h"
static const AIOCBInfo qed_aiocb_info = {
.aiocb_size = sizeof(QEDAIOCB),
@@ -479,7 +477,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
* feature is no longer valid.
*/
if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
!bdrv_is_read_only(bs->file->bs) && !(flags & BDRV_O_INACTIVE)) {
!bdrv_is_read_only(bs->file->bs) && !(flags & BDRV_O_INCOMING)) {
s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
ret = qed_write_header_sync(s);
@@ -507,7 +505,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
* aid data recovery from an otherwise inconsistent image.
*/
if (!bdrv_is_read_only(bs->file->bs) &&
!(flags & BDRV_O_INACTIVE)) {
!(flags & BDRV_O_INCOMING)) {
BdrvCheckResult result = {0};
ret = qed_check(s, &result, true);
@@ -581,7 +579,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
size_t l1_size = header.cluster_size * header.table_size;
Error *local_err = NULL;
int ret = 0;
BlockBackend *blk;
BlockDriverState *bs;
ret = bdrv_create_file(filename, opts, &local_err);
if (ret < 0) {
@@ -589,18 +587,17 @@ static int qed_create(const char *filename, uint32_t cluster_size,
return ret;
}
blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
bs = NULL;
ret = bdrv_open(&bs, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return -EIO;
return ret;
}
blk_set_allow_write_beyond_eof(blk, true);
/* File must start empty and grow, check truncate is supported */
ret = blk_truncate(blk, 0);
ret = bdrv_truncate(bs, 0);
if (ret < 0) {
goto out;
}
@@ -616,18 +613,18 @@ static int qed_create(const char *filename, uint32_t cluster_size,
}
qed_header_cpu_to_le(&header, &le_header);
ret = blk_pwrite(blk, 0, &le_header, sizeof(le_header));
ret = bdrv_pwrite(bs, 0, &le_header, sizeof(le_header));
if (ret < 0) {
goto out;
}
ret = blk_pwrite(blk, sizeof(le_header), backing_file,
header.backing_filename_size);
ret = bdrv_pwrite(bs, sizeof(le_header), backing_file,
header.backing_filename_size);
if (ret < 0) {
goto out;
}
l1_table = g_malloc0(l1_size);
ret = blk_pwrite(blk, header.l1_table_offset, l1_table, l1_size);
ret = bdrv_pwrite(bs, header.l1_table_offset, l1_table, l1_size);
if (ret < 0) {
goto out;
}
@@ -635,7 +632,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
ret = 0; /* success */
out:
g_free(l1_table);
blk_unref(blk);
bdrv_unref(bs);
return ret;
}
@@ -695,7 +692,6 @@ typedef struct {
uint64_t pos;
int64_t status;
int *pnum;
BlockDriverState **file;
} QEDIsAllocatedCB;
static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t len)
@@ -707,7 +703,6 @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l
case QED_CLUSTER_FOUND:
offset |= qed_offset_into_cluster(s, cb->pos);
cb->status = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
*cb->file = cb->bs->file->bs;
break;
case QED_CLUSTER_ZERO:
cb->status = BDRV_BLOCK_ZERO;
@@ -729,8 +724,7 @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l
static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
BDRVQEDState *s = bs->opaque;
size_t len = (size_t)nb_sectors * BDRV_SECTOR_SIZE;
@@ -739,7 +733,6 @@ static int64_t coroutine_fn bdrv_qed_co_get_block_status(BlockDriverState *bs,
.pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE,
.status = BDRV_BLOCK_OFFSET_MASK,
.pnum = pnum,
.file = file,
};
QEDRequest request = { .l2_table = NULL };
@@ -1618,8 +1611,9 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)
memset(s, 0, sizeof(BDRVQEDState));
ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_prepend(errp, "Could not reopen qed layer: ");
error_setg(errp, "Could not reopen qed layer: %s",
error_get_pretty(local_err));
error_free(local_err);
return;
} else if (ret < 0) {
error_setg_errno(errp, -ret, "Could not reopen qed layer");

View File

@@ -13,7 +13,6 @@
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "block/block_int.h"
#include "qapi/qmp/qbool.h"
#include "qapi/qmp/qdict.h"
@@ -215,16 +214,14 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
return acb;
}
static void quorum_report_bad(QuorumOpType type, uint64_t sector_num,
int nb_sectors, char *node_name, int ret)
static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
{
const char *msg = NULL;
if (ret < 0) {
msg = strerror(-ret);
}
qapi_event_send_quorum_report_bad(type, !!msg, msg, node_name,
sector_num, nb_sectors, &error_abort);
qapi_event_send_quorum_report_bad(!!msg, msg, node_name,
acb->sector_num, acb->nb_sectors, &error_abort);
}
static void quorum_report_failure(QuorumAIOCB *acb)
@@ -284,13 +281,11 @@ static void quorum_aio_cb(void *opaque, int ret)
QuorumChildRequest *sacb = opaque;
QuorumAIOCB *acb = sacb->parent;
BDRVQuorumState *s = acb->common.bs->opaque;
QuorumOpType type;
bool rewrite = false;
if (acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO) {
/* We try to read next child in FIFO order if we fail to read */
if (ret < 0 && (acb->child_iter + 1) < s->num_children) {
acb->child_iter++;
if (ret < 0 && ++acb->child_iter < s->num_children) {
read_fifo_child(acb);
return;
}
@@ -303,14 +298,12 @@ static void quorum_aio_cb(void *opaque, int ret)
return;
}
type = acb->is_read ? QUORUM_OP_TYPE_READ : QUORUM_OP_TYPE_WRITE;
sacb->ret = ret;
acb->count++;
if (ret == 0) {
acb->success_count++;
} else {
quorum_report_bad(type, acb->sector_num, acb->nb_sectors,
sacb->aiocb->bs->node_name, ret);
quorum_report_bad(acb, sacb->aiocb->bs->node_name, ret);
}
assert(acb->count <= s->num_children);
assert(acb->success_count <= s->num_children);
@@ -343,9 +336,7 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
continue;
}
QLIST_FOREACH(item, &version->items, next) {
quorum_report_bad(QUORUM_OP_TYPE_READ, acb->sector_num,
acb->nb_sectors,
s->children[item->index]->bs->node_name, 0);
quorum_report_bad(acb, s->children[item->index]->bs->node_name, 0);
}
}
}
@@ -769,30 +760,19 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
QuorumVoteValue result_value;
int i;
int result = 0;
int success_count = 0;
QLIST_INIT(&error_votes.vote_list);
error_votes.compare = quorum_64bits_compare;
for (i = 0; i < s->num_children; i++) {
result = bdrv_co_flush(s->children[i]->bs);
if (result) {
quorum_report_bad(QUORUM_OP_TYPE_FLUSH, 0,
bdrv_nb_sectors(s->children[i]->bs),
s->children[i]->bs->node_name, result);
result_value.l = result;
quorum_count_vote(&error_votes, &result_value, i);
} else {
success_count++;
}
result_value.l = result;
quorum_count_vote(&error_votes, &result_value, i);
}
if (success_count >= s->threshold) {
result = 0;
} else {
winner = quorum_get_vote_winner(&error_votes);
result = winner->value.l;
}
winner = quorum_get_vote_winner(&error_votes);
result = winner->value.l;
quorum_free_vote_list(&error_votes);
return result;
@@ -869,7 +849,7 @@ static int parse_read_pattern(const char *opt)
return QUORUM_READ_PATTERN_QUORUM;
}
for (i = 0; i < QUORUM_READ_PATTERN__MAX; i++) {
for (i = 0; i < QUORUM_READ_PATTERN_MAX; i++) {
if (!strcmp(opt, QuorumReadPattern_lookup[i])) {
return i;
}
@@ -1019,7 +999,7 @@ static void quorum_attach_aio_context(BlockDriverState *bs,
}
}
static void quorum_refresh_filename(BlockDriverState *bs, QDict *options)
static void quorum_refresh_filename(BlockDriverState *bs)
{
BDRVQuorumState *s = bs->opaque;
QDict *opts;

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qemu/timer.h"
@@ -52,6 +51,8 @@
#include <sys/dkio.h>
#endif
#ifdef __linux__
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/ioctl.h>
#include <sys/param.h>
#include <linux/cdrom.h>
@@ -499,17 +500,21 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
goto fail;
}
if (!s->use_aio && (bdrv_flags & BDRV_O_NATIVE_AIO)) {
error_setg(errp, "aio=native was specified, but it requires "
"cache.direct=on, which was not specified.");
ret = -EINVAL;
goto fail;
error_printf("WARNING: aio=native was specified for '%s', but "
"it requires cache.direct=on, which was not "
"specified. Falling back to aio=threads.\n"
" This will become an error condition in "
"future QEMU versions.\n",
bs->filename);
}
#else
if (bdrv_flags & BDRV_O_NATIVE_AIO) {
error_setg(errp, "aio=native was specified, but is not supported "
"in this build.");
ret = -EINVAL;
goto fail;
error_printf("WARNING: aio=native was specified for '%s', but "
"is not supported in this build. Falling back to "
"aio=threads.\n"
" This will become an error condition in "
"future QEMU versions.\n",
bs->filename);
}
#endif /* !defined(CONFIG_LINUX_AIO) */
@@ -1624,7 +1629,7 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
nocow = qemu_opt_get_bool(opts, BLOCK_OPT_NOCOW, false);
buf = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
prealloc = qapi_enum_parse(PreallocMode_lookup, buf,
PREALLOC_MODE__MAX, PREALLOC_MODE_OFF,
PREALLOC_MODE_MAX, PREALLOC_MODE_OFF,
&local_err);
g_free(buf);
if (local_err) {
@@ -1818,8 +1823,7 @@ static int find_allocation(BlockDriverState *bs, off_t start,
*/
static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
off_t start, data = 0, hole = 0;
int64_t total_size;
@@ -1861,7 +1865,6 @@ static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
*pnum = MIN(nb_sectors, (data - start) / BDRV_SECTOR_SIZE);
ret = BDRV_BLOCK_ZERO;
}
*file = bs;
return ret | BDRV_BLOCK_OFFSET_VALID | start;
}

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/timer.h"
#include "block/block_int.h"

View File

@@ -26,7 +26,6 @@
* IN THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/block_int.h"
#include "qemu/option.h"
@@ -115,11 +114,9 @@ fail:
static int64_t coroutine_fn raw_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum,
BlockDriverState **file)
int nb_sectors, int *pnum)
{
*pnum = nb_sectors;
*file = bs->file->bs;
return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
(sector_num << BDRV_SECTOR_BITS);
}

View File

@@ -11,12 +11,11 @@
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include <inttypes.h>
#include "qemu-common.h"
#include "qemu/error-report.h"
#include "block/block_int.h"
#include "crypto/secret.h"
#include <rbd/librbd.h>
@@ -229,27 +228,6 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
return NULL;
}
static int qemu_rbd_set_auth(rados_t cluster, const char *secretid,
Error **errp)
{
if (secretid == 0) {
return 0;
}
gchar *secret = qcrypto_secret_lookup_as_base64(secretid,
errp);
if (!secret) {
return -1;
}
rados_conf_set(cluster, "key", secret);
g_free(secret);
return 0;
}
static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
bool only_read_conf_file,
Error **errp)
@@ -321,13 +299,10 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
const char *secretid;
rados_t cluster;
rados_ioctx_t io_ctx;
int ret;
secretid = qemu_opt_get(opts, "password-secret");
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
name, sizeof(name),
@@ -375,11 +350,6 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
return -EIO;
}
if (qemu_rbd_set_auth(cluster, secretid, errp) < 0) {
rados_shutdown(cluster);
return -EIO;
}
if (rados_connect(cluster) < 0) {
error_setg(errp, "error connecting");
rados_shutdown(cluster);
@@ -453,11 +423,6 @@ static QemuOptsList runtime_opts = {
.type = QEMU_OPT_STRING,
.help = "Specification of the rbd image",
},
{
.name = "password-secret",
.type = QEMU_OPT_STRING,
.help = "ID of secret providing the password",
},
{ /* end of list */ }
},
};
@@ -471,7 +436,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
char conf[RBD_MAX_CONF_SIZE];
char clientname_buf[RBD_MAX_CONF_SIZE];
char *clientname;
const char *secretid;
QemuOpts *opts;
Error *local_err = NULL;
const char *filename;
@@ -486,7 +450,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
}
filename = qemu_opt_get(opts, "filename");
secretid = qemu_opt_get(opts, "password-secret");
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
@@ -525,11 +488,6 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
}
}
if (qemu_rbd_set_auth(s->cluster, secretid, errp) < 0) {
r = -EIO;
goto failed_shutdown;
}
/*
* Fallback to more conservative semantics if setting cache
* options fails. Ignore errors from setting rbd_cache because the
@@ -961,11 +919,6 @@ static QemuOptsList qemu_rbd_create_opts = {
.type = QEMU_OPT_SIZE,
.help = "RBD object size"
},
{
.name = "password-secret",
.type = QEMU_OPT_STRING,
.help = "ID of secret providing the password",
},
{ /* end of list */ }
}
};

View File

@@ -12,13 +12,11 @@
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/uri.h"
#include "qemu/error-report.h"
#include "qemu/sockets.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/bitops.h"
#define SD_PROTO_VER 0x01
@@ -285,12 +283,6 @@ static inline bool is_snapshot(struct SheepdogInode *inode)
return !!inode->snap_ctime;
}
static inline size_t count_data_objs(const struct SheepdogInode *inode)
{
return DIV_ROUND_UP(inode->vdi_size,
(1UL << inode->block_size_shift));
}
#undef DPRINTF
#ifdef DEBUG_SDOG
#define DPRINTF(fmt, args...) \
@@ -616,13 +608,14 @@ static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data,
ret = qemu_co_send(sockfd, hdr, sizeof(*hdr));
if (ret != sizeof(*hdr)) {
error_report("failed to send a req, %s", strerror(errno));
return -errno;
ret = -socket_error();
return ret;
}
ret = qemu_co_send(sockfd, data, *wlen);
if (ret != *wlen) {
ret = -socket_error();
error_report("failed to send a req, %s", strerror(errno));
return -errno;
}
return ret;
@@ -1637,7 +1630,7 @@ static int do_sd_create(BDRVSheepdogState *s, uint32_t *vdi_id, int snapshot,
static int sd_prealloc(const char *filename, Error **errp)
{
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
BDRVSheepdogState *base = NULL;
unsigned long buf_size;
uint32_t idx, max_idx;
@@ -1646,23 +1639,19 @@ static int sd_prealloc(const char *filename, Error **errp)
void *buf = NULL;
int ret;
blk = blk_new_open("image-prealloc", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
errp);
if (blk == NULL) {
ret = -EIO;
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
errp);
if (ret < 0) {
goto out_with_err_set;
}
blk_set_allow_write_beyond_eof(blk, true);
vdi_size = blk_getlength(blk);
vdi_size = bdrv_getlength(bs);
if (vdi_size < 0) {
ret = vdi_size;
goto out;
}
base = blk_bs(blk)->opaque;
base = bs->opaque;
object_size = (UINT32_C(1) << base->inode.block_size_shift);
buf_size = MIN(object_size, SD_DATA_OBJ_SIZE);
buf = g_malloc0(buf_size);
@@ -1674,24 +1663,23 @@ static int sd_prealloc(const char *filename, Error **errp)
* The created image can be a cloned image, so we need to read
* a data from the source image.
*/
ret = blk_pread(blk, idx * buf_size, buf, buf_size);
ret = bdrv_pread(bs, idx * buf_size, buf, buf_size);
if (ret < 0) {
goto out;
}
ret = blk_pwrite(blk, idx * buf_size, buf, buf_size);
ret = bdrv_pwrite(bs, idx * buf_size, buf, buf_size);
if (ret < 0) {
goto out;
}
}
ret = 0;
out:
if (ret < 0) {
error_setg_errno(errp, -ret, "Can't pre-allocate");
}
out_with_err_set:
if (blk) {
blk_unref(blk);
if (bs) {
bdrv_unref(bs);
}
g_free(buf);
@@ -1831,7 +1819,7 @@ static int sd_create(const char *filename, QemuOpts *opts,
}
if (backing_file) {
BlockBackend *blk;
BlockDriverState *bs;
BDRVSheepdogState *base;
BlockDriver *drv;
@@ -1843,23 +1831,22 @@ static int sd_create(const char *filename, QemuOpts *opts,
goto out;
}
blk = blk_new_open("backing", backing_file, NULL, NULL,
BDRV_O_PROTOCOL | BDRV_O_CACHE_WB, errp);
if (blk == NULL) {
ret = -EIO;
bs = NULL;
ret = bdrv_open(&bs, backing_file, NULL, NULL, BDRV_O_PROTOCOL, errp);
if (ret < 0) {
goto out;
}
base = blk_bs(blk)->opaque;
base = bs->opaque;
if (!is_snapshot(&base->inode)) {
error_setg(errp, "cannot clone from a non snapshot vdi");
blk_unref(blk);
bdrv_unref(bs);
ret = -EINVAL;
goto out;
}
s->inode.vdi_id = base->inode.vdi_id;
blk_unref(blk);
bdrv_unref(bs);
}
s->aio_context = qemu_get_aio_context();
@@ -1874,7 +1861,8 @@ static int sd_create(const char *filename, QemuOpts *opts,
fd = connect_to_sdog(s, &local_err);
if (fd < 0) {
error_report_err(local_err);
error_report("%s", error_get_pretty(local_err));
error_free(local_err);
ret = -EIO;
goto out;
}
@@ -2418,8 +2406,9 @@ static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
ret = do_sd_create(s, &new_vid, 1, &local_err);
if (ret < 0) {
error_reportf_err(local_err,
"failed to create inode for snapshot: ");
error_report("failed to create inode for snapshot: %s",
error_get_pretty(local_err));
error_free(local_err);
goto cleanup;
}
@@ -2490,128 +2479,13 @@ out:
return ret;
}
#define NR_BATCHED_DISCARD 128
static bool remove_objects(BDRVSheepdogState *s)
{
int fd, i = 0, nr_objs = 0;
Error *local_err = NULL;
int ret = 0;
bool result = true;
SheepdogInode *inode = &s->inode;
fd = connect_to_sdog(s, &local_err);
if (fd < 0) {
error_report_err(local_err);
return false;
}
nr_objs = count_data_objs(inode);
while (i < nr_objs) {
int start_idx, nr_filled_idx;
while (i < nr_objs && !inode->data_vdi_id[i]) {
i++;
}
start_idx = i;
nr_filled_idx = 0;
while (i < nr_objs && nr_filled_idx < NR_BATCHED_DISCARD) {
if (inode->data_vdi_id[i]) {
inode->data_vdi_id[i] = 0;
nr_filled_idx++;
}
i++;
}
ret = write_object(fd, s->aio_context,
(char *)&inode->data_vdi_id[start_idx],
vid_to_vdi_oid(s->inode.vdi_id), inode->nr_copies,
(i - start_idx) * sizeof(uint32_t),
offsetof(struct SheepdogInode,
data_vdi_id[start_idx]),
false, s->cache_flags);
if (ret < 0) {
error_report("failed to discard snapshot inode.");
result = false;
goto out;
}
}
out:
closesocket(fd);
return result;
}
static int sd_snapshot_delete(BlockDriverState *bs,
const char *snapshot_id,
const char *name,
Error **errp)
{
uint32_t snap_id = 0;
char snap_tag[SD_MAX_VDI_TAG_LEN];
Error *local_err = NULL;
int fd, ret;
char buf[SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN];
BDRVSheepdogState *s = bs->opaque;
unsigned int wlen = SD_MAX_VDI_LEN + SD_MAX_VDI_TAG_LEN, rlen = 0;
uint32_t vid;
SheepdogVdiReq hdr = {
.opcode = SD_OP_DEL_VDI,
.data_length = wlen,
.flags = SD_FLAG_CMD_WRITE,
};
SheepdogVdiRsp *rsp = (SheepdogVdiRsp *)&hdr;
if (!remove_objects(s)) {
return -1;
}
memset(buf, 0, sizeof(buf));
memset(snap_tag, 0, sizeof(snap_tag));
pstrcpy(buf, SD_MAX_VDI_LEN, s->name);
if (qemu_strtoul(snapshot_id, NULL, 10, (unsigned long *)&snap_id)) {
return -1;
}
if (snap_id) {
hdr.snapid = snap_id;
} else {
pstrcpy(snap_tag, sizeof(snap_tag), snapshot_id);
pstrcpy(buf + SD_MAX_VDI_LEN, SD_MAX_VDI_TAG_LEN, snap_tag);
}
ret = find_vdi_name(s, s->name, snap_id, snap_tag, &vid, true,
&local_err);
if (ret) {
return ret;
}
fd = connect_to_sdog(s, &local_err);
if (fd < 0) {
error_report_err(local_err);
return -1;
}
ret = do_req(fd, s->aio_context, (SheepdogReq *)&hdr,
buf, &wlen, &rlen);
closesocket(fd);
if (ret) {
return ret;
}
switch (rsp->result) {
case SD_RES_NO_VDI:
error_report("%s was already deleted", s->name);
case SD_RES_SUCCESS:
break;
default:
error_report("%s, %s", sd_strerror(rsp->result), s->name);
return -1;
}
return ret;
/* FIXME: Delete specified snapshot id. */
return 0;
}
static int sd_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
@@ -2835,7 +2709,7 @@ retry:
static coroutine_fn int64_t
sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
int *pnum, BlockDriverState **file)
int *pnum)
{
BDRVSheepdogState *s = bs->opaque;
SheepdogInode *inode = &s->inode;
@@ -2866,9 +2740,6 @@ sd_co_get_block_status(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
if (*pnum > nb_sectors) {
*pnum = nb_sectors;
}
if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID) {
*file = bs;
}
return ret;
}

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/snapshot.h"
#include "block/block_int.h"
#include "qapi/qmp/qerror.h"
@@ -230,8 +229,6 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
Error **errp)
{
BlockDriver *drv = bs->drv;
int ret;
if (!drv) {
error_setg(errp, QERR_DEVICE_HAS_NO_MEDIUM, bdrv_get_device_name(bs));
return -ENOMEDIUM;
@@ -242,21 +239,18 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
}
/* drain all pending i/o before deleting snapshot */
bdrv_drained_begin(bs);
bdrv_drain(bs);
if (drv->bdrv_snapshot_delete) {
ret = drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
} else if (bs->file) {
ret = bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
} else {
error_setg(errp, "Block format '%s' used by device '%s' "
"does not support internal snapshot deletion",
drv->format_name, bdrv_get_device_name(bs));
ret = -ENOTSUP;
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}
bdrv_drained_end(bs);
return ret;
if (bs->file) {
return bdrv_snapshot_delete(bs->file->bs, snapshot_id, name, errp);
}
error_setg(errp, "Block format '%s' used by device '%s' "
"does not support internal snapshot deletion",
drv->format_name, bdrv_get_device_name(bs));
return -ENOTSUP;
}
int bdrv_snapshot_delete_by_id_or_name(BlockDriverState *bs,

View File

@@ -22,7 +22,9 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <stdio.h>
#include <stdlib.h>
#include <stdarg.h>
#include <libssh2.h>
#include <libssh2_sftp.h>

View File

@@ -11,7 +11,6 @@
*
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"

View File

@@ -22,7 +22,6 @@
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include "qemu/osdep.h"
#include "block/throttle-groups.h"
#include "qemu/queue.h"
#include "qemu/thread.h"

View File

@@ -49,10 +49,8 @@
* so this seems to be reasonable.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include "migration/migration.h"
#include "qemu/coroutine.h"
@@ -528,7 +526,7 @@ static int vdi_reopen_prepare(BDRVReopenState *state,
}
static int64_t coroutine_fn vdi_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
/* TODO: Check for too large sector_num (in bdrv_is_allocated or here). */
BDRVVdiState *s = (BDRVVdiState *)bs->opaque;
@@ -552,7 +550,6 @@ static int64_t coroutine_fn vdi_co_get_block_status(BlockDriverState *bs,
offset = s->header.offset_data +
(uint64_t)bmap_entry * s->block_size +
sector_in_block * SECTOR_SIZE;
*file = bs->file->bs;
return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | offset;
}
@@ -734,7 +731,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
size_t bmap_size;
int64_t offset = 0;
Error *local_err = NULL;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
uint32_t *bmap = NULL;
logout("\n");
@@ -767,18 +764,13 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
error_propagate(errp, local_err);
goto exit;
}
blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto exit;
}
blk_set_allow_write_beyond_eof(blk, true);
/* We need enough blocks to store the given disk size,
so always round up. */
blocks = DIV_ROUND_UP(bytes, block_size);
@@ -808,7 +800,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
vdi_header_print(&header);
#endif
vdi_header_to_le(&header);
ret = blk_pwrite(blk, offset, &header, sizeof(header));
ret = bdrv_pwrite_sync(bs, offset, &header, sizeof(header));
if (ret < 0) {
error_setg(errp, "Error writing header to %s", filename);
goto exit;
@@ -829,7 +821,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
bmap[i] = VDI_UNALLOCATED;
}
}
ret = blk_pwrite(blk, offset, bmap, bmap_size);
ret = bdrv_pwrite_sync(bs, offset, bmap, bmap_size);
if (ret < 0) {
error_setg(errp, "Error writing bmap to %s", filename);
goto exit;
@@ -838,7 +830,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
}
if (image_type == VDI_TYPE_STATIC) {
ret = blk_truncate(blk, offset + blocks * block_size);
ret = bdrv_truncate(bs, offset + blocks * block_size);
if (ret < 0) {
error_setg(errp, "Failed to statically allocate %s", filename);
goto exit;
@@ -846,7 +838,7 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
}
exit:
blk_unref(blk);
bdrv_unref(bs);
g_free(bmap);
return ret;
}

View File

@@ -15,7 +15,6 @@
*
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "block/vhdx.h"

View File

@@ -17,7 +17,6 @@
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "qemu/error-report.h"
@@ -785,13 +784,12 @@ int vhdx_parse_log(BlockDriverState *bs, BDRVVHDXState *s, bool *flushed,
if (logs.valid) {
if (bs->read_only) {
ret = -EPERM;
error_setg(errp,
"VHDX image file '%s' opened read-only, but "
"contains a log that needs to be replayed",
bs->filename);
error_append_hint(errp, "To replay the log, run:\n"
"qemu-img check -r all '%s'\n",
bs->filename);
error_setg_errno(errp, EPERM,
"VHDX image file '%s' opened read-only, but "
"contains a log that needs to be replayed. To "
"replay the log, execute:\n qemu-img check -r "
"all '%s'",
bs->filename, bs->filename);
goto exit;
}
/* now flush the log */

View File

@@ -15,10 +15,8 @@
*
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include "qemu/crc32c.h"
#include "block/vhdx.h"
@@ -265,10 +263,10 @@ static void vhdx_region_unregister_all(BDRVVHDXState *s)
static void vhdx_set_shift_bits(BDRVVHDXState *s)
{
s->logical_sector_size_bits = ctz32(s->logical_sector_size);
s->sectors_per_block_bits = ctz32(s->sectors_per_block);
s->chunk_ratio_bits = ctz64(s->chunk_ratio);
s->block_size_bits = ctz32(s->block_size);
s->logical_sector_size_bits = 31 - clz32(s->logical_sector_size);
s->sectors_per_block_bits = 31 - clz32(s->sectors_per_block);
s->chunk_ratio_bits = 63 - clz64(s->chunk_ratio);
s->block_size_bits = 31 - clz32(s->block_size);
}
/*
@@ -858,8 +856,14 @@ static void vhdx_calc_bat_entries(BDRVVHDXState *s)
{
uint32_t data_blocks_cnt, bitmap_blocks_cnt;
data_blocks_cnt = DIV_ROUND_UP(s->virtual_disk_size, s->block_size);
bitmap_blocks_cnt = DIV_ROUND_UP(data_blocks_cnt, s->chunk_ratio);
data_blocks_cnt = s->virtual_disk_size >> s->block_size_bits;
if (s->virtual_disk_size - (data_blocks_cnt << s->block_size_bits)) {
data_blocks_cnt++;
}
bitmap_blocks_cnt = data_blocks_cnt >> s->chunk_ratio_bits;
if (data_blocks_cnt - (bitmap_blocks_cnt << s->chunk_ratio_bits)) {
bitmap_blocks_cnt++;
}
if (s->parent_entries) {
s->bat_entries = bitmap_blocks_cnt * (s->chunk_ratio + 1);
@@ -1773,7 +1777,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
gunichar2 *creator = NULL;
glong creator_items;
BlockBackend *blk;
BlockDriverState *bs;
char *type = NULL;
VHDXImageType image_type;
Error *local_err = NULL;
@@ -1838,17 +1842,14 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
goto exit;
}
blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
bs = NULL;
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto exit;
}
blk_set_allow_write_beyond_eof(blk, true);
/* Create (A) */
/* The creator field is optional, but may be useful for
@@ -1856,13 +1857,13 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
creator = g_utf8_to_utf16("QEMU v" QEMU_VERSION, -1, NULL,
&creator_items, NULL);
signature = cpu_to_le64(VHDX_FILE_SIGNATURE);
ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET, &signature, sizeof(signature));
if (ret < 0) {
goto delete_and_exit;
}
if (creator) {
ret = blk_pwrite(blk, VHDX_FILE_ID_OFFSET + sizeof(signature),
creator, creator_items * sizeof(gunichar2));
ret = bdrv_pwrite(bs, VHDX_FILE_ID_OFFSET + sizeof(signature),
creator, creator_items * sizeof(gunichar2));
if (ret < 0) {
goto delete_and_exit;
}
@@ -1870,13 +1871,13 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
/* Creates (B),(C) */
ret = vhdx_create_new_headers(blk_bs(blk), image_size, log_size);
ret = vhdx_create_new_headers(bs, image_size, log_size);
if (ret < 0) {
goto delete_and_exit;
}
/* Creates (D),(E),(G) explicitly. (F) created as by-product */
ret = vhdx_create_new_region_table(blk_bs(blk), image_size, block_size, 512,
ret = vhdx_create_new_region_table(bs, image_size, block_size, 512,
log_size, use_zero_blocks, image_type,
&metadata_offset);
if (ret < 0) {
@@ -1884,7 +1885,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
}
/* Creates (H) */
ret = vhdx_create_new_metadata(blk_bs(blk), image_size, block_size, 512,
ret = vhdx_create_new_metadata(bs, image_size, block_size, 512,
metadata_offset, image_type);
if (ret < 0) {
goto delete_and_exit;
@@ -1892,7 +1893,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
delete_and_exit:
blk_unref(blk);
bdrv_unref(bs);
exit:
g_free(type);
g_free(creator);

View File

@@ -23,10 +23,8 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qapi/qmp/qerror.h"
#include "qemu/error-report.h"
#include "qemu/module.h"
@@ -243,17 +241,15 @@ static void vmdk_free_last_extent(BlockDriverState *bs)
static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
{
char *desc;
char desc[DESC_SIZE];
uint32_t cid = 0xffffffff;
const char *p_name, *cid_str;
size_t cid_str_size;
BDRVVmdkState *s = bs->opaque;
int ret;
desc = g_malloc0(DESC_SIZE);
ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
if (ret < 0) {
g_free(desc);
return 0;
}
@@ -272,45 +268,41 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
sscanf(p_name, "%" SCNx32, &cid);
}
g_free(desc);
return cid;
}
static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
{
char *desc, *tmp_desc;
char desc[DESC_SIZE], tmp_desc[DESC_SIZE];
char *p_name, *tmp_str;
BDRVVmdkState *s = bs->opaque;
int ret = 0;
int ret;
desc = g_malloc0(DESC_SIZE);
tmp_desc = g_malloc0(DESC_SIZE);
ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
if (ret < 0) {
goto out;
return ret;
}
desc[DESC_SIZE - 1] = '\0';
tmp_str = strstr(desc, "parentCID");
if (tmp_str == NULL) {
ret = -EINVAL;
goto out;
return -EINVAL;
}
pstrcpy(tmp_desc, DESC_SIZE, tmp_str);
pstrcpy(tmp_desc, sizeof(tmp_desc), tmp_str);
p_name = strstr(desc, "CID");
if (p_name != NULL) {
p_name += sizeof("CID");
snprintf(p_name, DESC_SIZE - (p_name - desc), "%" PRIx32 "\n", cid);
pstrcat(desc, DESC_SIZE, tmp_desc);
snprintf(p_name, sizeof(desc) - (p_name - desc), "%" PRIx32 "\n", cid);
pstrcat(desc, sizeof(desc), tmp_desc);
}
ret = bdrv_pwrite_sync(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
if (ret < 0) {
return ret;
}
out:
g_free(desc);
g_free(tmp_desc);
return ret;
return 0;
}
static int vmdk_is_cid_valid(BlockDriverState *bs)
@@ -344,16 +336,15 @@ static int vmdk_reopen_prepare(BDRVReopenState *state,
static int vmdk_parent_open(BlockDriverState *bs)
{
char *p_name;
char *desc;
char desc[DESC_SIZE + 1];
BDRVVmdkState *s = bs->opaque;
int ret;
desc = g_malloc0(DESC_SIZE + 1);
desc[DESC_SIZE] = '\0';
ret = bdrv_pread(bs->file->bs, s->desc_offset, desc, DESC_SIZE);
if (ret < 0) {
goto out;
return ret;
}
ret = 0;
p_name = strstr(desc, "parentFileNameHint");
if (p_name != NULL) {
@@ -362,20 +353,16 @@ static int vmdk_parent_open(BlockDriverState *bs)
p_name += sizeof("parentFileNameHint") + 1;
end_name = strchr(p_name, '\"');
if (end_name == NULL) {
ret = -EINVAL;
goto out;
return -EINVAL;
}
if ((end_name - p_name) > sizeof(bs->backing_file) - 1) {
ret = -EINVAL;
goto out;
return -EINVAL;
}
pstrcpy(bs->backing_file, end_name - p_name + 1, p_name);
}
out:
g_free(desc);
return ret;
return 0;
}
/* Create and append extent to the extent array. Return the added VmdkExtent
@@ -777,17 +764,6 @@ static int vmdk_open_sparse(BlockDriverState *bs, BdrvChild *file, int flags,
}
}
static const char *next_line(const char *s)
{
while (*s) {
if (*s == '\n') {
return s + 1;
}
s++;
}
return s;
}
static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
const char *desc_file_path, QDict *options,
Error **errp)
@@ -797,7 +773,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
char access[11];
char type[11];
char fname[512];
const char *p, *np;
const char *p = desc;
int64_t sectors = 0;
int64_t flat_offset;
char *extent_path;
@@ -807,7 +783,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
char extent_opt_prefix[32];
Error *local_err = NULL;
for (p = desc; *p; p = next_line(p)) {
while (*p) {
/* parse extent line in one of below formats:
*
* RW [size in sectors] FLAT "file-name.vmdk" OFFSET
@@ -819,26 +795,29 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
matches = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
access, &sectors, type, fname, &flat_offset);
if (matches < 4 || strcmp(access, "RW")) {
continue;
goto next_line;
} else if (!strcmp(type, "FLAT")) {
if (matches != 5 || flat_offset < 0) {
goto invalid;
error_setg(errp, "Invalid extent lines: \n%s", p);
return -EINVAL;
}
} else if (!strcmp(type, "VMFS")) {
if (matches == 4) {
flat_offset = 0;
} else {
goto invalid;
error_setg(errp, "Invalid extent lines:\n%s", p);
return -EINVAL;
}
} else if (matches != 4) {
goto invalid;
error_setg(errp, "Invalid extent lines:\n%s", p);
return -EINVAL;
}
if (sectors <= 0 ||
(strcmp(type, "FLAT") && strcmp(type, "SPARSE") &&
strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE")) ||
(strcmp(access, "RW"))) {
continue;
goto next_line;
}
if (!path_is_absolute(fname) && !path_has_protocol(fname) &&
@@ -895,17 +874,17 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
return -ENOTSUP;
}
extent->type = g_strdup(type);
next_line:
/* move to next line */
while (*p) {
if (*p == '\n') {
p++;
break;
}
p++;
}
}
return 0;
invalid:
np = next_line(p);
assert(np != p);
if (np[-1] == '\n') {
np--;
}
error_setg(errp, "Invalid extent line: %.*s", (int)(np - p), p);
return -EINVAL;
}
static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
@@ -1273,7 +1252,7 @@ static inline uint64_t vmdk_find_index_in_cluster(VmdkExtent *extent,
}
static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
BDRVVmdkState *s = bs->opaque;
int64_t index_in_cluster, n, ret;
@@ -1290,7 +1269,6 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
0, 0);
qemu_co_mutex_unlock(&s->lock);
index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
switch (ret) {
case VMDK_ERROR:
ret = -EIO;
@@ -1303,15 +1281,14 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
break;
case VMDK_OK:
ret = BDRV_BLOCK_DATA;
if (!extent->compressed) {
ret |= BDRV_BLOCK_OFFSET_VALID;
ret |= (offset + (index_in_cluster << BDRV_SECTOR_BITS))
& BDRV_BLOCK_OFFSET_MASK;
if (extent->file == bs->file && !extent->compressed) {
ret |= BDRV_BLOCK_OFFSET_VALID | offset;
}
*file = extent->file->bs;
break;
}
index_in_cluster = vmdk_find_index_in_cluster(extent, sector_num);
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
@@ -1521,8 +1498,8 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
if (sector_num > bs->total_sectors) {
error_report("Wrong offset: sector_num=0x%" PRIx64
" total_sectors=0x%" PRIx64,
sector_num, bs->total_sectors);
" total_sectors=0x%" PRIx64 "\n",
sector_num, bs->total_sectors);
return -EIO;
}
@@ -1651,7 +1628,7 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
QemuOpts *opts, Error **errp)
{
int ret, i;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
VMDK4Header header;
Error *local_err = NULL;
uint32_t tmp, magic, grains, gd_sectors, gt_size, gt_count;
@@ -1664,19 +1641,16 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
goto exit;
}
blk = blk_new_open("extent", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
assert(bs == NULL);
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto exit;
}
blk_set_allow_write_beyond_eof(blk, true);
if (flat) {
ret = blk_truncate(blk, filesize);
ret = bdrv_truncate(bs, filesize);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not truncate file");
}
@@ -1731,18 +1705,18 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
header.check_bytes[3] = 0xa;
/* write all the data */
ret = blk_pwrite(blk, 0, &magic, sizeof(magic));
ret = bdrv_pwrite(bs, 0, &magic, sizeof(magic));
if (ret < 0) {
error_setg(errp, QERR_IO_ERROR);
goto exit;
}
ret = blk_pwrite(blk, sizeof(magic), &header, sizeof(header));
ret = bdrv_pwrite(bs, sizeof(magic), &header, sizeof(header));
if (ret < 0) {
error_setg(errp, QERR_IO_ERROR);
goto exit;
}
ret = blk_truncate(blk, le64_to_cpu(header.grain_offset) << 9);
ret = bdrv_truncate(bs, le64_to_cpu(header.grain_offset) << 9);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not truncate file");
goto exit;
@@ -1755,8 +1729,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
i < gt_count; i++, tmp += gt_size) {
gd_buf[i] = cpu_to_le32(tmp);
}
ret = blk_pwrite(blk, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE,
gd_buf, gd_buf_size);
ret = bdrv_pwrite(bs, le64_to_cpu(header.rgd_offset) * BDRV_SECTOR_SIZE,
gd_buf, gd_buf_size);
if (ret < 0) {
error_setg(errp, QERR_IO_ERROR);
goto exit;
@@ -1767,8 +1741,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
i < gt_count; i++, tmp += gt_size) {
gd_buf[i] = cpu_to_le32(tmp);
}
ret = blk_pwrite(blk, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE,
gd_buf, gd_buf_size);
ret = bdrv_pwrite(bs, le64_to_cpu(header.gd_offset) * BDRV_SECTOR_SIZE,
gd_buf, gd_buf_size);
if (ret < 0) {
error_setg(errp, QERR_IO_ERROR);
goto exit;
@@ -1776,8 +1750,8 @@ static int vmdk_create_extent(const char *filename, int64_t filesize,
ret = 0;
exit:
if (blk) {
blk_unref(blk);
if (bs) {
bdrv_unref(bs);
}
g_free(gd_buf);
return ret;
@@ -1826,7 +1800,7 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
{
int idx = 0;
BlockBackend *new_blk = NULL;
BlockDriverState *new_bs = NULL;
Error *local_err = NULL;
char *desc = NULL;
int64_t total_size = 0, filesize;
@@ -1937,7 +1911,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
goto exit;
}
if (backing_file) {
BlockBackend *blk;
BlockDriverState *bs = NULL;
char *full_backing = g_new0(char, PATH_MAX);
bdrv_get_full_backing_filename_from_filename(filename, backing_file,
full_backing, PATH_MAX,
@@ -1948,21 +1922,18 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
ret = -ENOENT;
goto exit;
}
blk = blk_new_open("backing", full_backing, NULL, NULL,
BDRV_O_NO_BACKING | BDRV_O_CACHE_WB, errp);
ret = bdrv_open(&bs, full_backing, NULL, NULL, BDRV_O_NO_BACKING, errp);
g_free(full_backing);
if (blk == NULL) {
ret = -EIO;
if (ret != 0) {
goto exit;
}
if (strcmp(blk_bs(blk)->drv->format_name, "vmdk")) {
blk_unref(blk);
if (strcmp(bs->drv->format_name, "vmdk")) {
bdrv_unref(bs);
ret = -EINVAL;
goto exit;
}
parent_cid = vmdk_read_cid(blk_bs(blk), 0);
blk_unref(blk);
parent_cid = vmdk_read_cid(bs, 0);
bdrv_unref(bs);
snprintf(parent_desc_line, BUF_SIZE,
"parentFileNameHint=\"%s\"", backing_file);
}
@@ -2020,19 +1991,14 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
goto exit;
}
}
new_blk = blk_new_open("descriptor", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (new_blk == NULL) {
assert(new_bs == NULL);
ret = bdrv_open(&new_bs, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_PROTOCOL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto exit;
}
blk_set_allow_write_beyond_eof(new_blk, true);
ret = blk_pwrite(new_blk, desc_offset, desc, desc_len);
ret = bdrv_pwrite(new_bs, desc_offset, desc, desc_len);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not write description");
goto exit;
@@ -2040,14 +2006,14 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
/* bdrv_pwrite write padding zeros to align to sector, we don't need that
* for description file */
if (desc_offset == 0) {
ret = blk_truncate(new_blk, desc_len);
ret = bdrv_truncate(new_bs, desc_len);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not truncate file");
}
}
exit:
if (new_blk) {
blk_unref(new_blk);
if (new_bs) {
bdrv_unref(new_bs);
}
g_free(adapter_type);
g_free(backing_file);

View File

@@ -22,10 +22,8 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block_int.h"
#include "sysemu/block-backend.h"
#include "qemu/module.h"
#include "migration/migration.h"
#if defined(CONFIG_UUID)
@@ -47,14 +45,8 @@ enum vhd_type {
// Seconds since Jan 1, 2000 0:00:00 (UTC)
#define VHD_TIMESTAMP_BASE 946684800
#define VHD_CHS_MAX_C 65535LL
#define VHD_CHS_MAX_H 16
#define VHD_CHS_MAX_S 255
#define VHD_MAX_SECTORS (65535LL * 255 * 255)
#define VHD_MAX_GEOMETRY (VHD_CHS_MAX_C * VHD_CHS_MAX_H * VHD_CHS_MAX_S)
#define VPC_OPT_FORCE_SIZE "force_size"
#define VHD_MAX_GEOMETRY (65535LL * 16 * 255)
// always big-endian
typedef struct vhd_footer {
@@ -135,8 +127,6 @@ typedef struct BDRVVPCState {
uint32_t block_size;
uint32_t bitmap_size;
bool force_use_chs;
bool force_use_sz;
#ifdef CACHE
uint8_t *pageentry_u8;
@@ -149,22 +139,6 @@ typedef struct BDRVVPCState {
Error *migration_blocker;
} BDRVVPCState;
#define VPC_OPT_SIZE_CALC "force_size_calc"
static QemuOptsList vpc_runtime_opts = {
.name = "vpc-runtime-opts",
.head = QTAILQ_HEAD_INITIALIZER(vpc_runtime_opts.head),
.desc = {
{
.name = VPC_OPT_SIZE_CALC,
.type = QEMU_OPT_STRING,
.help = "Force disk size calculation to use either CHS geometry, "
"or use the disk current_size specified in the VHD footer. "
"{chs, current_size}"
},
{ /* end of list */ }
}
};
static uint32_t vpc_checksum(uint8_t* buf, size_t size)
{
uint32_t res = 0;
@@ -184,25 +158,6 @@ static int vpc_probe(const uint8_t *buf, int buf_size, const char *filename)
return 0;
}
static void vpc_parse_options(BlockDriverState *bs, QemuOpts *opts,
Error **errp)
{
BDRVVPCState *s = bs->opaque;
const char *size_calc;
size_calc = qemu_opt_get(opts, VPC_OPT_SIZE_CALC);
if (!size_calc) {
/* no override, use autodetect only */
} else if (!strcmp(size_calc, "current_size")) {
s->force_use_sz = true;
} else if (!strcmp(size_calc, "chs")) {
s->force_use_chs = true;
} else {
error_setg(errp, "Invalid size calculation mode: '%s'", size_calc);
}
}
static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
@@ -210,9 +165,6 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int i;
VHDFooter *footer;
VHDDynDiskHeader *dyndisk_header;
QemuOpts *opts = NULL;
Error *local_err = NULL;
bool use_chs;
uint8_t buf[HEADER_SIZE];
uint32_t checksum;
uint64_t computed_size;
@@ -220,21 +172,6 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int disk_type = VHD_DYNAMIC;
int ret;
opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
vpc_parse_options(bs, opts, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
ret = bdrv_pread(bs->file->bs, 0, s->footer_buf, HEADER_SIZE);
if (ret < 0) {
goto fail;
@@ -280,36 +217,12 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
bs->total_sectors = (int64_t)
be16_to_cpu(footer->cyls) * footer->heads * footer->secs_per_cyl;
/* Microsoft Virtual PC and Microsoft Hyper-V produce and read
* VHD image sizes differently. VPC will rely on CHS geometry,
* while Hyper-V and disk2vhd use the size specified in the footer.
*
* We use a couple of approaches to try and determine the correct method:
* look at the Creator App field, and look for images that have CHS
* geometry that is the maximum value.
*
* If the CHS geometry is the maximum CHS geometry, then we assume that
* the size is the footer->current_size to avoid truncation. Otherwise,
* we follow the table based on footer->creator_app:
*
* Known creator apps:
* 'vpc ' : CHS Virtual PC (uses disk geometry)
* 'qemu' : CHS QEMU (uses disk geometry)
* 'qem2' : current_size QEMU (uses current_size)
* 'win ' : current_size Hyper-V
* 'd2v ' : current_size Disk2vhd
*
* The user can override the table values via drive options, however
* even with an override we will still use current_size for images
* that have CHS geometry of the maximum size.
*/
use_chs = (!!strncmp(footer->creator_app, "win ", 4) &&
!!strncmp(footer->creator_app, "qem2", 4) &&
!!strncmp(footer->creator_app, "d2v ", 4)) || s->force_use_chs;
if (!use_chs || bs->total_sectors == VHD_MAX_GEOMETRY || s->force_use_sz) {
/* Images that have exactly the maximum geometry are probably bigger and
* would be truncated if we adhered to the geometry for them. Rely on
* footer->current_size for them. */
if (bs->total_sectors == VHD_MAX_GEOMETRY) {
bs->total_sectors = be64_to_cpu(footer->current_size) /
BDRV_SECTOR_SIZE;
BDRV_SECTOR_SIZE;
}
/* Allow a maximum disk size of approximately 2 TB */
@@ -665,7 +578,7 @@ static coroutine_fn int vpc_co_write(BlockDriverState *bs, int64_t sector_num,
}
static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *pnum, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int *pnum)
{
BDRVVPCState *s = bs->opaque;
VHDFooter *footer = (VHDFooter*) s->footer_buf;
@@ -675,7 +588,6 @@ static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
if (be32_to_cpu(footer->type) == VHD_FIXED) {
*pnum = nb_sectors;
*file = bs->file->bs;
return BDRV_BLOCK_RAW | BDRV_BLOCK_OFFSET_VALID | BDRV_BLOCK_DATA |
(sector_num << BDRV_SECTOR_BITS);
}
@@ -697,7 +609,6 @@ static int64_t coroutine_fn vpc_co_get_block_status(BlockDriverState *bs,
/* *pnum can't be greater than one block for allocated
* sectors since there is always a bitmap in between. */
if (allocated) {
*file = bs->file->bs;
return BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID | start;
}
if (nb_sectors == 0) {
@@ -759,7 +670,7 @@ static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
return 0;
}
static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
static int create_dynamic_disk(BlockDriverState *bs, uint8_t *buf,
int64_t total_sectors)
{
VHDDynDiskHeader *dyndisk_header =
@@ -773,13 +684,13 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
block_size = 0x200000;
num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
ret = blk_pwrite(blk, offset, buf, HEADER_SIZE);
ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE);
if (ret) {
goto fail;
}
offset = 1536 + ((num_bat_entries * 4 + 511) & ~511);
ret = blk_pwrite(blk, offset, buf, HEADER_SIZE);
ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE);
if (ret < 0) {
goto fail;
}
@@ -789,7 +700,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
memset(buf, 0xFF, 512);
for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++) {
ret = blk_pwrite(blk, offset, buf, 512);
ret = bdrv_pwrite_sync(bs, offset, buf, 512);
if (ret < 0) {
goto fail;
}
@@ -816,7 +727,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
// Write the header
offset = 512;
ret = blk_pwrite(blk, offset, buf, 1024);
ret = bdrv_pwrite_sync(bs, offset, buf, 1024);
if (ret < 0) {
goto fail;
}
@@ -825,7 +736,7 @@ static int create_dynamic_disk(BlockBackend *blk, uint8_t *buf,
return ret;
}
static int create_fixed_disk(BlockBackend *blk, uint8_t *buf,
static int create_fixed_disk(BlockDriverState *bs, uint8_t *buf,
int64_t total_size)
{
int ret;
@@ -833,12 +744,12 @@ static int create_fixed_disk(BlockBackend *blk, uint8_t *buf,
/* Add footer to total size */
total_size += HEADER_SIZE;
ret = blk_truncate(blk, total_size);
ret = bdrv_truncate(bs, total_size);
if (ret < 0) {
return ret;
}
ret = blk_pwrite(blk, total_size - HEADER_SIZE, buf, HEADER_SIZE);
ret = bdrv_pwrite_sync(bs, total_size - HEADER_SIZE, buf, HEADER_SIZE);
if (ret < 0) {
return ret;
}
@@ -859,9 +770,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
int64_t total_size;
int disk_type;
int ret = -EIO;
bool force_size;
Error *local_err = NULL;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
@@ -880,44 +790,30 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
disk_type = VHD_DYNAMIC;
}
force_size = qemu_opt_get_bool_del(opts, VPC_OPT_FORCE_SIZE, false);
ret = bdrv_create_file(filename, opts, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto out;
}
blk = blk_new_open("image", filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_PROTOCOL,
&local_err);
if (blk == NULL) {
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
&local_err);
if (ret < 0) {
error_propagate(errp, local_err);
ret = -EIO;
goto out;
}
blk_set_allow_write_beyond_eof(blk, true);
/*
* Calculate matching total_size and geometry. Increase the number of
* sectors requested until we get enough (or fail). This ensures that
* qemu-img convert doesn't truncate images, but rather rounds up.
*
* If the image size can't be represented by a spec conformant CHS geometry,
* If the image size can't be represented by a spec conform CHS geometry,
* we set the geometry to 65535 x 16 x 255 (CxHxS) sectors and use
* the image size from the VHD footer to calculate total_sectors.
*/
if (force_size) {
/* This will force the use of total_size for sector count, below */
cyls = VHD_CHS_MAX_C;
heads = VHD_CHS_MAX_H;
secs_per_cyl = VHD_CHS_MAX_S;
} else {
total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE);
for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) {
calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl);
}
total_sectors = MIN(VHD_MAX_GEOMETRY, total_size / BDRV_SECTOR_SIZE);
for (i = 0; total_sectors > (int64_t)cyls * heads * secs_per_cyl; i++) {
calculate_geometry(total_sectors + i, &cyls, &heads, &secs_per_cyl);
}
if ((int64_t)cyls * heads * secs_per_cyl == VHD_MAX_GEOMETRY) {
@@ -936,11 +832,8 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
memset(buf, 0, 1024);
memcpy(footer->creator, "conectix", 8);
if (force_size) {
memcpy(footer->creator_app, "qem2", 4);
} else {
memcpy(footer->creator_app, "qemu", 4);
}
/* TODO Check if "qemu" creator_app is ok for VPC */
memcpy(footer->creator_app, "qemu", 4);
memcpy(footer->creator_os, "Wi2k", 4);
footer->features = cpu_to_be32(0x02);
@@ -970,13 +863,13 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
footer->checksum = cpu_to_be32(vpc_checksum(buf, HEADER_SIZE));
if (disk_type == VHD_DYNAMIC) {
ret = create_dynamic_disk(blk, buf, total_sectors);
ret = create_dynamic_disk(bs, buf, total_sectors);
} else {
ret = create_fixed_disk(blk, buf, total_size);
ret = create_fixed_disk(bs, buf, total_size);
}
out:
blk_unref(blk);
bdrv_unref(bs);
g_free(disk_type_param);
return ret;
}
@@ -1021,13 +914,6 @@ static QemuOptsList vpc_create_opts = {
"Type of virtual hard disk format. Supported formats are "
"{dynamic (default) | fixed} "
},
{
.name = VPC_OPT_FORCE_SIZE,
.type = QEMU_OPT_BOOL,
.help = "Force disk size calculation to use the actual size "
"specified, rather than using the nearest CHS-based "
"calculation"
},
{ /* end of list */ }
}
};

View File

@@ -22,7 +22,7 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <sys/stat.h>
#include <dirent.h>
#include "qemu-common.h"
#include "block/block_int.h"
@@ -2884,7 +2884,7 @@ static coroutine_fn int vvfat_co_write(BlockDriverState *bs, int64_t sector_num,
}
static int64_t coroutine_fn vvfat_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *n, BlockDriverState **file)
int64_t sector_num, int nb_sectors, int* n)
{
BDRVVVFATState* s = bs->opaque;
*n = s->sector_count - sector_num;

View File

@@ -21,7 +21,6 @@
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/timer.h"
#include "block/block_int.h"

View File

@@ -10,7 +10,6 @@
* See the COPYING.LIB file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "block/block_int.h"
#include "qemu/coroutine.h"
#include "block/write-threshold.h"

View File

@@ -9,7 +9,6 @@
* later. See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "sysemu/blockdev.h"
#include "sysemu/block-backend.h"
#include "hw/block/block.h"
@@ -18,128 +17,58 @@
#include "qmp-commands.h"
#include "trace.h"
#include "block/nbd.h"
#include "io/channel-socket.h"
#include "qemu/sockets.h"
typedef struct NBDServerData {
QIOChannelSocket *listen_ioc;
int watch;
QCryptoTLSCreds *tlscreds;
} NBDServerData;
static int server_fd = -1;
static NBDServerData *nbd_server;
static gboolean nbd_accept(QIOChannel *ioc, GIOCondition condition,
gpointer opaque)
static void nbd_accept(void *opaque)
{
QIOChannelSocket *cioc;
struct sockaddr_in addr;
socklen_t addr_len = sizeof(addr);
if (!nbd_server) {
return FALSE;
int fd = accept(server_fd, (struct sockaddr *)&addr, &addr_len);
if (fd >= 0 && !nbd_client_new(NULL, fd, nbd_client_put)) {
shutdown(fd, 2);
close(fd);
}
cioc = qio_channel_socket_accept(QIO_CHANNEL_SOCKET(ioc),
NULL);
if (!cioc) {
return TRUE;
}
nbd_client_new(NULL, cioc,
nbd_server->tlscreds, NULL,
nbd_client_put);
object_unref(OBJECT(cioc));
return TRUE;
}
static void nbd_server_free(NBDServerData *server)
void qmp_nbd_server_start(SocketAddress *addr, Error **errp)
{
if (!server) {
return;
}
if (server->watch != -1) {
g_source_remove(server->watch);
}
object_unref(OBJECT(server->listen_ioc));
if (server->tlscreds) {
object_unref(OBJECT(server->tlscreds));
}
g_free(server);
}
static QCryptoTLSCreds *nbd_get_tls_creds(const char *id, Error **errp)
{
Object *obj;
QCryptoTLSCreds *creds;
obj = object_resolve_path_component(
object_get_objects_root(), id);
if (!obj) {
error_setg(errp, "No TLS credentials with id '%s'",
id);
return NULL;
}
creds = (QCryptoTLSCreds *)
object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS);
if (!creds) {
error_setg(errp, "Object with id '%s' is not TLS credentials",
id);
return NULL;
}
if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_SERVER) {
error_setg(errp,
"Expecting TLS credentials with a server endpoint");
return NULL;
}
object_ref(obj);
return creds;
}
void qmp_nbd_server_start(SocketAddress *addr,
bool has_tls_creds, const char *tls_creds,
Error **errp)
{
if (nbd_server) {
if (server_fd != -1) {
error_setg(errp, "NBD server already running");
return;
}
nbd_server = g_new0(NBDServerData, 1);
nbd_server->watch = -1;
nbd_server->listen_ioc = qio_channel_socket_new();
if (qio_channel_socket_listen_sync(
nbd_server->listen_ioc, addr, errp) < 0) {
goto error;
server_fd = socket_listen(addr, errp);
if (server_fd != -1) {
qemu_set_fd_handler(server_fd, nbd_accept, NULL, NULL);
}
}
if (has_tls_creds) {
nbd_server->tlscreds = nbd_get_tls_creds(tls_creds, errp);
if (!nbd_server->tlscreds) {
goto error;
}
/*
* Hook into the BlockBackend notifiers to close the export when the
* backend is closed.
*/
typedef struct NBDCloseNotifier {
Notifier n;
NBDExport *exp;
QTAILQ_ENTRY(NBDCloseNotifier) next;
} NBDCloseNotifier;
if (addr->type != SOCKET_ADDRESS_KIND_INET) {
error_setg(errp, "TLS is only supported with IPv4/IPv6");
goto error;
}
}
static QTAILQ_HEAD(, NBDCloseNotifier) close_notifiers =
QTAILQ_HEAD_INITIALIZER(close_notifiers);
nbd_server->watch = qio_channel_add_watch(
QIO_CHANNEL(nbd_server->listen_ioc),
G_IO_IN,
nbd_accept,
NULL,
NULL);
static void nbd_close_notifier(Notifier *n, void *data)
{
NBDCloseNotifier *cn = DO_UPCAST(NBDCloseNotifier, n, n);
return;
notifier_remove(&cn->n);
QTAILQ_REMOVE(&close_notifiers, cn, next);
error:
nbd_server_free(nbd_server);
nbd_server = NULL;
nbd_export_close(cn->exp);
nbd_export_put(cn->exp);
g_free(cn);
}
void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
@@ -147,8 +76,9 @@ void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
{
BlockBackend *blk;
NBDExport *exp;
NBDCloseNotifier *n;
if (!nbd_server) {
if (server_fd == -1) {
error_setg(errp, "NBD server not running");
return;
}
@@ -184,16 +114,23 @@ void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
nbd_export_set_name(exp, device);
/* The list of named exports has a strong reference to this export now and
* our only way of accessing it is through nbd_export_find(), so we can drop
* the strong reference that is @exp. */
nbd_export_put(exp);
n = g_new0(NBDCloseNotifier, 1);
n->n.notify = nbd_close_notifier;
n->exp = exp;
blk_add_close_notifier(blk, &n->n);
QTAILQ_INSERT_TAIL(&close_notifiers, n, next);
}
void qmp_nbd_server_stop(Error **errp)
{
nbd_export_close_all();
while (!QTAILQ_EMPTY(&close_notifiers)) {
NBDCloseNotifier *cn = QTAILQ_FIRST(&close_notifiers);
nbd_close_notifier(&cn->n, nbd_export_get_blockdev(cn->exp));
}
nbd_server_free(nbd_server);
nbd_server = NULL;
if (server_fd != -1) {
qemu_set_fd_handler(server_fd, NULL, NULL, NULL);
close(server_fd);
server_fd = -1;
}
}

View File

@@ -30,7 +30,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "sysemu/block-backend.h"
#include "sysemu/blockdev.h"
#include "hw/block/block.h"
@@ -51,9 +50,6 @@
#include "trace.h"
#include "sysemu/arch_init.h"
static QTAILQ_HEAD(, BlockDriverState) monitor_bdrv_states =
QTAILQ_HEAD_INITIALIZER(monitor_bdrv_states);
static const char *const if_name[IF_COUNT] = {
[IF_NONE] = "none",
[IF_IDE] = "ide",
@@ -343,6 +339,28 @@ static bool parse_stats_intervals(BlockAcctStats *stats, QList *intervals,
return true;
}
static bool check_throttle_config(ThrottleConfig *cfg, Error **errp)
{
if (throttle_conflicting(cfg)) {
error_setg(errp, "bps/iops/max total values and read/write values"
" cannot be used at the same time");
return false;
}
if (!throttle_is_valid(cfg)) {
error_setg(errp, "bps/iops/maxs values must be 0 or greater");
return false;
}
if (throttle_max_is_missing_limit(cfg)) {
error_setg(errp, "bps_max/iops_max require corresponding"
" bps/iops values");
return false;
}
return true;
}
typedef enum { MEDIA_DISK, MEDIA_CDROM } DriveMediaType;
/* All parameters but @opts are optional and may be set to NULL. */
@@ -369,6 +387,16 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
}
}
if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_WB, true)) {
*bdrv_flags |= BDRV_O_CACHE_WB;
}
if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_DIRECT, false)) {
*bdrv_flags |= BDRV_O_NOCACHE;
}
if (qemu_opt_get_bool(opts, BDRV_OPT_CACHE_NO_FLUSH, false)) {
*bdrv_flags |= BDRV_O_NO_FLUSH;
}
if ((aio = qemu_opt_get(opts, "aio")) != NULL) {
if (!strcmp(aio, "native")) {
*bdrv_flags |= BDRV_O_NATIVE_AIO;
@@ -387,7 +415,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
}
if (throttle_cfg) {
throttle_config_init(throttle_cfg);
memset(throttle_cfg, 0, sizeof(*throttle_cfg));
throttle_cfg->buckets[THROTTLE_BPS_TOTAL].avg =
qemu_opt_get_number(opts, "throttling.bps-total", 0);
throttle_cfg->buckets[THROTTLE_BPS_READ].avg =
@@ -414,23 +442,10 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
throttle_cfg->buckets[THROTTLE_OPS_WRITE].max =
qemu_opt_get_number(opts, "throttling.iops-write-max", 0);
throttle_cfg->buckets[THROTTLE_BPS_TOTAL].burst_length =
qemu_opt_get_number(opts, "throttling.bps-total-max-length", 1);
throttle_cfg->buckets[THROTTLE_BPS_READ].burst_length =
qemu_opt_get_number(opts, "throttling.bps-read-max-length", 1);
throttle_cfg->buckets[THROTTLE_BPS_WRITE].burst_length =
qemu_opt_get_number(opts, "throttling.bps-write-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_TOTAL].burst_length =
qemu_opt_get_number(opts, "throttling.iops-total-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_READ].burst_length =
qemu_opt_get_number(opts, "throttling.iops-read-max-length", 1);
throttle_cfg->buckets[THROTTLE_OPS_WRITE].burst_length =
qemu_opt_get_number(opts, "throttling.iops-write-max-length", 1);
throttle_cfg->op_size =
qemu_opt_get_number(opts, "throttling.iops-size", 0);
if (!throttle_is_valid(throttle_cfg, errp)) {
if (!check_throttle_config(throttle_cfg, errp)) {
return;
}
}
@@ -439,7 +454,7 @@ static void extract_common_blockdev_options(QemuOpts *opts, int *bdrv_flags,
*detect_zeroes =
qapi_enum_parse(BlockdevDetectZeroesOptions_lookup,
qemu_opt_get(opts, "detect-zeroes"),
BLOCKDEV_DETECT_ZEROES_OPTIONS__MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_MAX,
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF,
&local_error);
if (local_error) {
@@ -475,6 +490,7 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
QDict *interval_dict = NULL;
QList *interval_list = NULL;
const char *id;
bool has_driver_specific_opts;
BlockdevDetectZeroesOptions detect_zeroes =
BLOCKDEV_DETECT_ZEROES_OPTIONS_OFF;
const char *throttling_group = NULL;
@@ -498,6 +514,8 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
qdict_del(bs_opts, "id");
}
has_driver_specific_opts = !!qdict_size(bs_opts);
/* extract parameters */
snapshot = qemu_opt_get_bool(opts, "snapshot", 0);
@@ -554,11 +572,13 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
}
if (snapshot) {
bdrv_flags |= BDRV_O_SNAPSHOT;
/* always use cache=unsafe with snapshot */
bdrv_flags &= ~BDRV_O_CACHE_MASK;
bdrv_flags |= (BDRV_O_SNAPSHOT|BDRV_O_CACHE_WB|BDRV_O_NO_FLUSH);
}
/* init */
if ((!file || !*file) && !qdict_size(bs_opts)) {
if ((!file || !*file) && !has_driver_specific_opts) {
BlockBackendRootState *blk_rs;
blk = blk_new(qemu_opts_id(opts), errp);
@@ -586,17 +606,6 @@ static BlockBackend *blockdev_init(const char *file, QDict *bs_opts,
file = NULL;
}
/* bdrv_open() defaults to the values in bdrv_flags (for compatibility
* with other callers) rather than what we want as the real defaults.
* Apply the defaults here instead. */
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_WB, "on");
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_DIRECT, "off");
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off");
if (runstate_check(RUN_STATE_INMIGRATE)) {
bdrv_flags |= BDRV_O_INACTIVE;
}
blk = blk_new_open(qemu_opts_id(opts), file, NULL, bs_opts, bdrv_flags,
errp);
if (!blk) {
@@ -675,17 +684,6 @@ static BlockDriverState *bds_tree_init(QDict *bs_opts, Error **errp)
goto fail;
}
/* bdrv_open() defaults to the values in bdrv_flags (for compatibility
* with other callers) rather than what we want as the real defaults.
* Apply the defaults here instead. */
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_WB, "on");
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_DIRECT, "off");
qdict_set_default_str(bs_opts, BDRV_OPT_CACHE_NO_FLUSH, "off");
if (runstate_check(RUN_STATE_INMIGRATE)) {
bdrv_flags |= BDRV_O_INACTIVE;
}
bs = NULL;
ret = bdrv_open(&bs, NULL, NULL, bs_opts, bdrv_flags, errp);
if (ret < 0) {
@@ -704,19 +702,6 @@ fail:
return NULL;
}
void blockdev_close_all_bdrv_states(void)
{
BlockDriverState *bs, *next_bs;
QTAILQ_FOREACH_SAFE(bs, &monitor_bdrv_states, monitor_list, next_bs) {
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
bdrv_unref(bs);
aio_context_release(ctx);
}
}
static void qemu_opt_rename(QemuOpts *opts, const char *from, const char *to,
Error **errp)
{
@@ -1202,11 +1187,15 @@ void hmp_commit(Monitor *mon, const QDict *qdict)
}
}
static void blockdev_do_action(TransactionAction *action, Error **errp)
static void blockdev_do_action(TransactionActionKind type, void *data,
Error **errp)
{
TransactionAction action;
TransactionActionList list;
list.value = action;
action.type = type;
action.u.data = data;
list.value = &action;
list.next = NULL;
qmp_transaction(&list, false, NULL, errp);
}
@@ -1232,11 +1221,8 @@ void qmp_blockdev_snapshot_sync(bool has_device, const char *device,
.has_mode = has_mode,
.mode = mode,
};
TransactionAction action = {
.type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC,
.u.blockdev_snapshot_sync = &snapshot,
};
blockdev_do_action(&action, errp);
blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_SYNC,
&snapshot, errp);
}
void qmp_blockdev_snapshot(const char *node, const char *overlay,
@@ -1246,11 +1232,9 @@ void qmp_blockdev_snapshot(const char *node, const char *overlay,
.node = (char *) node,
.overlay = (char *) overlay
};
TransactionAction action = {
.type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT,
.u.blockdev_snapshot = &snapshot_data,
};
blockdev_do_action(&action, errp);
blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT,
&snapshot_data, errp);
}
void qmp_blockdev_snapshot_internal_sync(const char *device,
@@ -1261,11 +1245,9 @@ void qmp_blockdev_snapshot_internal_sync(const char *device,
.device = (char *) device,
.name = (char *) name
};
TransactionAction action = {
.type = TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC,
.u.blockdev_snapshot_internal_sync = &snapshot,
};
blockdev_do_action(&action, errp);
blockdev_do_action(TRANSACTION_ACTION_KIND_BLOCKDEV_SNAPSHOT_INTERNAL_SYNC,
&snapshot, errp);
}
SnapshotInfo *qmp_blockdev_snapshot_delete_internal_sync(const char *device,
@@ -1601,11 +1583,13 @@ static void internal_snapshot_abort(BlkActionState *common)
}
if (bdrv_snapshot_delete(bs, sn->id_str, sn->name, &local_error) < 0) {
error_reportf_err(local_error,
"Failed to delete snapshot with id '%s' and "
"name '%s' on device '%s' in abort: ",
sn->id_str, sn->name,
bdrv_get_device_name(bs));
error_report("Failed to delete snapshot with id '%s' and name '%s' on "
"device '%s' in abort: %s",
sn->id_str,
sn->name,
bdrv_get_device_name(bs),
error_get_pretty(local_error));
error_free(local_error);
}
}
@@ -1732,15 +1716,10 @@ static void external_snapshot_prepare(BlkActionState *common,
/* create new image w/backing file */
mode = s->has_mode ? s->mode : NEW_IMAGE_MODE_ABSOLUTE_PATHS;
if (mode != NEW_IMAGE_MODE_EXISTING) {
int64_t size = bdrv_getlength(state->old_bs);
if (size < 0) {
error_setg_errno(errp, -size, "bdrv_getlength failed");
return;
}
bdrv_img_create(new_image_file, format,
state->old_bs->filename,
state->old_bs->drv->format_name,
NULL, size, flags, &local_err, false);
NULL, -1, flags, &local_err, false);
if (local_err) {
error_propagate(errp, local_err);
return;
@@ -2521,8 +2500,6 @@ void qmp_blockdev_change_medium(const char *device, const char *filename,
}
bdrv_flags = blk_get_open_flags_from_root_state(blk);
bdrv_flags &= ~(BDRV_O_TEMPORARY | BDRV_O_SNAPSHOT | BDRV_O_NO_BACKING |
BDRV_O_PROTOCOL);
if (!has_read_only) {
read_only = BLOCKDEV_CHANGE_READ_ONLY_MODE_RETAIN;
@@ -2608,18 +2585,6 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
int64_t iops_rd_max,
bool has_iops_wr_max,
int64_t iops_wr_max,
bool has_bps_max_length,
int64_t bps_max_length,
bool has_bps_rd_max_length,
int64_t bps_rd_max_length,
bool has_bps_wr_max_length,
int64_t bps_wr_max_length,
bool has_iops_max_length,
int64_t iops_max_length,
bool has_iops_rd_max_length,
int64_t iops_rd_max_length,
bool has_iops_wr_max_length,
int64_t iops_wr_max_length,
bool has_iops_size,
int64_t iops_size,
bool has_group,
@@ -2646,7 +2611,7 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
goto out;
}
throttle_config_init(&cfg);
memset(&cfg, 0, sizeof(cfg));
cfg.buckets[THROTTLE_BPS_TOTAL].avg = bps;
cfg.buckets[THROTTLE_BPS_READ].avg = bps_rd;
cfg.buckets[THROTTLE_BPS_WRITE].avg = bps_wr;
@@ -2674,30 +2639,11 @@ void qmp_block_set_io_throttle(const char *device, int64_t bps, int64_t bps_rd,
cfg.buckets[THROTTLE_OPS_WRITE].max = iops_wr_max;
}
if (has_bps_max_length) {
cfg.buckets[THROTTLE_BPS_TOTAL].burst_length = bps_max_length;
}
if (has_bps_rd_max_length) {
cfg.buckets[THROTTLE_BPS_READ].burst_length = bps_rd_max_length;
}
if (has_bps_wr_max_length) {
cfg.buckets[THROTTLE_BPS_WRITE].burst_length = bps_wr_max_length;
}
if (has_iops_max_length) {
cfg.buckets[THROTTLE_OPS_TOTAL].burst_length = iops_max_length;
}
if (has_iops_rd_max_length) {
cfg.buckets[THROTTLE_OPS_READ].burst_length = iops_rd_max_length;
}
if (has_iops_wr_max_length) {
cfg.buckets[THROTTLE_OPS_WRITE].burst_length = iops_wr_max_length;
}
if (has_iops_size) {
cfg.op_size = iops_size;
}
if (!throttle_is_valid(&cfg, errp)) {
if (!check_throttle_config(&cfg, errp)) {
goto out;
}
@@ -2824,15 +2770,6 @@ void hmp_drive_del(Monitor *mon, const QDict *qdict)
AioContext *aio_context;
Error *local_err = NULL;
bs = bdrv_find_node(id);
if (bs) {
qmp_x_blockdev_del(false, NULL, true, id, &local_err);
if (local_err) {
error_report_err(local_err);
}
return;
}
blk = blk_by_name(id);
if (!blk) {
error_report("Device '%s' not found", id);
@@ -2856,7 +2793,7 @@ void hmp_drive_del(Monitor *mon, const QDict *qdict)
return;
}
blk_remove_bs(blk);
bdrv_close(bs);
}
/* if we have a device attached to this BlockDriverState
@@ -3381,23 +3318,29 @@ void qmp_blockdev_backup(const char *device, const char *target,
NULL, errp);
}
/* Parameter check and block job starting for drive mirroring.
* Caller should hold @device and @target's aio context (must be the same).
**/
static void blockdev_mirror_common(BlockDriverState *bs,
BlockDriverState *target,
bool has_replaces, const char *replaces,
enum MirrorSyncMode sync,
bool has_speed, int64_t speed,
bool has_granularity, uint32_t granularity,
bool has_buf_size, int64_t buf_size,
bool has_on_source_error,
BlockdevOnError on_source_error,
bool has_on_target_error,
BlockdevOnError on_target_error,
bool has_unmap, bool unmap,
Error **errp)
void qmp_drive_mirror(const char *device, const char *target,
bool has_format, const char *format,
bool has_node_name, const char *node_name,
bool has_replaces, const char *replaces,
enum MirrorSyncMode sync,
bool has_mode, enum NewImageMode mode,
bool has_speed, int64_t speed,
bool has_granularity, uint32_t granularity,
bool has_buf_size, int64_t buf_size,
bool has_on_source_error, BlockdevOnError on_source_error,
bool has_on_target_error, BlockdevOnError on_target_error,
bool has_unmap, bool unmap,
Error **errp)
{
BlockBackend *blk;
BlockDriverState *bs;
BlockDriverState *source, *target_bs;
AioContext *aio_context;
Error *local_err = NULL;
QDict *options;
int flags;
int64_t size;
int ret;
if (!has_speed) {
speed = 0;
@@ -3408,6 +3351,9 @@ static void blockdev_mirror_common(BlockDriverState *bs,
if (!has_on_target_error) {
on_target_error = BLOCKDEV_ON_ERROR_REPORT;
}
if (!has_mode) {
mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
}
if (!has_granularity) {
granularity = 0;
}
@@ -3429,55 +3375,6 @@ static void blockdev_mirror_common(BlockDriverState *bs,
return;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR_SOURCE, errp)) {
return;
}
if (bdrv_op_is_blocked(target, BLOCK_OP_TYPE_MIRROR_TARGET, errp)) {
return;
}
if (target->blk) {
error_setg(errp, "Cannot mirror to an attached block device");
return;
}
if (!bs->backing && sync == MIRROR_SYNC_MODE_TOP) {
sync = MIRROR_SYNC_MODE_FULL;
}
/* pass the node name to replace to mirror start since it's loose coupling
* and will allow to check whether the node still exist at mirror completion
*/
mirror_start(bs, target,
has_replaces ? replaces : NULL,
speed, granularity, buf_size, sync,
on_source_error, on_target_error, unmap,
block_job_cb, bs, errp);
}
void qmp_drive_mirror(const char *device, const char *target,
bool has_format, const char *format,
bool has_node_name, const char *node_name,
bool has_replaces, const char *replaces,
enum MirrorSyncMode sync,
bool has_mode, enum NewImageMode mode,
bool has_speed, int64_t speed,
bool has_granularity, uint32_t granularity,
bool has_buf_size, int64_t buf_size,
bool has_on_source_error, BlockdevOnError on_source_error,
bool has_on_target_error, BlockdevOnError on_target_error,
bool has_unmap, bool unmap,
Error **errp)
{
BlockDriverState *bs;
BlockBackend *blk;
BlockDriverState *source, *target_bs;
AioContext *aio_context;
Error *local_err = NULL;
QDict *options = NULL;
int flags;
int64_t size;
int ret;
blk = blk_by_name(device);
if (!blk) {
error_set(errp, ERROR_CLASS_DEVICE_NOT_FOUND,
@@ -3493,14 +3390,15 @@ void qmp_drive_mirror(const char *device, const char *target,
goto out;
}
bs = blk_bs(blk);
if (!has_mode) {
mode = NEW_IMAGE_MODE_ABSOLUTE_PATHS;
}
if (!has_format) {
format = mode == NEW_IMAGE_MODE_EXISTING ? NULL : bs->drv->format_name;
}
if (bdrv_op_is_blocked(bs, BLOCK_OP_TYPE_MIRROR, errp)) {
goto out;
}
flags = bs->open_flags | BDRV_O_RDWR;
source = backing_bs(bs);
if (!source && sync == MIRROR_SYNC_MODE_TOP) {
@@ -3595,81 +3493,25 @@ void qmp_drive_mirror(const char *device, const char *target,
bdrv_set_aio_context(target_bs, aio_context);
blockdev_mirror_common(bs, target_bs,
has_replaces, replaces, sync,
has_speed, speed,
has_granularity, granularity,
has_buf_size, buf_size,
has_on_source_error, on_source_error,
has_on_target_error, on_target_error,
has_unmap, unmap,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
/* pass the node name to replace to mirror start since it's loose coupling
* and will allow to check whether the node still exist at mirror completion
*/
mirror_start(bs, target_bs,
has_replaces ? replaces : NULL,
speed, granularity, buf_size, sync,
on_source_error, on_target_error,
unmap,
block_job_cb, bs, &local_err);
if (local_err != NULL) {
bdrv_unref(target_bs);
error_propagate(errp, local_err);
goto out;
}
out:
aio_context_release(aio_context);
}
void qmp_blockdev_mirror(const char *device, const char *target,
bool has_replaces, const char *replaces,
MirrorSyncMode sync,
bool has_speed, int64_t speed,
bool has_granularity, uint32_t granularity,
bool has_buf_size, int64_t buf_size,
bool has_on_source_error,
BlockdevOnError on_source_error,
bool has_on_target_error,
BlockdevOnError on_target_error,
Error **errp)
{
BlockDriverState *bs;
BlockBackend *blk;
BlockDriverState *target_bs;
AioContext *aio_context;
Error *local_err = NULL;
blk = blk_by_name(device);
if (!blk) {
error_setg(errp, "Device '%s' not found", device);
return;
}
bs = blk_bs(blk);
if (!bs) {
error_setg(errp, "Device '%s' has no media", device);
return;
}
target_bs = bdrv_lookup_bs(target, target, errp);
if (!target_bs) {
return;
}
aio_context = bdrv_get_aio_context(bs);
aio_context_acquire(aio_context);
bdrv_ref(target_bs);
bdrv_set_aio_context(target_bs, aio_context);
blockdev_mirror_common(bs, target_bs,
has_replaces, replaces, sync,
has_speed, speed,
has_granularity, granularity,
has_buf_size, buf_size,
has_on_source_error, on_source_error,
has_on_target_error, on_target_error,
true, true,
&local_err);
if (local_err) {
error_propagate(errp, local_err);
bdrv_unref(target_bs);
}
aio_context_release(aio_context);
}
/* Get the block job for a given device name and acquire its AioContext */
static BlockJob *find_block_job(const char *device, AioContext **aio_context,
Error **errp)
@@ -3884,36 +3726,6 @@ out:
aio_context_release(aio_context);
}
void hmp_drive_add_node(Monitor *mon, const char *optstr)
{
QemuOpts *opts;
QDict *qdict;
Error *local_err = NULL;
opts = qemu_opts_parse_noisily(&qemu_drive_opts, optstr, false);
if (!opts) {
return;
}
qdict = qemu_opts_to_qdict(opts, NULL);
if (!qdict_get_try_str(qdict, "node-name")) {
error_report("'node-name' needs to be specified");
goto out;
}
BlockDriverState *bs = bds_tree_init(qdict, &local_err);
if (!bs) {
error_report_err(local_err);
goto out;
}
QTAILQ_INSERT_TAIL(&monitor_bdrv_states, bs, monitor_list);
out:
qemu_opts_del(opts);
}
void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
{
QmpOutputVisitor *ov = qmp_output_visitor_new();
@@ -3938,8 +3750,8 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
}
}
visit_type_BlockdevOptions(qmp_output_get_visitor(ov), NULL, &options,
&local_err);
visit_type_BlockdevOptions(qmp_output_get_visitor(ov),
&options, NULL, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto fail;
@@ -3969,15 +3781,12 @@ void qmp_blockdev_add(BlockdevOptions *options, Error **errp)
if (!bs) {
goto fail;
}
QTAILQ_INSERT_TAIL(&monitor_bdrv_states, bs, monitor_list);
}
if (bs && bdrv_key_required(bs)) {
if (blk) {
blk_unref(blk);
} else {
QTAILQ_REMOVE(&monitor_bdrv_states, bs, monitor_list);
bdrv_unref(bs);
}
error_setg(errp, "blockdev-add doesn't support encrypted devices");
@@ -4037,13 +3846,7 @@ void qmp_x_blockdev_del(bool has_id, const char *id,
goto out;
}
if (!blk && !bs->monitor_list.tqe_prev) {
error_setg(errp, "Node %s is not owned by the monitor",
bs->node_name);
goto out;
}
if (bs->refcnt > 1) {
if (bs->refcnt > 1 || !QLIST_EMPTY(&bs->parents)) {
error_setg(errp, "Block device %s is in use",
bdrv_get_device_or_node_name(bs));
goto out;
@@ -4053,7 +3856,6 @@ void qmp_x_blockdev_del(bool has_id, const char *id,
if (blk) {
blk_unref(blk);
} else {
QTAILQ_REMOVE(&monitor_bdrv_states, bs, monitor_list);
bdrv_unref(bs);
}
@@ -4096,6 +3898,18 @@ QemuOptsList qemu_common_drive_opts = {
.name = "discard",
.type = QEMU_OPT_STRING,
.help = "discard operation (ignore/off, unmap/on)",
},{
.name = BDRV_OPT_CACHE_WB,
.type = QEMU_OPT_BOOL,
.help = "enables writeback mode for any caches",
},{
.name = BDRV_OPT_CACHE_DIRECT,
.type = QEMU_OPT_BOOL,
.help = "enables use of O_DIRECT (bypass the host page cache)",
},{
.name = BDRV_OPT_CACHE_NO_FLUSH,
.type = QEMU_OPT_BOOL,
.help = "ignore any flush requests for the device",
},{
.name = "aio",
.type = QEMU_OPT_STRING,
@@ -4164,30 +3978,6 @@ QemuOptsList qemu_common_drive_opts = {
.name = "throttling.bps-write-max",
.type = QEMU_OPT_NUMBER,
.help = "total bytes write burst",
},{
.name = "throttling.iops-total-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the iops-total-max burst period, in seconds",
},{
.name = "throttling.iops-read-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the iops-read-max burst period, in seconds",
},{
.name = "throttling.iops-write-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the iops-write-max burst period, in seconds",
},{
.name = "throttling.bps-total-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the bps-total-max burst period, in seconds",
},{
.name = "throttling.bps-read-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the bps-read-max burst period, in seconds",
},{
.name = "throttling.bps-write-max-length",
.type = QEMU_OPT_NUMBER,
.help = "length of the bps-write-max burst period, in seconds",
},{
.name = "throttling.iops-size",
.type = QEMU_OPT_NUMBER,
@@ -4227,6 +4017,18 @@ static QemuOptsList qemu_root_bds_opts = {
.name = "discard",
.type = QEMU_OPT_STRING,
.help = "discard operation (ignore/off, unmap/on)",
},{
.name = "cache.writeback",
.type = QEMU_OPT_BOOL,
.help = "enables writeback mode for any caches",
},{
.name = "cache.direct",
.type = QEMU_OPT_BOOL,
.help = "enables use of O_DIRECT (bypass the host page cache)",
},{
.name = "cache.no-flush",
.type = QEMU_OPT_BOOL,
.help = "ignore any flush requests for the device",
},{
.name = "aio",
.type = QEMU_OPT_STRING,

View File

@@ -23,7 +23,7 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "config-host.h"
#include "qemu-common.h"
#include "trace.h"
#include "block/block.h"
@@ -278,6 +278,14 @@ void block_job_iostatus_reset(BlockJob *job)
}
}
struct BlockFinishData {
BlockJob *job;
BlockCompletionFunc *cb;
void *opaque;
bool cancelled;
int ret;
};
static int block_job_finish_sync(BlockJob *job,
void (*finish)(BlockJob *, Error **errp),
Error **errp)
@@ -296,9 +304,7 @@ static int block_job_finish_sync(BlockJob *job,
return -EBUSY;
}
while (!job->completed) {
aio_poll(job->deferred_to_main_loop ? qemu_get_aio_context() :
bdrv_get_aio_context(bs),
true);
aio_poll(bdrv_get_aio_context(bs), true);
}
ret = (job->cancelled && job->ret == 0) ? -ECANCELED : job->ret;
block_job_unref(job);
@@ -472,7 +478,6 @@ static void block_job_defer_to_main_loop_bh(void *opaque)
aio_context = bdrv_get_aio_context(data->job->bs);
aio_context_acquire(aio_context);
data->job->deferred_to_main_loop = false;
data->fn(data->job, data->opaque);
aio_context_release(aio_context);
@@ -492,7 +497,6 @@ void block_job_defer_to_main_loop(BlockJob *job,
data->aio_context = bdrv_get_aio_context(job->bs);
data->fn = fn;
data->opaque = opaque;
job->deferred_to_main_loop = true;
qemu_bh_schedule(data->bh);
}

View File

@@ -22,7 +22,6 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "sysemu/sysemu.h"
#include "qapi/visitor.h"
#include "qemu/error-report.h"
@@ -271,21 +270,21 @@ typedef struct {
DeviceState *dev;
} BootIndexProperty;
static void device_get_bootindex(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
static void device_get_bootindex(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
BootIndexProperty *prop = opaque;
visit_type_int32(v, name, prop->bootindex, errp);
visit_type_int32(v, prop->bootindex, name, errp);
}
static void device_set_bootindex(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
static void device_set_bootindex(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
BootIndexProperty *prop = opaque;
int32_t boot_index;
Error *local_err = NULL;
visit_type_int32(v, name, &boot_index, &local_err);
visit_type_int32(v, &boot_index, name, &local_err);
if (local_err) {
goto out;
}

Some files were not shown because too many files have changed in this diff Show More