Compare commits

..

119 Commits

Author SHA1 Message Date
Michael Roth
f053f6b83d Update VERSION for 2.0.2 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-18 11:00:53 -05:00
Luiz Capitulino
3d79eb5b30 audio: fmopl: drop INLINE macro
This commit expands all uses of the INLINE macro and drop it.

The reason for this is to avoid clashes with external libraries with
bad name conventions and also because renaming keywords is not a good
practice.

Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
(cherry picked from commit 37f6be977a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-17 11:43:40 -05:00
Luiz Capitulino
6ec48b09b7 fpu: softfloat: drop INLINE macro
This commit expands all uses of the INLINE macro and drop it.

The reason for this is to avoid clashes with external libraries with
bad name conventions and also because renaming keywords is not a good
practice.

PS: I'm fine with this change to be licensed under softfloat-2a or
softfloat-2b.

Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
(cherry picked from commit a49db98d1f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-17 11:42:00 -05:00
Michael Roth
543347215c Update VERSION for 2.0.1 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-15 15:51:19 -05:00
Kevin Wolf
3c548f6700 mirror: Fix qiov size for short requests
When mirroring an image of a size that is not a multiple of the
mirror job granularity, the last request would have the right nb_sectors
argument, but a qiov that is rounded up to the next multiple of the
granularity. Don't do this.

This fixes a segfault that is caused by raw-posix being confused by this
and allocating a buffer with request length, but operating on it with
qiov length.

[s/Driver/Drive/ in qemu-iotests 041 as suggested by Eric
--Stefan]

Reported-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Tested-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 5a0f6fd5c8)

Conflicts:
	tests/qemu-iotests/041.out

*updated 041.out to reflect tests missing from 2.0

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 17:59:15 -05:00
Fam Zheng
d0d83e8fe7 qemu-iotests: Test 0-length image for mirror
All behavior and invariant should hold for images with 0 length, so
add a class to repeat all the tests in TestSingleDrive.

Hide two unapplicable test methods that would fail with 0 image length
because it's also used as cluster size.

Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3b9f27d2b3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 17:42:39 -05:00
Jeff Cody
98103fa736 block: make 'top' argument to block-commit optional
Now that active layer block-commit is supported, the 'top' argument
no longer needs to be mandatory.

Change it to optional, with the default being the active layer in the
device chain.

[kwolf: Rebased and resolved conflict in tests/qemu-iotests/040]

Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 7676e2c597)

Conflicts:
	qapi/block-core.json

*removed dependency on 1ad166b6

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 03:58:45 -05:00
Fam Zheng
e5f0eb06a8 qemu-iotests: Test BLOCK_JOB_READY event for 0Kb image active commit
There should be a BLOCK_JOB_READY event with active commit, regardless
of image length. Let's test the 0 length image case, and make sure it
goes through the ready->complete process.

Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 8b9a30ca5b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 03:52:48 -05:00
Fam Zheng
43ac708d4c mirror: Go through ready -> complete process for 0 len image
When mirroring or active committing a zero length image, BLOCK_JOB_READY
is not reported now, instead the job completes because we short circuit
the mirror job loop.

This is inconsistent with non-zero length images, and only confuses
management software.

Let's do the same thing when seeing a 0-length image: report ready
immediately; wait for block-job-cancel or block-job-complete; clear the
cancel flag as existing non-zero image synced case (cancelled after
ready); then jump to the exit.

Reported-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 9e48b02540)

*removed dependency on bcada37b

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 03:50:04 -05:00
Fam Zheng
8e09e2013d blockjob: Add block_job_yield()
This will unset busy flag and put coroutine to sleep, can be used to
wait for QMP complete/cancel.

Signed-off-by: Fam Zheng <famz@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit dc71ce45de)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 03:39:35 -05:00
Fam Zheng
520b341264 mirror: Fix resource leak when bdrv_getlength fails
The direct return will skip releasing of all the resouces at
immediate_exit, don't miss that.

Signed-off-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 373df5b135)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-07 03:24:19 -05:00
Peter Maydell
e0efb023c0 hw/arm/boot: Set PC correctly when loading AArch64 ELF files
The code in do_cpu_reset() correctly handled AArch64 CPUs
when running Linux kernels, but was missing code in the
branch of the if() that deals with loading ELF files.
Correctly jump to the ELF entry point on reset rather than
leaving the reset PC at zero.

Reported-by: Christopher Covington <cov@codeaurora.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Tested-by: Christopher Covington <cov@codeaurora.org>
Cc: qemu-stable@nongnu.org
(cherry picked from commit a9047ec3f6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 15:09:41 -05:00
Peter Maydell
d56b0b85c8 hw/misc/imx_ccm.c: Add missing VMState list terminator
The VMStateDescription for the imx_ccm device was missing its
terminator. Found by static search of the codebase using
a regex based on one suggested by Ian Jackson:
  pcregrep -rMi '(?s)VMStateField(?:(?!END_OF_LIST).)*?;' $(git grep -l 'VMStateField\[\]')

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable@nongnu.org
(cherry picked from commit ef493d5c29)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Laszlo Ersek
750f169519 vmstate_xhci_event: fix unterminated field list
"vmstate_xhci_event" was introduced in commit 37352df3 ("xhci: add live
migration support"), and first released in v1.6.0. The field list in this
VMSD is not terminated with the VMSTATE_END_OF_LIST() macro.

During normal use (ie. migration), the issue is practically invisible,
because the "vmstate_xhci_event" object (with the unterminated field list)
is only ever referenced -- via "vmstate_xhci_intr" -- if xhci_er_full()
returns true, for the "ev_buffer" test. Since that field_exists() check
(apparently) almost always returns false, we almost never traverse
"vmstate_xhci_event" during migration, which hides the bug.

However, Amit's vmstate checker forces recursion into this VMSD as well,
and the lack of VMSTATE_END_OF_LIST() breaks the field list terminator
check (field->name != NULL) in dump_vmstate_vmsd(). The result is
undefined behavior, which in my case translates to infinite recursion
(because the loop happens to overflow into "vmstate_xhci_intr", which then
links back to "vmstate_xhci_event").

Add the missing terminator.

Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Amit Shah <amit.shah@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 3afca1d6d4)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Chen Gang
046e357379 kvm-all: Use 'tmpcpu' instead of 'cpu' in sub-looping to avoid 'cpu' be NULL
If kvm_arch_remove_sw_breakpoint() in CPU_FOREACH() always be fail, it
will let 'cpu' NULL. And the next kvm_arch_remove_sw_breakpoint() in
QTAILQ_FOREACH_SAFE() will get NULL parameter for 'cpu'.

And kvm_arch_remove_sw_breakpoint() can assumes 'cpu' must never be NULL,
so need define additional temporary variable for 'cpu' to avoid the case.

Cc: qemu-stable@nongnu.org
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit dc54e25253)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
KONRAD Frederic
b1251db258 cadence_uart: check for serial backend before using it.
This checks that s->chr is not NULL before using it.

Signed-off-by: KONRAD Frederic <fred.konrad@greensocs.com>
Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit af52fe862f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Jason J. Herne
29cffd368a s390x/kvm: synchronize guest floating point registers
Add code to kvm_arch_get_registers and kvm_arch_put_registers to
save/restore floating point registers. This missing sync was
unnoticed until migration of userspace that uses fprs.

Signed-off-by: Jason J. Herne <jjherne@us.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
[Update patch to latest upstream]
Cc: qemu-stable@nongnu.org
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>

(cherry picked from commit 85ad6230b3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Stefano Stabellini
5a782bbcae disas/libvixl: prepend the include path of libvixl header files
Currently the Makefile of disas/libvixl appends
-I$(SRC_PATH)/disas/libvixl to QEMU_CFLAGS. As a consequence C++ files
that #include "utils.h", such as disas/libvixl/a64/instructions-a64.cc,
are going to look for utils.h on all the other include paths first.

When building QEMU as part of the Xen make system, another unrelated
utils.h file is going to be chosen for inclusion, causing a build
failure:

In file included from disas/libvixl/a64/instructions-a64.cc:27:0:
/qemu/disas/libvixl/a64/instructions-a64.h:88:64: error:
'rawbits_to_float' was not declared in this scope
 const float kFP32PositiveInfinity = rawbits_to_float(0x7f800000);

Fix the problem by prepending (rather than appending) the libvixl
include path to QEMU_CFLAGS.

Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 834fb1b269)

*added 2.0-specific fixup from Stefano in disas/Makefile.obj due to
 lack of 849d8284

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Paolo Bonzini
ad0d183175 mc146818rtc: register the clock reset notifier on the right clock
Commit 884f17c (aio / timers: Convert rtc_clock to be a QEMUClockType,
2013-08-21) erroneously changed an occurrence of rtc_clock to
QEMU_CLOCK_REALTIME, which broke the RTC reset notifier in
mc146818rtc.  Fix this.

I redid the patch myself since the original reporter did not sign
off on his.

Cc: qemu-stable@nongnu.org
Reported-by: Lb peace <peaceustc@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 13c0cbaec5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Le Tan
210ec8f757 pci: assign devfn to pci_dev before calling pci_device_iommu_address_space()
In function do_pci_register_device() in file hw/pci/pci.c, move the assignment
of pci_dev->devfn to the position before the call to
pci_device_iommu_address_space(pci_dev) which will use the value of
pci_dev->devfn.

Fixes: 9eda7d373e
    pci: Introduce helper to retrieve a PCI device's DMA address space

Cc: qemu-stable@nongnu.org
Signed-off-by: Le Tan <tamlokveer@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit efc8188e93)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:49 -05:00
Dr. David Alan Gilbert
55103ab3b4 Allow mismatched virtio config-len
Commit 'virtio: validate config_len on load' restricted config_len
loaded from the wire to match the config_len that the device had.

Unfortunately, there are cases where this isn't true, the one
we found it on was the wce addition in virtio-blk.

Allow mismatched config-lengths:
   *) If the version on the wire is shorter then fine
   *) If the version on the wire is longer, load what we have space
      for and skip the rest.

(This is mst@redhat.com's rework of what I originally posted)

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 2f5732e964)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:48 -05:00
Michael S. Tsirkin
3bb84a6c98 virtio: validate config_len on load
Malformed input can have config_len in migration stream
exceed the array size allocated on destination, the
result will be heap overflow.

To fix, that config_len matches on both sides.

CVE-2014-0182

Reported-by: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>

--

v2: use %ix and %zx to print config_len values
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit a890a2f913)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:48 -05:00
Michael S. Tsirkin
48935f029f virtio: out-of-bounds buffer write on invalid state load
CVE-2013-4151 QEMU 1.0 out-of-bounds buffer write in
virtio_load@hw/virtio/virtio.c

So we have this code since way back when:

    num = qemu_get_be32(f);

    for (i = 0; i < num; i++) {
        vdev->vq[i].vring.num = qemu_get_be32(f);

array of vqs has size VIRTIO_PCI_QUEUE_MAX, so
on invalid input this will write beyond end of buffer.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit cc45995294)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 14:55:48 -05:00
Andreas Färber
3477445077 hw: Fix qemu_allocate_irqs() leaks
Replace qemu_allocate_irqs(foo, bar, 1)[0]
with qemu_allocate_irq(foo, bar, 0).

This avoids leaking the dereferenced qemu_irq *.

Cc: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Andreas Färber <afaerber@suse.de>
[PC Changes:
 * Applied change to instance in sh4/sh7750.c
]
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Reviewed-by: Kirill Batuzov <batuzovk@ispras.ru>
[AF: Fix IRQ index in sh4/sh7750.c]
Cc: qemu-stable@nongnu.org
Signed-off-by: Andreas Färber <afaerber@suse.de>

(cherry picked from commit f3c7d0389f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 11:56:14 -05:00
Andreas Färber
7be09afb61 sdhci: Fix misuse of qemu_free_irqs()
It does a g_free() on the pointer, so don't pass a local &foo reference.

Reviewed-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable@nongnu.org
Signed-off-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit 127a4e1a51)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 11:53:56 -05:00
Don Slutz
cab7dfcb06 pc: make isapc and pc-0.10 to pc-0.13 have 1.7.0 memory layout
QEMU 2.0 changed memory layout for isapc and pc-0.10 to pc-0.13.
This prevents migration from QEMU 1.7.0 for these
machine types when -m 3.5G is specified.

Paolo Bonzini asked that:

    smbios_legacy_mode = true;
    has_reserved_memory = false;
    option_rom_has_mr = true;
    rom_file_has_mr = false;

also be done.

Cc: qemu-stable@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Don Slutz <dslutz@verizon.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Fixes: https://bugs.launchpad.net/qemu/+bug/1334307
Tested-by: "Slutz, Donald Christopher" <dslutz@verizon.com>
(cherry picked from commit 5f8632d3c3)

Conflicts:
	hw/i386/pc_piix.c

*removed dependency on c97294ec: smbios_legacy_mode always true pre-2.1.0
*removed dependency on de268e13: has_reserved_memory always false pre-2.1.0

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-06 11:46:52 -05:00
Gabriel L. Somlo
b5706a74b1 SMBIOS: Rename symbols to better reflect future use
Rename the following symbols:

  - smbios_set_type1_defaults() to the more general smbios_set_defaults();
  - bool smbios_type1_defaults to the more general smbios_defaults;
  - smbios_get_table() to smbios_get_table_legacy();

This patch contains no functional changes.

Signed-off-by: Gabriel Somlo <somlo@cmu.edu>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit e6667f719c)

Conflicts:
	hw/i386/pc_piix.c
	hw/i386/pc_q35.c

*removed dependency on 3458b2b0

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:33:01 -05:00
Hani Benhabiles
41971817a6 nbd: Shutdown socket before closing.
This forces finishing data sending to client before closing the socket like in
exports listing or replying with NBD_REP_ERR_UNSUP cases.

Signed-off-by: Hani Benhabiles <kroosec@gmail.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 27e5eae457)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:19:27 -05:00
Hani Benhabiles
3f977a5be8 nbd: Close socket on negotiation failure.
Otherwise, the nbd client may hang waiting for the server response.

Signed-off-by: Hani Benhabiles <hani@linux.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
(cherry picked from commit 36af599417)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:19:22 -05:00
Hani Benhabiles
80cfe4a43f nbd: Don't validate from and len in NBD_CMD_DISC.
These values aren't used in this case.

Currently, the from field in the request sent by the nbd kernel module leading
to a false error message when ending the connection with the client.

$ qemu-nbd some.img -v
// After nbd-client -d /dev/nbd0
nbd.c:nbd_trip():L1031: From: 18446744073709551104, Len: 0, Size: 20971520,
Offset: 0
nbd.c:nbd_trip():L1032: requested operation past EOF--bad client?
nbd.c:nbd_receive_request():L638: read failed

Signed-off-by: Hani Benhabiles <kroosec@gmail.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 8c5d1abbb7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:17:53 -05:00
Hani Benhabiles
01083f16de nbd: Don't export a block device with no medium.
The device is exported with erroneous values and can't be read.

Before the patch:
$ sudo nbd-client localhost -p 10809 /dev/nbd0 -name floppy0
Negotiation: ..size = 17592186044415MB
bs=1024, sz=18446744073709547520 bytes

$ sudo mount /dev/nbd0 /mnt/tmp/
mount: block device /dev/nbd0 is write-protected, mounting read-only
mount: /dev/nbd0: can't read superblock

After the patch:
(qemu) nbd_server_add ide0-hd0
(qemu) nbd_server_add floppy0
Device 'floppy0' has no medium

Signed-off-by: Hani Benhabiles <kroosec@gmail.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 60fe4fac22)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:17:41 -05:00
Alexander Graf
9221efd775 virtio-serial: don't migrate the config space
The device configuration is set at realize time and never changes. It
should not be migrated as it is done today. For the sake of compatibility,
let's just skip them at load time.

Signed-off-by: Alexander Graf <agraf@suse.de>
[ added missing casts to uint16_t *,
  added From, SoB and commit message,
  Greg Kurz <gkurz@linux.vnet.ibm.com> ]
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

(cherry picked from commit e38e943a1f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:16:50 -05:00
Cédric Le Goater
4ce91be0c3 virtio-net: byteswap virtio-net header
TCP connectivity fails when the guest has a different endianness.
The packets are silently dropped on the host by the tap backend
when they are read from user space because the endianness of the
virtio-net header is in the wrong order. These lines may appear
in the guest console:

[  454.709327] skbuff: bad partial csum: csum=8704/4096 len=74
[  455.702554] skbuff: bad partial csum: csum=8704/4096 len=74

The issue that got first spotted with a ppc64le PowerKVM guest,
but it also exists for the less common case of a x86_64 guest run
by a big-endian ppc64 TCG hypervisor.

Signed-off-by: Cédric Le Goater <clg@fr.ibm.com>
[ Ported from PowerKVM,
  Greg Kurz <gkurz@linux.vnet.ibm.com> ]
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

(cherry picked from commit 032a74a1c0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:16:30 -05:00
Eduardo Habkost
b2f0e9240b target-i386: Filter FEAT_7_0_EBX TCG features too
The TCG_7_0_EBX_FEATURES macro was defined but never used (it even had a
typo that was never noticed). Make the existing TCG feature filtering
code use it.

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit d0a70f46fa)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:14:43 -05:00
Eduardo Habkost
f9ac1dc507 target-i386: Make TCG feature filtering more readable
Instead of an #ifdef in the middle of the code, just set
TCG_EXT2_FEATURES to a different value depending on TARGET_X86_64.

Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit a42d9938a1)

Conflicts:
	target-i386/cpu.c

*removed dependency on 77549a78

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:13:15 -05:00
Max Filippov
a1d82075ab hw/xtensa/xtfpga: fix FLASH mapping to boot region for KC705
On KC705 bootloader area is located at FLASH offset 0x06000000, not 0 as
on older xtfpga boards.

Cc: qemu-stable@nongnu.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
(cherry picked from commit 37ed7c4b24)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:05:20 -05:00
Peter Maydell
e4b3a2b349 coroutine-win32.c: Add noinline attribute to work around gcc bug
A gcc codegen bug in x86_64-w64-mingw32-gcc (GCC) 4.6.3 means that
non-debug builds of QEMU for Windows tend to assert when using
coroutines. Work around this by marking qemu_coroutine_switch
as noinline.

If we allow gcc to inline qemu_coroutine_switch into
coroutine_trampoline, then it hoists the code to get the
address of the TLS variable "current" out of the while() loop.
This is an invalid transformation because the SwitchToFiber()
call may be called when running thread A but return in thread B,
and so we might be in a different thread context each time
round the loop. This can happen quite often.  Typically.
a coroutine is started when a VCPU thread does bdrv_aio_readv:

     VCPU thread

     main VCPU thread coroutine      I/O coroutine
        bdrv_aio_readv ----->
                                     start I/O operation
                                       thread_pool_submit_co
                       <------------ yields
        back to emulation

Then I/O finishes and the thread-pool.c event notifier triggers in
the I/O thread.  event_notifier_ready calls thread_pool_co_cb, and
the I/O coroutine now restarts *in another thread*:

     iothread

     main iothread coroutine         I/O coroutine (formerly in VCPU thread)
        event_notifier_ready
          thread_pool_co_cb ----->   current = I/O coroutine;
                                     call AIO callback

But on Win32, because of the bug, the "current" being set here the
current coroutine of the VCPU thread, not the iothread.

noinline is a good-enough workaround, and quite unlikely to break in
the future.

(Thanks to Paolo Bonzini for assistance in diagnosing the problem
and providing the detailed example/ascii art quoted above.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 1403535303-14939-1-git-send-email-peter.maydell@linaro.org
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
(cherry picked from commit ff4873cb8c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:03:00 -05:00
Eduardo Habkost
84461c74b7 q35: Use PC_Q35_COMPAT_1_4 on pc-q35-1.4 compat_props
pc-q35-1.4 was incorrectly using PC_COMPAT_1_4 instead of
PC_Q35_COMPAT_1_4.

The only side-effect was that the hpet compat property (inherited from
PC_Q35_COMPAT_1_7) was missing.

Without this patch, pc-q35-1.4 inicorrectly initializes hpet-intcap to
0xff0104 (behavior introduced in QEMU 2.0, by commit
7a10ef51c2).

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

Reviewed-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 48cb7f3c15)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:02:09 -05:00
Alexander Graf
552e70d844 KVM: Fix GSI number space limit
KVM tells us the number of GSIs it can handle inside the kernel. That value is
basically KVM_MAX_IRQ_ROUTES. However when we try to set the GSI mapping table,
it checks for

    r = -EINVAL;
    if (routing.nr >= KVM_MAX_IRQ_ROUTES)
        goto out;

erroring out even when we're only using all of the GSIs. To make sure we never
hit that limit, let's reduce the number of GSIs we get from KVM by one.

Cc: qemu-stable@nongnu.org
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 00008418aa)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:01:11 -05:00
Hani Benhabiles
6ef0b7a992 usb: Fix usb-bt-dongle initialization.
Due to an incomplete initialization, adding a usb-bt-dongle device through HMP
or QMP will cause a segmentation fault.

Signed-off-by: Hani Benhabiles <hani@linux.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit c340a284f3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 14:00:31 -05:00
Ming Lei
aa69eda237 virtio-scsi: define dummy handle_output for vhost-scsi vqs
vhost userspace needn't to handle vq's notification from guest,
so define dummy handle_output callback for all vqs of vhost-scsi.

In some corner cases(such as when handling vq's reset from VM), virtio-pci
still trys to handle pending virtio-scsi events, then object check failure
inside virtio_scsi_handle_event() for vhost-scsi can be triggered.

The issue can be reproduced by 'rmmod virtio-scsi', 'system sleep' or reboot
inside VM.

Cc: qemu-stable@nongnu.org
Cc: Anthony Liguori <aliguori@amazon.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Ming Lei <ming.lei@canonical.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 91d670fbf9)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:58:37 -05:00
Michael S. Tsirkin
8dedaf0f70 vhost: fix resource leak in error handling
vhost_verify_ring_mappings leaks mappings on error.
Fix this up.

Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

(cherry picked from commit 8617343faa)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:57:04 -05:00
Ulrich Obergfell
eb3eb3dd36 scsi-disk: fix bug in scsi_block_new_request() introduced by commit 137745c
This patch fixes a bug in scsi_block_new_request() that was introduced
by commit 137745c5c6. If the host cache
is used - i.e. if BDRV_O_NOCACHE is _not_ set - the 'break' statement
needs to be executed to 'fall back' to SG_IO.

Cc: qemu-stable@nongnu.org
Signed-off-by: Ulrich Obergfell <uobergfe@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 2fe5a9f73b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:56:29 -05:00
Paolo Bonzini
88efef64db qdev: recursively unrealize devices when unrealizing bus
When the patch was posted that became 5c21ce7 (qdev: Realize buses
on device realization, 2014-03-12), it included recursive realization
and unrealization of devices when the bus's "realized" property
was toggled.

However, due to the same old worries about recursive realization
and prerequisites not being realized yet, those hunks were dropped when
committing the patch.  Unfortunately, this causes a use-after-free bug
(easily reproduced by a PCI hot-unplug action).

Before the patch, device_unparent behaved as follows:

   for each child bus
     unparent bus ----------------------------.
     | for each child device                  |
     |   unparent device ---------------.     |
     |   | unrealize device             |     |
     |   | call dc->unparent            |     |
     |   '-------------------------------     |
     '----------------------------------------'
   unrealize device

After the patch, it behaves as follows instead:

   unrealize device --------------------.
   | for each child bus                 |
   |   unrealize bus               (A)  |
   '------------------------------------'
   for each child bus
     unparent bus ----------------------.
     | for each child device            |
     |   unrealize device          (B)  |
     |   call dc->unparent              |
     '----------------------------------'

At the step marked (B) the device might use data from the bus that is
not available anymore due to step (A).

To fix this, we need to unrealize devices before step (A).  To sidestep
concerns about recursive realization, only do recursive unrealization
and leave the "value && !bus->realized" case as it is.

The resulting flow is:

   for each child bus
     unrealize bus ---------------------.
     | for each child device            |
     |   unrealize device          (B)  |
     | call bc->unrealize          (A)  |
     '----------------------------------'
   unrealize device
   for each child bus
     unparent bus ----------------------.
     | for each child device            |
     |   unparent device                |
     '----------------------------------'

where everything is "powered down" before it is unassembled.

Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit 5942a19040)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:55:40 -05:00
Paolo Bonzini
ab139bf9d2 qdev: reorganize error reporting in bus_set_realized
No semantic change.

Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit b7b34d055d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:55:07 -05:00
Markus Armbruster
d728dafe5a hw: Consistently name Error ** objects errp, and not err
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit a7737e4496)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:54:57 -05:00
Michael R. Hines
0f00455b4c rdma: bug fixes
1. Fix small memory leak in parsing inet address from command line in data_init()
2. Fix ibv_post_send() return value check and pass error code back up correctly.
3. Fix rdma_destroy_qp() segfault after failure to connect to destination.

Reported-by: frank.yangjie@gmail.com
Reported-by: dgilbert@redhat.com
Signed-off-by: Michael R. Hines <mrhines@us.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit e325b49a32)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:47:52 -05:00
Peter Lieven
6ea6bd5d75 migration: catch unknown flags in ram_load
if a saved vm has unknown flags in the memory data qemu
currently simply ignores this flag and continues which
yields in an unpredictable result.

This patch catches all unknown flags and aborts the
loading of the vm. Additionally error reports are thrown
if the migration aborts abnormally.

Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit db80facefa)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:45:18 -05:00
Chen Gang
86cfc10440 arch_init: Be sure of only one exit entry with DPRINTF() for ram_load()
When DPRINTF() has effect, the original author wants to print all
ram_load() calling results. So need use 'goto' instead of 'return'
within ram_load(), just like other areas have done.

Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
(cherry picked from commit 4798fe55c4)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:45:11 -05:00
ChenLiang
fe7e98c46e migration: remove duplicate code
version_id is checked twice in the ram_load.

Signed-off-by: ChenLiang <chenliang88@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 21a246a43b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:45:05 -05:00
Gonglei
ba980a52d6 qga: Fix handle fd leak in acquire_privilege()
token should be closed in all conditions.
So move CloseHandle(token) to "out" branch.

Signed-off-by: Wang Rui <moon.wangrui@huawei.com>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
(cherry picked from commit 374044f08f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:41:28 -05:00
Stefan Hajnoczi
df54f5efed aio: fix qemu_bh_schedule() bh->ctx race condition
qemu_bh_schedule() is supposed to be thread-safe at least the first time
it is called.  Unfortunately this is not quite true:

  bh->scheduled = 1;
  aio_notify(bh->ctx);

Since another thread may run the BH callback once it has been scheduled,
there is a race condition if the callback frees the BH before
aio_notify(bh->ctx) has a chance to run.

Reported-by: Stefan Priebe <s.priebe@profihost.ag>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Stefan Priebe <s.priebe@profihost.ag>
(cherry picked from commit 924fe1293c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:35:17 -05:00
Cornelia Huck
0d38666664 s390x/css: handle emw correctly for tsch
We should not try to store the emw portion of the irb if extended
measurements are not applicable. In particular, we should not surprise
the guest by storing a larger irb if it did not enable extended
measurements.

Cc: qemu-stable@nongnu.org
Reviewed-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit f068d320de)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:34:34 -05:00
Peter Maydell
27fb65dd1b target-arm: Fix errors in writes to generic timer control registers
The code for handling writes to the generic timer control registers
had several bugs:
 * ISTATUS (bit 2) is read-only but we forced it to zero on any write
 * the check for "was IMASK (bit 1) toggled?" incorrectly used '&' where
   it should be '^'
 * the handling of IMASK was inverted: we should set the IRQ if
   ISTATUS is set and IMASK is clear, not if both are set

The combination of these bugs meant that when running a Linux guest
that uses the generic timers we would fairly quickly end up either
forgetting that the timer output should be asserted, or failing to
set the IRQ when the timer was unmasked. The result is that the guest
never gets any more timer interrupts.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 1401803208-1281-1-git-send-email-peter.maydell@linaro.org
Cc: qemu-stable@nongnu.org
(cherry picked from commit d3afacc726)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:33:30 -05:00
Richard Henderson
6ea80edc01 tcg-i386: Fix win64 qemu store
The first non-register argument isn't placed at offset 0.

Cc: qemu-stable@nongnu.org
Reviewed-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Richard Henderson <rth@twiddle.net>
(cherry picked from commit 0b91966730)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:32:36 -05:00
Peter Maydell
f99329cd82 linux-user: Don't overrun guest buffer in sched_getaffinity
If the guest's "long" type is smaller than the host's, then
our sched_getaffinity wrapper needs to round the buffer size
up to a multiple of the host sizeof(long). This means that when
we copy the data back from the host buffer to the guest's
buffer there might be more than we can fit. Rather than
overflowing the guest's buffer, handle this case by returning
EINVAL or ignoring the unused extra space, as appropriate.

Note that only guests using the syscall interface directly might
run into this bug -- the glibc wrappers around it will always
use a buffer whose size is a multiple of 8 regardless of guest
architecture.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
(cherry picked from commit be3bd286bc)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 13:30:29 -05:00
Markus Armbruster
207f61dc28 qcow2: Plug memory leak on qcow2_invalidate_cache() error paths
Introduced in commit 5a8a30d.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit a1904e48c4)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:43:00 -05:00
Markus Armbruster
d1567e2980 block: Plug memory leak on brv_open_image() error path
Introduced in commit da557a.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b20e61e0d5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:42:52 -05:00
Markus Armbruster
5e3322eec3 qemu-io: Plug memory leak in open command
Introduced in commit b543c5c.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 29f2601aa6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:42:09 -05:00
Markus Armbruster
5a0913f782 blockdev: Plug memory leak in blockdev_init()
blockdev_init() leaks bs_opts when qemu_opts_create() fails, i.e. when
the ID is bad.  Missed in commit ec9c10d.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6376f95223)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:40 -05:00
Markus Armbruster
40a3fb54b2 blockdev: Plug memory leak in drive_init()
bs_opts is leaked on all paths from its qdev_new() that don't got
through blockdev_init().  Add the missing QDECREF(), and zap bs_opts
after blockdev_init(), so the new QDECREF() does nothing when we go
through blockdev_init().

Leak introduced in commit f298d07.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 3cb0e25c4b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:34 -05:00
Markus Armbruster
98646a11d0 block/qapi: Plug memory leak in dump_qobject() case QTYPE_QERROR
Introduced in commit a8d8ecb.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit f25391c2a6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:26 -05:00
Markus Armbruster
53bdfb5b62 block/vvfat: Plug memory leak in check_directory_consistency()
On error path.  Introduced in commit a046433a.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 6262bbd363)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:18 -05:00
Markus Armbruster
a3e3f0964d block/vvfat: Plug memory leak in read_directory()
Has always been leaky.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b122c3b6d0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:12 -05:00
Markus Armbruster
7812cbe580 block/sheepdog: Plug memory leak in sd_snapshot_create()
Has always been leaky.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 2df5fee2db)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:07 -05:00
Markus Armbruster
12d5fc6ab4 qemu-img: Plug memory leak in convert command
Introduced in commit 661a0f7.  Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit bb9cd2ee99)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:41:00 -05:00
Andrew Oates
b203bba0ce input (curses): mask keycodes to remove modifier bits
Without the mask, control bits are passed on in the keycode, generating
incorrect PS/2 sequences when SHIFT, ALT, etc are held down.

Cc: qemu-stable@nongnu.org
Signed-off-by: Andrew Oates <andrew@aoates.org>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit f5c0ab1312)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:36:31 -05:00
Stefan Weil
91148decd2 cputlb: Fix regression with TCG interpreter (bug 1310324)
Commit 0f842f8a24 replaced GETPC_EXT() which
was derived from GETPC() by GETRA_EXT() without fixing cputlb.c. A later
patch replaced GETRA_EXT() by GETRA() in exec/softmmu_template.h which
is included in cputlb.c.

The TCG interpreter failed because the values returned by GETRA() were no
longer explicitly set to 0. The redefinition of GETRA() introduced here
fixes this.

In addition, GETPC_ADJ which is also used in exec/softmmu_template.h is
set to 0. Both changes reduce the compiled code size for cputlb.c by more
than 100 bytes, so the normal TCG without interpreter also profits from
the reduced code size and slightly faster code.

Cc: qemu-stable@nongnu.org
Reported-by: Giovanni Mascellani <gio@debian.org>
Signed-off-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 7e4e88656c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-08-05 11:33:36 -05:00
Max Filippov
ae2e18e0ca target-xtensa: fix cross-page jumps/calls at the end of TB
Use tb->pc instead of dc->pc to check for cross-page jumps.
When TB translation stops at the page boundary dc->pc points to the next
page allowing chaining to TBs in it, which is wrong.

Cc: qemu-stable@nongnu.org
Signed-off-by: Max Filippov <jcmvbkbc@gmail.com>
(cherry picked from commit 433d33c555)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:34:00 -05:00
Markus Armbruster
2dbd09ff5c virtio-scsi: Plug memory leak on virtio_scsi_push_event() error path
Spotted by Coverity.

Signed-off-by: Markus Armbruster <armbru@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 91e7fcca47)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:33:18 -05:00
Kevin Wolf
3d5acbeb71 qcow1: Stricter backing file length check
Like qcow2 since commit 6d33e8e7, error out on invalid lengths instead
of silently truncating them to 1023.

Also don't rely on bdrv_pread() catching integer overflows that make len
negative, but use unsigned variables in the first place.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
(cherry picked from commit d66e5cee00)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:32:15 -05:00
Kevin Wolf
a4b73ed3f3 qcow1: Validate image size (CVE-2014-0223)
A huge image size could cause s->l1_size to overflow. Make sure that
images never require a L1 table larger than what fits in s->l1_size.

This cannot only cause unbounded allocations, but also the allocation of
a too small L1 table, resulting in out-of-bounds array accesses (both
reads and writes).

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit 46485de0cb)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:32:10 -05:00
Kevin Wolf
a3967c74de qcow1: Validate L2 table size (CVE-2014-0222)
Too large L2 table sizes cause unbounded allocations. Images actually
created by qemu-img only have 512 byte or 4k L2 tables.

To keep things consistent with cluster sizes, allow ranges between 512
bytes and 64k (in fact, down to 1 entry = 8 bytes is technically
working, but L2 table sizes smaller than a cluster don't make a lot of
sense).

This also means that the number of bytes on the virtual disk that are
described by the same L2 table is limited to at most 8k * 64k or 2^29,
preventively avoiding any integer overflows.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
(cherry picked from commit 42eb58179b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:32:05 -05:00
Kevin Wolf
5c85998739 qcow1: Check maximum cluster size
Huge values for header.cluster_bits cause unbounded allocations (e.g.
for s->cluster_cache) and crash qemu this way. Less huge values may
survive those allocations, but can cause integer overflows later on.

The only cluster sizes that qemu can create are 4k (for standalone
images) and 512 (for images with backing files), so we can limit it
to 64k.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
(cherry picked from commit 7159a45b2b)

Conflicts:
	tests/qemu-iotests/group

*removed context lines for tests not present in v2.0.0

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:30:36 -05:00
Kevin Wolf
d234c8f1f6 qcow1: Make padding in the header explicit
We were relying on all compilers inserting the same padding in the
header struct that is used for the on-disk format. Let's not do that.
Mark the struct as packed and insert an explicit padding field for
compatibility.

Cc: qemu-stable@nongnu.org
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Benoit Canet <benoit@irqsave.net>
(cherry picked from commit ea54feff58)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:29:09 -05:00
Michael S. Tsirkin
3ba1e617e7 virtio: allow mapping up to max queue size
It's a loop from i < num_sg  and the array is VIRTQUEUE_MAX_SIZE - so
it's OK if the value read is VIRTQUEUE_MAX_SIZE.

Not a big problem in practice as people don't use
such big queues, but it's inelegant.

Reported-by: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 9372514080)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:27:40 -05:00
Michael S. Tsirkin
96e7f7a911 pci-assign: limit # of msix vectors
KVM only supports MSIX table size up to 256 vectors,
but some assigned devices support more vectors,
at the moment attempts to assign them fail with EINVAL.

Tweak the MSIX capability exposed to guest to limit table size
to a supported value.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Gonglei <arei.gonglei@huawei.com>
Cc: qemu-stable@nongnu.org
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 639973a474)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:25:40 -05:00
Peter Lieven
c230ab2ba2 Revert "qapi: Clean up superfluous null check in qapi_dealloc_type_str()"
This reverts commit 25a7017555.

Turns out the argument *can* be null: QEMU now segfaults if it
receives an invalid parameter via a qmp command instead of throwing an
error.

For example:
{ "execute": "blockdev-add",
     "arguments": { "options" : { "driver": "invalid-driver" } } }

CC: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
(cherry picked from commit b690d679c1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:23:46 -05:00
Michael Tokarev
274c96e4e1 configure: remove bashism
Commit e26110cfc6 added a check for shacmd to create a hash
for modules.  This check in configure is using bash construct &>
to redirect both stdout and stderr, which does fun things on some
shells.  Get rid of it, use standard redirection instead.

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Reviewed-by: Fam Zheng <famz@redhat.com>
(cherry picked from commit 4fc00556ab)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:20:36 -05:00
Alexey Kardashevskiy
32c113c182 spapr_pci: Fix number of returned vectors in ibm, change-msi
Current guest kernels try allocating as many vectors as the quota is.
For example, in the case of virtio-net (which has just 3 vectors)
the guest requests 4 vectors (that is the quota in the test) and
the existing ibm,change-msi handler returns 4. But before it returns,
it calls msix_set_message() in a loop and corrupts memory behind
the end of msix_table.

This limits the number of vectors returned by ibm,change-msi to
the maximum supported by the actual device.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: qemu-stable@nongnu.org
[agraf: squash in bugfix from aik]
Signed-off-by: Alexander Graf <agraf@suse.de>

(cherry picked from commit b26696b519)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:20:07 -05:00
Peter Maydell
912d9cc089 linux-user/elfload.c: Fix A64 code which was incorrectly acting like A32
The ARM target-specific code in elfload.c was incorrectly allowing
the 64-bit ARM target to use most of the existing 32-bit definitions:
most noticably this meant that our HWCAP bits passed to the guest
were wrong, and register handling when dumping core was totally
broken. Fix this by properly separating the 64 and 32 bit code,
since they have more differences than similarities.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable@nongnu.org
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
(cherry picked from commit 24e76ff06b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:17:33 -05:00
Peter Maydell
074f673a9a linux-user/elfload.c: Update ARM HWCAP bits
The kernel has added support for a number of new ARM HWCAP bits;
add them to QEMU, including support for setting them where we have
a corresponding CPU feature bit.

We were also incorrectly setting the VFPv3D16 HWCAP -- this means
"only 16 D registers", not "supports 16-bit floating point format";
since QEMU always has 32 D registers for VFPv3, we can just remove
the line that incorrectly set this bit.

The kernel does not set the HWCAP_FPA even if it is providing FPA
emulation via nwfpe, so don't set this bit in QEMU either.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable@nongnu.org
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
(cherry picked from commit 2468265465)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:17:19 -05:00
Peter Maydell
83b1dc162c linux-user/elfload.c: Fix incorrect ARM HWCAP bits
The ELF HWCAP bits for ARM features THUMBEE, NEON, VFPv3 and VFPv3D16 are
all off by one compared to the kernel definitions. Fix this discrepancy
and add in the missing CRUNCH bit which was the cause of the off-by-one
error. (We don't emulate any of the CPUs which have that weird hardware,
so it's otherwise uninteresting to us.)

Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
(cherry picked from commit 43ce393ee5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:17:09 -05:00
Edgar E. Iglesias
c2d37222ae target-arm: Make vbar_write 64bit friendly on 32bit hosts
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 1398926097-28097-2-git-send-email-edgar.iglesias@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit fed3ffb9f1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:16:25 -05:00
Edgar E. Iglesias
e40585f8f1 target-arm: A64: Handle blr lr
For linked branches, updates to the link register happen
conceptually after the read of the branch target register.

Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Cc: qemu-stable@nongnu.org
Message-id: 1398926097-28097-3-git-send-email-edgar.iglesias@gmail.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 1b505f93bc)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:15:16 -05:00
Amos Kong
837e02ef07 qdev: Fix crash by validating the object type
QEMU crashed when I try to list device parameters and the driver name is
actually an available bus name.

 # qemu -device virtio-pci-bus,?
 # qemu -device virtio-bus,?
 # qemu -device virtio-serial-bus,?
 qdev-monitor.c:212:qdev_device_help: Object 0x7fd932f50620 is not an
 instance of type device
 Aborted (core dumped)

We can also reproduce this bug by adding device from monitor, so it's
worth to fix the crash.

 (qemu) device_add virtio-serial-bus
 qdev-monitor.c:491:qdev_device_add: Object 0x7f5e89530920 is not an
 instance of type device
 Aborted (core dumped)

Cc: qemu-stable@nongnu.org
Signed-off-by: Amos Kong <akong@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
(cherry picked from commit ce0abca3e3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:14:21 -05:00
Paolo Bonzini
46a1b0e489 target-i386: fix set of registers zeroed on reset
BND0-3, BNDCFGU, BNDCFGS, BNDSTATUS were not zeroed on reset, but they
should be (Intel Instruction Set Extensions Programming Reference
319433-015, pages 9-4 and 9-6).  Same for YMM.

XCR0 should be reset to 1.

TSC and TSC_RESET were zeroed already by the memset, remove the explicit
assignments.

Cc: Andreas Faerber <afaerber@suse.de>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 05e7e819d7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:13:08 -05:00
Christian Borntraeger
a14d42919f s390x/kvm: rework KVM synchronize to tracing for some ONEREGS
Some ONE_REGS on s390 are not protected by a capability. Older kernels
might not provide those and return an error. Fortunately these registers
are only critical for the migration path. There is no need to error out
on reset and normal runtime. Furthermore, these kernels don't provide
a proper dirty bitmap anyway, so let's use tracing for those errors.

Also provide generic one reg helper to simplify the code.

Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 860643bc5a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:12:20 -05:00
Michael S. Tsirkin
2ac9549453 stellaris_enet: block migration
Incoming migration with stellaris_enet is unsafe.
It's being reworked, but for now, simply block it
since noone is using it anyway.
Block outgoing migration for good measure.

CVE-2013-4532

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:10:36 -05:00
Michael S. Tsirkin
2f18e44b0c acpi: fix tables for no-hpet configuration
acpi build tried to add offset of hpet table to rsdt even when hpet was
disabled.  If no tables follow hpet, this could lead to a malformed
rsdt.

Fix it up.

To avoid such errors in the future, rearrange code slightly to make it
clear that acpi_add_table stores the offset of the following table - not
of the previous one.

Reported-by: TeLeMan <geleman@gmail.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: qemu-stable@nongnu.org
(cherry picked from commit 9ac1c4c07e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:57 -05:00
Michael Tokarev
4c1e06408d po/Makefile: fix $SRC_PATH reference
The rule for messages.po appears to be slightly wrong.
Move the `cd' command within parens.

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Tested-by: Stefan Weil <sw@weilnetz.de>
(cherry picked from commit b920cad669)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:57 -05:00
David Hildenbrand
4a7a497509 s390x: empty function stubs in preparation for __KVM_HAVE_GUEST_DEBUG
This patch creates empty function stubs (used by the gdbserver) in preparation
for the hw debugging support by kvm on s390, which will enable the
__KVM_HAVE_GUEST_DEBUG define in the linux headers and require these methods on
the qemu side.

Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 8c0124490b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:57 -05:00
Benoît Canet
7dfa87e9cb block: Prevent coroutine stack overflow when recursing in bdrv_open_backing_file.
In 1.7.1 qcow2_create2 reopen the file for flushing without the BDRV_O_NO_BACKING
flags.

As a consequence the code would recursively open the whole backing chain.

These three stack arrays would pile up through the recursion and lead to a coroutine
stack overflow.

Convert these array to malloced buffers in order to streamline the coroutine
footprint.

Symptoms where freezes or segfaults on production machines while taking QMP externals
snapshots. The overflow disturbed coroutine switching.

[Resolved conflicts on qemu.git/master since the patch was against v1.7.1
--Stefan]

Signed-off-by: Benoit Canet <benoit.canet@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 1ba4b6a553)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:57 -05:00
Peter Crosthwaite
7b0387ad90 arm: translate.c: Fix smlald Instruction
The smlald (and probably smlsld) instruction was doing incorrect sign
extensions of the operands amongst 64bit result calculation. The
instruction psuedo-code is:

 operand2 = if m_swap then ROR(R[m],16) else R[m];
 product1 = SInt(R[n]<15:0>) * SInt(operand2<15:0>);
 product2 = SInt(R[n]<31:16>) * SInt(operand2<31:16>);
 result = product1 + product2 + SInt(R[dHi]:R[dLo]);
 R[dHi] = result<63:32>;
 R[dLo] = result<31:0>;

The result calculation should be done in 64 bit arithmetic, and hence
product1 and product2 should be sign extended to 64b before calculation.

The current implementation was adding product1 and product2 together
then sign-extending the intermediate result leading to false negatives.

E.G. if product1 = product2 = 0x4000000, their sum = 0x80000000, which
will be incorrectly interpreted as -ve on sign extension.

We fix by doing the 64b extensions on both product1 and product2 before
any addition/subtraction happens.

We also fix where we were possibly incorrectly setting the Q saturation
flag for SMLSLD, which the ARM ARM specifically says is not set.

Reported-by: Christina Smith <christina.smith@xilinx.com>
Signed-off-by: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 2cddb6f5a15be4ab8d2160f3499d128ae93d304d.1397704570.git.peter.crosthwaite@xilinx.com
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 33bbd75a7c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:56 -05:00
Hannes Reinecke
1624861997 megasas: Implement LD_LIST_QUERY
Newer firmware implement a LD_LIST_QUERY command, and due to a driver
issue no drives might be detected if this command isn't supported.
So add emulation for this command, too.

Cc: qemu-stable@nongnu.org
Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 34bb4d02e0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:56 -05:00
Alex Bennée
fb039011ff target-arm: A64: fix unallocated test of scalar SQXTUN
The test for the U bit was incorrectly inverted in the scalar case of SQXTUN.
This doesn't affect the vector case as the U bit is used to select XTN(2).

Reported-by: Hao Liu <hao.liu@arm.com>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Claudio Fontana <claudio.fontana@huawei.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit e44a90c596)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:56 -05:00
Michael S. Tsirkin
5ad12b3235 virtio-scsi: fix buffer overrun on invalid state load
CVE-2013-4542

hw/scsi/scsi-bus.c invokes load_request.

 virtio_scsi_load_request does:
    qemu_get_buffer(f, (unsigned char *)&req->elem, sizeof(req->elem));

this probably can make elem invalid, for example,
make in_num or out_num huge, then:

    virtio_scsi_parse_req(s, vs->cmd_vqs[n], req);

will do:

    if (req->elem.out_num > 1) {
        qemu_sgl_init_external(req, &req->elem.out_sg[1],
                               &req->elem.out_addr[1],
                               req->elem.out_num - 1);
    } else {
        qemu_sgl_init_external(req, &req->elem.in_sg[1],
                               &req->elem.in_addr[1],
                               req->elem.in_num - 1);
    }

and this will access out of array bounds.

Note: this adds security checks within assert calls since
SCSIBusInfo's load_request cannot fail.
For now simply disable builds with NDEBUG - there seems
to be little value in supporting these.

Cc: Andreas Färber <afaerber@suse.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 3c3ce98142)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:56 -05:00
Michael S. Tsirkin
15c35dfd92 usb: sanity check setup_index+setup_len in post_load
CVE-2013-4541

s->setup_len and s->setup_index are fed into usb_packet_copy as
size/offset into s->data_buf, it's possible for invalid state to exploit
this to load arbitrary data.

setup_len and setup_index should be checked to make sure
they are not negative.

Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 9f8e9895c5)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael S. Tsirkin
e7ff13929f zaurus: fix buffer overrun on invalid state load
CVE-2013-4540

Within scoop_gpio_handler_update, if prev_level has a high bit set, then
we get bit > 16 and that causes a buffer overrun.

Since prev_level comes from wire indirectly, this can
happen on invalid state load.

Similarly for gpio_level and gpio_dir.

To fix, limit to 16 bit.

Reported-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 52f91c3723)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael S. Tsirkin
894f179e8d tsc210x: fix buffer overrun on invalid state load
CVE-2013-4539

s->precision, nextprecision, function and nextfunction
come from wire and are used
as idx into resolution[] in TSC_CUT_RESOLUTION.

Validate after load to avoid buffer overrun.

Cc: Andreas Färber <afaerber@suse.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 5193be3be3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael S. Tsirkin
2265c71b35 ssd0323: fix buffer overun on invalid state load
CVE-2013-4538

s->cmd_len used as index in ssd0323_transfer() to store 32-bit field.
Possible this field might then be supplied by guest to overwrite a
return addr somewhere. Same for row/col fields, which are indicies into
framebuffer array.

To fix validate after load.

Additionally, validate that the row/col_start/end are within bounds;
otherwise the guest can provoke an overrun by either setting the _end
field so large that the row++ increments just walk off the end of the
array, or by setting the _start value to something bogus and then
letting the "we hit end of row" logic reset row to row_start.

For completeness, validate mode as well.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit ead7a57df3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael S. Tsirkin
95d9149ed3 ssi-sd: fix buffer overrun on invalid state load
CVE-2013-4537

s->arglen is taken from wire and used as idx
in ssi_sd_transfer().

Validate it before access.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit a9c380db3b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael S. Tsirkin
eb55958e18 pxa2xx: avoid buffer overrun on incoming migration
CVE-2013-4533

s->rx_level is read from the wire and used to determine how many bytes
to subsequently read into s->rx_fifo[]. If s->rx_level exceeds the
length of s->rx_fifo[] the buffer can be overrun with arbitrary data
from the wire.

Fix this by validating rx_level against the size of s->rx_fifo.

Cc: Don Koch <dkoch@verizon.com>
Reported-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Don Koch <dkoch@verizon.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit caa881abe0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:55 -05:00
Michael Roth
1124696193 openpic: avoid buffer overrun on incoming migration
CVE-2013-4534

opp->nb_cpus is read from the wire and used to determine how many
IRQDest elements to read into opp->dst[]. If the value exceeds the
length of opp->dst[], MAX_CPU, opp->dst[] can be overrun with arbitrary
data from the wire.

Fix this by failing migration if the value read from the wire exceeds
MAX_CPU.

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Reviewed-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 73d963c0a7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael S. Tsirkin
4e48018ae9 virtio: validate num_sg when mapping
CVE-2013-4535
CVE-2013-4536

Both virtio-block and virtio-serial read,
VirtQueueElements are read in as buffers, and passed to
virtqueue_map_sg(), where num_sg is taken from the wire and can force
writes to indicies beyond VIRTQUEUE_MAX_SIZE.

To fix, validate num_sg.

Reported-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 36cf2a3713)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael Roth
7297dba271 virtio: avoid buffer overrun on incoming migration
CVE-2013-6399

vdev->queue_sel is read from the wire, and later used in the
emulation code as an index into vdev->vq[]. If the value of
vdev->queue_sel exceeds the length of vdev->vq[], currently
allocated to be VIRTIO_PCI_QUEUE_MAX elements, subsequent PIO
operations such as VIRTIO_PCI_QUEUE_PFN can be used to overrun
the buffer with arbitrary data originating from the source.

Fix this by failing migration if the value from the wire exceeds
VIRTIO_PCI_QUEUE_MAX.

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 4b53c2c72c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael S. Tsirkin
9c01a91c7b vmstate: fix buffer overflow in target-arm/machine.c
CVE-2013-4531

cpreg_vmstate_indexes is a VARRAY_INT32. A negative value for
cpreg_vmstate_array_len will cause a buffer overflow.

VMSTATE_INT32_LE was supposed to protect against this
but doesn't because it doesn't validate that input is
non-negative.

Fix this macro to valide the value appropriately.

The only other user of VMSTATE_INT32_LE doesn't
ever use negative numbers so it doesn't care.

Reported-by: Anthony Liguori <anthony@codemonkey.ws>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit d2ef4b61fe)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael S. Tsirkin
7cf5f5d087 pl022: fix buffer overun on invalid state load
CVE-2013-4530

pl022.c did not bounds check tx_fifo_head and
rx_fifo_head after loading them from file and
before they are used to dereference array.

Reported-by: Michael S. Tsirkin <mst@redhat.com
Reported-by: Anthony Liguori <anthony@codemonkey.ws>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit d8d0a0bc7e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael S. Tsirkin
f7ef3baa49 hw/pci/pcie_aer.c: fix buffer overruns on invalid state load
4) CVE-2013-4529
hw/pci/pcie_aer.c    pcie aer log can overrun the buffer if log_num is
                     too large

There are two issues in this file:
1. log_max from remote can be larger than on local
then buffer will overrun with data coming from state file.
2. log_num can be larger then we get data corruption
again with an overflow but not adversary controlled.

Fix both issues.

Reported-by: Anthony Liguori <anthony@codemonkey.ws>
Reported-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 5f691ff91d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:54 -05:00
Michael S. Tsirkin
3c6066172f hpet: fix buffer overrun on invalid state load
CVE-2013-4527 hw/timer/hpet.c buffer overrun

hpet is a VARRAY with a uint8 size but static array of 32

To fix, make sure num_timers is valid using VMSTATE_VALID hook.

Reported-by: Anthony Liguori <anthony@codemonkey.ws>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 3f1c49e213)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
d4c9095900 ahci: fix buffer overrun on invalid state load
CVE-2013-4526

Within hw/ide/ahci.c, VARRAY refers to ports which is also loaded.  So
we use the old version of ports to read the array but then allow any
value for ports.  This can cause the code to overflow.

There's no reason to migrate ports - it never changes.
So just make sure it matches.

Reported-by: Anthony Liguori <anthony@codemonkey.ws>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit ae2158ad6c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
331c549b2d virtio-net: out-of-bounds buffer write on load
CVE-2013-4149 QEMU 1.3.0 out-of-bounds buffer write in
virtio_net_load()@hw/net/virtio-net.c

>         } else if (n->mac_table.in_use) {
>             uint8_t *buf = g_malloc0(n->mac_table.in_use);

We are allocating buffer of size n->mac_table.in_use

>             qemu_get_buffer(f, buf, n->mac_table.in_use * ETH_ALEN);

and read to the n->mac_table.in_use size buffer n->mac_table.in_use *
ETH_ALEN bytes, corrupting memory.

If adversary controls state then memory written there is controlled
by adversary.

Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 98f93ddd84)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
b24cfb0f1e virtio-net: out-of-bounds buffer write on invalid state load
CVE-2013-4150 QEMU 1.5.0 out-of-bounds buffer write in
virtio_net_load()@hw/net/virtio-net.c

This code is in hw/net/virtio-net.c:

    if (n->max_queues > 1) {
        if (n->max_queues != qemu_get_be16(f)) {
            error_report("virtio-net: different max_queues ");
            return -1;
        }

        n->curr_queues = qemu_get_be16(f);
        for (i = 1; i < n->curr_queues; i++) {
            n->vqs[i].tx_waiting = qemu_get_be32(f);
        }
    }

Number of vqs is max_queues, so if we get invalid input here,
for example if max_queues = 2, curr_queues = 3, we get
write beyond end of the buffer, with data that comes from
wire.

This might be used to corrupt qemu memory in hard to predict ways.
Since we have lots of function pointers around, RCE might be possible.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit eea750a562)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
7872f3e77e virtio-net: fix buffer overflow on invalid state load
CVE-2013-4148 QEMU 1.0 integer conversion in
virtio_net_load()@hw/net/virtio-net.c

Deals with loading a corrupted savevm image.

>         n->mac_table.in_use = qemu_get_be32(f);

in_use is int so it can get negative when assigned 32bit unsigned value.

>         /* MAC_TABLE_ENTRIES may be different from the saved image */
>         if (n->mac_table.in_use <= MAC_TABLE_ENTRIES) {

passing this check ^^^

>             qemu_get_buffer(f, n->mac_table.macs,
>                             n->mac_table.in_use * ETH_ALEN);

with good in_use value, "n->mac_table.in_use * ETH_ALEN" can get
positive and bigger than mac_table.macs. For example 0x81000000
satisfies this condition when ETH_ALEN is 6.

Fix it by making the value unsigned.
For consistency, change first_multi as well.

Note: all call sites were audited to confirm that
making them unsigned didn't cause any issues:
it turns out we actually never do math on them,
so it's easy to validate because both values are
always <= MAC_TABLE_ENTRIES.

Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 71f7fe48e1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
390252193c vmstate: add VMSTATE_VALIDATE
Validate state using VMS_ARRAY with num = 0 and VMS_MUST_EXIST

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 4082f0889b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:53 -05:00
Michael S. Tsirkin
49e8918a4d vmstate: add VMS_MUST_EXIST
Can be used to verify a required field exists or validate
state in some other way.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 5bf81c8d63)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:52 -05:00
Michael S. Tsirkin
6067df7a5d vmstate: reduce code duplication
move size offset and number of elements math out
to functions, to reduce code duplication.

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
(cherry picked from commit 35fc1f7189)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 22:05:52 -05:00
Peter Maydell
9ee8ab5503 hw/net/stellaris_enet: Correct handling of packet padding
The PADEN bit in the transmit control register enables padding of short
data packets out to the required minimum length. However a typo here
meant we were adjusting tx_fifo_len rather than tx_frame_len, so the
padding didn't actually happen. Fix this bug.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: qemu-stable@nongnu.org
(cherry picked from commit 7fd5f064d1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 19:05:18 -05:00
Peter Maydell
c8723d46c1 hw/net/stellaris_enet: Restructure tx_fifo code to avoid buffer overrun
The current tx_fifo code has a corner case where the guest can overrun
the fifo buffer: if automatic CRCs are disabled we allow the guest to write
the CRC word even if there isn't actually space for it in the FIFO.
The datasheet is unclear about exactly how the hardware deals with this
situation; the most plausible answer seems to be that the CRC word is
just lost.

Implement this fix by separating the "can we stuff another word in the
FIFO" logic from the "should we transmit the packet now" check. This
also moves us closer to the real hardware, which has a number of ways
it can be configured to trigger sending the packet, some of which we
don't implement.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: qemu-stable@nongnu.org
(cherry picked from commit 5c10495ab1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2014-07-20 19:05:14 -05:00
1669 changed files with 48406 additions and 139372 deletions

24
.gitignore vendored
View File

@@ -4,17 +4,12 @@
/config-host.*
/config-target.*
/config.status
/config-temp
/trace/generated-tracers.h
/trace/generated-tracers.c
/trace/generated-tracers-dtrace.h
/trace/generated-tracers.dtrace
/trace/generated-events.h
/trace/generated-events.c
/trace/generated-helpers-wrappers.h
/trace/generated-helpers.h
/trace/generated-helpers.c
/trace/generated-tcg-tracers.h
/trace/generated-ust-provider.h
/trace/generated-ust.c
/libcacard/trace/generated-tracers.c
@@ -23,14 +18,13 @@
/*-darwin-user
/*-linux-user
/*-bsd-user
/libdis*
/libuser
libdis*
libuser
/linux-headers/asm
/qga/qapi-generated
/qapi-generated
/qapi-types.[ch]
/qapi-visit.[ch]
/qapi-event.[ch]
/qmp-commands.h
/qmp-marshal.c
/qemu-doc.html
@@ -55,9 +49,19 @@
/qemu-monitor.texi
/qmp-commands.txt
/vscclient
/test-bitops
/test-coroutine
/test-int128
/test-opts-visitor
/test-qmp-input-visitor
/test-qmp-output-visitor
/test-string-input-visitor
/test-string-output-visitor
/test-visitor-serialization
/fsdev/virtfs-proxy-helper
/fsdev/virtfs-proxy-helper.1
/fsdev/virtfs-proxy-helper.pod
/.gdbinit
*.a
*.aux
*.cp
@@ -86,8 +90,12 @@
*.pc
.libs
.sdk
*.swp
*.orig
.pc
*.gcda
*.gcno
patches
/pc-bios/bios-pq/status
/pc-bios/vgabios-pq/status
/pc-bios/optionrom/linuxboot.asm

3
.gitmodules vendored
View File

@@ -28,6 +28,3 @@
[submodule "dtc"]
path = dtc
url = git://git.qemu-project.org/dtc.git
[submodule "roms/u-boot"]
path = roms/u-boot
url = git://git.qemu-project.org/u-boot.git

View File

@@ -12,7 +12,7 @@ notifications:
on_failure: always
env:
global:
- TEST_CMD=""
- TEST_CMD="make check"
- EXTRA_CONFIG=""
# Development packages, EXTRA_PKGS saved for additional builds
- CORE_PKGS="libusb-1.0-0-dev libiscsi-dev librados-dev libncurses5-dev"
@@ -20,51 +20,31 @@ env:
- 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
- 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=m68k-softmmu,m68k-linux-user
- TARGETS=microblaze-softmmu,microblazeel-softmmu,microblaze-linux-user,microblazeel-linux-user
- TARGETS=arm-softmmu,arm-linux-user
- TARGETS=aarch64-softmmu,aarch64-linux-user
- TARGETS=cris-softmmu
- TARGETS=i386-softmmu,x86_64-softmmu
- TARGETS=lm32-softmmu
- TARGETS=m68k-softmmu
- TARGETS=microblaze-softmmu,microblazeel-softmmu
- 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:
# we want to do this ourselves
submodules: false
- TARGETS=moxie-softmmu
- TARGETS=or32-softmmu,
- TARGETS=ppc-softmmu,ppc64-softmmu,ppcemb-softmmu
- TARGETS=s390x-softmmu
- TARGETS=sh4-softmmu,sh4eb-softmmu
- TARGETS=sparc-softmmu,sparc64-softmmu
- TARGETS=unicore32-softmmu
- TARGETS=xtensa-softmmu,xtensaeb-softmmu
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:
- make -j2 && ${TEST_CMD}
script: "./configure --target-list=${TARGETS} ${EXTRA_CONFIG} && make && ${TEST_CMD}"
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=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-debug"
@@ -86,15 +66,16 @@ matrix:
compiler: gcc
# All the trace backends (apart from dtrace)
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=stderr"
EXTRA_CONFIG="--enable-trace-backend=stderr"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=simple"
EXTRA_CONFIG="--enable-trace-backend=simple"
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_CONFIG="--enable-trace-backends=ftrace"
EXTRA_CONFIG="--enable-trace-backend=ftrace"
TEST_CMD=""
compiler: gcc
- env: TARGETS=i386-softmmu,x86_64-softmmu
EXTRA_PKGS="liblttng-ust-dev liburcu-dev"
EXTRA_CONFIG="--enable-trace-backends=ust"
EXTRA_CONFIG="--enable-trace-backend=ust"
compiler: gcc

View File

@@ -91,17 +91,3 @@ Mixed declarations (interleaving statements and declarations within blocks)
are not allowed; declarations should be at the beginning of blocks. In other
words, the code should not generate warnings if using GCC's
-Wdeclaration-after-statement option.
6. Conditional statements
When comparing a variable for (in)equality with a constant, list the
constant on the right, as in:
if (a == 1) {
/* Reads like: "If a equals 1" */
do_something();
}
Rationale: Yoda conditions (as in 'if (1 == a)') are awkward to read.
Besides, good compilers already warn users when '==' is mis-typed as '=',
even when the constant is on the right.

View File

@@ -51,34 +51,14 @@ Descriptions of section entries:
General Project Administration
------------------------------
M: Anthony Liguori <aliguori@amazon.com>
M: Peter Maydell <peter.maydell@linaro.org>
Responsible Disclosure, Reporting Security Issues
------------------------------
W: http://wiki.qemu.org/SecurityProcess
M: Michael S. Tsirkin <mst@redhat.com>
M: Anthony Liguori <aliguori@amazon.com>
L: secalert@redhat.com
Guest CPU cores (TCG):
----------------------
Overall
L: qemu-devel@nongnu.org
S: Odd fixes
F: cpu-exec.c
F: cputlb.c
F: softmmu_template.h
F: translate-all.c
F: include/exec/cpu_ldst.h
F: include/exec/cpu_ldst_template.h
F: include/exec/helper*.h
Alpha
M: Richard Henderson <rth@twiddle.net>
S: Maintained
F: target-alpha/
F: hw/alpha/
F: tests/tcg/alpha/
ARM
M: Peter Maydell <peter.maydell@linaro.org>
@@ -92,7 +72,6 @@ M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
S: Maintained
F: target-cris/
F: hw/cris/
F: tests/tcg/cris/
LM32
M: Michael Walle <michael@walle.cc>
@@ -100,7 +79,6 @@ S: Maintained
F: target-lm32/
F: hw/lm32/
F: hw/char/lm32_*
F: tests/tcg/lm32/
M68K
S: Orphan
@@ -115,11 +93,9 @@ F: hw/microblaze/
MIPS
M: Aurelien Jarno <aurelien@aurel32.net>
M: Leon Alrae <leon.alrae@imgtec.com>
S: Maintained
S: Odd Fixes
F: target-mips/
F: hw/mips/
F: tests/tcg/mips/
Moxie
M: Anthony Green <green@moxielogic.com>
@@ -131,7 +107,6 @@ M: Jia Liu <proljc@gmail.com>
S: Maintained
F: target-openrisc/
F: hw/openrisc/
F: tests/tcg/openrisc/
PowerPC
M: Alexander Graf <agraf@suse.de>
@@ -167,8 +142,7 @@ F: target-unicore32/
F: hw/unicore32/
X86
M: Paolo Bonzini <pbonzini@redhat.com>
M: Richard Henderson <rth@twiddle.net>
M: qemu-devel@nongnu.org
S: Odd Fixes
F: target-i386/
F: hw/i386/
@@ -179,13 +153,6 @@ W: http://wiki.osll.spb.ru/doku.php?id=etc:users:jcmvbkbc:qemu-target-xtensa
S: Maintained
F: target-xtensa/
F: hw/xtensa/
F: tests/tcg/xtensa/
TriCore
M: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
S: Maintained
F: target-tricore/
F: hw/tricore/
Guest CPU Cores (KVM):
----------------------
@@ -202,11 +169,6 @@ M: Peter Maydell <peter.maydell@linaro.org>
S: Maintained
F: target-arm/kvm.c
MIPS
M: James Hogan <james.hogan@imgtec.com>
S: Maintained
F: target-mips/kvm.c
PPC
M: Alexander Graf <agraf@suse.de>
S: Maintained
@@ -218,12 +180,9 @@ M: Cornelia Huck <cornelia.huck@de.ibm.com>
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: target-s390x/kvm.c
F: hw/intc/s390_flic.c
F: hw/intc/s390_flic_kvm.c
F: include/hw/s390x/s390_flic.h
F: hw/intc/s390_flic.[hc]
X86
M: Paolo Bonzini <pbonzini@redhat.com>
M: Marcelo Tosatti <mtosatti@redhat.com>
L: kvm@vger.kernel.org
S: Supported
@@ -277,8 +236,8 @@ S: Maintained
F: hw/*/exynos*
Calxeda Highbank
M: Rob Herring <robh@kernel.org>
S: Maintained
M: Mark Langsdorf <mark.langsdorf@calxeda.com>
S: Supported
F: hw/arm/highbank.c
F: hw/net/xgmac.c
@@ -289,7 +248,7 @@ F: include/hw/arm/digic.h
F: hw/*/digic*
Gumstix
L: qemu-devel@nongnu.org
M: qemu-devel@nongnu.org
S: Orphan
F: hw/arm/gumstix.c
@@ -305,7 +264,7 @@ S: Maintained
F: hw/arm/integratorcp.c
Mainstone
L: qemu-devel@nongnu.org
M: qemu-devel@nongnu.org
S: Orphan
F: hw/arm/mainstone.c
@@ -411,7 +370,7 @@ S: Maintained
F: hw/mips/mips_malta.c
Mipssim
L: qemu-devel@nongnu.org
M: qemu-devel@nongnu.org
S: Orphan
F: hw/mips/mips_mipssim.c
@@ -544,8 +503,6 @@ F: hw/s390x/s390-virtio-ccw.c
F: hw/s390x/css.[hc]
F: hw/s390x/sclp*.[hc]
F: hw/s390x/ipl*.[hc]
F: include/hw/s390x/
F: pc-bios/s390-ccw/
T: git git://github.com/cohuck/qemu virtio-ccw-upstr
UniCore32 Machines
@@ -583,19 +540,17 @@ Xtensa Machines
sim
M: Max Filippov <jcmvbkbc@gmail.com>
S: Maintained
F: hw/xtensa/sim.c
F: hw/xtensa/xtensa_sim.c
XTFPGA (LX60, LX200, ML605, KC705)
Avnet LX60
M: Max Filippov <jcmvbkbc@gmail.com>
S: Maintained
F: hw/xtensa/xtfpga.c
F: hw/net/opencores_eth.c
F: hw/xtensa/xtensa_lx60.c
Devices
-------
IDE
M: Kevin Wolf <kwolf@redhat.com>
M: Stefan Hajnoczi <stefanha@redhat.com>
S: Odd Fixes
F: include/hw/ide.h
F: hw/ide/
@@ -646,13 +601,6 @@ USB
M: Gerd Hoffmann <kraxel@redhat.com>
S: Maintained
F: hw/usb/*
F: tests/usb-*-test.c
USB (serial adapter)
M: Gerd Hoffmann <kraxel@redhat.com>
M: Samuel Thibault <samuel.thibault@ens-lyon.org>
S: Maintained
F: hw/usb/dev-serial.c
VFIO
M: Alex Williamson <alex.williamson@redhat.com>
@@ -703,12 +651,6 @@ S: Supported
F: hw/block/nvme*
F: tests/nvme-test.c
megasas
M: Hannes Reinecke <hare@suse.de>
S: Supported
F: hw/scsi/megasas.c
F: hw/scsi/mfi.h
Xilinx EDK
M: Peter Crosthwaite <peter.crosthwaite@xilinx.com>
M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
@@ -716,12 +658,6 @@ S: Maintained
F: hw/*/xilinx_*
F: include/hw/xilinx.h
Vmware
M: Dmitry Fleytman <dmitry@daynix.com>
S: Maintained
F: hw/net/vmxnet*
F: hw/scsi/vmw_pvscsi*
Subsystems
----------
Audio
@@ -730,38 +666,21 @@ M: Gerd Hoffmann <kraxel@redhat.com>
S: Maintained
F: audio/
F: hw/audio/
F: tests/ac97-test.c
F: tests/es1370-test.c
F: tests/intel-hda-test.c
Block
M: Kevin Wolf <kwolf@redhat.com>
M: Stefan Hajnoczi <stefanha@redhat.com>
S: Supported
F: async.c
F: aio-*.c
F: block*
F: block/
F: hw/block/
F: qemu-img*
F: qemu-io*
F: tests/image-fuzzer/
F: tests/qemu-iotests/
T: git git://repo.or.cz/qemu/kevin.git block
T: git git://github.com/stefanha/qemu.git block
Character Devices
M: Anthony Liguori <aliguori@amazon.com>
M: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: qemu-char.c
F: backends/msmouse.c
F: backends/testdev.c
Character Devices (Braille)
M: Samuel Thibault <samuel.thibault@ens-lyon.org>
S: Maintained
F: backends/baum.c
CPU
M: Andreas Färber <afaerber@suse.de>
@@ -783,21 +702,11 @@ S: Maintained
F: device_tree.[ch]
GDB stub
L: qemu-devel@nongnu.org
M: qemu-devel@nongnu.org
S: Odd Fixes
F: gdbstub*
F: gdb-xml/
Memory API
M: Paolo Bonzini <pbonzini@redhat.com>
S: Supported
F: include/exec/ioport.h
F: ioport.c
F: include/exec/memory.h
F: memory.c
F: include/exec/memory-internal.h
F: exec.c
SPICE
M: Gerd Hoffmann <kraxel@redhat.com>
S: Supported
@@ -820,11 +729,7 @@ F: ui/cocoa.m
Main loop
M: Anthony Liguori <aliguori@amazon.com>
M: Paolo Bonzini <pbonzini@redhat.com>
S: Maintained
F: cpus.c
F: main-loop.c
F: qemu-timer.c
S: Supported
F: vl.c
Human Monitor (HMP)
@@ -863,7 +768,6 @@ M: Luiz Capitulino <lcapitulino@redhat.com>
M: Michael Roth <mdroth@linux.vnet.ibm.com>
S: Maintained
F: qapi/
F: tests/qapi-schema/
T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
QAPI Schema
@@ -874,23 +778,6 @@ S: Supported
F: qapi-schema.json
T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
QObject
M: Luiz Capitulino <lcapitulino@redhat.com>
S: Maintained
F: qobject/
T: git git://repo.or.cz/qemu/qmp-unstable.git queue/qmp
QOM
M: Anthony Liguori <aliguori@amazon.com>
M: Andreas Färber <afaerber@suse.de>
S: Supported
T: git git://github.com/afaerber/qemu-cpu.git qom-next
F: include/qom/
X: include/qom/cpu.h
F: qom/
X: qom/cpu.c
F: tests/qom-test.c
QMP
M: Luiz Capitulino <lcapitulino@redhat.com>
S: Maintained
@@ -921,19 +808,13 @@ S: Odd Fixes
F: scripts/checkpatch.pl
Seccomp
M: Eduardo Otubo <eduardo.otubo@profitbricks.com>
M: Eduardo Otubo <otubo@linux.vnet.ibm.com>
S: Supported
F: qemu-seccomp.c
F: include/sysemu/seccomp.h
Usermode Emulation
------------------
Overall
M: Riku Voipio <riku.voipio@iki.fi>
S: Maintained
F: thunk.c
F: user-exec.c
BSD user
M: Blue Swirl <blauwirbel@gmail.com>
S: Maintained
@@ -947,6 +828,7 @@ F: linux-user/
Tiny Code Generator (TCG)
-------------------------
Common code
M: qemu-devel@nongnu.org
M: Richard Henderson <rth@twiddle.net>
S: Maintained
F: tcg/
@@ -963,7 +845,7 @@ S: Maintained
F: tcg/arm/
i386 target
L: qemu-devel@nongnu.org
M: qemu-devel@nongnu.org
S: Maintained
F: tcg/i386/
@@ -1040,7 +922,7 @@ S: Supported
F: block/rbd.c
Sheepdog
M: Hitoshi Mitake <mitake.hitoshi@lab.ntt.co.jp>
M: MORITA Kazutaka <morita.kazutaka@lab.ntt.co.jp>
M: Liu Yuan <namei.unix@gmail.com>
L: sheepdog@lists.wpkg.org
S: Supported
@@ -1072,9 +954,3 @@ SSH
M: Richard W.M. Jones <rjones@redhat.com>
S: Supported
F: block/ssh.c
ARCHIPELAGO
M: Chrysostomos Nanakos <cnanakos@grnet.gr>
M: Chrysostomos Nanakos <chris@include.gr>
S: Maintained
F: block/archipelago.c

View File

@@ -45,25 +45,19 @@ endif
endif
GENERATED_HEADERS = config-host.h qemu-options.def
GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h qapi-event.h
GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
GENERATED_HEADERS += qmp-commands.h qapi-types.h qapi-visit.h
GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c
GENERATED_HEADERS += trace/generated-events.h
GENERATED_SOURCES += trace/generated-events.c
GENERATED_HEADERS += trace/generated-tracers.h
ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),dtrace)
ifeq ($(TRACE_BACKEND),dtrace)
GENERATED_HEADERS += trace/generated-tracers-dtrace.h
endif
GENERATED_SOURCES += trace/generated-tracers.c
GENERATED_HEADERS += trace/generated-tcg-tracers.h
GENERATED_HEADERS += trace/generated-helpers-wrappers.h
GENERATED_HEADERS += trace/generated-helpers.h
GENERATED_SOURCES += trace/generated-helpers.c
ifeq ($(findstring ust,$(TRACE_BACKENDS)),ust)
ifeq ($(TRACE_BACKEND),ust)
GENERATED_HEADERS += trace/generated-ust-provider.h
GENERATED_SOURCES += trace/generated-ust.c
endif
@@ -154,6 +148,10 @@ endif
all: $(DOCS) $(TOOLS) $(HELPERS-y) recurse-all modules
vl.o: QEMU_CFLAGS+=$(GPROF_CFLAGS)
vl.o: QEMU_CFLAGS+=$(SDL_CFLAGS)
config-host.h: config-host.h-timestamp
config-host.h-timestamp: config-host.mak
qemu-options.def: $(SRC_PATH)/qemu-options.hx
@@ -197,6 +195,8 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
bt-host.o: QEMU_CFLAGS += $(BLUEZ_CFLAGS)
$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h | $(BUILD_DIR)/version.lo
$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<," RC version.o")
$(BUILD_DIR)/version.lo: $(SRC_PATH)/version.rc $(BUILD_DIR)/config-host.h
@@ -208,7 +208,7 @@ Makefile: $(version-obj-y) $(version-lobj-y)
# Build libraries
libqemustub.a: $(stub-obj-y)
libqemuutil.a: $(util-obj-y)
libqemuutil.a: $(util-obj-y) qapi-types.o qapi-visit.o
block-modules = $(foreach o,$(block-obj-m),"$(basename $(subst /,-,$o))",) NULL
util/module.o-cflags = -D'CONFIG_BLOCK_MODULES=$(block-modules)'
@@ -238,44 +238,23 @@ qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
qga/qapi-generated/qga-qapi-types.c qga/qapi-generated/qga-qapi-types.h :\
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
" GEN $@")
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " GEN $@")
qga/qapi-generated/qga-qapi-visit.c qga/qapi-generated/qga-qapi-visit.h :\
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
" GEN $@")
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " GEN $@")
qga/qapi-generated/qga-qmp-commands.h qga/qapi-generated/qga-qmp-marshal.c :\
$(SRC_PATH)/qga/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
$(gen-out-type) -o qga/qapi-generated -p "qga-" -i $<, \
" GEN $@")
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
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -o qga/qapi-generated -p "qga-" < $<, " GEN $@")
qapi-types.c qapi-types.h :\
$(qapi-modules) $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py \
$(gen-out-type) -o "." -b -i $<, \
" GEN $@")
$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-types.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-types.py $(gen-out-type) -o "." -b < $<, " GEN $@")
qapi-visit.c qapi-visit.h :\
$(qapi-modules) $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py \
$(gen-out-type) -o "." -b -i $<, \
" GEN $@")
qapi-event.c qapi-event.h :\
$(qapi-modules) $(SRC_PATH)/scripts/qapi-event.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-event.py \
$(gen-out-type) -o "." -b -i $<, \
" GEN $@")
$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-visit.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-visit.py $(gen-out-type) -o "." -b < $<, " GEN $@")
qmp-commands.h qmp-marshal.c :\
$(qapi-modules) $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py \
$(gen-out-type) -o "." -m -i $<, \
" GEN $@")
$(SRC_PATH)/qapi-schema.json $(SRC_PATH)/scripts/qapi-commands.py $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi-commands.py $(gen-out-type) -m -o "." < $<, " GEN $@")
QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
@@ -350,8 +329,7 @@ multiboot.bin linuxboot.bin kvmvapic.bin \
s390-zipl.rom \
s390-ccw.img \
spapr-rtas.bin slof.bin \
palcode-clipper \
u-boot.e500
palcode-clipper
else
BLOBS=
endif
@@ -392,19 +370,19 @@ install-sysconfig: install-datadir install-confdir
install: all $(if $(BUILD_DOCS),install-doc) install-sysconfig \
install-datadir install-localstatedir
$(INSTALL_DIR) "$(DESTDIR)$(bindir)"
ifneq ($(TOOLS),)
$(call install-prog,$(TOOLS),$(DESTDIR)$(bindir))
$(INSTALL_PROG) $(STRIP_OPT) $(TOOLS) "$(DESTDIR)$(bindir)"
endif
ifneq ($(CONFIG_MODULES),)
$(INSTALL_DIR) "$(DESTDIR)$(qemu_moddir)"
for s in $(modules-m:.mo=$(DSOSUF)); do \
t="$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
$(INSTALL_LIB) $$s "$$t"; \
test -z "$(STRIP)" || $(STRIP) "$$t"; \
for s in $(patsubst %.mo,%$(DSOSUF),$(modules-m)); do \
$(INSTALL_PROG) $(STRIP_OPT) $$s "$(DESTDIR)$(qemu_moddir)/$$(echo $$s | tr / -)"; \
done
endif
ifneq ($(HELPERS-y),)
$(call install-prog,$(HELPERS-y),$(DESTDIR)$(libexecdir))
$(INSTALL_DIR) "$(DESTDIR)$(libexecdir)"
$(INSTALL_PROG) $(STRIP_OPT) $(HELPERS-y) "$(DESTDIR)$(libexecdir)"
endif
ifneq ($(BLOBS),)
set -e; for x in $(BLOBS); do \
@@ -418,7 +396,6 @@ endif
set -e; for x in $(KEYMAPS); do \
$(INSTALL_DATA) $(SRC_PATH)/pc-bios/keymaps/$$x "$(DESTDIR)$(qemu_datadir)/keymaps"; \
done
$(INSTALL_DATA) $(SRC_PATH)/trace-events "$(DESTDIR)$(qemu_datadir)/trace-events"
for d in $(TARGET_DIRS); do \
$(MAKE) $(SUBDIR_MAKEFLAGS) TARGET_DIR=$$d/ -C $$d $@ || exit 1 ; \
done

View File

@@ -1,7 +1,7 @@
#######################################################################
# Common libraries for tools and emulators
stub-obj-y = stubs/
util-obj-y = util/ qobject/ qapi/ qapi-types.o qapi-visit.o qapi-event.o
util-obj-y = util/ qobject/ qapi/ trace/
#######################################################################
# block-obj-y is code used by both qemu system emulation and qemu-img
@@ -12,6 +12,7 @@ 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
block-obj-y += block/
block-obj-y += qapi-types.o qapi-visit.o
block-obj-y += qemu-io-cmds.o
block-obj-y += qemu-coroutine.o qemu-coroutine-lock.o qemu-coroutine-io.o
@@ -30,8 +31,6 @@ libcacard-y += libcacard/vcard_emul_nss.o
libcacard-y += libcacard/vcard_emul_type.o
libcacard-y += libcacard/card_7816.o
libcacard-y += libcacard/vcardt.o
libcacard/vcard_emul_nss.o-cflags := $(NSS_CFLAGS)
libcacard/vcard_emul_nss.o-libs := $(NSS_LIBS)
######################################################################
# Target independent part of system emulation. The long term path is to
@@ -50,7 +49,7 @@ common-obj-$(CONFIG_LINUX) += fsdev/
common-obj-y += migration.o migration-tcp.o
common-obj-y += vmstate.o
common-obj-y += qemu-file.o qemu-file-unix.o qemu-file-stdio.o
common-obj-y += qemu-file.o
common-obj-$(CONFIG_RDMA) += migration-rdma.o
common-obj-y += qemu-char.o #aio.o
common-obj-y += block-migration.o
@@ -62,15 +61,12 @@ common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
common-obj-y += audio/
common-obj-y += hw/
common-obj-y += accel.o
common-obj-y += ui/
common-obj-y += bt-host.o bt-vhci.o
bt-host.o-cflags := $(BLUEZ_CFLAGS)
common-obj-y += dma-helpers.o
common-obj-y += vl.o
vl.o-cflags := $(GPROF_CFLAGS) $(SDL_CFLAGS)
common-obj-y += tpm.o
common-obj-$(CONFIG_SLIRP) += slirp/
@@ -88,6 +84,11 @@ common-obj-y += qmp-marshal.o
common-obj-y += qmp.o hmp.o
endif
######################################################################
# some qapi visitors are used by both system and user emulation:
common-obj-y += qapi-visit.o qapi-types.o
#######################################################################
# Target-independent parts used in system and user emulation
common-obj-y += qemu-log.o
@@ -101,15 +102,10 @@ common-obj-y += disas/
version-obj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.o
version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
######################################################################
# tracing
util-obj-y += trace/
target-obj-y += trace/
######################################################################
# guest agent
# FIXME: a few definitions from qapi-types.o/qapi-visit.o are needed
# by libqemuutil.a. These should be moved to a separate .json schema.
qga-obj-y = qga/
qga-obj-y = qga/ qapi-types.o qapi-visit.o
qga-vss-dll-obj-y = qga/

View File

@@ -16,29 +16,26 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/include
ifdef CONFIG_USER_ONLY
# user emulator name
QEMU_PROG=qemu-$(TARGET_NAME)
QEMU_PROG_BUILD = $(QEMU_PROG)
else
# system emulator name
QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
ifneq (,$(findstring -mwindows,$(libs_softmmu)))
# Terminate program name with a 'w' because the linker builds a windows executable.
QEMU_PROGW=qemu-system-$(TARGET_NAME)w$(EXESUF)
$(QEMU_PROG): $(QEMU_PROGW)
$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG)," GEN $(TARGET_DIR)$(QEMU_PROG)")
QEMU_PROG_BUILD = $(QEMU_PROGW)
else
QEMU_PROG_BUILD = $(QEMU_PROG)
endif
endif # windows executable
QEMU_PROG=qemu-system-$(TARGET_NAME)$(EXESUF)
endif
PROGS=$(QEMU_PROG) $(QEMU_PROGW)
PROGS=$(QEMU_PROG)
ifdef QEMU_PROGW
PROGS+=$(QEMU_PROGW)
endif
STPFILES=
config-target.h: config-target.h-timestamp
config-target.h-timestamp: config-target.mak
ifdef CONFIG_TRACE_SYSTEMTAP
stap: $(QEMU_PROG).stp-installed $(QEMU_PROG).stp $(QEMU_PROG)-simpletrace.stp
stap: $(QEMU_PROG).stp-installed $(QEMU_PROG).stp
ifdef CONFIG_USER_ONLY
TARGET_TYPE=user
@@ -49,7 +46,7 @@ endif
$(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
$(call quiet-command,$(TRACETOOL) \
--format=stap \
--backends=$(TRACE_BACKENDS) \
--backend=$(TRACE_BACKEND) \
--binary=$(bindir)/$(QEMU_PROG) \
--target-name=$(TARGET_NAME) \
--target-type=$(TARGET_TYPE) \
@@ -58,19 +55,12 @@ $(QEMU_PROG).stp-installed: $(SRC_PATH)/trace-events
$(QEMU_PROG).stp: $(SRC_PATH)/trace-events
$(call quiet-command,$(TRACETOOL) \
--format=stap \
--backends=$(TRACE_BACKENDS) \
--backend=$(TRACE_BACKEND) \
--binary=$(realpath .)/$(QEMU_PROG) \
--target-name=$(TARGET_NAME) \
--target-type=$(TARGET_TYPE) \
< $< > $@," GEN $(TARGET_DIR)$(QEMU_PROG).stp")
$(QEMU_PROG)-simpletrace.stp: $(SRC_PATH)/trace-events
$(call quiet-command,$(TRACETOOL) \
--format=simpletrace-stap \
--backends=$(TRACE_BACKENDS) \
--probe-prefix=qemu.$(TARGET_TYPE).$(TARGET_NAME) \
< $< > $@," GEN $(TARGET_DIR)$(QEMU_PROG)-simpletrace.stp")
else
stap:
endif
@@ -92,12 +82,6 @@ obj-y += disas.o
obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decNumber.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal32.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal64.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/dpd/decimal128.o
#########################################################
# Linux user emulator target
@@ -115,8 +99,7 @@ endif #CONFIG_LINUX_USER
ifdef CONFIG_BSD_USER
QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
-I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR)
obj-y += bsd-user/
obj-y += gdbstub.o user-exec.o
@@ -126,8 +109,8 @@ endif #CONFIG_BSD_USER
#########################################################
# System emulator target
ifdef CONFIG_SOFTMMU
obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o numa.o
obj-y += qtest.o bootdevice.o
obj-y += arch_init.o cpus.o monitor.o gdbstub.o balloon.o ioport.o
obj-y += qtest.o
obj-y += hw/
obj-$(CONFIG_FDT) += device_tree.o
obj-$(CONFIG_KVM) += kvm-all.o
@@ -137,10 +120,8 @@ obj-y += dump.o
LIBS+=$(libs_softmmu)
# xen support
obj-$(CONFIG_XEN) += xen-common.o
obj-$(CONFIG_XEN_I386) += xen-hvm.o xen-mapcache.o
obj-$(call lnot,$(CONFIG_XEN)) += xen-common-stub.o
obj-$(call lnot,$(CONFIG_XEN_I386)) += xen-hvm-stub.o
obj-$(CONFIG_XEN) += xen-all.o xen-mapcache.o
obj-$(call lnot,$(CONFIG_XEN)) += xen-stub.o
# Hardware support
ifeq ($(TARGET_NAME), sparc64)
@@ -157,27 +138,40 @@ endif # CONFIG_SOFTMMU
%/translate.o: QEMU_CFLAGS += $(TRANSLATE_OPT_CFLAGS)
dummy := $(call unnest-vars,,obj-y)
all-obj-y := $(obj-y)
target-obj-y :=
# we are making another call to unnest-vars with different vars, protect obj-y,
# it can be overriden in subdir Makefile.objs
obj-y-save := $(obj-y)
block-obj-y :=
common-obj-y :=
include $(SRC_PATH)/Makefile.objs
dummy := $(call unnest-vars,,target-obj-y)
target-obj-y-save := $(target-obj-y)
dummy := $(call unnest-vars,.., \
block-obj-y \
block-obj-m \
common-obj-y \
common-obj-m)
target-obj-y := $(target-obj-y-save)
all-obj-y += $(common-obj-y)
all-obj-y += $(target-obj-y)
# Now restore obj-y
obj-y := $(obj-y-save)
all-obj-y = $(obj-y) $(common-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
# build either PROG or PROGW
$(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
ifndef CONFIG_HAIKU
LIBS+=-lm
endif
ifdef QEMU_PROGW
# The linker builds a windows executable. Make also a console executable.
$(QEMU_PROGW): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
$(call LINK,$^)
$(QEMU_PROG): $(QEMU_PROGW)
$(call quiet-command,$(OBJCOPY) --subsystem console $(QEMU_PROGW) $(QEMU_PROG)," GEN $(TARGET_DIR)$(QEMU_PROG)")
else
$(QEMU_PROG): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
$(call LINK,$^)
endif
gdbstub-xml.c: $(TARGET_XML_FILES) $(SRC_PATH)/scripts/feature_to_c.sh
$(call quiet-command,rm -f $@ && $(SHELL) $(SRC_PATH)/scripts/feature_to_c.sh $@ $(TARGET_XML_FILES)," GEN $(TARGET_DIR)$@")
@@ -198,12 +192,14 @@ endif
install: all
ifneq ($(PROGS),)
$(call install-prog,$(PROGS),$(DESTDIR)$(bindir))
$(INSTALL) -m 755 $(PROGS) "$(DESTDIR)$(bindir)"
ifneq ($(STRIP),)
$(STRIP) $(patsubst %,"$(DESTDIR)$(bindir)/%",$(PROGS))
endif
endif
ifdef CONFIG_TRACE_SYSTEMTAP
$(INSTALL_DIR) "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset"
$(INSTALL_DATA) $(QEMU_PROG).stp-installed "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset/$(QEMU_PROG).stp"
$(INSTALL_DATA) $(QEMU_PROG)-simpletrace.stp "$(DESTDIR)$(qemu_datadir)/../systemtap/tapset/$(QEMU_PROG)-simpletrace.stp"
endif
GENERATED_HEADERS += config-target.h

View File

@@ -1 +1 @@
2.1.90
2.0.2

157
accel.c
View File

@@ -1,157 +0,0 @@
/*
* QEMU System Emulator, accelerator interfaces
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2014 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 "sysemu/accel.h"
#include "hw/boards.h"
#include "qemu-common.h"
#include "sysemu/arch_init.h"
#include "sysemu/sysemu.h"
#include "sysemu/kvm.h"
#include "sysemu/qtest.h"
#include "hw/xen/xen.h"
#include "qom/object.h"
#include "hw/boards.h"
int tcg_tb_size;
static bool tcg_allowed = true;
static int tcg_init(MachineState *ms)
{
tcg_exec_init(tcg_tb_size * 1024 * 1024);
return 0;
}
static const TypeInfo accel_type = {
.name = TYPE_ACCEL,
.parent = TYPE_OBJECT,
.class_size = sizeof(AccelClass),
.instance_size = sizeof(AccelState),
};
/* Lookup AccelClass from opt_name. Returns NULL if not found */
static AccelClass *accel_find(const char *opt_name)
{
char *class_name = g_strdup_printf(ACCEL_CLASS_NAME("%s"), opt_name);
AccelClass *ac = ACCEL_CLASS(object_class_by_name(class_name));
g_free(class_name);
return ac;
}
static int accel_init_machine(AccelClass *acc, MachineState *ms)
{
ObjectClass *oc = OBJECT_CLASS(acc);
const char *cname = object_class_get_name(oc);
AccelState *accel = ACCEL(object_new(cname));
int ret;
ms->accelerator = accel;
*(acc->allowed) = true;
ret = acc->init_machine(ms);
if (ret < 0) {
ms->accelerator = NULL;
*(acc->allowed) = false;
object_unref(OBJECT(accel));
}
return ret;
}
int configure_accelerator(MachineState *ms)
{
const char *p;
char buf[10];
int ret;
bool accel_initialised = false;
bool init_failed = false;
AccelClass *acc = NULL;
p = qemu_opt_get(qemu_get_machine_opts(), "accel");
if (p == NULL) {
/* Use the default "accelerator", tcg */
p = "tcg";
}
while (!accel_initialised && *p != '\0') {
if (*p == ':') {
p++;
}
p = get_opt_name(buf, sizeof(buf), p, ':');
acc = accel_find(buf);
if (!acc) {
fprintf(stderr, "\"%s\" accelerator not found.\n", buf);
continue;
}
if (acc->available && !acc->available()) {
printf("%s not supported for this target\n",
acc->name);
continue;
}
ret = accel_init_machine(acc, ms);
if (ret < 0) {
init_failed = true;
fprintf(stderr, "failed to initialize %s: %s\n",
acc->name,
strerror(-ret));
} else {
accel_initialised = true;
}
}
if (!accel_initialised) {
if (!init_failed) {
fprintf(stderr, "No accelerator found!\n");
}
exit(1);
}
if (init_failed) {
fprintf(stderr, "Back to %s accelerator.\n", acc->name);
}
return !accel_initialised;
}
static void tcg_accel_class_init(ObjectClass *oc, void *data)
{
AccelClass *ac = ACCEL_CLASS(oc);
ac->name = "tcg";
ac->init_machine = tcg_init;
ac->allowed = &tcg_allowed;
}
#define TYPE_TCG_ACCEL ACCEL_CLASS_NAME("tcg")
static const TypeInfo tcg_accel_type = {
.name = TYPE_TCG_ACCEL,
.parent = TYPE_ACCEL,
.class_init = tcg_accel_class_init,
};
static void register_accel_types(void)
{
type_register_static(&accel_type);
type_register_static(&tcg_accel_type);
}
type_init(register_accel_types);

View File

@@ -100,11 +100,6 @@ void aio_set_event_notifier(AioContext *ctx,
(IOHandler *)io_read, NULL, notifier);
}
bool aio_prepare(AioContext *ctx)
{
return false;
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
@@ -124,22 +119,13 @@ bool aio_pending(AioContext *ctx)
return false;
}
bool aio_dispatch(AioContext *ctx)
static bool aio_dispatch(AioContext *ctx)
{
AioHandler *node;
bool progress = false;
/*
* If there are callbacks left that have been queued, we need to call them.
* Do not call select in this case, because it is possible that the caller
* does not need a complete flush (as is the case for aio_poll loops).
*/
if (aio_bh_poll(ctx)) {
progress = true;
}
/*
* We have to walk very carefully in case aio_set_fd_handler is
* We have to walk very carefully in case qemu_aio_set_fd_handler is
* called while we're walking.
*/
node = QLIST_FIRST(&ctx->aio_handlers);
@@ -189,24 +175,28 @@ bool aio_dispatch(AioContext *ctx)
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
bool was_dispatching;
int ret;
bool progress;
was_dispatching = ctx->dispatching;
progress = false;
/* aio_notify can avoid the expensive event_notifier_set if
* everything (file descriptors, bottom halves, timers) will
* be re-evaluated before the next blocking poll(). This is
* already true when aio_poll is called with blocking == false;
* if blocking == true, it is only true after poll() returns.
*
* If we're in a nested event loop, ctx->dispatching might be true.
* In that case we can restore it just before returning, but we
* have to clear it now.
/*
* If there are callbacks left that have been queued, we need to call them.
* Do not call select in this case, because it is possible that the caller
* does not need a complete flush (as is the case for qemu_aio_wait loops).
*/
aio_set_dispatching(ctx, !blocking);
if (aio_bh_poll(ctx)) {
blocking = false;
progress = true;
}
if (aio_dispatch(ctx)) {
progress = true;
}
if (progress && !blocking) {
return true;
}
ctx->walking_handlers++;
@@ -230,7 +220,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
/* wait until next event */
ret = qemu_poll_ns((GPollFD *)ctx->pollfds->data,
ctx->pollfds->len,
blocking ? aio_compute_timeout(ctx) : 0);
blocking ? timerlistgroup_deadline_ns(&ctx->tlg) : 0);
/* if we have any readable fds, dispatch event */
if (ret > 0) {
@@ -244,11 +234,9 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
/* Run dispatch even if there were no readable fds to run timers */
aio_set_dispatching(ctx, true);
if (aio_dispatch(ctx)) {
progress = true;
}
aio_set_dispatching(ctx, was_dispatching);
return progress;
}

View File

@@ -22,80 +22,12 @@
struct AioHandler {
EventNotifier *e;
IOHandler *io_read;
IOHandler *io_write;
EventNotifierHandler *io_notify;
GPollFD pfd;
int deleted;
void *opaque;
QLIST_ENTRY(AioHandler) node;
};
void aio_set_fd_handler(AioContext *ctx,
int fd,
IOHandler *io_read,
IOHandler *io_write,
void *opaque)
{
/* fd is a SOCKET in our case */
AioHandler *node;
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->pfd.fd == fd && !node->deleted) {
break;
}
}
/* Are we deleting the fd handler? */
if (!io_read && !io_write) {
if (node) {
/* If the lock is held, just mark the node as deleted */
if (ctx->walking_handlers) {
node->deleted = 1;
node->pfd.revents = 0;
} else {
/* Otherwise, delete it for real. We can't just mark it as
* deleted because deleted nodes are only cleaned up after
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
g_free(node);
}
}
} else {
HANDLE event;
if (node == NULL) {
/* Alloc and insert if it's not already there */
node = g_malloc0(sizeof(AioHandler));
node->pfd.fd = fd;
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
}
node->pfd.events = 0;
if (node->io_read) {
node->pfd.events |= G_IO_IN;
}
if (node->io_write) {
node->pfd.events |= G_IO_OUT;
}
node->e = &ctx->notifier;
/* Update handler with latest information */
node->opaque = opaque;
node->io_read = io_read;
node->io_write = io_write;
event = event_notifier_get_handle(&ctx->notifier);
WSAEventSelect(node->pfd.fd, event,
FD_READ | FD_ACCEPT | FD_CLOSE |
FD_CONNECT | FD_WRITE | FD_OOB);
}
aio_notify(ctx);
}
void aio_set_event_notifier(AioContext *ctx,
EventNotifier *e,
EventNotifierHandler *io_notify)
@@ -144,43 +76,6 @@ void aio_set_event_notifier(AioContext *ctx,
aio_notify(ctx);
}
bool aio_prepare(AioContext *ctx)
{
static struct timeval tv0;
AioHandler *node;
bool have_select_revents = false;
fd_set rfds, wfds;
/* fill fd sets */
FD_ZERO(&rfds);
FD_ZERO(&wfds);
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->io_read) {
FD_SET ((SOCKET)node->pfd.fd, &rfds);
}
if (node->io_write) {
FD_SET ((SOCKET)node->pfd.fd, &wfds);
}
}
if (select(0, &rfds, &wfds, NULL, &tv0) > 0) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
node->pfd.revents = 0;
if (FD_ISSET(node->pfd.fd, &rfds)) {
node->pfd.revents |= G_IO_IN;
have_select_revents = true;
}
if (FD_ISSET(node->pfd.fd, &wfds)) {
node->pfd.revents |= G_IO_OUT;
have_select_revents = true;
}
}
}
return have_select_revents;
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
@@ -189,37 +84,47 @@ bool aio_pending(AioContext *ctx)
if (node->pfd.revents && node->io_notify) {
return true;
}
if ((node->pfd.revents & G_IO_IN) && node->io_read) {
return true;
}
if ((node->pfd.revents & G_IO_OUT) && node->io_write) {
return true;
}
}
return false;
}
static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
bool progress = false;
HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
bool progress;
int count;
int timeout;
progress = false;
/*
* We have to walk very carefully in case aio_set_fd_handler is
* If there are callbacks left that have been queued, we need to call then.
* Do not call select in this case, because it is possible that the caller
* does not need a complete flush (as is the case for qemu_aio_wait loops).
*/
if (aio_bh_poll(ctx)) {
blocking = false;
progress = true;
}
/* Run timers */
progress |= timerlistgroup_run_timers(&ctx->tlg);
/*
* Then dispatch any pending callbacks from the GSource.
*
* We have to walk very carefully in case qemu_aio_set_fd_handler is
* called while we're walking.
*/
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
int revents = node->pfd.revents;
ctx->walking_handlers++;
if (!node->deleted &&
(revents || event_notifier_get_handle(node->e) == event) &&
node->io_notify) {
if (node->pfd.revents && node->io_notify) {
node->pfd.revents = 0;
node->io_notify(node->e);
@@ -229,28 +134,6 @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
}
}
if (!node->deleted &&
(node->io_read || node->io_write)) {
node->pfd.revents = 0;
if ((revents & G_IO_IN) && node->io_read) {
node->io_read(node->opaque);
progress = true;
}
if ((revents & G_IO_OUT) && node->io_write) {
node->io_write(node->opaque);
progress = true;
}
/* if the next select() will return an event, we have progressed */
if (event == event_notifier_get_handle(&ctx->notifier)) {
WSANETWORKEVENTS ev;
WSAEnumNetworkEvents(node->pfd.fd, event, &ev);
if (ev.lNetworkEvents) {
progress = true;
}
}
}
tmp = node;
node = QLIST_NEXT(node, node);
@@ -262,47 +145,10 @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
}
}
return progress;
}
bool aio_dispatch(AioContext *ctx)
{
bool progress;
progress = aio_bh_poll(ctx);
progress |= aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE);
progress |= timerlistgroup_run_timers(&ctx->tlg);
return progress;
}
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
HANDLE events[MAXIMUM_WAIT_OBJECTS + 1];
bool was_dispatching, progress, have_select_revents, first;
int count;
int timeout;
have_select_revents = aio_prepare(ctx);
if (have_select_revents) {
blocking = false;
if (progress && !blocking) {
return true;
}
was_dispatching = ctx->dispatching;
progress = false;
/* aio_notify can avoid the expensive event_notifier_set if
* everything (file descriptors, bottom halves, timers) will
* be re-evaluated before the next blocking poll(). This is
* already true when aio_poll is called with blocking == false;
* if blocking == true, it is only true after poll() returns.
*
* If we're in a nested event loop, ctx->dispatching might be true.
* In that case we can restore it just before returning, but we
* have to clear it now.
*/
aio_set_dispatching(ctx, !blocking);
ctx->walking_handlers++;
/* fill fd sets */
@@ -314,40 +160,64 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
ctx->walking_handlers--;
first = true;
/* wait until next event */
while (count > 0) {
HANDLE event;
int ret;
timeout = blocking
? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0;
timeout = blocking ?
qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg)) : 0;
ret = WaitForMultipleObjects(count, events, FALSE, timeout);
aio_set_dispatching(ctx, true);
if (first && aio_bh_poll(ctx)) {
progress = true;
}
first = false;
/* if we have any signaled events, dispatch event */
event = NULL;
if ((DWORD) (ret - WAIT_OBJECT_0) < count) {
event = events[ret - WAIT_OBJECT_0];
events[ret - WAIT_OBJECT_0] = events[--count];
} else if (!have_select_revents) {
if ((DWORD) (ret - WAIT_OBJECT_0) >= count) {
break;
}
have_select_revents = false;
blocking = false;
progress |= aio_dispatch_handlers(ctx, event);
/* we have to walk very carefully in case
* qemu_aio_set_fd_handler is called while we're walking */
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
ctx->walking_handlers++;
if (!node->deleted &&
event_notifier_get_handle(node->e) == events[ret - WAIT_OBJECT_0] &&
node->io_notify) {
node->io_notify(node->e);
/* aio_notify() does not count as progress */
if (node->e != &ctx->notifier) {
progress = true;
}
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
/* Try again, but only call each handler once. */
events[ret - WAIT_OBJECT_0] = events[--count];
}
progress |= timerlistgroup_run_timers(&ctx->tlg);
if (blocking) {
/* Run the timers a second time. We do this because otherwise aio_wait
* will not note progress - and will stop a drain early - if we have
* a timer that was not ready to run entering g_poll but is ready
* after g_poll. This will only do anything if a timer has expired.
*/
progress |= timerlistgroup_run_timers(&ctx->tlg);
}
aio_set_dispatching(ctx, was_dispatching);
return progress;
}

View File

@@ -45,7 +45,6 @@
#include "hw/audio/pcspk.h"
#include "migration/page_cache.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qmp-commands.h"
#include "trace.h"
#include "exec/cpu-all.h"
@@ -104,8 +103,6 @@ int graphic_depth = 32;
#define QEMU_ARCH QEMU_ARCH_XTENSA
#elif defined(TARGET_UNICORE32)
#define QEMU_ARCH QEMU_ARCH_UNICORE32
#elif defined(TARGET_TRICORE)
#define QEMU_ARCH QEMU_ARCH_TRICORE
#endif
const uint32_t arch_type = QEMU_ARCH;
@@ -113,8 +110,6 @@ static bool mig_throttle_on;
static int dirty_rate_high_cnt;
static void check_guest_throttling(void);
static uint64_t bitmap_sync_count;
/***********************************************************/
/* ram save/restore */
@@ -172,8 +167,11 @@ static struct {
/* Cache for XBZRLE, Protected by lock. */
PageCache *cache;
QemuMutex lock;
} XBZRLE;
} XBZRLE = {
.encoded_buf = NULL,
.current_buf = NULL,
.cache = NULL,
};
/* buffer used for XBZRLE decoding */
static uint8_t *xbzrle_decoded_buf;
@@ -189,44 +187,41 @@ static void XBZRLE_cache_unlock(void)
qemu_mutex_unlock(&XBZRLE.lock);
}
/*
* called from qmp_migrate_set_cache_size in main thread, possibly while
* a migration is in progress.
* A running migration maybe using the cache and might finish during this
* call, hence changes to the cache are protected by XBZRLE.lock().
*/
int64_t xbzrle_cache_resize(int64_t new_size)
{
PageCache *new_cache;
int64_t ret;
PageCache *new_cache, *cache_to_free;
if (new_size < TARGET_PAGE_SIZE) {
return -1;
}
XBZRLE_cache_lock();
/* no need to lock, the current thread holds qemu big lock */
if (XBZRLE.cache != NULL) {
/* check XBZRLE.cache again later */
if (pow2floor(new_size) == migrate_xbzrle_cache_size()) {
goto out_new_size;
return pow2floor(new_size);
}
new_cache = cache_init(new_size / TARGET_PAGE_SIZE,
TARGET_PAGE_SIZE);
if (!new_cache) {
error_report("Error creating cache");
ret = -1;
goto out;
DPRINTF("Error creating cache\n");
return -1;
}
cache_fini(XBZRLE.cache);
XBZRLE.cache = new_cache;
XBZRLE_cache_lock();
/* the XBZRLE.cache may have be destroyed, check it again */
if (XBZRLE.cache != NULL) {
cache_to_free = XBZRLE.cache;
XBZRLE.cache = new_cache;
} else {
cache_to_free = new_cache;
}
XBZRLE_cache_unlock();
cache_fini(cache_to_free);
}
out_new_size:
ret = pow2floor(new_size);
out:
XBZRLE_cache_unlock();
return ret;
return pow2floor(new_size);
}
/* accounting for migration statistics */
@@ -238,7 +233,6 @@ typedef struct AccountingInfo {
uint64_t xbzrle_bytes;
uint64_t xbzrle_pages;
uint64_t xbzrle_cache_miss;
double xbzrle_cache_miss_rate;
uint64_t xbzrle_overflows;
} AccountingInfo;
@@ -294,11 +288,6 @@ uint64_t xbzrle_mig_pages_cache_miss(void)
return acct_info.xbzrle_cache_miss;
}
double xbzrle_mig_cache_miss_rate(void)
{
return acct_info.xbzrle_cache_miss_rate;
}
uint64_t xbzrle_mig_pages_overflow(void)
{
return acct_info.xbzrle_overflows;
@@ -351,7 +340,7 @@ static void xbzrle_cache_zero_page(ram_addr_t current_addr)
#define ENCODING_FLAG_XBZRLE 0x1
static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
static int save_xbzrle_page(QEMUFile *f, uint8_t *current_data,
ram_addr_t current_addr, RAMBlock *block,
ram_addr_t offset, int cont, bool last_stage)
{
@@ -359,23 +348,19 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
uint8_t *prev_cached_page;
if (!cache_is_cached(XBZRLE.cache, current_addr)) {
acct_info.xbzrle_cache_miss++;
if (!last_stage) {
if (cache_insert(XBZRLE.cache, current_addr, *current_data) == -1) {
if (cache_insert(XBZRLE.cache, current_addr, current_data) == -1) {
return -1;
} else {
/* update *current_data when the page has been
inserted into cache */
*current_data = get_cached_data(XBZRLE.cache, current_addr);
}
}
acct_info.xbzrle_cache_miss++;
return -1;
}
prev_cached_page = get_cached_data(XBZRLE.cache, current_addr);
/* save current buffer into memory */
memcpy(XBZRLE.current_buf, *current_data, TARGET_PAGE_SIZE);
memcpy(XBZRLE.current_buf, current_data, TARGET_PAGE_SIZE);
/* XBZRLE encoding (if there is no overflow) */
encoded_len = xbzrle_encode_buffer(prev_cached_page, XBZRLE.current_buf,
@@ -388,10 +373,7 @@ static int save_xbzrle_page(QEMUFile *f, uint8_t **current_data,
DPRINTF("Overflow\n");
acct_info.xbzrle_overflows++;
/* update data in the cache */
if (!last_stage) {
memcpy(prev_cached_page, *current_data, TARGET_PAGE_SIZE);
*current_data = prev_cached_page;
}
memcpy(prev_cached_page, current_data, TARGET_PAGE_SIZE);
return -1;
}
@@ -497,10 +479,6 @@ static void migration_bitmap_sync(void)
static int64_t num_dirty_pages_period;
int64_t end_time;
int64_t bytes_xfer_now;
static uint64_t xbzrle_cache_miss_prev;
static uint64_t iterations_prev;
bitmap_sync_count++;
if (!bytes_xfer_prev) {
bytes_xfer_prev = ram_bytes_transferred();
@@ -542,113 +520,29 @@ static void migration_bitmap_sync(void)
} else {
mig_throttle_on = false;
}
if (migrate_use_xbzrle()) {
if (iterations_prev != 0) {
acct_info.xbzrle_cache_miss_rate =
(double)(acct_info.xbzrle_cache_miss -
xbzrle_cache_miss_prev) /
(acct_info.iterations - iterations_prev);
}
iterations_prev = acct_info.iterations;
xbzrle_cache_miss_prev = acct_info.xbzrle_cache_miss;
}
s->dirty_pages_rate = num_dirty_pages_period * 1000
/ (end_time - start_time);
s->dirty_bytes_rate = s->dirty_pages_rate * TARGET_PAGE_SIZE;
start_time = end_time;
num_dirty_pages_period = 0;
s->dirty_sync_count = bitmap_sync_count;
}
}
/*
* ram_save_page: Send the given page to the stream
*
* Returns: Number of bytes written.
*/
static int ram_save_page(QEMUFile *f, RAMBlock* block, ram_addr_t offset,
bool last_stage)
{
int bytes_sent;
int cont;
ram_addr_t current_addr;
MemoryRegion *mr = block->mr;
uint8_t *p;
int ret;
bool send_async = true;
cont = (block == last_sent_block) ? RAM_SAVE_FLAG_CONTINUE : 0;
p = memory_region_get_ram_ptr(mr) + offset;
/* In doubt sent page as normal */
bytes_sent = -1;
ret = ram_control_save_page(f, block->offset,
offset, TARGET_PAGE_SIZE, &bytes_sent);
XBZRLE_cache_lock();
current_addr = block->offset + offset;
if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret != RAM_SAVE_CONTROL_DELAYED) {
if (bytes_sent > 0) {
acct_info.norm_pages++;
} else if (bytes_sent == 0) {
acct_info.dup_pages++;
}
}
} else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
acct_info.dup_pages++;
bytes_sent = save_block_hdr(f, block, offset, cont,
RAM_SAVE_FLAG_COMPRESS);
qemu_put_byte(f, 0);
bytes_sent++;
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
*/
xbzrle_cache_zero_page(current_addr);
} else if (!ram_bulk_stage && migrate_use_xbzrle()) {
bytes_sent = save_xbzrle_page(f, &p, current_addr, block,
offset, cont, last_stage);
if (!last_stage) {
/* Can't send this cached data async, since the cache page
* might get updated before it gets to the wire
*/
send_async = false;
}
}
/* XBZRLE overflow or normal page */
if (bytes_sent == -1) {
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
if (send_async) {
qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
} else {
qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
}
bytes_sent += TARGET_PAGE_SIZE;
acct_info.norm_pages++;
}
XBZRLE_cache_unlock();
return bytes_sent;
}
/*
* ram_find_and_save_block: Finds a page to send and sends it to f
* ram_save_block: Writes a page of memory to the stream f
*
* Returns: The number of bytes written.
* 0 means no dirty pages
*/
static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
static int ram_save_block(QEMUFile *f, bool last_stage)
{
RAMBlock *block = last_seen_block;
ram_addr_t offset = last_offset;
bool complete_round = false;
int bytes_sent = 0;
MemoryRegion *mr;
ram_addr_t current_addr;
if (!block)
block = QTAILQ_FIRST(&ram_list.blocks);
@@ -669,8 +563,70 @@ static int ram_find_and_save_block(QEMUFile *f, bool last_stage)
ram_bulk_stage = false;
}
} else {
bytes_sent = ram_save_page(f, block, offset, last_stage);
int ret;
uint8_t *p;
bool send_async = true;
int cont = (block == last_sent_block) ?
RAM_SAVE_FLAG_CONTINUE : 0;
p = memory_region_get_ram_ptr(mr) + offset;
/* In doubt sent page as normal */
bytes_sent = -1;
ret = ram_control_save_page(f, block->offset,
offset, TARGET_PAGE_SIZE, &bytes_sent);
XBZRLE_cache_lock();
current_addr = block->offset + offset;
if (ret != RAM_SAVE_CONTROL_NOT_SUPP) {
if (ret != RAM_SAVE_CONTROL_DELAYED) {
if (bytes_sent > 0) {
acct_info.norm_pages++;
} else if (bytes_sent == 0) {
acct_info.dup_pages++;
}
}
} else if (is_zero_range(p, TARGET_PAGE_SIZE)) {
acct_info.dup_pages++;
bytes_sent = save_block_hdr(f, block, offset, cont,
RAM_SAVE_FLAG_COMPRESS);
qemu_put_byte(f, 0);
bytes_sent++;
/* Must let xbzrle know, otherwise a previous (now 0'd) cached
* page would be stale
*/
xbzrle_cache_zero_page(current_addr);
} else if (!ram_bulk_stage && migrate_use_xbzrle()) {
bytes_sent = save_xbzrle_page(f, p, current_addr, block,
offset, cont, last_stage);
if (!last_stage) {
/* We must send exactly what's in the xbzrle cache
* even if the page wasn't xbzrle compressed, so that
* it's right next time.
*/
p = get_cached_data(XBZRLE.cache, current_addr);
/* Can't send this cached data async, since the cache page
* might get updated before it gets to the wire
*/
send_async = false;
}
}
/* XBZRLE overflow or normal page */
if (bytes_sent == -1) {
bytes_sent = save_block_hdr(f, block, offset, cont, RAM_SAVE_FLAG_PAGE);
if (send_async) {
qemu_put_buffer_async(f, p, TARGET_PAGE_SIZE);
} else {
qemu_put_buffer(f, p, TARGET_PAGE_SIZE);
}
bytes_sent += TARGET_PAGE_SIZE;
acct_info.norm_pages++;
}
XBZRLE_cache_unlock();
/* if page is unmodified, continue to the next */
if (bytes_sent > 0) {
last_sent_block = block;
@@ -741,6 +697,7 @@ static void migration_end(void)
XBZRLE_cache_lock();
if (XBZRLE.cache) {
cache_fini(XBZRLE.cache);
g_free(XBZRLE.cache);
g_free(XBZRLE.encoded_buf);
g_free(XBZRLE.current_buf);
XBZRLE.cache = NULL;
@@ -769,34 +726,37 @@ static void reset_ram_globals(void)
static int ram_save_setup(QEMUFile *f, void *opaque)
{
RAMBlock *block;
int64_t ram_bitmap_pages; /* Size of bitmap in pages, including gaps */
int64_t ram_pages = last_ram_offset() >> TARGET_PAGE_BITS;
migration_bitmap = bitmap_new(ram_pages);
bitmap_set(migration_bitmap, 0, ram_pages);
migration_dirty_pages = ram_pages;
mig_throttle_on = false;
dirty_rate_high_cnt = 0;
bitmap_sync_count = 0;
if (migrate_use_xbzrle()) {
XBZRLE_cache_lock();
qemu_mutex_lock_iothread();
XBZRLE.cache = cache_init(migrate_xbzrle_cache_size() /
TARGET_PAGE_SIZE,
TARGET_PAGE_SIZE);
if (!XBZRLE.cache) {
XBZRLE_cache_unlock();
error_report("Error creating cache");
qemu_mutex_unlock_iothread();
DPRINTF("Error creating cache\n");
return -1;
}
XBZRLE_cache_unlock();
qemu_mutex_init(&XBZRLE.lock);
qemu_mutex_unlock_iothread();
/* We prefer not to abort if there is no memory */
XBZRLE.encoded_buf = g_try_malloc0(TARGET_PAGE_SIZE);
if (!XBZRLE.encoded_buf) {
error_report("Error allocating encoded_buf");
DPRINTF("Error allocating encoded_buf\n");
return -1;
}
XBZRLE.current_buf = g_try_malloc(TARGET_PAGE_SIZE);
if (!XBZRLE.current_buf) {
error_report("Error allocating current_buf");
DPRINTF("Error allocating current_buf\n");
g_free(XBZRLE.encoded_buf);
XBZRLE.encoded_buf = NULL;
return -1;
@@ -810,22 +770,6 @@ static int ram_save_setup(QEMUFile *f, void *opaque)
bytes_transferred = 0;
reset_ram_globals();
ram_bitmap_pages = last_ram_offset() >> TARGET_PAGE_BITS;
migration_bitmap = bitmap_new(ram_bitmap_pages);
bitmap_set(migration_bitmap, 0, ram_bitmap_pages);
/*
* Count the total number of pages used by ram blocks not including any
* gaps due to alignment or unplugs.
*/
migration_dirty_pages = 0;
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
uint64_t block_pages;
block_pages = block->length >> TARGET_PAGE_BITS;
migration_dirty_pages += block_pages;
}
memory_global_dirty_log_start();
migration_bitmap_sync();
qemu_mutex_unlock_iothread();
@@ -868,7 +812,7 @@ static int ram_save_iterate(QEMUFile *f, void *opaque)
while ((ret = qemu_file_rate_limit(f)) == 0) {
int bytes_sent;
bytes_sent = ram_find_and_save_block(f, false);
bytes_sent = ram_save_block(f, false);
/* no more blocks to sent */
if (bytes_sent == 0) {
break;
@@ -930,7 +874,7 @@ static int ram_save_complete(QEMUFile *f, void *opaque)
while (true) {
int bytes_sent;
bytes_sent = ram_find_and_save_block(f, true);
bytes_sent = ram_save_block(f, true);
/* no more blocks to sent */
if (bytes_sent == 0) {
break;
@@ -964,6 +908,7 @@ static uint64_t ram_save_pending(QEMUFile *f, void *opaque, uint64_t max_size)
static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
{
int ret, rc = 0;
unsigned int xh_len;
int xh_flags;
@@ -976,25 +921,30 @@ static int load_xbzrle(QEMUFile *f, ram_addr_t addr, void *host)
xh_len = qemu_get_be16(f);
if (xh_flags != ENCODING_FLAG_XBZRLE) {
error_report("Failed to load XBZRLE page - wrong compression!");
fprintf(stderr, "Failed to load XBZRLE page - wrong compression!\n");
return -1;
}
if (xh_len > TARGET_PAGE_SIZE) {
error_report("Failed to load XBZRLE page - len overflow!");
fprintf(stderr, "Failed to load XBZRLE page - len overflow!\n");
return -1;
}
/* load data and decode */
qemu_get_buffer(f, xbzrle_decoded_buf, xh_len);
/* decode RLE */
if (xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
TARGET_PAGE_SIZE) == -1) {
error_report("Failed to load XBZRLE page - decode error!");
return -1;
ret = xbzrle_decode_buffer(xbzrle_decoded_buf, xh_len, host,
TARGET_PAGE_SIZE);
if (ret == -1) {
fprintf(stderr, "Failed to load XBZRLE page - decode error!\n");
rc = -1;
} else if (ret > TARGET_PAGE_SIZE) {
fprintf(stderr, "Failed to load XBZRLE page - size %d exceeds %d!\n",
ret, TARGET_PAGE_SIZE);
abort();
}
return 0;
return rc;
}
static inline void *host_from_stream_offset(QEMUFile *f,
@@ -1007,7 +957,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
if (flags & RAM_SAVE_FLAG_CONTINUE) {
if (!block) {
error_report("Ack, bad migration stream!");
fprintf(stderr, "Ack, bad migration stream!\n");
return NULL;
}
@@ -1023,7 +973,7 @@ static inline void *host_from_stream_offset(QEMUFile *f,
return memory_region_get_ram_ptr(block->mr) + offset;
}
error_report("Can't find block %s!", id);
fprintf(stderr, "Can't find block %s!\n", id);
return NULL;
}
@@ -1040,7 +990,8 @@ void ram_handle_compressed(void *host, uint8_t ch, uint64_t size)
static int ram_load(QEMUFile *f, void *opaque, int version_id)
{
int flags = 0, ret = 0;
ram_addr_t addr;
int flags, ret = 0;
static uint64_t seq_iter;
seq_iter++;
@@ -1049,24 +1000,21 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
ret = -EINVAL;
}
while (!ret && !(flags & RAM_SAVE_FLAG_EOS)) {
ram_addr_t addr, total_ram_bytes;
void *host;
uint8_t ch;
while (!ret) {
addr = qemu_get_be64(f);
flags = addr & ~TARGET_PAGE_MASK;
addr &= TARGET_PAGE_MASK;
switch (flags & ~RAM_SAVE_FLAG_CONTINUE) {
case RAM_SAVE_FLAG_MEM_SIZE:
if (flags & RAM_SAVE_FLAG_MEM_SIZE) {
/* Synchronize RAM block list */
total_ram_bytes = addr;
while (!ret && total_ram_bytes) {
char id[256];
ram_addr_t length;
ram_addr_t total_ram_bytes = addr;
while (total_ram_bytes) {
RAMBlock *block;
uint8_t len;
char id[256];
ram_addr_t length;
len = qemu_get_byte(f);
qemu_get_buffer(f, (uint8_t *)id, len);
@@ -1076,9 +1024,10 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
QTAILQ_FOREACH(block, &ram_list.blocks, next) {
if (!strncmp(id, block->idstr, sizeof(id))) {
if (block->length != length) {
error_report("Length mismatch: %s: 0x" RAM_ADDR_FMT
" in != 0x" RAM_ADDR_FMT, id, length,
block->length);
fprintf(stderr,
"Length mismatch: %s: " RAM_ADDR_FMT
" in != " RAM_ADDR_FMT "\n", id, length,
block->length);
ret = -EINVAL;
}
break;
@@ -1086,15 +1035,20 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
}
if (!block) {
error_report("Unknown ramblock \"%s\", cannot "
"accept migration", id);
fprintf(stderr, "Unknown ramblock \"%s\", cannot "
"accept migration\n", id);
ret = -EINVAL;
}
if (ret) {
break;
}
total_ram_bytes -= length;
}
break;
case RAM_SAVE_FLAG_COMPRESS:
} else if (flags & RAM_SAVE_FLAG_COMPRESS) {
void *host;
uint8_t ch;
host = host_from_stream_offset(f, addr, flags);
if (!host) {
error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
@@ -1104,8 +1058,9 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
ch = qemu_get_byte(f);
ram_handle_compressed(host, ch, TARGET_PAGE_SIZE);
break;
case RAM_SAVE_FLAG_PAGE:
} else if (flags & RAM_SAVE_FLAG_PAGE) {
void *host;
host = host_from_stream_offset(f, addr, flags);
if (!host) {
error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
@@ -1114,9 +1069,8 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
}
qemu_get_buffer(f, host, TARGET_PAGE_SIZE);
break;
case RAM_SAVE_FLAG_XBZRLE:
host = host_from_stream_offset(f, addr, flags);
} else if (flags & RAM_SAVE_FLAG_XBZRLE) {
void *host = host_from_stream_offset(f, addr, flags);
if (!host) {
error_report("Illegal RAM offset " RAM_ADDR_FMT, addr);
ret = -EINVAL;
@@ -1129,22 +1083,17 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
ret = -EINVAL;
break;
}
break;
case RAM_SAVE_FLAG_EOS:
} else if (flags & RAM_SAVE_FLAG_HOOK) {
ram_control_load_hook(f, flags);
} else if (flags & RAM_SAVE_FLAG_EOS) {
/* normal exit */
break;
default:
if (flags & RAM_SAVE_FLAG_HOOK) {
ram_control_load_hook(f, flags);
} else {
error_report("Unknown combination of migration flags: %#x",
flags);
ret = -EINVAL;
}
}
if (!ret) {
ret = qemu_file_get_error(f);
} else {
error_report("Unknown migration flags: %#x", flags);
ret = -EINVAL;
break;
}
ret = qemu_file_get_error(f);
}
DPRINTF("Completed load of VM with exit code %d seq iteration "
@@ -1152,7 +1101,7 @@ static int ram_load(QEMUFile *f, void *opaque, int version_id)
return ret;
}
static SaveVMHandlers savevm_ram_handlers = {
SaveVMHandlers savevm_ram_handlers = {
.save_live_setup = ram_save_setup,
.save_live_iterate = ram_save_iterate,
.save_live_complete = ram_save_complete,
@@ -1161,12 +1110,6 @@ static SaveVMHandlers savevm_ram_handlers = {
.cancel = ram_migration_cancel,
};
void ram_mig_init(void)
{
qemu_mutex_init(&XBZRLE.lock);
register_savevm_live(NULL, "ram", 0, 4, &savevm_ram_handlers, NULL);
}
struct soundhw {
const char *name;
const char *descr;
@@ -1249,11 +1192,12 @@ void select_soundhw(const char *optarg)
if (!c->name) {
if (l > 80) {
error_report("Unknown sound card name (too big to show)");
fprintf(stderr,
"Unknown sound card name (too big to show)\n");
}
else {
error_report("Unknown sound card name `%.*s'",
(int) l, p);
fprintf(stderr, "Unknown sound card name `%.*s'\n",
(int) l, p);
}
bad_card = 1;
}
@@ -1276,13 +1220,13 @@ void audio_init(void)
if (c->enabled) {
if (c->isa) {
if (!isa_bus) {
error_report("ISA bus not available for %s", c->name);
fprintf(stderr, "ISA bus not available for %s\n", c->name);
exit(1);
}
c->init.init_isa(isa_bus);
} else {
if (!pci_bus) {
error_report("PCI bus not available for %s", c->name);
fprintf(stderr, "PCI bus not available for %s\n", c->name);
exit(1);
}
c->init.init_pci(pci_bus);
@@ -1339,6 +1283,11 @@ void cpudef_init(void)
#endif
}
int tcg_available(void)
{
return 1;
}
int kvm_available(void)
{
#ifdef CONFIG_KVM

74
async.c
View File

@@ -26,7 +26,6 @@
#include "block/aio.h"
#include "block/thread-pool.h"
#include "qemu/main-loop.h"
#include "qemu/atomic.h"
/***********************************************************/
/* bottom halves (can be seen as timers which expire ASAP) */
@@ -152,48 +151,39 @@ void qemu_bh_delete(QEMUBH *bh)
bh->deleted = 1;
}
int64_t
aio_compute_timeout(AioContext *ctx)
static gboolean
aio_ctx_prepare(GSource *source, gint *timeout)
{
int64_t deadline;
int timeout = -1;
AioContext *ctx = (AioContext *) source;
QEMUBH *bh;
int deadline;
/* We assume there is no timeout already supplied */
*timeout = -1;
for (bh = ctx->first_bh; bh; bh = bh->next) {
if (!bh->deleted && bh->scheduled) {
if (bh->idle) {
/* idle bottom halves will be polled at least
* every 10ms */
timeout = 10000000;
*timeout = 10;
} else {
/* non-idle bottom halves will be executed
* immediately */
return 0;
*timeout = 0;
return true;
}
}
}
deadline = timerlistgroup_deadline_ns(&ctx->tlg);
deadline = qemu_timeout_ns_to_ms(timerlistgroup_deadline_ns(&ctx->tlg));
if (deadline == 0) {
return 0;
} else {
return qemu_soonest_timeout(timeout, deadline);
}
}
static gboolean
aio_ctx_prepare(GSource *source, gint *timeout)
{
AioContext *ctx = (AioContext *) source;
/* We assume there is no timeout already supplied */
*timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
if (aio_prepare(ctx)) {
*timeout = 0;
return true;
} else {
*timeout = qemu_soonest_timeout(*timeout, deadline);
}
return *timeout == 0;
return false;
}
static gboolean
@@ -218,7 +208,7 @@ aio_ctx_dispatch(GSource *source,
AioContext *ctx = (AioContext *) source;
assert(callback == NULL);
aio_dispatch(ctx);
aio_poll(ctx, false);
return true;
}
@@ -257,25 +247,9 @@ ThreadPool *aio_get_thread_pool(AioContext *ctx)
return ctx->thread_pool;
}
void aio_set_dispatching(AioContext *ctx, bool dispatching)
{
ctx->dispatching = dispatching;
if (!dispatching) {
/* Write ctx->dispatching before reading e.g. bh->scheduled.
* Optimization: this is only needed when we're entering the "unsafe"
* phase where other threads must call event_notifier_set.
*/
smp_mb();
}
}
void aio_notify(AioContext *ctx)
{
/* Write e.g. bh->scheduled before reading ctx->dispatching. */
smp_mb();
if (!ctx->dispatching) {
event_notifier_set(&ctx->notifier);
}
event_notifier_set(&ctx->notifier);
}
static void aio_timerlist_notify(void *opaque)
@@ -289,24 +263,18 @@ static void aio_rfifolock_cb(void *opaque)
aio_notify(opaque);
}
AioContext *aio_context_new(Error **errp)
AioContext *aio_context_new(void)
{
int ret;
AioContext *ctx;
ctx = (AioContext *) g_source_new(&aio_source_funcs, sizeof(AioContext));
ret = event_notifier_init(&ctx->notifier, false);
if (ret < 0) {
g_source_destroy(&ctx->source);
error_setg_errno(errp, -ret, "Failed to initialize event notifier");
return NULL;
}
aio_set_event_notifier(ctx, &ctx->notifier,
(EventNotifierHandler *)
event_notifier_test_and_clear);
ctx->pollfds = g_array_new(FALSE, FALSE, sizeof(GPollFD));
ctx->thread_pool = NULL;
qemu_mutex_init(&ctx->bh_lock);
rfifolock_init(&ctx->lock, aio_rfifolock_cb, ctx);
event_notifier_init(&ctx->notifier, false);
aio_set_event_notifier(ctx, &ctx->notifier,
(EventNotifierHandler *)
event_notifier_test_and_clear);
timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
return ctx;

View File

@@ -14,4 +14,4 @@ common-obj-$(CONFIG_AUDIO_WIN_INT) += audio_win_int.o
common-obj-y += wavcapture.o
$(obj)/audio.o $(obj)/fmodaudio.o: QEMU_CFLAGS += $(FMOD_CFLAGS)
sdlaudio.o-cflags := $(SDL_CFLAGS)
$(obj)/sdlaudio.o: QEMU_CFLAGS += $(SDL_CFLAGS)

View File

@@ -815,8 +815,10 @@ static void alsa_fini_out (HWVoiceOut *hw)
ldebug ("alsa_fini\n");
alsa_anal_close (&alsa->handle, &alsa->pollhlp);
g_free(alsa->pcm_buf);
alsa->pcm_buf = NULL;
if (alsa->pcm_buf) {
g_free (alsa->pcm_buf);
alsa->pcm_buf = NULL;
}
}
static int alsa_init_out (HWVoiceOut *hw, struct audsettings *as)
@@ -976,8 +978,10 @@ static void alsa_fini_in (HWVoiceIn *hw)
alsa_anal_close (&alsa->handle, &alsa->pollhlp);
g_free(alsa->pcm_buf);
alsa->pcm_buf = NULL;
if (alsa->pcm_buf) {
g_free (alsa->pcm_buf);
alsa->pcm_buf = NULL;
}
}
static int alsa_run_in (HWVoiceIn *hw)

View File

@@ -1812,7 +1812,8 @@ static const VMStateDescription vmstate_audio = {
.name = "audio",
.version_id = 1,
.minimum_version_id = 1,
.fields = (VMStateField[]) {
.minimum_version_id_old = 1,
.fields = (VMStateField []) {
VMSTATE_END_OF_LIST()
}
};

View File

@@ -71,7 +71,10 @@ static void glue (audio_init_nb_voices_, TYPE) (struct audio_driver *drv)
static void glue (audio_pcm_hw_free_resources_, TYPE) (HW *hw)
{
g_free (HWBUF);
if (HWBUF) {
g_free (HWBUF);
}
HWBUF = NULL;
}
@@ -89,7 +92,9 @@ static int glue (audio_pcm_hw_alloc_resources_, TYPE) (HW *hw)
static void glue (audio_pcm_sw_free_resources_, TYPE) (SW *sw)
{
g_free (sw->buf);
if (sw->buf) {
g_free (sw->buf);
}
if (sw->rate) {
st_rate_stop (sw->rate);
@@ -167,8 +172,10 @@ static int glue (audio_pcm_sw_init_, TYPE) (
static void glue (audio_pcm_sw_fini_, TYPE) (SW *sw)
{
glue (audio_pcm_sw_free_resources_, TYPE) (sw);
g_free (sw->name);
sw->name = NULL;
if (sw->name) {
g_free (sw->name);
sw->name = NULL;
}
}
static void glue (audio_pcm_hw_add_sw_, TYPE) (HW *hw, SW *sw)

View File

@@ -736,8 +736,10 @@ static void oss_fini_in (HWVoiceIn *hw)
oss_anal_close (&oss->fd);
g_free(oss->pcm_buf);
oss->pcm_buf = NULL;
if (oss->pcm_buf) {
g_free (oss->pcm_buf);
oss->pcm_buf = NULL;
}
}
static int oss_run_in (HWVoiceIn *hw)

View File

@@ -105,7 +105,7 @@ static int rate_get_samples (struct audio_pcm_info *info, SpiceRateCtl *rate)
bytes = muldiv64 (ticks, info->bytes_per_second, get_ticks_per_sec ());
samples = (bytes - rate->bytes_sent) >> info->shift;
if (samples < 0 || samples > 65536) {
error_report("Resetting rate control (%" PRId64 " samples)", samples);
fprintf (stderr, "Resetting rate control (%" PRId64 " samples)\n", samples);
rate_start (rate);
samples = 0;
}

View File

@@ -63,7 +63,8 @@ static void wav_destroy (void *opaque)
}
doclose:
if (fclose (wav->f)) {
error_report("wav_destroy: fclose failed: %s", strerror(errno));
fprintf (stderr, "wav_destroy: fclose failed: %s",
strerror (errno));
}
}

View File

@@ -1,11 +1,8 @@
common-obj-y += rng.o rng-egd.o
common-obj-$(CONFIG_POSIX) += rng-random.o
common-obj-y += msmouse.o testdev.o
common-obj-y += msmouse.o
common-obj-$(CONFIG_BRLAPI) += baum.o
baum.o-cflags := $(SDL_CFLAGS)
$(obj)/baum.o: QEMU_CFLAGS += $(SDL_CFLAGS)
common-obj-$(CONFIG_TPM) += tpm.o
common-obj-y += hostmem.o hostmem-ram.o
common-obj-$(CONFIG_LINUX) += hostmem-file.o

View File

@@ -574,7 +574,7 @@ CharDriverState *chr_baum_init(void)
int tty;
baum = g_malloc0(sizeof(BaumDriverState));
baum->chr = chr = qemu_chr_alloc();
baum->chr = chr = g_malloc0(sizeof(CharDriverState));
chr->opaque = baum;
chr->chr_write = baum_write;
@@ -629,7 +629,7 @@ fail_handle:
static void register_types(void)
{
register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL);
register_char_driver_qapi("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL);
}
type_init(register_types);

View File

@@ -1,134 +0,0 @@
/*
* QEMU Host Memory Backend for hugetlbfs
*
* Copyright (C) 2013-2014 Red Hat Inc
*
* Authors:
* Paolo Bonzini <pbonzini@redhat.com>
*
* 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-common.h"
#include "sysemu/hostmem.h"
#include "sysemu/sysemu.h"
#include "qom/object_interfaces.h"
/* hostmem-file.c */
/**
* @TYPE_MEMORY_BACKEND_FILE:
* name of backend that uses mmap on a file descriptor
*/
#define TYPE_MEMORY_BACKEND_FILE "memory-backend-file"
#define MEMORY_BACKEND_FILE(obj) \
OBJECT_CHECK(HostMemoryBackendFile, (obj), TYPE_MEMORY_BACKEND_FILE)
typedef struct HostMemoryBackendFile HostMemoryBackendFile;
struct HostMemoryBackendFile {
HostMemoryBackend parent_obj;
bool share;
char *mem_path;
};
static void
file_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
{
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(backend);
if (!backend->size) {
error_setg(errp, "can't create backend with size 0");
return;
}
if (!fb->mem_path) {
error_setg(errp, "mem_path property not set");
return;
}
#ifndef CONFIG_LINUX
error_setg(errp, "-mem-path not supported on this host");
#else
if (!memory_region_size(&backend->mr)) {
backend->force_prealloc = mem_prealloc;
memory_region_init_ram_from_file(&backend->mr, OBJECT(backend),
object_get_canonical_path(OBJECT(backend)),
backend->size, fb->share,
fb->mem_path, errp);
}
#endif
}
static void
file_backend_class_init(ObjectClass *oc, void *data)
{
HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
bc->alloc = file_backend_memory_alloc;
}
static char *get_mem_path(Object *o, Error **errp)
{
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
return g_strdup(fb->mem_path);
}
static void set_mem_path(Object *o, const char *str, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
if (memory_region_size(&backend->mr)) {
error_setg(errp, "cannot change property value");
return;
}
if (fb->mem_path) {
g_free(fb->mem_path);
}
fb->mem_path = g_strdup(str);
}
static bool file_memory_backend_get_share(Object *o, Error **errp)
{
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
return fb->share;
}
static void file_memory_backend_set_share(Object *o, bool value, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
HostMemoryBackendFile *fb = MEMORY_BACKEND_FILE(o);
if (memory_region_size(&backend->mr)) {
error_setg(errp, "cannot change property value");
return;
}
fb->share = value;
}
static void
file_backend_instance_init(Object *o)
{
object_property_add_bool(o, "share",
file_memory_backend_get_share,
file_memory_backend_set_share, NULL);
object_property_add_str(o, "mem-path", get_mem_path,
set_mem_path, NULL);
}
static const TypeInfo file_backend_info = {
.name = TYPE_MEMORY_BACKEND_FILE,
.parent = TYPE_MEMORY_BACKEND,
.class_init = file_backend_class_init,
.instance_init = file_backend_instance_init,
.instance_size = sizeof(HostMemoryBackendFile),
};
static void register_types(void)
{
type_register_static(&file_backend_info);
}
type_init(register_types);

View File

@@ -1,53 +0,0 @@
/*
* QEMU Host Memory Backend
*
* Copyright (C) 2013-2014 Red Hat Inc
*
* Authors:
* Igor Mammedov <imammedo@redhat.com>
*
* 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 "sysemu/hostmem.h"
#include "qom/object_interfaces.h"
#define TYPE_MEMORY_BACKEND_RAM "memory-backend-ram"
static void
ram_backend_memory_alloc(HostMemoryBackend *backend, Error **errp)
{
char *path;
if (!backend->size) {
error_setg(errp, "can't create backend with size 0");
return;
}
path = object_get_canonical_path_component(OBJECT(backend));
memory_region_init_ram(&backend->mr, OBJECT(backend), path,
backend->size, errp);
g_free(path);
}
static void
ram_backend_class_init(ObjectClass *oc, void *data)
{
HostMemoryBackendClass *bc = MEMORY_BACKEND_CLASS(oc);
bc->alloc = ram_backend_memory_alloc;
}
static const TypeInfo ram_backend_info = {
.name = TYPE_MEMORY_BACKEND_RAM,
.parent = TYPE_MEMORY_BACKEND,
.class_init = ram_backend_class_init,
};
static void register_types(void)
{
type_register_static(&ram_backend_info);
}
type_init(register_types);

View File

@@ -1,365 +0,0 @@
/*
* QEMU Host Memory Backend
*
* Copyright (C) 2013-2014 Red Hat Inc
*
* Authors:
* Igor Mammedov <imammedo@redhat.com>
*
* 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 "sysemu/hostmem.h"
#include "qapi/visitor.h"
#include "qapi-types.h"
#include "qapi-visit.h"
#include "qapi/qmp/qerror.h"
#include "qemu/config-file.h"
#include "qom/object_interfaces.h"
#ifdef CONFIG_NUMA
#include <numaif.h>
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_DEFAULT != MPOL_DEFAULT);
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_PREFERRED != MPOL_PREFERRED);
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_BIND != MPOL_BIND);
QEMU_BUILD_BUG_ON(HOST_MEM_POLICY_INTERLEAVE != MPOL_INTERLEAVE);
#endif
static void
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, &value, name, errp);
}
static void
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;
uint64_t value;
if (memory_region_size(&backend->mr)) {
error_setg(&local_err, "cannot change property value");
goto out;
}
visit_type_size(v, &value, name, &local_err);
if (local_err) {
goto out;
}
if (!value) {
error_setg(&local_err, "Property '%s.%s' doesn't take value '%"
PRIu64 "'", object_get_typename(obj), name, value);
goto out;
}
backend->size = value;
out:
error_propagate(errp, local_err);
}
static void
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;
uint16List **node = &host_nodes;
unsigned long value;
value = find_first_bit(backend->host_nodes, MAX_NODES);
if (value == MAX_NODES) {
return;
}
*node = g_malloc0(sizeof(**node));
(*node)->value = value;
node = &(*node)->next;
do {
value = find_next_bit(backend->host_nodes, MAX_NODES, value + 1);
if (value == MAX_NODES) {
break;
}
*node = g_malloc0(sizeof(**node));
(*node)->value = value;
node = &(*node)->next;
} while (true);
visit_type_uint16List(v, &host_nodes, name, errp);
}
static void
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, &l, name, errp);
while (l) {
bitmap_set(backend->host_nodes, l->value, 1);
l = l->next;
}
#else
error_setg(errp, "NUMA node binding are not supported by this QEMU");
#endif
}
static void
host_memory_backend_get_policy(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
int policy = backend->policy;
visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
}
static void
host_memory_backend_set_policy(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
int policy;
visit_type_enum(v, &policy, HostMemPolicy_lookup, NULL, name, errp);
backend->policy = policy;
#ifndef CONFIG_NUMA
if (policy != HOST_MEM_POLICY_DEFAULT) {
error_setg(errp, "NUMA policies are not supported by this QEMU");
}
#endif
}
static bool host_memory_backend_get_merge(Object *obj, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->merge;
}
static void host_memory_backend_set_merge(Object *obj, bool value, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (!memory_region_size(&backend->mr)) {
backend->merge = value;
return;
}
if (value != backend->merge) {
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
qemu_madvise(ptr, sz,
value ? QEMU_MADV_MERGEABLE : QEMU_MADV_UNMERGEABLE);
backend->merge = value;
}
}
static bool host_memory_backend_get_dump(Object *obj, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->dump;
}
static void host_memory_backend_set_dump(Object *obj, bool value, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (!memory_region_size(&backend->mr)) {
backend->dump = value;
return;
}
if (value != backend->dump) {
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
qemu_madvise(ptr, sz,
value ? QEMU_MADV_DODUMP : QEMU_MADV_DONTDUMP);
backend->dump = value;
}
}
static bool host_memory_backend_get_prealloc(Object *obj, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
return backend->prealloc || backend->force_prealloc;
}
static void host_memory_backend_set_prealloc(Object *obj, bool value,
Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
if (backend->force_prealloc) {
if (value) {
error_setg(errp,
"remove -mem-prealloc to use the prealloc property");
return;
}
}
if (!memory_region_size(&backend->mr)) {
backend->prealloc = value;
return;
}
if (value && !backend->prealloc) {
int fd = memory_region_get_fd(&backend->mr);
void *ptr = memory_region_get_ram_ptr(&backend->mr);
uint64_t sz = memory_region_size(&backend->mr);
os_mem_prealloc(fd, ptr, sz);
backend->prealloc = true;
}
}
static void host_memory_backend_init(Object *obj)
{
HostMemoryBackend *backend = MEMORY_BACKEND(obj);
backend->merge = qemu_opt_get_bool(qemu_get_machine_opts(),
"mem-merge", true);
backend->dump = qemu_opt_get_bool(qemu_get_machine_opts(),
"dump-guest-core", true);
backend->prealloc = mem_prealloc;
object_property_add_bool(obj, "merge",
host_memory_backend_get_merge,
host_memory_backend_set_merge, NULL);
object_property_add_bool(obj, "dump",
host_memory_backend_get_dump,
host_memory_backend_set_dump, NULL);
object_property_add_bool(obj, "prealloc",
host_memory_backend_get_prealloc,
host_memory_backend_set_prealloc, NULL);
object_property_add(obj, "size", "int",
host_memory_backend_get_size,
host_memory_backend_set_size, NULL, NULL, NULL);
object_property_add(obj, "host-nodes", "int",
host_memory_backend_get_host_nodes,
host_memory_backend_set_host_nodes, NULL, NULL, NULL);
object_property_add(obj, "policy", "str",
host_memory_backend_get_policy,
host_memory_backend_set_policy, NULL, NULL, NULL);
}
MemoryRegion *
host_memory_backend_get_memory(HostMemoryBackend *backend, Error **errp)
{
return memory_region_size(&backend->mr) ? &backend->mr : NULL;
}
static void
host_memory_backend_memory_complete(UserCreatable *uc, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(uc);
HostMemoryBackendClass *bc = MEMORY_BACKEND_GET_CLASS(uc);
Error *local_err = NULL;
void *ptr;
uint64_t sz;
if (bc->alloc) {
bc->alloc(backend, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
ptr = memory_region_get_ram_ptr(&backend->mr);
sz = memory_region_size(&backend->mr);
if (backend->merge) {
qemu_madvise(ptr, sz, QEMU_MADV_MERGEABLE);
}
if (!backend->dump) {
qemu_madvise(ptr, sz, QEMU_MADV_DONTDUMP);
}
#ifdef CONFIG_NUMA
unsigned long lastbit = find_last_bit(backend->host_nodes, MAX_NODES);
/* lastbit == MAX_NODES means maxnode = 0 */
unsigned long maxnode = (lastbit + 1) % (MAX_NODES + 1);
/* ensure policy won't be ignored in case memory is preallocated
* before mbind(). note: MPOL_MF_STRICT is ignored on hugepages so
* this doesn't catch hugepage case. */
unsigned flags = MPOL_MF_STRICT | MPOL_MF_MOVE;
/* check for invalid host-nodes and policies and give more verbose
* error messages than mbind(). */
if (maxnode && backend->policy == MPOL_DEFAULT) {
error_setg(errp, "host-nodes must be empty for policy default,"
" or you should explicitly specify a policy other"
" than default");
return;
} else if (maxnode == 0 && backend->policy != MPOL_DEFAULT) {
error_setg(errp, "host-nodes must be set for policy %s",
HostMemPolicy_lookup[backend->policy]);
return;
}
/* We can have up to MAX_NODES nodes, but we need to pass maxnode+1
* as argument to mbind() due to an old Linux bug (feature?) which
* cuts off the last specified node. This means backend->host_nodes
* must have MAX_NODES+1 bits available.
*/
assert(sizeof(backend->host_nodes) >=
BITS_TO_LONGS(MAX_NODES + 1) * sizeof(unsigned long));
assert(maxnode <= MAX_NODES);
if (mbind(ptr, sz, backend->policy,
maxnode ? backend->host_nodes : NULL, maxnode + 1, flags)) {
error_setg_errno(errp, errno,
"cannot bind memory to host NUMA nodes");
return;
}
#endif
/* Preallocate memory after the NUMA policy has been instantiated.
* This is necessary to guarantee memory is allocated with
* specified NUMA policy in place.
*/
if (backend->prealloc) {
os_mem_prealloc(memory_region_get_fd(&backend->mr), ptr, sz);
}
}
}
static void
host_memory_backend_class_init(ObjectClass *oc, void *data)
{
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
ucc->complete = host_memory_backend_memory_complete;
}
static const TypeInfo host_memory_backend_info = {
.name = TYPE_MEMORY_BACKEND,
.parent = TYPE_OBJECT,
.abstract = true,
.class_size = sizeof(HostMemoryBackendClass),
.class_init = host_memory_backend_class_init,
.instance_size = sizeof(HostMemoryBackend),
.instance_init = host_memory_backend_init,
.interfaces = (InterfaceInfo[]) {
{ TYPE_USER_CREATABLE },
{ }
}
};
static void register_types(void)
{
type_register_static(&host_memory_backend_info);
}
type_init(register_types);

View File

@@ -67,7 +67,7 @@ CharDriverState *qemu_chr_open_msmouse(void)
{
CharDriverState *chr;
chr = qemu_chr_alloc();
chr = g_malloc0(sizeof(CharDriverState));
chr->chr_write = msmouse_chr_write;
chr->chr_close = msmouse_chr_close;
chr->explicit_be_open = true;
@@ -79,7 +79,7 @@ CharDriverState *qemu_chr_open_msmouse(void)
static void register_types(void)
{
register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL);
register_char_driver_qapi("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL);
}
type_init(register_types);

View File

@@ -169,7 +169,6 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
if (b->opened) {
error_set(errp, QERR_PERMISSION_DENIED);
} else {
g_free(s->chr_name);
s->chr_name = g_strdup(value);
}
}

View File

@@ -106,7 +106,10 @@ static void rng_random_set_filename(Object *obj, const char *filename,
return;
}
g_free(s->filename);
if (s->filename) {
g_free(s->filename);
}
s->filename = g_strdup(filename);
}

View File

@@ -50,7 +50,6 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
{
RngBackend *s = RNG_BACKEND(obj);
RngBackendClass *k = RNG_BACKEND_GET_CLASS(s);
Error *local_err = NULL;
if (value == s->opened) {
return;
@@ -62,14 +61,12 @@ static void rng_backend_prop_set_opened(Object *obj, bool value, Error **errp)
}
if (k->opened) {
k->opened(s, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
k->opened(s, errp);
}
s->opened = true;
if (!error_is_set(errp)) {
s->opened = value;
}
}
static void rng_backend_init(Object *obj)

View File

@@ -1,131 +0,0 @@
/*
* QEMU Char Device for testsuite control
*
* Copyright (c) 2014 Red Hat, Inc.
*
* Author: Paolo Bonzini <pbonzini@redhat.com>
*
* 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-common.h"
#include "sysemu/char.h"
#define BUF_SIZE 32
typedef struct {
CharDriverState *chr;
uint8_t in_buf[32];
int in_buf_used;
} TestdevCharState;
/* Try to interpret a whole incoming packet */
static int testdev_eat_packet(TestdevCharState *testdev)
{
const uint8_t *cur = testdev->in_buf;
int len = testdev->in_buf_used;
uint8_t c;
int arg;
#define EAT(c) do { \
if (!len--) { \
return 0; \
} \
c = *cur++; \
} while (0)
EAT(c);
while (isspace(c)) {
EAT(c);
}
arg = 0;
while (isdigit(c)) {
arg = arg * 10 + c - '0';
EAT(c);
}
while (isspace(c)) {
EAT(c);
}
switch (c) {
case 'q':
exit((arg << 1) | 1);
break;
default:
break;
}
return cur - testdev->in_buf;
}
/* The other end is writing some data. Store it and try to interpret */
static int testdev_write(CharDriverState *chr, const uint8_t *buf, int len)
{
TestdevCharState *testdev = chr->opaque;
int tocopy, eaten, orig_len = len;
while (len) {
/* Complete our buffer as much as possible */
tocopy = MIN(len, BUF_SIZE - testdev->in_buf_used);
memcpy(testdev->in_buf + testdev->in_buf_used, buf, tocopy);
testdev->in_buf_used += tocopy;
buf += tocopy;
len -= tocopy;
/* Interpret it as much as possible */
while (testdev->in_buf_used > 0 &&
(eaten = testdev_eat_packet(testdev)) > 0) {
memmove(testdev->in_buf, testdev->in_buf + eaten,
testdev->in_buf_used - eaten);
testdev->in_buf_used -= eaten;
}
}
return orig_len;
}
static void testdev_close(struct CharDriverState *chr)
{
TestdevCharState *testdev = chr->opaque;
g_free(testdev);
}
CharDriverState *chr_testdev_init(void)
{
TestdevCharState *testdev;
CharDriverState *chr;
testdev = g_malloc0(sizeof(TestdevCharState));
testdev->chr = chr = g_malloc0(sizeof(CharDriverState));
chr->opaque = testdev;
chr->chr_write = testdev_write;
chr->chr_close = testdev_close;
return chr;
}
static void register_types(void)
{
register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL);
}
type_init(register_types);

View File

@@ -112,7 +112,6 @@ static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
{
TPMBackend *s = TPM_BACKEND(obj);
TPMBackendClass *k = TPM_BACKEND_GET_CLASS(s);
Error *local_err = NULL;
if (value == s->opened) {
return;
@@ -124,14 +123,12 @@ static void tpm_backend_prop_set_opened(Object *obj, bool value, Error **errp)
}
if (k->opened) {
k->opened(s, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return;
}
k->opened(s, errp);
}
s->opened = true;
if (!error_is_set(errp)) {
s->opened = value;
}
}
static void tpm_backend_instance_init(Object *obj)

View File

@@ -81,6 +81,19 @@ static int qemu_balloon_status(BalloonInfo *info)
return 1;
}
void qemu_balloon_changed(int64_t actual)
{
QObject *data;
data = qobject_from_jsonf("{ 'actual': %" PRId64 " }",
actual);
monitor_protocol_event(QEVENT_BALLOON_CHANGE, data);
qobject_decref(data);
}
BalloonInfo *qmp_query_balloon(Error **errp)
{
BalloonInfo *info;

View File

@@ -14,9 +14,7 @@
*/
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/error-report.h"
#include "qemu/main-loop.h"
#include "block/block_int.h"
#include "hw/hw.h"
#include "qemu/queue.h"
#include "qemu/timer.h"
@@ -61,7 +59,6 @@ typedef struct BlkMigDevState {
unsigned long *aio_bitmap;
int64_t completed_sectors;
BdrvDirtyBitmap *dirty_bitmap;
Error *blocker;
} BlkMigDevState;
typedef struct BlkMigBlock {
@@ -72,7 +69,7 @@ typedef struct BlkMigBlock {
int nr_sectors;
struct iovec iov;
QEMUIOVector qiov;
BlockAIOCB *aiocb;
BlockDriverAIOCB *aiocb;
/* Protected by block migration lock. */
int ret;
@@ -132,9 +129,9 @@ static void blk_send(QEMUFile *f, BlkMigBlock * blk)
| flags);
/* device name */
len = strlen(bdrv_get_device_name(blk->bmds->bs));
len = strlen(blk->bmds->bs->device_name);
qemu_put_byte(f, len);
qemu_put_buffer(f, (uint8_t *)bdrv_get_device_name(blk->bmds->bs), len);
qemu_put_buffer(f, (uint8_t *)blk->bmds->bs->device_name, len);
/* if a block is zero we need to flush here since the network
* bandwidth is now a lot higher than the storage device bandwidth.
@@ -188,7 +185,7 @@ static int bmds_aio_inflight(BlkMigDevState *bmds, int64_t sector)
{
int64_t chunk = sector / (int64_t)BDRV_SECTORS_PER_DIRTY_CHUNK;
if (sector < bdrv_nb_sectors(bmds->bs)) {
if ((sector << BDRV_SECTOR_BITS) < bdrv_getlength(bmds->bs)) {
return !!(bmds->aio_bitmap[chunk / (sizeof(unsigned long) * 8)] &
(1UL << (chunk % (sizeof(unsigned long) * 8))));
} else {
@@ -225,7 +222,8 @@ static void alloc_aio_bitmap(BlkMigDevState *bmds)
BlockDriverState *bs = bmds->bs;
int64_t bitmap_size;
bitmap_size = bdrv_nb_sectors(bs) + BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
bitmap_size = (bdrv_getlength(bs) >> BDRV_SECTOR_BITS) +
BDRV_SECTORS_PER_DIRTY_CHUNK * 8 - 1;
bitmap_size /= BDRV_SECTORS_PER_DIRTY_CHUNK * 8;
bmds->aio_bitmap = g_malloc0(bitmap_size);
@@ -285,7 +283,7 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
nr_sectors = total_sectors - cur_sector;
}
blk = g_new(BlkMigBlock, 1);
blk = g_malloc(sizeof(BlkMigBlock));
blk->buf = g_malloc(BLOCK_SIZE);
blk->bmds = bmds;
blk->sector = cur_sector;
@@ -312,28 +310,13 @@ static int mig_save_device_bulk(QEMUFile *f, BlkMigDevState *bmds)
/* Called with iothread lock taken. */
static int set_dirty_tracking(void)
static void set_dirty_tracking(void)
{
BlkMigDevState *bmds;
int ret;
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE,
NULL);
if (!bmds->dirty_bitmap) {
ret = -errno;
goto fail;
}
bmds->dirty_bitmap = bdrv_create_dirty_bitmap(bmds->bs, BLOCK_SIZE);
}
return 0;
fail:
QSIMPLEQ_FOREACH(bmds, &block_mig_state.bmds_list, entry) {
if (bmds->dirty_bitmap) {
bdrv_release_dirty_bitmap(bmds->bs, bmds->dirty_bitmap);
}
}
return ret;
}
static void unset_dirty_tracking(void)
@@ -345,12 +328,42 @@ static void unset_dirty_tracking(void)
}
}
static void init_blk_migration(QEMUFile *f)
static void init_blk_migration_it(void *opaque, BlockDriverState *bs)
{
BlockDriverState *bs;
BlkMigDevState *bmds;
int64_t sectors;
if (!bdrv_is_read_only(bs)) {
sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
if (sectors <= 0) {
return;
}
bmds = g_malloc0(sizeof(BlkMigDevState));
bmds->bs = bs;
bmds->bulk_completed = 0;
bmds->total_sectors = sectors;
bmds->completed_sectors = 0;
bmds->shared_base = block_mig_state.shared_base;
alloc_aio_bitmap(bmds);
bdrv_set_in_use(bs, 1);
bdrv_ref(bs);
block_mig_state.total_sector_sum += sectors;
if (bmds->shared_base) {
DPRINTF("Start migration for %s with shared base image\n",
bs->device_name);
} else {
DPRINTF("Start full migration for %s\n", bs->device_name);
}
QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
}
}
static void init_blk_migration(QEMUFile *f)
{
block_mig_state.submitted = 0;
block_mig_state.read_done = 0;
block_mig_state.transferred = 0;
@@ -359,38 +372,7 @@ static void init_blk_migration(QEMUFile *f)
block_mig_state.bulk_completed = 0;
block_mig_state.zero_blocks = migrate_zero_blocks();
for (bs = bdrv_next(NULL); bs; bs = bdrv_next(bs)) {
if (bdrv_is_read_only(bs)) {
continue;
}
sectors = bdrv_nb_sectors(bs);
if (sectors <= 0) {
return;
}
bmds = g_new0(BlkMigDevState, 1);
bmds->bs = bs;
bmds->bulk_completed = 0;
bmds->total_sectors = sectors;
bmds->completed_sectors = 0;
bmds->shared_base = block_mig_state.shared_base;
alloc_aio_bitmap(bmds);
error_setg(&bmds->blocker, "block device is in use by migration");
bdrv_op_block_all(bs, bmds->blocker);
bdrv_ref(bs);
block_mig_state.total_sector_sum += sectors;
if (bmds->shared_base) {
DPRINTF("Start migration for %s with shared base image\n",
bdrv_get_device_name(bs));
} else {
DPRINTF("Start full migration for %s\n", bdrv_get_device_name(bs));
}
QSIMPLEQ_INSERT_TAIL(&block_mig_state.bmds_list, bmds, entry);
}
bdrv_iterate(init_blk_migration_it, NULL);
}
/* Called with no lock taken. */
@@ -467,7 +449,7 @@ static int mig_save_device_dirty(QEMUFile *f, BlkMigDevState *bmds,
} else {
nr_sectors = BDRV_SECTORS_PER_DIRTY_CHUNK;
}
blk = g_new(BlkMigBlock, 1);
blk = g_malloc(sizeof(BlkMigBlock));
blk->buf = g_malloc(BLOCK_SIZE);
blk->bmds = bmds;
blk->sector = sector;
@@ -602,8 +584,7 @@ static void blk_mig_cleanup(void)
blk_mig_lock();
while ((bmds = QSIMPLEQ_FIRST(&block_mig_state.bmds_list)) != NULL) {
QSIMPLEQ_REMOVE_HEAD(&block_mig_state.bmds_list, entry);
bdrv_op_unblock_all(bmds->bs, bmds->blocker);
error_free(bmds->blocker);
bdrv_set_in_use(bmds->bs, 0);
bdrv_unref(bmds->bs);
g_free(bmds->aio_bitmap);
g_free(bmds);
@@ -633,13 +614,7 @@ static int block_save_setup(QEMUFile *f, void *opaque)
init_blk_migration(f);
/* start track dirty blocks */
ret = set_dirty_tracking();
if (ret) {
qemu_mutex_unlock_iothread();
return ret;
}
set_dirty_tracking();
qemu_mutex_unlock_iothread();
ret = flush_blks(f);
@@ -800,7 +775,7 @@ static int block_load(QEMUFile *f, void *opaque, int version_id)
if (bs != bs_prev) {
bs_prev = bs;
total_sectors = bdrv_nb_sectors(bs);
total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
if (total_sectors <= 0) {
error_report("Error getting length of block device %s",
device_name);
@@ -862,7 +837,7 @@ static bool block_is_active(void *opaque)
return block_mig_state.blk_enable == 1;
}
static SaveVMHandlers savevm_block_handlers = {
SaveVMHandlers savevm_block_handlers = {
.set_params = block_set_params,
.save_live_setup = block_save_setup,
.save_live_iterate = block_save_iterate,

1962
block.c

File diff suppressed because it is too large Load Diff

View File

@@ -1,28 +1,28 @@
block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
block-obj-y += raw_bsd.o cow.o qcow.o vdi.o vmdk.o cloop.o dmg.o bochs.o vpc.o vvfat.o
block-obj-y += qcow2.o qcow2-refcount.o qcow2-cluster.o qcow2-snapshot.o qcow2-cache.o
block-obj-y += qed.o qed-gencb.o qed-l2-cache.o qed-table.o qed-cluster.o
block-obj-y += qed-check.o
block-obj-$(CONFIG_VHDX) += vhdx.o vhdx-endian.o vhdx-log.o
block-obj-$(CONFIG_QUORUM) += quorum.o
block-obj-y += parallels.o blkdebug.o blkverify.o
block-obj-y += block-backend.o snapshot.o qapi.o
block-obj-y += snapshot.o qapi.o
block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
block-obj-$(CONFIG_POSIX) += raw-posix.o
block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
block-obj-y += null.o mirror.o
ifeq ($(CONFIG_POSIX),y)
block-obj-y += nbd.o nbd-client.o sheepdog.o
block-obj-$(CONFIG_LIBISCSI) += iscsi.o
block-obj-$(CONFIG_LIBNFS) += nfs.o
block-obj-$(CONFIG_CURL) += curl.o
block-obj-$(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
endif
common-obj-y += stream.o
common-obj-y += commit.o
common-obj-y += mirror.o
common-obj-y += backup.o
iscsi.o-cflags := $(LIBISCSI_CFLAGS)
@@ -35,6 +35,5 @@ gluster.o-cflags := $(GLUSTERFS_CFLAGS)
gluster.o-libs := $(GLUSTERFS_LIBS)
ssh.o-cflags := $(LIBSSH2_CFLAGS)
ssh.o-libs := $(LIBSSH2_LIBS)
archipelago.o-libs := $(ARCHIPELAGO_LIBS)
qcow.o-libs := -lz
linux-aio.o-libs := -laio

View File

@@ -1,54 +0,0 @@
/*
* QEMU System Emulator block accounting
*
* Copyright (c) 2011 Christoph Hellwig
*
* 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 "block/accounting.h"
#include "block/block_int.h"
void block_acct_start(BlockAcctStats *stats, BlockAcctCookie *cookie,
int64_t bytes, enum BlockAcctType type)
{
assert(type < BLOCK_MAX_IOTYPE);
cookie->bytes = bytes;
cookie->start_time_ns = get_clock();
cookie->type = type;
}
void block_acct_done(BlockAcctStats *stats, BlockAcctCookie *cookie)
{
assert(cookie->type < BLOCK_MAX_IOTYPE);
stats->nr_bytes[cookie->type] += cookie->bytes;
stats->nr_ops[cookie->type]++;
stats->total_time_ns[cookie->type] += get_clock() - cookie->start_time_ns;
}
void block_acct_highest_sector(BlockAcctStats *stats, int64_t sector_num,
unsigned int nb_sectors)
{
if (stats->wr_highest_sector < sector_num + nb_sectors - 1) {
stats->wr_highest_sector = sector_num + nb_sectors - 1;
}
}

File diff suppressed because it is too large Load Diff

View File

@@ -227,25 +227,9 @@ static BlockErrorAction backup_error_action(BackupBlockJob *job,
}
}
typedef struct {
int ret;
} BackupCompleteData;
static void backup_complete(BlockJob *job, void *opaque)
{
BackupBlockJob *s = container_of(job, BackupBlockJob, common);
BackupCompleteData *data = opaque;
bdrv_unref(s->target);
block_job_completed(job, data->ret);
g_free(data);
}
static void coroutine_fn backup_run(void *opaque)
{
BackupBlockJob *job = opaque;
BackupCompleteData *data;
BlockDriverState *bs = job->common.bs;
BlockDriverState *target = job->target;
BlockdevOnError on_target_error = job->on_target_error;
@@ -323,7 +307,7 @@ static void coroutine_fn backup_run(void *opaque)
BACKUP_SECTORS_PER_CLUSTER - i, &n);
i += n;
if (alloced == 1 || n == 0) {
if (alloced == 1) {
break;
}
}
@@ -341,7 +325,7 @@ static void coroutine_fn backup_run(void *opaque)
/* Depending on error action, fail now or retry cluster */
BlockErrorAction action =
backup_error_action(job, error_is_read, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT) {
if (action == BDRV_ACTION_REPORT) {
break;
} else {
start--;
@@ -360,17 +344,16 @@ static void coroutine_fn backup_run(void *opaque)
hbitmap_free(job->bitmap);
bdrv_iostatus_disable(target);
bdrv_unref(target);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&job->common, backup_complete, data);
block_job_completed(&job->common, ret);
}
void backup_start(BlockDriverState *bs, BlockDriverState *target,
int64_t speed, MirrorSyncMode sync_mode,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockCompletionFunc *cb, void *opaque,
BlockDriverCompletionFunc *cb, void *opaque,
Error **errp)
{
int64_t len;

View File

@@ -26,10 +26,6 @@
#include "qemu/config-file.h"
#include "block/block_int.h"
#include "qemu/module.h"
#include "qapi/qmp/qbool.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qint.h"
#include "qapi/qmp/qstring.h"
typedef struct BDRVBlkdebugState {
int state;
@@ -41,7 +37,7 @@ typedef struct BDRVBlkdebugState {
} BDRVBlkdebugState;
typedef struct BlkdebugAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
QEMUBH *bh;
int ret;
} BlkdebugAIOCB;
@@ -52,8 +48,11 @@ typedef struct BlkdebugSuspendedReq {
QLIST_ENTRY(BlkdebugSuspendedReq) next;
} BlkdebugSuspendedReq;
static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb);
static const AIOCBInfo blkdebug_aiocb_info = {
.aiocb_size = sizeof(BlkdebugAIOCB),
.aiocb_size = sizeof(BlkdebugAIOCB),
.cancel = blkdebug_aio_cancel,
};
enum {
@@ -195,8 +194,6 @@ static const char *event_names[BLKDBG_EVENT_MAX] = {
[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)
@@ -216,7 +213,6 @@ static int get_event_by_name(const char *name, BlkDebugEvent *event)
struct add_rule_data {
BDRVBlkdebugState *s;
int action;
Error **errp;
};
static int add_rule(QemuOpts *opts, void *opaque)
@@ -229,11 +225,7 @@ static int add_rule(QemuOpts *opts, void *opaque)
/* Find the right event for the rule */
event_name = qemu_opt_get(opts, "event");
if (!event_name) {
error_setg(d->errp, "Missing event name for rule");
return -1;
} else if (get_event_by_name(event_name, &event) < 0) {
error_setg(d->errp, "Invalid event name \"%s\"", event_name);
if (!event_name || get_event_by_name(event_name, &event) < 0) {
return -1;
}
@@ -319,21 +311,10 @@ static int read_config(BDRVBlkdebugState *s, const char *filename,
d.s = s;
d.action = ACTION_INJECT_ERROR;
d.errp = &local_err;
qemu_opts_foreach(&inject_error_opts, add_rule, &d, 1);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
qemu_opts_foreach(&inject_error_opts, add_rule, &d, 0);
d.action = ACTION_SET_STATE;
qemu_opts_foreach(&set_state_opts, add_rule, &d, 1);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail;
}
qemu_opts_foreach(&set_state_opts, add_rule, &d, 0);
ret = 0;
fail:
@@ -462,11 +443,17 @@ static void error_callback_bh(void *opaque)
struct BlkdebugAIOCB *acb = opaque;
qemu_bh_delete(acb->bh);
acb->common.cb(acb->common.opaque, acb->ret);
qemu_aio_unref(acb);
qemu_aio_release(acb);
}
static BlockAIOCB *inject_error(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
static void blkdebug_aio_cancel(BlockDriverAIOCB *blockacb)
{
BlkdebugAIOCB *acb = container_of(blockacb, BlkdebugAIOCB, common);
qemu_aio_release(acb);
}
static BlockDriverAIOCB *inject_error(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
{
BDRVBlkdebugState *s = bs->opaque;
int error = rule->options.inject.error;
@@ -484,16 +471,16 @@ static BlockAIOCB *inject_error(BlockDriverState *bs,
acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
acb->ret = -error;
bh = aio_bh_new(bdrv_get_aio_context(bs), error_callback_bh, acb);
bh = qemu_bh_new(error_callback_bh, acb);
acb->bh = bh;
qemu_bh_schedule(bh);
return &acb->common;
}
static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
static BlockDriverAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugRule *rule = NULL;
@@ -513,9 +500,9 @@ static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
}
static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
static BlockDriverAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugRule *rule = NULL;
@@ -535,25 +522,6 @@ static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors, cb, opaque);
}
static BlockAIOCB *blkdebug_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugRule *rule = NULL;
QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
if (rule->options.inject.sector == -1) {
break;
}
}
if (rule && rule->options.inject.error) {
return inject_error(bs, cb, opaque, rule);
}
return bdrv_aio_flush(bs->file, cb, opaque);
}
static void blkdebug_close(BlockDriverState *bs)
{
@@ -719,98 +687,6 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
return bdrv_getlength(bs->file);
}
static void blkdebug_refresh_filename(BlockDriverState *bs)
{
BDRVBlkdebugState *s = bs->opaque;
struct BlkdebugRule *rule;
QDict *opts;
QList *inject_error_list = NULL, *set_state_list = NULL;
QList *suspend_list = NULL;
int event;
if (!bs->file->full_open_options) {
/* The config file cannot be recreated, so creating a plain filename
* is impossible */
return;
}
opts = qdict_new();
qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkdebug")));
QINCREF(bs->file->full_open_options);
qdict_put_obj(opts, "image", QOBJECT(bs->file->full_open_options));
for (event = 0; event < BLKDBG_EVENT_MAX; event++) {
QLIST_FOREACH(rule, &s->rules[event], next) {
if (rule->action == ACTION_INJECT_ERROR) {
QDict *inject_error = qdict_new();
qdict_put_obj(inject_error, "event", QOBJECT(qstring_from_str(
BlkdebugEvent_lookup[rule->event])));
qdict_put_obj(inject_error, "state",
QOBJECT(qint_from_int(rule->state)));
qdict_put_obj(inject_error, "errno", QOBJECT(qint_from_int(
rule->options.inject.error)));
qdict_put_obj(inject_error, "sector", QOBJECT(qint_from_int(
rule->options.inject.sector)));
qdict_put_obj(inject_error, "once", QOBJECT(qbool_from_int(
rule->options.inject.once)));
qdict_put_obj(inject_error, "immediately",
QOBJECT(qbool_from_int(
rule->options.inject.immediately)));
if (!inject_error_list) {
inject_error_list = qlist_new();
}
qlist_append_obj(inject_error_list, QOBJECT(inject_error));
} else if (rule->action == ACTION_SET_STATE) {
QDict *set_state = qdict_new();
qdict_put_obj(set_state, "event", QOBJECT(qstring_from_str(
BlkdebugEvent_lookup[rule->event])));
qdict_put_obj(set_state, "state",
QOBJECT(qint_from_int(rule->state)));
qdict_put_obj(set_state, "new_state", QOBJECT(qint_from_int(
rule->options.set_state.new_state)));
if (!set_state_list) {
set_state_list = qlist_new();
}
qlist_append_obj(set_state_list, QOBJECT(set_state));
} else if (rule->action == ACTION_SUSPEND) {
QDict *suspend = qdict_new();
qdict_put_obj(suspend, "event", QOBJECT(qstring_from_str(
BlkdebugEvent_lookup[rule->event])));
qdict_put_obj(suspend, "state",
QOBJECT(qint_from_int(rule->state)));
qdict_put_obj(suspend, "tag", QOBJECT(qstring_from_str(
rule->options.suspend.tag)));
if (!suspend_list) {
suspend_list = qlist_new();
}
qlist_append_obj(suspend_list, QOBJECT(suspend));
}
}
}
if (inject_error_list) {
qdict_put_obj(opts, "inject-error", QOBJECT(inject_error_list));
}
if (set_state_list) {
qdict_put_obj(opts, "set-state", QOBJECT(set_state_list));
}
if (suspend_list) {
qdict_put_obj(opts, "suspend", QOBJECT(suspend_list));
}
bs->full_open_options = opts;
}
static BlockDriver bdrv_blkdebug = {
.format_name = "blkdebug",
.protocol_name = "blkdebug",
@@ -820,11 +696,9 @@ static BlockDriver bdrv_blkdebug = {
.bdrv_file_open = blkdebug_open,
.bdrv_close = blkdebug_close,
.bdrv_getlength = blkdebug_getlength,
.bdrv_refresh_filename = blkdebug_refresh_filename,
.bdrv_aio_readv = blkdebug_aio_readv,
.bdrv_aio_writev = blkdebug_aio_writev,
.bdrv_aio_flush = blkdebug_aio_flush,
.bdrv_debug_event = blkdebug_debug_event,
.bdrv_debug_breakpoint = blkdebug_debug_breakpoint,

View File

@@ -10,8 +10,6 @@
#include <stdarg.h>
#include "qemu/sockets.h" /* for EINPROGRESS on Windows */
#include "block/block_int.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
typedef struct {
BlockDriverState *test_file;
@@ -19,7 +17,7 @@ typedef struct {
typedef struct BlkverifyAIOCB BlkverifyAIOCB;
struct BlkverifyAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
QEMUBH *bh;
/* Request metadata */
@@ -29,6 +27,7 @@ struct BlkverifyAIOCB {
int ret; /* first completed request's result */
unsigned int done; /* completion counter */
bool *finished; /* completion signal for cancel */
QEMUIOVector *qiov; /* user I/O vector */
QEMUIOVector raw_qiov; /* cloned I/O vector for raw file */
@@ -37,8 +36,21 @@ struct BlkverifyAIOCB {
void (*verify)(BlkverifyAIOCB *acb);
};
static void blkverify_aio_cancel(BlockDriverAIOCB *blockacb)
{
BlkverifyAIOCB *acb = (BlkverifyAIOCB *)blockacb;
bool finished = false;
/* Wait until request completes, invokes its callback, and frees itself */
acb->finished = &finished;
while (!finished) {
qemu_aio_wait();
}
}
static const AIOCBInfo blkverify_aiocb_info = {
.aiocb_size = sizeof(BlkverifyAIOCB),
.cancel = blkverify_aio_cancel,
};
static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
@@ -143,7 +155,6 @@ static int blkverify_open(BlockDriverState *bs, QDict *options, int flags,
ret = 0;
fail:
qemu_opts_del(opts);
return ret;
}
@@ -165,7 +176,7 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
int64_t sector_num, QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque)
{
BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
@@ -179,6 +190,7 @@ static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
acb->qiov = qiov;
acb->buf = NULL;
acb->verify = NULL;
acb->finished = NULL;
return acb;
}
@@ -192,7 +204,10 @@ static void blkverify_aio_bh(void *opaque)
qemu_vfree(acb->buf);
}
acb->common.cb(acb->common.opaque, acb->ret);
qemu_aio_unref(acb);
if (acb->finished) {
*acb->finished = true;
}
qemu_aio_release(acb);
}
static void blkverify_aio_cb(void *opaque, int ret)
@@ -213,8 +228,7 @@ static void blkverify_aio_cb(void *opaque, int ret)
acb->verify(acb);
}
acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
blkverify_aio_bh, acb);
acb->bh = qemu_bh_new(blkverify_aio_bh, acb);
qemu_bh_schedule(acb->bh);
break;
}
@@ -229,9 +243,9 @@ static void blkverify_verify_readv(BlkverifyAIOCB *acb)
}
}
static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
static BlockDriverAIOCB *blkverify_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
@@ -249,9 +263,9 @@ static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
return &acb->common;
}
static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
static BlockDriverAIOCB *blkverify_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
@@ -264,9 +278,9 @@ static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
return &acb->common;
}
static BlockAIOCB *blkverify_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *blkverify_aio_flush(BlockDriverState *bs,
BlockDriverCompletionFunc *cb,
void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
@@ -288,67 +302,21 @@ static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
return bdrv_recurse_is_first_non_filter(s->test_file, candidate);
}
/* Propagate AioContext changes to ->test_file */
static void blkverify_detach_aio_context(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
bdrv_detach_aio_context(s->test_file);
}
static void blkverify_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVBlkverifyState *s = bs->opaque;
bdrv_attach_aio_context(s->test_file, new_context);
}
static void blkverify_refresh_filename(BlockDriverState *bs)
{
BDRVBlkverifyState *s = bs->opaque;
/* bs->file has already been refreshed */
bdrv_refresh_filename(s->test_file);
if (bs->file->full_open_options && s->test_file->full_open_options) {
QDict *opts = qdict_new();
qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("blkverify")));
QINCREF(bs->file->full_open_options);
qdict_put_obj(opts, "raw", QOBJECT(bs->file->full_open_options));
QINCREF(s->test_file->full_open_options);
qdict_put_obj(opts, "test", QOBJECT(s->test_file->full_open_options));
bs->full_open_options = opts;
}
if (bs->file->exact_filename[0] && s->test_file->exact_filename[0]) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"blkverify:%s:%s",
bs->file->exact_filename, s->test_file->exact_filename);
}
}
static BlockDriver bdrv_blkverify = {
.format_name = "blkverify",
.protocol_name = "blkverify",
.instance_size = sizeof(BDRVBlkverifyState),
.format_name = "blkverify",
.protocol_name = "blkverify",
.instance_size = sizeof(BDRVBlkverifyState),
.bdrv_parse_filename = blkverify_parse_filename,
.bdrv_file_open = blkverify_open,
.bdrv_close = blkverify_close,
.bdrv_getlength = blkverify_getlength,
.bdrv_refresh_filename = blkverify_refresh_filename,
.bdrv_parse_filename = blkverify_parse_filename,
.bdrv_file_open = blkverify_open,
.bdrv_close = blkverify_close,
.bdrv_getlength = blkverify_getlength,
.bdrv_aio_readv = blkverify_aio_readv,
.bdrv_aio_writev = blkverify_aio_writev,
.bdrv_aio_flush = blkverify_aio_flush,
.bdrv_aio_readv = blkverify_aio_readv,
.bdrv_aio_writev = blkverify_aio_writev,
.bdrv_aio_flush = blkverify_aio_flush,
.bdrv_attach_aio_context = blkverify_attach_aio_context,
.bdrv_detach_aio_context = blkverify_detach_aio_context,
.is_filter = true,
.is_filter = true,
.bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,
};

View File

@@ -1,631 +0,0 @@
/*
* QEMU Block backends
*
* Copyright (C) 2014 Red Hat, Inc.
*
* Authors:
* Markus Armbruster <armbru@redhat.com>,
*
* This work is licensed under the terms of the GNU LGPL, version 2.1
* or later. See the COPYING.LIB file in the top-level directory.
*/
#include "sysemu/block-backend.h"
#include "block/block_int.h"
#include "sysemu/blockdev.h"
#include "qapi-event.h"
/* Number of coroutines to reserve per attached device model */
#define COROUTINE_POOL_RESERVATION 64
struct BlockBackend {
char *name;
int refcnt;
BlockDriverState *bs;
DriveInfo *legacy_dinfo; /* null unless created by drive_new() */
QTAILQ_ENTRY(BlockBackend) link; /* for blk_backends */
void *dev; /* attached device model, if any */
/* TODO change to DeviceState when all users are qdevified */
const BlockDevOps *dev_ops;
void *dev_opaque;
};
static void drive_info_del(DriveInfo *dinfo);
/* All the BlockBackends (except for hidden ones) */
static QTAILQ_HEAD(, BlockBackend) blk_backends =
QTAILQ_HEAD_INITIALIZER(blk_backends);
/*
* Create a new BlockBackend with @name, with a reference count of one.
* @name must not be null or empty.
* Fail if a BlockBackend with this name already exists.
* Store an error through @errp on failure, unless it's null.
* Return the new BlockBackend on success, null on failure.
*/
BlockBackend *blk_new(const char *name, Error **errp)
{
BlockBackend *blk;
assert(name && name[0]);
if (!id_wellformed(name)) {
error_setg(errp, "Invalid device name");
return NULL;
}
if (blk_by_name(name)) {
error_setg(errp, "Device with id '%s' already exists", name);
return NULL;
}
if (bdrv_find_node(name)) {
error_setg(errp,
"Device name '%s' conflicts with an existing node name",
name);
return NULL;
}
blk = g_new0(BlockBackend, 1);
blk->name = g_strdup(name);
blk->refcnt = 1;
QTAILQ_INSERT_TAIL(&blk_backends, blk, link);
return blk;
}
/*
* Create a new BlockBackend with a new BlockDriverState attached.
* Otherwise just like blk_new(), which see.
*/
BlockBackend *blk_new_with_bs(const char *name, Error **errp)
{
BlockBackend *blk;
BlockDriverState *bs;
blk = blk_new(name, errp);
if (!blk) {
return NULL;
}
bs = bdrv_new_root();
blk->bs = bs;
bs->blk = blk;
return blk;
}
static void blk_delete(BlockBackend *blk)
{
assert(!blk->refcnt);
assert(!blk->dev);
if (blk->bs) {
assert(blk->bs->blk == blk);
blk->bs->blk = NULL;
bdrv_unref(blk->bs);
blk->bs = NULL;
}
/* Avoid double-remove after blk_hide_on_behalf_of_do_drive_del() */
if (blk->name[0]) {
QTAILQ_REMOVE(&blk_backends, blk, link);
}
g_free(blk->name);
drive_info_del(blk->legacy_dinfo);
g_free(blk);
}
static void drive_info_del(DriveInfo *dinfo)
{
if (!dinfo) {
return;
}
qemu_opts_del(dinfo->opts);
g_free(dinfo->serial);
g_free(dinfo);
}
/*
* Increment @blk's reference count.
* @blk must not be null.
*/
void blk_ref(BlockBackend *blk)
{
blk->refcnt++;
}
/*
* Decrement @blk's reference count.
* If this drops it to zero, destroy @blk.
* For convenience, do nothing if @blk is null.
*/
void blk_unref(BlockBackend *blk)
{
if (blk) {
assert(blk->refcnt > 0);
if (!--blk->refcnt) {
blk_delete(blk);
}
}
}
/*
* Return the BlockBackend after @blk.
* If @blk is null, return the first one.
* Else, return @blk's next sibling, which may be null.
*
* To iterate over all BlockBackends, do
* for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
* ...
* }
*/
BlockBackend *blk_next(BlockBackend *blk)
{
return blk ? QTAILQ_NEXT(blk, link) : QTAILQ_FIRST(&blk_backends);
}
/*
* Return @blk's name, a non-null string.
* Wart: the name is empty iff @blk has been hidden with
* blk_hide_on_behalf_of_do_drive_del().
*/
const char *blk_name(BlockBackend *blk)
{
return blk->name;
}
/*
* Return the BlockBackend with name @name if it exists, else null.
* @name must not be null.
*/
BlockBackend *blk_by_name(const char *name)
{
BlockBackend *blk;
assert(name);
QTAILQ_FOREACH(blk, &blk_backends, link) {
if (!strcmp(name, blk->name)) {
return blk;
}
}
return NULL;
}
/*
* Return the BlockDriverState attached to @blk if any, else null.
*/
BlockDriverState *blk_bs(BlockBackend *blk)
{
return blk->bs;
}
/*
* Return @blk's DriveInfo if any, else null.
*/
DriveInfo *blk_legacy_dinfo(BlockBackend *blk)
{
return blk->legacy_dinfo;
}
/*
* Set @blk's DriveInfo to @dinfo, and return it.
* @blk must not have a DriveInfo set already.
* No other BlockBackend may have the same DriveInfo set.
*/
DriveInfo *blk_set_legacy_dinfo(BlockBackend *blk, DriveInfo *dinfo)
{
assert(!blk->legacy_dinfo);
return blk->legacy_dinfo = dinfo;
}
/*
* Return the BlockBackend with DriveInfo @dinfo.
* It must exist.
*/
BlockBackend *blk_by_legacy_dinfo(DriveInfo *dinfo)
{
BlockBackend *blk;
QTAILQ_FOREACH(blk, &blk_backends, link) {
if (blk->legacy_dinfo == dinfo) {
return blk;
}
}
abort();
}
/*
* Hide @blk.
* @blk must not have been hidden already.
* Make attached BlockDriverState, if any, anonymous.
* Once hidden, @blk is invisible to all functions that don't receive
* it as argument. For example, blk_by_name() won't return it.
* Strictly for use by do_drive_del().
* TODO get rid of it!
*/
void blk_hide_on_behalf_of_do_drive_del(BlockBackend *blk)
{
QTAILQ_REMOVE(&blk_backends, blk, link);
blk->name[0] = 0;
if (blk->bs) {
bdrv_make_anon(blk->bs);
}
}
/*
* Attach device model @dev to @blk.
* Return 0 on success, -EBUSY when a device model is attached already.
*/
int blk_attach_dev(BlockBackend *blk, void *dev)
/* TODO change to DeviceState *dev when all users are qdevified */
{
if (blk->dev) {
return -EBUSY;
}
blk_ref(blk);
blk->dev = dev;
bdrv_iostatus_reset(blk->bs);
/* We're expecting I/O from the device so bump up coroutine pool size */
qemu_coroutine_adjust_pool_size(COROUTINE_POOL_RESERVATION);
return 0;
}
/*
* Attach device model @dev to @blk.
* @blk must not have a device model attached already.
* TODO qdevified devices don't use this, remove when devices are qdevified
*/
void blk_attach_dev_nofail(BlockBackend *blk, void *dev)
{
if (blk_attach_dev(blk, dev) < 0) {
abort();
}
}
/*
* Detach device model @dev from @blk.
* @dev must be currently attached to @blk.
*/
void blk_detach_dev(BlockBackend *blk, void *dev)
/* TODO change to DeviceState *dev when all users are qdevified */
{
assert(blk->dev == dev);
blk->dev = NULL;
blk->dev_ops = NULL;
blk->dev_opaque = NULL;
bdrv_set_guest_block_size(blk->bs, 512);
qemu_coroutine_adjust_pool_size(-COROUTINE_POOL_RESERVATION);
blk_unref(blk);
}
/*
* Return the device model attached to @blk if any, else null.
*/
void *blk_get_attached_dev(BlockBackend *blk)
/* TODO change to return DeviceState * when all users are qdevified */
{
return blk->dev;
}
/*
* Set @blk's device model callbacks to @ops.
* @opaque is the opaque argument to pass to the callbacks.
* This is for use by device models.
*/
void blk_set_dev_ops(BlockBackend *blk, const BlockDevOps *ops,
void *opaque)
{
blk->dev_ops = ops;
blk->dev_opaque = opaque;
}
/*
* Notify @blk's attached device model of media change.
* If @load is true, notify of media load.
* Else, notify of media eject.
* Also send DEVICE_TRAY_MOVED events as appropriate.
*/
void blk_dev_change_media_cb(BlockBackend *blk, bool load)
{
if (blk->dev_ops && blk->dev_ops->change_media_cb) {
bool tray_was_closed = !blk_dev_is_tray_open(blk);
blk->dev_ops->change_media_cb(blk->dev_opaque, load);
if (tray_was_closed) {
/* tray open */
qapi_event_send_device_tray_moved(blk_name(blk),
true, &error_abort);
}
if (load) {
/* tray close */
qapi_event_send_device_tray_moved(blk_name(blk),
false, &error_abort);
}
}
}
/*
* Does @blk's attached device model have removable media?
* %true if no device model is attached.
*/
bool blk_dev_has_removable_media(BlockBackend *blk)
{
return !blk->dev || (blk->dev_ops && blk->dev_ops->change_media_cb);
}
/*
* Notify @blk's attached device model of a media eject request.
* If @force is true, the medium is about to be yanked out forcefully.
*/
void blk_dev_eject_request(BlockBackend *blk, bool force)
{
if (blk->dev_ops && blk->dev_ops->eject_request_cb) {
blk->dev_ops->eject_request_cb(blk->dev_opaque, force);
}
}
/*
* Does @blk's attached device model have a tray, and is it open?
*/
bool blk_dev_is_tray_open(BlockBackend *blk)
{
if (blk->dev_ops && blk->dev_ops->is_tray_open) {
return blk->dev_ops->is_tray_open(blk->dev_opaque);
}
return false;
}
/*
* Does @blk's attached device model have the medium locked?
* %false if the device model has no such lock.
*/
bool blk_dev_is_medium_locked(BlockBackend *blk)
{
if (blk->dev_ops && blk->dev_ops->is_medium_locked) {
return blk->dev_ops->is_medium_locked(blk->dev_opaque);
}
return false;
}
/*
* Notify @blk's attached device model of a backend size change.
*/
void blk_dev_resize_cb(BlockBackend *blk)
{
if (blk->dev_ops && blk->dev_ops->resize_cb) {
blk->dev_ops->resize_cb(blk->dev_opaque);
}
}
void blk_iostatus_enable(BlockBackend *blk)
{
bdrv_iostatus_enable(blk->bs);
}
int blk_read(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
int nb_sectors)
{
return bdrv_read(blk->bs, sector_num, buf, nb_sectors);
}
int blk_read_unthrottled(BlockBackend *blk, int64_t sector_num, uint8_t *buf,
int nb_sectors)
{
return bdrv_read_unthrottled(blk->bs, sector_num, buf, nb_sectors);
}
int blk_write(BlockBackend *blk, int64_t sector_num, const uint8_t *buf,
int nb_sectors)
{
return bdrv_write(blk->bs, sector_num, buf, nb_sectors);
}
BlockAIOCB *blk_aio_write_zeroes(BlockBackend *blk, int64_t sector_num,
int nb_sectors, BdrvRequestFlags flags,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_write_zeroes(blk->bs, sector_num, nb_sectors, flags,
cb, opaque);
}
int blk_pread(BlockBackend *blk, int64_t offset, void *buf, int count)
{
return bdrv_pread(blk->bs, offset, buf, count);
}
int blk_pwrite(BlockBackend *blk, int64_t offset, const void *buf, int count)
{
return bdrv_pwrite(blk->bs, offset, buf, count);
}
int64_t blk_getlength(BlockBackend *blk)
{
return bdrv_getlength(blk->bs);
}
void blk_get_geometry(BlockBackend *blk, uint64_t *nb_sectors_ptr)
{
bdrv_get_geometry(blk->bs, nb_sectors_ptr);
}
BlockAIOCB *blk_aio_readv(BlockBackend *blk, int64_t sector_num,
QEMUIOVector *iov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_readv(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
}
BlockAIOCB *blk_aio_writev(BlockBackend *blk, int64_t sector_num,
QEMUIOVector *iov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_writev(blk->bs, sector_num, iov, nb_sectors, cb, opaque);
}
BlockAIOCB *blk_aio_flush(BlockBackend *blk,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_flush(blk->bs, cb, opaque);
}
BlockAIOCB *blk_aio_discard(BlockBackend *blk,
int64_t sector_num, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_discard(blk->bs, sector_num, nb_sectors, cb, opaque);
}
void blk_aio_cancel(BlockAIOCB *acb)
{
bdrv_aio_cancel(acb);
}
void blk_aio_cancel_async(BlockAIOCB *acb)
{
bdrv_aio_cancel_async(acb);
}
int blk_aio_multiwrite(BlockBackend *blk, BlockRequest *reqs, int num_reqs)
{
return bdrv_aio_multiwrite(blk->bs, reqs, num_reqs);
}
int blk_ioctl(BlockBackend *blk, unsigned long int req, void *buf)
{
return bdrv_ioctl(blk->bs, req, buf);
}
BlockAIOCB *blk_aio_ioctl(BlockBackend *blk, unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque)
{
return bdrv_aio_ioctl(blk->bs, req, buf, cb, opaque);
}
int blk_flush(BlockBackend *blk)
{
return bdrv_flush(blk->bs);
}
int blk_flush_all(void)
{
return bdrv_flush_all();
}
void blk_drain_all(void)
{
bdrv_drain_all();
}
BlockdevOnError blk_get_on_error(BlockBackend *blk, bool is_read)
{
return bdrv_get_on_error(blk->bs, is_read);
}
BlockErrorAction blk_get_error_action(BlockBackend *blk, bool is_read,
int error)
{
return bdrv_get_error_action(blk->bs, is_read, error);
}
void blk_error_action(BlockBackend *blk, BlockErrorAction action,
bool is_read, int error)
{
bdrv_error_action(blk->bs, action, is_read, error);
}
int blk_is_read_only(BlockBackend *blk)
{
return bdrv_is_read_only(blk->bs);
}
int blk_is_sg(BlockBackend *blk)
{
return bdrv_is_sg(blk->bs);
}
int blk_enable_write_cache(BlockBackend *blk)
{
return bdrv_enable_write_cache(blk->bs);
}
void blk_set_enable_write_cache(BlockBackend *blk, bool wce)
{
bdrv_set_enable_write_cache(blk->bs, wce);
}
int blk_is_inserted(BlockBackend *blk)
{
return bdrv_is_inserted(blk->bs);
}
void blk_lock_medium(BlockBackend *blk, bool locked)
{
bdrv_lock_medium(blk->bs, locked);
}
void blk_eject(BlockBackend *blk, bool eject_flag)
{
bdrv_eject(blk->bs, eject_flag);
}
int blk_get_flags(BlockBackend *blk)
{
return bdrv_get_flags(blk->bs);
}
void blk_set_guest_block_size(BlockBackend *blk, int align)
{
bdrv_set_guest_block_size(blk->bs, align);
}
void *blk_blockalign(BlockBackend *blk, size_t size)
{
return qemu_blockalign(blk ? blk->bs : NULL, size);
}
bool blk_op_is_blocked(BlockBackend *blk, BlockOpType op, Error **errp)
{
return bdrv_op_is_blocked(blk->bs, op, errp);
}
void blk_op_unblock(BlockBackend *blk, BlockOpType op, Error *reason)
{
bdrv_op_unblock(blk->bs, op, reason);
}
void blk_op_block_all(BlockBackend *blk, Error *reason)
{
bdrv_op_block_all(blk->bs, reason);
}
void blk_op_unblock_all(BlockBackend *blk, Error *reason)
{
bdrv_op_unblock_all(blk->bs, reason);
}
AioContext *blk_get_aio_context(BlockBackend *blk)
{
return bdrv_get_aio_context(blk->bs);
}
void blk_set_aio_context(BlockBackend *blk, AioContext *new_context)
{
bdrv_set_aio_context(blk->bs, new_context);
}
void blk_io_plug(BlockBackend *blk)
{
bdrv_io_plug(blk->bs);
}
void blk_io_unplug(BlockBackend *blk)
{
bdrv_io_unplug(blk->bs);
}
BlockAcctStats *blk_get_stats(BlockBackend *blk)
{
return bdrv_get_stats(blk->bs);
}
void *blk_aio_get(const AIOCBInfo *aiocb_info, BlockBackend *blk,
BlockCompletionFunc *cb, void *opaque)
{
return qemu_aio_get(aiocb_info, blk_bs(blk), cb, opaque);
}

View File

@@ -131,11 +131,7 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
return -EFBIG;
}
s->catalog_bitmap = g_try_new(uint32_t, s->catalog_size);
if (s->catalog_size && s->catalog_bitmap == NULL) {
error_setg(errp, "Could not allocate memory for catalog");
return -ENOMEM;
}
s->catalog_bitmap = g_malloc(s->catalog_size * 4);
ret = bdrv_pread(bs->file, le32_to_cpu(bochs.header), s->catalog_bitmap,
s->catalog_size * 4);
@@ -191,14 +187,13 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
uint64_t offset = sector_num * 512;
uint64_t extent_index, extent_offset, bitmap_offset;
char bitmap_entry;
int ret;
// seek to sector
extent_index = offset / s->extent_size;
extent_offset = (offset % s->extent_size) / 512;
if (s->catalog_bitmap[extent_index] == 0xffffffff) {
return 0; /* not allocated */
return -1; /* not allocated */
}
bitmap_offset = s->data_offset +
@@ -206,14 +201,13 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
(s->extent_blocks + s->bitmap_blocks));
/* read in bitmap for current extent */
ret = bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
&bitmap_entry, 1);
if (ret < 0) {
return ret;
if (bdrv_pread(bs->file, bitmap_offset + (extent_offset / 8),
&bitmap_entry, 1) != 1) {
return -1;
}
if (!((bitmap_entry >> (extent_offset % 8)) & 1)) {
return 0; /* not allocated */
return -1; /* not allocated */
}
return bitmap_offset + (512 * (s->bitmap_blocks + extent_offset));
@@ -226,16 +220,13 @@ static int bochs_read(BlockDriverState *bs, int64_t sector_num,
while (nb_sectors > 0) {
int64_t block_offset = seek_to_sector(bs, sector_num);
if (block_offset < 0) {
return block_offset;
} else if (block_offset > 0) {
if (block_offset >= 0) {
ret = bdrv_pread(bs->file, block_offset, buf, 512);
if (ret < 0) {
return ret;
if (ret != 512) {
return -1;
}
} else {
} else
memset(buf, 0, 512);
}
nb_sectors--;
sector_num++;
buf += 512;

View File

@@ -72,7 +72,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
}
s->block_size = be32_to_cpu(s->block_size);
if (s->block_size % 512) {
error_setg(errp, "block_size %" PRIu32 " must be a multiple of 512",
error_setg(errp, "block_size %u must be a multiple of 512",
s->block_size);
return -EINVAL;
}
@@ -86,7 +86,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
* need a buffer this big.
*/
if (s->block_size > MAX_BLOCK_SIZE) {
error_setg(errp, "block_size %" PRIu32 " must be %u MB or less",
error_setg(errp, "block_size %u must be %u MB or less",
s->block_size,
MAX_BLOCK_SIZE / (1024 * 1024));
return -EINVAL;
@@ -101,7 +101,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
/* read offsets */
if (s->n_blocks > (UINT32_MAX - 1) / sizeof(uint64_t)) {
/* Prevent integer overflow */
error_setg(errp, "n_blocks %" PRIu32 " must be %zu or less",
error_setg(errp, "n_blocks %u must be %zu or less",
s->n_blocks,
(UINT32_MAX - 1) / sizeof(uint64_t));
return -EINVAL;
@@ -116,12 +116,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
"try increasing block size");
return -EINVAL;
}
s->offsets = g_try_malloc(offsets_size);
if (s->offsets == NULL) {
error_setg(errp, "Could not allocate offsets table");
return -ENOMEM;
}
s->offsets = g_malloc(offsets_size);
ret = bdrv_pread(bs->file, 128 + 4 + 4, s->offsets, offsets_size);
if (ret < 0) {
@@ -138,7 +133,7 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
if (s->offsets[i] < s->offsets[i - 1]) {
error_setg(errp, "offsets not monotonically increasing at "
"index %" PRIu32 ", image file is corrupt", i);
"index %u, image file is corrupt", i);
ret = -EINVAL;
goto fail;
}
@@ -151,8 +146,8 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
* ridiculous s->compressed_block allocation.
*/
if (size > 2 * MAX_BLOCK_SIZE) {
error_setg(errp, "invalid compressed block size at index %" PRIu32
", image file is corrupt", i);
error_setg(errp, "invalid compressed block size at index %u, "
"image file is corrupt", i);
ret = -EINVAL;
goto fail;
}
@@ -163,20 +158,8 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
}
/* initialize zlib engine */
s->compressed_block = g_try_malloc(max_compressed_block_size + 1);
if (s->compressed_block == NULL) {
error_setg(errp, "Could not allocate compressed_block");
ret = -ENOMEM;
goto fail;
}
s->uncompressed_block = g_try_malloc(s->block_size);
if (s->uncompressed_block == NULL) {
error_setg(errp, "Could not allocate uncompressed_block");
ret = -ENOMEM;
goto fail;
}
s->compressed_block = g_malloc(max_compressed_block_size + 1);
s->uncompressed_block = g_malloc(s->block_size);
if (inflateInit(&s->zstream) != Z_OK) {
ret = -EINVAL;
goto fail;

View File

@@ -37,7 +37,6 @@ typedef struct CommitBlockJob {
BlockdevOnError on_error;
int base_flags;
int orig_overlay_flags;
char *backing_file_str;
} CommitBlockJob;
static int coroutine_fn commit_populate(BlockDriverState *bs,
@@ -60,50 +59,17 @@ static int coroutine_fn commit_populate(BlockDriverState *bs,
return 0;
}
typedef struct {
int ret;
} CommitCompleteData;
static void commit_complete(BlockJob *job, void *opaque)
static void coroutine_fn commit_run(void *opaque)
{
CommitBlockJob *s = container_of(job, CommitBlockJob, common);
CommitCompleteData *data = opaque;
CommitBlockJob *s = opaque;
BlockDriverState *active = s->active;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
BlockDriverState *overlay_bs;
int ret = data->ret;
if (!block_job_is_cancelled(&s->common) && ret == 0) {
/* success */
ret = bdrv_drop_intermediate(active, top, base, s->backing_file_str);
}
/* restore base open flags here if appropriate (e.g., change the base back
* to r/o). These reopens do not need to be atomic, since we won't abort
* even on failure here */
if (s->base_flags != bdrv_get_flags(base)) {
bdrv_reopen(base, s->base_flags, NULL);
}
overlay_bs = bdrv_find_overlay(active, top);
if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
}
g_free(s->backing_file_str);
block_job_completed(&s->common, ret);
g_free(data);
}
static void coroutine_fn commit_run(void *opaque)
{
CommitBlockJob *s = opaque;
CommitCompleteData *data;
BlockDriverState *top = s->top;
BlockDriverState *base = s->base;
int64_t sector_num, end;
int ret = 0;
int n = 0;
void *buf = NULL;
void *buf;
int bytes_written = 0;
int64_t base_len;
@@ -111,18 +77,18 @@ static void coroutine_fn commit_run(void *opaque)
if (s->common.len < 0) {
goto out;
goto exit_restore_reopen;
}
ret = base_len = bdrv_getlength(base);
if (base_len < 0) {
goto out;
goto exit_restore_reopen;
}
if (base_len < s->common.len) {
ret = bdrv_truncate(base, s->common.len);
if (ret) {
goto out;
goto exit_restore_reopen;
}
}
@@ -161,7 +127,7 @@ wait:
if (s->on_error == BLOCKDEV_ON_ERROR_STOP ||
s->on_error == BLOCKDEV_ON_ERROR_REPORT||
(s->on_error == BLOCKDEV_ON_ERROR_ENOSPC && ret == -ENOSPC)) {
goto out;
goto exit_free_buf;
} else {
n = 0;
continue;
@@ -173,12 +139,27 @@ wait:
ret = 0;
out:
if (!block_job_is_cancelled(&s->common) && sector_num == end) {
/* success */
ret = bdrv_drop_intermediate(active, top, base);
}
exit_free_buf:
qemu_vfree(buf);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&s->common, commit_complete, data);
exit_restore_reopen:
/* restore base open flags here if appropriate (e.g., change the base back
* to r/o). These reopens do not need to be atomic, since we won't abort
* even on failure here */
if (s->base_flags != bdrv_get_flags(base)) {
bdrv_reopen(base, s->base_flags, NULL);
}
overlay_bs = bdrv_find_overlay(active, top);
if (overlay_bs && s->orig_overlay_flags != bdrv_get_flags(overlay_bs)) {
bdrv_reopen(overlay_bs, s->orig_overlay_flags, NULL);
}
block_job_completed(&s->common, ret);
}
static void commit_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -200,8 +181,8 @@ static const BlockJobDriver commit_job_driver = {
void commit_start(BlockDriverState *bs, BlockDriverState *base,
BlockDriverState *top, int64_t speed,
BlockdevOnError on_error, BlockCompletionFunc *cb,
void *opaque, const char *backing_file_str, Error **errp)
BlockdevOnError on_error, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
CommitBlockJob *s;
BlockReopenQueue *reopen_queue = NULL;
@@ -213,7 +194,7 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
if ((on_error == BLOCKDEV_ON_ERROR_STOP ||
on_error == BLOCKDEV_ON_ERROR_ENOSPC) &&
!bdrv_iostatus_is_enabled(bs)) {
error_setg(errp, "Invalid parameter combination");
error_set(errp, QERR_INVALID_PARAMETER_COMBINATION);
return;
}
@@ -263,8 +244,6 @@ void commit_start(BlockDriverState *bs, BlockDriverState *base,
s->base_flags = orig_base_flags;
s->orig_overlay_flags = orig_overlay_flags;
s->backing_file_str = g_strdup(backing_file_str);
s->on_error = on_error;
s->common.co = qemu_coroutine_create(commit_run);

432
block/cow.c Normal file
View File

@@ -0,0 +1,432 @@
/*
* Block driver for the COW format
*
* Copyright (c) 2004 Fabrice Bellard
*
* 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-common.h"
#include "block/block_int.h"
#include "qemu/module.h"
/**************************************************************/
/* COW block driver using file system holes */
/* user mode linux compatible COW file */
#define COW_MAGIC 0x4f4f4f4d /* MOOO */
#define COW_VERSION 2
struct cow_header_v2 {
uint32_t magic;
uint32_t version;
char backing_file[1024];
int32_t mtime;
uint64_t size;
uint32_t sectorsize;
};
typedef struct BDRVCowState {
CoMutex lock;
int64_t cow_sectors_offset;
} BDRVCowState;
static int cow_probe(const uint8_t *buf, int buf_size, const char *filename)
{
const struct cow_header_v2 *cow_header = (const void *)buf;
if (buf_size >= sizeof(struct cow_header_v2) &&
be32_to_cpu(cow_header->magic) == COW_MAGIC &&
be32_to_cpu(cow_header->version) == COW_VERSION)
return 100;
else
return 0;
}
static int cow_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVCowState *s = bs->opaque;
struct cow_header_v2 cow_header;
int bitmap_size;
int64_t size;
int ret;
/* see if it is a cow image */
ret = bdrv_pread(bs->file, 0, &cow_header, sizeof(cow_header));
if (ret < 0) {
goto fail;
}
if (be32_to_cpu(cow_header.magic) != COW_MAGIC) {
error_setg(errp, "Image not in COW format");
ret = -EINVAL;
goto fail;
}
if (be32_to_cpu(cow_header.version) != COW_VERSION) {
char version[64];
snprintf(version, sizeof(version),
"COW version %d", cow_header.version);
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bs->device_name, "cow", version);
ret = -ENOTSUP;
goto fail;
}
/* cow image found */
size = be64_to_cpu(cow_header.size);
bs->total_sectors = size / 512;
pstrcpy(bs->backing_file, sizeof(bs->backing_file),
cow_header.backing_file);
bitmap_size = ((bs->total_sectors + 7) >> 3) + sizeof(cow_header);
s->cow_sectors_offset = (bitmap_size + 511) & ~511;
qemu_co_mutex_init(&s->lock);
return 0;
fail:
return ret;
}
static inline void cow_set_bits(uint8_t *bitmap, int start, int64_t nb_sectors)
{
int64_t bitnum = start, last = start + nb_sectors;
while (bitnum < last) {
if ((bitnum & 7) == 0 && bitnum + 8 <= last) {
bitmap[bitnum / 8] = 0xFF;
bitnum += 8;
continue;
}
bitmap[bitnum/8] |= (1 << (bitnum % 8));
bitnum++;
}
}
#define BITS_PER_BITMAP_SECTOR (512 * 8)
/* Cannot use bitmap.c on big-endian machines. */
static int cow_test_bit(int64_t bitnum, const uint8_t *bitmap)
{
return (bitmap[bitnum / 8] & (1 << (bitnum & 7))) != 0;
}
static int cow_find_streak(const uint8_t *bitmap, int value, int start, int nb_sectors)
{
int streak_value = value ? 0xFF : 0;
int last = MIN(start + nb_sectors, BITS_PER_BITMAP_SECTOR);
int bitnum = start;
while (bitnum < last) {
if ((bitnum & 7) == 0 && bitmap[bitnum / 8] == streak_value) {
bitnum += 8;
continue;
}
if (cow_test_bit(bitnum, bitmap) == value) {
bitnum++;
continue;
}
break;
}
return MIN(bitnum, last) - start;
}
/* Return true if first block has been changed (ie. current version is
* in COW file). Set the number of continuous blocks for which that
* is true. */
static int coroutine_fn cow_co_is_allocated(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *num_same)
{
int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
bool first = true;
int changed = 0, same = 0;
do {
int ret;
uint8_t bitmap[BDRV_SECTOR_SIZE];
bitnum &= BITS_PER_BITMAP_SECTOR - 1;
int sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
if (ret < 0) {
return ret;
}
if (first) {
changed = cow_test_bit(bitnum, bitmap);
first = false;
}
same += cow_find_streak(bitmap, changed, bitnum, nb_sectors);
bitnum += sector_bits;
nb_sectors -= sector_bits;
offset += BDRV_SECTOR_SIZE;
} while (nb_sectors);
*num_same = same;
return changed;
}
static int64_t coroutine_fn cow_co_get_block_status(BlockDriverState *bs,
int64_t sector_num, int nb_sectors, int *num_same)
{
BDRVCowState *s = bs->opaque;
int ret = cow_co_is_allocated(bs, sector_num, nb_sectors, num_same);
int64_t offset = s->cow_sectors_offset + (sector_num << BDRV_SECTOR_BITS);
if (ret < 0) {
return ret;
}
return (ret ? BDRV_BLOCK_DATA : 0) | offset | BDRV_BLOCK_OFFSET_VALID;
}
static int cow_update_bitmap(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
int64_t bitnum = sector_num + sizeof(struct cow_header_v2) * 8;
uint64_t offset = (bitnum / 8) & -BDRV_SECTOR_SIZE;
bool first = true;
int sector_bits;
for ( ; nb_sectors;
bitnum += sector_bits,
nb_sectors -= sector_bits,
offset += BDRV_SECTOR_SIZE) {
int ret, set;
uint8_t bitmap[BDRV_SECTOR_SIZE];
bitnum &= BITS_PER_BITMAP_SECTOR - 1;
sector_bits = MIN(nb_sectors, BITS_PER_BITMAP_SECTOR - bitnum);
ret = bdrv_pread(bs->file, offset, &bitmap, sizeof(bitmap));
if (ret < 0) {
return ret;
}
/* Skip over any already set bits */
set = cow_find_streak(bitmap, 1, bitnum, sector_bits);
bitnum += set;
sector_bits -= set;
nb_sectors -= set;
if (!sector_bits) {
continue;
}
if (first) {
ret = bdrv_flush(bs->file);
if (ret < 0) {
return ret;
}
first = false;
}
cow_set_bits(bitmap, bitnum, sector_bits);
ret = bdrv_pwrite(bs->file, offset, &bitmap, sizeof(bitmap));
if (ret < 0) {
return ret;
}
}
return 0;
}
static int coroutine_fn cow_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
BDRVCowState *s = bs->opaque;
int ret, n;
while (nb_sectors > 0) {
ret = cow_co_is_allocated(bs, sector_num, nb_sectors, &n);
if (ret < 0) {
return ret;
}
if (ret) {
ret = bdrv_pread(bs->file,
s->cow_sectors_offset + sector_num * 512,
buf, n * 512);
if (ret < 0) {
return ret;
}
} else {
if (bs->backing_hd) {
/* read from the base image */
ret = bdrv_read(bs->backing_hd, sector_num, buf, n);
if (ret < 0) {
return ret;
}
} else {
memset(buf, 0, n * 512);
}
}
nb_sectors -= n;
sector_num += n;
buf += n * 512;
}
return 0;
}
static coroutine_fn int cow_co_read(BlockDriverState *bs, int64_t sector_num,
uint8_t *buf, int nb_sectors)
{
int ret;
BDRVCowState *s = bs->opaque;
qemu_co_mutex_lock(&s->lock);
ret = cow_read(bs, sector_num, buf, nb_sectors);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static int cow_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
BDRVCowState *s = bs->opaque;
int ret;
ret = bdrv_pwrite(bs->file, s->cow_sectors_offset + sector_num * 512,
buf, nb_sectors * 512);
if (ret < 0) {
return ret;
}
return cow_update_bitmap(bs, sector_num, nb_sectors);
}
static coroutine_fn int cow_co_write(BlockDriverState *bs, int64_t sector_num,
const uint8_t *buf, int nb_sectors)
{
int ret;
BDRVCowState *s = bs->opaque;
qemu_co_mutex_lock(&s->lock);
ret = cow_write(bs, sector_num, buf, nb_sectors);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static void cow_close(BlockDriverState *bs)
{
}
static int cow_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
struct cow_header_v2 cow_header;
struct stat st;
int64_t image_sectors = 0;
const char *image_filename = NULL;
Error *local_err = NULL;
int ret;
BlockDriverState *cow_bs;
/* Read out options */
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
image_sectors = options->value.n / 512;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
image_filename = options->value.s;
}
options++;
}
ret = bdrv_create_file(filename, options, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return ret;
}
cow_bs = NULL;
ret = bdrv_open(&cow_bs, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return ret;
}
memset(&cow_header, 0, sizeof(cow_header));
cow_header.magic = cpu_to_be32(COW_MAGIC);
cow_header.version = cpu_to_be32(COW_VERSION);
if (image_filename) {
/* Note: if no file, we put a dummy mtime */
cow_header.mtime = cpu_to_be32(0);
if (stat(image_filename, &st) != 0) {
goto mtime_fail;
}
cow_header.mtime = cpu_to_be32(st.st_mtime);
mtime_fail:
pstrcpy(cow_header.backing_file, sizeof(cow_header.backing_file),
image_filename);
}
cow_header.sectorsize = cpu_to_be32(512);
cow_header.size = cpu_to_be64(image_sectors * 512);
ret = bdrv_pwrite(cow_bs, 0, &cow_header, sizeof(cow_header));
if (ret < 0) {
goto exit;
}
/* resize to include at least all the bitmap */
ret = bdrv_truncate(cow_bs,
sizeof(cow_header) + ((image_sectors + 7) >> 3));
if (ret < 0) {
goto exit;
}
exit:
bdrv_unref(cow_bs);
return ret;
}
static QEMUOptionParameter cow_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = OPT_STRING,
.help = "File name of a base image"
},
{ NULL }
};
static BlockDriver bdrv_cow = {
.format_name = "cow",
.instance_size = sizeof(BDRVCowState),
.bdrv_probe = cow_probe,
.bdrv_open = cow_open,
.bdrv_close = cow_close,
.bdrv_create = cow_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_read = cow_co_read,
.bdrv_write = cow_co_write,
.bdrv_co_get_block_status = cow_co_get_block_status,
.create_options = cow_create_options,
};
static void bdrv_cow_init(void)
{
bdrv_register(&bdrv_cow);
}
block_init(bdrv_cow_init);

View File

@@ -23,10 +23,9 @@
*/
#include "qemu-common.h"
#include "block/block_int.h"
#include "qapi/qmp/qbool.h"
#include <curl/curl.h>
// #define DEBUG_CURL
// #define DEBUG
// #define DEBUG_VERBOSE
#ifdef DEBUG_CURL
@@ -38,21 +37,6 @@
#if LIBCURL_VERSION_NUM >= 0x071000
/* The multi interface timer callback was introduced in 7.16.0 */
#define NEED_CURL_TIMER_CALLBACK
#define HAVE_SOCKET_ACTION
#endif
#ifndef HAVE_SOCKET_ACTION
/* If curl_multi_socket_action isn't available, define it statically here in
* terms of curl_multi_socket. Note that ev_bitmask will be ignored, which is
* less efficient but still safe. */
static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
curl_socket_t sockfd,
int ev_bitmask,
int *running_handles)
{
return curl_multi_socket(multi_handle, sockfd, running_handles);
}
#define curl_multi_socket_action __curl_multi_socket_action
#endif
#define PROTOCOLS (CURLPROTO_HTTP | CURLPROTO_HTTPS | \
@@ -62,24 +46,16 @@ static CURLMcode __curl_multi_socket_action(CURLM *multi_handle,
#define CURL_NUM_STATES 8
#define CURL_NUM_ACB 8
#define SECTOR_SIZE 512
#define READ_AHEAD_DEFAULT (256 * 1024)
#define CURL_TIMEOUT_DEFAULT 5
#define CURL_TIMEOUT_MAX 10000
#define READ_AHEAD_SIZE (256 * 1024)
#define FIND_RET_NONE 0
#define FIND_RET_OK 1
#define FIND_RET_WAIT 2
#define CURL_BLOCK_OPT_URL "url"
#define CURL_BLOCK_OPT_READAHEAD "readahead"
#define CURL_BLOCK_OPT_SSLVERIFY "sslverify"
#define CURL_BLOCK_OPT_TIMEOUT "timeout"
#define CURL_BLOCK_OPT_COOKIE "cookie"
struct BDRVCURLState;
typedef struct CURLAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
QEMUBH *bh;
QEMUIOVector *qiov;
@@ -95,7 +71,6 @@ typedef struct CURLState
struct BDRVCURLState *s;
CURLAIOCB *acb[CURL_NUM_ACB];
CURL *curl;
curl_socket_t sock_fd;
char *orig_buf;
size_t buf_start;
size_t buf_off;
@@ -112,16 +87,11 @@ typedef struct BDRVCURLState {
CURLState states[CURL_NUM_STATES];
char *url;
size_t readahead_size;
bool sslverify;
uint64_t timeout;
char *cookie;
bool accept_range;
AioContext *aio_context;
} BDRVCURLState;
static void curl_clean_state(CURLState *s);
static void curl_multi_do(void *arg);
static void curl_multi_read(void *arg);
#ifdef NEED_CURL_TIMER_CALLBACK
static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
@@ -141,29 +111,21 @@ static int curl_timer_cb(CURLM *multi, long timeout_ms, void *opaque)
#endif
static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
void *userp, void *sp)
void *s, void *sp)
{
BDRVCURLState *s;
CURLState *state = NULL;
curl_easy_getinfo(curl, CURLINFO_PRIVATE, (char **)&state);
state->sock_fd = fd;
s = state->s;
DPRINTF("CURL (AIO): Sock action %d on fd %d\n", action, fd);
switch (action) {
case CURL_POLL_IN:
aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
NULL, state);
qemu_aio_set_fd_handler(fd, curl_multi_do, NULL, s);
break;
case CURL_POLL_OUT:
aio_set_fd_handler(s->aio_context, fd, NULL, curl_multi_do, state);
qemu_aio_set_fd_handler(fd, NULL, curl_multi_do, s);
break;
case CURL_POLL_INOUT:
aio_set_fd_handler(s->aio_context, fd, curl_multi_read,
curl_multi_do, state);
qemu_aio_set_fd_handler(fd, curl_multi_do, curl_multi_do, s);
break;
case CURL_POLL_REMOVE:
aio_set_fd_handler(s->aio_context, fd, NULL, NULL, NULL);
qemu_aio_set_fd_handler(fd, NULL, NULL, NULL);
break;
}
@@ -193,7 +155,7 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
DPRINTF("CURL: Just reading %zd bytes\n", realsize);
if (!s || !s->orig_buf)
return 0;
goto read_end;
if (s->buf_off >= s->buf_len) {
/* buffer full, read nothing */
@@ -213,11 +175,12 @@ static size_t curl_read_cb(void *ptr, size_t size, size_t nmemb, void *opaque)
qemu_iovec_from_buf(acb->qiov, 0, s->orig_buf + acb->start,
acb->end - acb->start);
acb->common.cb(acb->common.opaque, 0);
qemu_aio_unref(acb);
qemu_aio_release(acb);
s->acb[i] = NULL;
}
}
read_end:
return realsize;
}
@@ -252,8 +215,7 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
}
// Wait for unfinished chunks
if (state->in_use &&
(start >= state->buf_start) &&
if ((start >= state->buf_start) &&
(start <= buf_fend) &&
(end >= state->buf_start) &&
(end <= buf_fend))
@@ -275,69 +237,68 @@ static int curl_find_buf(BDRVCURLState *s, size_t start, size_t len,
return FIND_RET_NONE;
}
static void curl_multi_check_completion(BDRVCURLState *s)
static void curl_multi_read(BDRVCURLState *s)
{
int msgs_in_queue;
/* Try to find done transfers, so we can free the easy
* handle again. */
for (;;) {
do {
CURLMsg *msg;
msg = curl_multi_info_read(s->multi, &msgs_in_queue);
/* Quit when there are no more completions */
if (!msg)
break;
if (msg->msg == CURLMSG_DONE) {
CURLState *state = NULL;
curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE,
(char **)&state);
/* ACBs for successful messages get completed in curl_read_cb */
if (msg->data.result != CURLE_OK) {
int i;
for (i = 0; i < CURL_NUM_ACB; i++) {
CURLAIOCB *acb = state->acb[i];
if (acb == NULL) {
continue;
}
acb->common.cb(acb->common.opaque, -EIO);
qemu_aio_unref(acb);
state->acb[i] = NULL;
}
}
curl_clean_state(state);
if (msg->msg == CURLMSG_NONE)
break;
switch (msg->msg) {
case CURLMSG_DONE:
{
CURLState *state = NULL;
curl_easy_getinfo(msg->easy_handle, CURLINFO_PRIVATE, (char**)&state);
/* ACBs for successful messages get completed in curl_read_cb */
if (msg->data.result != CURLE_OK) {
int i;
for (i = 0; i < CURL_NUM_ACB; i++) {
CURLAIOCB *acb = state->acb[i];
if (acb == NULL) {
continue;
}
acb->common.cb(acb->common.opaque, -EIO);
qemu_aio_release(acb);
state->acb[i] = NULL;
}
}
curl_clean_state(state);
break;
}
default:
msgs_in_queue = 0;
break;
}
}
} while(msgs_in_queue);
}
static void curl_multi_do(void *arg)
{
CURLState *s = (CURLState *)arg;
BDRVCURLState *s = (BDRVCURLState *)arg;
int running;
int r;
if (!s->s->multi) {
if (!s->multi) {
return;
}
do {
r = curl_multi_socket_action(s->s->multi, s->sock_fd, 0, &running);
r = curl_multi_socket_all(s->multi, &running);
} while(r == CURLM_CALL_MULTI_PERFORM);
}
static void curl_multi_read(void *arg)
{
CURLState *s = (CURLState *)arg;
curl_multi_do(arg);
curl_multi_check_completion(s->s);
curl_multi_read(s);
}
static void curl_multi_timeout_do(void *arg)
@@ -352,13 +313,13 @@ static void curl_multi_timeout_do(void *arg)
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
curl_multi_check_completion(s);
curl_multi_read(s);
#else
abort();
#endif
}
static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
static CURLState *curl_init_state(BDRVCURLState *s)
{
CURLState *state = NULL;
int i, j;
@@ -376,47 +337,44 @@ static CURLState *curl_init_state(BlockDriverState *bs, BDRVCURLState *s)
break;
}
if (!state) {
aio_poll(bdrv_get_aio_context(bs), true);
g_usleep(100);
curl_multi_do(s);
}
} while(!state);
if (!state->curl) {
state->curl = curl_easy_init();
if (!state->curl) {
return NULL;
}
curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
curl_easy_setopt(state->curl, CURLOPT_SSL_VERIFYPEER,
(long) s->sslverify);
if (s->cookie) {
curl_easy_setopt(state->curl, CURLOPT_COOKIE, s->cookie);
}
curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, (long)s->timeout);
curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION,
(void *)curl_read_cb);
curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
if (state->curl)
goto has_curl;
/* Restrict supported protocols to avoid security issues in the more
* obscure protocols. For example, do not allow POP3/SMTP/IMAP see
* CVE-2013-0249.
*
* Restricting protocols is only supported from 7.19.4 upwards.
*/
state->curl = curl_easy_init();
if (!state->curl)
return NULL;
curl_easy_setopt(state->curl, CURLOPT_URL, s->url);
curl_easy_setopt(state->curl, CURLOPT_TIMEOUT, 5);
curl_easy_setopt(state->curl, CURLOPT_WRITEFUNCTION, (void *)curl_read_cb);
curl_easy_setopt(state->curl, CURLOPT_WRITEDATA, (void *)state);
curl_easy_setopt(state->curl, CURLOPT_PRIVATE, (void *)state);
curl_easy_setopt(state->curl, CURLOPT_AUTOREFERER, 1);
curl_easy_setopt(state->curl, CURLOPT_FOLLOWLOCATION, 1);
curl_easy_setopt(state->curl, CURLOPT_NOSIGNAL, 1);
curl_easy_setopt(state->curl, CURLOPT_ERRORBUFFER, state->errmsg);
curl_easy_setopt(state->curl, CURLOPT_FAILONERROR, 1);
/* Restrict supported protocols to avoid security issues in the more
* obscure protocols. For example, do not allow POP3/SMTP/IMAP see
* CVE-2013-0249.
*
* Restricting protocols is only supported from 7.19.4 upwards.
*/
#if LIBCURL_VERSION_NUM >= 0x071304
curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
curl_easy_setopt(state->curl, CURLOPT_PROTOCOLS, PROTOCOLS);
curl_easy_setopt(state->curl, CURLOPT_REDIR_PROTOCOLS, PROTOCOLS);
#endif
#ifdef DEBUG_VERBOSE
curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
curl_easy_setopt(state->curl, CURLOPT_VERBOSE, 1);
#endif
}
has_curl:
state->s = s;
@@ -433,50 +391,43 @@ static void curl_clean_state(CURLState *s)
static void curl_parse_filename(const char *filename, QDict *options,
Error **errp)
{
qdict_put(options, CURL_BLOCK_OPT_URL, qstring_from_str(filename));
}
static void curl_detach_aio_context(BlockDriverState *bs)
{
BDRVCURLState *s = bs->opaque;
int i;
#define RA_OPTSTR ":readahead="
char *file;
char *ra;
const char *ra_val;
int parse_state = 0;
for (i = 0; i < CURL_NUM_STATES; i++) {
if (s->states[i].in_use) {
curl_clean_state(&s->states[i]);
file = g_strdup(filename);
/* Parse a trailing ":readahead=#:" param, if present. */
ra = file + strlen(file) - 1;
while (ra >= file) {
if (parse_state == 0) {
if (*ra == ':') {
parse_state++;
} else {
break;
}
} else if (parse_state == 1) {
if (*ra > '9' || *ra < '0') {
char *opt_start = ra - strlen(RA_OPTSTR) + 1;
if (opt_start > file &&
strncmp(opt_start, RA_OPTSTR, strlen(RA_OPTSTR)) == 0) {
ra_val = ra + 1;
ra -= strlen(RA_OPTSTR) - 1;
*ra = '\0';
qdict_put(options, "readahead", qstring_from_str(ra_val));
}
break;
}
}
if (s->states[i].curl) {
curl_easy_cleanup(s->states[i].curl);
s->states[i].curl = NULL;
}
g_free(s->states[i].orig_buf);
s->states[i].orig_buf = NULL;
}
if (s->multi) {
curl_multi_cleanup(s->multi);
s->multi = NULL;
ra--;
}
timer_del(&s->timer);
}
qdict_put(options, "url", qstring_from_str(file));
static void curl_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVCURLState *s = bs->opaque;
aio_timer_init(new_context, &s->timer,
QEMU_CLOCK_REALTIME, SCALE_NS,
curl_multi_timeout_do, s);
assert(!s->multi);
s->multi = curl_multi_init();
s->aio_context = new_context;
curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
#ifdef NEED_CURL_TIMER_CALLBACK
curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
#endif
g_free(file);
}
static QemuOptsList runtime_opts = {
@@ -484,30 +435,15 @@ static QemuOptsList runtime_opts = {
.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
.desc = {
{
.name = CURL_BLOCK_OPT_URL,
.name = "url",
.type = QEMU_OPT_STRING,
.help = "URL to open",
},
{
.name = CURL_BLOCK_OPT_READAHEAD,
.name = "readahead",
.type = QEMU_OPT_SIZE,
.help = "Readahead size",
},
{
.name = CURL_BLOCK_OPT_SSLVERIFY,
.type = QEMU_OPT_BOOL,
.help = "Verify SSL certificate"
},
{
.name = CURL_BLOCK_OPT_TIMEOUT,
.type = QEMU_OPT_NUMBER,
.help = "Curl timeout"
},
{
.name = CURL_BLOCK_OPT_COOKIE,
.type = QEMU_OPT_STRING,
.help = "Pass the cookie or list of cookies with each request"
},
{ /* end of list */ }
},
};
@@ -520,7 +456,6 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
QemuOpts *opts;
Error *local_err = NULL;
const char *file;
const char *cookie;
double d;
static int inited = 0;
@@ -537,27 +472,14 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
goto out_noclean;
}
s->readahead_size = qemu_opt_get_size(opts, CURL_BLOCK_OPT_READAHEAD,
READ_AHEAD_DEFAULT);
s->readahead_size = qemu_opt_get_size(opts, "readahead", READ_AHEAD_SIZE);
if ((s->readahead_size & 0x1ff) != 0) {
error_setg(errp, "HTTP_READAHEAD_SIZE %zd is not a multiple of 512",
s->readahead_size);
goto out_noclean;
}
s->timeout = qemu_opt_get_number(opts, CURL_BLOCK_OPT_TIMEOUT,
CURL_TIMEOUT_DEFAULT);
if (s->timeout > CURL_TIMEOUT_MAX) {
error_setg(errp, "timeout parameter is too large or negative");
goto out_noclean;
}
s->sslverify = qemu_opt_get_bool(opts, CURL_BLOCK_OPT_SSLVERIFY, true);
cookie = qemu_opt_get(opts, CURL_BLOCK_OPT_COOKIE);
s->cookie = g_strdup(cookie);
file = qemu_opt_get(opts, CURL_BLOCK_OPT_URL);
file = qemu_opt_get(opts, "url");
if (file == NULL) {
error_setg(errp, "curl block driver requires an 'url' option");
goto out_noclean;
@@ -569,9 +491,8 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
}
DPRINTF("CURL: Opening %s\n", file);
s->aio_context = bdrv_get_aio_context(bs);
s->url = g_strdup(file);
state = curl_init_state(bs, s);
state = curl_init_state(s);
if (!state)
goto out_noclean;
@@ -602,31 +523,49 @@ static int curl_open(BlockDriverState *bs, QDict *options, int flags,
curl_easy_cleanup(state->curl);
state->curl = NULL;
curl_attach_aio_context(bs, bdrv_get_aio_context(bs));
aio_timer_init(bdrv_get_aio_context(bs), &s->timer,
QEMU_CLOCK_REALTIME, SCALE_NS,
curl_multi_timeout_do, s);
// Now we know the file exists and its size, so let's
// initialize the multi interface!
s->multi = curl_multi_init();
curl_multi_setopt(s->multi, CURLMOPT_SOCKETDATA, s);
curl_multi_setopt(s->multi, CURLMOPT_SOCKETFUNCTION, curl_sock_cb);
#ifdef NEED_CURL_TIMER_CALLBACK
curl_multi_setopt(s->multi, CURLMOPT_TIMERDATA, s);
curl_multi_setopt(s->multi, CURLMOPT_TIMERFUNCTION, curl_timer_cb);
#endif
curl_multi_do(s);
qemu_opts_del(opts);
return 0;
out:
error_setg(errp, "CURL: Error opening file: %s", state->errmsg);
fprintf(stderr, "CURL: Error opening file: %s\n", state->errmsg);
curl_easy_cleanup(state->curl);
state->curl = NULL;
out_noclean:
g_free(s->cookie);
g_free(s->url);
qemu_opts_del(opts);
return -EINVAL;
}
static void curl_aio_cancel(BlockDriverAIOCB *blockacb)
{
// Do we have to implement canceling? Seems to work without...
}
static const AIOCBInfo curl_aiocb_info = {
.aiocb_size = sizeof(CURLAIOCB),
.cancel = curl_aio_cancel,
};
static void curl_readv_bh_cb(void *p)
{
CURLState *state;
int running;
CURLAIOCB *acb = p;
BDRVCURLState *s = acb->common.bs->opaque;
@@ -641,7 +580,7 @@ static void curl_readv_bh_cb(void *p)
// we can just call the callback and be done.
switch (curl_find_buf(s, start, acb->nb_sectors * SECTOR_SIZE, acb)) {
case FIND_RET_OK:
qemu_aio_unref(acb);
qemu_aio_release(acb);
// fall through
case FIND_RET_WAIT:
return;
@@ -650,10 +589,10 @@ static void curl_readv_bh_cb(void *p)
}
// No cache found, so let's start a new request
state = curl_init_state(acb->common.bs, s);
state = curl_init_state(s);
if (!state) {
acb->common.cb(acb->common.opaque, -EIO);
qemu_aio_unref(acb);
qemu_aio_release(acb);
return;
}
@@ -661,17 +600,12 @@ static void curl_readv_bh_cb(void *p)
acb->end = (acb->nb_sectors * SECTOR_SIZE);
state->buf_off = 0;
g_free(state->orig_buf);
if (state->orig_buf)
g_free(state->orig_buf);
state->buf_start = start;
state->buf_len = acb->end + s->readahead_size;
end = MIN(start + state->buf_len, s->len) - 1;
state->orig_buf = g_try_malloc(state->buf_len);
if (state->buf_len && state->orig_buf == NULL) {
curl_clean_state(state);
acb->common.cb(acb->common.opaque, -ENOMEM);
qemu_aio_unref(acb);
return;
}
state->orig_buf = g_malloc(state->buf_len);
state->acb[0] = acb;
snprintf(state->range, 127, "%zd-%zd", start, end);
@@ -680,14 +614,13 @@ static void curl_readv_bh_cb(void *p)
curl_easy_setopt(state->curl, CURLOPT_RANGE, state->range);
curl_multi_add_handle(s->multi, state->curl);
curl_multi_do(s);
/* Tell curl it needs to kick things off */
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
}
static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,
static BlockDriverAIOCB *curl_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
CURLAIOCB *acb;
@@ -697,7 +630,7 @@ static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
acb->bh = aio_bh_new(bdrv_get_aio_context(bs), curl_readv_bh_cb, acb);
acb->bh = qemu_bh_new(curl_readv_bh_cb, acb);
qemu_bh_schedule(acb->bh);
return &acb->common;
}
@@ -705,11 +638,26 @@ static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,
static void curl_close(BlockDriverState *bs)
{
BDRVCURLState *s = bs->opaque;
int i;
DPRINTF("CURL: Close\n");
curl_detach_aio_context(bs);
for (i=0; i<CURL_NUM_STATES; i++) {
if (s->states[i].in_use)
curl_clean_state(&s->states[i]);
if (s->states[i].curl) {
curl_easy_cleanup(s->states[i].curl);
s->states[i].curl = NULL;
}
if (s->states[i].orig_buf) {
g_free(s->states[i].orig_buf);
s->states[i].orig_buf = NULL;
}
}
if (s->multi)
curl_multi_cleanup(s->multi);
timer_del(&s->timer);
g_free(s->cookie);
g_free(s->url);
}
@@ -720,83 +668,68 @@ static int64_t curl_getlength(BlockDriverState *bs)
}
static BlockDriver bdrv_http = {
.format_name = "http",
.protocol_name = "http",
.format_name = "http",
.protocol_name = "http",
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.bdrv_aio_readv = curl_aio_readv,
.bdrv_detach_aio_context = curl_detach_aio_context,
.bdrv_attach_aio_context = curl_attach_aio_context,
.bdrv_aio_readv = curl_aio_readv,
};
static BlockDriver bdrv_https = {
.format_name = "https",
.protocol_name = "https",
.format_name = "https",
.protocol_name = "https",
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.bdrv_aio_readv = curl_aio_readv,
.bdrv_detach_aio_context = curl_detach_aio_context,
.bdrv_attach_aio_context = curl_attach_aio_context,
.bdrv_aio_readv = curl_aio_readv,
};
static BlockDriver bdrv_ftp = {
.format_name = "ftp",
.protocol_name = "ftp",
.format_name = "ftp",
.protocol_name = "ftp",
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.bdrv_aio_readv = curl_aio_readv,
.bdrv_detach_aio_context = curl_detach_aio_context,
.bdrv_attach_aio_context = curl_attach_aio_context,
.bdrv_aio_readv = curl_aio_readv,
};
static BlockDriver bdrv_ftps = {
.format_name = "ftps",
.protocol_name = "ftps",
.format_name = "ftps",
.protocol_name = "ftps",
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.bdrv_aio_readv = curl_aio_readv,
.bdrv_detach_aio_context = curl_detach_aio_context,
.bdrv_attach_aio_context = curl_attach_aio_context,
.bdrv_aio_readv = curl_aio_readv,
};
static BlockDriver bdrv_tftp = {
.format_name = "tftp",
.protocol_name = "tftp",
.format_name = "tftp",
.protocol_name = "tftp",
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.instance_size = sizeof(BDRVCURLState),
.bdrv_parse_filename = curl_parse_filename,
.bdrv_file_open = curl_open,
.bdrv_close = curl_close,
.bdrv_getlength = curl_getlength,
.bdrv_aio_readv = curl_aio_readv,
.bdrv_detach_aio_context = curl_detach_aio_context,
.bdrv_attach_aio_context = curl_attach_aio_context,
.bdrv_aio_readv = curl_aio_readv,
};
static void curl_block_init(void)

View File

@@ -248,8 +248,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
offset += 8;
if (s->sectorcounts[i] > DMG_SECTORCOUNTS_MAX) {
error_report("sector count %" PRIu64 " for chunk %" PRIu32
" is larger than max (%u)",
error_report("sector count %" PRIu64 " for chunk %u is "
"larger than max (%u)",
s->sectorcounts[i], i, DMG_SECTORCOUNTS_MAX);
ret = -EINVAL;
goto fail;
@@ -269,8 +269,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
offset += 8;
if (s->lengths[i] > DMG_LENGTHS_MAX) {
error_report("length %" PRIu64 " for chunk %" PRIu32
" is larger than max (%u)",
error_report("length %" PRIu64 " for chunk %u is larger "
"than max (%u)",
s->lengths[i], i, DMG_LENGTHS_MAX);
ret = -EINVAL;
goto fail;
@@ -284,15 +284,8 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
}
/* initialize zlib engine */
s->compressed_chunk = qemu_try_blockalign(bs->file,
max_compressed_size + 1);
s->uncompressed_chunk = qemu_try_blockalign(bs->file,
512 * max_sectors_per_chunk);
if (s->compressed_chunk == NULL || s->uncompressed_chunk == NULL) {
ret = -ENOMEM;
goto fail;
}
s->compressed_chunk = g_malloc(max_compressed_size + 1);
s->uncompressed_chunk = g_malloc(512 * max_sectors_per_chunk);
if (inflateInit(&s->zstream) != Z_OK) {
ret = -EINVAL;
goto fail;
@@ -309,8 +302,8 @@ fail:
g_free(s->lengths);
g_free(s->sectors);
g_free(s->sectorcounts);
qemu_vfree(s->compressed_chunk);
qemu_vfree(s->uncompressed_chunk);
g_free(s->compressed_chunk);
g_free(s->uncompressed_chunk);
return ret;
}
@@ -433,8 +426,8 @@ static void dmg_close(BlockDriverState *bs)
g_free(s->lengths);
g_free(s->sectors);
g_free(s->sectorcounts);
qemu_vfree(s->compressed_chunk);
qemu_vfree(s->uncompressed_chunk);
g_free(s->compressed_chunk);
g_free(s->uncompressed_chunk);
inflateEnd(&s->zstream);
}

View File

@@ -16,7 +16,6 @@ typedef struct GlusterAIOCB {
int ret;
QEMUBH *bh;
Coroutine *coroutine;
AioContext *aio_context;
} GlusterAIOCB;
typedef struct BDRVGlusterState {
@@ -208,11 +207,6 @@ static struct glfs *qemu_gluster_init(GlusterConf *gconf, const char *filename,
"volume=%s image=%s transport=%s", gconf->server,
gconf->port, gconf->volname, gconf->image,
gconf->transport);
/* glfs_init sometimes doesn't set errno although docs suggest that */
if (errno == 0)
errno = EINVAL;
goto out;
}
return glfs;
@@ -250,7 +244,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
acb->ret = -EIO; /* Partial read/write - fail it */
}
acb->bh = aio_bh_new(acb->aio_context, qemu_gluster_complete_aio, acb);
acb->bh = qemu_bh_new(qemu_gluster_complete_aio, acb);
qemu_bh_schedule(acb->bh);
}
@@ -291,7 +285,7 @@ static int qemu_gluster_open(BlockDriverState *bs, QDict *options,
BDRVGlusterState *s = bs->opaque;
int open_flags = 0;
int ret = 0;
GlusterConf *gconf = g_new0(GlusterConf, 1);
GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
QemuOpts *opts;
Error *local_err = NULL;
const char *filename;
@@ -351,12 +345,12 @@ static int qemu_gluster_reopen_prepare(BDRVReopenState *state,
assert(state != NULL);
assert(state->bs != NULL);
state->opaque = g_new0(BDRVGlusterReopenState, 1);
state->opaque = g_malloc0(sizeof(BDRVGlusterReopenState));
reop_s = state->opaque;
qemu_gluster_parse_flags(state->flags, &open_flags);
gconf = g_new0(GlusterConf, 1);
gconf = g_malloc0(sizeof(GlusterConf));
reop_s->glfs = qemu_gluster_init(gconf, state->bs->filename, errp);
if (reop_s->glfs == NULL) {
@@ -437,7 +431,6 @@ static coroutine_fn int qemu_gluster_co_write_zeroes(BlockDriverState *bs,
acb->size = size;
acb->ret = 0;
acb->coroutine = qemu_coroutine_self();
acb->aio_context = bdrv_get_aio_context(bs);
ret = glfs_zerofill_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
if (ret < 0) {
@@ -478,37 +471,39 @@ static inline int qemu_gluster_zerofill(struct glfs_fd *fd, int64_t offset,
#endif
static int qemu_gluster_create(const char *filename,
QemuOpts *opts, Error **errp)
QEMUOptionParameter *options, Error **errp)
{
struct glfs *glfs;
struct glfs_fd *fd;
int ret = 0;
int prealloc = 0;
int64_t total_size = 0;
char *tmp = NULL;
GlusterConf *gconf = g_new0(GlusterConf, 1);
GlusterConf *gconf = g_malloc0(sizeof(GlusterConf));
glfs = qemu_gluster_init(gconf, filename, errp);
if (!glfs) {
ret = -errno;
ret = -EINVAL;
goto out;
}
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
tmp = qemu_opt_get_del(opts, BLOCK_OPT_PREALLOC);
if (!tmp || !strcmp(tmp, "off")) {
prealloc = 0;
} else if (!strcmp(tmp, "full") &&
gluster_supports_zerofill()) {
prealloc = 1;
} else {
error_setg(errp, "Invalid preallocation mode: '%s'"
" or GlusterFS doesn't support zerofill API",
tmp);
ret = -EINVAL;
goto out;
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n / BDRV_SECTOR_SIZE;
} else if (!strcmp(options->name, BLOCK_OPT_PREALLOC)) {
if (!options->value.s || !strcmp(options->value.s, "off")) {
prealloc = 0;
} else if (!strcmp(options->value.s, "full") &&
gluster_supports_zerofill()) {
prealloc = 1;
} else {
error_setg(errp, "Invalid preallocation mode: '%s'"
" or GlusterFS doesn't support zerofill API",
options->value.s);
ret = -EINVAL;
goto out;
}
}
options++;
}
fd = glfs_creat(glfs, gconf->image,
@@ -516,8 +511,9 @@ static int qemu_gluster_create(const char *filename,
if (!fd) {
ret = -errno;
} else {
if (!glfs_ftruncate(fd, total_size)) {
if (prealloc && qemu_gluster_zerofill(fd, 0, total_size)) {
if (!glfs_ftruncate(fd, total_size * BDRV_SECTOR_SIZE)) {
if (prealloc && qemu_gluster_zerofill(fd, 0,
total_size * BDRV_SECTOR_SIZE)) {
ret = -errno;
}
} else {
@@ -529,7 +525,6 @@ static int qemu_gluster_create(const char *filename,
}
}
out:
g_free(tmp);
qemu_gluster_gconf_free(gconf);
if (glfs) {
glfs_fini(glfs);
@@ -549,7 +544,6 @@ static coroutine_fn int qemu_gluster_co_rw(BlockDriverState *bs,
acb->size = size;
acb->ret = 0;
acb->coroutine = qemu_coroutine_self();
acb->aio_context = bdrv_get_aio_context(bs);
if (write) {
ret = glfs_pwritev_async(s->fd, qiov->iov, qiov->niov, offset, 0,
@@ -606,7 +600,6 @@ static coroutine_fn int qemu_gluster_co_flush_to_disk(BlockDriverState *bs)
acb->size = 0;
acb->ret = 0;
acb->coroutine = qemu_coroutine_self();
acb->aio_context = bdrv_get_aio_context(bs);
ret = glfs_fsync_async(s->fd, &gluster_finish_aiocb, acb);
if (ret < 0) {
@@ -635,7 +628,6 @@ static coroutine_fn int qemu_gluster_co_discard(BlockDriverState *bs,
acb->size = 0;
acb->ret = 0;
acb->coroutine = qemu_coroutine_self();
acb->aio_context = bdrv_get_aio_context(bs);
ret = glfs_discard_async(s->fd, offset, size, &gluster_finish_aiocb, acb);
if (ret < 0) {
@@ -696,22 +688,18 @@ static int qemu_gluster_has_zero_init(BlockDriverState *bs)
return 0;
}
static QemuOptsList qemu_gluster_create_opts = {
.name = "qemu-gluster-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qemu_gluster_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_PREALLOC,
.type = QEMU_OPT_STRING,
.help = "Preallocation mode (allowed values: off, full)"
},
{ /* end of list */ }
}
static QEMUOptionParameter qemu_gluster_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_PREALLOC,
.type = OPT_STRING,
.help = "Preallocation mode (allowed values: off, full)"
},
{ NULL }
};
static BlockDriver bdrv_gluster = {
@@ -738,7 +726,7 @@ static BlockDriver bdrv_gluster = {
#ifdef CONFIG_GLUSTERFS_ZEROFILL
.bdrv_co_write_zeroes = qemu_gluster_co_write_zeroes,
#endif
.create_opts = &qemu_gluster_create_opts,
.create_options = qemu_gluster_create_options,
};
static BlockDriver bdrv_gluster_tcp = {
@@ -765,7 +753,7 @@ static BlockDriver bdrv_gluster_tcp = {
#ifdef CONFIG_GLUSTERFS_ZEROFILL
.bdrv_co_write_zeroes = qemu_gluster_co_write_zeroes,
#endif
.create_opts = &qemu_gluster_create_opts,
.create_options = qemu_gluster_create_options,
};
static BlockDriver bdrv_gluster_unix = {
@@ -792,7 +780,7 @@ static BlockDriver bdrv_gluster_unix = {
#ifdef CONFIG_GLUSTERFS_ZEROFILL
.bdrv_co_write_zeroes = qemu_gluster_co_write_zeroes,
#endif
.create_opts = &qemu_gluster_create_opts,
.create_options = qemu_gluster_create_options,
};
static BlockDriver bdrv_gluster_rdma = {
@@ -819,7 +807,7 @@ static BlockDriver bdrv_gluster_rdma = {
#ifdef CONFIG_GLUSTERFS_ZEROFILL
.bdrv_co_write_zeroes = qemu_gluster_co_write_zeroes,
#endif
.create_opts = &qemu_gluster_create_opts,
.create_options = qemu_gluster_create_options,
};
static void bdrv_gluster_init(void)

File diff suppressed because it is too large Load Diff

View File

@@ -25,10 +25,8 @@
*/
#define MAX_EVENTS 128
#define MAX_QUEUED_IO 128
struct qemu_laiocb {
BlockAIOCB common;
BlockDriverAIOCB common;
struct qemu_laio_state *ctx;
struct iocb iocb;
ssize_t ret;
@@ -38,25 +36,9 @@ struct qemu_laiocb {
QLIST_ENTRY(qemu_laiocb) node;
};
typedef struct {
struct iocb *iocbs[MAX_QUEUED_IO];
int plugged;
unsigned int size;
unsigned int idx;
} LaioQueue;
struct qemu_laio_state {
io_context_t ctx;
EventNotifier e;
/* io queue for submit at batch */
LaioQueue io_q;
/* I/O completion processing */
QEMUBH *completion_bh;
struct io_event events[MAX_EVENTS];
int event_idx;
int event_max;
};
static inline ssize_t io_event_ret(struct io_event *ev)
@@ -85,167 +67,77 @@ static void qemu_laio_process_completion(struct qemu_laio_state *s,
ret = -EINVAL;
}
}
}
laiocb->common.cb(laiocb->common.opaque, ret);
qemu_aio_unref(laiocb);
}
/* The completion BH fetches completed I/O requests and invokes their
* callbacks.
*
* The function is somewhat tricky because it supports nested event loops, for
* example when a request callback invokes aio_poll(). In order to do this,
* the completion events array and index are kept in qemu_laio_state. The BH
* reschedules itself as long as there are completions pending so it will
* either be called again in a nested event loop or will be called after all
* events have been completed. When there are no events left to complete, the
* BH returns without rescheduling.
*/
static void qemu_laio_completion_bh(void *opaque)
{
struct qemu_laio_state *s = opaque;
/* Fetch more completion events when empty */
if (s->event_idx == s->event_max) {
do {
struct timespec ts = { 0 };
s->event_max = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS,
s->events, &ts);
} while (s->event_max == -EINTR);
s->event_idx = 0;
if (s->event_max <= 0) {
s->event_max = 0;
return; /* no more events */
}
laiocb->common.cb(laiocb->common.opaque, ret);
}
/* Reschedule so nested event loops see currently pending completions */
qemu_bh_schedule(s->completion_bh);
/* Process completion events */
while (s->event_idx < s->event_max) {
struct iocb *iocb = s->events[s->event_idx].obj;
struct qemu_laiocb *laiocb =
container_of(iocb, struct qemu_laiocb, iocb);
laiocb->ret = io_event_ret(&s->events[s->event_idx]);
s->event_idx++;
qemu_laio_process_completion(s, laiocb);
}
qemu_aio_release(laiocb);
}
static void qemu_laio_completion_cb(EventNotifier *e)
{
struct qemu_laio_state *s = container_of(e, struct qemu_laio_state, e);
if (event_notifier_test_and_clear(&s->e)) {
qemu_bh_schedule(s->completion_bh);
while (event_notifier_test_and_clear(&s->e)) {
struct io_event events[MAX_EVENTS];
struct timespec ts = { 0 };
int nevents, i;
do {
nevents = io_getevents(s->ctx, MAX_EVENTS, MAX_EVENTS, events, &ts);
} while (nevents == -EINTR);
for (i = 0; i < nevents; i++) {
struct iocb *iocb = events[i].obj;
struct qemu_laiocb *laiocb =
container_of(iocb, struct qemu_laiocb, iocb);
laiocb->ret = io_event_ret(&events[i]);
qemu_laio_process_completion(s, laiocb);
}
}
}
static void laio_cancel(BlockAIOCB *blockacb)
static void laio_cancel(BlockDriverAIOCB *blockacb)
{
struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
struct io_event event;
int ret;
if (laiocb->ret != -EINPROGRESS) {
if (laiocb->ret != -EINPROGRESS)
return;
}
/*
* Note that as of Linux 2.6.31 neither the block device code nor any
* filesystem implements cancellation of AIO request.
* Thus the polling loop below is the normal code path.
*/
ret = io_cancel(laiocb->ctx->ctx, &laiocb->iocb, &event);
laiocb->ret = -ECANCELED;
if (ret != 0) {
/* iocb is not cancelled, cb will be called by the event loop later */
if (ret == 0) {
laiocb->ret = -ECANCELED;
return;
}
laiocb->common.cb(laiocb->common.opaque, laiocb->ret);
/*
* We have to wait for the iocb to finish.
*
* The only way to get the iocb status update is by polling the io context.
* We might be able to do this slightly more optimal by removing the
* O_NONBLOCK flag.
*/
while (laiocb->ret == -EINPROGRESS) {
qemu_laio_completion_cb(&laiocb->ctx->e);
}
}
static const AIOCBInfo laio_aiocb_info = {
.aiocb_size = sizeof(struct qemu_laiocb),
.cancel_async = laio_cancel,
.cancel = laio_cancel,
};
static void ioq_init(LaioQueue *io_q)
{
io_q->size = MAX_QUEUED_IO;
io_q->idx = 0;
io_q->plugged = 0;
}
static int ioq_submit(struct qemu_laio_state *s)
{
int ret, i = 0;
int len = s->io_q.idx;
do {
ret = io_submit(s->ctx, len, s->io_q.iocbs);
} while (i++ < 3 && ret == -EAGAIN);
/* empty io queue */
s->io_q.idx = 0;
if (ret < 0) {
i = 0;
} else {
i = ret;
}
for (; i < len; i++) {
struct qemu_laiocb *laiocb =
container_of(s->io_q.iocbs[i], struct qemu_laiocb, iocb);
laiocb->ret = (ret < 0) ? ret : -EIO;
qemu_laio_process_completion(s, laiocb);
}
return ret;
}
static void ioq_enqueue(struct qemu_laio_state *s, struct iocb *iocb)
{
unsigned int idx = s->io_q.idx;
s->io_q.iocbs[idx++] = iocb;
s->io_q.idx = idx;
/* submit immediately if queue is full */
if (idx == s->io_q.size) {
ioq_submit(s);
}
}
void laio_io_plug(BlockDriverState *bs, void *aio_ctx)
{
struct qemu_laio_state *s = aio_ctx;
s->io_q.plugged++;
}
int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug)
{
struct qemu_laio_state *s = aio_ctx;
int ret = 0;
assert(s->io_q.plugged > 0 || !unplug);
if (unplug && --s->io_q.plugged > 0) {
return 0;
}
if (s->io_q.idx > 0) {
ret = ioq_submit(s);
}
return ret;
}
BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type)
BlockDriverCompletionFunc *cb, void *opaque, int type)
{
struct qemu_laio_state *s = aio_ctx;
struct qemu_laiocb *laiocb;
@@ -276,36 +168,15 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
}
io_set_eventfd(&laiocb->iocb, event_notifier_get_fd(&s->e));
if (!s->io_q.plugged) {
if (io_submit(s->ctx, 1, &iocbs) < 0) {
goto out_free_aiocb;
}
} else {
ioq_enqueue(s, iocbs);
}
if (io_submit(s->ctx, 1, &iocbs) < 0)
goto out_free_aiocb;
return &laiocb->common;
out_free_aiocb:
qemu_aio_unref(laiocb);
qemu_aio_release(laiocb);
return NULL;
}
void laio_detach_aio_context(void *s_, AioContext *old_context)
{
struct qemu_laio_state *s = s_;
aio_set_event_notifier(old_context, &s->e, NULL);
qemu_bh_delete(s->completion_bh);
}
void laio_attach_aio_context(void *s_, AioContext *new_context)
{
struct qemu_laio_state *s = s_;
s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
aio_set_event_notifier(new_context, &s->e, qemu_laio_completion_cb);
}
void *laio_init(void)
{
struct qemu_laio_state *s;
@@ -319,7 +190,7 @@ void *laio_init(void)
goto out_close_efd;
}
ioq_init(&s->io_q);
qemu_aio_set_event_notifier(&s->e, qemu_laio_completion_cb);
return s;
@@ -329,16 +200,3 @@ out_free_state:
g_free(s);
return NULL;
}
void laio_cleanup(void *s_)
{
struct qemu_laio_state *s = s_;
event_notifier_cleanup(&s->e);
if (io_destroy(s->ctx) != 0) {
fprintf(stderr, "%s: destroy AIO context %p failed\n",
__func__, &s->ctx);
}
g_free(s);
}

View File

@@ -32,12 +32,6 @@ typedef struct MirrorBlockJob {
RateLimit limit;
BlockDriverState *target;
BlockDriverState *base;
/* The name of the graph node to replace */
char *replaces;
/* The BDS to replace */
BlockDriverState *to_replace;
/* Used to block operations on the drive-mirror-replace target */
Error *replace_blocker;
bool is_none_mode;
BlockdevOnError on_source_error, on_target_error;
bool synced;
@@ -45,7 +39,6 @@ typedef struct MirrorBlockJob {
int64_t sector_num;
int64_t granularity;
size_t buf_size;
int64_t bdev_length;
unsigned long *cow_bitmap;
BdrvDirtyBitmap *dirty_bitmap;
HBitmapIter hbi;
@@ -55,7 +48,6 @@ typedef struct MirrorBlockJob {
unsigned long *in_flight_bitmap;
int in_flight;
int sectors_in_flight;
int ret;
} MirrorBlockJob;
@@ -89,7 +81,6 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
trace_mirror_iteration_done(s, op->sector_num, op->nb_sectors, ret);
s->in_flight--;
s->sectors_in_flight -= op->nb_sectors;
iov = op->qiov.iov;
for (i = 0; i < op->qiov.niov; i++) {
MirrorBuffer *buf = (MirrorBuffer *) iov[i].iov_base;
@@ -101,11 +92,8 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
chunk_num = op->sector_num / sectors_per_chunk;
nb_chunks = op->nb_sectors / sectors_per_chunk;
bitmap_clear(s->in_flight_bitmap, chunk_num, nb_chunks);
if (ret >= 0) {
if (s->cow_bitmap) {
bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
}
s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
if (s->cow_bitmap && ret >= 0) {
bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
}
qemu_iovec_destroy(&op->qiov);
@@ -130,7 +118,7 @@ static void mirror_write_complete(void *opaque, int ret)
bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
action = mirror_error_action(s, false, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
s->ret = ret;
}
}
@@ -147,7 +135,7 @@ static void mirror_read_complete(void *opaque, int ret)
bdrv_set_dirty(source, op->sector_num, op->nb_sectors);
action = mirror_error_action(s, true, -ret);
if (action == BLOCK_ERROR_ACTION_REPORT && s->ret >= 0) {
if (action == BDRV_ACTION_REPORT && s->ret >= 0) {
s->ret = ret;
}
@@ -163,7 +151,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
BlockDriverState *source = s->common.bs;
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;
uint64_t delay_ns;
MirrorOp *op;
s->sector_num = hbitmap_iter_next(&s->hbi);
@@ -178,7 +166,7 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
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;
end = s->common.len >> BDRV_SECTOR_BITS;
/* Extend the QEMUIOVector to include all adjacent blocks that will
* be copied in this operation.
@@ -253,6 +241,8 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
next_chunk += added_chunks;
if (!s->synced && s->common.speed) {
delay_ns = ratelimit_calculate_delay(&s->limit, added_sectors);
} else {
delay_ns = 0;
}
} while (delay_ns == 0 && next_sector < end);
@@ -290,7 +280,6 @@ static uint64_t coroutine_fn mirror_iteration(MirrorBlockJob *s)
/* 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);
@@ -321,56 +310,9 @@ static void mirror_drain(MirrorBlockJob *s)
}
}
typedef struct {
int ret;
} MirrorExitData;
static void mirror_exit(BlockJob *job, void *opaque)
{
MirrorBlockJob *s = container_of(job, MirrorBlockJob, common);
MirrorExitData *data = opaque;
AioContext *replace_aio_context = NULL;
if (s->to_replace) {
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
}
if (s->should_complete && data->ret == 0) {
BlockDriverState *to_replace = s->common.bs;
if (s->to_replace) {
to_replace = s->to_replace;
}
if (bdrv_get_flags(s->target) != bdrv_get_flags(to_replace)) {
bdrv_reopen(s->target, bdrv_get_flags(to_replace), NULL);
}
bdrv_swap(s->target, to_replace);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
bdrv_set_backing_hd(s->base, NULL);
bdrv_unref(p);
}
}
if (s->to_replace) {
bdrv_op_unblock_all(s->to_replace, s->replace_blocker);
error_free(s->replace_blocker);
bdrv_unref(s->to_replace);
}
if (replace_aio_context) {
aio_context_release(replace_aio_context);
}
g_free(s->replaces);
bdrv_unref(s->target);
block_job_completed(&s->common, data->ret);
g_free(data);
}
static void coroutine_fn mirror_run(void *opaque)
{
MirrorBlockJob *s = opaque;
MirrorExitData *data;
BlockDriverState *bs = s->common.bs;
int64_t sector_num, end, sectors_per_chunk, length;
uint64_t last_pause_ns;
@@ -383,13 +325,13 @@ static void coroutine_fn mirror_run(void *opaque)
goto immediate_exit;
}
s->bdev_length = bdrv_getlength(bs);
if (s->bdev_length < 0) {
ret = s->bdev_length;
s->common.len = bdrv_getlength(bs);
if (s->common.len < 0) {
ret = s->common.len;
goto immediate_exit;
} else if (s->bdev_length == 0) {
} else if (s->common.len == 0) {
/* Report BLOCK_JOB_READY and wait for complete. */
block_job_event_ready(&s->common);
block_job_ready(&s->common);
s->synced = true;
while (!block_job_is_cancelled(&s->common) && !s->should_complete) {
block_job_yield(&s->common);
@@ -398,7 +340,7 @@ static void coroutine_fn mirror_run(void *opaque)
goto immediate_exit;
}
length = DIV_ROUND_UP(s->bdev_length, s->granularity);
length = (bdrv_getlength(bs) + s->granularity - 1) / s->granularity;
s->in_flight_bitmap = bitmap_new(length);
/* If we have no backing file yet in the destination, we cannot let
@@ -408,23 +350,15 @@ static void coroutine_fn mirror_run(void *opaque)
bdrv_get_backing_filename(s->target, backing_filename,
sizeof(backing_filename));
if (backing_filename[0] && !s->target->backing_hd) {
ret = bdrv_get_info(s->target, &bdi);
if (ret < 0) {
goto immediate_exit;
}
bdrv_get_info(s->target, &bdi);
if (s->granularity < bdi.cluster_size) {
s->buf_size = MAX(s->buf_size, bdi.cluster_size);
s->cow_bitmap = bitmap_new(length);
}
}
end = s->bdev_length / BDRV_SECTOR_SIZE;
s->buf = qemu_try_blockalign(bs, s->buf_size);
if (s->buf == NULL) {
ret = -ENOMEM;
goto immediate_exit;
}
end = s->common.len >> BDRV_SECTOR_BITS;
s->buf = qemu_blockalign(bs, s->buf_size);
sectors_per_chunk = s->granularity >> BDRV_SECTOR_BITS;
mirror_free_init(s);
@@ -463,12 +397,6 @@ static void coroutine_fn mirror_run(void *opaque)
}
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
/* s->common.offset contains the number of bytes already processed so
* far, cnt is the number of dirty sectors remaining and
* s->sectors_in_flight is the number of sectors currently being
* processed; together those are the current total operation length */
s->common.len = s->common.offset +
(cnt + s->sectors_in_flight) * BDRV_SECTOR_SIZE;
/* Note that even when no rate limit is applied we need to yield
* periodically with no pending I/O so that qemu_aio_flush() returns.
@@ -495,8 +423,7 @@ static void coroutine_fn mirror_run(void *opaque)
trace_mirror_before_flush(s);
ret = bdrv_flush(s->target);
if (ret < 0) {
if (mirror_error_action(s, false, -ret) ==
BLOCK_ERROR_ACTION_REPORT) {
if (mirror_error_action(s, false, -ret) == BDRV_ACTION_REPORT) {
goto immediate_exit;
}
} else {
@@ -505,8 +432,9 @@ static void coroutine_fn mirror_run(void *opaque)
* report completion. This way, block-job-cancel will leave
* the target in a consistent state.
*/
s->common.offset = end * BDRV_SECTOR_SIZE;
if (!s->synced) {
block_job_event_ready(&s->common);
block_job_ready(&s->common);
s->synced = true;
}
@@ -526,13 +454,15 @@ static void coroutine_fn mirror_run(void *opaque)
* mirror_populate runs.
*/
trace_mirror_before_drain(s, cnt);
bdrv_drain(bs);
bdrv_drain_all();
cnt = bdrv_get_dirty_count(bs, s->dirty_bitmap);
}
ret = 0;
trace_mirror_before_sleep(s, cnt, s->synced, delay_ns);
if (!s->synced) {
/* Publish progress */
s->common.offset = (end - cnt) * BDRV_SECTOR_SIZE;
block_job_sleep_ns(&s->common, QEMU_CLOCK_REALTIME, delay_ns);
if (block_job_is_cancelled(&s->common)) {
break;
@@ -567,10 +497,21 @@ immediate_exit:
g_free(s->in_flight_bitmap);
bdrv_release_dirty_bitmap(bs, s->dirty_bitmap);
bdrv_iostatus_disable(s->target);
data = g_malloc(sizeof(*data));
data->ret = ret;
block_job_defer_to_main_loop(&s->common, mirror_exit, data);
if (s->should_complete && ret == 0) {
if (bdrv_get_flags(s->target) != bdrv_get_flags(s->common.bs)) {
bdrv_reopen(s->target, bdrv_get_flags(s->common.bs), NULL);
}
bdrv_swap(s->target, s->common.bs);
if (s->common.driver->job_type == BLOCK_JOB_TYPE_COMMIT) {
/* drop the bs loop chain formed by the swap: break the loop then
* trigger the unref from the top one */
BlockDriverState *p = s->base->backing_hd;
s->base->backing_hd = NULL;
bdrv_unref(p);
}
}
bdrv_unref(s->target);
block_job_completed(&s->common, ret);
}
static void mirror_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -603,32 +544,10 @@ static void mirror_complete(BlockJob *job, Error **errp)
return;
}
if (!s->synced) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY,
bdrv_get_device_name(job->bs));
error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
return;
}
/* check the target bs is not blocked and block all operations on it */
if (s->replaces) {
AioContext *replace_aio_context;
s->to_replace = check_to_replace_node(s->replaces, &local_err);
if (!s->to_replace) {
error_propagate(errp, local_err);
return;
}
replace_aio_context = bdrv_get_aio_context(s->to_replace);
aio_context_acquire(replace_aio_context);
error_setg(&s->replace_blocker,
"block device is in use by block-job-complete");
bdrv_op_block_all(s->to_replace, s->replace_blocker);
bdrv_ref(s->to_replace);
aio_context_release(replace_aio_context);
}
s->should_complete = true;
block_job_resume(job);
}
@@ -651,15 +570,14 @@ static const BlockJobDriver commit_active_job_driver = {
};
static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, int64_t granularity,
int64_t buf_size,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockCompletionFunc *cb,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base)
int64_t speed, int64_t granularity,
int64_t buf_size,
BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp,
const BlockJobDriver *driver,
bool is_none_mode, BlockDriverState *base)
{
MirrorBlockJob *s;
@@ -690,7 +608,6 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
return;
}
s->replaces = g_strdup(replaces);
s->on_source_error = on_source_error;
s->on_target_error = on_target_error;
s->target = target;
@@ -699,10 +616,7 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
s->granularity = granularity;
s->buf_size = MAX(buf_size, granularity);
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity, errp);
if (!s->dirty_bitmap) {
return;
}
s->dirty_bitmap = bdrv_create_dirty_bitmap(bs, granularity);
bdrv_set_enable_write_cache(s->target, true);
bdrv_set_on_error(s->target, on_target_error, on_target_error);
bdrv_iostatus_enable(s->target);
@@ -712,11 +626,10 @@ static void mirror_start_job(BlockDriverState *bs, BlockDriverState *target,
}
void mirror_start(BlockDriverState *bs, BlockDriverState *target,
const char *replaces,
int64_t speed, int64_t granularity, int64_t buf_size,
MirrorSyncMode mode, BlockdevOnError on_source_error,
BlockdevOnError on_target_error,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
bool is_none_mode;
@@ -724,8 +637,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
is_none_mode = mode == MIRROR_SYNC_MODE_NONE;
base = mode == MIRROR_SYNC_MODE_TOP ? bs->backing_hd : NULL;
mirror_start_job(bs, target, replaces,
speed, granularity, buf_size,
mirror_start_job(bs, target, speed, granularity, buf_size,
on_source_error, on_target_error, cb, opaque, errp,
&mirror_job_driver, is_none_mode, base);
}
@@ -733,7 +645,7 @@ void mirror_start(BlockDriverState *bs, BlockDriverState *target,
void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
int64_t speed,
BlockdevOnError on_error,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
int64_t length, base_length;
@@ -773,10 +685,10 @@ void commit_active_start(BlockDriverState *bs, BlockDriverState *base,
}
bdrv_ref(base);
mirror_start_job(bs, base, NULL, speed, 0, 0,
mirror_start_job(bs, base, speed, 0, 0,
on_error, on_error, cb, opaque, &local_err,
&commit_active_job_driver, false, base);
if (local_err) {
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
goto error_restore_flags;
}

View File

@@ -49,7 +49,7 @@ static void nbd_teardown_connection(NbdClientSession *client)
shutdown(client->sock, 2);
nbd_recv_coroutines_enter_all(client);
nbd_client_session_detach_aio_context(client);
qemu_aio_set_fd_handler(client->sock, NULL, NULL, NULL);
closesocket(client->sock);
client->sock = -1;
}
@@ -103,14 +103,11 @@ static int nbd_co_send_request(NbdClientSession *s,
struct nbd_request *request,
QEMUIOVector *qiov, int offset)
{
AioContext *aio_context;
int rc, ret;
qemu_co_mutex_lock(&s->send_mutex);
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(s->bs);
aio_set_fd_handler(aio_context, s->sock,
nbd_reply_ready, nbd_restart_write, s);
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
if (qiov) {
if (!s->is_unix) {
socket_set_cork(s->sock, 1);
@@ -129,7 +126,7 @@ static int nbd_co_send_request(NbdClientSession *s,
} else {
rc = nbd_send_request(s->sock, request);
}
aio_set_fd_handler(aio_context, s->sock, nbd_reply_ready, NULL, s);
qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
@@ -338,19 +335,6 @@ int nbd_client_session_co_discard(NbdClientSession *client, int64_t sector_num,
}
void nbd_client_session_detach_aio_context(NbdClientSession *client)
{
aio_set_fd_handler(bdrv_get_aio_context(client->bs), client->sock,
NULL, NULL, NULL);
}
void nbd_client_session_attach_aio_context(NbdClientSession *client,
AioContext *new_context)
{
aio_set_fd_handler(new_context, client->sock,
nbd_reply_ready, NULL, client);
}
void nbd_client_session_close(NbdClientSession *client)
{
struct nbd_request request = {
@@ -397,7 +381,7 @@ int nbd_client_session_init(NbdClientSession *client, BlockDriverState *bs,
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qemu_set_nonblock(sock);
nbd_client_session_attach_aio_context(client, bdrv_get_aio_context(bs));
qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, client);
logout("Established connection with NBD server\n");
return 0;

View File

@@ -47,8 +47,4 @@ int nbd_client_session_co_writev(NbdClientSession *client, int64_t sector_num,
int nbd_client_session_co_readv(NbdClientSession *client, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov);
void nbd_client_session_detach_aio_context(NbdClientSession *client);
void nbd_client_session_attach_aio_context(NbdClientSession *client,
AioContext *new_context);
#endif /* NBD_CLIENT_H */

View File

@@ -31,10 +31,8 @@
#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>
@@ -177,7 +175,7 @@ static void nbd_parse_filename(const char *filename, QDict *options,
InetSocketAddress *addr = NULL;
addr = inet_parse(host_spec, errp);
if (!addr) {
if (error_is_set(errp)) {
goto out;
}
@@ -325,115 +323,46 @@ static int64_t nbd_getlength(BlockDriverState *bs)
return s->client.size;
}
static void nbd_detach_aio_context(BlockDriverState *bs)
{
BDRVNBDState *s = bs->opaque;
nbd_client_session_detach_aio_context(&s->client);
}
static void nbd_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVNBDState *s = bs->opaque;
nbd_client_session_attach_aio_context(&s->client, new_context);
}
static void nbd_refresh_filename(BlockDriverState *bs)
{
QDict *opts = qdict_new();
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")));
if (path && export) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd+unix:///%s?socket=%s", export, path);
} else if (path && !export) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd+unix://?socket=%s", path);
} else if (!path && export && port) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd://%s:%s/%s", host, port, export);
} else if (!path && export && !port) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd://%s/%s", host, export);
} else if (!path && !export && port) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd://%s:%s", host, port);
} else if (!path && !export && !port) {
snprintf(bs->exact_filename, sizeof(bs->exact_filename),
"nbd://%s", host);
}
if (path) {
qdict_put_obj(opts, "path", QOBJECT(qstring_from_str(path)));
} else if (port) {
qdict_put_obj(opts, "host", QOBJECT(qstring_from_str(host)));
qdict_put_obj(opts, "port", QOBJECT(qstring_from_str(port)));
} else {
qdict_put_obj(opts, "host", QOBJECT(qstring_from_str(host)));
}
if (export) {
qdict_put_obj(opts, "export", QOBJECT(qstring_from_str(export)));
}
bs->full_open_options = opts;
}
static BlockDriver bdrv_nbd = {
.format_name = "nbd",
.protocol_name = "nbd",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
.bdrv_detach_aio_context = nbd_detach_aio_context,
.bdrv_attach_aio_context = nbd_attach_aio_context,
.bdrv_refresh_filename = nbd_refresh_filename,
.format_name = "nbd",
.protocol_name = "nbd",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
};
static BlockDriver bdrv_nbd_tcp = {
.format_name = "nbd",
.protocol_name = "nbd+tcp",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
.bdrv_detach_aio_context = nbd_detach_aio_context,
.bdrv_attach_aio_context = nbd_attach_aio_context,
.bdrv_refresh_filename = nbd_refresh_filename,
.format_name = "nbd",
.protocol_name = "nbd+tcp",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
};
static BlockDriver bdrv_nbd_unix = {
.format_name = "nbd",
.protocol_name = "nbd+unix",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
.bdrv_detach_aio_context = nbd_detach_aio_context,
.bdrv_attach_aio_context = nbd_attach_aio_context,
.bdrv_refresh_filename = nbd_refresh_filename,
.format_name = "nbd",
.protocol_name = "nbd+unix",
.instance_size = sizeof(BDRVNBDState),
.bdrv_parse_filename = nbd_parse_filename,
.bdrv_file_open = nbd_open,
.bdrv_co_readv = nbd_co_readv,
.bdrv_co_writev = nbd_co_writev,
.bdrv_close = nbd_close,
.bdrv_co_flush_to_os = nbd_co_flush,
.bdrv_co_discard = nbd_co_discard,
.bdrv_getlength = nbd_getlength,
};
static void bdrv_nbd_init(void)

View File

@@ -40,7 +40,6 @@ typedef struct NFSClient {
struct nfsfh *fh;
int events;
bool has_zero_init;
AioContext *aio_context;
} NFSClient;
typedef struct NFSRPC {
@@ -50,7 +49,6 @@ typedef struct NFSRPC {
struct stat *st;
Coroutine *co;
QEMUBH *bh;
NFSClient *client;
} NFSRPC;
static void nfs_process_read(void *arg);
@@ -60,11 +58,10 @@ static void nfs_set_events(NFSClient *client)
{
int ev = nfs_which_events(client->context);
if (ev != client->events) {
aio_set_fd_handler(client->aio_context,
nfs_get_fd(client->context),
(ev & POLLIN) ? nfs_process_read : NULL,
(ev & POLLOUT) ? nfs_process_write : NULL,
client);
qemu_aio_set_fd_handler(nfs_get_fd(client->context),
(ev & POLLIN) ? nfs_process_read : NULL,
(ev & POLLOUT) ? nfs_process_write : NULL,
client);
}
client->events = ev;
@@ -87,15 +84,13 @@ static void nfs_process_write(void *arg)
static void nfs_co_init_task(NFSClient *client, NFSRPC *task)
{
*task = (NFSRPC) {
.co = qemu_coroutine_self(),
.client = client,
.co = qemu_coroutine_self(),
};
}
static void nfs_co_generic_bh_cb(void *opaque)
{
NFSRPC *task = opaque;
task->complete = 1;
qemu_bh_delete(task->bh);
qemu_coroutine_enter(task->co, NULL);
}
@@ -105,6 +100,7 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
void *private_data)
{
NFSRPC *task = private_data;
task->complete = 1;
task->ret = ret;
if (task->ret > 0 && task->iov) {
if (task->ret <= task->iov->size) {
@@ -120,11 +116,8 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
error_report("NFS Error: %s", nfs_get_error(nfs));
}
if (task->co) {
task->bh = aio_bh_new(task->client->aio_context,
nfs_co_generic_bh_cb, task);
task->bh = qemu_bh_new(nfs_co_generic_bh_cb, task);
qemu_bh_schedule(task->bh);
} else {
task->complete = 1;
}
}
@@ -172,11 +165,7 @@ static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
nfs_co_init_task(client, &task);
buf = g_try_malloc(nb_sectors * BDRV_SECTOR_SIZE);
if (nb_sectors && buf == NULL) {
return -ENOMEM;
}
buf = g_malloc(nb_sectors * BDRV_SECTOR_SIZE);
qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
if (nfs_pwrite_async(client->context, client->fh,
@@ -235,34 +224,13 @@ static QemuOptsList runtime_opts = {
},
};
static void nfs_detach_aio_context(BlockDriverState *bs)
{
NFSClient *client = bs->opaque;
aio_set_fd_handler(client->aio_context,
nfs_get_fd(client->context),
NULL, NULL, NULL);
client->events = 0;
}
static void nfs_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
NFSClient *client = bs->opaque;
client->aio_context = new_context;
nfs_set_events(client);
}
static void nfs_client_close(NFSClient *client)
{
if (client->context) {
if (client->fh) {
nfs_close(client->context, client->fh);
}
aio_set_fd_handler(client->aio_context,
nfs_get_fd(client->context),
NULL, NULL, NULL);
qemu_aio_set_fd_handler(nfs_get_fd(client->context), NULL, NULL, NULL);
nfs_destroy_context(client->context);
}
memset(client, 0, sizeof(NFSClient));
@@ -288,10 +256,6 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
error_setg(errp, "Invalid URL specified");
goto fail;
}
if (!uri->server) {
error_setg(errp, "Invalid URL specified");
goto fail;
}
strp = strrchr(uri->path, '/');
if (strp == NULL) {
error_setg(errp, "Invalid URL specified");
@@ -308,27 +272,17 @@ static int64_t nfs_client_open(NFSClient *client, const char *filename,
qp = query_params_parse(uri->query);
for (i = 0; i < qp->n; i++) {
unsigned long long val;
if (!qp->p[i].value) {
error_setg(errp, "Value for NFS parameter expected: %s",
qp->p[i].name);
goto fail;
}
if (parse_uint_full(qp->p[i].value, &val, 0)) {
error_setg(errp, "Illegal value for NFS parameter: %s",
qp->p[i].name);
goto fail;
}
if (!strcmp(qp->p[i].name, "uid")) {
nfs_set_uid(client->context, val);
} else if (!strcmp(qp->p[i].name, "gid")) {
nfs_set_gid(client->context, val);
} else if (!strcmp(qp->p[i].name, "tcp-syncnt")) {
nfs_set_tcp_syncnt(client->context, val);
#ifdef LIBNFS_FEATURE_READAHEAD
} else if (!strcmp(qp->p[i].name, "readahead")) {
nfs_set_readahead(client->context, val);
#endif
if (!strncmp(qp->p[i].name, "uid", 3)) {
nfs_set_uid(client->context, atoi(qp->p[i].value));
} else if (!strncmp(qp->p[i].name, "gid", 3)) {
nfs_set_gid(client->context, atoi(qp->p[i].value));
} else if (!strncmp(qp->p[i].name, "tcp-syncnt", 10)) {
nfs_set_tcp_syncnt(client->context, atoi(qp->p[i].value));
} else {
error_setg(errp, "Unknown NFS parameter name: %s",
qp->p[i].name);
@@ -387,39 +341,36 @@ static int nfs_file_open(BlockDriverState *bs, QDict *options, int flags,
QemuOpts *opts;
Error *local_err = NULL;
client->aio_context = bdrv_get_aio_context(bs);
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto out;
return -EINVAL;
}
ret = nfs_client_open(client, qemu_opt_get(opts, "filename"),
(flags & BDRV_O_RDWR) ? O_RDWR : O_RDONLY,
errp);
if (ret < 0) {
goto out;
return ret;
}
bs->total_sectors = ret;
ret = 0;
out:
qemu_opts_del(opts);
return ret;
return 0;
}
static int nfs_file_create(const char *url, QemuOpts *opts, Error **errp)
static int nfs_file_create(const char *url, QEMUOptionParameter *options,
Error **errp)
{
int ret = 0;
int64_t total_size = 0;
NFSClient *client = g_new0(NFSClient, 1);
client->aio_context = qemu_get_aio_context();
NFSClient *client = g_malloc0(sizeof(NFSClient));
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
while (options && options->name) {
if (!strcmp(options->name, "size")) {
total_size = options->value.n;
}
options++;
}
ret = nfs_client_open(client, url, O_CREAT, errp);
if (ret < 0) {
@@ -452,7 +403,7 @@ static int64_t nfs_get_allocated_file_size(BlockDriverState *bs)
while (!task.complete) {
nfs_set_events(client);
aio_poll(client->aio_context, true);
qemu_aio_wait();
}
return (task.ret < 0 ? task.ret : st.st_blocks * st.st_blksize);
@@ -465,25 +416,22 @@ static int nfs_file_truncate(BlockDriverState *bs, int64_t offset)
}
static BlockDriver bdrv_nfs = {
.format_name = "nfs",
.protocol_name = "nfs",
.format_name = "nfs",
.protocol_name = "nfs",
.instance_size = sizeof(NFSClient),
.bdrv_needs_filename = true,
.bdrv_has_zero_init = nfs_has_zero_init,
.bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
.bdrv_truncate = nfs_file_truncate,
.instance_size = sizeof(NFSClient),
.bdrv_needs_filename = true,
.bdrv_has_zero_init = nfs_has_zero_init,
.bdrv_get_allocated_file_size = nfs_get_allocated_file_size,
.bdrv_truncate = nfs_file_truncate,
.bdrv_file_open = nfs_file_open,
.bdrv_close = nfs_file_close,
.bdrv_create = nfs_file_create,
.bdrv_file_open = nfs_file_open,
.bdrv_close = nfs_file_close,
.bdrv_create = nfs_file_create,
.bdrv_co_readv = nfs_co_readv,
.bdrv_co_writev = nfs_co_writev,
.bdrv_co_flush_to_disk = nfs_co_flush,
.bdrv_detach_aio_context = nfs_detach_aio_context,
.bdrv_attach_aio_context = nfs_attach_aio_context,
.bdrv_co_readv = nfs_co_readv,
.bdrv_co_writev = nfs_co_writev,
.bdrv_co_flush_to_disk = nfs_co_flush,
};
static void nfs_block_init(void)

View File

@@ -1,168 +0,0 @@
/*
* Null block driver
*
* Authors:
* Fam Zheng <famz@redhat.com>
*
* Copyright (C) 2014 Red Hat, Inc.
*
* 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 "block/block_int.h"
typedef struct {
int64_t length;
} BDRVNullState;
static QemuOptsList runtime_opts = {
.name = "null",
.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
.desc = {
{
.name = "filename",
.type = QEMU_OPT_STRING,
.help = "",
},
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "size of the null block",
},
{ /* end of list */ }
},
};
static int null_file_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
QemuOpts *opts;
BDRVNullState *s = bs->opaque;
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &error_abort);
s->length =
qemu_opt_get_size(opts, BLOCK_OPT_SIZE, 1 << 30);
qemu_opts_del(opts);
return 0;
}
static void null_close(BlockDriverState *bs)
{
}
static int64_t null_getlength(BlockDriverState *bs)
{
BDRVNullState *s = bs->opaque;
return s->length;
}
static coroutine_fn int null_co_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *qiov)
{
return 0;
}
static coroutine_fn int null_co_writev(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *qiov)
{
return 0;
}
static coroutine_fn int null_co_flush(BlockDriverState *bs)
{
return 0;
}
typedef struct {
BlockAIOCB common;
QEMUBH *bh;
} NullAIOCB;
static const AIOCBInfo null_aiocb_info = {
.aiocb_size = sizeof(NullAIOCB),
};
static void null_bh_cb(void *opaque)
{
NullAIOCB *acb = opaque;
acb->common.cb(acb->common.opaque, 0);
qemu_bh_delete(acb->bh);
qemu_aio_unref(acb);
}
static inline BlockAIOCB *null_aio_common(BlockDriverState *bs,
BlockCompletionFunc *cb,
void *opaque)
{
NullAIOCB *acb;
acb = qemu_aio_get(&null_aiocb_info, bs, cb, opaque);
acb->bh = aio_bh_new(bdrv_get_aio_context(bs), null_bh_cb, acb);
qemu_bh_schedule(acb->bh);
return &acb->common;
}
static BlockAIOCB *null_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
return null_aio_common(bs, cb, opaque);
}
static BlockAIOCB *null_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
return null_aio_common(bs, cb, opaque);
}
static BlockAIOCB *null_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb,
void *opaque)
{
return null_aio_common(bs, cb, opaque);
}
static BlockDriver bdrv_null_co = {
.format_name = "null-co",
.protocol_name = "null-co",
.instance_size = sizeof(BDRVNullState),
.bdrv_file_open = null_file_open,
.bdrv_close = null_close,
.bdrv_getlength = null_getlength,
.bdrv_co_readv = null_co_readv,
.bdrv_co_writev = null_co_writev,
.bdrv_co_flush_to_disk = null_co_flush,
};
static BlockDriver bdrv_null_aio = {
.format_name = "null-aio",
.protocol_name = "null-aio",
.instance_size = sizeof(BDRVNullState),
.bdrv_file_open = null_file_open,
.bdrv_close = null_close,
.bdrv_getlength = null_getlength,
.bdrv_aio_readv = null_aio_readv,
.bdrv_aio_writev = null_aio_writev,
.bdrv_aio_flush = null_aio_flush,
};
static void bdrv_null_init(void)
{
bdrv_register(&bdrv_null_co);
bdrv_register(&bdrv_null_aio);
}
block_init(bdrv_null_init);

View File

@@ -30,7 +30,6 @@
/**************************************************************/
#define HEADER_MAGIC "WithoutFreeSpace"
#define HEADER_MAGIC2 "WithouFreSpacExt"
#define HEADER_VERSION 2
#define HEADER_SIZE 64
@@ -42,10 +41,8 @@ struct parallels_header {
uint32_t cylinders;
uint32_t tracks;
uint32_t catalog_entries;
uint64_t nb_sectors;
uint32_t inuse;
uint32_t data_off;
char padding[12];
uint32_t nb_sectors;
char padding[24];
} QEMU_PACKED;
typedef struct BDRVParallelsState {
@@ -55,8 +52,6 @@ typedef struct BDRVParallelsState {
unsigned int catalog_size;
unsigned int tracks;
unsigned int off_multiplier;
} BDRVParallelsState;
static int parallels_probe(const uint8_t *buf, int buf_size, const char *filename)
@@ -64,12 +59,11 @@ static int parallels_probe(const uint8_t *buf, int buf_size, const char *filenam
const struct parallels_header *ph = (const void *)buf;
if (buf_size < HEADER_SIZE)
return 0;
return 0;
if ((!memcmp(ph->magic, HEADER_MAGIC, 16) ||
!memcmp(ph->magic, HEADER_MAGIC2, 16)) &&
(le32_to_cpu(ph->version) == HEADER_VERSION))
return 100;
if (!memcmp(ph->magic, HEADER_MAGIC, 16) &&
(le32_to_cpu(ph->version) == HEADER_VERSION))
return 100;
return 0;
}
@@ -89,19 +83,14 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
goto fail;
}
bs->total_sectors = le64_to_cpu(ph.nb_sectors);
if (memcmp(ph.magic, HEADER_MAGIC, 16) ||
(le32_to_cpu(ph.version) != HEADER_VERSION)) {
error_setg(errp, "Image not in Parallels format");
ret = -EINVAL;
goto fail;
}
if (le32_to_cpu(ph.version) != HEADER_VERSION) {
goto fail_format;
}
if (!memcmp(ph.magic, HEADER_MAGIC, 16)) {
s->off_multiplier = 1;
bs->total_sectors = 0xffffffff & bs->total_sectors;
} else if (!memcmp(ph.magic, HEADER_MAGIC2, 16)) {
s->off_multiplier = le32_to_cpu(ph.tracks);
} else {
goto fail_format;
}
bs->total_sectors = le32_to_cpu(ph.nb_sectors);
s->tracks = le32_to_cpu(ph.tracks);
if (s->tracks == 0) {
@@ -109,11 +98,6 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
ret = -EINVAL;
goto fail;
}
if (s->tracks > INT32_MAX/513) {
error_setg(errp, "Invalid image: Too big cluster");
ret = -EFBIG;
goto fail;
}
s->catalog_size = le32_to_cpu(ph.catalog_entries);
if (s->catalog_size > INT_MAX / 4) {
@@ -121,11 +105,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
ret = -EFBIG;
goto fail;
}
s->catalog_bitmap = g_try_new(uint32_t, s->catalog_size);
if (s->catalog_size && s->catalog_bitmap == NULL) {
ret = -ENOMEM;
goto fail;
}
s->catalog_bitmap = g_malloc(s->catalog_size * 4);
ret = bdrv_pread(bs->file, 64, s->catalog_bitmap, s->catalog_size * 4);
if (ret < 0) {
@@ -133,14 +113,11 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
}
for (i = 0; i < s->catalog_size; i++)
le32_to_cpus(&s->catalog_bitmap[i]);
le32_to_cpus(&s->catalog_bitmap[i]);
qemu_co_mutex_init(&s->lock);
return 0;
fail_format:
error_setg(errp, "Image not in Parallels format");
ret = -EINVAL;
fail:
g_free(s->catalog_bitmap);
return ret;
@@ -155,10 +132,9 @@ static int64_t seek_to_sector(BlockDriverState *bs, int64_t sector_num)
offset = sector_num % s->tracks;
/* not allocated */
if ((index >= s->catalog_size) || (s->catalog_bitmap[index] == 0))
return -1;
return
((uint64_t)s->catalog_bitmap[index] * s->off_multiplier + offset) * 512;
if ((index > s->catalog_size) || (s->catalog_bitmap[index] == 0))
return -1;
return (uint64_t)(s->catalog_bitmap[index] + offset) * 512;
}
static int parallels_read(BlockDriverState *bs, int64_t sector_num,

View File

@@ -28,14 +28,6 @@
#include "qapi-visit.h"
#include "qapi/qmp-output-visitor.h"
#include "qapi/qmp/types.h"
#include "sysemu/block-backend.h"
#ifdef __linux__
#include <linux/fs.h>
#include <sys/ioctl.h>
#ifndef FS_NOCOW_FL
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
#endif
#endif
BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
{
@@ -58,7 +50,6 @@ BlockDeviceInfo *bdrv_block_device_info(BlockDriverState *bs)
}
info->backing_file_depth = bdrv_get_backing_file_depth(bs);
info->detect_zeroes = bs->detect_zeroes;
if (bs->io_limits_enabled) {
ThrottleConfig cfg;
@@ -173,28 +164,19 @@ void bdrv_query_image_info(BlockDriverState *bs,
ImageInfo **p_info,
Error **errp)
{
int64_t size;
uint64_t total_sectors;
const char *backing_filename;
char backing_filename2[1024];
BlockDriverInfo bdi;
int ret;
Error *err = NULL;
ImageInfo *info;
#ifdef __linux__
int fd, attr;
#endif
ImageInfo *info = g_new0(ImageInfo, 1);
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
return;
}
bdrv_get_geometry(bs, &total_sectors);
info = g_new0(ImageInfo, 1);
info->filename = g_strdup(bs->filename);
info->format = g_strdup(bdrv_get_format_name(bs));
info->virtual_size = size;
info->virtual_size = total_sectors * 512;
info->actual_size = bdrv_get_allocated_file_size(bs);
info->has_actual_size = info->actual_size >= 0;
if (bdrv_is_encrypted(bs)) {
@@ -212,18 +194,6 @@ void bdrv_query_image_info(BlockDriverState *bs,
info->format_specific = bdrv_get_specific_info(bs);
info->has_format_specific = info->format_specific != NULL;
#ifdef __linux__
/* get NOCOW info */
fd = qemu_open(bs->filename, O_RDONLY | O_NONBLOCK);
if (fd >= 0) {
if (ioctl(fd, FS_IOC_GETFLAGS, &attr) == 0 && (attr & FS_NOCOW_FL)) {
info->has_nocow = true;
info->nocow = true;
}
qemu_close(fd);
}
#endif
backing_filename = bs->backing_file;
if (backing_filename[0] != '\0') {
info->backing_filename = g_strdup(backing_filename);
@@ -265,22 +235,22 @@ void bdrv_query_image_info(BlockDriverState *bs,
}
/* @p_info will be set only on success. */
static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
Error **errp)
void bdrv_query_info(BlockDriverState *bs,
BlockInfo **p_info,
Error **errp)
{
BlockInfo *info = g_malloc0(sizeof(*info));
BlockDriverState *bs = blk_bs(blk);
BlockDriverState *bs0;
ImageInfo **p_image_info;
Error *local_err = NULL;
info->device = g_strdup(blk_name(blk));
info->device = g_strdup(bs->device_name);
info->type = g_strdup("unknown");
info->locked = blk_dev_is_medium_locked(blk);
info->removable = blk_dev_has_removable_media(blk);
info->locked = bdrv_dev_is_medium_locked(bs);
info->removable = bdrv_dev_has_removable_media(bs);
if (blk_dev_has_removable_media(blk)) {
if (bdrv_dev_has_removable_media(bs)) {
info->has_tray_open = true;
info->tray_open = blk_dev_is_tray_open(blk);
info->tray_open = bdrv_dev_is_tray_open(bs);
}
if (bdrv_iostatus_is_enabled(bs)) {
@@ -322,28 +292,27 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
qapi_free_BlockInfo(info);
}
static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
BlockStats *bdrv_query_stats(const BlockDriverState *bs)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
if (bdrv_get_device_name(bs)[0]) {
if (bs->device_name[0]) {
s->has_device = true;
s->device = g_strdup(bdrv_get_device_name(bs));
s->device = g_strdup(bs->device_name);
}
s->stats = g_malloc0(sizeof(*s->stats));
s->stats->rd_bytes = bs->stats.nr_bytes[BLOCK_ACCT_READ];
s->stats->wr_bytes = bs->stats.nr_bytes[BLOCK_ACCT_WRITE];
s->stats->rd_operations = bs->stats.nr_ops[BLOCK_ACCT_READ];
s->stats->wr_operations = bs->stats.nr_ops[BLOCK_ACCT_WRITE];
s->stats->wr_highest_offset =
bs->stats.wr_highest_sector * BDRV_SECTOR_SIZE;
s->stats->flush_operations = bs->stats.nr_ops[BLOCK_ACCT_FLUSH];
s->stats->wr_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_WRITE];
s->stats->rd_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_READ];
s->stats->flush_total_time_ns = bs->stats.total_time_ns[BLOCK_ACCT_FLUSH];
s->stats->rd_bytes = bs->nr_bytes[BDRV_ACCT_READ];
s->stats->wr_bytes = bs->nr_bytes[BDRV_ACCT_WRITE];
s->stats->rd_operations = bs->nr_ops[BDRV_ACCT_READ];
s->stats->wr_operations = bs->nr_ops[BDRV_ACCT_WRITE];
s->stats->wr_highest_offset = bs->wr_highest_sector * BDRV_SECTOR_SIZE;
s->stats->flush_operations = bs->nr_ops[BDRV_ACCT_FLUSH];
s->stats->wr_total_time_ns = bs->total_time_ns[BDRV_ACCT_WRITE];
s->stats->rd_total_time_ns = bs->total_time_ns[BDRV_ACCT_READ];
s->stats->flush_total_time_ns = bs->total_time_ns[BDRV_ACCT_FLUSH];
if (bs->file) {
s->has_parent = true;
@@ -361,12 +330,12 @@ static BlockStats *bdrv_query_stats(const BlockDriverState *bs)
BlockInfoList *qmp_query_block(Error **errp)
{
BlockInfoList *head = NULL, **p_next = &head;
BlockBackend *blk;
BlockDriverState *bs = NULL;
Error *local_err = NULL;
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
while ((bs = bdrv_next(bs))) {
BlockInfoList *info = g_malloc0(sizeof(*info));
bdrv_query_info(blk, &info->value, &local_err);
bdrv_query_info(bs, &info->value, &local_err);
if (local_err) {
error_propagate(errp, local_err);
goto err;
@@ -390,11 +359,7 @@ BlockStatsList *qmp_query_blockstats(Error **errp)
while ((bs = bdrv_next(bs))) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = bdrv_get_aio_context(bs);
aio_context_acquire(ctx);
info->value = bdrv_query_stats(bs);
aio_context_release(ctx);
*p_next = info;
p_next = &info->next;
@@ -568,11 +533,12 @@ static void dump_qdict(fprintf_function func_fprintf, void *f, int indentation,
void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
ImageInfoSpecific *info_spec)
{
Error *local_err = NULL;
QmpOutputVisitor *ov = qmp_output_visitor_new();
QObject *obj, *data;
visit_type_ImageInfoSpecific(qmp_output_get_visitor(ov), &info_spec, NULL,
&error_abort);
&local_err);
obj = qmp_output_get_qobject(ov);
assert(qobject_type(obj) == QTYPE_QDICT);
data = qdict_get(qobject_to_qdict(obj), "data");
@@ -655,8 +621,4 @@ void bdrv_image_info_dump(fprintf_function func_fprintf, void *f,
func_fprintf(f, "Format specific information:\n");
bdrv_image_info_specific_dump(func_fprintf, f, info->format_specific);
}
if (info->has_nocow && info->nocow) {
func_fprintf(f, "NOCOW flag: set\n");
}
}

View File

@@ -121,10 +121,9 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
}
if (header.version != QCOW_VERSION) {
char version[64];
snprintf(version, sizeof(version), "QCOW version %" PRIu32,
header.version);
snprintf(version, sizeof(version), "QCOW version %d", header.version);
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bdrv_get_device_name(bs), "qcow", version);
bs->device_name, "qcow", version);
ret = -ENOTSUP;
goto fail;
}
@@ -182,12 +181,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
}
s->l1_table_offset = header.l1_table_offset;
s->l1_table = g_try_new(uint64_t, s->l1_size);
if (s->l1_table == NULL) {
error_setg(errp, "Could not allocate memory for L1 table");
ret = -ENOMEM;
goto fail;
}
s->l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
ret = bdrv_pread(bs->file, s->l1_table_offset, s->l1_table,
s->l1_size * sizeof(uint64_t));
@@ -198,16 +192,8 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
for(i = 0;i < s->l1_size; i++) {
be64_to_cpus(&s->l1_table[i]);
}
/* alloc L2 cache (max. 64k * 16 * 8 = 8 MB) */
s->l2_cache =
qemu_try_blockalign(bs->file,
s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
if (s->l2_cache == NULL) {
error_setg(errp, "Could not allocate L2 table cache");
ret = -ENOMEM;
goto fail;
}
/* alloc L2 cache */
s->l2_cache = g_malloc(s->l2_size * L2_CACHE_SIZE * sizeof(uint64_t));
s->cluster_cache = g_malloc(s->cluster_size);
s->cluster_data = g_malloc(s->cluster_size);
s->cluster_cache_offset = -1;
@@ -231,7 +217,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
/* Disable migration when qcow images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"qcow", bdrv_get_device_name(bs), "live migration");
"qcow", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
qemu_co_mutex_init(&s->lock);
@@ -239,7 +225,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
fail:
g_free(s->l1_table);
qemu_vfree(s->l2_cache);
g_free(s->l2_cache);
g_free(s->cluster_cache);
g_free(s->cluster_data);
return ret;
@@ -530,10 +516,7 @@ static coroutine_fn int qcow_co_readv(BlockDriverState *bs, int64_t sector_num,
void *orig_buf;
if (qiov->niov > 1) {
buf = orig_buf = qemu_try_blockalign(bs, qiov->size);
if (buf == NULL) {
return -ENOMEM;
}
buf = orig_buf = qemu_blockalign(bs, qiov->size);
} else {
orig_buf = NULL;
buf = (uint8_t *)qiov->iov->iov_base;
@@ -635,10 +618,7 @@ static coroutine_fn int qcow_co_writev(BlockDriverState *bs, int64_t sector_num,
s->cluster_cache_offset = -1; /* disable compressed cache */
if (qiov->niov > 1) {
buf = orig_buf = qemu_try_blockalign(bs, qiov->size);
if (buf == NULL) {
return -ENOMEM;
}
buf = orig_buf = qemu_blockalign(bs, qiov->size);
qemu_iovec_to_buf(qiov, 0, buf, qiov->size);
} else {
orig_buf = NULL;
@@ -704,7 +684,7 @@ static void qcow_close(BlockDriverState *bs)
BDRVQcowState *s = bs->opaque;
g_free(s->l1_table);
qemu_vfree(s->l2_cache);
g_free(s->l2_cache);
g_free(s->cluster_cache);
g_free(s->cluster_data);
@@ -712,30 +692,35 @@ static void qcow_close(BlockDriverState *bs)
error_free(s->migration_blocker);
}
static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
static int qcow_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int header_size, backing_filename_len, l1_size, shift, i;
QCowHeader header;
uint8_t *tmp;
int64_t total_size = 0;
char *backing_file = NULL;
const char *backing_file = NULL;
int flags = 0;
Error *local_err = NULL;
int ret;
BlockDriverState *qcow_bs;
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ENCRYPT, false)) {
flags |= BLOCK_FLAG_ENCRYPT;
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n / 512;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
backing_file = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_ENCRYPT)) {
flags |= options->value.n ? BLOCK_FLAG_ENCRYPT : 0;
}
options++;
}
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, options, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto cleanup;
return ret;
}
qcow_bs = NULL;
@@ -743,7 +728,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto cleanup;
return ret;
}
ret = bdrv_truncate(qcow_bs, 0);
@@ -754,7 +739,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
memset(&header, 0, sizeof(header));
header.magic = cpu_to_be32(QCOW_MAGIC);
header.version = cpu_to_be32(QCOW_VERSION);
header.size = cpu_to_be64(total_size);
header.size = cpu_to_be64(total_size * 512);
header_size = sizeof(header);
backing_filename_len = 0;
if (backing_file) {
@@ -776,7 +761,7 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
}
header_size = (header_size + 7) & ~7;
shift = header.cluster_bits + header.l2_bits;
l1_size = (total_size + (1LL << shift) - 1) >> shift;
l1_size = ((total_size * 512) + (1LL << shift) - 1) >> shift;
header.l1_table_offset = cpu_to_be64(header_size);
if (flags & BLOCK_FLAG_ENCRYPT) {
@@ -814,8 +799,6 @@ static int qcow_create(const char *filename, QemuOpts *opts, Error **errp)
ret = 0;
exit:
bdrv_unref(qcow_bs);
cleanup:
g_free(backing_file);
return ret;
}
@@ -928,28 +911,24 @@ static int qcow_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
return 0;
}
static QemuOptsList qcow_create_opts = {
.name = "qcow-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qcow_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = QEMU_OPT_STRING,
.help = "File name of a base image"
},
{
.name = BLOCK_OPT_ENCRYPT,
.type = QEMU_OPT_BOOL,
.help = "Encrypt the image",
.def_value_str = "off"
},
{ /* end of list */ }
}
static QEMUOptionParameter qcow_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = OPT_STRING,
.help = "File name of a base image"
},
{
.name = BLOCK_OPT_ENCRYPT,
.type = OPT_FLAG,
.help = "Encrypt the image"
},
{ NULL }
};
static BlockDriver bdrv_qcow = {
@@ -958,10 +937,9 @@ static BlockDriver bdrv_qcow = {
.bdrv_probe = qcow_probe,
.bdrv_open = qcow_open,
.bdrv_close = qcow_close,
.bdrv_reopen_prepare = qcow_reopen_prepare,
.bdrv_create = qcow_create,
.bdrv_reopen_prepare = qcow_reopen_prepare,
.bdrv_create = qcow_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.supports_backing = true,
.bdrv_co_readv = qcow_co_readv,
.bdrv_co_writev = qcow_co_writev,
@@ -972,7 +950,7 @@ static BlockDriver bdrv_qcow = {
.bdrv_write_compressed = qcow_write_compressed,
.bdrv_get_info = qcow_get_info,
.create_opts = &qcow_create_opts,
.create_options = qcow_create_options,
};
static void bdrv_qcow_init(void)

View File

@@ -48,31 +48,15 @@ Qcow2Cache *qcow2_cache_create(BlockDriverState *bs, int num_tables)
Qcow2Cache *c;
int i;
c = g_new0(Qcow2Cache, 1);
c = g_malloc0(sizeof(*c));
c->size = num_tables;
c->entries = g_try_new0(Qcow2CachedTable, num_tables);
if (!c->entries) {
goto fail;
}
c->entries = g_malloc0(sizeof(*c->entries) * num_tables);
for (i = 0; i < c->size; i++) {
c->entries[i].table = qemu_try_blockalign(bs->file, s->cluster_size);
if (c->entries[i].table == NULL) {
goto fail;
}
c->entries[i].table = qemu_blockalign(bs, s->cluster_size);
}
return c;
fail:
if (c->entries) {
for (i = 0; i < c->size; i++) {
qemu_vfree(c->entries[i].table);
}
}
g_free(c->entries);
g_free(c);
return NULL;
}
int qcow2_cache_destroy(BlockDriverState* bs, Qcow2Cache *c)

View File

@@ -42,13 +42,6 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
if (min_size <= s->l1_size)
return 0;
/* Do a sanity check on min_size before trying to calculate new_l1_size
* (this prevents overflows during the while loop for the calculation of
* new_l1_size) */
if (min_size > INT_MAX / sizeof(uint64_t)) {
return -EFBIG;
}
if (exact_size) {
new_l1_size = min_size;
} else {
@@ -72,20 +65,14 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
#endif
new_l1_size2 = sizeof(uint64_t) * new_l1_size;
new_l1_table = qemu_try_blockalign(bs->file,
align_offset(new_l1_size2, 512));
if (new_l1_table == NULL) {
return -ENOMEM;
}
memset(new_l1_table, 0, align_offset(new_l1_size2, 512));
new_l1_table = g_malloc0(align_offset(new_l1_size2, 512));
memcpy(new_l1_table, s->l1_table, s->l1_size * sizeof(uint64_t));
/* write new table (align to cluster) */
BLKDBG_EVENT(bs->file, BLKDBG_L1_GROW_ALLOC_TABLE);
new_l1_table_offset = qcow2_alloc_clusters(bs, new_l1_size2);
if (new_l1_table_offset < 0) {
qemu_vfree(new_l1_table);
g_free(new_l1_table);
return new_l1_table_offset;
}
@@ -119,7 +106,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
if (ret < 0) {
goto fail;
}
qemu_vfree(s->l1_table);
g_free(s->l1_table);
old_l1_table_offset = s->l1_table_offset;
s->l1_table_offset = new_l1_table_offset;
s->l1_table = new_l1_table;
@@ -129,7 +116,7 @@ int qcow2_grow_l1_table(BlockDriverState *bs, uint64_t min_size,
QCOW2_DISCARD_OTHER);
return 0;
fail:
qemu_vfree(new_l1_table);
g_free(new_l1_table);
qcow2_free_clusters(bs, new_l1_table_offset, new_l1_size2,
QCOW2_DISCARD_OTHER);
return ret;
@@ -164,14 +151,12 @@ static int l2_load(BlockDriverState *bs, uint64_t l2_offset,
int qcow2_write_l1_entry(BlockDriverState *bs, int l1_index)
{
BDRVQcowState *s = bs->opaque;
uint64_t buf[L1_ENTRIES_PER_SECTOR] = { 0 };
uint64_t buf[L1_ENTRIES_PER_SECTOR];
int l1_start_index;
int i, ret;
l1_start_index = l1_index & ~(L1_ENTRIES_PER_SECTOR - 1);
for (i = 0; i < L1_ENTRIES_PER_SECTOR && l1_start_index + i < s->l1_size;
i++)
{
for (i = 0; i < L1_ENTRIES_PER_SECTOR; i++) {
buf[i] = cpu_to_be64(s->l1_table[l1_start_index + i]);
}
@@ -380,18 +365,14 @@ static int coroutine_fn copy_sectors(BlockDriverState *bs,
}
iov.iov_len = n * BDRV_SECTOR_SIZE;
iov.iov_base = qemu_try_blockalign(bs, iov.iov_len);
if (iov.iov_base == NULL) {
return -ENOMEM;
}
iov.iov_base = qemu_blockalign(bs, iov.iov_len);
qemu_iovec_init_external(&qiov, &iov, 1);
BLKDBG_EVENT(bs->file, BLKDBG_COW_READ);
if (!bs->drv) {
ret = -ENOMEDIUM;
goto out;
return -ENOMEDIUM;
}
/* Call .bdrv_co_readv() directly instead of using the public block-layer
@@ -488,13 +469,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
goto out;
}
if (offset_into_cluster(s, l2_offset)) {
qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#" PRIx64
" unaligned (L1 index: %#" PRIx64 ")",
l2_offset, l1_index);
return -EIO;
}
/* load the l2 table in memory */
ret = l2_load(bs, l2_offset, &l2_table);
@@ -517,11 +491,8 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
break;
case QCOW2_CLUSTER_ZERO:
if (s->qcow_version < 3) {
qcow2_signal_corruption(bs, true, -1, -1, "Zero cluster entry found"
" in pre-v3 image (L2 offset: %#" PRIx64
", L2 index: %#x)", l2_offset, l2_index);
ret = -EIO;
goto fail;
qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
return -EIO;
}
c = count_contiguous_clusters(nb_clusters, s->cluster_size,
&l2_table[l2_index], QCOW_OFLAG_ZERO);
@@ -537,14 +508,6 @@ int qcow2_get_cluster_offset(BlockDriverState *bs, uint64_t offset,
c = count_contiguous_clusters(nb_clusters, s->cluster_size,
&l2_table[l2_index], QCOW_OFLAG_ZERO);
*cluster_offset &= L2E_OFFSET_MASK;
if (offset_into_cluster(s, *cluster_offset)) {
qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset %#"
PRIx64 " unaligned (L2 offset: %#" PRIx64
", L2 index: %#x)", *cluster_offset,
l2_offset, l2_index);
ret = -EIO;
goto fail;
}
break;
default:
abort();
@@ -561,10 +524,6 @@ out:
*num = nb_available - index_in_cluster;
return ret;
fail:
qcow2_cache_put(bs, s->l2_table_cache, (void **)&l2_table);
return ret;
}
/*
@@ -600,12 +559,6 @@ static int get_cluster_table(BlockDriverState *bs, uint64_t offset,
assert(l1_index < s->l1_size);
l2_offset = s->l1_table[l1_index] & L1E_OFFSET_MASK;
if (offset_into_cluster(s, l2_offset)) {
qcow2_signal_corruption(bs, true, -1, -1, "L2 table offset %#" PRIx64
" unaligned (L1 index: %#" PRIx64 ")",
l2_offset, l1_index);
return -EIO;
}
/* seek the l2 table of the given l2 offset */
@@ -741,11 +694,7 @@ int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m)
trace_qcow2_cluster_link_l2(qemu_coroutine_self(), m->nb_clusters);
assert(m->nb_clusters > 0);
old_cluster = g_try_new(uint64_t, m->nb_clusters);
if (old_cluster == NULL) {
ret = -ENOMEM;
goto err;
}
old_cluster = g_malloc(m->nb_clusters * sizeof(uint64_t));
/* copy content of unmodified sectors */
ret = perform_cow(bs, m, &m->cow_start);
@@ -978,15 +927,6 @@ static int handle_copied(BlockDriverState *bs, uint64_t guest_offset,
bool offset_matches =
(cluster_offset & L2E_OFFSET_MASK) == *host_offset;
if (offset_into_cluster(s, cluster_offset & L2E_OFFSET_MASK)) {
qcow2_signal_corruption(bs, true, -1, -1, "Data cluster offset "
"%#llx unaligned (guest offset: %#" PRIx64
")", cluster_offset & L2E_OFFSET_MASK,
guest_offset);
ret = -EIO;
goto out;
}
if (*host_offset != 0 && !offset_matches) {
*bytes = 0;
ret = 0;
@@ -1018,7 +958,7 @@ out:
/* Only return a host offset if we actually made progress. Otherwise we
* would make requirements for handle_alloc() that it can't fulfill */
if (ret > 0) {
if (ret) {
*host_offset = (cluster_offset & L2E_OFFSET_MASK)
+ offset_into_cluster(s, guest_offset);
}
@@ -1158,17 +1098,6 @@ static int handle_alloc(BlockDriverState *bs, uint64_t guest_offset,
return 0;
}
/* !*host_offset would overwrite the image header and is reserved for "no
* host offset preferred". If 0 was a valid host offset, it'd trigger the
* following overlap check; do that now to avoid having an invalid value in
* *host_offset. */
if (!alloc_cluster_offset) {
ret = qcow2_pre_write_overlap_check(bs, 0, alloc_cluster_offset,
nb_clusters * s->cluster_size);
assert(ret < 0);
goto fail;
}
/*
* Save info needed for meta data update.
*
@@ -1414,7 +1343,7 @@ int qcow2_decompress_cluster(BlockDriverState *bs, uint64_t cluster_offset)
* clusters.
*/
static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
unsigned int nb_clusters, enum qcow2_discard_type type, bool full_discard)
unsigned int nb_clusters, enum qcow2_discard_type type)
{
BDRVQcowState *s = bs->opaque;
uint64_t *l2_table;
@@ -1431,54 +1360,37 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
nb_clusters = MIN(nb_clusters, s->l2_size - l2_index);
for (i = 0; i < nb_clusters; i++) {
uint64_t old_l2_entry;
uint64_t old_offset;
old_l2_entry = be64_to_cpu(l2_table[l2_index + i]);
old_offset = be64_to_cpu(l2_table[l2_index + i]);
/*
* If full_discard is false, make sure that a discarded area reads back
* as zeroes for v3 images (we cannot do it for v2 without actually
* writing a zero-filled buffer). We can skip the operation if the
* cluster is already marked as zero, or if it's unallocated and we
* don't have a backing file.
* Make sure that a discarded area reads back as zeroes for v3 images
* (we cannot do it for v2 without actually writing a zero-filled
* buffer). We can skip the operation if the cluster is already marked
* as zero, or if it's unallocated and we don't have a backing file.
*
* TODO We might want to use bdrv_get_block_status(bs) here, but we're
* holding s->lock, so that doesn't work today.
*
* If full_discard is true, the sector should not read back as zeroes,
* but rather fall through to the backing file.
*/
switch (qcow2_get_cluster_type(old_l2_entry)) {
case QCOW2_CLUSTER_UNALLOCATED:
if (full_discard || !bs->backing_hd) {
continue;
}
break;
if (old_offset & QCOW_OFLAG_ZERO) {
continue;
}
case QCOW2_CLUSTER_ZERO:
if (!full_discard) {
continue;
}
break;
case QCOW2_CLUSTER_NORMAL:
case QCOW2_CLUSTER_COMPRESSED:
break;
default:
abort();
if ((old_offset & L2E_OFFSET_MASK) == 0 && !bs->backing_hd) {
continue;
}
/* First remove L2 entries */
qcow2_cache_entry_mark_dirty(s->l2_table_cache, l2_table);
if (!full_discard && s->qcow_version >= 3) {
if (s->qcow_version >= 3) {
l2_table[l2_index + i] = cpu_to_be64(QCOW_OFLAG_ZERO);
} else {
l2_table[l2_index + i] = cpu_to_be64(0);
}
/* Then decrease the refcount */
qcow2_free_any_clusters(bs, old_l2_entry, 1, type);
qcow2_free_any_clusters(bs, old_offset, 1, type);
}
ret = qcow2_cache_put(bs, s->l2_table_cache, (void**) &l2_table);
@@ -1490,7 +1402,7 @@ static int discard_single_l2(BlockDriverState *bs, uint64_t offset,
}
int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
int nb_sectors, enum qcow2_discard_type type, bool full_discard)
int nb_sectors, enum qcow2_discard_type type)
{
BDRVQcowState *s = bs->opaque;
uint64_t end_offset;
@@ -1513,7 +1425,7 @@ int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
/* Each L2 table is handled by its own loop iteration */
while (nb_clusters > 0) {
ret = discard_single_l2(bs, offset, nb_clusters, type, full_discard);
ret = discard_single_l2(bs, offset, nb_clusters, type);
if (ret < 0) {
goto fail;
}
@@ -1613,14 +1525,15 @@ fail:
* Expands all zero clusters in a specific L1 table (or deallocates them, for
* non-backed non-pre-allocated zero clusters).
*
* l1_entries and *visited_l1_entries are used to keep track of progress for
* status_cb(). l1_entries contains the total number of L1 entries and
* *visited_l1_entries counts all visited L1 entries.
* expanded_clusters is a bitmap where every bit corresponds to one cluster in
* the image file; a bit gets set if the corresponding cluster has been used for
* zero expansion (i.e., has been filled with zeroes and is referenced from an
* L2 table). nb_clusters contains the total cluster count of the image file,
* i.e., the number of bits in expanded_clusters.
*/
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)
int l1_size, uint8_t **expanded_clusters,
uint64_t *nb_clusters)
{
BDRVQcowState *s = bs->opaque;
bool is_active_l1 = (l1_table == s->l1_table);
@@ -1631,23 +1544,15 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
if (!is_active_l1) {
/* inactive L2 tables require a buffer to be stored in when loading
* them from disk */
l2_table = qemu_try_blockalign(bs->file, s->cluster_size);
if (l2_table == NULL) {
return -ENOMEM;
}
l2_table = qemu_blockalign(bs, s->cluster_size);
}
for (i = 0; i < l1_size; i++) {
uint64_t l2_offset = l1_table[i] & L1E_OFFSET_MASK;
bool l2_dirty = false;
int l2_refcount;
if (!l2_offset) {
/* unallocated */
(*visited_l1_entries)++;
if (status_cb) {
status_cb(bs, *visited_l1_entries, l1_entries);
}
continue;
}
@@ -1664,19 +1569,33 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
goto fail;
}
l2_refcount = qcow2_get_refcount(bs, l2_offset >> s->cluster_bits);
if (l2_refcount < 0) {
ret = l2_refcount;
goto fail;
}
for (j = 0; j < s->l2_size; j++) {
uint64_t l2_entry = be64_to_cpu(l2_table[j]);
int64_t offset = l2_entry & L2E_OFFSET_MASK;
int64_t offset = l2_entry & L2E_OFFSET_MASK, cluster_index;
int cluster_type = qcow2_get_cluster_type(l2_entry);
bool preallocated = offset != 0;
if (cluster_type != QCOW2_CLUSTER_ZERO) {
if (cluster_type == QCOW2_CLUSTER_NORMAL) {
cluster_index = offset >> s->cluster_bits;
assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
if ((*expanded_clusters)[cluster_index / 8] &
(1 << (cluster_index % 8))) {
/* Probably a shared L2 table; this cluster was a zero
* cluster which has been expanded, its refcount
* therefore most likely requires an update. */
ret = qcow2_update_cluster_refcount(bs, cluster_index, 1,
QCOW2_DISCARD_NEVER);
if (ret < 0) {
goto fail;
}
/* Since we just increased the refcount, the COPIED flag may
* no longer be set. */
l2_table[j] = cpu_to_be64(l2_entry & ~QCOW_OFLAG_COPIED);
l2_dirty = true;
}
continue;
}
else if (qcow2_get_cluster_type(l2_entry) != QCOW2_CLUSTER_ZERO) {
continue;
}
@@ -1694,19 +1613,6 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
ret = offset;
goto fail;
}
if (l2_refcount > 1) {
/* For shared L2 tables, set the refcount accordingly (it is
* already 1 and needs to be l2_refcount) */
ret = qcow2_update_cluster_refcount(bs,
offset >> s->cluster_bits, l2_refcount - 1,
QCOW2_DISCARD_OTHER);
if (ret < 0) {
qcow2_free_clusters(bs, offset, s->cluster_size,
QCOW2_DISCARD_OTHER);
goto fail;
}
}
}
ret = qcow2_pre_write_overlap_check(bs, 0, offset, s->cluster_size);
@@ -1728,12 +1634,29 @@ static int expand_zero_clusters_in_l1(BlockDriverState *bs, uint64_t *l1_table,
goto fail;
}
if (l2_refcount == 1) {
l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED);
} else {
l2_table[j] = cpu_to_be64(offset);
}
l2_table[j] = cpu_to_be64(offset | QCOW_OFLAG_COPIED);
l2_dirty = true;
cluster_index = offset >> s->cluster_bits;
if (cluster_index >= *nb_clusters) {
uint64_t old_bitmap_size = (*nb_clusters + 7) / 8;
uint64_t new_bitmap_size;
/* The offset may lie beyond the old end of the underlying image
* file for growable files only */
assert(bs->file->growable);
*nb_clusters = size_to_clusters(s, bs->file->total_sectors *
BDRV_SECTOR_SIZE);
new_bitmap_size = (*nb_clusters + 7) / 8;
*expanded_clusters = g_realloc(*expanded_clusters,
new_bitmap_size);
/* clear the newly allocated space */
memset(&(*expanded_clusters)[old_bitmap_size], 0,
new_bitmap_size - old_bitmap_size);
}
assert((cluster_index >= 0) && (cluster_index < *nb_clusters));
(*expanded_clusters)[cluster_index / 8] |= 1 << (cluster_index % 8);
}
if (is_active_l1) {
@@ -1762,11 +1685,6 @@ 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);
}
}
ret = 0;
@@ -1793,25 +1711,21 @@ fail:
* allocation for pre-allocated ones). This is important for downgrading to a
* qcow2 version which doesn't yet support metadata zero clusters.
*/
int qcow2_expand_zero_clusters(BlockDriverState *bs,
BlockDriverAmendStatusCB *status_cb)
int qcow2_expand_zero_clusters(BlockDriverState *bs)
{
BDRVQcowState *s = bs->opaque;
uint64_t *l1_table = NULL;
int64_t l1_entries = 0, visited_l1_entries = 0;
uint64_t nb_clusters;
uint8_t *expanded_clusters;
int ret;
int i, j;
if (status_cb) {
l1_entries = s->l1_size;
for (i = 0; i < s->nb_snapshots; i++) {
l1_entries += s->snapshots[i].l1_size;
}
}
nb_clusters = size_to_clusters(s, bs->file->total_sectors *
BDRV_SECTOR_SIZE);
expanded_clusters = g_malloc0((nb_clusters + 7) / 8);
ret = expand_zero_clusters_in_l1(bs, s->l1_table, s->l1_size,
&visited_l1_entries, l1_entries,
status_cb);
&expanded_clusters, &nb_clusters);
if (ret < 0) {
goto fail;
}
@@ -1845,8 +1759,7 @@ 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);
&expanded_clusters, &nb_clusters);
if (ret < 0) {
goto fail;
}
@@ -1855,6 +1768,7 @@ int qcow2_expand_zero_clusters(BlockDriverState *bs,
ret = 0;
fail:
g_free(expanded_clusters);
g_free(l1_table);
return ret;
}

File diff suppressed because it is too large Load Diff

View File

@@ -58,7 +58,7 @@ int qcow2_read_snapshots(BlockDriverState *bs)
}
offset = s->snapshots_offset;
s->snapshots = g_new0(QCowSnapshot, s->nb_snapshots);
s->snapshots = g_malloc0(s->nb_snapshots * sizeof(QCowSnapshot));
for(i = 0; i < s->nb_snapshots; i++) {
/* Read statically sized part of the snapshot header */
@@ -381,12 +381,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
sn->l1_table_offset = l1_table_offset;
sn->l1_size = s->l1_size;
l1_table = g_try_new(uint64_t, s->l1_size);
if (s->l1_size && l1_table == NULL) {
ret = -ENOMEM;
goto fail;
}
l1_table = g_malloc(s->l1_size * sizeof(uint64_t));
for(i = 0; i < s->l1_size; i++) {
l1_table[i] = cpu_to_be64(s->l1_table[i]);
}
@@ -417,7 +412,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
}
/* Append the new snapshot to the snapshot list */
new_snapshot_list = g_new(QCowSnapshot, s->nb_snapshots + 1);
new_snapshot_list = g_malloc((s->nb_snapshots + 1) * sizeof(QCowSnapshot));
if (s->snapshots) {
memcpy(new_snapshot_list, s->snapshots,
s->nb_snapshots * sizeof(QCowSnapshot));
@@ -441,7 +436,7 @@ int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
qcow2_discard_clusters(bs, qcow2_vm_state_offset(s),
align_offset(sn->vm_state_size, s->cluster_size)
>> BDRV_SECTOR_BITS,
QCOW2_DISCARD_NEVER, false);
QCOW2_DISCARD_NEVER);
#ifdef DEBUG_ALLOC
{
@@ -504,11 +499,7 @@ int qcow2_snapshot_goto(BlockDriverState *bs, const char *snapshot_id)
* Decrease the refcount referenced by the old one only when the L1
* table is overwritten.
*/
sn_l1_table = g_try_malloc0(cur_l1_bytes);
if (cur_l1_bytes && sn_l1_table == NULL) {
ret = -ENOMEM;
goto fail;
}
sn_l1_table = g_malloc0(cur_l1_bytes);
ret = bdrv_pread(bs->file, sn->l1_table_offset, sn_l1_table, sn_l1_bytes);
if (ret < 0) {
@@ -661,7 +652,7 @@ int qcow2_snapshot_list(BlockDriverState *bs, QEMUSnapshotInfo **psn_tab)
return s->nb_snapshots;
}
sn_tab = g_new0(QEMUSnapshotInfo, s->nb_snapshots);
sn_tab = g_malloc0(s->nb_snapshots * sizeof(QEMUSnapshotInfo));
for(i = 0; i < s->nb_snapshots; i++) {
sn_info = sn_tab + i;
sn = s->snapshots + i;
@@ -707,21 +698,17 @@ int qcow2_snapshot_load_tmp(BlockDriverState *bs,
return -EFBIG;
}
new_l1_bytes = sn->l1_size * sizeof(uint64_t);
new_l1_table = qemu_try_blockalign(bs->file,
align_offset(new_l1_bytes, 512));
if (new_l1_table == NULL) {
return -ENOMEM;
}
new_l1_table = g_malloc0(align_offset(new_l1_bytes, 512));
ret = bdrv_pread(bs->file, sn->l1_table_offset, new_l1_table, new_l1_bytes);
if (ret < 0) {
error_setg(errp, "Failed to read l1 table for snapshot");
qemu_vfree(new_l1_table);
g_free(new_l1_table);
return ret;
}
/* Switch the L1 table */
qemu_vfree(s->l1_table);
g_free(s->l1_table);
s->l1_size = sn->l1_size;
s->l1_table_offset = sn->l1_table_offset;

File diff suppressed because it is too large Load Diff

View File

@@ -59,19 +59,15 @@
/* The cluster reads as all zeros */
#define QCOW_OFLAG_ZERO (1ULL << 0)
#define REFCOUNT_SHIFT 1 /* refcount size is 2 bytes */
#define MIN_CLUSTER_BITS 9
#define MAX_CLUSTER_BITS 21
#define MIN_L2_CACHE_SIZE 1 /* cluster */
#define L2_CACHE_SIZE 16
/* Must be at least 4 to cover all cases of refcount table growth */
#define MIN_REFCOUNT_CACHE_SIZE 4 /* clusters */
#define DEFAULT_L2_CACHE_BYTE_SIZE 1048576 /* bytes */
/* The refblock cache needs only a fourth of the L2 cache size to cover as many
* clusters */
#define DEFAULT_L2_REFCOUNT_SIZE_RATIO 4
#define REFCOUNT_CACHE_SIZE 4
#define DEFAULT_CLUSTER_SIZE 65536
@@ -81,7 +77,6 @@
#define QCOW2_OPT_DISCARD_SNAPSHOT "pass-discard-snapshot"
#define QCOW2_OPT_DISCARD_OTHER "pass-discard-other"
#define QCOW2_OPT_OVERLAP "overlap-check"
#define QCOW2_OPT_OVERLAP_TEMPLATE "overlap-check.template"
#define QCOW2_OPT_OVERLAP_MAIN_HEADER "overlap-check.main-header"
#define QCOW2_OPT_OVERLAP_ACTIVE_L1 "overlap-check.active-l1"
#define QCOW2_OPT_OVERLAP_ACTIVE_L2 "overlap-check.active-l2"
@@ -90,9 +85,6 @@
#define QCOW2_OPT_OVERLAP_SNAPSHOT_TABLE "overlap-check.snapshot-table"
#define QCOW2_OPT_OVERLAP_INACTIVE_L1 "overlap-check.inactive-l1"
#define QCOW2_OPT_OVERLAP_INACTIVE_L2 "overlap-check.inactive-l2"
#define QCOW2_OPT_CACHE_SIZE "cache-size"
#define QCOW2_OPT_L2_CACHE_SIZE "l2-cache-size"
#define QCOW2_OPT_REFCOUNT_CACHE_SIZE "refcount-cache-size"
typedef struct QCowHeader {
uint32_t magic;
@@ -221,8 +213,6 @@ typedef struct BDRVQcowState {
int l2_size;
int l1_size;
int l1_vm_state_index;
int refcount_block_bits;
int refcount_block_size;
int csize_shift;
int csize_mask;
uint64_t cluster_offset_mask;
@@ -262,7 +252,6 @@ typedef struct BDRVQcowState {
bool discard_passthrough[QCOW2_DISCARD_MAX];
int overlap_check; /* bitmask of Qcow2MetadataOverlap values */
bool signaled_corruption;
uint64_t incompatible_features;
uint64_t compatible_features;
@@ -479,16 +468,10 @@ int qcow2_mark_corrupt(BlockDriverState *bs);
int qcow2_mark_consistent(BlockDriverState *bs);
int qcow2_update_header(BlockDriverState *bs);
void qcow2_signal_corruption(BlockDriverState *bs, bool fatal, int64_t offset,
int64_t size, const char *message_format, ...)
GCC_FMT_ATTR(5, 6);
/* qcow2-refcount.c functions */
int qcow2_refcount_init(BlockDriverState *bs);
void qcow2_refcount_close(BlockDriverState *bs);
int qcow2_get_refcount(BlockDriverState *bs, int64_t cluster_index);
int qcow2_update_cluster_refcount(BlockDriverState *bs, int64_t cluster_index,
int addend, enum qcow2_discard_type type);
@@ -536,11 +519,10 @@ uint64_t qcow2_alloc_compressed_cluster_offset(BlockDriverState *bs,
int qcow2_alloc_cluster_link_l2(BlockDriverState *bs, QCowL2Meta *m);
int qcow2_discard_clusters(BlockDriverState *bs, uint64_t offset,
int nb_sectors, enum qcow2_discard_type type, bool full_discard);
int nb_sectors, enum qcow2_discard_type type);
int qcow2_zero_clusters(BlockDriverState *bs, uint64_t offset, int nb_sectors);
int qcow2_expand_zero_clusters(BlockDriverState *bs,
BlockDriverAmendStatusCB *status_cb);
int qcow2_expand_zero_clusters(BlockDriverState *bs);
/* qcow2-snapshot.c functions */
int qcow2_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info);

View File

@@ -227,10 +227,8 @@ int qed_check(BDRVQEDState *s, BdrvCheckResult *result, bool fix)
};
int ret;
check.used_clusters = g_try_new0(uint32_t, (check.nclusters + 31) / 32);
if (check.nclusters && check.used_clusters == NULL) {
return -ENOMEM;
}
check.used_clusters = g_malloc0(((check.nclusters + 31) / 32) *
sizeof(check.used_clusters[0]));
check.result->bfi.total_clusters =
(s->header.image_size + s->header.cluster_size - 1) /

View File

@@ -13,7 +13,7 @@
#include "qed.h"
void *gencb_alloc(size_t len, BlockCompletionFunc *cb, void *opaque)
void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque)
{
GenericCB *gencb = g_malloc(len);
gencb->cb = cb;
@@ -24,7 +24,7 @@ void *gencb_alloc(size_t len, BlockCompletionFunc *cb, void *opaque)
void gencb_complete(void *opaque, int ret)
{
GenericCB *gencb = opaque;
BlockCompletionFunc *cb = gencb->cb;
BlockDriverCompletionFunc *cb = gencb->cb;
void *user_opaque = gencb->opaque;
g_free(gencb);

View File

@@ -49,7 +49,7 @@ out:
}
static void qed_read_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDReadTableCB *read_table_cb = gencb_alloc(sizeof(*read_table_cb),
cb, opaque);
@@ -119,7 +119,7 @@ out:
*/
static void qed_write_table(BDRVQEDState *s, uint64_t offset, QEDTable *table,
unsigned int index, unsigned int n, bool flush,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDWriteTableCB *write_table_cb;
unsigned int sector_mask = BDRV_SECTOR_SIZE / sizeof(uint64_t) - 1;
@@ -173,14 +173,14 @@ int qed_read_l1_table_sync(BDRVQEDState *s)
qed_read_table(s, s->header.l1_table_offset,
s->l1_table, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
qemu_aio_wait();
}
return ret;
}
void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L1_UPDATE);
qed_write_table(s, s->header.l1_table_offset,
@@ -194,7 +194,7 @@ int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
qed_write_l1_table(s, index, n, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
qemu_aio_wait();
}
return ret;
@@ -235,7 +235,7 @@ static void qed_read_l2_table_cb(void *opaque, int ret)
}
void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
QEDReadL2TableCB *read_l2_table_cb;
@@ -267,7 +267,7 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset
qed_read_l2_table(s, request, offset, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
qemu_aio_wait();
}
return ret;
@@ -275,7 +275,7 @@ int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request, uint64_t offset
void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BLKDBG_EVENT(s->bs->file, BLKDBG_L2_UPDATE);
qed_write_table(s, request->l2_table->offset,
@@ -289,7 +289,7 @@ int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
qed_write_l2_table(s, request, index, n, flush, qed_sync_cb, &ret);
while (ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(s->bs), true);
qemu_aio_wait();
}
return ret;

View File

@@ -18,8 +18,21 @@
#include "qapi/qmp/qerror.h"
#include "migration/migration.h"
static void qed_aio_cancel(BlockDriverAIOCB *blockacb)
{
QEDAIOCB *acb = (QEDAIOCB *)blockacb;
bool finished = false;
/* Wait for the request to finish */
acb->finished = &finished;
while (!finished) {
qemu_aio_wait();
}
}
static const AIOCBInfo qed_aiocb_info = {
.aiocb_size = sizeof(QEDAIOCB),
.cancel = qed_aio_cancel,
};
static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
@@ -130,7 +143,7 @@ static void qed_write_header_read_cb(void *opaque, int ret)
* This function only updates known header fields in-place and does not affect
* extra data after the QED header.
*/
static void qed_write_header(BDRVQEDState *s, BlockCompletionFunc cb,
static void qed_write_header(BDRVQEDState *s, BlockDriverCompletionFunc cb,
void *opaque)
{
/* We must write full sectors for O_DIRECT but cannot necessarily generate
@@ -360,27 +373,6 @@ static void bdrv_qed_rebind(BlockDriverState *bs)
s->bs = bs;
}
static void bdrv_qed_detach_aio_context(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
qed_cancel_need_check_timer(s);
timer_free(s->need_check_timer);
}
static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVQEDState *s = bs->opaque;
s->need_check_timer = aio_timer_new(new_context,
QEMU_CLOCK_VIRTUAL, SCALE_NS,
qed_need_check_timer_cb, s);
if (s->header.features & QED_F_NEED_CHECK) {
qed_start_need_check_timer(s);
}
}
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
@@ -408,7 +400,7 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
snprintf(buf, sizeof(buf), "%" PRIx64,
s->header.features & ~QED_FEATURE_MASK);
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bdrv_get_device_name(bs), "QED", buf);
bs->device_name, "QED", buf);
return -ENOTSUP;
}
if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
@@ -504,7 +496,8 @@ static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
}
}
bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
s->need_check_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL,
qed_need_check_timer_cb, s);
out:
if (ret) {
@@ -514,11 +507,13 @@ out:
return ret;
}
static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
static int bdrv_qed_refresh_limits(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
bs->bl.write_zeroes_alignment = s->header.cluster_size >> BDRV_SECTOR_BITS;
return 0;
}
/* We have nothing to do for QED reopen, stubs just return
@@ -533,7 +528,8 @@ static void bdrv_qed_close(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
bdrv_qed_detach_aio_context(bs);
qed_cancel_need_check_timer(s);
timer_free(s->need_check_timer);
/* Ensure writes reach stable storage */
bdrv_flush(bs->file);
@@ -551,7 +547,7 @@ static void bdrv_qed_close(BlockDriverState *bs)
static int qed_create(const char *filename, uint32_t cluster_size,
uint64_t image_size, uint32_t table_size,
const char *backing_file, const char *backing_fmt,
QemuOpts *opts, Error **errp)
Error **errp)
{
QEDHeader header = {
.magic = QED_MAGIC,
@@ -570,7 +566,7 @@ static int qed_create(const char *filename, uint32_t cluster_size,
int ret = 0;
BlockDriverState *bs;
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
return ret;
@@ -625,54 +621,53 @@ out:
return ret;
}
static int bdrv_qed_create(const char *filename, QemuOpts *opts, Error **errp)
static int bdrv_qed_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
uint64_t image_size = 0;
uint32_t cluster_size = QED_DEFAULT_CLUSTER_SIZE;
uint32_t table_size = QED_DEFAULT_TABLE_SIZE;
char *backing_file = NULL;
char *backing_fmt = NULL;
int ret;
const char *backing_file = NULL;
const char *backing_fmt = NULL;
image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
backing_fmt = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FMT);
cluster_size = qemu_opt_get_size_del(opts,
BLOCK_OPT_CLUSTER_SIZE,
QED_DEFAULT_CLUSTER_SIZE);
table_size = qemu_opt_get_size_del(opts, BLOCK_OPT_TABLE_SIZE,
QED_DEFAULT_TABLE_SIZE);
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
image_size = options->value.n;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
backing_file = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FMT)) {
backing_fmt = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
if (options->value.n) {
cluster_size = options->value.n;
}
} else if (!strcmp(options->name, BLOCK_OPT_TABLE_SIZE)) {
if (options->value.n) {
table_size = options->value.n;
}
}
options++;
}
if (!qed_is_cluster_size_valid(cluster_size)) {
error_setg(errp, "QED cluster size must be within range [%u, %u] "
"and power of 2",
QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
ret = -EINVAL;
goto finish;
fprintf(stderr, "QED cluster size must be within range [%u, %u] and power of 2\n",
QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
return -EINVAL;
}
if (!qed_is_table_size_valid(table_size)) {
error_setg(errp, "QED table size must be within range [%u, %u] "
"and power of 2",
QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
ret = -EINVAL;
goto finish;
fprintf(stderr, "QED table size must be within range [%u, %u] and power of 2\n",
QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
return -EINVAL;
}
if (!qed_is_image_size_valid(image_size, cluster_size, table_size)) {
error_setg(errp, "QED image size must be a non-zero multiple of "
"cluster size and less than %" PRIu64 " bytes",
qed_max_image_size(cluster_size, table_size));
ret = -EINVAL;
goto finish;
fprintf(stderr, "QED image size must be a non-zero multiple of "
"cluster size and less than %" PRIu64 " bytes\n",
qed_max_image_size(cluster_size, table_size));
return -EINVAL;
}
ret = qed_create(filename, cluster_size, image_size, table_size,
backing_file, backing_fmt, opts, errp);
finish:
g_free(backing_file);
g_free(backing_fmt);
return ret;
return qed_create(filename, cluster_size, image_size, table_size,
backing_file, backing_fmt, errp);
}
typedef struct {
@@ -746,20 +741,18 @@ static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
/**
* Read from the backing file or zero-fill if no backing file
*
* @s: QED state
* @pos: Byte position in device
* @qiov: Destination I/O vector
* @backing_qiov: Possibly shortened copy of qiov, to be allocated here
* @cb: Completion function
* @opaque: User data for completion function
* @s: QED state
* @pos: Byte position in device
* @qiov: Destination I/O vector
* @cb: Completion function
* @opaque: User data for completion function
*
* This function reads qiov->size bytes starting at pos from the backing file.
* If there is no backing file then zeroes are read.
*/
static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
QEMUIOVector *qiov,
QEMUIOVector **backing_qiov,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
uint64_t backing_length = 0;
size_t size;
@@ -791,21 +784,15 @@ static void qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
/* If the read straddles the end of the backing file, shorten it */
size = MIN((uint64_t)backing_length - pos, qiov->size);
assert(*backing_qiov == NULL);
*backing_qiov = g_new(QEMUIOVector, 1);
qemu_iovec_init(*backing_qiov, qiov->niov);
qemu_iovec_concat(*backing_qiov, qiov, 0, size);
BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
bdrv_aio_readv(s->bs->backing_hd, pos / BDRV_SECTOR_SIZE,
*backing_qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
qiov, size / BDRV_SECTOR_SIZE, cb, opaque);
}
typedef struct {
GenericCB gencb;
BDRVQEDState *s;
QEMUIOVector qiov;
QEMUIOVector *backing_qiov;
struct iovec iov;
uint64_t offset;
} CopyFromBackingFileCB;
@@ -822,12 +809,6 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
CopyFromBackingFileCB *copy_cb = opaque;
BDRVQEDState *s = copy_cb->s;
if (copy_cb->backing_qiov) {
qemu_iovec_destroy(copy_cb->backing_qiov);
g_free(copy_cb->backing_qiov);
copy_cb->backing_qiov = NULL;
}
if (ret) {
qed_copy_from_backing_file_cb(copy_cb, ret);
return;
@@ -851,7 +832,7 @@ static void qed_copy_from_backing_file_write(void *opaque, int ret)
*/
static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
uint64_t len, uint64_t offset,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque)
{
CopyFromBackingFileCB *copy_cb;
@@ -865,12 +846,11 @@ static void qed_copy_from_backing_file(BDRVQEDState *s, uint64_t pos,
copy_cb = gencb_alloc(sizeof(*copy_cb), cb, opaque);
copy_cb->s = s;
copy_cb->offset = offset;
copy_cb->backing_qiov = NULL;
copy_cb->iov.iov_base = qemu_blockalign(s->bs, len);
copy_cb->iov.iov_len = len;
qemu_iovec_init_external(&copy_cb->qiov, &copy_cb->iov, 1);
qed_read_backing_file(s, pos, &copy_cb->qiov, &copy_cb->backing_qiov,
qed_read_backing_file(s, pos, &copy_cb->qiov,
qed_copy_from_backing_file_write, copy_cb);
}
@@ -902,15 +882,21 @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
static void qed_aio_complete_bh(void *opaque)
{
QEDAIOCB *acb = opaque;
BlockCompletionFunc *cb = acb->common.cb;
BlockDriverCompletionFunc *cb = acb->common.cb;
void *user_opaque = acb->common.opaque;
int ret = acb->bh_ret;
bool *finished = acb->finished;
qemu_bh_delete(acb->bh);
qemu_aio_unref(acb);
qemu_aio_release(acb);
/* Invoke callback */
cb(user_opaque, ret);
/* Signal cancel completion */
if (finished) {
*finished = true;
}
}
static void qed_aio_complete(QEDAIOCB *acb, int ret)
@@ -931,8 +917,7 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)
/* Arrange for a bh to invoke the completion function */
acb->bh_ret = ret;
acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
qed_aio_complete_bh, acb);
acb->bh = qemu_bh_new(qed_aio_complete_bh, acb);
qemu_bh_schedule(acb->bh);
/* Start next allocating write request waiting behind this one. Note that
@@ -1064,7 +1049,7 @@ static void qed_aio_write_main(void *opaque, int ret)
BDRVQEDState *s = acb_to_s(acb);
uint64_t offset = acb->cur_cluster +
qed_offset_into_cluster(s, acb->cur_pos);
BlockCompletionFunc *next_fn;
BlockDriverCompletionFunc *next_fn;
trace_qed_aio_write_main(s, acb, ret, offset, acb->cur_qiov.size);
@@ -1164,7 +1149,7 @@ static void qed_aio_write_zero_cluster(void *opaque, int ret)
static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
{
BDRVQEDState *s = acb_to_s(acb);
BlockCompletionFunc *cb;
BlockDriverCompletionFunc *cb;
/* Cancel timer when the first allocating request comes in */
if (QSIMPLEQ_EMPTY(&s->allocating_write_reqs)) {
@@ -1221,11 +1206,7 @@ static void qed_aio_write_inplace(QEDAIOCB *acb, uint64_t offset, size_t len)
struct iovec *iov = acb->qiov->iov;
if (!iov->iov_base) {
iov->iov_base = qemu_try_blockalign(acb->common.bs, iov->iov_len);
if (iov->iov_base == NULL) {
qed_aio_complete(acb, -ENOMEM);
return;
}
iov->iov_base = qemu_blockalign(acb->common.bs, iov->iov_len);
memset(iov->iov_base, 0, iov->iov_len);
}
}
@@ -1311,7 +1292,7 @@ static void qed_aio_read_data(void *opaque, int ret,
return;
} else if (ret != QED_CLUSTER_FOUND) {
qed_read_backing_file(s, acb->cur_pos, &acb->cur_qiov,
&acb->backing_qiov, qed_aio_next_io, acb);
qed_aio_next_io, acb);
return;
}
@@ -1337,12 +1318,6 @@ static void qed_aio_next_io(void *opaque, int ret)
trace_qed_aio_next_io(s, acb, ret, acb->cur_pos + acb->cur_qiov.size);
if (acb->backing_qiov) {
qemu_iovec_destroy(acb->backing_qiov);
g_free(acb->backing_qiov);
acb->backing_qiov = NULL;
}
/* Handle I/O error */
if (ret) {
qed_aio_complete(acb, ret);
@@ -1365,11 +1340,11 @@ static void qed_aio_next_io(void *opaque, int ret)
io_fn, acb);
}
static BlockAIOCB *qed_aio_setup(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb,
void *opaque, int flags)
static BlockDriverAIOCB *qed_aio_setup(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque, int flags)
{
QEDAIOCB *acb = qemu_aio_get(&qed_aiocb_info, bs, cb, opaque);
@@ -1377,11 +1352,11 @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs,
opaque, flags);
acb->flags = flags;
acb->finished = NULL;
acb->qiov = qiov;
acb->qiov_offset = 0;
acb->cur_pos = (uint64_t)sector_num * BDRV_SECTOR_SIZE;
acb->end_pos = acb->cur_pos + nb_sectors * BDRV_SECTOR_SIZE;
acb->backing_qiov = NULL;
acb->request.l2_table = NULL;
qemu_iovec_init(&acb->cur_qiov, qiov->niov);
@@ -1390,20 +1365,20 @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs,
return &acb->common;
}
static BlockAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *bdrv_qed_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb, opaque, 0);
}
static BlockAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *bdrv_qed_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov, int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return qed_aio_setup(bs, sector_num, qiov, nb_sectors, cb,
opaque, QED_AIOCB_WRITE);
@@ -1431,7 +1406,7 @@ static int coroutine_fn bdrv_qed_co_write_zeroes(BlockDriverState *bs,
int nb_sectors,
BdrvRequestFlags flags)
{
BlockAIOCB *blockacb;
BlockDriverAIOCB *blockacb;
BDRVQEDState *s = bs->opaque;
QEDWriteZeroesCB cb = { .done = false };
QEMUIOVector qiov;
@@ -1618,45 +1593,36 @@ static int bdrv_qed_check(BlockDriverState *bs, BdrvCheckResult *result,
return qed_check(s, result, !!fix);
}
static QemuOptsList qed_create_opts = {
.name = "qed-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qed_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = QEMU_OPT_STRING,
.help = "File name of a base image"
},
{
.name = BLOCK_OPT_BACKING_FMT,
.type = QEMU_OPT_STRING,
.help = "Image format of the base image"
},
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Cluster size (in bytes)",
.def_value_str = stringify(QED_DEFAULT_CLUSTER_SIZE)
},
{
.name = BLOCK_OPT_TABLE_SIZE,
.type = QEMU_OPT_SIZE,
.help = "L1/L2 table size (in clusters)"
},
{ /* end of list */ }
}
static QEMUOptionParameter qed_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size (in bytes)"
}, {
.name = BLOCK_OPT_BACKING_FILE,
.type = OPT_STRING,
.help = "File name of a base image"
}, {
.name = BLOCK_OPT_BACKING_FMT,
.type = OPT_STRING,
.help = "Image format of the base image"
}, {
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
.help = "Cluster size (in bytes)",
.value = { .n = QED_DEFAULT_CLUSTER_SIZE },
}, {
.name = BLOCK_OPT_TABLE_SIZE,
.type = OPT_SIZE,
.help = "L1/L2 table size (in clusters)"
},
{ /* end of list */ }
};
static BlockDriver bdrv_qed = {
.format_name = "qed",
.instance_size = sizeof(BDRVQEDState),
.create_opts = &qed_create_opts,
.supports_backing = true,
.create_options = qed_create_options,
.bdrv_probe = bdrv_qed_probe,
.bdrv_rebind = bdrv_qed_rebind,
@@ -1676,8 +1642,6 @@ static BlockDriver bdrv_qed = {
.bdrv_change_backing_file = bdrv_qed_change_backing_file,
.bdrv_invalidate_cache = bdrv_qed_invalidate_cache,
.bdrv_check = bdrv_qed_check,
.bdrv_detach_aio_context = bdrv_qed_detach_aio_context,
.bdrv_attach_aio_context = bdrv_qed_attach_aio_context,
};
static void bdrv_qed_init(void)

View File

@@ -43,7 +43,7 @@
*
* All fields are little-endian on disk.
*/
#define QED_DEFAULT_CLUSTER_SIZE 65536
enum {
QED_MAGIC = 'Q' | 'E' << 8 | 'D' << 16 | '\0' << 24,
@@ -69,6 +69,7 @@ enum {
*/
QED_MIN_CLUSTER_SIZE = 4 * 1024, /* in bytes */
QED_MAX_CLUSTER_SIZE = 64 * 1024 * 1024,
QED_DEFAULT_CLUSTER_SIZE = 64 * 1024,
/* Allocated clusters are tracked using a 2-level pagetable. Table size is
* a multiple of clusters so large maximum image sizes can be supported
@@ -128,7 +129,7 @@ enum {
};
typedef struct QEDAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
QEMUBH *bh;
int bh_ret; /* final return status for completion bh */
QSIMPLEQ_ENTRY(QEDAIOCB) next; /* next request */
@@ -142,7 +143,6 @@ typedef struct QEDAIOCB {
/* Current cluster scatter-gather list */
QEMUIOVector cur_qiov;
QEMUIOVector *backing_qiov;
uint64_t cur_pos; /* position on block device, in bytes */
uint64_t cur_cluster; /* cluster offset in image file */
unsigned int cur_nclusters; /* number of clusters being accessed */
@@ -203,11 +203,11 @@ typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t l
* Generic callback for chaining async callbacks
*/
typedef struct {
BlockCompletionFunc *cb;
BlockDriverCompletionFunc *cb;
void *opaque;
} GenericCB;
void *gencb_alloc(size_t len, BlockCompletionFunc *cb, void *opaque);
void *gencb_alloc(size_t len, BlockDriverCompletionFunc *cb, void *opaque);
void gencb_complete(void *opaque, int ret);
/**
@@ -230,16 +230,16 @@ void qed_commit_l2_cache_entry(L2TableCache *l2_cache, CachedL2Table *l2_table);
*/
int qed_read_l1_table_sync(BDRVQEDState *s);
void qed_write_l1_table(BDRVQEDState *s, unsigned int index, unsigned int n,
BlockCompletionFunc *cb, void *opaque);
BlockDriverCompletionFunc *cb, void *opaque);
int qed_write_l1_table_sync(BDRVQEDState *s, unsigned int index,
unsigned int n);
int qed_read_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
uint64_t offset);
void qed_read_l2_table(BDRVQEDState *s, QEDRequest *request, uint64_t offset,
BlockCompletionFunc *cb, void *opaque);
BlockDriverCompletionFunc *cb, void *opaque);
void qed_write_l2_table(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush,
BlockCompletionFunc *cb, void *opaque);
BlockDriverCompletionFunc *cb, void *opaque);
int qed_write_l2_table_sync(BDRVQEDState *s, QEDRequest *request,
unsigned int index, unsigned int n, bool flush);

View File

@@ -16,20 +16,12 @@
#include <gnutls/gnutls.h>
#include <gnutls/crypto.h>
#include "block/block_int.h"
#include "qapi/qmp/qbool.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qint.h"
#include "qapi/qmp/qjson.h"
#include "qapi/qmp/qlist.h"
#include "qapi/qmp/qstring.h"
#include "qapi-event.h"
#define HASH_LENGTH 32
#define QUORUM_OPT_VOTE_THRESHOLD "vote-threshold"
#define QUORUM_OPT_BLKVERIFY "blkverify"
#define QUORUM_OPT_REWRITE "rewrite-corrupted"
#define QUORUM_OPT_READ_PATTERN "read-pattern"
/* This union holds a vote hash value */
typedef union QuorumVoteValue {
@@ -77,11 +69,6 @@ typedef struct BDRVQuorumState {
* It is useful to debug other block drivers by
* comparing them with a reference one.
*/
bool rewrite_corrupted;/* true if the driver must rewrite-on-read corrupted
* block if Quorum is reached.
*/
QuorumReadPattern read_pattern;
} BDRVQuorumState;
typedef struct QuorumAIOCB QuorumAIOCB;
@@ -92,7 +79,7 @@ typedef struct QuorumAIOCB QuorumAIOCB;
* $children_count QuorumChildRequest.
*/
typedef struct QuorumChildRequest {
BlockAIOCB *aiocb;
BlockDriverAIOCB *aiocb;
QEMUIOVector qiov;
uint8_t *buf;
int ret;
@@ -105,7 +92,7 @@ typedef struct QuorumChildRequest {
* used to do operations on each children and track overall progress.
*/
struct QuorumAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
/* Request metadata */
uint64_t sector_num;
@@ -117,20 +104,15 @@ struct QuorumAIOCB {
int count; /* number of completed AIOCB */
int success_count; /* number of successfully completed AIOCB */
int rewrite_count; /* number of replica to rewrite: count down to
* zero once writes are fired
*/
QuorumVotes votes;
bool is_read;
int vote_ret;
int child_iter; /* which child to read in fifo pattern */
};
static bool quorum_vote(QuorumAIOCB *acb);
static void quorum_vote(QuorumAIOCB *acb);
static void quorum_aio_cancel(BlockAIOCB *blockacb)
static void quorum_aio_cancel(BlockDriverAIOCB *blockacb)
{
QuorumAIOCB *acb = container_of(blockacb, QuorumAIOCB, common);
BDRVQuorumState *s = acb->common.bs->opaque;
@@ -138,19 +120,21 @@ static void quorum_aio_cancel(BlockAIOCB *blockacb)
/* cancel all callbacks */
for (i = 0; i < s->num_children; i++) {
if (acb->qcrs[i].aiocb) {
bdrv_aio_cancel_async(acb->qcrs[i].aiocb);
}
bdrv_aio_cancel(acb->qcrs[i].aiocb);
}
g_free(acb->qcrs);
qemu_aio_release(acb);
}
static AIOCBInfo quorum_aiocb_info = {
.aiocb_size = sizeof(QuorumAIOCB),
.cancel_async = quorum_aio_cancel,
.cancel = quorum_aio_cancel,
};
static void quorum_aio_finalize(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->common.bs->opaque;
int i, ret = 0;
if (acb->vote_ret) {
@@ -160,15 +144,14 @@ static void quorum_aio_finalize(QuorumAIOCB *acb)
acb->common.cb(acb->common.opaque, ret);
if (acb->is_read) {
/* on the quorum case acb->child_iter == s->num_children - 1 */
for (i = 0; i <= acb->child_iter; i++) {
for (i = 0; i < s->num_children; i++) {
qemu_vfree(acb->qcrs[i].buf);
qemu_iovec_destroy(&acb->qcrs[i].qiov);
}
}
g_free(acb->qcrs);
qemu_aio_unref(acb);
qemu_aio_release(acb);
}
static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)
@@ -186,7 +169,7 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
QEMUIOVector *qiov,
uint64_t sector_num,
int nb_sectors,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque)
{
QuorumAIOCB *acb = qemu_aio_get(&quorum_aiocb_info, bs, cb, opaque);
@@ -199,7 +182,6 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
acb->qcrs = g_new0(QuorumChildRequest, s->num_children);
acb->count = 0;
acb->success_count = 0;
acb->rewrite_count = 0;
acb->votes.compare = quorum_sha256_compare;
QLIST_INIT(&acb->votes.vote_list);
acb->is_read = false;
@@ -216,22 +198,32 @@ static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
static void quorum_report_bad(QuorumAIOCB *acb, char *node_name, int ret)
{
const char *msg = NULL;
QObject *data;
assert(node_name);
data = qobject_from_jsonf("{ 'node-name': %s"
", 'sector-num': %" PRId64
", 'sectors-count': %d }",
node_name, acb->sector_num, acb->nb_sectors);
if (ret < 0) {
msg = strerror(-ret);
QDict *dict = qobject_to_qdict(data);
qdict_put(dict, "error", qstring_from_str(strerror(-ret)));
}
qapi_event_send_quorum_report_bad(!!msg, msg, node_name,
acb->sector_num, acb->nb_sectors, &error_abort);
monitor_protocol_event(QEVENT_QUORUM_REPORT_BAD, data);
qobject_decref(data);
}
static void quorum_report_failure(QuorumAIOCB *acb)
{
const char *reference = bdrv_get_device_name(acb->common.bs)[0] ?
bdrv_get_device_name(acb->common.bs) :
QObject *data;
const char *reference = acb->common.bs->device_name[0] ?
acb->common.bs->device_name :
acb->common.bs->node_name;
qapi_event_send_quorum_failure(reference, acb->sector_num,
acb->nb_sectors, &error_abort);
data = qobject_from_jsonf("{ 'reference': %s"
", 'sector-num': %" PRId64
", 'sectors-count': %d }",
reference, acb->sector_num, acb->nb_sectors);
monitor_protocol_event(QEVENT_QUORUM_FAILURE, data);
qobject_decref(data);
}
static int quorum_vote_error(QuorumAIOCB *acb);
@@ -249,57 +241,11 @@ static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
return false;
}
static void quorum_rewrite_aio_cb(void *opaque, int ret)
{
QuorumAIOCB *acb = opaque;
/* one less rewrite to do */
acb->rewrite_count--;
/* wait until all rewrite callbacks have completed */
if (acb->rewrite_count) {
return;
}
quorum_aio_finalize(acb);
}
static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb);
static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
{
int i;
assert(dest->niov == source->niov);
assert(dest->size == source->size);
for (i = 0; i < source->niov; i++) {
assert(dest->iov[i].iov_len == source->iov[i].iov_len);
memcpy(dest->iov[i].iov_base,
source->iov[i].iov_base,
source->iov[i].iov_len);
}
}
static void quorum_aio_cb(void *opaque, int ret)
{
QuorumChildRequest *sacb = opaque;
QuorumAIOCB *acb = sacb->parent;
BDRVQuorumState *s = acb->common.bs->opaque;
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 < s->num_children) {
read_fifo_child(acb);
return;
}
if (ret == 0) {
quorum_copy_qiov(acb->qiov, &acb->qcrs[acb->child_iter].qiov);
}
acb->vote_ret = ret;
quorum_aio_finalize(acb);
return;
}
sacb->ret = ret;
acb->count++;
@@ -316,15 +262,12 @@ static void quorum_aio_cb(void *opaque, int ret)
/* Do the vote on read */
if (acb->is_read) {
rewrite = quorum_vote(acb);
quorum_vote(acb);
} else {
quorum_has_too_much_io_failed(acb);
}
/* if no rewrite is done the code will finish right away */
if (!rewrite) {
quorum_aio_finalize(acb);
}
quorum_aio_finalize(acb);
}
static void quorum_report_bad_versions(BDRVQuorumState *s,
@@ -344,41 +287,17 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
}
}
static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
QuorumVoteValue *value)
static void quorum_copy_qiov(QEMUIOVector *dest, QEMUIOVector *source)
{
QuorumVoteVersion *version;
QuorumVoteItem *item;
int count = 0;
/* first count the number of bad versions: done first to avoid concurrency
* issues.
*/
QLIST_FOREACH(version, &acb->votes.vote_list, next) {
if (acb->votes.compare(&version->value, value)) {
continue;
}
QLIST_FOREACH(item, &version->items, next) {
count++;
}
int i;
assert(dest->niov == source->niov);
assert(dest->size == source->size);
for (i = 0; i < source->niov; i++) {
assert(dest->iov[i].iov_len == source->iov[i].iov_len);
memcpy(dest->iov[i].iov_base,
source->iov[i].iov_base,
source->iov[i].iov_len);
}
/* quorum_rewrite_aio_cb will count down this to zero */
acb->rewrite_count = count;
/* now fire the correcting rewrites */
QLIST_FOREACH(version, &acb->votes.vote_list, next) {
if (acb->votes.compare(&version->value, value)) {
continue;
}
QLIST_FOREACH(item, &version->items, next) {
bdrv_aio_writev(s->bs[item->index], acb->sector_num, acb->qiov,
acb->nb_sectors, quorum_rewrite_aio_cb, acb);
}
}
/* return true if any rewrite is done else false */
return count;
}
static void quorum_count_vote(QuorumVotes *votes,
@@ -558,17 +477,16 @@ static int quorum_vote_error(QuorumAIOCB *acb)
return ret;
}
static bool quorum_vote(QuorumAIOCB *acb)
static void quorum_vote(QuorumAIOCB *acb)
{
bool quorum = true;
bool rewrite = false;
int i, j, ret;
QuorumVoteValue hash;
BDRVQuorumState *s = acb->common.bs->opaque;
QuorumVoteVersion *winner;
if (quorum_has_too_much_io_failed(acb)) {
return false;
return;
}
/* get the index of the first successful read */
@@ -596,7 +514,7 @@ static bool quorum_vote(QuorumAIOCB *acb)
/* Every successful read agrees */
if (quorum) {
quorum_copy_qiov(acb->qiov, &acb->qcrs[i].qiov);
return false;
return;
}
/* compute hashes for each successful read, also store indexes */
@@ -629,79 +547,45 @@ static bool quorum_vote(QuorumAIOCB *acb)
/* some versions are bad print them */
quorum_report_bad_versions(s, acb, &winner->value);
/* corruption correction is enabled */
if (s->rewrite_corrupted) {
rewrite = quorum_rewrite_bad_versions(s, acb, &winner->value);
}
free_exit:
/* free lists */
quorum_free_vote_list(&acb->votes);
return rewrite;
}
static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->common.bs->opaque;
int i;
for (i = 0; i < s->num_children; i++) {
acb->qcrs[i].buf = qemu_blockalign(s->bs[i], acb->qiov->size);
qemu_iovec_init(&acb->qcrs[i].qiov, acb->qiov->niov);
qemu_iovec_clone(&acb->qcrs[i].qiov, acb->qiov, acb->qcrs[i].buf);
}
for (i = 0; i < s->num_children; i++) {
bdrv_aio_readv(s->bs[i], acb->sector_num, &acb->qcrs[i].qiov,
acb->nb_sectors, quorum_aio_cb, &acb->qcrs[i]);
}
return &acb->common;
}
static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->common.bs->opaque;
acb->qcrs[acb->child_iter].buf = qemu_blockalign(s->bs[acb->child_iter],
acb->qiov->size);
qemu_iovec_init(&acb->qcrs[acb->child_iter].qiov, acb->qiov->niov);
qemu_iovec_clone(&acb->qcrs[acb->child_iter].qiov, acb->qiov,
acb->qcrs[acb->child_iter].buf);
bdrv_aio_readv(s->bs[acb->child_iter], acb->sector_num,
&acb->qcrs[acb->child_iter].qiov, acb->nb_sectors,
quorum_aio_cb, &acb->qcrs[acb->child_iter]);
return &acb->common;
}
static BlockAIOCB *quorum_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *quorum_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
BDRVQuorumState *s = bs->opaque;
QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num,
nb_sectors, cb, opaque);
int i;
acb->is_read = true;
if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
acb->child_iter = s->num_children - 1;
return read_quorum_children(acb);
for (i = 0; i < s->num_children; i++) {
acb->qcrs[i].buf = qemu_blockalign(s->bs[i], qiov->size);
qemu_iovec_init(&acb->qcrs[i].qiov, qiov->niov);
qemu_iovec_clone(&acb->qcrs[i].qiov, qiov, acb->qcrs[i].buf);
}
acb->child_iter = 0;
return read_fifo_child(acb);
for (i = 0; i < s->num_children; i++) {
bdrv_aio_readv(s->bs[i], sector_num, &acb->qcrs[i].qiov, nb_sectors,
quorum_aio_cb, &acb->qcrs[i]);
}
return &acb->common;
}
static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *quorum_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
BDRVQuorumState *s = bs->opaque;
QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num, nb_sectors,
@@ -830,44 +714,16 @@ static QemuOptsList quorum_runtime_opts = {
.type = QEMU_OPT_BOOL,
.help = "Trigger block verify mode if set",
},
{
.name = QUORUM_OPT_REWRITE,
.type = QEMU_OPT_BOOL,
.help = "Rewrite corrupted block on read quorum",
},
{
.name = QUORUM_OPT_READ_PATTERN,
.type = QEMU_OPT_STRING,
.help = "Allowed pattern: quorum, fifo. Quorum is default",
},
{ /* end of list */ }
},
};
static int parse_read_pattern(const char *opt)
{
int i;
if (!opt) {
/* Set quorum as default */
return QUORUM_READ_PATTERN_QUORUM;
}
for (i = 0; i < QUORUM_READ_PATTERN_MAX; i++) {
if (!strcmp(opt, QuorumReadPattern_lookup[i])) {
return i;
}
}
return -EINVAL;
}
static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVQuorumState *s = bs->opaque;
Error *local_err = NULL;
QemuOpts *opts = NULL;
QemuOpts *opts;
bool *opened;
QDict *sub = NULL;
QList *list = NULL;
@@ -897,43 +753,26 @@ static int quorum_open(BlockDriverState *bs, QDict *options, int flags,
opts = qemu_opts_create(&quorum_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
if (error_is_set(&local_err)) {
ret = -EINVAL;
goto exit;
}
s->threshold = qemu_opt_get_number(opts, QUORUM_OPT_VOTE_THRESHOLD, 0);
ret = parse_read_pattern(qemu_opt_get(opts, QUORUM_OPT_READ_PATTERN));
/* and validate it against s->num_children */
ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
if (ret < 0) {
error_setg(&local_err, "Please set read-pattern as fifo or quorum");
goto exit;
}
s->read_pattern = ret;
if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
/* and validate it against s->num_children */
ret = quorum_valid_threshold(s->threshold, s->num_children, &local_err);
if (ret < 0) {
goto exit;
}
/* is the driver in blkverify mode */
if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) &&
s->num_children == 2 && s->threshold == 2) {
s->is_blkverify = true;
} else if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false)) {
fprintf(stderr, "blkverify mode is set by setting blkverify=on "
"and using two files with vote_threshold=2\n");
}
s->rewrite_corrupted = qemu_opt_get_bool(opts, QUORUM_OPT_REWRITE,
false);
if (s->rewrite_corrupted && s->is_blkverify) {
error_setg(&local_err,
"rewrite-corrupted=on cannot be used with blkverify=on");
ret = -EINVAL;
goto exit;
}
/* is the driver in blkverify mode */
if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false) &&
s->num_children == 2 && s->threshold == 2) {
s->is_blkverify = true;
} else if (qemu_opt_get_bool(opts, QUORUM_OPT_BLKVERIFY, false)) {
fprintf(stderr, "blkverify mode is set by setting blkverify=on "
"and using two files with vote_threshold=2\n");
}
/* allocate the children BlockDriverState array */
@@ -988,9 +827,8 @@ close_exit:
g_free(s->bs);
g_free(opened);
exit:
qemu_opts_del(opts);
/* propagate error */
if (local_err) {
if (error_is_set(&local_err)) {
error_propagate(errp, local_err);
}
QDECREF(list);
@@ -1010,83 +848,25 @@ static void quorum_close(BlockDriverState *bs)
g_free(s->bs);
}
static void quorum_detach_aio_context(BlockDriverState *bs)
{
BDRVQuorumState *s = bs->opaque;
int i;
for (i = 0; i < s->num_children; i++) {
bdrv_detach_aio_context(s->bs[i]);
}
}
static void quorum_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVQuorumState *s = bs->opaque;
int i;
for (i = 0; i < s->num_children; i++) {
bdrv_attach_aio_context(s->bs[i], new_context);
}
}
static void quorum_refresh_filename(BlockDriverState *bs)
{
BDRVQuorumState *s = bs->opaque;
QDict *opts;
QList *children;
int i;
for (i = 0; i < s->num_children; i++) {
bdrv_refresh_filename(s->bs[i]);
if (!s->bs[i]->full_open_options) {
return;
}
}
children = qlist_new();
for (i = 0; i < s->num_children; i++) {
QINCREF(s->bs[i]->full_open_options);
qlist_append_obj(children, QOBJECT(s->bs[i]->full_open_options));
}
opts = qdict_new();
qdict_put_obj(opts, "driver", QOBJECT(qstring_from_str("quorum")));
qdict_put_obj(opts, QUORUM_OPT_VOTE_THRESHOLD,
QOBJECT(qint_from_int(s->threshold)));
qdict_put_obj(opts, QUORUM_OPT_BLKVERIFY,
QOBJECT(qbool_from_int(s->is_blkverify)));
qdict_put_obj(opts, QUORUM_OPT_REWRITE,
QOBJECT(qbool_from_int(s->rewrite_corrupted)));
qdict_put_obj(opts, "children", QOBJECT(children));
bs->full_open_options = opts;
}
static BlockDriver bdrv_quorum = {
.format_name = "quorum",
.protocol_name = "quorum",
.format_name = "quorum",
.protocol_name = "quorum",
.instance_size = sizeof(BDRVQuorumState),
.instance_size = sizeof(BDRVQuorumState),
.bdrv_file_open = quorum_open,
.bdrv_close = quorum_close,
.bdrv_refresh_filename = quorum_refresh_filename,
.bdrv_file_open = quorum_open,
.bdrv_close = quorum_close,
.bdrv_co_flush_to_disk = quorum_co_flush,
.bdrv_co_flush_to_disk = quorum_co_flush,
.bdrv_getlength = quorum_getlength,
.bdrv_getlength = quorum_getlength,
.bdrv_aio_readv = quorum_aio_readv,
.bdrv_aio_writev = quorum_aio_writev,
.bdrv_invalidate_cache = quorum_invalidate_cache,
.bdrv_aio_readv = quorum_aio_readv,
.bdrv_aio_writev = quorum_aio_writev,
.bdrv_invalidate_cache = quorum_invalidate_cache,
.bdrv_detach_aio_context = quorum_detach_aio_context,
.bdrv_attach_aio_context = quorum_attach_aio_context,
.is_filter = true,
.bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
.is_filter = true,
.bdrv_recurse_is_first_non_filter = quorum_recurse_is_first_non_filter,
};
static void bdrv_quorum_init(void)

View File

@@ -34,29 +34,19 @@
/* linux-aio.c - Linux native implementation */
#ifdef CONFIG_LINUX_AIO
void *laio_init(void);
void laio_cleanup(void *s);
BlockAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
BlockDriverAIOCB *laio_submit(BlockDriverState *bs, void *aio_ctx, int fd,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type);
void laio_detach_aio_context(void *s, AioContext *old_context);
void laio_attach_aio_context(void *s, AioContext *new_context);
void laio_io_plug(BlockDriverState *bs, void *aio_ctx);
int laio_io_unplug(BlockDriverState *bs, void *aio_ctx, bool unplug);
BlockDriverCompletionFunc *cb, void *opaque, int type);
#endif
#ifdef _WIN32
typedef struct QEMUWin32AIOState QEMUWin32AIOState;
QEMUWin32AIOState *win32_aio_init(void);
void win32_aio_cleanup(QEMUWin32AIOState *aio);
int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile);
BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
QEMUWin32AIOState *aio, HANDLE hfile,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type);
void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
AioContext *old_context);
void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
AioContext *new_context);
BlockDriverCompletionFunc *cb, void *opaque, int type);
#endif
#endif /* QEMU_RAW_AIO_H */

File diff suppressed because it is too large Load Diff

View File

@@ -36,6 +36,8 @@
#define FTYPE_CD 1
#define FTYPE_HARDDISK 2
static QEMUWin32AIOState *aio;
typedef struct RawWin32AIOData {
BlockDriverState *bs;
HANDLE hfile;
@@ -138,9 +140,9 @@ static int aio_worker(void *arg)
return ret;
}
static BlockAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
static BlockDriverAIOCB *paio_submit(BlockDriverState *bs, HANDLE hfile,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type)
BlockDriverCompletionFunc *cb, void *opaque, int type)
{
RawWin32AIOData *acb = g_slice_new(RawWin32AIOData);
ThreadPool *pool;
@@ -200,25 +202,6 @@ static int set_sparse(int fd)
NULL, 0, NULL, 0, &returned, NULL);
}
static void raw_detach_aio_context(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
if (s->aio) {
win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
}
}
static void raw_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVRawState *s = bs->opaque;
if (s->aio) {
win32_aio_attach_aio_context(s->aio, new_context);
}
}
static void raw_probe_alignment(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
@@ -317,6 +300,15 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
raw_parse_flags(flags, &access_flags, &overlapped);
if ((flags & BDRV_O_NATIVE_AIO) && aio == NULL) {
aio = win32_aio_init();
if (aio == NULL) {
error_setg(errp, "Could not initialize AIO");
ret = -EINVAL;
goto fail;
}
}
if (filename[0] && filename[1] == ':') {
snprintf(s->drive_path, sizeof(s->drive_path), "%c:\\", filename[0]);
} else if (filename[0] == '\\' && filename[1] == '\\') {
@@ -343,23 +335,13 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
}
if (flags & BDRV_O_NATIVE_AIO) {
s->aio = win32_aio_init();
if (s->aio == NULL) {
CloseHandle(s->hfile);
error_setg(errp, "Could not initialize AIO");
ret = -EINVAL;
goto fail;
}
ret = win32_aio_attach(s->aio, s->hfile);
ret = win32_aio_attach(aio, s->hfile);
if (ret < 0) {
win32_aio_cleanup(s->aio);
CloseHandle(s->hfile);
error_setg_errno(errp, -ret, "Could not enable AIO");
goto fail;
}
win32_aio_attach_aio_context(s->aio, bdrv_get_aio_context(bs));
s->aio = aio;
}
raw_probe_alignment(bs);
@@ -369,9 +351,9 @@ fail:
return ret;
}
static BlockAIOCB *raw_aio_readv(BlockDriverState *bs,
static BlockDriverAIOCB *raw_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
if (s->aio) {
@@ -383,9 +365,9 @@ static BlockAIOCB *raw_aio_readv(BlockDriverState *bs,
}
}
static BlockAIOCB *raw_aio_writev(BlockDriverState *bs,
static BlockDriverAIOCB *raw_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
if (s->aio) {
@@ -397,8 +379,8 @@ static BlockAIOCB *raw_aio_writev(BlockDriverState *bs,
}
}
static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque)
static BlockDriverAIOCB *raw_aio_flush(BlockDriverState *bs,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
return paio_submit(bs, s->hfile, 0, NULL, 0, cb, opaque, QEMU_AIO_FLUSH);
@@ -407,17 +389,7 @@ static BlockAIOCB *raw_aio_flush(BlockDriverState *bs,
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
if (s->aio) {
win32_aio_detach_aio_context(s->aio, bdrv_get_aio_context(bs));
win32_aio_cleanup(s->aio);
s->aio = NULL;
}
CloseHandle(s->hfile);
if (bs->open_flags & BDRV_O_TEMPORARY) {
unlink(bs->filename);
}
}
static int raw_truncate(BlockDriverState *bs, int64_t offset)
@@ -503,7 +475,8 @@ static int64_t raw_get_allocated_file_size(BlockDriverState *bs)
return st.st_size;
}
static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
static int raw_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int fd;
int64_t total_size = 0;
@@ -511,8 +484,12 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
strstart(filename, "file:", &filename);
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n / 512;
}
options++;
}
fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
0644);
@@ -521,23 +498,18 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
return -EIO;
}
set_sparse(fd);
ftruncate(fd, total_size);
ftruncate(fd, total_size * 512);
qemu_close(fd);
return 0;
}
static QemuOptsList raw_create_opts = {
.name = "raw-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{ /* end of list */ }
}
static QEMUOptionParameter raw_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{ NULL }
};
static BlockDriver bdrv_file = {
@@ -546,9 +518,9 @@ static BlockDriver bdrv_file = {
.instance_size = sizeof(BDRVRawState),
.bdrv_needs_filename = true,
.bdrv_parse_filename = raw_parse_filename,
.bdrv_file_open = raw_open,
.bdrv_close = raw_close,
.bdrv_create = raw_create,
.bdrv_file_open = raw_open,
.bdrv_close = raw_close,
.bdrv_create = raw_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_aio_readv = raw_aio_readv,
@@ -560,7 +532,7 @@ static BlockDriver bdrv_file = {
.bdrv_get_allocated_file_size
= raw_get_allocated_file_size,
.create_opts = &raw_create_opts,
.create_options = raw_create_options,
};
/***********************************************/
@@ -709,9 +681,6 @@ static BlockDriver bdrv_host_device = {
.bdrv_aio_writev = raw_aio_writev,
.bdrv_aio_flush = raw_aio_flush,
.bdrv_detach_aio_context = raw_detach_aio_context,
.bdrv_attach_aio_context = raw_attach_aio_context,
.bdrv_getlength = raw_getlength,
.has_variable_length = true,

View File

@@ -29,17 +29,13 @@
#include "block/block_int.h"
#include "qemu/option.h"
static QemuOptsList raw_create_opts = {
.name = "raw-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(raw_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{ /* end of list */ }
}
static QEMUOptionParameter raw_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{ 0 }
};
static int raw_reopen_prepare(BDRVReopenState *reopen_state,
@@ -94,9 +90,10 @@ static int raw_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
return bdrv_get_info(bs->file, bdi);
}
static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
static int raw_refresh_limits(BlockDriverState *bs)
{
bs->bl = bs->file->bl;
return 0;
}
static int raw_truncate(BlockDriverState *bs, int64_t offset)
@@ -129,10 +126,10 @@ static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
return bdrv_ioctl(bs->file, req, buf);
}
static BlockAIOCB *raw_aio_ioctl(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *raw_aio_ioctl(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return bdrv_aio_ioctl(bs->file, req, buf, cb, opaque);
}
@@ -142,12 +139,13 @@ static int raw_has_zero_init(BlockDriverState *bs)
return bdrv_has_zero_init(bs->file);
}
static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
static int raw_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
Error *local_err = NULL;
int ret;
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
}
@@ -196,7 +194,7 @@ static BlockDriver bdrv_raw = {
.bdrv_lock_medium = &raw_lock_medium,
.bdrv_ioctl = &raw_ioctl,
.bdrv_aio_ioctl = &raw_aio_ioctl,
.create_opts = &raw_create_opts,
.create_options = &raw_create_options[0],
.bdrv_has_zero_init = &raw_has_zero_init
};

View File

@@ -68,7 +68,7 @@ typedef enum {
} RBDAIOCmd;
typedef struct RBDAIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
QEMUBH *bh;
int64_t ret;
QEMUIOVector *qiov;
@@ -77,6 +77,7 @@ typedef struct RBDAIOCB {
int64_t sector_num;
int error;
struct BDRVRBDState *s;
int cancelled;
int status;
} RBDAIOCB;
@@ -104,7 +105,7 @@ typedef struct BDRVRBDState {
static int qemu_rbd_next_tok(char *dst, int dst_len,
char *src, char delim,
const char *name,
char **p, Error **errp)
char **p)
{
int l;
char *end;
@@ -127,10 +128,10 @@ static int qemu_rbd_next_tok(char *dst, int dst_len,
}
l = strlen(src);
if (l >= dst_len) {
error_setg(errp, "%s too long", name);
error_report("%s too long", name);
return -EINVAL;
} else if (l == 0) {
error_setg(errp, "%s too short", name);
error_report("%s too short", name);
return -EINVAL;
}
@@ -156,15 +157,13 @@ static int qemu_rbd_parsename(const char *filename,
char *pool, int pool_len,
char *snap, int snap_len,
char *name, int name_len,
char *conf, int conf_len,
Error **errp)
char *conf, int conf_len)
{
const char *start;
char *p, *buf;
int ret;
if (!strstart(filename, "rbd:", &start)) {
error_setg(errp, "File name must start with 'rbd:'");
return -EINVAL;
}
@@ -173,8 +172,7 @@ static int qemu_rbd_parsename(const char *filename,
*snap = '\0';
*conf = '\0';
ret = qemu_rbd_next_tok(pool, pool_len, p,
'/', "pool name", &p, errp);
ret = qemu_rbd_next_tok(pool, pool_len, p, '/', "pool name", &p);
if (ret < 0 || !p) {
ret = -EINVAL;
goto done;
@@ -182,25 +180,21 @@ static int qemu_rbd_parsename(const char *filename,
qemu_rbd_unescape(pool);
if (strchr(p, '@')) {
ret = qemu_rbd_next_tok(name, name_len, p,
'@', "object name", &p, errp);
ret = qemu_rbd_next_tok(name, name_len, p, '@', "object name", &p);
if (ret < 0) {
goto done;
}
ret = qemu_rbd_next_tok(snap, snap_len, p,
':', "snap name", &p, errp);
ret = qemu_rbd_next_tok(snap, snap_len, p, ':', "snap name", &p);
qemu_rbd_unescape(snap);
} else {
ret = qemu_rbd_next_tok(name, name_len, p,
':', "object name", &p, errp);
ret = qemu_rbd_next_tok(name, name_len, p, ':', "object name", &p);
}
qemu_rbd_unescape(name);
if (ret < 0 || !p) {
goto done;
}
ret = qemu_rbd_next_tok(conf, conf_len, p,
'\0', "configuration", &p, errp);
ret = qemu_rbd_next_tok(conf, conf_len, p, '\0', "configuration", &p);
done:
g_free(buf);
@@ -235,7 +229,7 @@ static char *qemu_rbd_parse_clientname(const char *conf, char *clientname)
return NULL;
}
static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
static int qemu_rbd_set_conf(rados_t cluster, const char *conf)
{
char *p, *buf;
char name[RBD_MAX_CONF_NAME_SIZE];
@@ -247,20 +241,20 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
while (p) {
ret = qemu_rbd_next_tok(name, sizeof(name), p,
'=', "conf option name", &p, errp);
'=', "conf option name", &p);
if (ret < 0) {
break;
}
qemu_rbd_unescape(name);
if (!p) {
error_setg(errp, "conf option %s has no value", name);
error_report("conf option %s has no value", name);
ret = -EINVAL;
break;
}
ret = qemu_rbd_next_tok(value, sizeof(value), p,
':', "conf option value", &p, errp);
':', "conf option value", &p);
if (ret < 0) {
break;
}
@@ -269,7 +263,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
if (strcmp(name, "conf") == 0) {
ret = rados_conf_read_file(cluster, value);
if (ret < 0) {
error_setg(errp, "error reading conf file %s", value);
error_report("error reading conf file %s", value);
break;
}
} else if (strcmp(name, "id") == 0) {
@@ -277,7 +271,7 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
} else {
ret = rados_conf_set(cluster, name, value);
if (ret < 0) {
error_setg(errp, "invalid conf option %s", name);
error_report("invalid conf option %s", name);
ret = -EINVAL;
break;
}
@@ -288,9 +282,9 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf, Error **errp)
return ret;
}
static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
static int qemu_rbd_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
Error *local_err = NULL;
int64_t bytes = 0;
int64_t objsize;
int obj_order = 0;
@@ -307,30 +301,34 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
name, sizeof(name),
conf, sizeof(conf), &local_err) < 0) {
error_propagate(errp, local_err);
conf, sizeof(conf)) < 0) {
return -EINVAL;
}
/* Read out options */
bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
objsize = qemu_opt_get_size_del(opts, BLOCK_OPT_CLUSTER_SIZE, 0);
if (objsize) {
if ((objsize - 1) & objsize) { /* not a power of 2? */
error_setg(errp, "obj size needs to be power of 2");
return -EINVAL;
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
bytes = options->value.n;
} else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
if (options->value.n) {
objsize = options->value.n;
if ((objsize - 1) & objsize) { /* not a power of 2? */
error_report("obj size needs to be power of 2");
return -EINVAL;
}
if (objsize < 4096) {
error_report("obj size too small");
return -EINVAL;
}
obj_order = ffs(objsize) - 1;
}
}
if (objsize < 4096) {
error_setg(errp, "obj size too small");
return -EINVAL;
}
obj_order = ffs(objsize) - 1;
options++;
}
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
if (rados_create(&cluster, clientname) < 0) {
error_setg(errp, "error initializing");
error_report("error initializing");
return -EIO;
}
@@ -340,20 +338,20 @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
}
if (conf[0] != '\0' &&
qemu_rbd_set_conf(cluster, conf, &local_err) < 0) {
qemu_rbd_set_conf(cluster, conf) < 0) {
error_report("error setting config options");
rados_shutdown(cluster);
error_propagate(errp, local_err);
return -EIO;
}
if (rados_connect(cluster) < 0) {
error_setg(errp, "error connecting");
error_report("error connecting");
rados_shutdown(cluster);
return -EIO;
}
if (rados_ioctx_create(cluster, pool, &io_ctx) < 0) {
error_setg(errp, "error opening pool %s", pool);
error_report("error opening pool %s", pool);
rados_shutdown(cluster);
return -EIO;
}
@@ -407,7 +405,9 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
acb->status = 0;
qemu_aio_unref(acb);
if (!acb->cancelled) {
qemu_aio_release(acb);
}
}
/* TODO Convert to fine grained options */
@@ -441,7 +441,8 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
error_propagate(errp, local_err);
qerror_report_err(local_err);
error_free(local_err);
qemu_opts_del(opts);
return -EINVAL;
}
@@ -451,7 +452,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
if (qemu_rbd_parsename(filename, pool, sizeof(pool),
snap_buf, sizeof(snap_buf),
s->name, sizeof(s->name),
conf, sizeof(conf), errp) < 0) {
conf, sizeof(conf)) < 0) {
r = -EINVAL;
goto failed_opts;
}
@@ -459,7 +460,7 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
clientname = qemu_rbd_parse_clientname(conf, clientname_buf);
r = rados_create(&s->cluster, clientname);
if (r < 0) {
error_setg(&local_err, "error initializing");
error_report("error initializing");
goto failed_opts;
}
@@ -487,27 +488,28 @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
}
if (conf[0] != '\0') {
r = qemu_rbd_set_conf(s->cluster, conf, errp);
r = qemu_rbd_set_conf(s->cluster, conf);
if (r < 0) {
error_report("error setting config options");
goto failed_shutdown;
}
}
r = rados_connect(s->cluster);
if (r < 0) {
error_setg(&local_err, "error connecting");
error_report("error connecting");
goto failed_shutdown;
}
r = rados_ioctx_create(s->cluster, pool, &s->io_ctx);
if (r < 0) {
error_setg(&local_err, "error opening pool %s", pool);
error_report("error opening pool %s", pool);
goto failed_shutdown;
}
r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
if (r < 0) {
error_setg(&local_err, "error reading header from %s", s->name);
error_report("error reading header from %s", s->name);
goto failed_open;
}
@@ -536,8 +538,25 @@ static void qemu_rbd_close(BlockDriverState *bs)
rados_shutdown(s->cluster);
}
/*
* Cancel aio. Since we don't reference acb in a non qemu threads,
* it is safe to access it here.
*/
static void qemu_rbd_aio_cancel(BlockDriverAIOCB *blockacb)
{
RBDAIOCB *acb = (RBDAIOCB *) blockacb;
acb->cancelled = 1;
while (acb->status == -EINPROGRESS) {
qemu_aio_wait();
}
qemu_aio_release(acb);
}
static const AIOCBInfo rbd_aiocb_info = {
.aiocb_size = sizeof(RBDAIOCB),
.cancel = qemu_rbd_aio_cancel,
};
static void rbd_finish_bh(void *opaque)
@@ -562,8 +581,7 @@ static void rbd_finish_aiocb(rbd_completion_t c, RADOSCB *rcb)
rcb->ret = rbd_aio_get_return_value(c);
rbd_aio_release(c);
acb->bh = aio_bh_new(bdrv_get_aio_context(acb->common.bs),
rbd_finish_bh, rcb);
acb->bh = qemu_bh_new(rbd_finish_bh, rcb);
qemu_bh_schedule(acb->bh);
}
@@ -589,16 +607,16 @@ static int rbd_aio_flush_wrapper(rbd_image_t image,
#endif
}
static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
static BlockDriverAIOCB *rbd_start_aio(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque,
RBDAIOCmd cmd)
{
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
RADOSCB *rcb;
rbd_completion_t c;
int64_t off, size;
char *buf;
@@ -612,14 +630,12 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
if (cmd == RBD_AIO_DISCARD || cmd == RBD_AIO_FLUSH) {
acb->bounce = NULL;
} else {
acb->bounce = qemu_try_blockalign(bs, qiov->size);
if (acb->bounce == NULL) {
goto failed;
}
acb->bounce = qemu_blockalign(bs, qiov->size);
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
acb->cancelled = 0;
acb->bh = NULL;
acb->status = -EINPROGRESS;
@@ -632,7 +648,7 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
off = sector_num * BDRV_SECTOR_SIZE;
size = nb_sectors * BDRV_SECTOR_SIZE;
rcb = g_new(RADOSCB, 1);
rcb = g_malloc(sizeof(RADOSCB));
rcb->done = 0;
rcb->acb = acb;
rcb->buf = buf;
@@ -661,46 +677,43 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
}
if (r < 0) {
goto failed_completion;
goto failed;
}
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
qemu_vfree(acb->bounce);
qemu_aio_unref(acb);
qemu_aio_release(acb);
return NULL;
}
static BlockAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *qemu_rbd_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
RBD_AIO_READ);
}
static BlockAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *qemu_rbd_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return rbd_start_aio(bs, sector_num, qiov, nb_sectors, cb, opaque,
RBD_AIO_WRITE);
}
#ifdef LIBRBD_SUPPORTS_AIO_FLUSH
static BlockAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB *qemu_rbd_aio_flush(BlockDriverState *bs,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return rbd_start_aio(bs, 0, NULL, 0, cb, opaque, RBD_AIO_FLUSH);
}
@@ -842,7 +855,7 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
int max_snaps = RBD_MAX_SNAPS;
do {
snaps = g_new(rbd_snap_info_t, max_snaps);
snaps = g_malloc(sizeof(*snaps) * max_snaps);
snap_count = rbd_snap_list(s->image, snaps, &max_snaps);
if (snap_count <= 0) {
g_free(snaps);
@@ -853,7 +866,7 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
goto done;
}
sn_tab = g_new0(QEMUSnapshotInfo, snap_count);
sn_tab = g_malloc0(snap_count * sizeof(QEMUSnapshotInfo));
for (i = 0; i < snap_count; i++) {
const char *snap_name = snaps[i].name;
@@ -876,45 +889,29 @@ static int qemu_rbd_snap_list(BlockDriverState *bs,
}
#ifdef LIBRBD_SUPPORTS_DISCARD
static BlockAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
static BlockDriverAIOCB* qemu_rbd_aio_discard(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors,
BlockDriverCompletionFunc *cb,
void *opaque)
{
return rbd_start_aio(bs, sector_num, NULL, nb_sectors, cb, opaque,
RBD_AIO_DISCARD);
}
#endif
#ifdef LIBRBD_SUPPORTS_INVALIDATE
static void qemu_rbd_invalidate_cache(BlockDriverState *bs,
Error **errp)
{
BDRVRBDState *s = bs->opaque;
int r = rbd_invalidate_cache(s->image);
if (r < 0) {
error_setg_errno(errp, -r, "Failed to invalidate the cache");
}
}
#endif
static QemuOptsList qemu_rbd_create_opts = {
.name = "rbd-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(qemu_rbd_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = QEMU_OPT_SIZE,
.help = "RBD object size"
},
{ /* end of list */ }
}
static QEMUOptionParameter qemu_rbd_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
.help = "RBD object size"
},
{NULL}
};
static BlockDriver bdrv_rbd = {
@@ -926,7 +923,7 @@ static BlockDriver bdrv_rbd = {
.bdrv_create = qemu_rbd_create,
.bdrv_has_zero_init = bdrv_has_zero_init_1,
.bdrv_get_info = qemu_rbd_getinfo,
.create_opts = &qemu_rbd_create_opts,
.create_options = qemu_rbd_create_options,
.bdrv_getlength = qemu_rbd_getlength,
.bdrv_truncate = qemu_rbd_truncate,
.protocol_name = "rbd",
@@ -948,9 +945,6 @@ static BlockDriver bdrv_rbd = {
.bdrv_snapshot_delete = qemu_rbd_snap_remove,
.bdrv_snapshot_list = qemu_rbd_snap_list,
.bdrv_snapshot_goto = qemu_rbd_snap_rollback,
#ifdef LIBRBD_SUPPORTS_INVALIDATE
.bdrv_invalidate_cache = qemu_rbd_invalidate_cache,
#endif
};
static void bdrv_rbd_init(void)

File diff suppressed because it is too large Load Diff

View File

@@ -236,10 +236,6 @@ int bdrv_snapshot_delete(BlockDriverState *bs,
error_setg(errp, "snapshot_id and name are both NULL");
return -EINVAL;
}
/* drain all pending i/o before deleting snapshot */
bdrv_drain_all();
if (drv->bdrv_snapshot_delete) {
return drv->bdrv_snapshot_delete(bs, snapshot_id, name, errp);
}

View File

@@ -106,59 +106,30 @@ static void ssh_state_free(BDRVSSHState *s)
}
}
static void GCC_FMT_ATTR(3, 4)
session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
/* Wrappers around error_report which make sure to dump as much
* information from libssh2 as possible.
*/
static void GCC_FMT_ATTR(2, 3)
session_error_report(BDRVSSHState *s, const char *fs, ...)
{
va_list args;
char *msg;
va_start(args, fs);
msg = g_strdup_vprintf(fs, args);
va_end(args);
error_vprintf(fs, args);
if (s->session) {
if ((s)->session) {
char *ssh_err;
int ssh_err_code;
libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
/* This is not an errno. See <libssh2.h>. */
ssh_err_code = libssh2_session_last_error(s->session,
&ssh_err, NULL, 0);
error_setg(errp, "%s: %s (libssh2 error code: %d)",
msg, ssh_err, ssh_err_code);
} else {
error_setg(errp, "%s", msg);
ssh_err_code = libssh2_session_last_errno((s)->session);
error_printf(": %s (libssh2 error code: %d)", ssh_err, ssh_err_code);
}
g_free(msg);
}
static void GCC_FMT_ATTR(3, 4)
sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
{
va_list args;
char *msg;
va_start(args, fs);
msg = g_strdup_vprintf(fs, args);
va_end(args);
if (s->sftp) {
char *ssh_err;
int ssh_err_code;
unsigned long sftp_err_code;
/* This is not an errno. See <libssh2.h>. */
ssh_err_code = libssh2_session_last_error(s->session,
&ssh_err, NULL, 0);
/* See <libssh2_sftp.h>. */
sftp_err_code = libssh2_sftp_last_error((s)->sftp);
error_setg(errp,
"%s: %s (libssh2 error code: %d, sftp error code: %lu)",
msg, ssh_err, ssh_err_code, sftp_err_code);
} else {
error_setg(errp, "%s", msg);
}
g_free(msg);
error_printf("\n");
}
static void GCC_FMT_ATTR(2, 3)
@@ -174,9 +145,9 @@ sftp_error_report(BDRVSSHState *s, const char *fs, ...)
int ssh_err_code;
unsigned long sftp_err_code;
libssh2_session_last_error((s)->session, &ssh_err, NULL, 0);
/* This is not an errno. See <libssh2.h>. */
ssh_err_code = libssh2_session_last_error(s->session,
&ssh_err, NULL, 0);
ssh_err_code = libssh2_session_last_errno((s)->session);
/* See <libssh2_sftp.h>. */
sftp_err_code = libssh2_sftp_last_error((s)->sftp);
@@ -272,7 +243,7 @@ static void ssh_parse_filename(const char *filename, QDict *options,
}
static int check_host_key_knownhosts(BDRVSSHState *s,
const char *host, int port, Error **errp)
const char *host, int port)
{
const char *home;
char *knh_file = NULL;
@@ -286,15 +257,14 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
hostkey = libssh2_session_hostkey(s->session, &len, &type);
if (!hostkey) {
ret = -EINVAL;
session_error_setg(errp, s, "failed to read remote host key");
session_error_report(s, "failed to read remote host key");
goto out;
}
knh = libssh2_knownhost_init(s->session);
if (!knh) {
ret = -EINVAL;
session_error_setg(errp, s,
"failed to initialize known hosts support");
session_error_report(s, "failed to initialize known hosts support");
goto out;
}
@@ -319,23 +289,21 @@ static int check_host_key_knownhosts(BDRVSSHState *s,
break;
case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
ret = -EINVAL;
session_error_setg(errp, s,
"host key does not match the one in known_hosts"
" (found key %s)", found->key);
session_error_report(s, "host key does not match the one in known_hosts (found key %s)",
found->key);
goto out;
case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
ret = -EINVAL;
session_error_setg(errp, s, "no host key was found in known_hosts");
session_error_report(s, "no host key was found in known_hosts");
goto out;
case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
ret = -EINVAL;
session_error_setg(errp, s,
"failure matching the host key with known_hosts");
session_error_report(s, "failure matching the host key with known_hosts");
goto out;
default:
ret = -EINVAL;
session_error_setg(errp, s, "unknown error matching the host key"
" with known_hosts (%d)", r);
session_error_report(s, "unknown error matching the host key with known_hosts (%d)",
r);
goto out;
}
@@ -390,20 +358,20 @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
static int
check_host_key_hash(BDRVSSHState *s, const char *hash,
int hash_type, size_t fingerprint_len, Error **errp)
int hash_type, size_t fingerprint_len)
{
const char *fingerprint;
fingerprint = libssh2_hostkey_hash(s->session, hash_type);
if (!fingerprint) {
session_error_setg(errp, s, "failed to read remote host key");
session_error_report(s, "failed to read remote host key");
return -EINVAL;
}
if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
hash) != 0) {
error_setg(errp, "remote host key does not match host_key_check '%s'",
hash);
error_report("remote host key does not match host_key_check '%s'",
hash);
return -EPERM;
}
@@ -411,7 +379,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
}
static int check_host_key(BDRVSSHState *s, const char *host, int port,
const char *host_key_check, Error **errp)
const char *host_key_check)
{
/* host_key_check=no */
if (strcmp(host_key_check, "no") == 0) {
@@ -421,25 +389,25 @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
/* host_key_check=md5:xx:yy:zz:... */
if (strncmp(host_key_check, "md5:", 4) == 0) {
return check_host_key_hash(s, &host_key_check[4],
LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
LIBSSH2_HOSTKEY_HASH_MD5, 16);
}
/* host_key_check=sha1:xx:yy:zz:... */
if (strncmp(host_key_check, "sha1:", 5) == 0) {
return check_host_key_hash(s, &host_key_check[5],
LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
LIBSSH2_HOSTKEY_HASH_SHA1, 20);
}
/* host_key_check=yes */
if (strcmp(host_key_check, "yes") == 0) {
return check_host_key_knownhosts(s, host, port, errp);
return check_host_key_knownhosts(s, host, port);
}
error_setg(errp, "unknown host_key_check setting (%s)", host_key_check);
error_report("unknown host_key_check setting (%s)", host_key_check);
return -EINVAL;
}
static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
static int authenticate(BDRVSSHState *s, const char *user)
{
int r, ret;
const char *userauthlist;
@@ -450,8 +418,7 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
if (strstr(userauthlist, "publickey") == NULL) {
ret = -EPERM;
error_setg(errp,
"remote server does not support \"publickey\" authentication");
error_report("remote server does not support \"publickey\" authentication");
goto out;
}
@@ -459,18 +426,17 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
agent = libssh2_agent_init(s->session);
if (!agent) {
ret = -EINVAL;
session_error_setg(errp, s, "failed to initialize ssh-agent support");
session_error_report(s, "failed to initialize ssh-agent support");
goto out;
}
if (libssh2_agent_connect(agent)) {
ret = -ECONNREFUSED;
session_error_setg(errp, s, "failed to connect to ssh-agent");
session_error_report(s, "failed to connect to ssh-agent");
goto out;
}
if (libssh2_agent_list_identities(agent)) {
ret = -EINVAL;
session_error_setg(errp, s,
"failed requesting identities from ssh-agent");
session_error_report(s, "failed requesting identities from ssh-agent");
goto out;
}
@@ -481,8 +447,7 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
}
if (r < 0) {
ret = -EINVAL;
session_error_setg(errp, s,
"failed to obtain identity from ssh-agent");
session_error_report(s, "failed to obtain identity from ssh-agent");
goto out;
}
r = libssh2_agent_userauth(agent, user, identity);
@@ -496,8 +461,8 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
}
ret = -EPERM;
error_setg(errp, "failed to authenticate using publickey authentication "
"and the identities held by your ssh-agent");
error_report("failed to authenticate using publickey authentication "
"and the identities held by your ssh-agent");
out:
if (agent != NULL) {
@@ -511,17 +476,13 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
}
static int connect_to_ssh(BDRVSSHState *s, QDict *options,
int ssh_flags, int creat_mode, Error **errp)
int ssh_flags, int creat_mode)
{
int r, ret;
Error *err = NULL;
const char *host, *user, *path, *host_key_check;
int port;
if (!qdict_haskey(options, "host")) {
ret = -EINVAL;
error_setg(errp, "No hostname was specified");
goto err;
}
host = qdict_get_str(options, "host");
if (qdict_haskey(options, "port")) {
@@ -530,11 +491,6 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
port = 22;
}
if (!qdict_haskey(options, "path")) {
ret = -EINVAL;
error_setg(errp, "No path was specified");
goto err;
}
path = qdict_get_str(options, "path");
if (qdict_haskey(options, "user")) {
@@ -542,7 +498,6 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
} else {
user = g_get_user_name();
if (!user) {
error_setg_errno(errp, errno, "Can't get user name");
ret = -errno;
goto err;
}
@@ -559,9 +514,11 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
s->hostport = g_strdup_printf("%s:%d", host, port);
/* Open the socket and connect. */
s->sock = inet_connect(s->hostport, errp);
if (s->sock < 0) {
s->sock = inet_connect(s->hostport, &err);
if (err != NULL) {
ret = -errno;
qerror_report_err(err);
error_free(err);
goto err;
}
@@ -569,7 +526,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
s->session = libssh2_session_init();
if (!s->session) {
ret = -EINVAL;
session_error_setg(errp, s, "failed to initialize libssh2 session");
session_error_report(s, "failed to initialize libssh2 session");
goto err;
}
@@ -580,18 +537,18 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
r = libssh2_session_handshake(s->session, s->sock);
if (r != 0) {
ret = -EINVAL;
session_error_setg(errp, s, "failed to establish SSH session");
session_error_report(s, "failed to establish SSH session");
goto err;
}
/* Check the remote host's key against known_hosts. */
ret = check_host_key(s, host, port, host_key_check, errp);
ret = check_host_key(s, host, port, host_key_check);
if (ret < 0) {
goto err;
}
/* Authenticate. */
ret = authenticate(s, user, errp);
ret = authenticate(s, user);
if (ret < 0) {
goto err;
}
@@ -599,7 +556,7 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
/* Start SFTP. */
s->sftp = libssh2_sftp_init(s->session);
if (!s->sftp) {
session_error_setg(errp, s, "failed to initialize sftp handle");
session_error_report(s, "failed to initialize sftp handle");
ret = -EINVAL;
goto err;
}
@@ -609,14 +566,14 @@ static int connect_to_ssh(BDRVSSHState *s, QDict *options,
path, ssh_flags, creat_mode);
s->sftp_handle = libssh2_sftp_open(s->sftp, path, ssh_flags, creat_mode);
if (!s->sftp_handle) {
session_error_setg(errp, s, "failed to open remote file '%s'", path);
session_error_report(s, "failed to open remote file '%s'", path);
ret = -EINVAL;
goto err;
}
r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
if (r < 0) {
sftp_error_setg(errp, s, "failed to read file attributes");
sftp_error_report(s, "failed to read file attributes");
return -EINVAL;
}
@@ -666,7 +623,7 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
}
/* Start up SSH. */
ret = connect_to_ssh(s, options, ssh_flags, 0, errp);
ret = connect_to_ssh(s, options, ssh_flags, 0);
if (ret < 0) {
goto err;
}
@@ -685,22 +642,20 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
return ret;
}
static QemuOptsList ssh_create_opts = {
.name = "ssh-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(ssh_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{ /* end of list */ }
}
static QEMUOptionParameter ssh_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{ NULL }
};
static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
static int ssh_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int r, ret;
Error *local_err = NULL;
int64_t total_size = 0;
QDict *uri_options = NULL;
BDRVSSHState s;
@@ -710,21 +665,26 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
ssh_state_init(&s);
/* Get desired file size. */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n;
}
options++;
}
DPRINTF("total_size=%" PRIi64, total_size);
uri_options = qdict_new();
r = parse_uri(filename, uri_options, errp);
r = parse_uri(filename, uri_options, &local_err);
if (r < 0) {
qerror_report_err(local_err);
error_free(local_err);
ret = r;
goto out;
}
r = connect_to_ssh(&s, uri_options,
LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
0644, errp);
LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC, 0644);
if (r < 0) {
ret = r;
goto out;
@@ -734,7 +694,7 @@ static int ssh_create(const char *filename, QemuOpts *opts, Error **errp)
libssh2_sftp_seek64(s.sftp_handle, total_size-1);
r2 = libssh2_sftp_write(s.sftp_handle, c, 1);
if (r2 < 0) {
sftp_error_setg(errp, &s, "truncate failed");
sftp_error_report(&s, "truncate failed");
ret = -EINVAL;
goto out;
}
@@ -782,7 +742,7 @@ static void restart_coroutine(void *opaque)
qemu_coroutine_enter(co, NULL);
}
static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
static coroutine_fn void set_fd_handler(BDRVSSHState *s)
{
int r;
IOHandler *rd_handler = NULL, *wr_handler = NULL;
@@ -800,26 +760,24 @@ static coroutine_fn void set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
DPRINTF("s->sock=%d rd_handler=%p wr_handler=%p", s->sock,
rd_handler, wr_handler);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
rd_handler, wr_handler, co);
qemu_aio_set_fd_handler(s->sock, rd_handler, wr_handler, co);
}
static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
BlockDriverState *bs)
static coroutine_fn void clear_fd_handler(BDRVSSHState *s)
{
DPRINTF("s->sock=%d", s->sock);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, NULL, NULL, NULL);
qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
}
/* A non-blocking call returned EAGAIN, so yield, ensuring the
* handlers are set up so that we'll be rescheduled when there is an
* interesting event on the socket.
*/
static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
static coroutine_fn void co_yield(BDRVSSHState *s)
{
set_fd_handler(s, bs);
set_fd_handler(s);
qemu_coroutine_yield();
clear_fd_handler(s, bs);
clear_fd_handler(s);
}
/* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
@@ -849,7 +807,7 @@ static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
}
}
static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
static coroutine_fn int ssh_read(BDRVSSHState *s,
int64_t offset, size_t size,
QEMUIOVector *qiov)
{
@@ -882,7 +840,7 @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
DPRINTF("sftp_read returned %zd", r);
if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
co_yield(s, bs);
co_yield(s);
goto again;
}
if (r < 0) {
@@ -917,14 +875,14 @@ static coroutine_fn int ssh_co_readv(BlockDriverState *bs,
int ret;
qemu_co_mutex_lock(&s->lock);
ret = ssh_read(s, bs, sector_num * BDRV_SECTOR_SIZE,
ret = ssh_read(s, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE, qiov);
qemu_co_mutex_unlock(&s->lock);
return ret;
}
static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
static int ssh_write(BDRVSSHState *s,
int64_t offset, size_t size,
QEMUIOVector *qiov)
{
@@ -952,7 +910,7 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
DPRINTF("sftp_write returned %zd", r);
if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
co_yield(s, bs);
co_yield(s);
goto again;
}
if (r < 0) {
@@ -971,7 +929,7 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
*/
if (r == 0) {
ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
co_yield(s, bs);
co_yield(s);
goto again;
}
@@ -999,7 +957,7 @@ static coroutine_fn int ssh_co_writev(BlockDriverState *bs,
int ret;
qemu_co_mutex_lock(&s->lock);
ret = ssh_write(s, bs, sector_num * BDRV_SECTOR_SIZE,
ret = ssh_write(s, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE, qiov);
qemu_co_mutex_unlock(&s->lock);
@@ -1020,7 +978,7 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
#ifdef HAS_LIBSSH2_SFTP_FSYNC
static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
static coroutine_fn int ssh_flush(BDRVSSHState *s)
{
int r;
@@ -1028,7 +986,7 @@ static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
again:
r = libssh2_sftp_fsync(s->sftp_handle);
if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
co_yield(s, bs);
co_yield(s);
goto again;
}
if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
@@ -1050,7 +1008,7 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
int ret;
qemu_co_mutex_lock(&s->lock);
ret = ssh_flush(s, bs);
ret = ssh_flush(s);
qemu_co_mutex_unlock(&s->lock);
return ret;
@@ -1093,7 +1051,7 @@ static BlockDriver bdrv_ssh = {
.bdrv_co_writev = ssh_co_writev,
.bdrv_getlength = ssh_getlength,
.bdrv_co_flush_to_disk = ssh_co_flush,
.create_opts = &ssh_create_opts,
.create_options = ssh_create_options,
};
static void bdrv_ssh_init(void)

View File

@@ -32,7 +32,7 @@ typedef struct StreamBlockJob {
RateLimit limit;
BlockDriverState *base;
BlockdevOnError on_error;
char *backing_file_str;
char backing_file_id[1024];
} StreamBlockJob;
static int coroutine_fn stream_populate(BlockDriverState *bs,
@@ -60,7 +60,7 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
/* Must assign before bdrv_delete() to prevent traversing dangling pointer
* while we delete backing image instances.
*/
bdrv_set_backing_hd(top, base);
top->backing_hd = base;
while (intermediate) {
BlockDriverState *unused;
@@ -72,46 +72,16 @@ static void close_unused_images(BlockDriverState *top, BlockDriverState *base,
unused = intermediate;
intermediate = intermediate->backing_hd;
bdrv_set_backing_hd(unused, NULL);
unused->backing_hd = NULL;
bdrv_unref(unused);
}
bdrv_refresh_limits(top, NULL);
}
typedef struct {
int ret;
bool reached_end;
} StreamCompleteData;
static void stream_complete(BlockJob *job, void *opaque)
{
StreamBlockJob *s = container_of(job, StreamBlockJob, common);
StreamCompleteData *data = opaque;
BlockDriverState *base = s->base;
if (!block_job_is_cancelled(&s->common) && data->reached_end &&
data->ret == 0) {
const char *base_id = NULL, *base_fmt = NULL;
if (base) {
base_id = s->backing_file_str;
if (base->drv) {
base_fmt = base->drv->format_name;
}
}
data->ret = bdrv_change_backing_file(job->bs, base_id, base_fmt);
close_unused_images(job->bs, base, base_id);
}
g_free(s->backing_file_str);
block_job_completed(&s->common, data->ret);
g_free(data);
bdrv_refresh_limits(top);
}
static void coroutine_fn stream_run(void *opaque)
{
StreamBlockJob *s = opaque;
StreamCompleteData *data;
BlockDriverState *bs = s->common.bs;
BlockDriverState *base = s->base;
int64_t sector_num, end;
@@ -189,14 +159,14 @@ wait:
BlockErrorAction action =
block_job_error_action(&s->common, s->common.bs, s->on_error,
true, -ret);
if (action == BLOCK_ERROR_ACTION_STOP) {
if (action == BDRV_ACTION_STOP) {
n = 0;
continue;
}
if (error == 0) {
error = ret;
}
if (action == BLOCK_ERROR_ACTION_REPORT) {
if (action == BDRV_ACTION_REPORT) {
break;
}
}
@@ -213,13 +183,20 @@ wait:
/* Do not remove the backing file if an error was there but ignored. */
ret = error;
qemu_vfree(buf);
if (!block_job_is_cancelled(&s->common) && sector_num == end && ret == 0) {
const char *base_id = NULL, *base_fmt = NULL;
if (base) {
base_id = s->backing_file_id;
if (base->drv) {
base_fmt = base->drv->format_name;
}
}
ret = bdrv_change_backing_file(bs, base_id, base_fmt);
close_unused_images(bs, base, base_id);
}
/* Modify backing chain and close BDSes in main loop */
data = g_malloc(sizeof(*data));
data->ret = ret;
data->reached_end = sector_num == end;
block_job_defer_to_main_loop(&s->common, stream_complete, data);
qemu_vfree(buf);
block_job_completed(&s->common, ret);
}
static void stream_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -240,9 +217,9 @@ static const BlockJobDriver stream_job_driver = {
};
void stream_start(BlockDriverState *bs, BlockDriverState *base,
const char *backing_file_str, int64_t speed,
const char *base_id, int64_t speed,
BlockdevOnError on_error,
BlockCompletionFunc *cb,
BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
StreamBlockJob *s;
@@ -260,7 +237,9 @@ void stream_start(BlockDriverState *bs, BlockDriverState *base,
}
s->base = base;
s->backing_file_str = g_strdup(backing_file_str);
if (base_id) {
pstrcpy(s->backing_file_id, sizeof(s->backing_file_id), base_id);
}
s->on_error = on_error;
s->common.co = qemu_coroutine_create(stream_run);

View File

@@ -120,18 +120,8 @@ typedef unsigned char uuid_t[16];
#define VDI_IS_ALLOCATED(X) ((X) < VDI_DISCARDED)
/* The bmap will take up VDI_BLOCKS_IN_IMAGE_MAX * sizeof(uint32_t) bytes; since
* the bmap is read and written in a single operation, its size needs to be
* limited to INT_MAX; furthermore, when opening an image, the bmap size is
* rounded up to be aligned on BDRV_SECTOR_SIZE.
* Therefore this should satisfy the following:
* VDI_BLOCKS_IN_IMAGE_MAX * sizeof(uint32_t) + BDRV_SECTOR_SIZE == INT_MAX + 1
* (INT_MAX + 1 is the first value not representable as an int)
* This guarantees that any value below or equal to the constant will, when
* multiplied by sizeof(uint32_t) and rounded up to a BDRV_SECTOR_SIZE boundary,
* still be below or equal to INT_MAX. */
#define VDI_BLOCKS_IN_IMAGE_MAX \
((unsigned)((INT_MAX + 1u - BDRV_SECTOR_SIZE) / sizeof(uint32_t)))
/* max blocks in image is (0xffffffff / 4) */
#define VDI_BLOCKS_IN_IMAGE_MAX 0x3fffffff
#define VDI_DISK_SIZE_MAX ((uint64_t)VDI_BLOCKS_IN_IMAGE_MAX * \
(uint64_t)DEFAULT_CLUSTER_SIZE)
@@ -147,14 +137,12 @@ static inline int uuid_is_null(const uuid_t uu)
return memcmp(uu, null_uuid, sizeof(uuid_t)) == 0;
}
# if defined(CONFIG_VDI_DEBUG)
static inline void uuid_unparse(const uuid_t uu, char *out)
{
snprintf(out, 37, UUID_FMT,
uu[0], uu[1], uu[2], uu[3], uu[4], uu[5], uu[6], uu[7],
uu[8], uu[9], uu[10], uu[11], uu[12], uu[13], uu[14], uu[15]);
}
# endif
#endif
typedef struct {
@@ -251,6 +239,7 @@ static void vdi_header_to_le(VdiHeader *header)
cpu_to_le32s(&header->block_extra);
cpu_to_le32s(&header->blocks_in_image);
cpu_to_le32s(&header->blocks_allocated);
cpu_to_le32s(&header->blocks_allocated);
uuid_convert(header->uuid_image);
uuid_convert(header->uuid_last_snap);
uuid_convert(header->uuid_link);
@@ -304,12 +293,7 @@ static int vdi_check(BlockDriverState *bs, BdrvCheckResult *res,
return -ENOTSUP;
}
bmap = g_try_new(uint32_t, s->header.blocks_in_image);
if (s->header.blocks_in_image && bmap == NULL) {
res->check_errors++;
return -ENOMEM;
}
bmap = g_malloc(s->header.blocks_in_image * sizeof(uint32_t));
memset(bmap, 0xff, s->header.blocks_in_image * sizeof(uint32_t));
/* Check block map and value of blocks_allocated. */
@@ -367,23 +351,23 @@ static int vdi_make_empty(BlockDriverState *bs)
static int vdi_probe(const uint8_t *buf, int buf_size, const char *filename)
{
const VdiHeader *header = (const VdiHeader *)buf;
int ret = 0;
int result = 0;
logout("\n");
if (buf_size < sizeof(*header)) {
/* Header too small, no VDI. */
} else if (le32_to_cpu(header->signature) == VDI_SIGNATURE) {
ret = 100;
result = 100;
}
if (ret == 0) {
if (result == 0) {
logout("no vdi image\n");
} else {
logout("%s", header->text);
}
return ret;
return result;
}
static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
@@ -419,39 +403,39 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
We accept them but round the disk size to the next multiple of
SECTOR_SIZE. */
logout("odd disk size %" PRIu64 " B, round up\n", header.disk_size);
header.disk_size = ROUND_UP(header.disk_size, SECTOR_SIZE);
header.disk_size += SECTOR_SIZE - 1;
header.disk_size &= ~(SECTOR_SIZE - 1);
}
if (header.signature != VDI_SIGNATURE) {
error_setg(errp, "Image not in VDI format (bad signature %08" PRIx32
")", header.signature);
error_setg(errp, "Image not in VDI format (bad signature %08x)", header.signature);
ret = -EINVAL;
goto fail;
} else if (header.version != VDI_VERSION_1_1) {
error_setg(errp, "unsupported VDI image (version %" PRIu32 ".%" PRIu32
")", header.version >> 16, header.version & 0xffff);
error_setg(errp, "unsupported VDI image (version %u.%u)",
header.version >> 16, header.version & 0xffff);
ret = -ENOTSUP;
goto fail;
} else if (header.offset_bmap % SECTOR_SIZE != 0) {
/* We only support block maps which start on a sector boundary. */
error_setg(errp, "unsupported VDI image (unaligned block map offset "
"0x%" PRIx32 ")", header.offset_bmap);
"0x%x)", header.offset_bmap);
ret = -ENOTSUP;
goto fail;
} else if (header.offset_data % SECTOR_SIZE != 0) {
/* We only support data blocks which start on a sector boundary. */
error_setg(errp, "unsupported VDI image (unaligned data offset 0x%"
PRIx32 ")", header.offset_data);
error_setg(errp, "unsupported VDI image (unaligned data offset 0x%x)",
header.offset_data);
ret = -ENOTSUP;
goto fail;
} else if (header.sector_size != SECTOR_SIZE) {
error_setg(errp, "unsupported VDI image (sector size %" PRIu32
" is not %u)", header.sector_size, SECTOR_SIZE);
error_setg(errp, "unsupported VDI image (sector size %u is not %u)",
header.sector_size, SECTOR_SIZE);
ret = -ENOTSUP;
goto fail;
} else if (header.block_size != DEFAULT_CLUSTER_SIZE) {
error_setg(errp, "unsupported VDI image (block size %" PRIu32
" is not %u)", header.block_size, DEFAULT_CLUSTER_SIZE);
error_setg(errp, "unsupported VDI image (block size %u is not %u)",
header.block_size, DEFAULT_CLUSTER_SIZE);
ret = -ENOTSUP;
goto fail;
} else if (header.disk_size >
@@ -486,13 +470,8 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
s->header = header;
bmap_size = header.blocks_in_image * sizeof(uint32_t);
bmap_size = DIV_ROUND_UP(bmap_size, SECTOR_SIZE);
s->bmap = qemu_try_blockalign(bs->file, bmap_size * SECTOR_SIZE);
if (s->bmap == NULL) {
ret = -ENOMEM;
goto fail;
}
bmap_size = (bmap_size + SECTOR_SIZE - 1) / SECTOR_SIZE;
s->bmap = g_malloc(bmap_size * SECTOR_SIZE);
ret = bdrv_read(bs->file, s->bmap_sector, (uint8_t *)s->bmap, bmap_size);
if (ret < 0) {
goto fail_free_bmap;
@@ -501,13 +480,13 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
/* Disable migration when vdi images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vdi", bdrv_get_device_name(bs), "live migration");
"vdi", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
fail_free_bmap:
qemu_vfree(s->bmap);
g_free(s->bmap);
fail:
return ret;
@@ -693,9 +672,11 @@ static int vdi_co_write(BlockDriverState *bs,
return ret;
}
static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
static int vdi_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int ret = 0;
int fd;
int result = 0;
uint64_t bytes = 0;
uint32_t blocks;
size_t block_size = DEFAULT_CLUSTER_SIZE;
@@ -703,54 +684,52 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
VdiHeader header;
size_t i;
size_t bmap_size;
int64_t offset = 0;
Error *local_err = NULL;
BlockDriverState *bs = NULL;
uint32_t *bmap = NULL;
logout("\n");
/* Read out options. */
bytes = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
bytes = options->value.n;
#if defined(CONFIG_VDI_BLOCK_SIZE)
/* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
block_size = qemu_opt_get_size_del(opts,
BLOCK_OPT_CLUSTER_SIZE,
DEFAULT_CLUSTER_SIZE);
} else if (!strcmp(options->name, BLOCK_OPT_CLUSTER_SIZE)) {
if (options->value.n) {
/* TODO: Additional checks (SECTOR_SIZE * 2^n, ...). */
block_size = options->value.n;
}
#endif
#if defined(CONFIG_VDI_STATIC_IMAGE)
if (qemu_opt_get_bool_del(opts, BLOCK_OPT_STATIC, false)) {
image_type = VDI_TYPE_STATIC;
}
} else if (!strcmp(options->name, BLOCK_OPT_STATIC)) {
if (options->value.n) {
image_type = VDI_TYPE_STATIC;
}
#endif
}
options++;
}
if (bytes > VDI_DISK_SIZE_MAX) {
ret = -ENOTSUP;
result = -ENOTSUP;
error_setg(errp, "Unsupported VDI image size (size is 0x%" PRIx64
", max supported is 0x%" PRIx64 ")",
bytes, VDI_DISK_SIZE_MAX);
goto exit;
}
ret = bdrv_create_file(filename, opts, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto exit;
}
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
fd = qemu_open(filename,
O_WRONLY | O_CREAT | O_TRUNC | O_BINARY | O_LARGEFILE,
0644);
if (fd < 0) {
result = -errno;
goto exit;
}
/* We need enough blocks to store the given disk size,
so always round up. */
blocks = DIV_ROUND_UP(bytes, block_size);
blocks = (bytes + block_size - 1) / block_size;
bmap_size = blocks * sizeof(uint32_t);
bmap_size = ROUND_UP(bmap_size, SECTOR_SIZE);
bmap_size = ((bmap_size + SECTOR_SIZE - 1) & ~(SECTOR_SIZE -1));
memset(&header, 0, sizeof(header));
pstrcpy(header.text, sizeof(header.text), VDI_TEXT);
@@ -774,20 +753,12 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
vdi_header_print(&header);
#endif
vdi_header_to_le(&header);
ret = bdrv_pwrite_sync(bs, offset, &header, sizeof(header));
if (ret < 0) {
error_setg(errp, "Error writing header to %s", filename);
goto exit;
if (write(fd, &header, sizeof(header)) < 0) {
result = -errno;
}
offset += sizeof(header);
if (bmap_size > 0) {
bmap = g_try_malloc0(bmap_size);
if (bmap == NULL) {
ret = -ENOMEM;
error_setg(errp, "Could not allocate bmap");
goto exit;
}
uint32_t *bmap = g_malloc0(bmap_size);
for (i = 0; i < blocks; i++) {
if (image_type == VDI_TYPE_STATIC) {
bmap[i] = i;
@@ -795,71 +766,59 @@ static int vdi_create(const char *filename, QemuOpts *opts, Error **errp)
bmap[i] = VDI_UNALLOCATED;
}
}
ret = bdrv_pwrite_sync(bs, offset, bmap, bmap_size);
if (ret < 0) {
error_setg(errp, "Error writing bmap to %s", filename);
goto exit;
if (write(fd, bmap, bmap_size) < 0) {
result = -errno;
}
offset += bmap_size;
g_free(bmap);
}
if (image_type == VDI_TYPE_STATIC) {
ret = bdrv_truncate(bs, offset + blocks * block_size);
if (ret < 0) {
error_setg(errp, "Failed to statically allocate %s", filename);
goto exit;
if (ftruncate(fd, sizeof(header) + bmap_size + blocks * block_size)) {
result = -errno;
}
}
if (close(fd) < 0) {
result = -errno;
}
exit:
bdrv_unref(bs);
g_free(bmap);
return ret;
return result;
}
static void vdi_close(BlockDriverState *bs)
{
BDRVVdiState *s = bs->opaque;
qemu_vfree(s->bmap);
g_free(s->bmap);
migrate_del_blocker(s->migration_blocker);
error_free(s->migration_blocker);
}
static QemuOptsList vdi_create_opts = {
.name = "vdi-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(vdi_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
static QEMUOptionParameter vdi_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
#if defined(CONFIG_VDI_BLOCK_SIZE)
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = QEMU_OPT_SIZE,
.help = "VDI cluster (block) size",
.def_value_str = stringify(DEFAULT_CLUSTER_SIZE)
},
{
.name = BLOCK_OPT_CLUSTER_SIZE,
.type = OPT_SIZE,
.help = "VDI cluster (block) size",
.value = { .n = DEFAULT_CLUSTER_SIZE },
},
#endif
#if defined(CONFIG_VDI_STATIC_IMAGE)
{
.name = BLOCK_OPT_STATIC,
.type = QEMU_OPT_BOOL,
.help = "VDI static (pre-allocated) image",
.def_value_str = "off"
},
{
.name = BLOCK_OPT_STATIC,
.type = OPT_FLAG,
.help = "VDI static (pre-allocated) image"
},
#endif
{
.name = BLOCK_OPT_NOCOW,
.type = QEMU_OPT_BOOL,
.help = "Turn off copy-on-write (valid only on btrfs)"
},
/* TODO: An additional option to set UUID values might be useful. */
{ /* end of list */ }
}
/* TODO: An additional option to set UUID values might be useful. */
{ NULL }
};
static BlockDriver bdrv_vdi = {
@@ -881,7 +840,7 @@ static BlockDriver bdrv_vdi = {
.bdrv_get_info = vdi_get_info,
.create_opts = &vdi_create_opts,
.create_options = vdi_create_options,
.bdrv_check = vdi_check,
};

View File

@@ -82,6 +82,8 @@ void vhdx_log_desc_le_import(VHDXLogDescriptor *d)
assert(d != NULL);
le32_to_cpus(&d->signature);
le32_to_cpus(&d->trailing_bytes);
le64_to_cpus(&d->leading_bytes);
le64_to_cpus(&d->file_offset);
le64_to_cpus(&d->sequence_number);
}
@@ -97,15 +99,6 @@ void vhdx_log_desc_le_export(VHDXLogDescriptor *d)
cpu_to_le64s(&d->sequence_number);
}
void vhdx_log_data_le_import(VHDXLogDataSector *d)
{
assert(d != NULL);
le32_to_cpus(&d->data_signature);
le32_to_cpus(&d->sequence_high);
le32_to_cpus(&d->sequence_low);
}
void vhdx_log_data_le_export(VHDXLogDataSector *d)
{
assert(d != NULL);

View File

@@ -84,7 +84,6 @@ static int vhdx_log_peek_hdr(BlockDriverState *bs, VHDXLogEntries *log,
if (ret < 0) {
goto exit;
}
vhdx_log_entry_hdr_le_import(hdr);
exit:
return ret;
@@ -212,7 +211,7 @@ static bool vhdx_log_hdr_is_valid(VHDXLogEntries *log, VHDXLogEntryHeader *hdr,
{
int valid = false;
if (hdr->signature != VHDX_LOG_SIGNATURE) {
if (memcmp(&hdr->signature, "loge", 4)) {
goto exit;
}
@@ -276,12 +275,12 @@ static bool vhdx_log_desc_is_valid(VHDXLogDescriptor *desc,
goto exit;
}
if (desc->signature == VHDX_LOG_ZERO_SIGNATURE) {
if (!memcmp(&desc->signature, "zero", 4)) {
if (desc->zero_length % VHDX_LOG_SECTOR_SIZE == 0) {
/* valid */
ret = true;
}
} else if (desc->signature == VHDX_LOG_DESC_SIGNATURE) {
} else if (!memcmp(&desc->signature, "desc", 4)) {
/* valid */
ret = true;
}
@@ -328,15 +327,13 @@ static int vhdx_compute_desc_sectors(uint32_t desc_cnt)
* passed into this function. Each descriptor will also be validated,
* and error returned if any are invalid. */
static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
VHDXLogEntries *log, VHDXLogDescEntries **buffer,
bool convert_endian)
VHDXLogEntries *log, VHDXLogDescEntries **buffer)
{
int ret = 0;
uint32_t desc_sectors;
uint32_t sectors_read;
VHDXLogEntryHeader hdr;
VHDXLogDescEntries *desc_entries = NULL;
VHDXLogDescriptor desc;
int i;
assert(*buffer == NULL);
@@ -345,19 +342,14 @@ static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
if (ret < 0) {
goto exit;
}
vhdx_log_entry_hdr_le_import(&hdr);
if (vhdx_log_hdr_is_valid(log, &hdr, s) == false) {
ret = -EINVAL;
goto exit;
}
desc_sectors = vhdx_compute_desc_sectors(hdr.descriptor_count);
desc_entries = qemu_try_blockalign(bs->file,
desc_sectors * VHDX_LOG_SECTOR_SIZE);
if (desc_entries == NULL) {
ret = -ENOMEM;
goto exit;
}
desc_entries = qemu_blockalign(bs, desc_sectors * VHDX_LOG_SECTOR_SIZE);
ret = vhdx_log_read_sectors(bs, log, &sectors_read, desc_entries,
desc_sectors, false);
@@ -371,19 +363,12 @@ static int vhdx_log_read_desc(BlockDriverState *bs, BDRVVHDXState *s,
/* put in proper endianness, and validate each desc */
for (i = 0; i < hdr.descriptor_count; i++) {
desc = desc_entries->desc[i];
vhdx_log_desc_le_import(&desc);
if (convert_endian) {
desc_entries->desc[i] = desc;
}
if (vhdx_log_desc_is_valid(&desc, &hdr) == false) {
vhdx_log_desc_le_import(&desc_entries->desc[i]);
if (vhdx_log_desc_is_valid(&desc_entries->desc[i], &hdr) == false) {
ret = -EINVAL;
goto free_and_exit;
}
}
if (convert_endian) {
desc_entries->hdr = hdr;
}
*buffer = desc_entries;
goto exit;
@@ -418,7 +403,7 @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc,
buffer = qemu_blockalign(bs, VHDX_LOG_SECTOR_SIZE);
if (desc->signature == VHDX_LOG_DESC_SIGNATURE) {
if (!memcmp(&desc->signature, "desc", 4)) {
/* data sector */
if (data == NULL) {
ret = -EFAULT;
@@ -446,15 +431,10 @@ static int vhdx_log_flush_desc(BlockDriverState *bs, VHDXLogDescriptor *desc,
memcpy(buffer+offset, &desc->trailing_bytes, 4);
} else if (desc->signature == VHDX_LOG_ZERO_SIGNATURE) {
} else if (!memcmp(&desc->signature, "zero", 4)) {
/* write 'count' sectors of sector */
memset(buffer, 0, VHDX_LOG_SECTOR_SIZE);
count = desc->zero_length / VHDX_LOG_SECTOR_SIZE;
} else {
error_report("Invalid VHDX log descriptor entry signature 0x%" PRIx32,
desc->signature);
ret = -EINVAL;
goto exit;
}
file_offset = desc->file_offset;
@@ -513,13 +493,13 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
goto exit;
}
ret = vhdx_log_read_desc(bs, s, &logs->log, &desc_entries, true);
ret = vhdx_log_read_desc(bs, s, &logs->log, &desc_entries);
if (ret < 0) {
goto exit;
}
for (i = 0; i < desc_entries->hdr.descriptor_count; i++) {
if (desc_entries->desc[i].signature == VHDX_LOG_DESC_SIGNATURE) {
if (!memcmp(&desc_entries->desc[i].signature, "desc", 4)) {
/* data sector, so read a sector to flush */
ret = vhdx_log_read_sectors(bs, &logs->log, &sectors_read,
data, 1, false);
@@ -530,7 +510,6 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
ret = -EINVAL;
goto exit;
}
vhdx_log_data_le_import(data);
}
ret = vhdx_log_flush_desc(bs, &desc_entries->desc[i], data);
@@ -579,6 +558,9 @@ static int vhdx_validate_log_entry(BlockDriverState *bs, BDRVVHDXState *s,
goto inc_and_exit;
}
vhdx_log_entry_hdr_le_import(&hdr);
if (vhdx_log_hdr_is_valid(log, &hdr, s) == false) {
goto inc_and_exit;
}
@@ -591,13 +573,13 @@ static int vhdx_validate_log_entry(BlockDriverState *bs, BDRVVHDXState *s,
desc_sectors = vhdx_compute_desc_sectors(hdr.descriptor_count);
/* Read all log sectors, and calculate log checksum */
/* Read desc sectors, and calculate log checksum */
total_sectors = hdr.entry_length / VHDX_LOG_SECTOR_SIZE;
/* read_desc() will increment the read idx */
ret = vhdx_log_read_desc(bs, s, log, &desc_buffer, false);
ret = vhdx_log_read_desc(bs, s, log, &desc_buffer);
if (ret < 0) {
goto free_and_exit;
}
@@ -620,7 +602,7 @@ static int vhdx_validate_log_entry(BlockDriverState *bs, BDRVVHDXState *s,
}
}
crc ^= 0xffffffff;
if (crc != hdr.checksum) {
if (crc != desc_buffer->hdr.checksum) {
goto free_and_exit;
}
@@ -923,7 +905,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
buffer = qemu_blockalign(bs, total_length);
memcpy(buffer, &new_hdr, sizeof(new_hdr));
new_desc = buffer + sizeof(new_hdr);
new_desc = (VHDXLogDescriptor *) (buffer + sizeof(new_hdr));
data_sector = buffer + (desc_sectors * VHDX_LOG_SECTOR_SIZE);
data_tmp = data;
@@ -980,6 +962,7 @@ static int vhdx_log_write(BlockDriverState *bs, BDRVVHDXState *s,
* last data sector */
vhdx_update_checksum(buffer, total_length,
offsetof(VHDXLogEntryHeader, checksum));
cpu_to_le32s((uint32_t *)(buffer + 4));
/* now write to the log */
ret = vhdx_log_write_sectors(bs, &s->log, &sectors_written, buffer,

View File

@@ -99,8 +99,7 @@ static const MSGUID logical_sector_guid = { .data1 = 0x8141bf1d,
/* Each parent type must have a valid GUID; this is for parent images
* of type 'VHDX'. If we were to allow e.g. a QCOW2 parent, we would
* need to make up our own QCOW2 GUID type */
static const MSGUID parent_vhdx_guid __attribute__((unused))
= { .data1 = 0xb04aefb7,
static const MSGUID parent_vhdx_guid = { .data1 = 0xb04aefb7,
.data2 = 0xd19e,
.data3 = 0x4a81,
.data4 = { 0xb7, 0x89, 0x25, 0xb8,
@@ -136,8 +135,10 @@ typedef struct VHDXSectorInfo {
* buf: buffer pointer
* size: size of buffer (must be > crc_offset+4)
*
* Note: The buffer should have all multi-byte data in little-endian format,
* and the resulting checksum is in little endian format.
* Note: The resulting checksum is in the CPU endianness, not necessarily
* in the file format endianness (LE). Any header export to disk should
* make sure that vhdx_header_le_export() is used to convert to the
* correct endianness
*/
uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset)
{
@@ -148,7 +149,6 @@ uint32_t vhdx_update_checksum(uint8_t *buf, size_t size, int crc_offset)
memset(buf + crc_offset, 0, sizeof(crc));
crc = crc32c(0xffffffff, buf, size);
cpu_to_le32s(&crc);
memcpy(buf + crc_offset, &crc, sizeof(crc));
return crc;
@@ -300,7 +300,7 @@ static int vhdx_write_header(BlockDriverState *bs_file, VHDXHeader *hdr,
{
uint8_t *buffer = NULL;
int ret;
VHDXHeader *header_le;
VHDXHeader header_le;
assert(bs_file != NULL);
assert(hdr != NULL);
@@ -321,12 +321,11 @@ static int vhdx_write_header(BlockDriverState *bs_file, VHDXHeader *hdr,
}
/* overwrite the actual VHDXHeader portion */
header_le = (VHDXHeader *)buffer;
memcpy(header_le, hdr, sizeof(VHDXHeader));
vhdx_header_le_export(hdr, header_le);
vhdx_update_checksum(buffer, VHDX_HEADER_SIZE,
offsetof(VHDXHeader, checksum));
ret = bdrv_pwrite_sync(bs_file, offset, header_le, sizeof(VHDXHeader));
memcpy(buffer, hdr, sizeof(VHDXHeader));
hdr->checksum = vhdx_update_checksum(buffer, VHDX_HEADER_SIZE,
offsetof(VHDXHeader, checksum));
vhdx_header_le_export(hdr, &header_le);
ret = bdrv_pwrite_sync(bs_file, offset, &header_le, sizeof(VHDXHeader));
exit:
qemu_vfree(buffer);
@@ -433,14 +432,13 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
}
/* copy over just the relevant portion that we need */
memcpy(header1, buffer, sizeof(VHDXHeader));
vhdx_header_le_import(header1);
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4)) {
vhdx_header_le_import(header1);
if (header1->signature == VHDX_HEADER_SIGNATURE &&
header1->version == 1) {
h1_seq = header1->sequence_number;
h1_valid = true;
}
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
!memcmp(&header1->signature, "head", 4) &&
header1->version == 1) {
h1_seq = header1->sequence_number;
h1_valid = true;
}
ret = bdrv_pread(bs->file, VHDX_HEADER2_OFFSET, buffer, VHDX_HEADER_SIZE);
@@ -449,14 +447,13 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
}
/* copy over just the relevant portion that we need */
memcpy(header2, buffer, sizeof(VHDXHeader));
vhdx_header_le_import(header2);
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4)) {
vhdx_header_le_import(header2);
if (header2->signature == VHDX_HEADER_SIGNATURE &&
header2->version == 1) {
h2_seq = header2->sequence_number;
h2_valid = true;
}
if (vhdx_checksum_is_valid(buffer, VHDX_HEADER_SIZE, 4) &&
!memcmp(&header2->signature, "head", 4) &&
header2->version == 1) {
h2_seq = header2->sequence_number;
h2_valid = true;
}
/* If there is only 1 valid header (or no valid headers), we
@@ -476,14 +473,7 @@ static void vhdx_parse_header(BlockDriverState *bs, BDRVVHDXState *s,
} else if (h2_seq > h1_seq) {
s->curr_header = 1;
} else {
/* The Microsoft Disk2VHD tool will create 2 identical
* headers, with identical sequence numbers. If the headers are
* identical, don't consider the file corrupt */
if (!memcmp(header1, header2, sizeof(VHDXHeader))) {
s->curr_header = 0;
} else {
goto fail;
}
goto fail;
}
}
@@ -522,21 +512,15 @@ static int vhdx_open_region_tables(BlockDriverState *bs, BDRVVHDXState *s)
goto fail;
}
memcpy(&s->rt, buffer, sizeof(s->rt));
vhdx_region_header_le_import(&s->rt);
offset += sizeof(s->rt);
if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4)) {
if (!vhdx_checksum_is_valid(buffer, VHDX_HEADER_BLOCK_SIZE, 4) ||
memcmp(&s->rt.signature, "regi", 4)) {
ret = -EINVAL;
goto fail;
}
vhdx_region_header_le_import(&s->rt);
if (s->rt.signature != VHDX_REGION_SIGNATURE) {
ret = -EINVAL;
goto fail;
}
/* Per spec, maximum region table entry count is 2047 */
if (s->rt.entry_count > 2047) {
ret = -EINVAL;
@@ -639,7 +623,7 @@ static int vhdx_parse_metadata(BlockDriverState *bs, BDRVVHDXState *s)
vhdx_metadata_header_le_import(&s->metadata_hdr);
if (s->metadata_hdr.signature != VHDX_METADATA_SIGNATURE) {
if (memcmp(&s->metadata_hdr.signature, "metadata", 8)) {
ret = -EINVAL;
goto exit;
}
@@ -959,11 +943,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
}
/* s->bat is freed in vhdx_close() */
s->bat = qemu_try_blockalign(bs->file, s->bat_rt.length);
if (s->bat == NULL) {
ret = -ENOMEM;
goto fail;
}
s->bat = qemu_blockalign(bs, s->bat_rt.length);
ret = bdrv_pread(bs->file, s->bat_offset, s->bat, s->bat_rt.length);
if (ret < 0) {
@@ -1004,7 +984,7 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
/* Disable migration when VHDX images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vhdx", bdrv_get_device_name(bs), "live migration");
"vhdx", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
@@ -1382,7 +1362,7 @@ static int vhdx_create_new_headers(BlockDriverState *bs, uint64_t image_size,
int ret = 0;
VHDXHeader *hdr = NULL;
hdr = g_new0(VHDXHeader, 1);
hdr = g_malloc0(sizeof(VHDXHeader));
hdr->signature = VHDX_HEADER_SIGNATURE;
hdr->sequence_number = g_random_int();
@@ -1408,12 +1388,6 @@ exit:
return ret;
}
#define VHDX_METADATA_ENTRY_BUFFER_SIZE \
(sizeof(VHDXFileParameters) +\
sizeof(VHDXVirtualDiskSize) +\
sizeof(VHDXPage83Data) +\
sizeof(VHDXVirtualDiskLogicalSectorSize) +\
sizeof(VHDXVirtualDiskPhysicalSectorSize))
/*
* Create the Metadata entries.
@@ -1452,7 +1426,11 @@ static int vhdx_create_new_metadata(BlockDriverState *bs,
VHDXVirtualDiskLogicalSectorSize *mt_log_sector_size;
VHDXVirtualDiskPhysicalSectorSize *mt_phys_sector_size;
entry_buffer = g_malloc0(VHDX_METADATA_ENTRY_BUFFER_SIZE);
entry_buffer = g_malloc0(sizeof(VHDXFileParameters) +
sizeof(VHDXVirtualDiskSize) +
sizeof(VHDXPage83Data) +
sizeof(VHDXVirtualDiskLogicalSectorSize) +
sizeof(VHDXVirtualDiskPhysicalSectorSize));
mt_file_params = entry_buffer;
offset += sizeof(VHDXFileParameters);
@@ -1533,7 +1511,7 @@ static int vhdx_create_new_metadata(BlockDriverState *bs,
}
ret = bdrv_pwrite(bs, metadata_offset + (64 * KiB), entry_buffer,
VHDX_METADATA_ENTRY_BUFFER_SIZE);
VHDX_HEADER_BLOCK_SIZE);
if (ret < 0) {
goto exit;
}
@@ -1555,8 +1533,7 @@ exit:
*/
static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s,
uint64_t image_size, VHDXImageType type,
bool use_zero_blocks, uint64_t file_offset,
uint32_t length)
bool use_zero_blocks, VHDXRegionTableEntry *rt_bat)
{
int ret = 0;
uint64_t data_file_offset;
@@ -1571,7 +1548,7 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s,
/* this gives a data start after BAT/bitmap entries, and well
* past any metadata entries (with a 4 MB buffer for future
* expansion */
data_file_offset = file_offset + length + 5 * MiB;
data_file_offset = rt_bat->file_offset + rt_bat->length + 5 * MiB;
total_sectors = image_size >> s->logical_sector_size_bits;
if (type == VHDX_TYPE_DYNAMIC) {
@@ -1595,11 +1572,7 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s,
use_zero_blocks ||
bdrv_has_zero_init(bs) == 0) {
/* for a fixed file, the default BAT entry is not zero */
s->bat = g_try_malloc0(length);
if (length && s->bat == NULL) {
ret = -ENOMEM;
goto exit;
}
s->bat = g_malloc0(rt_bat->length);
block_state = type == VHDX_TYPE_FIXED ? PAYLOAD_BLOCK_FULLY_PRESENT :
PAYLOAD_BLOCK_NOT_PRESENT;
block_state = use_zero_blocks ? PAYLOAD_BLOCK_ZERO : block_state;
@@ -1614,7 +1587,7 @@ static int vhdx_create_bat(BlockDriverState *bs, BDRVVHDXState *s,
cpu_to_le64s(&s->bat[sinfo.bat_idx]);
sector_num += s->sectors_per_block;
}
ret = bdrv_pwrite(bs, file_offset, s->bat, length);
ret = bdrv_pwrite(bs, rt_bat->file_offset, s->bat, rt_bat->length);
if (ret < 0) {
goto exit;
}
@@ -1646,8 +1619,6 @@ static int vhdx_create_new_region_table(BlockDriverState *bs,
int ret = 0;
uint32_t offset = 0;
void *buffer = NULL;
uint64_t bat_file_offset;
uint32_t bat_length;
BDRVVHDXState *s = NULL;
VHDXRegionTableHeader *region_table;
VHDXRegionTableEntry *rt_bat;
@@ -1657,7 +1628,7 @@ static int vhdx_create_new_region_table(BlockDriverState *bs,
/* Populate enough of the BDRVVHDXState to be able to use the
* pre-existing BAT calculation, translation, and update functions */
s = g_new0(BDRVVHDXState, 1);
s = g_malloc0(sizeof(BDRVVHDXState));
s->chunk_ratio = (VHDX_MAX_SECTORS_PER_BLOCK) *
(uint64_t) sector_size / (uint64_t) block_size;
@@ -1696,26 +1667,19 @@ static int vhdx_create_new_region_table(BlockDriverState *bs,
rt_metadata->length = 1 * MiB; /* min size, and more than enough */
*metadata_offset = rt_metadata->file_offset;
bat_file_offset = rt_bat->file_offset;
bat_length = rt_bat->length;
vhdx_region_header_le_export(region_table);
vhdx_region_entry_le_export(rt_bat);
vhdx_region_entry_le_export(rt_metadata);
vhdx_update_checksum(buffer, VHDX_HEADER_BLOCK_SIZE,
offsetof(VHDXRegionTableHeader, checksum));
/* The region table gives us the data we need to create the BAT,
* so do that now */
ret = vhdx_create_bat(bs, s, image_size, type, use_zero_blocks,
bat_file_offset, bat_length);
if (ret < 0) {
goto exit;
}
ret = vhdx_create_bat(bs, s, image_size, type, use_zero_blocks, rt_bat);
/* Now write out the region headers to disk */
vhdx_region_header_le_export(region_table);
vhdx_region_entry_le_export(rt_bat);
vhdx_region_entry_le_export(rt_metadata);
ret = bdrv_pwrite(bs, VHDX_REGION_TABLE_OFFSET, buffer,
VHDX_HEADER_BLOCK_SIZE);
if (ret < 0) {
@@ -1728,6 +1692,7 @@ static int vhdx_create_new_region_table(BlockDriverState *bs,
goto exit;
}
exit:
g_free(s);
g_free(buffer);
@@ -1751,7 +1716,8 @@ exit:
* .---- ~ ----------- ~ ------------ ~ ---------------- ~ -----------.
* 1MB
*/
static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
static int vhdx_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int ret = 0;
uint64_t image_size = (uint64_t) 2 * GiB;
@@ -1764,16 +1730,24 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
gunichar2 *creator = NULL;
glong creator_items;
BlockDriverState *bs;
char *type = NULL;
const char *type = NULL;
VHDXImageType image_type;
Error *local_err = NULL;
image_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
log_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_LOG_SIZE, 0);
block_size = qemu_opt_get_size_del(opts, VHDX_BLOCK_OPT_BLOCK_SIZE, 0);
type = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
use_zero_blocks = qemu_opt_get_bool_del(opts, VHDX_BLOCK_OPT_ZERO, false);
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
image_size = options->value.n;
} else if (!strcmp(options->name, VHDX_BLOCK_OPT_LOG_SIZE)) {
log_size = options->value.n;
} else if (!strcmp(options->name, VHDX_BLOCK_OPT_BLOCK_SIZE)) {
block_size = options->value.n;
} else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
type = options->value.s;
} else if (!strcmp(options->name, VHDX_BLOCK_OPT_ZERO)) {
use_zero_blocks = options->value.n != 0;
}
options++;
}
if (image_size > VHDX_MAX_IMAGE_SIZE) {
error_setg_errno(errp, EINVAL, "Image size too large; max of 64TB");
@@ -1782,7 +1756,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
}
if (type == NULL) {
type = g_strdup("dynamic");
type = "dynamic";
}
if (!strcmp(type, "dynamic")) {
@@ -1822,7 +1796,7 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
block_size = block_size > VHDX_BLOCK_SIZE_MAX ? VHDX_BLOCK_SIZE_MAX :
block_size;
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, options, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto exit;
@@ -1878,10 +1852,10 @@ static int vhdx_create(const char *filename, QemuOpts *opts, Error **errp)
}
delete_and_exit:
bdrv_unref(bs);
exit:
g_free(type);
g_free(creator);
return ret;
}
@@ -1904,41 +1878,37 @@ static int vhdx_check(BlockDriverState *bs, BdrvCheckResult *result,
return 0;
}
static QemuOptsList vhdx_create_opts = {
.name = "vhdx-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(vhdx_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size; max of 64TB."
},
{
.name = VHDX_BLOCK_OPT_LOG_SIZE,
.type = QEMU_OPT_SIZE,
.def_value_str = stringify(DEFAULT_LOG_SIZE),
.help = "Log size; min 1MB."
},
{
.name = VHDX_BLOCK_OPT_BLOCK_SIZE,
.type = QEMU_OPT_SIZE,
.def_value_str = stringify(0),
.help = "Block Size; min 1MB, max 256MB. " \
"0 means auto-calculate based on image size."
},
{
.name = BLOCK_OPT_SUBFMT,
.type = QEMU_OPT_STRING,
.help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
"Default is 'dynamic'."
},
{
.name = VHDX_BLOCK_OPT_ZERO,
.type = QEMU_OPT_BOOL,
.help = "Force use of payload blocks of type 'ZERO'. Non-standard."
},
{ NULL }
}
static QEMUOptionParameter vhdx_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size; max of 64TB."
},
{
.name = VHDX_BLOCK_OPT_LOG_SIZE,
.type = OPT_SIZE,
.value.n = 1 * MiB,
.help = "Log size; min 1MB."
},
{
.name = VHDX_BLOCK_OPT_BLOCK_SIZE,
.type = OPT_SIZE,
.value.n = 0,
.help = "Block Size; min 1MB, max 256MB. " \
"0 means auto-calculate based on image size."
},
{
.name = BLOCK_OPT_SUBFMT,
.type = OPT_STRING,
.help = "VHDX format type, can be either 'dynamic' or 'fixed'. "\
"Default is 'dynamic'."
},
{
.name = VHDX_BLOCK_OPT_ZERO,
.type = OPT_FLAG,
.help = "Force use of payload blocks of type 'ZERO'. Non-standard."
},
{ NULL }
};
static BlockDriver bdrv_vhdx = {
@@ -1954,7 +1924,7 @@ static BlockDriver bdrv_vhdx = {
.bdrv_get_info = vhdx_get_info,
.bdrv_check = vhdx_check,
.create_opts = &vhdx_create_opts,
.create_options = vhdx_create_options,
};
static void bdrv_vhdx_init(void)

View File

@@ -23,7 +23,6 @@
#define GiB (MiB * 1024)
#define TiB ((uint64_t) GiB * 1024)
#define DEFAULT_LOG_SIZE 1048576 /* 1MiB */
/* Structures and fields present in the VHDX file */
/* The header section has the following blocks,
@@ -435,7 +434,6 @@ void vhdx_header_le_import(VHDXHeader *h);
void vhdx_header_le_export(VHDXHeader *orig_h, VHDXHeader *new_h);
void vhdx_log_desc_le_import(VHDXLogDescriptor *d);
void vhdx_log_desc_le_export(VHDXLogDescriptor *d);
void vhdx_log_data_le_import(VHDXLogDataSector *d);
void vhdx_log_data_le_export(VHDXLogDataSector *d);
void vhdx_log_entry_hdr_le_import(VHDXLogEntryHeader *hdr);
void vhdx_log_entry_hdr_le_export(VHDXLogEntryHeader *hdr);

View File

@@ -106,7 +106,6 @@ typedef struct VmdkExtent {
uint32_t l2_cache_counts[L2_CACHE_SIZE];
int64_t cluster_sectors;
int64_t next_cluster_sector;
char *type;
} VmdkExtent;
@@ -125,6 +124,7 @@ typedef struct BDRVVmdkState {
} BDRVVmdkState;
typedef struct VmdkMetaData {
uint32_t offset;
unsigned int l1_index;
unsigned int l2_index;
unsigned int l2_offset;
@@ -233,7 +233,7 @@ static void vmdk_free_last_extent(BlockDriverState *bs)
return;
}
s->num_extents--;
s->extents = g_renew(VmdkExtent, s->extents, s->num_extents);
s->extents = g_realloc(s->extents, s->num_extents * sizeof(VmdkExtent));
}
static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
@@ -262,7 +262,7 @@ static uint32_t vmdk_read_cid(BlockDriverState *bs, int parent)
p_name = strstr(desc, cid_str);
if (p_name != NULL) {
p_name += cid_str_size;
sscanf(p_name, "%" SCNx32, &cid);
sscanf(p_name, "%x", &cid);
}
return cid;
@@ -290,7 +290,7 @@ static int vmdk_write_cid(BlockDriverState *bs, uint32_t cid)
p_name = strstr(desc, "CID");
if (p_name != NULL) {
p_name += sizeof("CID");
snprintf(p_name, sizeof(desc) - (p_name - desc), "%" PRIx32 "\n", cid);
snprintf(p_name, sizeof(desc) - (p_name - desc), "%x\n", cid);
pstrcat(desc, sizeof(desc), tmp_desc);
}
@@ -397,7 +397,6 @@ static int vmdk_add_extent(BlockDriverState *bs,
{
VmdkExtent *extent;
BDRVVmdkState *s = bs->opaque;
int64_t nb_sectors;
if (cluster_sectors > 0x200000) {
/* 0x200000 * 512Bytes = 1GB for one cluster is unrealistic */
@@ -413,12 +412,8 @@ static int vmdk_add_extent(BlockDriverState *bs,
return -EFBIG;
}
nb_sectors = bdrv_nb_sectors(file);
if (nb_sectors < 0) {
return nb_sectors;
}
s->extents = g_renew(VmdkExtent, s->extents, s->num_extents + 1);
s->extents = g_realloc(s->extents,
(s->num_extents + 1) * sizeof(VmdkExtent));
extent = &s->extents[s->num_extents];
s->num_extents++;
@@ -432,7 +427,6 @@ static int vmdk_add_extent(BlockDriverState *bs,
extent->l1_entry_sectors = l2_size * cluster_sectors;
extent->l2_size = l2_size;
extent->cluster_sectors = flat ? sectors : cluster_sectors;
extent->next_cluster_sector = ROUND_UP(nb_sectors, cluster_sectors);
if (s->num_extents > 1) {
extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
@@ -454,11 +448,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
/* read the L1 table */
l1_size = extent->l1_size * sizeof(uint32_t);
extent->l1_table = g_try_malloc(l1_size);
if (l1_size && extent->l1_table == NULL) {
return -ENOMEM;
}
extent->l1_table = g_malloc(l1_size);
ret = bdrv_pread(extent->file,
extent->l1_table_offset,
extent->l1_table,
@@ -474,11 +464,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
}
if (extent->l1_backup_table_offset) {
extent->l1_backup_table = g_try_malloc(l1_size);
if (l1_size && extent->l1_backup_table == NULL) {
ret = -ENOMEM;
goto fail_l1;
}
extent->l1_backup_table = g_malloc(l1_size);
ret = bdrv_pread(extent->file,
extent->l1_backup_table_offset,
extent->l1_backup_table,
@@ -495,7 +481,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
}
extent->l2_cache =
g_new(uint32_t, extent->l2_size * L2_CACHE_SIZE);
g_malloc(extent->l2_size * L2_CACHE_SIZE * sizeof(uint32_t));
return 0;
fail_l1b:
g_free(extent->l1_backup_table);
@@ -654,10 +640,10 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
if (le32_to_cpu(header.version) > 3) {
char buf[64];
snprintf(buf, sizeof(buf), "VMDK version %" PRId32,
snprintf(buf, sizeof(buf), "VMDK version %d",
le32_to_cpu(header.version));
error_set(errp, QERR_UNKNOWN_BLOCK_FORMAT_FEATURE,
bdrv_get_device_name(bs), "vmdk", buf);
bs->device_name, "vmdk", buf);
return -ENOTSUP;
} else if (le32_to_cpu(header.version) == 3 && (flags & BDRV_O_RDWR)) {
/* VMware KB 2064959 explains that version 3 added support for
@@ -683,10 +669,10 @@ static int vmdk_open_vmdk4(BlockDriverState *bs,
if (le32_to_cpu(header.flags) & VMDK4_FLAG_RGD) {
l1_backup_offset = le64_to_cpu(header.rgd_offset) << 9;
}
if (bdrv_nb_sectors(file) < le64_to_cpu(header.grain_offset)) {
error_setg(errp, "File truncated, expecting at least %" PRId64 " bytes",
(int64_t)(le64_to_cpu(header.grain_offset)
* BDRV_SECTOR_SIZE));
if (bdrv_getlength(file) <
le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE) {
error_setg(errp, "File truncated, expecting at least %lld bytes",
le64_to_cpu(header.grain_offset) * BDRV_SECTOR_SIZE);
return -EINVAL;
}
@@ -834,7 +820,6 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
ret = vmdk_add_extent(bs, extent_file, true, sectors,
0, 0, 0, 0, 0, &extent, errp);
if (ret < 0) {
bdrv_unref(extent_file);
return ret;
}
extent->flat_start_offset = flat_offset << 9;
@@ -846,15 +831,14 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
} else {
ret = vmdk_open_sparse(bs, extent_file, bs->open_flags, buf, errp);
}
g_free(buf);
if (ret) {
g_free(buf);
bdrv_unref(extent_file);
return ret;
}
extent = &s->extents[s->num_extents - 1];
} else {
error_setg(errp, "Unsupported extent type '%s'", type);
bdrv_unref(extent_file);
return -ENOTSUP;
}
extent->type = g_strdup(type);
@@ -939,7 +923,7 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
/* Disable migration when VMDK images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vmdk", bdrv_get_device_name(bs), "live migration");
"vmdk", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
g_free(buf);
return 0;
@@ -953,7 +937,7 @@ fail:
}
static void vmdk_refresh_limits(BlockDriverState *bs, Error **errp)
static int vmdk_refresh_limits(BlockDriverState *bs)
{
BDRVVmdkState *s = bs->opaque;
int i;
@@ -965,99 +949,61 @@ static void vmdk_refresh_limits(BlockDriverState *bs, Error **errp)
s->extents[i].cluster_sectors);
}
}
return 0;
}
/**
* get_whole_cluster
*
* Copy backing file's cluster that covers @sector_num, otherwise write zero,
* to the cluster at @cluster_sector_num.
*
* If @skip_start_sector < @skip_end_sector, the relative range
* [@skip_start_sector, @skip_end_sector) is not copied or written, and leave
* it for call to write user data in the request.
*/
static int get_whole_cluster(BlockDriverState *bs,
VmdkExtent *extent,
uint64_t cluster_sector_num,
uint64_t sector_num,
uint64_t skip_start_sector,
uint64_t skip_end_sector)
VmdkExtent *extent,
uint64_t cluster_offset,
uint64_t offset,
bool allocate)
{
int ret = VMDK_OK;
int64_t cluster_bytes;
uint8_t *whole_grain;
uint8_t *whole_grain = NULL;
/* For COW, align request sector_num to cluster start */
sector_num = QEMU_ALIGN_DOWN(sector_num, extent->cluster_sectors);
cluster_bytes = extent->cluster_sectors << BDRV_SECTOR_BITS;
whole_grain = qemu_blockalign(bs, cluster_bytes);
if (!bs->backing_hd) {
memset(whole_grain, 0, skip_start_sector << BDRV_SECTOR_BITS);
memset(whole_grain + (skip_end_sector << BDRV_SECTOR_BITS), 0,
cluster_bytes - (skip_end_sector << BDRV_SECTOR_BITS));
}
assert(skip_end_sector <= extent->cluster_sectors);
/* we will be here if it's first write on non-exist grain(cluster).
* try to read from parent image, if exist */
if (bs->backing_hd && !vmdk_is_cid_valid(bs)) {
ret = VMDK_ERROR;
goto exit;
}
/* Read backing data before skip range */
if (skip_start_sector > 0) {
if (bs->backing_hd) {
ret = bdrv_read(bs->backing_hd, sector_num,
whole_grain, skip_start_sector);
if (ret < 0) {
ret = VMDK_ERROR;
goto exit;
}
if (bs->backing_hd) {
whole_grain =
qemu_blockalign(bs, extent->cluster_sectors << BDRV_SECTOR_BITS);
if (!vmdk_is_cid_valid(bs)) {
ret = VMDK_ERROR;
goto exit;
}
ret = bdrv_write(extent->file, cluster_sector_num, whole_grain,
skip_start_sector);
/* floor offset to cluster */
offset -= offset % (extent->cluster_sectors * 512);
ret = bdrv_read(bs->backing_hd, offset >> 9, whole_grain,
extent->cluster_sectors);
if (ret < 0) {
ret = VMDK_ERROR;
goto exit;
}
/* Write grain only into the active image */
ret = bdrv_write(extent->file, cluster_offset, whole_grain,
extent->cluster_sectors);
if (ret < 0) {
ret = VMDK_ERROR;
goto exit;
}
}
/* Read backing data after skip range */
if (skip_end_sector < extent->cluster_sectors) {
if (bs->backing_hd) {
ret = bdrv_read(bs->backing_hd, sector_num + skip_end_sector,
whole_grain + (skip_end_sector << BDRV_SECTOR_BITS),
extent->cluster_sectors - skip_end_sector);
if (ret < 0) {
ret = VMDK_ERROR;
goto exit;
}
}
ret = bdrv_write(extent->file, cluster_sector_num + skip_end_sector,
whole_grain + (skip_end_sector << BDRV_SECTOR_BITS),
extent->cluster_sectors - skip_end_sector);
if (ret < 0) {
ret = VMDK_ERROR;
goto exit;
}
}
exit:
qemu_vfree(whole_grain);
return ret;
}
static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data,
uint32_t offset)
static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data)
{
offset = cpu_to_le32(offset);
uint32_t offset;
QEMU_BUILD_BUG_ON(sizeof(offset) != sizeof(m_data->offset));
offset = cpu_to_le32(m_data->offset);
/* update L2 table */
if (bdrv_pwrite_sync(
extent->file,
((int64_t)m_data->l2_offset * 512)
+ (m_data->l2_index * sizeof(offset)),
+ (m_data->l2_index * sizeof(m_data->offset)),
&offset, sizeof(offset)) < 0) {
return VMDK_ERROR;
}
@@ -1067,7 +1013,7 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data,
if (bdrv_pwrite_sync(
extent->file,
((int64_t)m_data->l2_offset * 512)
+ (m_data->l2_index * sizeof(offset)),
+ (m_data->l2_index * sizeof(m_data->offset)),
&offset, sizeof(offset)) < 0) {
return VMDK_ERROR;
}
@@ -1079,41 +1025,17 @@ static int vmdk_L2update(VmdkExtent *extent, VmdkMetaData *m_data,
return VMDK_OK;
}
/**
* get_cluster_offset
*
* Look up cluster offset in extent file by sector number, and store in
* @cluster_offset.
*
* For flat extents, the start offset as parsed from the description file is
* returned.
*
* For sparse extents, look up in L1, L2 table. If allocate is true, return an
* offset for a new cluster and update L2 cache. If there is a backing file,
* COW is done before returning; otherwise, zeroes are written to the allocated
* cluster. Both COW and zero writing skips the sector range
* [@skip_start_sector, @skip_end_sector) passed in by caller, because caller
* has new data to write there.
*
* Returns: VMDK_OK if cluster exists and mapped in the image.
* VMDK_UNALLOC if cluster is not mapped and @allocate is false.
* VMDK_ERROR if failed.
*/
static int get_cluster_offset(BlockDriverState *bs,
VmdkExtent *extent,
VmdkMetaData *m_data,
uint64_t offset,
bool allocate,
uint64_t *cluster_offset,
uint64_t skip_start_sector,
uint64_t skip_end_sector)
VmdkExtent *extent,
VmdkMetaData *m_data,
uint64_t offset,
int allocate,
uint64_t *cluster_offset)
{
unsigned int l1_index, l2_offset, l2_index;
int min_index, i, j;
uint32_t min_count, *l2_table;
bool zeroed = false;
int64_t ret;
int64_t cluster_sector;
if (m_data) {
m_data->valid = 0;
@@ -1167,41 +1089,52 @@ static int get_cluster_offset(BlockDriverState *bs,
extent->l2_cache_counts[min_index] = 1;
found:
l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
cluster_sector = le32_to_cpu(l2_table[l2_index]);
*cluster_offset = le32_to_cpu(l2_table[l2_index]);
if (m_data) {
m_data->valid = 1;
m_data->l1_index = l1_index;
m_data->l2_index = l2_index;
m_data->offset = *cluster_offset;
m_data->l2_offset = l2_offset;
m_data->l2_cache_entry = &l2_table[l2_index];
}
if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
if (extent->has_zero_grain && *cluster_offset == VMDK_GTE_ZEROED) {
zeroed = true;
}
if (!cluster_sector || zeroed) {
if (!*cluster_offset || zeroed) {
if (!allocate) {
return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
}
cluster_sector = extent->next_cluster_sector;
extent->next_cluster_sector += extent->cluster_sectors;
/* Avoid the L2 tables update for the images that have snapshots. */
*cluster_offset = bdrv_getlength(extent->file);
if (!extent->compressed) {
bdrv_truncate(
extent->file,
*cluster_offset + (extent->cluster_sectors << 9)
);
}
*cluster_offset >>= 9;
l2_table[l2_index] = cpu_to_le32(*cluster_offset);
/* First of all we write grain itself, to avoid race condition
* that may to corrupt the image.
* This problem may occur because of insufficient space on host disk
* or inappropriate VM shutdown.
*/
ret = get_whole_cluster(bs, extent,
cluster_sector,
offset >> BDRV_SECTOR_BITS,
skip_start_sector, skip_end_sector);
if (ret) {
return ret;
if (get_whole_cluster(
bs, extent, *cluster_offset, offset, allocate) == -1) {
return VMDK_ERROR;
}
if (m_data) {
m_data->offset = *cluster_offset;
}
}
*cluster_offset = cluster_sector << BDRV_SECTOR_BITS;
*cluster_offset <<= 9;
return VMDK_OK;
}
@@ -1236,8 +1169,7 @@ static int64_t coroutine_fn vmdk_co_get_block_status(BlockDriverState *bs,
}
qemu_co_mutex_lock(&s->lock);
ret = get_cluster_offset(bs, extent, NULL,
sector_num * 512, false, &offset,
0, 0);
sector_num * 512, 0, &offset);
qemu_co_mutex_unlock(&s->lock);
switch (ret) {
@@ -1390,9 +1322,9 @@ static int vmdk_read(BlockDriverState *bs, int64_t sector_num,
if (!extent) {
return -EIO;
}
ret = get_cluster_offset(bs, extent, NULL,
sector_num << 9, false, &cluster_offset,
0, 0);
ret = get_cluster_offset(
bs, extent, NULL,
sector_num << 9, 0, &cluster_offset);
extent_begin_sector = extent->end_sector - extent->sectors;
extent_relative_sector_num = sector_num - extent_begin_sector;
index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
@@ -1473,17 +1405,12 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
if (!extent) {
return -EIO;
}
extent_begin_sector = extent->end_sector - extent->sectors;
extent_relative_sector_num = sector_num - extent_begin_sector;
index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
}
ret = get_cluster_offset(bs, extent, &m_data, sector_num << 9,
!(extent->compressed || zeroed),
&cluster_offset,
index_in_cluster, index_in_cluster + n);
ret = get_cluster_offset(
bs,
extent,
&m_data,
sector_num << 9, !extent->compressed,
&cluster_offset);
if (extent->compressed) {
if (ret == VMDK_OK) {
/* Refuse write to allocated cluster for streamOptimized */
@@ -1492,13 +1419,24 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
return -EIO;
} else {
/* allocate */
ret = get_cluster_offset(bs, extent, &m_data, sector_num << 9,
true, &cluster_offset, 0, 0);
ret = get_cluster_offset(
bs,
extent,
&m_data,
sector_num << 9, 1,
&cluster_offset);
}
}
if (ret == VMDK_ERROR) {
return -EINVAL;
}
extent_begin_sector = extent->end_sector - extent->sectors;
extent_relative_sector_num = sector_num - extent_begin_sector;
index_in_cluster = extent_relative_sector_num % extent->cluster_sectors;
n = extent->cluster_sectors - index_in_cluster;
if (n > nb_sectors) {
n = nb_sectors;
}
if (zeroed) {
/* Do zeroed write, buf is ignored */
if (extent->has_zero_grain &&
@@ -1506,9 +1444,9 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
n >= extent->cluster_sectors) {
n = extent->cluster_sectors;
if (!zero_dry_run) {
m_data.offset = VMDK_GTE_ZEROED;
/* update L2 tables */
if (vmdk_L2update(extent, &m_data, VMDK_GTE_ZEROED)
!= VMDK_OK) {
if (vmdk_L2update(extent, &m_data) != VMDK_OK) {
return -EIO;
}
}
@@ -1524,9 +1462,7 @@ static int vmdk_write(BlockDriverState *bs, int64_t sector_num,
}
if (m_data.valid) {
/* update L2 tables */
if (vmdk_L2update(extent, &m_data,
cluster_offset >> BDRV_SECTOR_BITS)
!= VMDK_OK) {
if (vmdk_L2update(extent, &m_data) != VMDK_OK) {
return -EIO;
}
}
@@ -1559,19 +1495,6 @@ static coroutine_fn int vmdk_co_write(BlockDriverState *bs, int64_t sector_num,
return ret;
}
static int vmdk_write_compressed(BlockDriverState *bs,
int64_t sector_num,
const uint8_t *buf,
int nb_sectors)
{
BDRVVmdkState *s = bs->opaque;
if (s->num_extents == 1 && s->extents[0].compressed) {
return vmdk_write(bs, sector_num, buf, nb_sectors, false, false);
} else {
return -ENOTSUP;
}
}
static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors,
@@ -1592,17 +1515,17 @@ static int coroutine_fn vmdk_co_write_zeroes(BlockDriverState *bs,
static int vmdk_create_extent(const char *filename, int64_t filesize,
bool flat, bool compress, bool zeroed_grain,
QemuOpts *opts, Error **errp)
Error **errp)
{
int ret, i;
BlockDriverState *bs = NULL;
VMDK4Header header;
Error *local_err = NULL;
Error *local_err;
uint32_t tmp, magic, grains, gd_sectors, gt_size, gt_count;
uint32_t *gd_buf = NULL;
int gd_buf_size;
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto exit;
@@ -1758,16 +1681,17 @@ static int filename_decompose(const char *filename, char *path, char *prefix,
return VMDK_OK;
}
static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
static int vmdk_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
int idx = 0;
BlockDriverState *new_bs = NULL;
Error *local_err = NULL;
Error *local_err;
char *desc = NULL;
int64_t total_size = 0, filesize;
char *adapter_type = NULL;
char *backing_file = NULL;
char *fmt = NULL;
const char *adapter_type = NULL;
const char *backing_file = NULL;
const char *fmt = NULL;
int flags = 0;
int ret = 0;
bool flat, split, compress;
@@ -1783,8 +1707,8 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
const char desc_template[] =
"# Disk DescriptorFile\n"
"version=1\n"
"CID=%" PRIx32 "\n"
"parentCID=%" PRIx32 "\n"
"CID=%x\n"
"parentCID=%x\n"
"createType=\"%s\"\n"
"%s"
"\n"
@@ -1796,7 +1720,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
"\n"
"ddb.virtualHWVersion = \"%d\"\n"
"ddb.geometry.cylinders = \"%" PRId64 "\"\n"
"ddb.geometry.heads = \"%" PRIu32 "\"\n"
"ddb.geometry.heads = \"%d\"\n"
"ddb.geometry.sectors = \"63\"\n"
"ddb.adapterType = \"%s\"\n";
@@ -1807,20 +1731,24 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
goto exit;
}
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
adapter_type = qemu_opt_get_del(opts, BLOCK_OPT_ADAPTER_TYPE);
backing_file = qemu_opt_get_del(opts, BLOCK_OPT_BACKING_FILE);
if (qemu_opt_get_bool_del(opts, BLOCK_OPT_COMPAT6, false)) {
flags |= BLOCK_FLAG_COMPAT6;
while (options && options->name) {
if (!strcmp(options->name, BLOCK_OPT_SIZE)) {
total_size = options->value.n;
} else if (!strcmp(options->name, BLOCK_OPT_ADAPTER_TYPE)) {
adapter_type = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_BACKING_FILE)) {
backing_file = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_COMPAT6)) {
flags |= options->value.n ? BLOCK_FLAG_COMPAT6 : 0;
} else if (!strcmp(options->name, BLOCK_OPT_SUBFMT)) {
fmt = options->value.s;
} else if (!strcmp(options->name, BLOCK_OPT_ZEROED_GRAIN)) {
zeroed_grain |= options->value.n;
}
options++;
}
fmt = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
if (qemu_opt_get_bool_del(opts, BLOCK_OPT_ZEROED_GRAIN, false)) {
zeroed_grain = true;
}
if (!adapter_type) {
adapter_type = g_strdup("ide");
adapter_type = "ide";
} else if (strcmp(adapter_type, "ide") &&
strcmp(adapter_type, "buslogic") &&
strcmp(adapter_type, "lsilogic") &&
@@ -1836,7 +1764,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
}
if (!fmt) {
/* Default format to monolithicSparse */
fmt = g_strdup("monolithicSparse");
fmt = "monolithicSparse";
} else if (strcmp(fmt, "monolithicFlat") &&
strcmp(fmt, "monolithicSparse") &&
strcmp(fmt, "twoGbMaxExtentSparse") &&
@@ -1852,9 +1780,9 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
strcmp(fmt, "twoGbMaxExtentFlat"));
compress = !strcmp(fmt, "streamOptimized");
if (flat) {
desc_extent_line = "RW %" PRId64 " FLAT \"%s\" 0\n";
desc_extent_line = "RW %lld FLAT \"%s\" 0\n";
} else {
desc_extent_line = "RW %" PRId64 " SPARSE \"%s\"\n";
desc_extent_line = "RW %lld SPARSE \"%s\"\n";
}
if (flat && backing_file) {
error_setg(errp, "Flat image can't have backing file");
@@ -1909,7 +1837,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
path, desc_filename);
if (vmdk_create_extent(ext_filename, size,
flat, compress, zeroed_grain, opts, errp)) {
flat, compress, zeroed_grain, errp)) {
ret = -EINVAL;
goto exit;
}
@@ -1922,7 +1850,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
}
/* generate descriptor file */
desc = g_strdup_printf(desc_template,
(uint32_t)time(NULL),
(unsigned int)time(NULL),
parent_cid,
fmt,
parent_desc_line,
@@ -1937,9 +1865,9 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
if (!split && !flat) {
desc_offset = 0x200;
} else {
ret = bdrv_create_file(filename, opts, &local_err);
ret = bdrv_create_file(filename, options, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
error_setg_errno(errp, -ret, "Could not create image file");
goto exit;
}
}
@@ -1947,7 +1875,7 @@ static int vmdk_create(const char *filename, QemuOpts *opts, Error **errp)
ret = bdrv_open(&new_bs, filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_PROTOCOL, NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
error_setg_errno(errp, -ret, "Could not write description");
goto exit;
}
ret = bdrv_pwrite(new_bs, desc_offset, desc, desc_len);
@@ -1967,9 +1895,6 @@ exit:
if (new_bs) {
bdrv_unref(new_bs);
}
g_free(adapter_type);
g_free(backing_file);
g_free(fmt);
g_free(desc);
g_string_free(ext_desc_lines, true);
return ret;
@@ -2065,7 +1990,7 @@ static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
BDRVVmdkState *s = bs->opaque;
VmdkExtent *extent = NULL;
int64_t sector_num = 0;
int64_t total_sectors = bdrv_nb_sectors(bs);
int64_t total_sectors = bdrv_getlength(bs) / BDRV_SECTOR_SIZE;
int ret;
uint64_t cluster_offset;
@@ -2086,7 +2011,7 @@ static int vmdk_check(BlockDriverState *bs, BdrvCheckResult *result,
}
ret = get_cluster_offset(bs, extent, NULL,
sector_num << BDRV_SECTOR_BITS,
false, &cluster_offset, 0, 0);
0, &cluster_offset);
if (ret == VMDK_ERROR) {
fprintf(stderr,
"ERROR: could not get cluster_offset for sector %"
@@ -2137,88 +2062,41 @@ static ImageInfoSpecific *vmdk_get_specific_info(BlockDriverState *bs)
return spec_info;
}
static int vmdk_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
{
int i;
BDRVVmdkState *s = bs->opaque;
assert(s->num_extents);
bdi->needs_compressed_writes = s->extents[0].compressed;
if (!s->extents[0].flat) {
bdi->cluster_size = s->extents[0].cluster_sectors << BDRV_SECTOR_BITS;
}
/* See if we have multiple extents but they have different cases */
for (i = 1; i < s->num_extents; i++) {
if (bdi->needs_compressed_writes != s->extents[i].compressed ||
(bdi->cluster_size && bdi->cluster_size !=
s->extents[i].cluster_sectors << BDRV_SECTOR_BITS)) {
return -ENOTSUP;
}
}
return 0;
}
static void vmdk_detach_aio_context(BlockDriverState *bs)
{
BDRVVmdkState *s = bs->opaque;
int i;
for (i = 0; i < s->num_extents; i++) {
bdrv_detach_aio_context(s->extents[i].file);
}
}
static void vmdk_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVVmdkState *s = bs->opaque;
int i;
for (i = 0; i < s->num_extents; i++) {
bdrv_attach_aio_context(s->extents[i].file, new_context);
}
}
static QemuOptsList vmdk_create_opts = {
.name = "vmdk-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(vmdk_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_ADAPTER_TYPE,
.type = QEMU_OPT_STRING,
.help = "Virtual adapter type, can be one of "
"ide (default), lsilogic, buslogic or legacyESX"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = QEMU_OPT_STRING,
.help = "File name of a base image"
},
{
.name = BLOCK_OPT_COMPAT6,
.type = QEMU_OPT_BOOL,
.help = "VMDK version 6 image",
.def_value_str = "off"
},
{
.name = BLOCK_OPT_SUBFMT,
.type = QEMU_OPT_STRING,
.help =
"VMDK flat extent format, can be one of "
"{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
},
{
.name = BLOCK_OPT_ZEROED_GRAIN,
.type = QEMU_OPT_BOOL,
.help = "Enable efficient zero writes "
"using the zeroed-grain GTE feature"
},
{ /* end of list */ }
}
static QEMUOptionParameter vmdk_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_ADAPTER_TYPE,
.type = OPT_STRING,
.help = "Virtual adapter type, can be one of "
"ide (default), lsilogic, buslogic or legacyESX"
},
{
.name = BLOCK_OPT_BACKING_FILE,
.type = OPT_STRING,
.help = "File name of a base image"
},
{
.name = BLOCK_OPT_COMPAT6,
.type = OPT_FLAG,
.help = "VMDK version 6 image"
},
{
.name = BLOCK_OPT_SUBFMT,
.type = OPT_STRING,
.help =
"VMDK flat extent format, can be one of "
"{monolithicSparse (default) | monolithicFlat | twoGbMaxExtentSparse | twoGbMaxExtentFlat | streamOptimized} "
},
{
.name = BLOCK_OPT_ZEROED_GRAIN,
.type = OPT_FLAG,
.help = "Enable efficient zero writes using the zeroed-grain GTE feature"
},
{ NULL }
};
static BlockDriver bdrv_vmdk = {
@@ -2230,7 +2108,6 @@ static BlockDriver bdrv_vmdk = {
.bdrv_reopen_prepare = vmdk_reopen_prepare,
.bdrv_read = vmdk_co_read,
.bdrv_write = vmdk_co_write,
.bdrv_write_compressed = vmdk_write_compressed,
.bdrv_co_write_zeroes = vmdk_co_write_zeroes,
.bdrv_close = vmdk_close,
.bdrv_create = vmdk_create,
@@ -2240,12 +2117,8 @@ static BlockDriver bdrv_vmdk = {
.bdrv_has_zero_init = vmdk_has_zero_init,
.bdrv_get_specific_info = vmdk_get_specific_info,
.bdrv_refresh_limits = vmdk_refresh_limits,
.bdrv_get_info = vmdk_get_info,
.bdrv_detach_aio_context = vmdk_detach_aio_context,
.bdrv_attach_aio_context = vmdk_attach_aio_context,
.supports_backing = true,
.create_opts = &vmdk_create_opts,
.create_options = vmdk_create_options,
};
static void bdrv_vmdk_init(void)

View File

@@ -207,7 +207,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
"incorrect.\n", bs->filename);
/* Write 'checksum' back to footer, or else will leave it with zero. */
footer->checksum = cpu_to_be32(checksum);
footer->checksum = be32_to_cpu(checksum);
// The visible size of a image in Virtual PC depends on the geometry
// rather than on the size stored in the footer (the size in the footer
@@ -269,11 +269,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
goto fail;
}
s->pagetable = qemu_try_blockalign(bs->file, s->max_table_entries * 4);
if (s->pagetable == NULL) {
ret = -ENOMEM;
goto fail;
}
s->pagetable = qemu_blockalign(bs, s->max_table_entries * 4);
s->bat_offset = be64_to_cpu(dyndisk_header->table_offset);
@@ -320,7 +316,7 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
/* Disable migration when VHD images are used */
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vpc", bdrv_get_device_name(bs), "live migration");
"vpc", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
return 0;
@@ -472,7 +468,7 @@ static int64_t alloc_block(BlockDriverState* bs, int64_t sector_num)
// Write BAT entry to disk
bat_offset = s->bat_offset + (4 * index);
bat_value = cpu_to_be32(s->pagetable[index]);
bat_value = be32_to_cpu(s->pagetable[index]);
ret = bdrv_pwrite_sync(bs->file, bat_offset, &bat_value, 4);
if (ret < 0)
goto fail;
@@ -489,7 +485,7 @@ static int vpc_get_info(BlockDriverState *bs, BlockDriverInfo *bdi)
BDRVVPCState *s = (BDRVVPCState *)bs->opaque;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
if (be32_to_cpu(footer->type) != VHD_FIXED) {
if (cpu_to_be32(footer->type) != VHD_FIXED) {
bdi->cluster_size = s->block_size;
}
@@ -506,7 +502,7 @@ static int vpc_read(BlockDriverState *bs, int64_t sector_num,
int64_t sectors, sectors_per_block;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
if (be32_to_cpu(footer->type) == VHD_FIXED) {
if (cpu_to_be32(footer->type) == VHD_FIXED) {
return bdrv_read(bs->file, sector_num, buf, nb_sectors);
}
while (nb_sectors > 0) {
@@ -555,7 +551,7 @@ static int vpc_write(BlockDriverState *bs, int64_t sector_num,
int ret;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
if (be32_to_cpu(footer->type) == VHD_FIXED) {
if (cpu_to_be32(footer->type) == VHD_FIXED) {
return bdrv_write(bs->file, sector_num, buf, nb_sectors);
}
while (nb_sectors > 0) {
@@ -653,41 +649,39 @@ static int calculate_geometry(int64_t total_sectors, uint16_t* cyls,
return 0;
}
static int create_dynamic_disk(BlockDriverState *bs, uint8_t *buf,
int64_t total_sectors)
static int create_dynamic_disk(int fd, uint8_t *buf, int64_t total_sectors)
{
VHDDynDiskHeader *dyndisk_header =
(VHDDynDiskHeader *) buf;
size_t block_size, num_bat_entries;
int i;
int ret;
int64_t offset = 0;
int ret = -EIO;
// Write the footer (twice: at the beginning and at the end)
block_size = 0x200000;
num_bat_entries = (total_sectors + block_size / 512) / (block_size / 512);
ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE);
if (ret) {
if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE) {
goto fail;
}
offset = 1536 + ((num_bat_entries * 4 + 511) & ~511);
ret = bdrv_pwrite_sync(bs, offset, buf, HEADER_SIZE);
if (ret < 0) {
if (lseek(fd, 1536 + ((num_bat_entries * 4 + 511) & ~511), SEEK_SET) < 0) {
goto fail;
}
if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE) {
goto fail;
}
// Write the initial BAT
offset = 3 * 512;
if (lseek(fd, 3 * 512, SEEK_SET) < 0) {
goto fail;
}
memset(buf, 0xFF, 512);
for (i = 0; i < (num_bat_entries * 4 + 511) / 512; i++) {
ret = bdrv_pwrite_sync(bs, offset, buf, 512);
if (ret < 0) {
if (write(fd, buf, 512) != 512) {
goto fail;
}
offset += 512;
}
// Prepare the Dynamic Disk Header
@@ -699,53 +693,58 @@ static int create_dynamic_disk(BlockDriverState *bs, uint8_t *buf,
* Note: The spec is actually wrong here for data_offset, it says
* 0xFFFFFFFF, but MS tools expect all 64 bits to be set.
*/
dyndisk_header->data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
dyndisk_header->table_offset = cpu_to_be64(3 * 512);
dyndisk_header->version = cpu_to_be32(0x00010000);
dyndisk_header->block_size = cpu_to_be32(block_size);
dyndisk_header->max_table_entries = cpu_to_be32(num_bat_entries);
dyndisk_header->data_offset = be64_to_cpu(0xFFFFFFFFFFFFFFFFULL);
dyndisk_header->table_offset = be64_to_cpu(3 * 512);
dyndisk_header->version = be32_to_cpu(0x00010000);
dyndisk_header->block_size = be32_to_cpu(block_size);
dyndisk_header->max_table_entries = be32_to_cpu(num_bat_entries);
dyndisk_header->checksum = cpu_to_be32(vpc_checksum(buf, 1024));
dyndisk_header->checksum = be32_to_cpu(vpc_checksum(buf, 1024));
// Write the header
offset = 512;
ret = bdrv_pwrite_sync(bs, offset, buf, 1024);
if (ret < 0) {
if (lseek(fd, 512, SEEK_SET) < 0) {
goto fail;
}
if (write(fd, buf, 1024) != 1024) {
goto fail;
}
ret = 0;
fail:
return ret;
}
static int create_fixed_disk(BlockDriverState *bs, uint8_t *buf,
int64_t total_size)
static int create_fixed_disk(int fd, uint8_t *buf, int64_t total_size)
{
int ret;
int ret = -EIO;
/* Add footer to total size */
total_size += HEADER_SIZE;
ret = bdrv_truncate(bs, total_size);
if (ret < 0) {
return ret;
total_size += 512;
if (ftruncate(fd, total_size) != 0) {
ret = -errno;
goto fail;
}
if (lseek(fd, -512, SEEK_END) < 0) {
goto fail;
}
if (write(fd, buf, HEADER_SIZE) != HEADER_SIZE) {
goto fail;
}
ret = bdrv_pwrite_sync(bs, total_size - HEADER_SIZE, buf, HEADER_SIZE);
if (ret < 0) {
return ret;
}
ret = 0;
fail:
return ret;
}
static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
static int vpc_create(const char *filename, QEMUOptionParameter *options,
Error **errp)
{
uint8_t buf[1024];
VHDFooter *footer = (VHDFooter *) buf;
char *disk_type_param;
int i;
QEMUOptionParameter *disk_type_param;
int fd, i;
uint16_t cyls = 0;
uint8_t heads = 0;
uint8_t secs_per_cyl = 0;
@@ -753,36 +752,27 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
int64_t total_size;
int disk_type;
int ret = -EIO;
Error *local_err = NULL;
BlockDriverState *bs = NULL;
/* Read out options */
total_size = ROUND_UP(qemu_opt_get_size_del(opts, BLOCK_OPT_SIZE, 0),
BDRV_SECTOR_SIZE);
disk_type_param = qemu_opt_get_del(opts, BLOCK_OPT_SUBFMT);
if (disk_type_param) {
if (!strcmp(disk_type_param, "dynamic")) {
total_size = get_option_parameter(options, BLOCK_OPT_SIZE)->value.n;
disk_type_param = get_option_parameter(options, BLOCK_OPT_SUBFMT);
if (disk_type_param && disk_type_param->value.s) {
if (!strcmp(disk_type_param->value.s, "dynamic")) {
disk_type = VHD_DYNAMIC;
} else if (!strcmp(disk_type_param, "fixed")) {
} else if (!strcmp(disk_type_param->value.s, "fixed")) {
disk_type = VHD_FIXED;
} else {
ret = -EINVAL;
goto out;
return -EINVAL;
}
} else {
disk_type = VHD_DYNAMIC;
}
ret = bdrv_create_file(filename, opts, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto out;
}
ret = bdrv_open(&bs, filename, NULL, NULL, BDRV_O_RDWR | BDRV_O_PROTOCOL,
NULL, &local_err);
if (ret < 0) {
error_propagate(errp, local_err);
goto out;
/* Create the file */
fd = qemu_open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY, 0644);
if (fd < 0) {
return -EIO;
}
/*
@@ -796,7 +786,7 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
&secs_per_cyl))
{
ret = -EFBIG;
goto out;
goto fail;
}
}
@@ -810,46 +800,45 @@ static int vpc_create(const char *filename, QemuOpts *opts, Error **errp)
memcpy(footer->creator_app, "qemu", 4);
memcpy(footer->creator_os, "Wi2k", 4);
footer->features = cpu_to_be32(0x02);
footer->version = cpu_to_be32(0x00010000);
footer->features = be32_to_cpu(0x02);
footer->version = be32_to_cpu(0x00010000);
if (disk_type == VHD_DYNAMIC) {
footer->data_offset = cpu_to_be64(HEADER_SIZE);
footer->data_offset = be64_to_cpu(HEADER_SIZE);
} else {
footer->data_offset = cpu_to_be64(0xFFFFFFFFFFFFFFFFULL);
footer->data_offset = be64_to_cpu(0xFFFFFFFFFFFFFFFFULL);
}
footer->timestamp = cpu_to_be32(time(NULL) - VHD_TIMESTAMP_BASE);
footer->timestamp = be32_to_cpu(time(NULL) - VHD_TIMESTAMP_BASE);
/* Version of Virtual PC 2007 */
footer->major = cpu_to_be16(0x0005);
footer->minor = cpu_to_be16(0x0003);
footer->major = be16_to_cpu(0x0005);
footer->minor = be16_to_cpu(0x0003);
if (disk_type == VHD_DYNAMIC) {
footer->orig_size = cpu_to_be64(total_sectors * 512);
footer->size = cpu_to_be64(total_sectors * 512);
footer->orig_size = be64_to_cpu(total_sectors * 512);
footer->size = be64_to_cpu(total_sectors * 512);
} else {
footer->orig_size = cpu_to_be64(total_size);
footer->size = cpu_to_be64(total_size);
footer->orig_size = be64_to_cpu(total_size);
footer->size = be64_to_cpu(total_size);
}
footer->cyls = cpu_to_be16(cyls);
footer->cyls = be16_to_cpu(cyls);
footer->heads = heads;
footer->secs_per_cyl = secs_per_cyl;
footer->type = cpu_to_be32(disk_type);
footer->type = be32_to_cpu(disk_type);
#if defined(CONFIG_UUID)
uuid_generate(footer->uuid);
#endif
footer->checksum = cpu_to_be32(vpc_checksum(buf, HEADER_SIZE));
footer->checksum = be32_to_cpu(vpc_checksum(buf, HEADER_SIZE));
if (disk_type == VHD_DYNAMIC) {
ret = create_dynamic_disk(bs, buf, total_sectors);
ret = create_dynamic_disk(fd, buf, total_sectors);
} else {
ret = create_fixed_disk(bs, buf, total_size);
ret = create_fixed_disk(fd, buf, total_size);
}
out:
bdrv_unref(bs);
g_free(disk_type_param);
fail:
qemu_close(fd);
return ret;
}
@@ -858,7 +847,7 @@ static int vpc_has_zero_init(BlockDriverState *bs)
BDRVVPCState *s = bs->opaque;
VHDFooter *footer = (VHDFooter *) s->footer_buf;
if (be32_to_cpu(footer->type) == VHD_FIXED) {
if (cpu_to_be32(footer->type) == VHD_FIXED) {
return bdrv_has_zero_init(bs->file);
} else {
return 1;
@@ -877,29 +866,20 @@ static void vpc_close(BlockDriverState *bs)
error_free(s->migration_blocker);
}
static QemuOptsList vpc_create_opts = {
.name = "vpc-create-opts",
.head = QTAILQ_HEAD_INITIALIZER(vpc_create_opts.head),
.desc = {
{
.name = BLOCK_OPT_SIZE,
.type = QEMU_OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_SUBFMT,
.type = QEMU_OPT_STRING,
.help =
"Type of virtual hard disk format. Supported formats are "
"{dynamic (default) | fixed} "
},
{
.name = BLOCK_OPT_NOCOW,
.type = QEMU_OPT_BOOL,
.help = "Turn off copy-on-write (valid only on btrfs)"
},
{ /* end of list */ }
}
static QEMUOptionParameter vpc_create_options[] = {
{
.name = BLOCK_OPT_SIZE,
.type = OPT_SIZE,
.help = "Virtual disk size"
},
{
.name = BLOCK_OPT_SUBFMT,
.type = OPT_STRING,
.help =
"Type of virtual hard disk format. Supported formats are "
"{dynamic (default) | fixed} "
},
{ NULL }
};
static BlockDriver bdrv_vpc = {
@@ -917,7 +897,7 @@ static BlockDriver bdrv_vpc = {
.bdrv_get_info = vpc_get_info,
.create_opts = &vpc_create_opts,
.create_options = vpc_create_options,
.bdrv_has_zero_init = vpc_has_zero_init,
};

View File

@@ -52,6 +52,10 @@
#define DLOG(a) a
#undef stderr
#define stderr STDERR
FILE* stderr = NULL;
static void checkpoint(void);
#ifdef __MINGW32__
@@ -728,7 +732,7 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
if(first_cluster == 0 && (is_dotdot || is_dot))
continue;
buffer = g_malloc(length);
buffer=(char*)g_malloc(length);
snprintf(buffer,length,"%s/%s",dirname,entry->d_name);
if(stat(buffer,&st)<0) {
@@ -763,7 +767,7 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
/* create mapping for this file */
if(!is_dot && !is_dotdot && (S_ISDIR(st.st_mode) || st.st_size)) {
s->current_mapping = array_get_next(&(s->mapping));
s->current_mapping=(mapping_t*)array_get_next(&(s->mapping));
s->current_mapping->begin=0;
s->current_mapping->end=st.st_size;
/*
@@ -807,12 +811,12 @@ static int read_directory(BDRVVVFATState* s, int mapping_index)
}
/* reget the mapping, since s->mapping was possibly realloc()ed */
mapping = array_get(&(s->mapping), mapping_index);
mapping = (mapping_t*)array_get(&(s->mapping), mapping_index);
first_cluster += (s->directory.next - mapping->info.dir.first_dir_index)
* 0x20 / s->cluster_size;
mapping->end = first_cluster;
direntry = array_get(&(s->directory), mapping->dir_index);
direntry = (direntry_t*)array_get(&(s->directory), mapping->dir_index);
set_begin_of_direntry(direntry, mapping->begin);
return 0;
@@ -829,8 +833,7 @@ static inline off_t cluster2sector(BDRVVVFATState* s, uint32_t cluster_num)
}
static int init_directories(BDRVVVFATState* s,
const char *dirname, int heads, int secs,
Error **errp)
const char *dirname, int heads, int secs)
{
bootsector_t* bootsector;
mapping_t* mapping;
@@ -891,8 +894,8 @@ static int init_directories(BDRVVVFATState* s,
if (mapping->mode & MODE_DIRECTORY) {
mapping->begin = cluster;
if(read_directory(s, i)) {
error_setg(errp, "Could not read directory %s",
mapping->path);
fprintf(stderr, "Could not read directory %s\n",
mapping->path);
return -1;
}
mapping = array_get(&(s->mapping), i);
@@ -918,10 +921,9 @@ static int init_directories(BDRVVVFATState* s,
cluster = mapping->end;
if(cluster > s->cluster_count) {
error_setg(errp,
"Directory does not fit in FAT%d (capacity %.2f MB)",
s->fat_type, s->sector_count / 2000.0);
return -1;
fprintf(stderr,"Directory does not fit in FAT%d (capacity %.2f MB)\n",
s->fat_type, s->sector_count / 2000.0);
return -EINVAL;
}
/* fix fat for entry */
@@ -979,7 +981,7 @@ static int init_directories(BDRVVVFATState* s,
static BDRVVVFATState *vvv = NULL;
#endif
static int enable_write_target(BDRVVVFATState *s, Error **errp);
static int enable_write_target(BDRVVVFATState *s);
static int is_consistent(BDRVVVFATState *s);
static void vvfat_rebind(BlockDriverState *bs)
@@ -1078,6 +1080,11 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
vvv = s;
#endif
DLOG(if (stderr == NULL) {
stderr = fopen("vvfat.log", "a");
setbuf(stderr, NULL);
})
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
@@ -1155,7 +1162,7 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);
if (qemu_opt_get_bool(opts, "rw", false)) {
ret = enable_write_target(s, errp);
ret = enable_write_target(s);
if (ret < 0) {
goto fail;
}
@@ -1164,7 +1171,7 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
bs->total_sectors = cyls * heads * secs;
if (init_directories(s, dirname, heads, secs, errp)) {
if (init_directories(s, dirname, heads, secs)) {
ret = -EIO;
goto fail;
}
@@ -1182,7 +1189,7 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
if (s->qcow) {
error_set(&s->migration_blocker,
QERR_BLOCK_FORMAT_FEATURE_NOT_SUPPORTED,
"vvfat (rw)", bdrv_get_device_name(bs), "live migration");
"vvfat (rw)", bs->device_name, "live migration");
migrate_add_blocker(s->migration_blocker);
}
@@ -2899,10 +2906,11 @@ static BlockDriver vvfat_write_target = {
.bdrv_close = write_target_close,
};
static int enable_write_target(BDRVVVFATState *s, Error **errp)
static int enable_write_target(BDRVVVFATState *s)
{
BlockDriver *bdrv_qcow = NULL;
QemuOpts *opts = NULL;
BlockDriver *bdrv_qcow;
QEMUOptionParameter *options;
Error *local_err = NULL;
int ret;
int size = sector2cluster(s, s->sector_count);
s->used_clusters = calloc(size, 1);
@@ -2912,26 +2920,28 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
s->qcow_filename = g_malloc(1024);
ret = get_tmp_filename(s->qcow_filename, 1024);
if (ret < 0) {
error_setg_errno(errp, -ret, "can't create temporary file");
goto err;
}
bdrv_qcow = bdrv_find_format("qcow");
opts = qemu_opts_create(bdrv_qcow->create_opts, NULL, 0, &error_abort);
qemu_opt_set_number(opts, BLOCK_OPT_SIZE, s->sector_count * 512);
qemu_opt_set(opts, BLOCK_OPT_BACKING_FILE, "fat:");
options = parse_option_parameters("", bdrv_qcow->create_options, NULL);
set_option_parameter_int(options, BLOCK_OPT_SIZE, s->sector_count * 512);
set_option_parameter(options, BLOCK_OPT_BACKING_FILE, "fat:");
ret = bdrv_create(bdrv_qcow, s->qcow_filename, opts, errp);
qemu_opts_del(opts);
ret = bdrv_create(bdrv_qcow, s->qcow_filename, options, &local_err);
if (ret < 0) {
qerror_report_err(local_err);
error_free(local_err);
goto err;
}
s->qcow = NULL;
ret = bdrv_open(&s->qcow, s->qcow_filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH,
bdrv_qcow, errp);
BDRV_O_RDWR | BDRV_O_CACHE_WB | BDRV_O_NO_FLUSH, bdrv_qcow,
&local_err);
if (ret < 0) {
qerror_report_err(local_err);
error_free(local_err);
goto err;
}
@@ -2939,9 +2949,9 @@ static int enable_write_target(BDRVVVFATState *s, Error **errp)
unlink(s->qcow_filename);
#endif
bdrv_set_backing_hd(s->bs, bdrv_new());
s->bs->backing_hd = bdrv_new("");
s->bs->backing_hd->drv = &vvfat_write_target;
s->bs->backing_hd->opaque = g_new(void *, 1);
s->bs->backing_hd->opaque = g_malloc(sizeof(void*));
*(void**)s->bs->backing_hd->opaque = s;
return 0;

View File

@@ -40,11 +40,10 @@ struct QEMUWin32AIOState {
HANDLE hIOCP;
EventNotifier e;
int count;
bool is_aio_context_attached;
};
typedef struct QEMUWin32AIOCB {
BlockAIOCB common;
BlockDriverAIOCB common;
struct QEMUWin32AIOState *ctx;
int nbytes;
OVERLAPPED ov;
@@ -88,7 +87,7 @@ static void win32_aio_process_completion(QEMUWin32AIOState *s,
waiocb->common.cb(waiocb->common.opaque, ret);
qemu_aio_unref(waiocb);
qemu_aio_release(waiocb);
}
static void win32_aio_completion_cb(EventNotifier *e)
@@ -106,14 +105,28 @@ static void win32_aio_completion_cb(EventNotifier *e)
}
}
static void win32_aio_cancel(BlockDriverAIOCB *blockacb)
{
QEMUWin32AIOCB *waiocb = (QEMUWin32AIOCB *)blockacb;
/*
* CancelIoEx is only supported in Vista and newer. For now, just
* wait for completion.
*/
while (!HasOverlappedIoCompleted(&waiocb->ov)) {
qemu_aio_wait();
}
}
static const AIOCBInfo win32_aiocb_info = {
.aiocb_size = sizeof(QEMUWin32AIOCB),
.cancel = win32_aio_cancel,
};
BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
BlockDriverAIOCB *win32_aio_submit(BlockDriverState *bs,
QEMUWin32AIOState *aio, HANDLE hfile,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque, int type)
BlockDriverCompletionFunc *cb, void *opaque, int type)
{
struct QEMUWin32AIOCB *waiocb;
uint64_t offset = sector_num * 512;
@@ -125,10 +138,7 @@ BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
waiocb->is_read = (type == QEMU_AIO_READ);
if (qiov->niov > 1) {
waiocb->buf = qemu_try_blockalign(bs, qiov->size);
if (waiocb->buf == NULL) {
goto out;
}
waiocb->buf = qemu_blockalign(bs, qiov->size);
if (type & QEMU_AIO_WRITE) {
iov_to_buf(qiov->iov, qiov->niov, 0, waiocb->buf, qiov->size);
}
@@ -157,8 +167,7 @@ BlockAIOCB *win32_aio_submit(BlockDriverState *bs,
out_dec_count:
aio->count--;
out:
qemu_aio_unref(waiocb);
qemu_aio_release(waiocb);
return NULL;
}
@@ -171,20 +180,6 @@ int win32_aio_attach(QEMUWin32AIOState *aio, HANDLE hfile)
}
}
void win32_aio_detach_aio_context(QEMUWin32AIOState *aio,
AioContext *old_context)
{
aio_set_event_notifier(old_context, &aio->e, NULL);
aio->is_aio_context_attached = false;
}
void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
AioContext *new_context)
{
aio->is_aio_context_attached = true;
aio_set_event_notifier(new_context, &aio->e, win32_aio_completion_cb);
}
QEMUWin32AIOState *win32_aio_init(void)
{
QEMUWin32AIOState *s;
@@ -199,6 +194,8 @@ QEMUWin32AIOState *win32_aio_init(void)
goto out_close_efd;
}
qemu_aio_set_event_notifier(&s->e, win32_aio_completion_cb);
return s;
out_close_efd:
@@ -207,11 +204,3 @@ out_free_state:
g_free(s);
return NULL;
}
void win32_aio_cleanup(QEMUWin32AIOState *aio)
{
assert(!aio->is_aio_context_attached);
CloseHandle(aio->hIOCP);
event_notifier_cleanup(&aio->e);
g_free(aio);
}

View File

@@ -108,7 +108,7 @@ void qmp_nbd_server_add(const char *device, bool has_writable, bool writable,
nbd_export_set_name(exp, device);
n = g_new0(NBDCloseNotifier, 1);
n = g_malloc0(sizeof(NBDCloseNotifier));
n->n.notify = nbd_close_notifier;
n->exp = exp;
bdrv_add_close_notifier(bs, &n->n);

File diff suppressed because it is too large Load Diff

View File

@@ -26,6 +26,7 @@
#include "config-host.h"
#include "qemu-common.h"
#include "trace.h"
#include "monitor/monitor.h"
#include "block/block.h"
#include "block/blockjob.h"
#include "block/block_int.h"
@@ -33,25 +34,21 @@
#include "block/coroutine.h"
#include "qmp-commands.h"
#include "qemu/timer.h"
#include "qapi-event.h"
void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
int64_t speed, BlockCompletionFunc *cb,
int64_t speed, BlockDriverCompletionFunc *cb,
void *opaque, Error **errp)
{
BlockJob *job;
if (bs->job) {
if (bs->job || bdrv_in_use(bs)) {
error_set(errp, QERR_DEVICE_IN_USE, bdrv_get_device_name(bs));
return NULL;
}
bdrv_ref(bs);
job = g_malloc0(driver->instance_size);
error_setg(&job->blocker, "block device is in use by block job: %s",
BlockJobType_lookup[driver->job_type]);
bdrv_op_block_all(bs, job->blocker);
bdrv_op_unblock(bs, BLOCK_OP_TYPE_DATAPLANE, job->blocker);
bdrv_set_in_use(bs, 1);
job = g_malloc0(driver->instance_size);
job->driver = driver;
job->bs = bs;
job->cb = cb;
@@ -66,9 +63,8 @@ void *block_job_create(const BlockJobDriver *driver, BlockDriverState *bs,
block_job_set_speed(job, speed, &local_err);
if (local_err) {
bs->job = NULL;
bdrv_op_unblock_all(bs, job->blocker);
error_free(job->blocker);
g_free(job);
bdrv_set_in_use(bs, 0);
error_propagate(errp, local_err);
return NULL;
}
@@ -83,9 +79,8 @@ void block_job_completed(BlockJob *job, int ret)
assert(bs->job == job);
job->cb(job->opaque, ret);
bs->job = NULL;
bdrv_op_unblock_all(bs, job->blocker);
error_free(job->blocker);
g_free(job);
bdrv_set_in_use(bs, 0);
}
void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
@@ -93,7 +88,7 @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
Error *local_err = NULL;
if (!job->driver->set_speed) {
error_set(errp, QERR_UNSUPPORTED);
error_set(errp, QERR_NOT_SUPPORTED);
return;
}
job->driver->set_speed(job, speed, &local_err);
@@ -108,8 +103,7 @@ void block_job_set_speed(BlockJob *job, int64_t speed, Error **errp)
void block_job_complete(BlockJob *job, Error **errp)
{
if (job->paused || job->cancelled || !job->driver->complete) {
error_set(errp, QERR_BLOCK_JOB_NOT_READY,
bdrv_get_device_name(job->bs));
error_set(errp, QERR_BLOCK_JOB_NOT_READY, job->bs->device_name);
return;
}
@@ -154,30 +148,27 @@ void block_job_iostatus_reset(BlockJob *job)
}
}
struct BlockFinishData {
struct BlockCancelData {
BlockJob *job;
BlockCompletionFunc *cb;
BlockDriverCompletionFunc *cb;
void *opaque;
bool cancelled;
int ret;
};
static void block_job_finish_cb(void *opaque, int ret)
static void block_job_cancel_cb(void *opaque, int ret)
{
struct BlockFinishData *data = opaque;
struct BlockCancelData *data = opaque;
data->cancelled = block_job_is_cancelled(data->job);
data->ret = ret;
data->cb(data->opaque, ret);
}
static int block_job_finish_sync(BlockJob *job,
void (*finish)(BlockJob *, Error **errp),
Error **errp)
int block_job_cancel_sync(BlockJob *job)
{
struct BlockFinishData data;
struct BlockCancelData data;
BlockDriverState *bs = job->bs;
Error *local_err = NULL;
assert(bs->job == job);
@@ -188,37 +179,15 @@ static int block_job_finish_sync(BlockJob *job,
data.cb = job->cb;
data.opaque = job->opaque;
data.ret = -EINPROGRESS;
job->cb = block_job_finish_cb;
job->cb = block_job_cancel_cb;
job->opaque = &data;
finish(job, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EBUSY;
}
block_job_cancel(job);
while (data.ret == -EINPROGRESS) {
aio_poll(bdrv_get_aio_context(bs), true);
qemu_aio_wait();
}
return (data.cancelled && data.ret == 0) ? -ECANCELED : data.ret;
}
/* A wrapper around block_job_cancel() taking an Error ** parameter so it may be
* used with block_job_finish_sync() without the need for (rather nasty)
* function pointer casts there. */
static void block_job_cancel_err(BlockJob *job, Error **errp)
{
block_job_cancel(job);
}
int block_job_cancel_sync(BlockJob *job)
{
return block_job_finish_sync(job, &block_job_cancel_err, NULL);
}
int block_job_complete_sync(BlockJob *job, Error **errp)
{
return block_job_finish_sync(job, &block_job_complete, errp);
}
void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
{
assert(job->busy);
@@ -232,7 +201,7 @@ void block_job_sleep_ns(BlockJob *job, QEMUClockType type, int64_t ns)
if (block_job_is_paused(job)) {
qemu_coroutine_yield();
} else {
co_aio_sleep_ns(bdrv_get_aio_context(job->bs), type, ns);
co_sleep_ns(type, ns);
}
job->busy = true;
}
@@ -262,7 +231,6 @@ BlockJobInfo *block_job_query(BlockJob *job)
info->offset = job->offset;
info->speed = job->speed;
info->io_status = job->iostatus;
info->ready = job->ready;
return info;
}
@@ -274,37 +242,26 @@ static void block_job_iostatus_set_err(BlockJob *job, int error)
}
}
void block_job_event_cancelled(BlockJob *job)
QObject *qobject_from_block_job(BlockJob *job)
{
qapi_event_send_block_job_cancelled(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed,
&error_abort);
return qobject_from_jsonf("{ 'type': %s,"
"'device': %s,"
"'len': %" PRId64 ","
"'offset': %" PRId64 ","
"'speed': %" PRId64 " }",
BlockJobType_lookup[job->driver->job_type],
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed);
}
void block_job_event_completed(BlockJob *job, const char *msg)
void block_job_ready(BlockJob *job)
{
qapi_event_send_block_job_completed(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed,
!!msg,
msg,
&error_abort);
}
void block_job_event_ready(BlockJob *job)
{
job->ready = true;
qapi_event_send_block_job_ready(job->driver->job_type,
bdrv_get_device_name(job->bs),
job->len,
job->offset,
job->speed, &error_abort);
QObject *data = qobject_from_block_job(job);
monitor_protocol_event(QEVENT_BLOCK_JOB_READY, data);
qobject_decref(data);
}
BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
@@ -315,26 +272,22 @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
switch (on_err) {
case BLOCKDEV_ON_ERROR_ENOSPC:
action = (error == ENOSPC) ?
BLOCK_ERROR_ACTION_STOP : BLOCK_ERROR_ACTION_REPORT;
action = (error == ENOSPC) ? BDRV_ACTION_STOP : BDRV_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_STOP:
action = BLOCK_ERROR_ACTION_STOP;
action = BDRV_ACTION_STOP;
break;
case BLOCKDEV_ON_ERROR_REPORT:
action = BLOCK_ERROR_ACTION_REPORT;
action = BDRV_ACTION_REPORT;
break;
case BLOCKDEV_ON_ERROR_IGNORE:
action = BLOCK_ERROR_ACTION_IGNORE;
action = BDRV_ACTION_IGNORE;
break;
default:
abort();
}
qapi_event_send_block_job_error(bdrv_get_device_name(job->bs),
is_read ? IO_OPERATION_TYPE_READ :
IO_OPERATION_TYPE_WRITE,
action, &error_abort);
if (action == BLOCK_ERROR_ACTION_STOP) {
bdrv_emit_qmp_error_event(job->bs, QEVENT_BLOCK_JOB_ERROR, action, is_read);
if (action == BDRV_ACTION_STOP) {
block_job_pause(job);
block_job_iostatus_set_err(job, error);
if (bs != job->bs) {
@@ -343,48 +296,3 @@ BlockErrorAction block_job_error_action(BlockJob *job, BlockDriverState *bs,
}
return action;
}
typedef struct {
BlockJob *job;
QEMUBH *bh;
AioContext *aio_context;
BlockJobDeferToMainLoopFn *fn;
void *opaque;
} BlockJobDeferToMainLoopData;
static void block_job_defer_to_main_loop_bh(void *opaque)
{
BlockJobDeferToMainLoopData *data = opaque;
AioContext *aio_context;
qemu_bh_delete(data->bh);
/* Prevent race with block_job_defer_to_main_loop() */
aio_context_acquire(data->aio_context);
/* Fetch BDS AioContext again, in case it has changed */
aio_context = bdrv_get_aio_context(data->job->bs);
aio_context_acquire(aio_context);
data->fn(data->job, data->opaque);
aio_context_release(aio_context);
aio_context_release(data->aio_context);
g_free(data);
}
void block_job_defer_to_main_loop(BlockJob *job,
BlockJobDeferToMainLoopFn *fn,
void *opaque)
{
BlockJobDeferToMainLoopData *data = g_malloc(sizeof(*data));
data->job = job;
data->bh = qemu_bh_new(block_job_defer_to_main_loop_bh, data);
data->aio_context = bdrv_get_aio_context(job->bs);
data->fn = fn;
data->opaque = opaque;
qemu_bh_schedule(data->bh);
}

View File

@@ -1,258 +0,0 @@
/*
* QEMU Boot Device Implement
*
* Copyright (c) 2014 HUAWEI TECHNOLOGIES CO.,LTD.
*
* 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 "sysemu/sysemu.h"
#include "qapi/visitor.h"
#include "qemu/error-report.h"
typedef struct FWBootEntry FWBootEntry;
struct FWBootEntry {
QTAILQ_ENTRY(FWBootEntry) link;
int32_t bootindex;
DeviceState *dev;
char *suffix;
};
static QTAILQ_HEAD(, FWBootEntry) fw_boot_order =
QTAILQ_HEAD_INITIALIZER(fw_boot_order);
void check_boot_index(int32_t bootindex, Error **errp)
{
FWBootEntry *i;
if (bootindex >= 0) {
QTAILQ_FOREACH(i, &fw_boot_order, link) {
if (i->bootindex == bootindex) {
error_setg(errp, "The bootindex %d has already been used",
bootindex);
return;
}
}
}
}
void del_boot_device_path(DeviceState *dev, const char *suffix)
{
FWBootEntry *i;
if (dev == NULL) {
return;
}
QTAILQ_FOREACH(i, &fw_boot_order, link) {
if ((!suffix || !g_strcmp0(i->suffix, suffix)) &&
i->dev == dev) {
QTAILQ_REMOVE(&fw_boot_order, i, link);
g_free(i->suffix);
g_free(i);
break;
}
}
}
void add_boot_device_path(int32_t bootindex, DeviceState *dev,
const char *suffix)
{
FWBootEntry *node, *i;
if (bootindex < 0) {
del_boot_device_path(dev, suffix);
return;
}
assert(dev != NULL || suffix != NULL);
del_boot_device_path(dev, suffix);
node = g_malloc0(sizeof(FWBootEntry));
node->bootindex = bootindex;
node->suffix = g_strdup(suffix);
node->dev = dev;
QTAILQ_FOREACH(i, &fw_boot_order, link) {
if (i->bootindex == bootindex) {
error_report("Two devices with same boot index %d", bootindex);
exit(1);
} else if (i->bootindex < bootindex) {
continue;
}
QTAILQ_INSERT_BEFORE(i, node, link);
return;
}
QTAILQ_INSERT_TAIL(&fw_boot_order, node, link);
}
DeviceState *get_boot_device(uint32_t position)
{
uint32_t counter = 0;
FWBootEntry *i = NULL;
DeviceState *res = NULL;
if (!QTAILQ_EMPTY(&fw_boot_order)) {
QTAILQ_FOREACH(i, &fw_boot_order, link) {
if (counter == position) {
res = i->dev;
break;
}
counter++;
}
}
return res;
}
/*
* This function returns null terminated string that consist of new line
* separated device paths.
*
* memory pointed by "size" is assigned total length of the array in bytes
*
*/
char *get_boot_devices_list(size_t *size, bool ignore_suffixes)
{
FWBootEntry *i;
size_t total = 0;
char *list = NULL;
QTAILQ_FOREACH(i, &fw_boot_order, link) {
char *devpath = NULL, *bootpath;
size_t len;
if (i->dev) {
devpath = qdev_get_fw_dev_path(i->dev);
assert(devpath);
}
if (i->suffix && !ignore_suffixes && devpath) {
size_t bootpathlen = strlen(devpath) + strlen(i->suffix) + 1;
bootpath = g_malloc(bootpathlen);
snprintf(bootpath, bootpathlen, "%s%s", devpath, i->suffix);
g_free(devpath);
} else if (devpath) {
bootpath = devpath;
} else if (!ignore_suffixes) {
assert(i->suffix);
bootpath = g_strdup(i->suffix);
} else {
bootpath = g_strdup("");
}
if (total) {
list[total-1] = '\n';
}
len = strlen(bootpath) + 1;
list = g_realloc(list, total + len);
memcpy(&list[total], bootpath, len);
total += len;
g_free(bootpath);
}
*size = total;
if (boot_strict && *size > 0) {
list[total-1] = '\n';
list = g_realloc(list, total + 5);
memcpy(&list[total], "HALT", 5);
*size = total + 5;
}
return list;
}
typedef struct {
int32_t *bootindex;
const char *suffix;
DeviceState *dev;
} BootIndexProperty;
static void device_get_bootindex(Object *obj, Visitor *v, void *opaque,
const char *name, Error **errp)
{
BootIndexProperty *prop = opaque;
visit_type_int32(v, prop->bootindex, name, 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, &boot_index, name, &local_err);
if (local_err) {
goto out;
}
/* check whether bootindex is present in fw_boot_order list */
check_boot_index(boot_index, &local_err);
if (local_err) {
goto out;
}
/* change bootindex to a new one */
*prop->bootindex = boot_index;
add_boot_device_path(*prop->bootindex, prop->dev, prop->suffix);
out:
if (local_err) {
error_propagate(errp, local_err);
}
}
static void property_release_bootindex(Object *obj, const char *name,
void *opaque)
{
BootIndexProperty *prop = opaque;
del_boot_device_path(prop->dev, prop->suffix);
g_free(prop);
}
void device_add_bootindex_property(Object *obj, int32_t *bootindex,
const char *name, const char *suffix,
DeviceState *dev, Error **errp)
{
Error *local_err = NULL;
BootIndexProperty *prop = g_malloc0(sizeof(*prop));
prop->bootindex = bootindex;
prop->suffix = suffix;
prop->dev = dev;
object_property_add(obj, name, "int32",
device_get_bootindex,
device_set_bootindex,
property_release_bootindex,
prop, &local_err);
if (local_err) {
error_propagate(errp, local_err);
g_free(prop);
return;
}
/* initialize devices' bootindex property to -1 */
object_property_set_int(obj, -1, name, NULL);
}

View File

@@ -1,37 +1,7 @@
/*
* FreeBSD strace list
*
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
{ TARGET_FREEBSD_NR___acl_aclcheck_fd, "__acl_aclcheck_fd", "%s(%d, %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_aclcheck_file, "__acl_aclcheck_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_aclcheck_link, "__acl_aclcheck_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_delete_fd, "__acl_delete_fd", "%s(%d, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_delete_file, "__acl_delete_file", "%s(\"%s\", %d)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_delete_link, "__acl_delete_link", "%s(\"%s\", %d)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_get_fd, "__acl_get_fd", "%s(%d, %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_get_file, "__acl_get_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_get_link, "__acl_get_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_set_fd, "__acl_set_fd", "%s(%d, %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_set_file, "__acl_set_file", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___acl_set_link, "__acl_set_link", "%s(\"%s\", %d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___getcwd, "__getcwd", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR___semctl, "__semctl", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR___syscall, "__syscall", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, print_sysctl, NULL },
{ TARGET_FREEBSD_NR__umtx_op, "_umtx_op", "%s(%#x, %d, %d, %#x, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR___sysctl, "__sysctl", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_accept, "accept", "%s(%d,%#x,%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_access, "access", "%s(\"%s\",%#o)", NULL, NULL },
{ TARGET_FREEBSD_NR_acct, "acct", NULL, NULL, NULL },
@@ -50,41 +20,24 @@
{ TARGET_FREEBSD_NR_connect, "connect", "%s(%d,%#x,%d)", NULL, NULL },
{ TARGET_FREEBSD_NR_dup, "dup", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_dup2, "dup2", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_eaccess, "eaccess", "%s(\"%s\",%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_execve, "execve", NULL, print_execve, NULL },
{ TARGET_FREEBSD_NR_exit, "exit", "%s(%d)\n", NULL, NULL },
{ TARGET_FREEBSD_NR_extattrctl, "extattrctl", "%s(\"%s\", %d, \"%s\", %d, \"%s\"", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_delete_fd, "extattr_delete_fd", "%s(%d, %d, \"%s\")", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_delete_file, "extattr_delete_file", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_delete_link, "extattr_delete_link", "%s(\"%s\", %d, \"%s\")", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_get_fd, "extattr_get_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_get_file, "extattr_get_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_list_fd, "extattr_list_fd", "%s(%d, %d, %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_list_file, "extattr_list_file", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_list_link, "extattr_list_link", "%s(\"%s\", %d, %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_set_fd, "extattr_set_fd", "%s(%d, %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_set_file, "extattr_set_file", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_extattr_set_link, "extattr_set_link", "%s(\"%s\", %d, \"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_fchdir, "fchdir", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fchflags, "fchflags", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fchmod, "fchmod", "%s(%d,%#o)", NULL, NULL },
{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(%d,%d,%d)", NULL, NULL },
{ TARGET_FREEBSD_NR_fchown, "fchown", "%s(\"%s\",%d,%d)", NULL, NULL },
{ TARGET_FREEBSD_NR_fcntl, "fcntl", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fexecve, "fexecve", NULL, print_execve, NULL },
{ TARGET_FREEBSD_NR_fhopen, "fhopen", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fhstat, "fhstat", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fhstatfs, "fhstatfs", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_flock, "flock", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fork, "fork", "%s()", NULL, NULL },
{ TARGET_FREEBSD_NR_fpathconf, "fpathconf", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_fstatat, "fstatat", "%s(%d,\"%s\", %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_fstat, "fstat", "%s(%d,%p)", NULL, NULL },
{ TARGET_FREEBSD_NR_fstatfs, "fstatfs", "%s(%d,%p)", NULL, NULL },
{ TARGET_FREEBSD_NR_fsync, "fsync", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_ftruncate, "ftruncate", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_futimes, "futimes", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_getcontext, "getcontext", "%s(%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_getdirentries, "getdirentries", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_freebsd6_mmap, "freebsd6_mmap", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_getegid, "getegid", "%s()", NULL, NULL },
@@ -110,7 +63,7 @@
{ TARGET_FREEBSD_NR_getsockopt, "getsockopt", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_gettimeofday, "gettimeofday", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_getuid, "getuid", "%s()", NULL, NULL },
{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, print_ioctl, NULL },
{ TARGET_FREEBSD_NR_ioctl, "ioctl", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_issetugid, "issetugid", "%s()", NULL, NULL },
{ TARGET_FREEBSD_NR_kevent, "kevent", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_kill, "kill", NULL, NULL, NULL },
@@ -119,7 +72,6 @@
{ TARGET_FREEBSD_NR_lchown, "lchown", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_link, "link", "%s(\"%s\",\"%s\")", NULL, NULL },
{ TARGET_FREEBSD_NR_listen, "listen", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_lpathconf, "lpathconf", "%s(\"%s\", %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_lseek, "lseek", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_lstat, "lstat", "%s(\"%s\",%p)", NULL, NULL },
{ TARGET_FREEBSD_NR_madvise, "madvise", NULL, NULL, NULL },
@@ -144,8 +96,7 @@
{ TARGET_FREEBSD_NR_nanosleep, "nanosleep", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_nfssvc, "nfssvc", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_open, "open", "%s(\"%s\",%#x,%#o)", NULL, NULL },
{ TARGET_FREEBSD_NR_openat, "openat", "%s(%d, \"%s\",%#x,%#o)", NULL, NULL },
{ TARGET_FREEBSD_NR_pathconf, "pathconf", "%s(\"%s\", %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_pathconf, "pathconf", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_pipe, "pipe", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_poll, "poll", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_pread, "pread", NULL, NULL, NULL },
@@ -165,7 +116,6 @@
{ TARGET_FREEBSD_NR_revoke, "revoke", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_rfork, "rfork", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_rmdir, "rmdir", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_rtprio_thread, "rtprio_thread", "%s(%d, %d, %p)", NULL, NULL },
{ TARGET_FREEBSD_NR_sbrk, "sbrk", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sched_yield, "sched_yield", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_select, "select", NULL, NULL, NULL },
@@ -173,7 +123,6 @@
{ TARGET_FREEBSD_NR_semop, "semop", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sendmsg, "sendmsg", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sendto, "sendto", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_setcontext, "setcontext", "%s(%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_setegid, "setegid", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_seteuid, "seteuid", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_setgid, "setgid", NULL, NULL, NULL },
@@ -202,7 +151,7 @@
{ TARGET_FREEBSD_NR_sigprocmask, "sigprocmask", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sigreturn, "sigreturn", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sigsuspend, "sigsuspend", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_socket, "socket", "%s(%d,%d,%d)", NULL, NULL },
{ TARGET_FREEBSD_NR_socket, "socket", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_socketpair, "socketpair", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sstk, "sstk", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_stat, "stat", "%s(\"%s\",%p)", NULL, NULL },
@@ -211,15 +160,6 @@
{ TARGET_FREEBSD_NR_sync, "sync", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_sysarch, "sysarch", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_syscall, "syscall", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_thr_create, "thr_create", "%s(%#x, %#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_exit, "thr_exit", "%s(%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_kill, "thr_kill", "%s(%d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_kill2, "thr_kill2", "%s(%d, %d, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_new, "thr_new", "%s(%#x, %d)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_self, "thr_self", "%s(%#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_set_name, "thr_set_name", "%s(%d, \"%s\")", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_suspend, "thr_suspend", "%s(%d, %#x)", NULL, NULL },
{ TARGET_FREEBSD_NR_thr_wake, "thr_wake", "%s(%d)", NULL, NULL },
{ TARGET_FREEBSD_NR_truncate, "truncate", NULL, NULL, NULL },
{ TARGET_FREEBSD_NR_umask, "umask", "%s(%#o)", NULL, NULL },
{ TARGET_FREEBSD_NR_unlink, "unlink", "%s(\"%s\")", NULL, NULL },

View File

@@ -1,450 +1,373 @@
/*
* System call numbers.
*
* created from FreeBSD: releng/9.1/sys/kern/syscalls.master 229723
* 2012-01-06 19:29:16Z jhb
* $FreeBSD: src/sys/sys/syscall.h,v 1.224 2008/08/24 21:23:08 rwatson Exp $
* created from FreeBSD: head/sys/kern/syscalls.master 182123 2008-08-24 21:20:35Z rwatson
*/
#define TARGET_FREEBSD_NR_syscall 0
#define TARGET_FREEBSD_NR_exit 1
#define TARGET_FREEBSD_NR_fork 2
#define TARGET_FREEBSD_NR_read 3
#define TARGET_FREEBSD_NR_write 4
#define TARGET_FREEBSD_NR_open 5
#define TARGET_FREEBSD_NR_close 6
#define TARGET_FREEBSD_NR_wait4 7
/* 8 is old creat */
#define TARGET_FREEBSD_NR_link 9
#define TARGET_FREEBSD_NR_unlink 10
/* 11 is obsolete execv */
#define TARGET_FREEBSD_NR_chdir 12
#define TARGET_FREEBSD_NR_fchdir 13
#define TARGET_FREEBSD_NR_mknod 14
#define TARGET_FREEBSD_NR_chmod 15
#define TARGET_FREEBSD_NR_chown 16
#define TARGET_FREEBSD_NR_break 17
#define TARGET_FREEBSD_NR_freebsd4_getfsstat 18
/* 19 is old lseek */
#define TARGET_FREEBSD_NR_getpid 20
#define TARGET_FREEBSD_NR_mount 21
#define TARGET_FREEBSD_NR_unmount 22
#define TARGET_FREEBSD_NR_setuid 23
#define TARGET_FREEBSD_NR_getuid 24
#define TARGET_FREEBSD_NR_geteuid 25
#define TARGET_FREEBSD_NR_ptrace 26
#define TARGET_FREEBSD_NR_recvmsg 27
#define TARGET_FREEBSD_NR_sendmsg 28
#define TARGET_FREEBSD_NR_recvfrom 29
#define TARGET_FREEBSD_NR_accept 30
#define TARGET_FREEBSD_NR_getpeername 31
#define TARGET_FREEBSD_NR_getsockname 32
#define TARGET_FREEBSD_NR_access 33
#define TARGET_FREEBSD_NR_chflags 34
#define TARGET_FREEBSD_NR_fchflags 35
#define TARGET_FREEBSD_NR_sync 36
#define TARGET_FREEBSD_NR_kill 37
/* 38 is old stat */
#define TARGET_FREEBSD_NR_getppid 39
/* 40 is old lstat */
#define TARGET_FREEBSD_NR_dup 41
#define TARGET_FREEBSD_NR_pipe 42
#define TARGET_FREEBSD_NR_getegid 43
#define TARGET_FREEBSD_NR_profil 44
#define TARGET_FREEBSD_NR_ktrace 45
/* 46 is old sigaction */
#define TARGET_FREEBSD_NR_getgid 47
/* 48 is old sigprocmask */
#define TARGET_FREEBSD_NR_getlogin 49
#define TARGET_FREEBSD_NR_setlogin 50
#define TARGET_FREEBSD_NR_acct 51
/* 52 is old sigpending */
#define TARGET_FREEBSD_NR_sigaltstack 53
#define TARGET_FREEBSD_NR_ioctl 54
#define TARGET_FREEBSD_NR_reboot 55
#define TARGET_FREEBSD_NR_revoke 56
#define TARGET_FREEBSD_NR_symlink 57
#define TARGET_FREEBSD_NR_readlink 58
#define TARGET_FREEBSD_NR_execve 59
#define TARGET_FREEBSD_NR_umask 60
#define TARGET_FREEBSD_NR_chroot 61
/* 62 is old fstat */
/* 63 is old getkerninfo */
/* 64 is old getpagesize */
#define TARGET_FREEBSD_NR_msync 65
#define TARGET_FREEBSD_NR_vfork 66
/* 67 is obsolete vread */
/* 68 is obsolete vwrite */
#define TARGET_FREEBSD_NR_sbrk 69
#define TARGET_FREEBSD_NR_sstk 70
/* 71 is old mmap */
#define TARGET_FREEBSD_NR_vadvise 72
#define TARGET_FREEBSD_NR_munmap 73
#define TARGET_FREEBSD_NR_mprotect 74
#define TARGET_FREEBSD_NR_madvise 75
/* 76 is obsolete vhangup */
/* 77 is obsolete vlimit */
#define TARGET_FREEBSD_NR_mincore 78
#define TARGET_FREEBSD_NR_getgroups 79
#define TARGET_FREEBSD_NR_setgroups 80
#define TARGET_FREEBSD_NR_getpgrp 81
#define TARGET_FREEBSD_NR_setpgid 82
#define TARGET_FREEBSD_NR_setitimer 83
/* 84 is old wait */
#define TARGET_FREEBSD_NR_swapon 85
#define TARGET_FREEBSD_NR_getitimer 86
/* 87 is old gethostname */
/* 88 is old sethostname */
#define TARGET_FREEBSD_NR_getdtablesize 89
#define TARGET_FREEBSD_NR_dup2 90
#define TARGET_FREEBSD_NR_fcntl 92
#define TARGET_FREEBSD_NR_select 93
#define TARGET_FREEBSD_NR_fsync 95
#define TARGET_FREEBSD_NR_setpriority 96
#define TARGET_FREEBSD_NR_socket 97
#define TARGET_FREEBSD_NR_connect 98
/* 99 is old accept */
#define TARGET_FREEBSD_NR_getpriority 100
/* 101 is old send */
/* 102 is old recv */
/* 103 is old sigreturn */
#define TARGET_FREEBSD_NR_bind 104
#define TARGET_FREEBSD_NR_setsockopt 105
#define TARGET_FREEBSD_NR_listen 106
/* 107 is obsolete vtimes */
/* 108 is old sigvec */
/* 109 is old sigblock */
/* 110 is old sigsetmask */
/* 111 is old sigsuspend */
/* 112 is old sigstack */
/* 113 is old recvmsg */
/* 114 is old sendmsg */
/* 115 is obsolete vtrace */
#define TARGET_FREEBSD_NR_gettimeofday 116
#define TARGET_FREEBSD_NR_getrusage 117
#define TARGET_FREEBSD_NR_getsockopt 118
#define TARGET_FREEBSD_NR_readv 120
#define TARGET_FREEBSD_NR_writev 121
#define TARGET_FREEBSD_NR_settimeofday 122
#define TARGET_FREEBSD_NR_fchown 123
#define TARGET_FREEBSD_NR_fchmod 124
/* 125 is old recvfrom */
#define TARGET_FREEBSD_NR_setreuid 126
#define TARGET_FREEBSD_NR_setregid 127
#define TARGET_FREEBSD_NR_rename 128
/* 129 is old truncate */
/* 130 is old ftruncate */
#define TARGET_FREEBSD_NR_flock 131
#define TARGET_FREEBSD_NR_mkfifo 132
#define TARGET_FREEBSD_NR_sendto 133
#define TARGET_FREEBSD_NR_shutdown 134
#define TARGET_FREEBSD_NR_socketpair 135
#define TARGET_FREEBSD_NR_mkdir 136
#define TARGET_FREEBSD_NR_rmdir 137
#define TARGET_FREEBSD_NR_utimes 138
/* 139 is obsolete 4.2 sigreturn */
#define TARGET_FREEBSD_NR_adjtime 140
/* 141 is old getpeername */
/* 142 is old gethostid */
/* 143 is old sethostid */
/* 144 is old getrlimit */
/* 145 is old setrlimit */
/* 146 is old killpg */
#define TARGET_FREEBSD_NR_killpg 146 /* COMPAT */
#define TARGET_FREEBSD_NR_setsid 147
#define TARGET_FREEBSD_NR_quotactl 148
/* 149 is old quota */
/* 150 is old getsockname */
#define TARGET_FREEBSD_NR_nlm_syscall 154
#define TARGET_FREEBSD_NR_nfssvc 155
/* 156 is old getdirentries */
#define TARGET_FREEBSD_NR_freebsd4_statfs 157
#define TARGET_FREEBSD_NR_freebsd4_fstatfs 158
#define TARGET_FREEBSD_NR_lgetfh 160
#define TARGET_FREEBSD_NR_getfh 161
#define TARGET_FREEBSD_NR_freebsd4_getdomainname 162
#define TARGET_FREEBSD_NR_freebsd4_setdomainname 163
#define TARGET_FREEBSD_NR_freebsd4_uname 164
#define TARGET_FREEBSD_NR_sysarch 165
#define TARGET_FREEBSD_NR_rtprio 166
#define TARGET_FREEBSD_NR_semsys 169
#define TARGET_FREEBSD_NR_msgsys 170
#define TARGET_FREEBSD_NR_shmsys 171
#define TARGET_FREEBSD_NR_freebsd6_pread 173
#define TARGET_FREEBSD_NR_freebsd6_pwrite 174
#define TARGET_FREEBSD_NR_setfib 175
#define TARGET_FREEBSD_NR_ntp_adjtime 176
#define TARGET_FREEBSD_NR_setgid 181
#define TARGET_FREEBSD_NR_setegid 182
#define TARGET_FREEBSD_NR_seteuid 183
#define TARGET_FREEBSD_NR_stat 188
#define TARGET_FREEBSD_NR_fstat 189
#define TARGET_FREEBSD_NR_lstat 190
#define TARGET_FREEBSD_NR_pathconf 191
#define TARGET_FREEBSD_NR_fpathconf 192
#define TARGET_FREEBSD_NR_getrlimit 194
#define TARGET_FREEBSD_NR_setrlimit 195
#define TARGET_FREEBSD_NR_getdirentries 196
#define TARGET_FREEBSD_NR_freebsd6_mmap 197
#define TARGET_FREEBSD_NR___syscall 198
#define TARGET_FREEBSD_NR_freebsd6_lseek 199
#define TARGET_FREEBSD_NR_freebsd6_truncate 200
#define TARGET_FREEBSD_NR_freebsd6_ftruncate 201
#define TARGET_FREEBSD_NR___sysctl 202
#define TARGET_FREEBSD_NR_mlock 203
#define TARGET_FREEBSD_NR_munlock 204
#define TARGET_FREEBSD_NR_undelete 205
#define TARGET_FREEBSD_NR_futimes 206
#define TARGET_FREEBSD_NR_getpgid 207
#define TARGET_FREEBSD_NR_poll 209
#define TARGET_FREEBSD_NR_freebsd7___semctl 220
#define TARGET_FREEBSD_NR_semget 221
#define TARGET_FREEBSD_NR_semop 222
#define TARGET_FREEBSD_NR_freebsd7_msgctl 224
#define TARGET_FREEBSD_NR_msgget 225
#define TARGET_FREEBSD_NR_msgsnd 226
#define TARGET_FREEBSD_NR_msgrcv 227
#define TARGET_FREEBSD_NR_shmat 228
#define TARGET_FREEBSD_NR_freebsd7_shmctl 229
#define TARGET_FREEBSD_NR_shmdt 230
#define TARGET_FREEBSD_NR_shmget 231
#define TARGET_FREEBSD_NR_clock_gettime 232
#define TARGET_FREEBSD_NR_clock_settime 233
#define TARGET_FREEBSD_NR_clock_getres 234
#define TARGET_FREEBSD_NR_ktimer_create 235
#define TARGET_FREEBSD_NR_ktimer_delete 236
#define TARGET_FREEBSD_NR_ktimer_settime 237
#define TARGET_FREEBSD_NR_ktimer_gettime 238
#define TARGET_FREEBSD_NR_ktimer_getoverrun 239
#define TARGET_FREEBSD_NR_nanosleep 240
#define TARGET_FREEBSD_NR_ntp_gettime 248
#define TARGET_FREEBSD_NR_minherit 250
#define TARGET_FREEBSD_NR_rfork 251
#define TARGET_FREEBSD_NR_openbsd_poll 252
#define TARGET_FREEBSD_NR_issetugid 253
#define TARGET_FREEBSD_NR_lchown 254
#define TARGET_FREEBSD_NR_aio_read 255
#define TARGET_FREEBSD_NR_aio_write 256
#define TARGET_FREEBSD_NR_lio_listio 257
#define TARGET_FREEBSD_NR_getdents 272
#define TARGET_FREEBSD_NR_lchmod 274
#define TARGET_FREEBSD_NR_netbsd_lchown 275
#define TARGET_FREEBSD_NR_lutimes 276
#define TARGET_FREEBSD_NR_netbsd_msync 277
#define TARGET_FREEBSD_NR_nstat 278
#define TARGET_FREEBSD_NR_nfstat 279
#define TARGET_FREEBSD_NR_nlstat 280
#define TARGET_FREEBSD_NR_preadv 289
#define TARGET_FREEBSD_NR_pwritev 290
#define TARGET_FREEBSD_NR_freebsd4_fhstatfs 297
#define TARGET_FREEBSD_NR_fhopen 298
#define TARGET_FREEBSD_NR_fhstat 299
#define TARGET_FREEBSD_NR_modnext 300
#define TARGET_FREEBSD_NR_modstat 301
#define TARGET_FREEBSD_NR_modfnext 302
#define TARGET_FREEBSD_NR_modfind 303
#define TARGET_FREEBSD_NR_kldload 304
#define TARGET_FREEBSD_NR_kldunload 305
#define TARGET_FREEBSD_NR_kldfind 306
#define TARGET_FREEBSD_NR_kldnext 307
#define TARGET_FREEBSD_NR_kldstat 308
#define TARGET_FREEBSD_NR_kldfirstmod 309
#define TARGET_FREEBSD_NR_getsid 310
#define TARGET_FREEBSD_NR_setresuid 311
#define TARGET_FREEBSD_NR_setresgid 312
/* 313 is obsolete signanosleep */
#define TARGET_FREEBSD_NR_aio_return 314
#define TARGET_FREEBSD_NR_aio_suspend 315
#define TARGET_FREEBSD_NR_aio_cancel 316
#define TARGET_FREEBSD_NR_aio_error 317
#define TARGET_FREEBSD_NR_oaio_read 318
#define TARGET_FREEBSD_NR_oaio_write 319
#define TARGET_FREEBSD_NR_olio_listio 320
#define TARGET_FREEBSD_NR_yield 321
/* 322 is obsolete thr_sleep */
/* 323 is obsolete thr_wakeup */
#define TARGET_FREEBSD_NR_mlockall 324
#define TARGET_FREEBSD_NR_munlockall 325
#define TARGET_FREEBSD_NR___getcwd 326
#define TARGET_FREEBSD_NR_sched_setparam 327
#define TARGET_FREEBSD_NR_sched_getparam 328
#define TARGET_FREEBSD_NR_sched_setscheduler 329
#define TARGET_FREEBSD_NR_sched_getscheduler 330
#define TARGET_FREEBSD_NR_sched_yield 331
#define TARGET_FREEBSD_NR_sched_get_priority_max 332
#define TARGET_FREEBSD_NR_sched_get_priority_min 333
#define TARGET_FREEBSD_NR_sched_rr_get_interval 334
#define TARGET_FREEBSD_NR_utrace 335
#define TARGET_FREEBSD_NR_freebsd4_sendfile 336
#define TARGET_FREEBSD_NR_kldsym 337
#define TARGET_FREEBSD_NR_jail 338
#define TARGET_FREEBSD_NR_nnpfs_syscall 339
#define TARGET_FREEBSD_NR_sigprocmask 340
#define TARGET_FREEBSD_NR_sigsuspend 341
#define TARGET_FREEBSD_NR_freebsd4_sigaction 342
#define TARGET_FREEBSD_NR_sigpending 343
#define TARGET_FREEBSD_NR_freebsd4_sigreturn 344
#define TARGET_FREEBSD_NR_sigtimedwait 345
#define TARGET_FREEBSD_NR_sigwaitinfo 346
#define TARGET_FREEBSD_NR___acl_get_file 347
#define TARGET_FREEBSD_NR___acl_set_file 348
#define TARGET_FREEBSD_NR___acl_get_fd 349
#define TARGET_FREEBSD_NR___acl_set_fd 350
#define TARGET_FREEBSD_NR___acl_delete_file 351
#define TARGET_FREEBSD_NR___acl_delete_fd 352
#define TARGET_FREEBSD_NR___acl_aclcheck_file 353
#define TARGET_FREEBSD_NR___acl_aclcheck_fd 354
#define TARGET_FREEBSD_NR_extattrctl 355
#define TARGET_FREEBSD_NR_extattr_set_file 356
#define TARGET_FREEBSD_NR_extattr_get_file 357
#define TARGET_FREEBSD_NR_extattr_delete_file 358
#define TARGET_FREEBSD_NR_aio_waitcomplete 359
#define TARGET_FREEBSD_NR_getresuid 360
#define TARGET_FREEBSD_NR_getresgid 361
#define TARGET_FREEBSD_NR_kqueue 362
#define TARGET_FREEBSD_NR_kevent 363
#define TARGET_FREEBSD_NR_extattr_set_fd 371
#define TARGET_FREEBSD_NR_extattr_get_fd 372
#define TARGET_FREEBSD_NR_extattr_delete_fd 373
#define TARGET_FREEBSD_NR___setugid 374
#define TARGET_FREEBSD_NR_eaccess 376
#define TARGET_FREEBSD_NR_afs3_syscall 377
#define TARGET_FREEBSD_NR_nmount 378
#define TARGET_FREEBSD_NR___mac_get_proc 384
#define TARGET_FREEBSD_NR___mac_set_proc 385
#define TARGET_FREEBSD_NR___mac_get_fd 386
#define TARGET_FREEBSD_NR___mac_get_file 387
#define TARGET_FREEBSD_NR___mac_set_fd 388
#define TARGET_FREEBSD_NR___mac_set_file 389
#define TARGET_FREEBSD_NR_kenv 390
#define TARGET_FREEBSD_NR_lchflags 391
#define TARGET_FREEBSD_NR_uuidgen 392
#define TARGET_FREEBSD_NR_sendfile 393
#define TARGET_FREEBSD_NR_mac_syscall 394
#define TARGET_FREEBSD_NR_getfsstat 395
#define TARGET_FREEBSD_NR_statfs 396
#define TARGET_FREEBSD_NR_fstatfs 397
#define TARGET_FREEBSD_NR_fhstatfs 398
#define TARGET_FREEBSD_NR_ksem_close 400
#define TARGET_FREEBSD_NR_ksem_post 401
#define TARGET_FREEBSD_NR_ksem_wait 402
#define TARGET_FREEBSD_NR_ksem_trywait 403
#define TARGET_FREEBSD_NR_ksem_init 404
#define TARGET_FREEBSD_NR_ksem_open 405
#define TARGET_FREEBSD_NR_ksem_unlink 406
#define TARGET_FREEBSD_NR_ksem_getvalue 407
#define TARGET_FREEBSD_NR_ksem_destroy 408
#define TARGET_FREEBSD_NR___mac_get_pid 409
#define TARGET_FREEBSD_NR___mac_get_link 410
#define TARGET_FREEBSD_NR___mac_set_link 411
#define TARGET_FREEBSD_NR_extattr_set_link 412
#define TARGET_FREEBSD_NR_extattr_get_link 413
#define TARGET_FREEBSD_NR_extattr_delete_link 414
#define TARGET_FREEBSD_NR___mac_execve 415
#define TARGET_FREEBSD_NR_sigaction 416
#define TARGET_FREEBSD_NR_sigreturn 417
#define TARGET_FREEBSD_NR_getcontext 421
#define TARGET_FREEBSD_NR_setcontext 422
#define TARGET_FREEBSD_NR_swapcontext 423
#define TARGET_FREEBSD_NR_swapoff 424
#define TARGET_FREEBSD_NR___acl_get_link 425
#define TARGET_FREEBSD_NR___acl_set_link 426
#define TARGET_FREEBSD_NR___acl_delete_link 427
#define TARGET_FREEBSD_NR___acl_aclcheck_link 428
#define TARGET_FREEBSD_NR_sigwait 429
#define TARGET_FREEBSD_NR_thr_create 430
#define TARGET_FREEBSD_NR_thr_exit 431
#define TARGET_FREEBSD_NR_thr_self 432
#define TARGET_FREEBSD_NR_thr_kill 433
#define TARGET_FREEBSD_NR__umtx_lock 434
#define TARGET_FREEBSD_NR__umtx_unlock 435
#define TARGET_FREEBSD_NR_jail_attach 436
#define TARGET_FREEBSD_NR_extattr_list_fd 437
#define TARGET_FREEBSD_NR_extattr_list_file 438
#define TARGET_FREEBSD_NR_extattr_list_link 439
#define TARGET_FREEBSD_NR_ksem_timedwait 441
#define TARGET_FREEBSD_NR_thr_suspend 442
#define TARGET_FREEBSD_NR_thr_wake 443
#define TARGET_FREEBSD_NR_kldunloadf 444
#define TARGET_FREEBSD_NR_audit 445
#define TARGET_FREEBSD_NR_auditon 446
#define TARGET_FREEBSD_NR_getauid 447
#define TARGET_FREEBSD_NR_setauid 448
#define TARGET_FREEBSD_NR_getaudit 449
#define TARGET_FREEBSD_NR_setaudit 450
#define TARGET_FREEBSD_NR_getaudit_addr 451
#define TARGET_FREEBSD_NR_setaudit_addr 452
#define TARGET_FREEBSD_NR_auditctl 453
#define TARGET_FREEBSD_NR__umtx_op 454
#define TARGET_FREEBSD_NR_thr_new 455
#define TARGET_FREEBSD_NR_sigqueue 456
#define TARGET_FREEBSD_NR_kmq_open 457
#define TARGET_FREEBSD_NR_kmq_setattr 458
#define TARGET_FREEBSD_NR_kmq_timedreceive 459
#define TARGET_FREEBSD_NR_kmq_timedsend 460
#define TARGET_FREEBSD_NR_kmq_notify 461
#define TARGET_FREEBSD_NR_kmq_unlink 462
#define TARGET_FREEBSD_NR_abort2 463
#define TARGET_FREEBSD_NR_thr_set_name 464
#define TARGET_FREEBSD_NR_aio_fsync 465
#define TARGET_FREEBSD_NR_rtprio_thread 466
#define TARGET_FREEBSD_NR_sctp_peeloff 471
#define TARGET_FREEBSD_NR_sctp_generic_sendmsg 472
#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov 473
#define TARGET_FREEBSD_NR_sctp_generic_recvmsg 474
#define TARGET_FREEBSD_NR_pread 475
#define TARGET_FREEBSD_NR_pwrite 476
#define TARGET_FREEBSD_NR_mmap 477
#define TARGET_FREEBSD_NR_lseek 478
#define TARGET_FREEBSD_NR_truncate 479
#define TARGET_FREEBSD_NR_ftruncate 480
#define TARGET_FREEBSD_NR_thr_kill2 481
#define TARGET_FREEBSD_NR_shm_open 482
#define TARGET_FREEBSD_NR_shm_unlink 483
#define TARGET_FREEBSD_NR_cpuset 484
#define TARGET_FREEBSD_NR_cpuset_setid 485
#define TARGET_FREEBSD_NR_cpuset_getid 486
#define TARGET_FREEBSD_NR_cpuset_getaffinity 487
#define TARGET_FREEBSD_NR_cpuset_setaffinity 488
#define TARGET_FREEBSD_NR_faccessat 489
#define TARGET_FREEBSD_NR_fchmodat 490
#define TARGET_FREEBSD_NR_fchownat 491
#define TARGET_FREEBSD_NR_fexecve 492
#define TARGET_FREEBSD_NR_fstatat 493
#define TARGET_FREEBSD_NR_futimesat 494
#define TARGET_FREEBSD_NR_linkat 495
#define TARGET_FREEBSD_NR_mkdirat 496
#define TARGET_FREEBSD_NR_mkfifoat 497
#define TARGET_FREEBSD_NR_mknodat 498
#define TARGET_FREEBSD_NR_openat 499
#define TARGET_FREEBSD_NR_readlinkat 500
#define TARGET_FREEBSD_NR_renameat 501
#define TARGET_FREEBSD_NR_symlinkat 502
#define TARGET_FREEBSD_NR_unlinkat 503
#define TARGET_FREEBSD_NR_posix_openpt 504
#define TARGET_FREEBSD_NR_gssd_syscall 505
#define TARGET_FREEBSD_NR_jail_get 506
#define TARGET_FREEBSD_NR_jail_set 507
#define TARGET_FREEBSD_NR_jail_remove 508
#define TARGET_FREEBSD_NR_closefrom 509
#define TARGET_FREEBSD_NR___semctl 510
#define TARGET_FREEBSD_NR_msgctl 511
#define TARGET_FREEBSD_NR_shmctl 512
#define TARGET_FREEBSD_NR_lpathconf 513
#define TARGET_FREEBSD_NR_cap_new 514
#define TARGET_FREEBSD_NR_cap_getrights 515
#define TARGET_FREEBSD_NR_cap_enter 516
#define TARGET_FREEBSD_NR_cap_getmode 517
#define TARGET_FREEBSD_NR_pdfork 518
#define TARGET_FREEBSD_NR_pdkill 519
#define TARGET_FREEBSD_NR_pdgetpid 520
#define TARGET_FREEBSD_NR_pselect 522
#define TARGET_FREEBSD_NR_getloginclass 523
#define TARGET_FREEBSD_NR_setloginclass 524
#define TARGET_FREEBSD_NR_rctl_get_racct 525
#define TARGET_FREEBSD_NR_rctl_get_rules 526
#define TARGET_FREEBSD_NR_rctl_get_limits 527
#define TARGET_FREEBSD_NR_rctl_add_rule 528
#define TARGET_FREEBSD_NR_rctl_remove_rule 529
#define TARGET_FREEBSD_NR_posix_fallocate 530
#define TARGET_FREEBSD_NR_posix_fadvise 531
#define TARGET_FREEBSD_NR_MAXSYSCALL 532
#define TARGET_FREEBSD_NR_syscall 0
#define TARGET_FREEBSD_NR_exit 1
#define TARGET_FREEBSD_NR_fork 2
#define TARGET_FREEBSD_NR_read 3
#define TARGET_FREEBSD_NR_write 4
#define TARGET_FREEBSD_NR_open 5
#define TARGET_FREEBSD_NR_close 6
#define TARGET_FREEBSD_NR_wait4 7
#define TARGET_FREEBSD_NR_link 9
#define TARGET_FREEBSD_NR_unlink 10
#define TARGET_FREEBSD_NR_chdir 12
#define TARGET_FREEBSD_NR_fchdir 13
#define TARGET_FREEBSD_NR_mknod 14
#define TARGET_FREEBSD_NR_chmod 15
#define TARGET_FREEBSD_NR_chown 16
#define TARGET_FREEBSD_NR_break 17
#define TARGET_FREEBSD_NR_freebsd4_getfsstat 18
#define TARGET_FREEBSD_NR_getpid 20
#define TARGET_FREEBSD_NR_mount 21
#define TARGET_FREEBSD_NR_unmount 22
#define TARGET_FREEBSD_NR_setuid 23
#define TARGET_FREEBSD_NR_getuid 24
#define TARGET_FREEBSD_NR_geteuid 25
#define TARGET_FREEBSD_NR_ptrace 26
#define TARGET_FREEBSD_NR_recvmsg 27
#define TARGET_FREEBSD_NR_sendmsg 28
#define TARGET_FREEBSD_NR_recvfrom 29
#define TARGET_FREEBSD_NR_accept 30
#define TARGET_FREEBSD_NR_getpeername 31
#define TARGET_FREEBSD_NR_getsockname 32
#define TARGET_FREEBSD_NR_access 33
#define TARGET_FREEBSD_NR_chflags 34
#define TARGET_FREEBSD_NR_fchflags 35
#define TARGET_FREEBSD_NR_sync 36
#define TARGET_FREEBSD_NR_kill 37
#define TARGET_FREEBSD_NR_getppid 39
#define TARGET_FREEBSD_NR_dup 41
#define TARGET_FREEBSD_NR_pipe 42
#define TARGET_FREEBSD_NR_getegid 43
#define TARGET_FREEBSD_NR_profil 44
#define TARGET_FREEBSD_NR_ktrace 45
#define TARGET_FREEBSD_NR_getgid 47
#define TARGET_FREEBSD_NR_getlogin 49
#define TARGET_FREEBSD_NR_setlogin 50
#define TARGET_FREEBSD_NR_acct 51
#define TARGET_FREEBSD_NR_sigaltstack 53
#define TARGET_FREEBSD_NR_ioctl 54
#define TARGET_FREEBSD_NR_reboot 55
#define TARGET_FREEBSD_NR_revoke 56
#define TARGET_FREEBSD_NR_symlink 57
#define TARGET_FREEBSD_NR_readlink 58
#define TARGET_FREEBSD_NR_execve 59
#define TARGET_FREEBSD_NR_umask 60
#define TARGET_FREEBSD_NR_chroot 61
#define TARGET_FREEBSD_NR_msync 65
#define TARGET_FREEBSD_NR_vfork 66
#define TARGET_FREEBSD_NR_sbrk 69
#define TARGET_FREEBSD_NR_sstk 70
#define TARGET_FREEBSD_NR_vadvise 72
#define TARGET_FREEBSD_NR_munmap 73
#define TARGET_FREEBSD_NR_mprotect 74
#define TARGET_FREEBSD_NR_madvise 75
#define TARGET_FREEBSD_NR_mincore 78
#define TARGET_FREEBSD_NR_getgroups 79
#define TARGET_FREEBSD_NR_setgroups 80
#define TARGET_FREEBSD_NR_getpgrp 81
#define TARGET_FREEBSD_NR_setpgid 82
#define TARGET_FREEBSD_NR_setitimer 83
#define TARGET_FREEBSD_NR_swapon 85
#define TARGET_FREEBSD_NR_getitimer 86
#define TARGET_FREEBSD_NR_getdtablesize 89
#define TARGET_FREEBSD_NR_dup2 90
#define TARGET_FREEBSD_NR_fcntl 92
#define TARGET_FREEBSD_NR_select 93
#define TARGET_FREEBSD_NR_fsync 95
#define TARGET_FREEBSD_NR_setpriority 96
#define TARGET_FREEBSD_NR_socket 97
#define TARGET_FREEBSD_NR_connect 98
#define TARGET_FREEBSD_NR_getpriority 100
#define TARGET_FREEBSD_NR_bind 104
#define TARGET_FREEBSD_NR_setsockopt 105
#define TARGET_FREEBSD_NR_listen 106
#define TARGET_FREEBSD_NR_gettimeofday 116
#define TARGET_FREEBSD_NR_getrusage 117
#define TARGET_FREEBSD_NR_getsockopt 118
#define TARGET_FREEBSD_NR_readv 120
#define TARGET_FREEBSD_NR_writev 121
#define TARGET_FREEBSD_NR_settimeofday 122
#define TARGET_FREEBSD_NR_fchown 123
#define TARGET_FREEBSD_NR_fchmod 124
#define TARGET_FREEBSD_NR_setreuid 126
#define TARGET_FREEBSD_NR_setregid 127
#define TARGET_FREEBSD_NR_rename 128
#define TARGET_FREEBSD_NR_flock 131
#define TARGET_FREEBSD_NR_mkfifo 132
#define TARGET_FREEBSD_NR_sendto 133
#define TARGET_FREEBSD_NR_shutdown 134
#define TARGET_FREEBSD_NR_socketpair 135
#define TARGET_FREEBSD_NR_mkdir 136
#define TARGET_FREEBSD_NR_rmdir 137
#define TARGET_FREEBSD_NR_utimes 138
#define TARGET_FREEBSD_NR_adjtime 140
#define TARGET_FREEBSD_NR_setsid 147
#define TARGET_FREEBSD_NR_quotactl 148
#define TARGET_FREEBSD_NR_nlm_syscall 154
#define TARGET_FREEBSD_NR_nfssvc 155
#define TARGET_FREEBSD_NR_freebsd4_statfs 157
#define TARGET_FREEBSD_NR_freebsd4_fstatfs 158
#define TARGET_FREEBSD_NR_lgetfh 160
#define TARGET_FREEBSD_NR_getfh 161
#define TARGET_FREEBSD_NR_getdomainname 162
#define TARGET_FREEBSD_NR_setdomainname 163
#define TARGET_FREEBSD_NR_uname 164
#define TARGET_FREEBSD_NR_sysarch 165
#define TARGET_FREEBSD_NR_rtprio 166
#define TARGET_FREEBSD_NR_semsys 169
#define TARGET_FREEBSD_NR_msgsys 170
#define TARGET_FREEBSD_NR_shmsys 171
#define TARGET_FREEBSD_NR_freebsd6_pread 173
#define TARGET_FREEBSD_NR_freebsd6_pwrite 174
#define TARGET_FREEBSD_NR_setfib 175
#define TARGET_FREEBSD_NR_ntp_adjtime 176
#define TARGET_FREEBSD_NR_setgid 181
#define TARGET_FREEBSD_NR_setegid 182
#define TARGET_FREEBSD_NR_seteuid 183
#define TARGET_FREEBSD_NR_stat 188
#define TARGET_FREEBSD_NR_fstat 189
#define TARGET_FREEBSD_NR_lstat 190
#define TARGET_FREEBSD_NR_pathconf 191
#define TARGET_FREEBSD_NR_fpathconf 192
#define TARGET_FREEBSD_NR_getrlimit 194
#define TARGET_FREEBSD_NR_setrlimit 195
#define TARGET_FREEBSD_NR_getdirentries 196
#define TARGET_FREEBSD_NR_freebsd6_mmap 197
#define TARGET_FREEBSD_NR___syscall 198
#define TARGET_FREEBSD_NR_freebsd6_lseek 199
#define TARGET_FREEBSD_NR_freebsd6_truncate 200
#define TARGET_FREEBSD_NR_freebsd6_ftruncate 201
#define TARGET_FREEBSD_NR___sysctl 202
#define TARGET_FREEBSD_NR_mlock 203
#define TARGET_FREEBSD_NR_munlock 204
#define TARGET_FREEBSD_NR_undelete 205
#define TARGET_FREEBSD_NR_futimes 206
#define TARGET_FREEBSD_NR_getpgid 207
#define TARGET_FREEBSD_NR_poll 209
#define TARGET_FREEBSD_NR___semctl 220
#define TARGET_FREEBSD_NR_semget 221
#define TARGET_FREEBSD_NR_semop 222
#define TARGET_FREEBSD_NR_msgctl 224
#define TARGET_FREEBSD_NR_msgget 225
#define TARGET_FREEBSD_NR_msgsnd 226
#define TARGET_FREEBSD_NR_msgrcv 227
#define TARGET_FREEBSD_NR_shmat 228
#define TARGET_FREEBSD_NR_shmctl 229
#define TARGET_FREEBSD_NR_shmdt 230
#define TARGET_FREEBSD_NR_shmget 231
#define TARGET_FREEBSD_NR_clock_gettime 232
#define TARGET_FREEBSD_NR_clock_settime 233
#define TARGET_FREEBSD_NR_clock_getres 234
#define TARGET_FREEBSD_NR_ktimer_create 235
#define TARGET_FREEBSD_NR_ktimer_delete 236
#define TARGET_FREEBSD_NR_ktimer_settime 237
#define TARGET_FREEBSD_NR_ktimer_gettime 238
#define TARGET_FREEBSD_NR_ktimer_getoverrun 239
#define TARGET_FREEBSD_NR_nanosleep 240
#define TARGET_FREEBSD_NR_ntp_gettime 248
#define TARGET_FREEBSD_NR_minherit 250
#define TARGET_FREEBSD_NR_rfork 251
#define TARGET_FREEBSD_NR_openbsd_poll 252
#define TARGET_FREEBSD_NR_issetugid 253
#define TARGET_FREEBSD_NR_lchown 254
#define TARGET_FREEBSD_NR_aio_read 255
#define TARGET_FREEBSD_NR_aio_write 256
#define TARGET_FREEBSD_NR_lio_listio 257
#define TARGET_FREEBSD_NR_getdents 272
#define TARGET_FREEBSD_NR_lchmod 274
#define TARGET_FREEBSD_NR_netbsd_lchown 275
#define TARGET_FREEBSD_NR_lutimes 276
#define TARGET_FREEBSD_NR_netbsd_msync 277
#define TARGET_FREEBSD_NR_nstat 278
#define TARGET_FREEBSD_NR_nfstat 279
#define TARGET_FREEBSD_NR_nlstat 280
#define TARGET_FREEBSD_NR_preadv 289
#define TARGET_FREEBSD_NR_pwritev 290
#define TARGET_FREEBSD_NR_freebsd4_fhstatfs 297
#define TARGET_FREEBSD_NR_fhopen 298
#define TARGET_FREEBSD_NR_fhstat 299
#define TARGET_FREEBSD_NR_modnext 300
#define TARGET_FREEBSD_NR_modstat 301
#define TARGET_FREEBSD_NR_modfnext 302
#define TARGET_FREEBSD_NR_modfind 303
#define TARGET_FREEBSD_NR_kldload 304
#define TARGET_FREEBSD_NR_kldunload 305
#define TARGET_FREEBSD_NR_kldfind 306
#define TARGET_FREEBSD_NR_kldnext 307
#define TARGET_FREEBSD_NR_kldstat 308
#define TARGET_FREEBSD_NR_kldfirstmod 309
#define TARGET_FREEBSD_NR_getsid 310
#define TARGET_FREEBSD_NR_setresuid 311
#define TARGET_FREEBSD_NR_setresgid 312
#define TARGET_FREEBSD_NR_aio_return 314
#define TARGET_FREEBSD_NR_aio_suspend 315
#define TARGET_FREEBSD_NR_aio_cancel 316
#define TARGET_FREEBSD_NR_aio_error 317
#define TARGET_FREEBSD_NR_oaio_read 318
#define TARGET_FREEBSD_NR_oaio_write 319
#define TARGET_FREEBSD_NR_olio_listio 320
#define TARGET_FREEBSD_NR_yield 321
#define TARGET_FREEBSD_NR_mlockall 324
#define TARGET_FREEBSD_NR_munlockall 325
#define TARGET_FREEBSD_NR___getcwd 326
#define TARGET_FREEBSD_NR_sched_setparam 327
#define TARGET_FREEBSD_NR_sched_getparam 328
#define TARGET_FREEBSD_NR_sched_setscheduler 329
#define TARGET_FREEBSD_NR_sched_getscheduler 330
#define TARGET_FREEBSD_NR_sched_yield 331
#define TARGET_FREEBSD_NR_sched_get_priority_max 332
#define TARGET_FREEBSD_NR_sched_get_priority_min 333
#define TARGET_FREEBSD_NR_sched_rr_get_interval 334
#define TARGET_FREEBSD_NR_utrace 335
#define TARGET_FREEBSD_NR_freebsd4_sendfile 336
#define TARGET_FREEBSD_NR_kldsym 337
#define TARGET_FREEBSD_NR_jail 338
#define TARGET_FREEBSD_NR_sigprocmask 340
#define TARGET_FREEBSD_NR_sigsuspend 341
#define TARGET_FREEBSD_NR_freebsd4_sigaction 342
#define TARGET_FREEBSD_NR_sigpending 343
#define TARGET_FREEBSD_NR_freebsd4_sigreturn 344
#define TARGET_FREEBSD_NR_sigtimedwait 345
#define TARGET_FREEBSD_NR_sigwaitinfo 346
#define TARGET_FREEBSD_NR___acl_get_file 347
#define TARGET_FREEBSD_NR___acl_set_file 348
#define TARGET_FREEBSD_NR___acl_get_fd 349
#define TARGET_FREEBSD_NR___acl_set_fd 350
#define TARGET_FREEBSD_NR___acl_delete_file 351
#define TARGET_FREEBSD_NR___acl_delete_fd 352
#define TARGET_FREEBSD_NR___acl_aclcheck_file 353
#define TARGET_FREEBSD_NR___acl_aclcheck_fd 354
#define TARGET_FREEBSD_NR_extattrctl 355
#define TARGET_FREEBSD_NR_extattr_set_file 356
#define TARGET_FREEBSD_NR_extattr_get_file 357
#define TARGET_FREEBSD_NR_extattr_delete_file 358
#define TARGET_FREEBSD_NR_aio_waitcomplete 359
#define TARGET_FREEBSD_NR_getresuid 360
#define TARGET_FREEBSD_NR_getresgid 361
#define TARGET_FREEBSD_NR_kqueue 362
#define TARGET_FREEBSD_NR_kevent 363
#define TARGET_FREEBSD_NR_extattr_set_fd 371
#define TARGET_FREEBSD_NR_extattr_get_fd 372
#define TARGET_FREEBSD_NR_extattr_delete_fd 373
#define TARGET_FREEBSD_NR___setugid 374
#define TARGET_FREEBSD_NR_nfsclnt 375
#define TARGET_FREEBSD_NR_eaccess 376
#define TARGET_FREEBSD_NR_nmount 378
#define TARGET_FREEBSD_NR___mac_get_proc 384
#define TARGET_FREEBSD_NR___mac_set_proc 385
#define TARGET_FREEBSD_NR___mac_get_fd 386
#define TARGET_FREEBSD_NR___mac_get_file 387
#define TARGET_FREEBSD_NR___mac_set_fd 388
#define TARGET_FREEBSD_NR___mac_set_file 389
#define TARGET_FREEBSD_NR_kenv 390
#define TARGET_FREEBSD_NR_lchflags 391
#define TARGET_FREEBSD_NR_uuidgen 392
#define TARGET_FREEBSD_NR_sendfile 393
#define TARGET_FREEBSD_NR_mac_syscall 394
#define TARGET_FREEBSD_NR_getfsstat 395
#define TARGET_FREEBSD_NR_statfs 396
#define TARGET_FREEBSD_NR_fstatfs 397
#define TARGET_FREEBSD_NR_fhstatfs 398
#define TARGET_FREEBSD_NR_ksem_close 400
#define TARGET_FREEBSD_NR_ksem_post 401
#define TARGET_FREEBSD_NR_ksem_wait 402
#define TARGET_FREEBSD_NR_ksem_trywait 403
#define TARGET_FREEBSD_NR_ksem_init 404
#define TARGET_FREEBSD_NR_ksem_open 405
#define TARGET_FREEBSD_NR_ksem_unlink 406
#define TARGET_FREEBSD_NR_ksem_getvalue 407
#define TARGET_FREEBSD_NR_ksem_destroy 408
#define TARGET_FREEBSD_NR___mac_get_pid 409
#define TARGET_FREEBSD_NR___mac_get_link 410
#define TARGET_FREEBSD_NR___mac_set_link 411
#define TARGET_FREEBSD_NR_extattr_set_link 412
#define TARGET_FREEBSD_NR_extattr_get_link 413
#define TARGET_FREEBSD_NR_extattr_delete_link 414
#define TARGET_FREEBSD_NR___mac_execve 415
#define TARGET_FREEBSD_NR_sigaction 416
#define TARGET_FREEBSD_NR_sigreturn 417
#define TARGET_FREEBSD_NR_getcontext 421
#define TARGET_FREEBSD_NR_setcontext 422
#define TARGET_FREEBSD_NR_swapcontext 423
#define TARGET_FREEBSD_NR_swapoff 424
#define TARGET_FREEBSD_NR___acl_get_link 425
#define TARGET_FREEBSD_NR___acl_set_link 426
#define TARGET_FREEBSD_NR___acl_delete_link 427
#define TARGET_FREEBSD_NR___acl_aclcheck_link 428
#define TARGET_FREEBSD_NR_sigwait 429
#define TARGET_FREEBSD_NR_thr_create 430
#define TARGET_FREEBSD_NR_thr_exit 431
#define TARGET_FREEBSD_NR_thr_self 432
#define TARGET_FREEBSD_NR_thr_kill 433
#define TARGET_FREEBSD_NR__umtx_lock 434
#define TARGET_FREEBSD_NR__umtx_unlock 435
#define TARGET_FREEBSD_NR_jail_attach 436
#define TARGET_FREEBSD_NR_extattr_list_fd 437
#define TARGET_FREEBSD_NR_extattr_list_file 438
#define TARGET_FREEBSD_NR_extattr_list_link 439
#define TARGET_FREEBSD_NR_ksem_timedwait 441
#define TARGET_FREEBSD_NR_thr_suspend 442
#define TARGET_FREEBSD_NR_thr_wake 443
#define TARGET_FREEBSD_NR_kldunloadf 444
#define TARGET_FREEBSD_NR_audit 445
#define TARGET_FREEBSD_NR_auditon 446
#define TARGET_FREEBSD_NR_getauid 447
#define TARGET_FREEBSD_NR_setauid 448
#define TARGET_FREEBSD_NR_getaudit 449
#define TARGET_FREEBSD_NR_setaudit 450
#define TARGET_FREEBSD_NR_getaudit_addr 451
#define TARGET_FREEBSD_NR_setaudit_addr 452
#define TARGET_FREEBSD_NR_auditctl 453
#define TARGET_FREEBSD_NR__umtx_op 454
#define TARGET_FREEBSD_NR_thr_new 455
#define TARGET_FREEBSD_NR_sigqueue 456
#define TARGET_FREEBSD_NR_kmq_open 457
#define TARGET_FREEBSD_NR_kmq_setattr 458
#define TARGET_FREEBSD_NR_kmq_timedreceive 459
#define TARGET_FREEBSD_NR_kmq_timedsend 460
#define TARGET_FREEBSD_NR_kmq_notify 461
#define TARGET_FREEBSD_NR_kmq_unlink 462
#define TARGET_FREEBSD_NR_abort2 463
#define TARGET_FREEBSD_NR_thr_set_name 464
#define TARGET_FREEBSD_NR_aio_fsync 465
#define TARGET_FREEBSD_NR_rtprio_thread 466
#define TARGET_FREEBSD_NR_sctp_peeloff 471
#define TARGET_FREEBSD_NR_sctp_generic_sendmsg 472
#define TARGET_FREEBSD_NR_sctp_generic_sendmsg_iov 473
#define TARGET_FREEBSD_NR_sctp_generic_recvmsg 474
#define TARGET_FREEBSD_NR_pread 475
#define TARGET_FREEBSD_NR_pwrite 476
#define TARGET_FREEBSD_NR_mmap 477
#define TARGET_FREEBSD_NR_lseek 478
#define TARGET_FREEBSD_NR_truncate 479
#define TARGET_FREEBSD_NR_ftruncate 480
#define TARGET_FREEBSD_NR_thr_kill2 481
#define TARGET_FREEBSD_NR_shm_open 482
#define TARGET_FREEBSD_NR_shm_unlink 483
#define TARGET_FREEBSD_NR_cpuset 484
#define TARGET_FREEBSD_NR_cpuset_setid 485
#define TARGET_FREEBSD_NR_cpuset_getid 486
#define TARGET_FREEBSD_NR_cpuset_getaffinity 487
#define TARGET_FREEBSD_NR_cpuset_setaffinity 488
#define TARGET_FREEBSD_NR_faccessat 489
#define TARGET_FREEBSD_NR_fchmodat 490
#define TARGET_FREEBSD_NR_fchownat 491
#define TARGET_FREEBSD_NR_fexecve 492
#define TARGET_FREEBSD_NR_fstatat 493
#define TARGET_FREEBSD_NR_futimesat 494
#define TARGET_FREEBSD_NR_linkat 495
#define TARGET_FREEBSD_NR_mkdirat 496
#define TARGET_FREEBSD_NR_mkfifoat 497
#define TARGET_FREEBSD_NR_mknodat 498
#define TARGET_FREEBSD_NR_openat 499
#define TARGET_FREEBSD_NR_readlinkat 500
#define TARGET_FREEBSD_NR_renameat 501
#define TARGET_FREEBSD_NR_symlinkat 502
#define TARGET_FREEBSD_NR_unlinkat 503
#define TARGET_FREEBSD_NR_posix_openpt 504

View File

@@ -43,7 +43,7 @@ unsigned long reserved_va;
#endif
static const char *interp_prefix = CONFIG_QEMU_INTERP_PREFIX;
const char *qemu_uname_release;
const char *qemu_uname_release = CONFIG_UNAME_RELEASE;
extern char **environ;
enum BSDType bsd_type;
@@ -1003,8 +1003,10 @@ int main(int argc, char **argv)
cpu->opaque = ts;
#if defined(TARGET_I386)
cpu_x86_set_cpl(env, 3);
env->cr[0] = CR0_PG_MASK | CR0_WP_MASK | CR0_PE_MASK;
env->hflags |= HF_PE_MASK | HF_CPL_MASK;
env->hflags |= HF_PE_MASK;
if (env->features[FEAT_1_EDX] & CPUID_SSE) {
env->cr[4] |= CR4_OSFXSR_MASK;
env->hflags |= HF_OSFXSR_MASK;

View File

@@ -74,6 +74,66 @@ void mmap_unlock(void)
}
#endif
static void *bsd_vmalloc(size_t size)
{
void *p;
mmap_lock();
/* Use map and mark the pages as used. */
p = mmap(NULL, size, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANON, -1, 0);
if (h2g_valid(p)) {
/* Allocated region overlaps guest address space.
This may recurse. */
abi_ulong addr = h2g(p);
page_set_flags(addr & TARGET_PAGE_MASK, TARGET_PAGE_ALIGN(addr + size),
PAGE_RESERVED);
}
mmap_unlock();
return p;
}
void *g_malloc(size_t size)
{
char * p;
size += 16;
p = bsd_vmalloc(size);
*(size_t *)p = size;
return p + 16;
}
/* We use map, which is always zero initialized. */
void * g_malloc0(size_t size)
{
return g_malloc(size);
}
void g_free(void *ptr)
{
/* FIXME: We should unmark the reserved pages here. However this gets
complicated when one target page spans multiple host pages, so we
don't bother. */
size_t *p;
p = (size_t *)((char *)ptr - 16);
munmap(p, *p);
}
void *g_realloc(void *ptr, size_t size)
{
size_t old_size, copy;
void *new_ptr;
if (!ptr)
return g_malloc(size);
old_size = *(size_t *)((char *)ptr - 16);
copy = old_size < size ? old_size : size;
new_ptr = g_malloc(size);
memcpy(new_ptr, ptr, copy);
g_free(ptr);
return new_ptr;
}
/* NOTE: all the constants are the HOST ones, but addresses are target. */
int target_mprotect(abi_ulong start, abi_ulong len, int prot)
{

View File

@@ -1,19 +1,3 @@
/*
* qemu bsd user mode definition
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#ifndef QEMU_H
#define QEMU_H
@@ -21,7 +5,6 @@
#include <string.h>
#include "cpu.h"
#include "exec/cpu_ldst.h"
#undef DEBUG_REMAP
#ifdef DEBUG_REMAP
@@ -166,16 +149,6 @@ void fork_end(int child);
#include "qemu/log.h"
/* strace.c */
struct syscallname {
int nr;
const char *name;
const char *format;
void (*call)(const struct syscallname *,
abi_long, abi_long, abi_long,
abi_long, abi_long, abi_long);
void (*result)(const struct syscallname *, abi_long);
};
void
print_freebsd_syscall(int num,
abi_long arg1, abi_long arg2, abi_long arg3,

View File

@@ -1,71 +1,37 @@
/*
* System call tracing and debugging
*
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, see <http://www.gnu.org/licenses/>.
*/
#include <stdio.h>
#include <errno.h>
#include <sys/select.h>
#include <sys/types.h>
#include <unistd.h>
#include <sys/syscall.h>
#include <sys/ioccom.h>
#include <ctype.h>
#include "qemu.h"
int do_strace;
int do_strace=0;
struct syscallname {
int nr;
const char *name;
const char *format;
void (*call)(const struct syscallname *,
abi_long, abi_long, abi_long,
abi_long, abi_long, abi_long);
void (*result)(const struct syscallname *, abi_long);
};
/*
* Utility functions
*/
static void print_sysctl(const struct syscallname *name, abi_long arg1,
abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
abi_long arg6)
{
uint32_t i;
int32_t *namep;
gemu_log("%s({ ", name->name);
namep = lock_user(VERIFY_READ, arg1, sizeof(int32_t) * arg2, 1);
if (namep) {
int32_t *p = namep;
for (i = 0; i < (uint32_t)arg2; i++) {
gemu_log("%d ", tswap32(*p++));
}
unlock_user(namep, arg1, 0);
}
gemu_log("}, %u, 0x" TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ", 0x"
TARGET_ABI_FMT_lx ", 0x" TARGET_ABI_FMT_lx ")",
(uint32_t)arg2, arg3, arg4, arg5, arg6);
}
static void print_execve(const struct syscallname *name, abi_long arg1,
abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5,
abi_long arg6)
static void
print_execve(const struct syscallname *name,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
{
abi_ulong arg_ptr_addr;
char *s;
s = lock_user_string(arg1);
if (s == NULL) {
if (!(s = lock_user_string(arg1)))
return;
}
gemu_log("%s(\"%s\",{", name->name, s);
unlock_user(s, arg1, 0);
@@ -73,48 +39,29 @@ static void print_execve(const struct syscallname *name, abi_long arg1,
abi_ulong *arg_ptr, arg_addr;
arg_ptr = lock_user(VERIFY_READ, arg_ptr_addr, sizeof(abi_ulong), 1);
if (!arg_ptr) {
if (!arg_ptr)
return;
}
arg_addr = tswapl(*arg_ptr);
unlock_user(arg_ptr, arg_ptr_addr, 0);
if (!arg_addr) {
if (!arg_addr)
break;
}
if ((s = lock_user_string(arg_addr))) {
gemu_log("\"%s\",", s);
unlock_user(s, arg_addr, 0);
}
}
gemu_log("NULL})");
}
static void print_ioctl(const struct syscallname *name,
abi_long arg1, abi_long arg2, abi_long arg3, abi_long arg4,
abi_long arg5, abi_long arg6)
{
/* Decode the ioctl request */
gemu_log("%s(%d, 0x%0lx { IO%s%s GRP:0x%x('%c') CMD:%d LEN:%d }, 0x"
TARGET_ABI_FMT_lx ", ...)",
name->name,
(int)arg1,
(unsigned long)arg2,
arg2 & IOC_OUT ? "R" : "",
arg2 & IOC_IN ? "W" : "",
(unsigned)IOCGROUP(arg2),
isprint(IOCGROUP(arg2)) ? (char)IOCGROUP(arg2) : '?',
(int)arg2 & 0xFF,
(int)IOCPARM_LEN(arg2),
arg3);
gemu_log("NULL})");
}
/*
* Variants for the return value output function
*/
static void print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
static void
print_syscall_ret_addr(const struct syscallname *name, abi_long ret)
{
if (ret == -1) {
if( ret == -1 ) {
gemu_log(" = -1 errno=%d (%s)\n", errno, strerror(errno));
} else {
gemu_log(" = 0x" TARGET_ABI_FMT_lx "\n", ret);
@@ -143,9 +90,10 @@ static const struct syscallname openbsd_scnames[] = {
#include "openbsd/strace.list"
};
static void print_syscall(int num, const struct syscallname *scnames,
unsigned int nscnames, abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
static void
print_syscall(int num, const struct syscallname *scnames, unsigned int nscnames,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
{
unsigned int i;
const char *format="%s(" TARGET_ABI_FMT_ld "," TARGET_ABI_FMT_ld ","
@@ -154,37 +102,36 @@ static void print_syscall(int num, const struct syscallname *scnames,
gemu_log("%d ", getpid() );
for (i = 0; i < nscnames; i++) {
for (i = 0; i < nscnames; i++)
if (scnames[i].nr == num) {
if (scnames[i].call != NULL) {
scnames[i].call(&scnames[i], arg1, arg2, arg3, arg4, arg5,
arg6);
arg6);
} else {
/* XXX: this format system is broken because it uses
host types and host pointers for strings */
if (scnames[i].format != NULL) {
if (scnames[i].format != NULL)
format = scnames[i].format;
}
gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4, arg5,
arg6);
gemu_log(format, scnames[i].name, arg1, arg2, arg3, arg4,
arg5, arg6);
}
return;
}
}
gemu_log("Unknown syscall %d\n", num);
}
static void print_syscall_ret(int num, abi_long ret,
const struct syscallname *scnames, unsigned int nscnames)
static void
print_syscall_ret(int num, abi_long ret, const struct syscallname *scnames,
unsigned int nscnames)
{
unsigned int i;
for (i = 0; i < nscnames; i++) {
for (i = 0; i < nscnames; i++)
if (scnames[i].nr == num) {
if (scnames[i].result != NULL) {
scnames[i].result(&scnames[i], ret);
} else {
if (ret < 0) {
if( ret < 0 ) {
gemu_log(" = -1 errno=" TARGET_ABI_FMT_ld " (%s)\n", -ret,
strerror(-ret));
} else {
@@ -193,50 +140,52 @@ static void print_syscall_ret(int num, abi_long ret,
}
break;
}
}
}
/*
* The public interface to this module.
*/
void print_freebsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
void
print_freebsd_syscall(int num,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
{
print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames), arg1, arg2,
arg3, arg4, arg5, arg6);
print_syscall(num, freebsd_scnames, ARRAY_SIZE(freebsd_scnames),
arg1, arg2, arg3, arg4, arg5, arg6);
}
void print_freebsd_syscall_ret(int num, abi_long ret)
void
print_freebsd_syscall_ret(int num, abi_long ret)
{
print_syscall_ret(num, ret, freebsd_scnames, ARRAY_SIZE(freebsd_scnames));
}
void print_netbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
void
print_netbsd_syscall(int num,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
{
print_syscall(num, netbsd_scnames, ARRAY_SIZE(netbsd_scnames),
arg1, arg2, arg3, arg4, arg5, arg6);
}
void print_netbsd_syscall_ret(int num, abi_long ret)
void
print_netbsd_syscall_ret(int num, abi_long ret)
{
print_syscall_ret(num, ret, netbsd_scnames, ARRAY_SIZE(netbsd_scnames));
}
void print_openbsd_syscall(int num, abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
void
print_openbsd_syscall(int num,
abi_long arg1, abi_long arg2, abi_long arg3,
abi_long arg4, abi_long arg5, abi_long arg6)
{
print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames), arg1, arg2,
arg3, arg4, arg5, arg6);
print_syscall(num, openbsd_scnames, ARRAY_SIZE(openbsd_scnames),
arg1, arg2, arg3, arg4, arg5, arg6);
}
void print_openbsd_syscall_ret(int num, abi_long ret)
void
print_openbsd_syscall_ret(int num, abi_long ret)
{
print_syscall_ret(num, ret, openbsd_scnames, ARRAY_SIZE(openbsd_scnames));
}

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