Compare commits

..

110 Commits

Author SHA1 Message Date
Michael Roth
d1b725ee12 Update version for 2.8.1.1 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-04-20 16:15:12 -05:00
Greg Kurz
96bae145e2 9pfs: local: set the path of the export root to "."
The local backend was recently converted to using "at*()" syscalls in order
to ensure all accesses happen below the shared directory. This requires that
we only pass relative paths, otherwise the dirfd argument to the "at*()"
syscalls is ignored and the path is treated as an absolute path in the host.
This is actually the case for paths in all fids, with the notable exception
of the root fid, whose path is "/". This causes the following backend ops to
act on the "/" directory of the host instead of the virtfs shared directory
when the export root is involved:
- lstat
- chmod
- chown
- utimensat

ie, chmod /9p_mount_point in the guest will be converted to chmod / in the
host for example. This could cause security issues with a privileged QEMU.

All "*at()" syscalls are being passed an open file descriptor. In the case
of the export root, this file descriptor points to the path in the host that
was passed to -fsdev.

The fix is thus as simple as changing the path of the export root fid to be
"." instead of "/".

This is CVE-2017-7471.

Cc: qemu-stable@nongnu.org
Reported-by: Léo Gaspard <leo@gaspard.io>
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 9c6b899f7a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-04-20 15:56:00 -05:00
Michael Roth
7124ccf8b3 Update version for 2.8.1 release
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 23:02:53 -05:00
Sam Bobroff
08c48c731a spapr: fix off-by-one error in spapr_ovec_populate_dt()
The last byte of the option vector was missing due to an off-by-one
error. Without this fix, client architecture support negotiation will
fail because the last byte of option vector 5, which contains the MMU
support, will be missed.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit fe93e3e6ec)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 15:45:06 -05:00
Gerd Hoffmann
12110bf70e seabios: update to 1.10.2 release
git shortlog rel-1.10.1..rel-1.10.2
===================================

Ben Warren (5):
      QEMU DMA: Add DMA write capability
      romfile-loader: Switch to using named structs
      QEMU fw_cfg: Add command to write back address of file
      QEMU fw_cfg: Add functions for accessing files by key
      QEMU fw_cfg: Write fw_cfg back on S3 resume

Kevin O'Connor (1):
      ps2port: Disable keyboard/mouse prior to resetting ps2 controller

Ladi Prosek (1):
      ahci: Set upper 32-bit registers to zero

Paul Menzel (1):
      vgasrc: Increase debug level

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 8779fccbef)
 * required for 98cb5dc: "ahci: advertise HOST_CAP_64"
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 14:53:59 -05:00
Eric Blake
07672ab003 qom: Fix regression with 'qom-type'
Commit 9a6d1ac assumed that 'qom-type' could be removed from QemuOpts
with no ill effects.  However, this command line proves otherwise:

$ ./x86_64-softmmu/qemu-system-x86_64 -nodefaults -nographic -qmp stdio \
  -object rng-random,filename=/dev/urandom,id=rng0 \
  -device virtio-rng-pci,rng=rng0
qemu-system-x86_64: -object rng-random,filename=/dev/urandom,id=rng0: Parameter 'qom-type' is missing

Fix the regression by restoring qom-type in opts after its temporary
removal that was needed for the duration of user_creatable_add_opts().

Reported-by: Richard W. M. Jones <rjones@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Tested-by: Richard W.M. Jones <rjones@redhat.com>
Message-id: 20170323160315.19696-1-eblake@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 0832970119)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:52:04 -05:00
Stefan Weil
877e2b016e target/s390x: Fix broken user mode
Returning NULL from get_max_cpu_model results in a SIGSEGV runtime error.

Signed-off-by: Stefan Weil <sw@weilnetz.de>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-Id: <20170130131517.8092-1-sw@weilnetz.de>
Cc: qemu-stable@nongnu.org
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit a352aa62a7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:47:49 -05:00
Eric Blake
2f8ab9b1dd qapi: Fix QemuOpts visitor regression on unvisited input
An off-by-one in commit 15c2f669e meant that we were failing to
check for unparsed input in all QemuOpts visitors.  Recent testsuite
additions show that fixing the obvious bug with bogus fields will
also fix the case of an incomplete list visit; update the tests to
match the new behavior.

Simple testcase:

./x86_64-softmmu/qemu-system-x86_64 -nodefaults -nographic -qmp stdio -numa node,size=1g

failed to diagnose that 'size' is not a valid argument to -numa, and
now once again reports:

qemu-system-x86_64: -numa node,size=1g: Invalid parameter 'size'

See also https://bugzilla.redhat.com/show_bug.cgi?id=1434666

CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20170322144525.18964-4-eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 21f88d021d)
 Conflicts:
	qapi/opts-visitor.c
	tests/test-opts-visitor.c
 * drop changes related to 9cb8ef36 and a9416dc6 tests
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:35:02 -05:00
Eric Blake
c15c6d2594 qom: Avoid unvisited 'id'/'qom-type' in user_creatable_add_opts
A regression in commit 15c2f669e caused us to silently ignore
excess input to the QemuOpts visitor.  Later, commit ea4641
accidentally abused that situation, by removing "qom-type" and
"id" from the corresponding QDict but leaving them defined in
the QemuOpts, when using the pair of containers to create a
user-defined object. Note that since we are already traversing
two separate items (a QDict and a QemuOpts), we are already
able to flag bogus arguments, as in:

$ ./x86_64-softmmu/qemu-system-x86_64 -nodefaults -nographic -qmp stdio -object memory-backend-ram,id=mem1,size=4k,bogus=huh
qemu-system-x86_64: -object memory-backend-ram,id=mem1,size=4k,bogus=huh: Property '.bogus' not found

So the only real concern is that when we re-enable strict checking
in the QemuOpts visitor, we do not want to start flagging the two
leftover keys as unvisited.  Rearrange the code to clean out the
QemuOpts listing in advance, rather than removing items from the
QDict.  Since "qom-type" is usually an automatic implicit default,
we don't have to restore it (this does mean that once instantiated,
QemuOpts is not necessarily an accurate representation of the
original command line - but this is not the first place to do that);
however "id" has to be put back (requiring us to cast away a const).

[As a side note, hmp_object_add() turns a QDict into a QemuOpts,
then calls user_creatable_add_opts() which converts QemuOpts into
a new QDict. There are probably a lot of wasteful conversions like
this, but cleaning them up is a much bigger task than the immediate
regression fix.]

CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-Id: <20170322144525.18964-3-eblake@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 9a6d1acb3e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
(cherry picked from commit 7967e0bd9d8c4d7aae11383f9d9bad2ceaf9c2a2)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:30:29 -05:00
Igor Mammedov
dd39c544f4 monitor: reuse user_creatable_add_opts() instead of user_creatable_add()
Simplify code by dropping ~57LOC by merging user_creatable_add()
into user_creatable_add_opts() and using the later from monitor.
Along with it allocate opts_visitor_new() once in user_creatable_add_opts().

As result we have one less API func and a more readable/simple
user_creatable_add_opts() vs user_creatable_add().

Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <1484052795-158195-3-git-send-email-imammedo@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit 3a4641054e)
* functional dep for 9a6d1ac
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:30:09 -05:00
Eric Blake
879b6454be tests: Expose regression in QemuOpts visitor
Commit 15c2f669e broke the ability of the QemuOpts visitor to
flag extra input parameters, but the regression went unnoticed
because of missing testsuite coverage.  Add a test to cover this;
take the approach already used in 9cb8ef3 of adding a test that
passes (to avoid breaking bisection) but marks with BUG the
behavior that we don't like, so that the actual impact of the
fix in a later patch is easier to see.

CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Michael Roth <mdroth@linux.vnet.ibm.com>
Message-Id: <20170322144525.18964-2-eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
(cherry picked from commit 76861f6bef)
 Conflicts:
	tests/test-opts-visitor.c
 * drop context dep on 9cb8ef36 and a9416dc6 tests
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-30 12:28:35 -05:00
Paolo Bonzini
ce37df91f4 virtio: always use handle_aio_output if registered
Commit ad07cd6 ("virtio-scsi: always use dataplane path if ioeventfd is
active", 2016-10-30) and 9ffe337 ("virtio-blk: always use dataplane
path if ioeventfd is active", 2016-10-30) broke the virtio 1.0
indirect access registers.

The indirect access registers bypass the ioeventfd, so that virtio-blk
and virtio-scsi now repeatedly try to initialize dataplane instead of
triggering the guest->host EventNotifier.  Detect the situation by
checking vq->handle_aio_output; if it is not NULL, trigger the
EventNotifier, which is how the device expects to get notifications
and in fact the only thread-safe manner to deliver them.

Fixes: ad07cd6
Fixes: 9ffe337
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit e49a661840)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-27 21:07:21 -05:00
Gerd Hoffmann
dc35a13747 cirrus: fix off-by-one in cirrus_bitblt_rop_bkwd_transp_*_16
The switch from pointers to addresses (commit
026aeffcb4 and
ffaf857778) added
a off-by-one bug to 16bit backward blits.  Fix.

Reported-by: 李强 <liqiang6-s@360.cn>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Li Qiang <liqiang6-s@360.cn>
Message-id: 1489735296-19047-1-git-send-email-kraxel@redhat.com
(cherry picked from commit f019722cbb)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:41 -05:00
Gerd Hoffmann
a290442234 cirrus: stop passing around src pointers in the blitter
Does basically the same as "cirrus: stop passing around dst pointers in
the blitter", just for the src pointer instead of the dst pointer.

For the src we have to care about cputovideo blits though and fetch the
data from s->cirrus_bltbuf instead of vga memory.  The cirrus_src*()
helper functions handle that.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1489584487-3489-1-git-send-email-kraxel@redhat.com
(cherry picked from commit ffaf857778)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:35 -05:00
Gerd Hoffmann
031700e452 cirrus: stop passing around dst pointers in the blitter
Instead pass around the address (aka offset into vga memory).  Calculate
the pointer in the rop_* functions, after applying the mask to the
address, to make sure the address stays within the valid range.

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1489574872-8679-1-git-send-email-kraxel@redhat.com
(cherry picked from commit 026aeffcb4)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:29 -05:00
Gerd Hoffmann
2f51fd1f73 cirrus: fix cirrus_invalidate_region
off_cur_end is exclusive, so off_cur_end == cirrus_addr_mask is valid.
Fix calculation to make sure to allow that, otherwise the assert added
by commit f153b563f8 can trigger for valid
blits.

Test case: boot windows nt 4.0

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1489579606-26020-1-git-send-email-kraxel@redhat.com
(cherry picked from commit e048dac616)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:23 -05:00
Gerd Hoffmann
63fdb09491 cirrus/vnc: zap bitblit support from console code.
There is a special code path (dpy_gfx_copy) to allow graphic emulation
notify user interface code about bitblit operations carryed out by
guests.  It is supported by cirrus and vnc server.  The intended purpose
is to optimize display scrolls and just send over the scroll op instead
of a full display update.

This is rarely used these days though because modern guests simply don't
use the cirrus blitter any more.  Any linux guest using the cirrus drm
driver doesn't.  Any windows guest newer than winxp doesn't ship with a
cirrus driver any more and thus uses the cirrus as simple framebuffer.

So this code tends to bitrot and bugs can go unnoticed for a long time.
See for example commit "3e10c3e vnc: fix qemu crash because of SIGSEGV"
which fixes a bug lingering in the code for almost a year, added by
commit "c7628bf vnc: only alloc server surface with clients connected".

Also the vnc server will throttle the frame rate in case it figures the
network can't keep up (send buffers are full).  This doesn't work with
dpy_gfx_copy, for any copy operation sent to the vnc client we have to
send all outstanding updates beforehand, otherwise the vnc client might
run the client side blit on outdated data and thereby corrupt the
display.  So this dpy_gfx_copy "optimization" might even make things
worse on slow network links.

Lets kill it once for all.

Oh, and one more reason: Turns out (after writing the patch) we have a
security bug in that code path ...

Fixes: CVE-2016-9603
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1489494419-14340-1-git-send-email-kraxel@redhat.com
(cherry picked from commit 50628d3479)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:15 -05:00
hangaohuai
3328c14e63 fix :cirrus_vga fix OOB read case qemu Segmentation fault
check the validity of parameters in cirrus_bitblt_rop_fwd_transp_xxx
and cirrus_bitblt_rop_fwd_xxx to avoid the OOB read which causes qemu Segmentation fault.

After the fix, we will touch the assert in
cirrus_invalidate_region:
assert(off_cur_end >= off_cur);

Signed-off-by: fangying <fangying1@huawei.com>
Signed-off-by: hangaohuai <hangaohuai@huawei.com>
Message-id: 20170314063919.16200-1-hangaohuai@huawei.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 215902d7b6)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:03:08 -05:00
Gerd Hoffmann
a99fd943c4 Revert "cirrus: allow zero source pitch in pattern fill rops"
This reverts commit 5858dd1801.

Conflicts:
	hw/display/cirrus_vga.c

Cc: Wolfgang Bumiller <w.bumiller@proxmox.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Message-id: 1486645341-5010-2-git-send-email-kraxel@redhat.com
(cherry picked from commit 12e97ec399)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:02:34 -05:00
Gerd Hoffmann
670ddcc0aa cirrus: fix patterncopy checks
The blit_region_is_unsafe checks don't work correctly for the
patterncopy source.  It's a fixed-sized region, which doesn't
depend on cirrus_blt_{width,height}.  So go do the check in
cirrus_bitblt_common_patterncopy instead, then tell blit_is_unsafe that
it doesn't need to verify the source.  Also handle the case where we
blit from cirrus_bitbuf correctly.

This patch replaces 5858dd1801.

Security impact:  I think for the most part error on the safe side this
time, refusing blits which should have been allowed.

Only exception is placing the blit source at the end of the video ram,
so cirrus_blt_srcaddr + 256 goes beyond the end of video memory.  But
even in that case I'm not fully sure this actually allows read access to
host memory.  To trick the commit 5858dd18 security checks one has to
pick very small cirrus_blt_{width,height} values, which in turn implies
only a fraction of the blit source will actually be used.

Cc: Wolfgang Bumiller <w.bumiller@proxmox.com>
Cc: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Reviewed-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Message-id: 1486645341-5010-1-git-send-email-kraxel@redhat.com
(cherry picked from commit 95280c31cd)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:02:29 -05:00
Gerd Hoffmann
8db38049c6 cirrus: fix blit address mask handling
Apply the cirrus_addr_mask to cirrus_blt_dstaddr and cirrus_blt_srcaddr
right after assigning them, in cirrus_bitblt_start(), instead of having
this all over the place in the cirrus code, and missing a few places.

Reported-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1485338996-17095-1-git-send-email-kraxel@redhat.com
(cherry picked from commit 60cd23e851)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:01:12 -05:00
Wolfgang Bumiller
205a619563 cirrus: allow zero source pitch in pattern fill rops
The rops used by cirrus_bitblt_common_patterncopy only use
the destination pitch, so the source pitch shoul allowed to
be zero and the blit with used for the range check around the
source address.

Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Message-id: 1485272138-23249-1-git-send-email-w.bumiller@proxmox.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 5858dd1801)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:01:05 -05:00
Wolfgang Bumiller
5d26f91c89 cirrus: handle negative pitch in cirrus_invalidate_region()
cirrus_invalidate_region() calls memory_region_set_dirty()
on a per-line basis, always ranging from off_begin to
off_begin+bytesperline. With a negative pitch off_begin
marks the top most used address and thus we need to do an
initial shift backwards by a line for negative pitches of
backward blits, otherwise the first iteration covers the
line going from the start offset forwards instead of
backwards.
Additionally since the start address is inclusive, if we
shift by a full `bytesperline` we move to the first address
*not* included in the blit, so we only shift by one less
than bytesperline.

Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
Message-id: 1485352137-29367-1-git-send-email-w.bumiller@proxmox.com

[ kraxel: codestyle fixes ]

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit f153b563f8)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 15:00:58 -05:00
Greg Kurz
1a184c3af3 9pfs: don't try to flush self and avoid QEMU hang on reset
According to the 9P spec [*], when a client wants to cancel a pending I/O
request identified by a given tag (uint16), it must send a Tflush message
and wait for the server to respond with a Rflush message before reusing this
tag for another I/O. The server may still send a completion message for the
I/O if it wasn't actually cancelled but the Rflush message must arrive after
that.

QEMU hence waits for the flushed PDU to complete before sending the Rflush
message back to the client.

If a client sends 'Tflush tag oldtag' and tag == oldtag, QEMU will then
allocate a PDU identified by tag, find it in the PDU list and wait for
this same PDU to complete... i.e. wait for a completion that will never
happen. This causes a tag and ring slot leak in the guest, and a PDU
leak in QEMU, all of them limited by the maximal number of PDUs (128).
But, worse, this causes QEMU to hang on device reset since v9fs_reset()
wants to drain all pending I/O.

This insane behavior is likely to denote a bug in the client, and it would
deserve an Rerror message to be sent back. Unfortunately, the protocol
allows it and requires all flush requests to suceed (only a Tflush response
is expected).

The only option is to detect when we have to handle a self-referencing
flush request and report success to the client right away.

[*] http://man.cat-v.org/plan_9/5/flush

Reported-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Greg Kurz <groug@kaod.org>
(cherry picked from commit d5f2af7b95)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:57:20 -05:00
Greg Kurz
7f515a96ab 9pfs: fix off-by-one error in PDU free list
The server can handle MAX_REQ - 1 PDUs at a time and the virtio-9p
device has a MAX_REQ sized virtqueue. If the client manages to fill
up the virtqueue, pdu_alloc() will fail and the request won't be
processed without any notice to the client (it actually causes the
linux 9p client to hang).

This has been there since the beginning (commit 9f10751365 "virtio-9p:
Add a virtio 9p device to qemu"), but it needs an agressive workload to
run in the guest to show up.

We actually allocate MAX_REQ PDUs and I see no reason not to link them
all into the free list, so let's fix the init loop.

Reported-by: Tuomas Tynkkynen <tuomas@tuxera.com>
Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Greg Kurz <groug@kaod.org>
(cherry picked from commit 0d78289c3d)

Conflicts:
	hw/9pfs/9p.c

* drop context dep on 583f21f8

Signed-off-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:53:30 -05:00
Richard Henderson
d437262fa8 target-arm: Fix aarch64 vec_reg_offset
Since CPUARMState.vfp.regs is not 16 byte aligned, the ^ 8 fixup used
for a big-endian host doesn't do what's intended.  Fix this by adding
in the vfp.regs offset after computing the inter-register offset.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-id: 1481085020-2614-2-git-send-email-rth@twiddle.net
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 416d72b97b)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:50:26 -05:00
Richard Henderson
74b13f92c2 target-arm: Fix aarch64 disas_ldst_single_struct
We add s->be_data within do_vec_ld/st.  Adding it here means that
we have the wrong bits set in SIZE for a big-endian host, leading
to g_assert_not_reached in write_vec_element and read_vec_element.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-id: 1481085020-2614-3-git-send-email-rth@twiddle.net
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 0a97c40f8e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:50:19 -05:00
Richard Henderson
4bcb497c7e linux-user: Fix s390x safe-syscall for z900
The LT instruction was added in the extended immediate facility
introduced with the z9-109 processor.

Cc: Riku Voipio <riku.voipio@iki.fi>
Reported-by: Michael Tokarev <mjt@tls.msk.ru>
Fixes: c9bc3437a9
Suggested-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Riku Voipio <riku.voipio@linaro.org>
(cherry picked from commit 6cde51769e)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:50:14 -05:00
Vladimir Sementsov-Ogievskiy
8029d55a93 nbd/client: fix drop_sync [CVE-2017-2630]
Comparison symbol is misused. It may lead to memory corruption.
Introduced in commit 7d3123e.

Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20170203154757.36140-6-vsementsov@virtuozzo.com>
[eblake: add CVE details, update conditional]
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-Id: <20170307151627.27212-1-eblake@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

(cherry picked from commit 2563c9c6b8)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-21 14:49:59 -05:00
Peter Lieven
a3aeb9f09d thread-pool: add missing qemu_bh_cancel in completion function
commit 3c80ca15 fixed a deadlock scenarion with nested aio_poll invocations.

However, the rescheduling of the completion BH introcuded unnecessary spinning
in the main-loop. On very fast file backends this can even lead to the
"WARNING: I/O thread spun for 1000 iterations" message popping up.

Callgrind reports about 3-4% less instructions with this patch running
qemu-img bench on a ramdisk based VMDK file.

Fixes: 3c80ca158c
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
(cherry picked from commit b7a745dc33)
* drop context dep on b9e413d
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-20 14:57:35 -05:00
Dong Jia Shi
34e9c09d03 s390x/css: reassign subchannel if schid is changed after migration
The subchannel is a means to access a device. While the device number is
assigned by the administrator, the subchannel number is assigned by
the channel subsystem in an ascending order on cold and hot plug.
When doing unplug and replug operations, the same device may end up on
a different subchannel; for example

- We start with a device fe.1.2222, which ends up at subchannel
  fe.1.0000.
- Now we detach the device, attach a device fe.1.3333 (which would get
  the now-free subchannel fe.1.0000), re-attach fe.1.2222 (which ends
  up at subchannel fe.1.0001) and detach fe.1.3333.
- We now have the same device (fe.1.2222) available to the guest; it
  just shows up on a different subchannel.

In such a case, the subchannel numbers are different from what a
QEMU would create during cold plug when parsing the command line.

As this would cause a guest visible change on migration, we do restore
the source system's value of the subchannel number on load.

So we are now fine from the guest perspective. From the host
perspective this will cause an inconsistent state in our internal data
structures, though.

For example, the subchannel 0 might not be at array position 0. This will
lead to problems when we continue doing hot (un/re) plug operations.

Let's fix this by cleaning up our internal data structures.

Reported-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Dong Jia Shi <bjsdjshi@linux.vnet.ibm.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 3c788ebc6f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-20 14:26:46 -05:00
Jason Wang
9e9483dea9 virtio-pci: reset modern vq meta data
We don't reset proxy->vqs[].{num|desc[]|avail[]|used[]}. This means if
a driver enable the vq without setting vq address after reset. The old
addresses were leaked. Fixing this by resetting modern vq meta data
during device reset.

Cc: qemu-stable@nongnu.org
Signed-off-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit 60a8d80234)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:42 -05:00
Li Qiang
ba9c51d225 scsi: mptsas: fix the wrong reading size in fetch request
When fetching request, it should read sizeof(*hdr), not the
pointer hdr.

Signed-off-by: Li Qiang <liqiang6-s@360.cn>
Message-Id: <1489488980-130668-1-git-send-email-liqiang6-s@360.cn>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit b01a2d07c9)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:42 -05:00
Paolo Bonzini
495756ef9d e1000e: correctly tear down MSI-X memory regions
MSI-X has been disabled by the time the e1000e device is unrealized, hence
msix_uninit is never called.  This causes the object to be leaked, which
shows up as a RAMBlock with empty name when attempting migration.

Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Laurent Vivier <lvivier@redhat.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 7ec7ae4b97)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:42 -05:00
Dmitry Fleytman
9ad26963bf NetRxPkt: Account buffer with ETH header in IOV length
In case of VLAN stripping ETH header is stored in a
separate chunk and length of IOV should take this into
account.

This patch fixes checksum validation for RX packets
with VLAN header.

Devices affected by this problem: e1000e and vmxnet3.

Cc: qemu-stable@nongnu.org
Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit c5d083c561)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:42 -05:00
Dmitry Fleytman
15ad066065 NetRxPkt: Do not try to pull more data than present
In case of VLAN stripping, ETH header put into a
separate buffer, therefore amont of data copied
from original IOV should be smaller.

Cc: qemu-stable@nongnu.org
Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit d5e772146d)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Dmitry Fleytman
7cfd9c114b NetRxPkt: Fix memory corruption on VLAN header stripping
This patch fixed a problem that was introduced in commit eb700029.

When net_rx_pkt_attach_iovec() calls eth_strip_vlan()
this can result in pkt->ehdr_buf being overflowed, because
ehdr_buf is only sizeof(struct eth_header) bytes large
but eth_strip_vlan() can write
sizeof(struct eth_header) + sizeof(struct vlan_header)
bytes into it.

Devices affected by this problem: vmxnet3.

Cc: qemu-stable@nongnu.org
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit df8bf7a7fe)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Dmitry Fleytman
bddf2232fc eth: Extend vlan stripping functions
Make VLAN stripping functions return number of bytes
copied to given Ethernet header buffer.

This information should be used to re-compose
packet IOV after VLAN stripping.

Cc: qemu-stable@nongnu.org
Signed-off-by: Dmitry Fleytman <dmitry@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
(cherry picked from commit 566342c312)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Gerd Hoffmann
fc8e94c3e5 cirrus: add blit_is_unsafe call to cirrus_bitblt_cputovideo (CVE-2017-2620)
CIRRUS_BLTMODE_MEMSYSSRC blits do NOT check blit destination
and blit width, at all.  Oops.  Fix it.

Security impact: high.

The missing blit destination check allows to write to host memory.
Basically same as CVE-2014-8106 for the other blit variants.

Cc: qemu-stable@nongnu.org
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 92f2b88cea)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Eric Blake
5e4641777c hmp: fix block_set_io_throttle
Commit 7a9877a made the 'device' parameter to BlockIOThrottle
optional, favoring 'id' instead.  But it forgot to update the
HMP usage to set has_device, which makes all attempts to change
throttling via HMP fail with "Need exactly one of 'device' and 'id'"

CC: qemu-stable@nongnu.org
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-Id: <20170120230359.4244-1-eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
(cherry picked from commit 3f35c3b166)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Peter Lieven
d5506b3128 qga: ignore EBUSY when freezing a filesystem
the current implementation fails if we try to freeze an
already frozen filesystem. This can happen if a filesystem
is mounted more than once (e.g. with a bind mount).

Suggested-by: Christian Theune <ct@flyingcircus.io>
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
(cherry picked from commit ce2eb6c4a0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Paolo Bonzini
823fb688eb target-i386: correctly propagate retaddr into SVM helpers
Commit 2afbdf8 ("target-i386: exception handling for memory helpers",
2015-09-15) changed tlb_fill's cpu_restore_state+raise_exception_err
to raise_exception_err_ra.  After this change, the cpu_restore_state
and raise_exception_err's cpu_loop_exit are merged into
raise_exception_err_ra's cpu_loop_exit_restore.

This actually fixed some bugs, but when SVM is enabled there is a
second path from raise_exception_err_ra to cpu_loop_exit.  This is
the VMEXIT path, and now cpu_vmexit is called without a
cpu_restore_state before.

The fix is to pass the retaddr to cpu_vmexit (via
cpu_svm_check_intercept_param).  All helpers can now use GETPC() to pass
the correct retaddr, too.

Cc: qemu-stable@nongnu.org
Fixes: 2afbdf8480
Reported-by: Alexander Boettcher <alexander.boettcher@genode-labs.com>
Tested-by: Alexander Boettcher <alexander.boettcher@genode-labs.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 65c9d60a3a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Pavel Dovgalyuk
270a46ea0d apic: reset apic_delivered global variable on machine reset
This patch adds call to apic_reset_irq_delivered when the virtual
machine is reset.

Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Message-Id: <20170131114054.276.62201.stgit@PASHA-ISP>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit f65e821262)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Richard Henderson
f61f76cb3f target/sparc: Restore ldstub of odd asis
Fixes the booting of ss20 roms.

Cc: qemu-stable@nongnu.org
Reported-by: Michael Russo <mike@papersolve.com>
Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Signed-off-by: Richard Henderson <rth@twiddle.net>
(cherry picked from commit 3db010c339)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
QingFeng Hao
8ac427cdd0 block/vmdk: Fix the endian problem of buf_len and lba
The problem was triggered by qemu-iotests case 055. It failed when it
was comparing the compressed vmdk image with original test.img.

The cause is that buf_len in vmdk_write_extent wasn't converted to
little-endian before it was stored to disk. But later vmdk_read_extent
read it and converted it from little-endian to cpu endian.
If the cpu is big-endian like s390, the problem will happen and
the data length read by vmdk_read_extent will become invalid!
The fix is to add the conversion in vmdk_write_extent, meanwhile,
repair the endianness problem of lba field which shall also be converted
to little-endian before storing to disk.

Cc: qemu-stable@nongnu.org
Signed-off-by: QingFeng Hao <haoqf@linux.vnet.ibm.com>
Signed-off-by: Jing Liu <liujbjl@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Reviewed-by: Fam Zheng <famz@redhat.com>
Message-id: 20161216052040.53067-2-haoqf@linux.vnet.ibm.com
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 4545d4f4af)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Sam Bobroff
1d1d9226d8 target-ppc, tcg: fix usermode segfault with pthread_create()
Programs run under qemu-ppc64 on an x86_64 host currently segfault
if they use pthread_create() due to the adjustment made to the NIP in
commit bd6fefe71c.

This patch changes cpu_loop() to set the NIP back to the
pre-incremented value before calling do_syscall(), which causes the
correct address to be used for the new thread and corrects the fault.

Signed-off-by: Sam Bobroff <sam.bobroff@au1.ibm.com>
Reviewed-by: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
(cherry picked from commit 2635531f20)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Michael Tokarev
adf2c47aa2 vnc: do not disconnect on EAGAIN
When qemu vnc server is trying to send large update to clients,
there might be a situation when system responds with something
like EAGAIN, indicating that there's no system memory to send
that much data (depending on the network speed, client and server
and what is happening).  In this case, something like this happens
on qemu side (from strace):

sendmsg(16, {msg_name(0)=NULL,
        msg_iov(1)=[{"\244\"..., 729186}],
        msg_controllen=0, msg_flags=0}, 0) = 103950
sendmsg(16, {msg_name(0)=NULL,
        msg_iov(1)=[{"lz\346"..., 1559618}],
        msg_controllen=0, msg_flags=0}, 0) = -1 EAGAIN
sendmsg(-1, {msg_name(0)=NULL,
        msg_iov(1)=[{"lz\346"..., 1559618}],
        msg_controllen=0, msg_flags=0}, 0) = -1 EBADF

qemu closes the socket before the retry, and obviously it gets EBADF
when trying to send to -1.

This is because there WAS a special handling for EAGAIN, but now it doesn't
work anymore, after commit 04d2529da2, because
now in all error-like cases we initiate vnc disconnect.

This change were introduced in qemu 2.6, and caused numerous grief for many
people, resulting in their vnc clients reporting sporadic random disconnects
from vnc server.

Fix that by doing the disconnect only when necessary, i.e. omitting this
very case of EAGAIN.

Hopefully the existing condition (comparing with QIO_CHANNEL_ERR_BLOCK)
is sufficient, as the original code (before the above commit) were
checking for other errno values too.

Apparently there's another (semi?)bug exist somewhere here, since the
code tries to write to fd# -1, it probably should check if the connection
is open before. But this isn't important.

Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Message-id: 1486115549-9398-1-git-send-email-mjt@msgid.tls.msk.ru
Fixes: 04d2529da2
Cc: Daniel P. Berrange <berrange@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 537848ee62)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:41 -05:00
Prasad J Pandit
1a156ae5d1 sd: sdhci: check data length during dma_memory_read
While doing multi block SDMA transfer in routine
'sdhci_sdma_transfer_multi_blocks', the 's->fifo_buffer' starting
index 'begin' and data length 's->data_count' could end up to be same.
This could lead to an OOB access issue. Correct transfer data length
to avoid it.

Cc: qemu-stable@nongnu.org
Reported-by: Jiang Xin <jiangxin1@huawei.com>
Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 20170130064736.9236-1-ppandit@redhat.com
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 42922105be)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Peter Lieven
3b8f27fe0b block/nfs: fix naming of runtime opts
commit 94d6a7a accidentally left the naming of runtime opts and QAPI
scheme inconsistent. As one consequence passing of parameters in the
URI is broken. Sync the naming of the runtime opts to the QAPI
scheme.

Please note that this is technically backwards incompatible with the 2.8
release, but the 2.8 release is the only version that had the wrong naming.
Furthermore release 2.8 suffered from a NULL pointer dereference during
URI parsing.

Fixes: 94d6a7a76e
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Message-id: 1485942829-10756-3-git-send-email-pl@kamp.de
[mreitz: Fixed commit message]
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Max Reitz <mreitz@redhat.com>

(cherry picked from commit f67409a5bb)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Peter Lieven
44d24c7b4a block/nfs: fix NULL pointer dereference in URI parsing
parse_uint_full wants to put the parsed value into the
variable passed via its second argument which is NULL.

Fixes: 94d6a7a76e
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 1485942829-10756-2-git-send-email-pl@kamp.de
Signed-off-by: Max Reitz <mreitz@redhat.com>
(cherry picked from commit 8d20abe87a)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Christian Borntraeger
5f4b9013e6 s390x/kvm: fix small race reboot vs. cmma
Right now we reset all devices before we reset the cmma states.  This
can result in the host kernel discarding guest pages that were
previously in the unused state but already contain a bios or a -kernel
file before the cmma reset has finished.  This race results in random
guest crashes or hangs during very early reboot.

Fixes: 1cd4e0f6f0 ("s390x/cmma: clean up cmma reset")
Cc: qemu-stable@nongnu.org
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
(cherry picked from commit 1a0e4c8b02)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
David Hildenbrand
5e40f283e5 target/s390x: use "qemu" cpu model in user mode
"any" does not exist, therefore resulting in a misleading error message.

Reported-by: Stefan Weil <sw@weilnetz.de>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20170130145025.26475-1-david@redhat.com>
Reviewed-by: Stefan Weil <sw@weilnetz.de>
Reviewed-by: Alexander Graf <agraf@suse.de>
Cc: qemu-stable@nongnu.org
(cherry picked from commit d8923bc754)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Ladi Prosek
d2b9063eb8 ahci: advertise HOST_CAP_64
The AHCI emulation code supports 64-bit addressing and should advertise this
fact in the Host Capabilities register. Both Linux and Windows drivers test
this bit to decide if the upper 32 bits of various registers may be written
to, and at least some versions of Windows have a bug where DMA is attempted
with an address above 4GB but, in the absence of HOST_CAP_64, the upper 32
bits are left unititialized which leads to a memory corruption.

[Maintainer edit:

This fixes https://bugzilla.redhat.com/show_bug.cgi?id=1411105,
which affects Windows Server 2008 SP2 in some cases.]

Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Message-id: 1484305370-6220-1-git-send-email-lprosek@redhat.com
[Amended commit message --js]
Signed-off-by: John Snow <jsnow@redhat.com>

(cherry picked from commit 98cb5dccb1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Paolo Bonzini
d8dea6fbcb cpu-exec: fix icount out-of-bounds access
When icount is active, tb_add_jump is surprisingly called with an
out of bounds basic block index.  I have no idea how that can work,
but it does not seem like a good idea.  Clear *last_tb for all
TB_EXIT_ICOUNT_EXPIRED cases, even when all you have to do is
refill icount_extra.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 43d70ddf9f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Li Qiang
f054cead44 cirrus: fix oob access issue (CVE-2017-2615)
When doing bitblt copy in backward mode, we should minus the
blt width first just like the adding in the forward mode. This
can avoid the oob access of the front of vga's vram.

Signed-off-by: Li Qiang <liqiang6-s@360.cn>

{ kraxel: with backward blits (negative pitch) addr is the topmost
          address, so check it as-is against vram size ]

Cc: qemu-stable@nongnu.org
Cc: P J P <ppandit@redhat.com>
Cc: Laszlo Ersek <lersek@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Wolfgang Bumiller <w.bumiller@proxmox.com>
Fixes: d3532a0db0 (CVE-2014-8106)
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Message-id: 1485938101-26602-1-git-send-email-kraxel@redhat.com
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
(cherry picked from commit 62d4c6bd52)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Christian Borntraeger
5fb07a7b6c s390x/kvm: fix cmma reset for KVM
We must reset the CMMA states for normal memory (when not on mem path),
but the current code does the opposite. This was unnoticed for some time
as the kernel since 4.6 also had a bug which mostly disabled the paging
optimizations.

Fixes: 07059effd1 ("s390x/kvm: let the CPU model control CMM(A)")
Cc: qemu-stable@nongnu.org # v2.8
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 0cf4d747cb)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Peter Lieven
3fb4b3c371 block/iscsi: avoid data corruption with cache=writeback
nb_cls_shrunk in iscsi_allocmap_update can become -1 if the
request starts and ends within the same cluster. This results
in passing -1 to bitmap_set and bitmap_clear and they don't
handle negative values properly. In the end this leads to data
corruption.

Fixes: e1123a3b40
Cc: qemu-stable@nongnu.org
Signed-off-by: Peter Lieven <pl@kamp.de>
Message-Id: <1484579832-18589-1-git-send-email-pl@kamp.de>
Reviewed-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 1da45e0c4c)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Michael S. Tsirkin
a626117f6a virtio: fix up max size checks
Coverity reports that ARRAY_SIZE(elem->out_sg) (and all the others too)
is wrong because elem->out_sg is a pointer.

However, the check is not in the right place and the max_size argument
of virtqueue_map_iovec can be removed.  The check on in_num/out_num
should be moved to qemu_get_virtqueue_element instead, before the call
to virtqueue_alloc_element.

Cc: qemu-stable@nongnu.org
Reported-by: Paolo Bonzini <pbonzini@redhat.com>
Fixes: 3724650db0 ("virtio: introduce virtqueue_alloc_element")
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
(cherry picked from commit 6bdc21c050)
* dropped context dep on 8607f5c30
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Daniel P. Berrange
3b33cba69c ui: use evdev keymap when running under wayland
Wayland always uses evdev as its input source, so QEMU
can use the existing evdev keymap data

Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Tested-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 20161201094117.16407-1-berrange@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit a8ffb372a2)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:40 -05:00
Richard Henderson
50b468d421 tcg/aarch64: Fix tcg_out_movi
There were some patterns, like 0x0000_ffff_ffff_00ff, for which we
would select to begin a multi-insn sequence with MOVN, but would
fail to set the 0x0000 lane back from 0xffff.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-Id: <20161207180727.6286-3-rth@twiddle.net>
(cherry picked from commit 8cf9a3d3f7)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Richard Henderson
028fbea477 tcg/aarch64: Fix addsub2 for 0+C
When al == xzr, we cannot use addi/subi because that encodes xsp.
Force a zero into the temp register for that (rare) case.

Signed-off-by: Richard Henderson <rth@twiddle.net>
Message-Id: <20161207180727.6286-2-rth@twiddle.net>
(cherry picked from commit b1eb20da62)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Marc-André Lureau
6e8052f967 char: fix ctrl-a b not working
CharDriverState.be should be updated to point to the current
associated backend.

Fix the regression introduced in the "mux" chardev from commit
a4afa548fc.

https://bugs.launchpad.net/bugs/1654137

Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-Id: <20170110110621.15287-1-marcandre.lureau@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit fb5e19d2e1)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Peter Xu
5c60c6ef61 x86: ioapic: fix fail migration when irqchip=split
Split irqchip works based on the fact that we kept the first 24 gsi
routing entries inside KVM for userspace ioapic's use. When system
boot, we'll reserve these MSI routing entries before hand. However,
after migration, we forgot to re-configure it up in the destination
side. The result is, we'll get invalid gsi routing entries after
migration (all empty), and we get interrupts with vector=0, then
strange things happen, like keyboard hang.

The solution is simple - we update them after migration, which is a
one line fix.

Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1483952153-7221-4-git-send-email-peterx@redhat.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 0f254b1ae0)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Bruce Rogers
2ab8276a1c display: cirrus: ignore source pitch value as needed in blit_is_unsafe
Commit 4299b90 added a check which is too broad, given that the source
pitch value is not required to be initialized for solid fill operations.
This patch refines the blit_is_unsafe() check to ignore source pitch in
that case. After applying the above commit as a security patch, we
noticed the SLES 11 SP4 guest gui failed to initialize properly.

Signed-off-by: Bruce Rogers <brogers@suse.com>
Message-id: 20170109203520.5619-1-brogers@suse.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 913a87885f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Roman Kapl
662a97d74f exec: Add missing rcu_read_unlock
rcu_read_unlock was not called if the address_space_access_valid result is
negative.

This caused (at least) a problem when qemu on PPC/E500+TAP failed to terminate
properly and instead got stuck in a deadlock.

Signed-off-by: Roman Kapl <rka@sysgo.com>
Message-Id: <20170109110921.4931-1-rka@sysgo.com>
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 5ad4a2b75f)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Gonglei
d6f119475d virtio-crypto: fix possible integer and heap overflow
Because the 'size_t' type is 4 bytes in 32-bit platform, which
is the same with 'int'. It's easy to make 'max_len' to zero when
integer overflow and then cause heap overflow if 'max_len' is zero.

Using uint_64 instead of size_t to avoid the integer overflow.

Cc: qemu-stable@nongnu.org
Reported-by: Li Qiang <liqiang6-s@360.cn>
Signed-off-by: Gonglei <arei.gonglei@huawei.com>
Tested-by: Li Qiang <liqiang6-s@360.cn>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit a08aaff811)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Caoxinhua
f47bf0823b qemu-thread: fix qemu_thread_set_name() race in qemu_thread_create()
QEMU will crash with the follow backtrace if the new created thread exited before
we call qemu_thread_set_name() for it.

  (gdb) bt
  #0 0x00007f9a68b095d7 in __GI_raise (sig=sig@entry=6) at ../nptl/sysdeps/unix/sysv/linux/raise.c:56
  #1 0x00007f9a68b0acc8 in __GI_abort () at abort.c:90
  #2 0x00007f9a69cda389 in PAT_abort () from /usr/lib64/libuvpuserhotfix.so
  #3 0x00007f9a69cdda0d in patchIllInsHandler () from /usr/lib64/libuvpuserhotfix.so
  #4 <signal handler called>
  #5 pthread_setname_np (th=140298470549248, name=name@entry=0x8cc74a "io-task-worker") at ../nptl/sysdeps/unix/sysv/linux/pthread_setname.c:49
  #6 0x00000000007f5f20 in qemu_thread_set_name (thread=thread@entry=0x7ffd2ac09680, name=name@entry=0x8cc74a "io-task-worker") at util/qemu_thread_posix.c:459
  #7 0x00000000007f679e in qemu_thread_create (thread=thread@entry=0x7ffd2ac09680, name=name@entry=0x8cc74a "io-task-worker",start_routine=start_routine@entry=0x7c1300 <qio_task_thread_worker>, arg=arg@entry=0x7f99b8001720, mode=mode@entry=1) at util/qemu_thread_posix.c:498
  #8 0x00000000007c15b6 in qio_task_run_in_thread (task=task@entry=0x7f99b80033d0, worker=worker@entry=0x7bd920 <qio_channel_socket_connect_worker>, opaque=0x7f99b8003370, destroy=0x7c6220 <qapi_free_SocketAddress>) at io/task.c:133
  #9 0x00000000007bda04 in qio_channel_socket_connect_async (ioc=0x7f99b80014c0, addr=0x37235d0, callback=callback@entry=0x54ad00 <qemu_chr_socket_connected>, opaque=opaque@entry=0x38118b0, destroy=destroy@entry=0x0) at io/channel_socket.c:191
  #10 0x00000000005487f6 in socket_reconnect_timeout (opaque=0x38118b0) at qemu_char.c:4402
  #11 0x00007f9a6a1533b3 in g_timeout_dispatch () from /usr/lib64/libglib-2.0.so.0
  #12 0x00007f9a6a15299a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0
  #13 0x0000000000747386 in glib_pollfds_poll () at main_loop.c:227
  #14 0x0000000000747424 in os_host_main_loop_wait (timeout=404000000) at main_loop.c:272
  #15 0x0000000000747575 in main_loop_wait (nonblocking=nonblocking@entry=0) at main_loop.c:520
  #16 0x0000000000557d31 in main_loop () at vl.c:2170
  #17 0x000000000041c8b7 in main (argc=<optimized out>, argv=<optimized out>, envp=<optimized out>) at vl.c:5083

Let's detach the new thread after calling qemu_thread_set_name().

Signed-off-by: Caoxinhua <caoxinhua@huawei.com>
Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Message-Id: <1483493521-9604-1-git-send-email-zhang.zhanghailiang@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 2f75bd73c3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Thomas Huth
8a6562592f ui/vnc: Fix problem with sending too many bytes as server name
If the buffer is not big enough, snprintf() does not return the number
of bytes that have been written to the buffer, but the number of bytes
that would be needed for writing the whole string. By using this value
for the following vnc_write() calls, we send some junk at the end of
the name in case the qemu_name is longer than 1017 bytes, which could
confuse the VNC clients. Fix this by adding an additional size check
here.

Buglink: https://bugs.launchpad.net/qemu/+bug/1637447
Signed-off-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 1479749115-21932-1-git-send-email-thuth@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 97efe4f961)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Paolo Bonzini
9f6cb916f2 scsi-block: fix direction of BYTCHK test for VERIFY commands
The direction is wrong; scsi_block_is_passthrough returns
false for commands that *can* use sglists.

Reported-by: Zhang Qian <zhangqian@sangfor.com.cn>
Fixes: 8fdc7839e4
Cc: qemu-stable@nongnu.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 1f8af0d186)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Hervé Poussineau
dc659e3aea ui/gtk: fix crash at startup when no console is available
This patch fixes a segfault at QEMU startup, introduced in a08156321a.
gd_vc_find_current() return NULL, which is dereferenced without checking it.

While at it, disable the whole 'View' menu if no console exists.

Reproducer: qemu-system-i386 -M none -nodefaults

Signed-off-by: Hervé Poussineau <hpoussin@reactos.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-id: 1483263585-8101-1-git-send-email-hpoussin@reactos.org
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
(cherry picked from commit 3d4da9d6f3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Igor Mammedov
87ede19db3 pc: fix crash in rtc_set_memory() if initial cpu is marked as hotplugged
'hotplugged' propperty is meant to be used on migration side when migrating
source with hotplugged devices.
However though it not exacly correct usage of 'hotplugged' property
it's possible to set generic hotplugged property for CPU using
 -cpu foo,hotplugged=on
or
 -global foo.hotplugged=on

in this case qemu crashes with following backtrace:

...

because pc_cpu_plug() assumes that hotplugged CPU could appear only after
rtc/fw_cfg are initialized.
Fix crash by replacing assumption with explicit checks of rtc/fw_cfg
and updating them only if they were initialized.

Cc: qemu-stable@nongnu.org
Reported-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <1483108391-199542-1-git-send-email-imammedo@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
(cherry picked from commit 26ef65beab)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Greg Kurz
da95bfe06b 9pfs: fix crash when fsdev is missing
If the user passes -device virtio-9p without the corresponding -fsdev, QEMU
dereferences a NULL pointer and crashes.

This is a 2.8 regression introduced by commit 702dbcc274.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Li Qiang <liq3ea@gmail.com>
(cherry picked from commit f2b58c4375)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:39 -05:00
Halil Pasic
7830be742a virtio: fix vq->inuse recalc after migr
Correct recalculation of vq->inuse after migration for the corner case
where the avail_idx has already wrapped but used_idx not yet.

Also change the type of the VirtQueue.inuse to unsigned int. This is
done to be consistent with other members representing sizes (VRing.num),
and because C99 guarantees max ring size < UINT_MAX but does not
guarantee max ring size < INT_MAX.

Signed-off-by: Halil Pasic <pasic@linux.vnet.ibm.com>
Fixes: bccdef6b ("virtio: recalculate vq->inuse after migration")
CC: qemu-stable@nongnu.org
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit e66bcc4081)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:38 -05:00
Michael S. Tsirkin
620a65dc44 pci: fix error message for express slots
PCI Express downstream slot has a single PCI slot
behind it, using PCI_DEVFN(PCI_SLOT(devfn), 0)
does not give you function 0 in cases such as ARI
as well as some error cases.

This is exactly what we are hitting:
   $ qemu-system-x86_64 -machine q35 -readconfig docs/q35-chipset.cfg
-monitor stdio
   (qemu) device_add e1000e,bus=ich9-pcie-port-4,addr=00
   (qemu) device_add e1000e,bus=ich9-pcie-port-4,addr=08
   Segmentation fault (core dumped)

The fix is to use the pci_get_function_0 API.

Cc: qemu-stable@nongnu.org
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reported-by: Eduardo Habkost <ehabkost@redhat.com>
Tested-by: Cao jin <caoj.fnst@cn.fujitsu.com>
Tested-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit d93ddfb1f8)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:38 -05:00
Dr. David Alan Gilbert
9d14f0cd65 balloon: Don't balloon roms
A broken guest can specify physical addresses that correspond
to any memory region, but it shouldn't be able to change ROM.

Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Cc: qemu-stable@nongnu.org
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
(cherry picked from commit f2fd57db36)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:38 -05:00
Eduardo Habkost
04cde530be machine: Convert abstract typename on compat_props to subclass names
Original problem description by Greg Kurz:

> Since commit "9a4c0e220d8a hw/virtio-pci: fix virtio
> behaviour", passing -device virtio-blk-pci.disable-modern=off
> has no effect on 2.6 machine types because the internal
> virtio-pci.disable-modern=on compat property always prevail.

The same bug also affects other abstract type names mentioned on
compat_props by machine-types: apic-common, i386-cpu, pci-device,
powerpc64-cpu, s390-skeys, spapr-pci-host-bridge, usb-device,
virtio-pci, x86_64-cpu.

The right fix for this problem is to make sure compat_props and
-global options are always applied in the order they are
registered, instead of reordering them based on the type
hierarchy. But changing the ordering rules of -global is risky
and might break existing configurations, so we shouldn't do that
on a stable branch.

This is a temporary hack that will work around the bug when
registering compat_props properties: if we find an abstract class
on compat_props, register properties for all its non-abstract
subtypes instead. This will make sure -global won't be overridden
by compat_props, while keeping the existing ordering rules on
-global options.

Note that there's one case that won't be fixed by this hack:
"-global spapr-pci-vfio-host-bridge.<option>=<value>" won't be
able to override compat_props, because spapr-pci-host-bridge is
not an abstract class.

Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <1481575745-26120-1-git-send-email-ehabkost@redhat.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.vnet.ibm.com>
Reviewed-by: Greg Kurz <groug@kaod.org>
Tested-by: Greg Kurz <groug@kaod.org>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
(cherry picked from commit 0bcba41fe3)
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:10:38 -05:00
Greg Kurz
a15785cfbd 9pfs: fix vulnerability in openat_dir() and local_unlinkat_common()
We should pass O_NOFOLLOW otherwise openat() will follow symlinks and make
QEMU vulnerable.

While here, we also fix local_unlinkat_common() to use openat_dir() for
the same reasons (it was a leftover in the original patchset actually).

This fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit b003fc0d8a)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:57 -05:00
Greg Kurz
3731a25a62 9pfs: fix O_PATH build break with older glibc versions
When O_PATH is used with O_DIRECTORY, it only acts as an optimization: the
openat() syscall simply finds the name in the VFS, and doesn't trigger the
underlying filesystem.

On systems that don't define O_PATH, because they have glibc version 2.13
or older for example, we can safely omit it. We don't want to deactivate
O_PATH globally though, in case it is used without O_DIRECTORY. The is done
with a dedicated macro.

Systems without O_PATH may thus fail to resolve names that involve
unreadable directories, compared to newer systems succeeding, but such
corner case failure is our only option on those older systems to avoid
the security hole of chasing symlinks inappropriately.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
(added last paragraph to changelog as suggested by Eric Blake)
Signed-off-by: Greg Kurz <groug@kaod.org>

(cherry picked from commit 918112c02a)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:53 -05:00
Greg Kurz
7e9a1c4914 9pfs: don't use AT_EMPTY_PATH in local_set_cred_passthrough()
The name argument can never be an empty string, and dirfd always point to
the containing directory of the file name. AT_EMPTY_PATH is hence useless
here. Also it breaks build with glibc version 2.13 and older.

It is actually an oversight of a previous tentative patch to implement this
function. We can safely drop it.

Reported-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Signed-off-by: Greg Kurz <groug@kaod.org>
Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit b314f6a077)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:50 -05:00
Greg Kurz
059f751ec2 9pfs: fail local_statfs() earlier
If we cannot open the given path, we can return right away instead of
passing -1 to fstatfs() and close(). This will make Coverity happy.

(Coverity issue CID1371729)

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Daniel P. berrange <berrange@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
(cherry picked from commit 23da0145cc)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:47 -05:00
Greg Kurz
bb07a379b5 9pfs: fix fd leak in local_opendir()
Coverity issue CID1371731

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
(cherry picked from commit faab207f11)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:44 -05:00
Greg Kurz
719e6dd171 9pfs: fix bogus fd check in local_remove()
This was spotted by Coverity as a fd leak. This is certainly true, but also
local_remove() would always return without doing anything, unless the fd is
zero, which is very unlikely.

(Coverity issue CID1371732)

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Eric Blake <eblake@redhat.com>
(cherry picked from commit b7361d46e7)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:41 -05:00
Greg Kurz
05a92c2005 9pfs: local: drop unused code
Now that the all callbacks have been converted to use "at" syscalls, we
can drop this code.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit c23d5f1d5b)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:33 -05:00
Greg Kurz
9c5cb58970 9pfs: local: open2: don't follow symlinks
The local_open2() callback is vulnerable to symlink attacks because it
calls:

(1) open() which follows symbolic links for all path elements but the
    rightmost one
(2) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(3) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one
(4) local_post_create_passthrough() which calls in turn lchown() and
    chmod(), both functions also following symbolic links

This patch converts local_open2() to rely on opendir_nofollow() and
mkdirat() to fix (1), as well as local_set_xattrat(),
local_set_mapped_file_attrat() and local_set_cred_passthrough() to
fix (2), (3) and (4) respectively. Since local_open2() already opens
a descriptor to the target file, local_set_cred_passthrough() is
modified to reuse it instead of opening a new one.

The mapped and mapped-file security modes are supposed to be identical,
except for the place where credentials and file modes are stored. While
here, we also make that explicit by sharing the call to openat().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit a565fea565)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:24 -05:00
Greg Kurz
c8c9aab173 9pfs: local: mkdir: don't follow symlinks
The local_mkdir() callback is vulnerable to symlink attacks because it
calls:

(1) mkdir() which follows symbolic links for all path elements but the
    rightmost one
(2) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(3) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one
(4) local_post_create_passthrough() which calls in turn lchown() and
    chmod(), both functions also following symbolic links

This patch converts local_mkdir() to rely on opendir_nofollow() and
mkdirat() to fix (1), as well as local_set_xattrat(),
local_set_mapped_file_attrat() and local_set_cred_passthrough() to
fix (2), (3) and (4) respectively.

The mapped and mapped-file security modes are supposed to be identical,
except for the place where credentials and file modes are stored. While
here, we also make that explicit by sharing the call to mkdirat().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 3f3a16990b)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:21 -05:00
Greg Kurz
5b24a96cd2 9pfs: local: mknod: don't follow symlinks
The local_mknod() callback is vulnerable to symlink attacks because it
calls:

(1) mknod() which follows symbolic links for all path elements but the
    rightmost one
(2) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(3) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one
(4) local_post_create_passthrough() which calls in turn lchown() and
    chmod(), both functions also following symbolic links

This patch converts local_mknod() to rely on opendir_nofollow() and
mknodat() to fix (1), as well as local_set_xattrat() and
local_set_mapped_file_attrat() to fix (2) and (3) respectively.

A new local_set_cred_passthrough() helper based on fchownat() and
fchmodat_nofollow() is introduced as a replacement to
local_post_create_passthrough() to fix (4).

The mapped and mapped-file security modes are supposed to be identical,
except for the place where credentials and file modes are stored. While
here, we also make that explicit by sharing the call to mknodat().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit d815e72190)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:18 -05:00
Greg Kurz
9f4ba82b06 9pfs: local: symlink: don't follow symlinks
The local_symlink() callback is vulnerable to symlink attacks because it
calls:

(1) symlink() which follows symbolic links for all path elements but the
    rightmost one
(2) open(O_NOFOLLOW) which follows symbolic links for all path elements but
    the rightmost one
(3) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(4) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one

This patch converts local_symlink() to rely on opendir_nofollow() and
symlinkat() to fix (1), openat(O_NOFOLLOW) to fix (2), as well as
local_set_xattrat() and local_set_mapped_file_attrat() to fix (3) and
(4) respectively.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 38771613ea)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:15 -05:00
Greg Kurz
62d1dbbfce 9pfs: local: chown: don't follow symlinks
The local_chown() callback is vulnerable to symlink attacks because it
calls:

(1) lchown() which follows symbolic links for all path elements but the
    rightmost one
(2) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(3) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one

This patch converts local_chown() to rely on open_nofollow() and
fchownat() to fix (1), as well as local_set_xattrat() and
local_set_mapped_file_attrat() to fix (2) and (3) respectively.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit d369f20763)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:11 -05:00
Greg Kurz
ea9e59bdf6 9pfs: local: chmod: don't follow symlinks
The local_chmod() callback is vulnerable to symlink attacks because it
calls:

(1) chmod() which follows symbolic links for all path elements
(2) local_set_xattr()->setxattr() which follows symbolic links for all
    path elements
(3) local_set_mapped_file_attr() which calls in turn local_fopen() and
    mkdir(), both functions following symbolic links for all path
    elements but the rightmost one

We would need fchmodat() to implement AT_SYMLINK_NOFOLLOW to fix (1). This
isn't the case on linux unfortunately: the kernel doesn't even have a flags
argument to the syscall :-\ It is impossible to fix it in userspace in
a race-free manner. This patch hence converts local_chmod() to rely on
open_nofollow() and fchmod(). This fixes the vulnerability but introduces
a limitation: the target file must readable and/or writable for the call
to openat() to succeed.

It introduces a local_set_xattrat() replacement to local_set_xattr()
based on fsetxattrat() to fix (2), and a local_set_mapped_file_attrat()
replacement to local_set_mapped_file_attr() based on local_fopenat()
and mkdirat() to fix (3). No effort is made to factor out code because
both local_set_xattr() and local_set_mapped_file_attr() will be dropped
when all users have been converted to use the "at" versions.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit e3187a45dd)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:06 -05:00
Greg Kurz
e314b1b1fb 9pfs: local: link: don't follow symlinks
The local_link() callback is vulnerable to symlink attacks because it calls:

(1) link() which follows symbolic links for all path elements but the
    rightmost one
(2) local_create_mapped_attr_dir()->mkdir() which follows symbolic links
    for all path elements but the rightmost one

This patch converts local_link() to rely on opendir_nofollow() and linkat()
to fix (1), mkdirat() to fix (2).

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit ad0b46e6ac)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:08:02 -05:00
Greg Kurz
d7322e13c6 9pfs: local: improve error handling in link op
When using the mapped-file security model, we also have to create a link
for the metadata file if it exists. In case of failure, we should rollback.

That's what this patch does.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 6dd4b1f1d0)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:59 -05:00
Greg Kurz
d93d06a2fc 9pfs: local: rename: use renameat
The local_rename() callback is vulnerable to symlink attacks because it
uses rename() which follows symbolic links in all path elements but the
rightmost one.

This patch simply transforms local_rename() into a wrapper around
local_renameat() which is symlink-attack safe.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit d2767edec5)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:56 -05:00
Greg Kurz
0f3490faa8 9pfs: local: renameat: don't follow symlinks
The local_renameat() callback is currently a wrapper around local_rename()
which is vulnerable to symlink attacks.

This patch rewrites local_renameat() to have its own implementation, based
on local_opendir_nofollow() and renameat().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 99f2cf4b2d)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:51 -05:00
Greg Kurz
cfe40e1485 9pfs: local: lstat: don't follow symlinks
The local_lstat() callback is vulnerable to symlink attacks because it
calls:

(1) lstat() which follows symbolic links in all path elements but the
    rightmost one
(2) getxattr() which follows symbolic links in all path elements
(3) local_mapped_file_attr()->local_fopen()->openat(O_NOFOLLOW) which
    follows symbolic links in all path elements but the rightmost
    one

This patch converts local_lstat() to rely on opendir_nofollow() and
fstatat(AT_SYMLINK_NOFOLLOW) to fix (1), fgetxattrat_nofollow() to
fix (2).

A new local_fopenat() helper is introduced as a replacement to
local_fopen() to fix (3). No effort is made to factor out code
because local_fopen() will be dropped when all users have been
converted to call local_fopenat().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit f9aef99b3e)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:48 -05:00
Greg Kurz
3439290f9e 9pfs: local: readlink: don't follow symlinks
The local_readlink() callback is vulnerable to symlink attacks because it
calls:

(1) open(O_NOFOLLOW) which follows symbolic links for all path elements but
    the rightmost one
(2) readlink() which follows symbolic links for all path elements but the
    rightmost one

This patch converts local_readlink() to rely on open_nofollow() to fix (1)
and opendir_nofollow(), readlinkat() to fix (2).

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit bec1e9546e)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:44 -05:00
Greg Kurz
ec10eada04 9pfs: local: truncate: don't follow symlinks
The local_truncate() callback is vulnerable to symlink attacks because
it calls truncate() which follows symbolic links in all path elements.

This patch converts local_truncate() to rely on open_nofollow() and
ftruncate() instead.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit ac125d993b)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:41 -05:00
Greg Kurz
d3c54bf9e7 9pfs: local: statfs: don't follow symlinks
The local_statfs() callback is vulnerable to symlink attacks because it
calls statfs() which follows symbolic links in all path elements.

This patch converts local_statfs() to rely on open_nofollow() and fstatfs()
instead.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 31e51d1c15)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:37 -05:00
Greg Kurz
91225c670a 9pfs: local: utimensat: don't follow symlinks
The local_utimensat() callback is vulnerable to symlink attacks because it
calls qemu_utimens()->utimensat(AT_SYMLINK_NOFOLLOW) which follows symbolic
links in all path elements but the rightmost one or qemu_utimens()->utimes()
which follows symbolic links for all path elements.

This patch converts local_utimensat() to rely on opendir_nofollow() and
utimensat(AT_SYMLINK_NOFOLLOW) directly instead of using qemu_utimens().
It is hence assumed that the OS supports utimensat(), i.e. has glibc 2.6
or higher and linux 2.6.22 or higher, which seems reasonable nowadays.

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit a33eda0dd9)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:34 -05:00
Greg Kurz
4286f58bfc 9pfs: local: remove: don't follow symlinks
The local_remove() callback is vulnerable to symlink attacks because it
calls:

(1) lstat() which follows symbolic links in all path elements but the
    rightmost one
(2) remove() which follows symbolic links in all path elements but the
    rightmost one

This patch converts local_remove() to rely on opendir_nofollow(),
fstatat(AT_SYMLINK_NOFOLLOW) to fix (1) and unlinkat() to fix (2).

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit a0e640a872)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:31 -05:00
Greg Kurz
0bb99557e1 9pfs: local: unlinkat: don't follow symlinks
The local_unlinkat() callback is vulnerable to symlink attacks because it
calls remove() which follows symbolic links in all path elements but the
rightmost one.

This patch converts local_unlinkat() to rely on opendir_nofollow() and
unlinkat() instead.

Most of the code is moved to a separate local_unlinkat_common() helper
which will be reused in a subsequent patch to fix the same issue in
local_remove().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit df4938a665)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:27 -05:00
Greg Kurz
a9f46b8b65 9pfs: local: lremovexattr: don't follow symlinks
The local_lremovexattr() callback is vulnerable to symlink attacks because
it calls lremovexattr() which follows symbolic links in all path elements
but the rightmost one.

This patch introduces a helper to emulate the non-existing fremovexattrat()
function: it is implemented with /proc/self/fd which provides a trusted
path that can be safely passed to lremovexattr().

local_lremovexattr() is converted to use this helper and opendir_nofollow().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 72f0d0bf51)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:25 -05:00
Greg Kurz
ed6083afc2 9pfs: local: lsetxattr: don't follow symlinks
The local_lsetxattr() callback is vulnerable to symlink attacks because
it calls lsetxattr() which follows symbolic links in all path elements but
the rightmost one.

This patch introduces a helper to emulate the non-existing fsetxattrat()
function: it is implemented with /proc/self/fd which provides a trusted
path that can be safely passed to lsetxattr().

local_lsetxattr() is converted to use this helper and opendir_nofollow().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 3e36aba757)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:22 -05:00
Greg Kurz
d10142c11b 9pfs: local: llistxattr: don't follow symlinks
The local_llistxattr() callback is vulnerable to symlink attacks because
it calls llistxattr() which follows symbolic links in all path elements but
the rightmost one.

This patch introduces a helper to emulate the non-existing flistxattrat()
function: it is implemented with /proc/self/fd which provides a trusted
path that can be safely passed to llistxattr().

local_llistxattr() is converted to use this helper and opendir_nofollow().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 5507904e36)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:19 -05:00
Greg Kurz
6c1e3a16bc 9pfs: local: lgetxattr: don't follow symlinks
The local_lgetxattr() callback is vulnerable to symlink attacks because
it calls lgetxattr() which follows symbolic links in all path elements but
the rightmost one.

This patch introduces a helper to emulate the non-existing fgetxattrat()
function: it is implemented with /proc/self/fd which provides a trusted
path that can be safely passed to lgetxattr().

local_lgetxattr() is converted to use this helper and opendir_nofollow().

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 56ad3e54da)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:16 -05:00
Greg Kurz
acf22d2264 9pfs: local: open/opendir: don't follow symlinks
The local_open() and local_opendir() callbacks are vulnerable to symlink
attacks because they call:

(1) open(O_NOFOLLOW) which follows symbolic links in all path elements but
    the rightmost one
(2) opendir() which follows symbolic links in all path elements

This patch converts both callbacks to use new helpers based on
openat_nofollow() to only open files and directories if they are
below the virtfs shared folder

This partly fixes CVE-2016-9602.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 996a0d76d7)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:10 -05:00
Greg Kurz
54f951d634 9pfs: local: keep a file descriptor on the shared folder
This patch opens the shared folder and caches the file descriptor, so that
it can be used to do symlink-safe path walk.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 0e35a37829)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:07:03 -05:00
Greg Kurz
984bd0a1b8 9pfs: introduce relative_openat_nofollow() helper
When using the passthrough security mode, symbolic links created by the
guest are actual symbolic links on the host file system.

Since the resolution of symbolic links during path walk is supposed to
occur on the client side. The server should hence never receive any path
pointing to an actual symbolic link. This isn't guaranteed by the protocol
though, and malicious code in the guest can trick the server to issue
various syscalls on paths whose one or more elements are symbolic links.
In the case of the "local" backend using the "passthrough" or "none"
security modes, the guest can directly create symbolic links to arbitrary
locations on the host (as per spec). The "mapped-xattr" and "mapped-file"
security modes are also affected to a lesser extent as they require some
help from an external entity to create actual symbolic links on the host,
i.e. another guest using "passthrough" mode for example.

The current code hence relies on O_NOFOLLOW and "l*()" variants of system
calls. Unfortunately, this only applies to the rightmost path component.
A guest could maliciously replace any component in a trusted path with a
symbolic link. This could allow any guest to escape a virtfs shared folder.

This patch introduces a variant of the openat() syscall that successively
opens each path element with O_NOFOLLOW. When passing a file descriptor
pointing to a trusted directory, one is guaranteed to be returned a
file descriptor pointing to a path which is beneath the trusted directory.
This will be used by subsequent patches to implement symlink-safe path walk
for any access to the backend.

Symbolic links aren't the only threats actually: a malicious guest could
change a path element to point to other types of file with undesirable
effects:
- a named pipe or any other thing that would cause openat() to block
- a terminal device which would become QEMU's controlling terminal

These issues can be addressed with O_NONBLOCK and O_NOCTTY.

Two helpers are introduced: one to open intermediate path elements and one
to open the rightmost path element.

Suggested-by: Jann Horn <jannh@google.com>
Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(renamed openat_nofollow() to relative_openat_nofollow(),
 assert path is relative and doesn't contain '//',
 fixed side-effect in assert, Greg Kurz)
Signed-off-by: Greg Kurz <groug@kaod.org>

(cherry picked from commit 6482a96163)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:06:56 -05:00
Greg Kurz
52d43ff72e 9pfs: remove side-effects in local_open() and local_opendir()
If these functions fail, they should not change *fs. Let's use local
variables to fix this.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 21328e1e57)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:06:52 -05:00
Greg Kurz
e103f9e7b4 9pfs: remove side-effects in local_init()
If this function fails, it should not modify *ctx.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 00c90bd1c2)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:06:49 -05:00
Greg Kurz
2c4f0f6c11 9pfs: local: move xattr security ops to 9p-xattr.c
These functions are always called indirectly. It really doesn't make sense
for them to sit in a header file.

Signed-off-by: Greg Kurz <groug@kaod.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
(cherry picked from commit 56fc494bdc)
Signed-off-by: Greg Kurz <gkurz@linux.vnet.ibm.com>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
2017-03-16 12:06:43 -05:00
1689 changed files with 29073 additions and 79268 deletions

38
.gitignore vendored
View File

@@ -6,12 +6,18 @@
/config.status
/config-temp
/trace-events-all
/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
/ui/shader/texture-blit-frag.h
/ui/shader/texture-blit-vert.h
*-timestamp
@@ -34,7 +40,6 @@
/qmp-marshal.c
/qemu-doc.html
/qemu-doc.info
/qemu-doc.txt
/qemu-img
/qemu-nbd
/qemu-options.def
@@ -55,6 +60,7 @@
*.a
*.aux
*.cp
*.dvi
*.exe
*.msi
*.dll
@@ -76,6 +82,10 @@
*.d
!/scripts/qemu-guest-agent/fsfreeze-hook.d
*.o
*.lo
*.la
*.pc
.libs
.sdk
*.gcda
*.gcno
@@ -99,35 +109,9 @@
/pc-bios/optionrom/kvmvapic.img
/pc-bios/s390-ccw/s390-ccw.elf
/pc-bios/s390-ccw/s390-ccw.img
/docs/qemu-ga-ref.html
/docs/qemu-ga-ref.txt
/docs/qemu-qmp-ref.html
/docs/qemu-qmp-ref.txt
docs/qemu-ga-ref.info*
docs/qemu-qmp-ref.info*
/qemu-ga-qapi.texi
/qemu-qapi.texi
/version.texi
*.tps
.stgit-*
cscope.*
tags
TAGS
docker-src.*
*~
trace.h
trace.c
trace-ust.h
trace-ust.h
trace-dtrace.h
trace-dtrace.dtrace
trace-root.h
trace-root.c
trace-ust-root.h
trace-ust-root.h
trace-ust-all.h
trace-ust-all.c
trace-dtrace-root.h
trace-dtrace-root.dtrace
trace-ust-all.h
trace-ust-all.c

View File

@@ -1,19 +0,0 @@
language: c
env:
matrix:
- IMAGE=debian-armhf-cross
TARGET_LIST=arm-softmmu,arm-linux-user
- IMAGE=debian-arm64-cross
TARGET_LIST=aarch64-softmmu,aarch64-linux-user
build:
pre_ci:
- make docker-image-${IMAGE}
pre_ci_boot:
image_name: qemu
image_tag: ${IMAGE}
pull: false
options: "-e HOME=/root"
ci:
- unset CC
- ./configure ${QEMU_CONFIGURE_OPTS} --target-list=${TARGET_LIST}
- make -j2

View File

@@ -4,6 +4,7 @@ python:
- "2.4"
compiler:
- gcc
- clang
cache: ccache
addons:
apt:
@@ -67,9 +68,6 @@ script:
- make -j3 && ${TEST_CMD}
matrix:
include:
# Test with CLang for compile portability
- env: CONFIG=""
compiler: clang
# gprof/gcov are GCC features
- env: CONFIG="--enable-gprof --enable-gcov --disable-pie"
compiler: gcc
@@ -92,8 +90,8 @@ matrix:
- env: CONFIG=""
os: osx
compiler: clang
# Plain Trusty System Build
- env: CONFIG="--disable-linux-user"
# Plain Trusty Build
- env: CONFIG=""
sudo: required
addons:
dist: trusty
@@ -103,55 +101,6 @@ matrix:
- sudo apt-get build-dep -qq qemu
- wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
- git submodule update --init --recursive
# Plain Trusty Linux User Build
- env: CONFIG="--disable-system"
sudo: required
addons:
dist: trusty
compiler: gcc
before_install:
- sudo apt-get update -qq
- sudo apt-get build-dep -qq qemu
- wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
- git submodule update --init --recursive
# Trusty System build with latest stable clang
- sudo: required
addons:
dist: trusty
language: generic
compiler: none
env:
- COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
- CONFIG="--disable-linux-user --cc=clang-3.9 --cxx=clang++-3.9"
before_install:
- wget -nv -O - http://llvm.org/apt/llvm-snapshot.gpg.key | sudo apt-key add -
- sudo apt-add-repository -y 'deb http://llvm.org/apt/trusty llvm-toolchain-trusty-3.9 main'
- sudo apt-get update -qq
- sudo apt-get install -qq -y clang-3.9
- sudo apt-get build-dep -qq qemu
- wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
- git submodule update --init --recursive
before_script:
- ./configure ${CONFIG} || cat config.log
# Trusty Linux User build with latest stable clang
- sudo: required
addons:
dist: trusty
language: generic
compiler: none
env:
- COMPILER_NAME=clang CXX=clang++-3.9 CC=clang-3.9
- CONFIG="--disable-system --cc=clang-3.9 --cxx=clang++-3.9"
before_install:
- wget -nv -O - http://llvm.org/apt/llvm-snapshot.gpg.key | sudo apt-key add -
- sudo apt-add-repository -y 'deb http://llvm.org/apt/trusty llvm-toolchain-trusty-3.9 main'
- sudo apt-get update -qq
- sudo apt-get install -qq -y clang-3.9
- sudo apt-get build-dep -qq qemu
- wget -O - http://people.linaro.org/~alex.bennee/qemu-submodule-git-seed.tar.xz | tar -xvJ
- git submodule update --init --recursive
before_script:
- ./configure ${CONFIG} || cat config.log
# Using newer GCC with sanitizers
- addons:
apt:

18
HACKING
View File

@@ -1,28 +1,10 @@
1. Preprocessor
1.1. Variadic macros
For variadic macros, stick with this C99-like syntax:
#define DPRINTF(fmt, ...) \
do { printf("IRQ: " fmt, ## __VA_ARGS__); } while (0)
1.2. Include directives
Order include directives as follows:
#include "qemu/osdep.h" /* Always first... */
#include <...> /* then system headers... */
#include "..." /* and finally QEMU headers. */
The "qemu/osdep.h" header contains preprocessor macros that affect the behavior
of core system headers like <stdint.h>. It must be the first include so that
core system headers included by external libraries get the preprocessor macros
that QEMU depends on.
Do not include "qemu/osdep.h" from header files since the .c file will have
already included it.
2. C types
It should be common sense to use the right type, but we have collected

View File

@@ -106,7 +106,7 @@ F: include/fpu/
Alpha
M: Richard Henderson <rth@twiddle.net>
S: Maintained
F: target/alpha/
F: target-alpha/
F: hw/alpha/
F: tests/tcg/alpha/
F: disas/alpha.c
@@ -115,7 +115,7 @@ ARM
M: Peter Maydell <peter.maydell@linaro.org>
L: qemu-arm@nongnu.org
S: Maintained
F: target/arm/
F: target-arm/
F: hw/arm/
F: hw/cpu/a*mpcore.c
F: include/hw/cpu/a*mpcore.h
@@ -126,22 +126,16 @@ F: disas/libvixl/
CRIS
M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
S: Maintained
F: target/cris/
F: target-cris/
F: hw/cris/
F: include/hw/cris/
F: tests/tcg/cris/
F: disas/cris.c
HPPA (PA-RISC)
M: Richard Henderson <rth@twiddle.net>
S: Maintained
F: target/hppa/
F: disas/hppa.c
LM32
M: Michael Walle <michael@walle.cc>
S: Maintained
F: target/lm32/
F: target-lm32/
F: disas/lm32.c
F: hw/lm32/
F: hw/*/lm32_*
@@ -153,13 +147,13 @@ F: tests/tcg/lm32/
M68K
M: Laurent Vivier <laurent@vivier.eu>
S: Maintained
F: target/m68k/
F: target-m68k/
F: disas/m68k.c
MicroBlaze
M: Edgar E. Iglesias <edgar.iglesias@gmail.com>
S: Maintained
F: target/microblaze/
F: target-microblaze/
F: hw/microblaze/
F: disas/microblaze.c
@@ -167,7 +161,7 @@ MIPS
M: Aurelien Jarno <aurelien@aurel32.net>
M: Yongbok Kim <yongbok.kim@imgtec.com>
S: Maintained
F: target/mips/
F: target-mips/
F: hw/mips/
F: hw/misc/mips_*
F: hw/intc/mips_gic.c
@@ -182,23 +176,15 @@ F: disas/mips.c
Moxie
M: Anthony Green <green@moxielogic.com>
S: Maintained
F: target/moxie/
F: target-moxie/
F: disas/moxie.c
F: hw/moxie/
F: default-configs/moxie-softmmu.mak
NiosII
M: Chris Wulff <crwulff@gmail.com>
M: Marek Vasut <marex@denx.de>
S: Maintained
F: target/nios2/
F: hw/nios2/
F: disas/nios2.c
OpenRISC
M: Jia Liu <proljc@gmail.com>
S: Maintained
F: target/openrisc/
F: target-openrisc/
F: hw/openrisc/
F: tests/tcg/openrisc/
@@ -207,7 +193,7 @@ M: David Gibson <david@gibson.dropbear.id.au>
M: Alexander Graf <agraf@suse.de>
L: qemu-ppc@nongnu.org
S: Maintained
F: target/ppc/
F: target-ppc/
F: hw/ppc/
F: include/hw/ppc/
F: disas/ppc.c
@@ -216,14 +202,14 @@ S390
M: Richard Henderson <rth@twiddle.net>
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: target/s390x/
F: target-s390x/
F: hw/s390x/
F: disas/s390.c
SH4
M: Aurelien Jarno <aurelien@aurel32.net>
S: Odd Fixes
F: target/sh4/
F: target-sh4/
F: hw/sh4/
F: disas/sh4.c
F: include/hw/sh4/
@@ -232,7 +218,7 @@ SPARC
M: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
M: Artyom Tarasenko <atar4qemu@gmail.com>
S: Maintained
F: target/sparc/
F: target-sparc/
F: hw/sparc/
F: hw/sparc64/
F: disas/sparc.c
@@ -240,7 +226,7 @@ F: disas/sparc.c
UniCore32
M: Guan Xuetao <gxt@mprc.pku.edu.cn>
S: Maintained
F: target/unicore32/
F: target-unicore32/
F: hw/unicore32/
F: include/hw/unicore32/
@@ -249,7 +235,7 @@ M: Paolo Bonzini <pbonzini@redhat.com>
M: Richard Henderson <rth@twiddle.net>
M: Eduardo Habkost <ehabkost@redhat.com>
S: Maintained
F: target/i386/
F: target-i386/
F: hw/i386/
F: disas/i386.c
@@ -257,14 +243,14 @@ Xtensa
M: Max Filippov <jcmvbkbc@gmail.com>
W: http://wiki.osll.spb.ru/doku.php?id=etc:users:jcmvbkbc:qemu-target-xtensa
S: Maintained
F: target/xtensa/
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: target-tricore/
F: hw/tricore/
F: include/hw/tricore/
@@ -283,26 +269,26 @@ ARM
M: Peter Maydell <peter.maydell@linaro.org>
L: qemu-arm@nongnu.org
S: Maintained
F: target/arm/kvm.c
F: target-arm/kvm.c
MIPS
M: James Hogan <james.hogan@imgtec.com>
S: Maintained
F: target/mips/kvm.c
F: target-mips/kvm.c
PPC
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: target/ppc/kvm.c
F: target-ppc/kvm.c
S390
M: Christian Borntraeger <borntraeger@de.ibm.com>
M: Cornelia Huck <cornelia.huck@de.ibm.com>
M: Alexander Graf <agraf@suse.de>
S: Maintained
F: target/s390x/kvm.c
F: target/s390x/ioinst.[ch]
F: target/s390x/machine.c
F: target-s390x/kvm.c
F: target-s390x/ioinst.[ch]
F: target-s390x/machine.c
F: hw/intc/s390_flic.c
F: hw/intc/s390_flic_kvm.c
F: include/hw/s390x/s390_flic.h
@@ -315,7 +301,7 @@ M: Paolo Bonzini <pbonzini@redhat.com>
M: Marcelo Tosatti <mtosatti@redhat.com>
L: kvm@vger.kernel.org
S: Supported
F: target/i386/kvm.c
F: target-i386/kvm.c
Guest CPU Cores (Xen):
----------------------
@@ -323,7 +309,7 @@ Guest CPU Cores (Xen):
X86
M: Stefano Stabellini <sstabellini@kernel.org>
M: Anthony Perard <anthony.perard@citrix.com>
L: xen-devel@lists.xenproject.org
L: xen-devel@lists.xensource.com
S: Supported
F: xen-*
F: */xen*
@@ -522,6 +508,7 @@ M: Shannon Zhao <shannon.zhao@linaro.org>
L: qemu-arm@nongnu.org
S: Maintained
F: hw/arm/virt-acpi-build.c
F: include/hw/arm/virt-acpi-build.h
STM32F205
M: Alistair Francis <alistair@alistair23.me>
@@ -561,19 +548,20 @@ F: hw/lm32/milkymist.c
M68K Machines
-------------
an5206
M: Thomas Huth <huth@tuxfamily.org>
S: Odd Fixes
S: Orphan
F: hw/m68k/an5206.c
F: hw/m68k/mcf5206.c
dummy_m68k
S: Orphan
F: hw/m68k/dummy_m68k.c
mcf5208
M: Thomas Huth <huth@tuxfamily.org>
S: Odd Fixes
S: Orphan
F: hw/m68k/mcf5208.c
F: hw/m68k/mcf_intc.c
F: hw/char/mcf_uart.c
F: hw/net/mcf_fec.c
F: include/hw/m68k/mcf*.h
MicroBlaze Machines
-------------------
@@ -670,13 +658,10 @@ F: hw/misc/macio/
F: hw/intc/heathrow_pic.c
PReP
M: Hervé Poussineau <hpoussin@reactos.org>
L: qemu-devel@nongnu.org
L: qemu-ppc@nongnu.org
S: Maintained
S: Odd Fixes
F: hw/ppc/prep.c
F: hw/ppc/prep_systemio.c
F: hw/ppc/rs6000_mc.c
F: hw/pci-host/prep.[hc]
F: hw/isa/pc87312.[hc]
F: pc-bios/ppc_rom.bin
@@ -741,13 +726,6 @@ S: Maintained
F: hw/sparc64/sun4u.c
F: pc-bios/openbios-sparc64
Sun4v
M: Artyom Tarasenko <atar4qemu@gmail.com>
S: Maintained
F: hw/sparc64/sun4v.c
F: hw/timer/sun4v-rtc.c
F: include/hw/timer/sun4v-rtc.h
Leon3
M: Fabien Chouteau <chouteau@adacore.com>
S: Maintained
@@ -829,7 +807,6 @@ M: Eduardo Habkost <ehabkost@redhat.com>
M: Marcel Apfelbaum <marcel@redhat.com>
S: Supported
F: hw/core/machine.c
F: hw/core/null-machine.c
F: include/hw/boards.h
Xtensa Machines
@@ -908,6 +885,7 @@ F: hw/acpi/*
F: hw/smbios/*
F: hw/i386/acpi-build.[hc]
F: hw/arm/virt-acpi-build.c
F: include/hw/arm/virt-acpi-build.h
ppc4xx
M: Alexander Graf <agraf@suse.de>
@@ -1033,7 +1011,7 @@ F: hw/input/virtio-input*.c
F: include/hw/virtio/virtio-input.h
virtio-serial
M: Amit Shah <amit@kernel.org>
M: Amit Shah <amit.shah@redhat.com>
S: Supported
F: hw/char/virtio-serial-bus.c
F: hw/char/virtio-console.c
@@ -1042,7 +1020,7 @@ F: tests/virtio-console-test.c
F: tests/virtio-serial-test.c
virtio-rng
M: Amit Shah <amit@kernel.org>
M: Amit Shah <amit.shah@redhat.com>
S: Supported
F: hw/virtio/virtio-rng.c
F: include/hw/virtio/virtio-rng.h
@@ -1196,9 +1174,8 @@ T: git git://github.com/jnsnow/qemu.git bitmaps
Character device backends
M: Paolo Bonzini <pbonzini@redhat.com>
M: Marc-André Lureau <marcandre.lureau@redhat.com>
S: Maintained
F: chardev/
F: qemu-char.c
F: backends/msmouse.c
F: backends/testdev.c
@@ -1430,7 +1407,7 @@ F: scripts/checkpatch.pl
Migration
M: Juan Quintela <quintela@redhat.com>
M: Dr. David Alan Gilbert <dgilbert@redhat.com>
M: Amit Shah <amit.shah@redhat.com>
S: Maintained
F: include/migration/
F: migration/
@@ -1519,7 +1496,6 @@ M: Riku Voipio <riku.voipio@iki.fi>
S: Maintained
F: thunk.c
F: user-exec.c
F: user-exec-stub.c
BSD user
S: Orphan
@@ -1644,7 +1620,6 @@ M: Peter Lieven <pl@kamp.de>
L: qemu-block@nongnu.org
S: Supported
F: block/iscsi.c
F: block/iscsi-opts.c
NFS
M: Jeff Cody <jcody@redhat.com>
@@ -1745,9 +1720,9 @@ L: qemu-block@nongnu.org
S: Supported
F: block/linux-aio.c
F: include/block/raw-aio.h
F: block/raw-format.c
F: block/file-posix.c
F: block/file-win32.c
F: block/raw-posix.c
F: block/raw-win32.c
F: block/raw_bsd.c
F: block/win32-aio.c
qcow2
@@ -1800,14 +1775,9 @@ F: docs/block-replication.txt
Build and test automation
-------------------------
M: Alex Bennée <alex.bennee@linaro.org>
M: Fam Zheng <famz@redhat.com>
L: qemu-devel@nongnu.org
S: Maintained
S: Supported
F: .travis.yml
F: .shippable.yml
F: tests/docker/
W: https://travis-ci.org/qemu/qemu
W: http://patchew.org/QEMU/
Documentation
-------------
@@ -1816,3 +1786,9 @@ M: Daniel P. Berrange <berrange@redhat.com>
S: Odd Fixes
F: docs/build-system.txt
Docker testing
--------------
Docker based testing framework and cases
M: Fam Zheng <famz@redhat.com>
S: Maintained
F: tests/docker/

277
Makefile
View File

@@ -56,143 +56,32 @@ GENERATED_SOURCES += qmp-marshal.c qapi-types.c qapi-visit.c qapi-event.c
GENERATED_HEADERS += qmp-introspect.h
GENERATED_SOURCES += qmp-introspect.c
GENERATED_HEADERS += trace/generated-tracers.h
ifeq ($(findstring dtrace,$(TRACE_BACKENDS)),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
ifdef CONFIG_TRACE_UST
GENERATED_HEADERS += trace-ust-all.h
GENERATED_SOURCES += trace-ust-all.c
ifeq ($(findstring ust,$(TRACE_BACKENDS)),ust)
GENERATED_HEADERS += trace/generated-ust-provider.h
GENERATED_SOURCES += trace/generated-ust.c
endif
GENERATED_HEADERS += module_block.h
TRACE_HEADERS = trace-root.h $(trace-events-subdirs:%=%/trace.h)
TRACE_SOURCES = trace-root.c $(trace-events-subdirs:%=%/trace.c)
TRACE_DTRACE =
ifdef CONFIG_TRACE_DTRACE
TRACE_HEADERS += trace-dtrace-root.h $(trace-events-subdirs:%=%/trace-dtrace.h)
TRACE_DTRACE += trace-dtrace-root.dtrace $(trace-events-subdirs:%=%/trace-dtrace.dtrace)
endif
ifdef CONFIG_TRACE_UST
TRACE_HEADERS += trace-ust-root.h $(trace-events-subdirs:%=%/trace-ust.h)
endif
GENERATED_HEADERS += $(TRACE_HEADERS)
GENERATED_SOURCES += $(TRACE_SOURCES)
trace-group-name = $(shell dirname $1 | sed -e 's/[^a-zA-Z0-9]/_/g')
%/trace.h: %/trace.h-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
%/trace.h-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=$(call trace-group-name,$@) \
--format=h \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
%/trace.c: %/trace.c-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
%/trace.c-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=$(call trace-group-name,$@) \
--format=c \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
%/trace-ust.h: %/trace-ust.h-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
%/trace-ust.h-timestamp: $(SRC_PATH)/%/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=$(call trace-group-name,$@) \
--format=ust-events-h \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
%/trace-dtrace.dtrace: %/trace-dtrace.dtrace-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
%/trace-dtrace.dtrace-timestamp: $(SRC_PATH)/%/trace-events $(BUILD_DIR)/config-host.mak $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=$(call trace-group-name,$@) \
--format=d \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
%/trace-dtrace.h: %/trace-dtrace.dtrace $(tracetool-y)
$(call quiet-command,dtrace -o $@ -h -s $<, "GEN","$@")
%/trace-dtrace.o: %/trace-dtrace.dtrace $(tracetool-y)
trace-root.h: trace-root.h-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-root.h-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=root \
--format=h \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
trace-root.c: trace-root.c-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-root.c-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=root \
--format=c \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
trace-ust-root.h: trace-ust-root.h-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-ust-root.h-timestamp: $(SRC_PATH)/trace-events $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=root \
--format=ust-events-h \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
trace-ust-all.h: trace-ust-all.h-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-ust-all.h-timestamp: $(trace-events-files) $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=all \
--format=ust-events-h \
--backends=$(TRACE_BACKENDS) \
$(trace-events-files) > $@,"GEN","$(@:%-timestamp=%)")
trace-ust-all.c: trace-ust-all.c-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-ust-all.c-timestamp: $(trace-events-files) $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=all \
--format=ust-events-c \
--backends=$(TRACE_BACKENDS) \
$(trace-events-files) > $@,"GEN","$(@:%-timestamp=%)")
trace-dtrace-root.dtrace: trace-dtrace-root.dtrace-timestamp
@cmp $< $@ >/dev/null 2>&1 || cp $< $@
trace-dtrace-root.dtrace-timestamp: $(SRC_PATH)/trace-events $(BUILD_DIR)/config-host.mak $(tracetool-y)
$(call quiet-command,$(TRACETOOL) \
--group=root \
--format=d \
--backends=$(TRACE_BACKENDS) \
$< > $@,"GEN","$(@:%-timestamp=%)")
trace-dtrace-root.h: trace-dtrace-root.dtrace
$(call quiet-command,dtrace -o $@ -h -s $<, "GEN","$@")
trace-dtrace-root.o: trace-dtrace-root.dtrace
# Don't try to regenerate Makefile or configure
# We don't generate any of them
Makefile: ;
configure: ;
.PHONY: all clean cscope distclean html info install install-doc \
pdf txt recurse-all speed test dist msi FORCE
.PHONY: all clean cscope distclean dvi html info install install-doc \
pdf recurse-all speed test dist msi FORCE
$(call set-vpath, $(SRC_PATH))
@@ -201,9 +90,7 @@ LIBS+=-lz $(LIBS_TOOLS)
HELPERS-$(CONFIG_LINUX) = qemu-bridge-helper$(EXESUF)
ifdef BUILD_DOCS
DOCS=qemu-doc.html qemu-doc.txt qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
DOCS+=docs/qemu-qmp-ref.html docs/qemu-qmp-ref.txt docs/qemu-qmp-ref.7
DOCS+=docs/qemu-ga-ref.html docs/qemu-ga-ref.txt docs/qemu-ga-ref.7
DOCS=qemu-doc.html qemu.1 qemu-img.1 qemu-nbd.8 qemu-ga.8
ifdef CONFIG_VIRTFS
DOCS+=fsdev/virtfs-proxy-helper.1
endif
@@ -258,12 +145,10 @@ endif
dummy := $(call unnest-vars,, \
stub-obj-y \
chardev-obj-y \
util-obj-y \
qga-obj-y \
ivshmem-client-obj-y \
ivshmem-server-obj-y \
libvhost-user-obj-y \
qga-vss-dll-obj-y \
block-obj-y \
block-obj-m \
@@ -272,8 +157,7 @@ dummy := $(call unnest-vars,, \
qom-obj-y \
io-obj-y \
common-obj-y \
common-obj-m \
trace-obj-y)
common-obj-m)
ifneq ($(wildcard config-host.mak),)
include $(SRC_PATH)/tests/Makefile.include
@@ -299,11 +183,7 @@ qemu-version.h: FORCE
printf '""\n'; \
fi; \
fi) > $@.tmp)
$(call quiet-command, if ! cmp -s $@ $@.tmp; then \
mv $@.tmp $@; \
else \
rm $@.tmp; \
fi)
$(call quiet-command, cmp -s $@ $@.tmp || mv $@.tmp $@)
config-host.h: config-host.h-timestamp
config-host.h-timestamp: config-host.mak
@@ -340,8 +220,7 @@ subdir-dtc:dtc/libfdt dtc/tests
dtc/%:
mkdir -p $@
$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(chardev-obj-y) \
$(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY)) $(trace-obj-y)
$(SUBDIR_RULES): libqemuutil.a libqemustub.a $(common-obj-y) $(qom-obj-y) $(crypto-aes-obj-$(CONFIG_USER_ONLY))
ROMSUBDIR_RULES=$(patsubst %,romsubdir-%, $(ROMS))
# Only keep -O and -g cflags
@@ -352,10 +231,12 @@ ALL_SUBDIRS=$(TARGET_DIRS) $(patsubst %,pc-bios/%, $(ROMS))
recurse-all: $(SUBDIR_RULES) $(ROMSUBDIR_RULES)
$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc config-host.h
$(BUILD_DIR)/version.o: $(SRC_PATH)/version.rc 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 config-host.h
$(call quiet-command,$(WINDRES) -I$(BUILD_DIR) -o $@ $<,"RC","version.lo")
Makefile: $(version-obj-y)
Makefile: $(version-obj-y) $(version-lobj-y)
######################################################################
# Build libraries
@@ -365,17 +246,15 @@ libqemuutil.a: $(util-obj-y)
######################################################################
COMMON_LDADDS = $(trace-obj-y) libqemuutil.a libqemustub.a
qemu-img.o: qemu-img-cmds.h
qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) $(COMMON_LDADDS)
qemu-img$(EXESUF): qemu-img.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-nbd$(EXESUF): qemu-nbd.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-io$(EXESUF): qemu-io.o $(block-obj-y) $(crypto-obj-y) $(io-obj-y) $(qom-obj-y) libqemuutil.a libqemustub.a
qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o $(COMMON_LDADDS)
qemu-bridge-helper$(EXESUF): qemu-bridge-helper.o libqemuutil.a libqemustub.a
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/9p-marshal.o fsdev/9p-iov-marshal.o $(COMMON_LDADDS)
fsdev/virtfs-proxy-helper$(EXESUF): fsdev/virtfs-proxy-helper.o fsdev/9p-marshal.o fsdev/9p-iov-marshal.o libqemuutil.a libqemustub.a
fsdev/virtfs-proxy-helper$(EXESUF): LIBS += -lcap
qemu-img-cmds.h: $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/scripts/hxtool
@@ -387,7 +266,6 @@ qemu-ga$(EXESUF): QEMU_CFLAGS += -I qga/qapi-generated
gen-out-type = $(subst .,-,$(suffix $@))
qapi-py = $(SRC_PATH)/scripts/qapi.py $(SRC_PATH)/scripts/ordereddict.py
qapi-py += $(SRC_PATH)/scripts/qapi2texi.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)
@@ -440,7 +318,7 @@ $(qapi-modules) $(SRC_PATH)/scripts/qapi-introspect.py $(qapi-py)
QGALIB_GEN=$(addprefix qga/qapi-generated/, qga-qapi-types.h qga-qapi-visit.h qga-qmp-commands.h)
$(qga-obj-y) qemu-ga.o: $(QGALIB_GEN)
qemu-ga$(EXESUF): $(qga-obj-y) $(COMMON_LDADDS)
qemu-ga$(EXESUF): $(qga-obj-y) libqemuutil.a libqemustub.a
$(call LINK, $^)
ifdef QEMU_GA_MSI_ENABLED
@@ -465,9 +343,9 @@ ifneq ($(EXESUF),)
qemu-ga: qemu-ga$(EXESUF) $(QGA_VSS_PROVIDER) $(QEMU_GA_MSI)
endif
ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) $(COMMON_LDADDS)
ivshmem-client$(EXESUF): $(ivshmem-client-obj-y) libqemuutil.a libqemustub.a
$(call LINK, $^)
ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) $(COMMON_LDADDS)
ivshmem-server$(EXESUF): $(ivshmem-server-obj-y) libqemuutil.a libqemustub.a
$(call LINK, $^)
module_block.h: $(SRC_PATH)/scripts/modules/module_block.py config-host.mak
@@ -480,9 +358,10 @@ clean:
rm -f config.mak op-i386.h opc-i386.h gen-op-i386.h op-arm.h opc-arm.h gen-op-arm.h
rm -f qemu-options.def
rm -f *.msi
find . \( -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
find . \( -name '*.l[oa]' -o -name '*.so' -o -name '*.dll' -o -name '*.mo' -o -name '*.[oda]' \) -type f -exec rm {} +
rm -f $(filter-out %.tlb,$(TOOLS)) $(HELPERS-y) qemu-ga TAGS cscope.* *.pod *~ */*~
rm -f fsdev/*.pod
rm -rf .libs */.libs
rm -f qemu-img-cmds.h
rm -f ui/shader/*-vert.h ui/shader/*-frag.h
@# May not be present in GENERATED_HEADERS
@@ -510,17 +389,12 @@ distclean: clean
rm -f config-all-devices.mak config-all-disas.mak config.status
rm -f po/*.mo tests/qemu-iotests/common.env
rm -f roms/seabios/config.mak roms/vgabios/config.mak
rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps
rm -f qemu-doc.info qemu-doc.aux qemu-doc.cp qemu-doc.cps qemu-doc.dvi
rm -f qemu-doc.fn qemu-doc.fns qemu-doc.info qemu-doc.ky qemu-doc.kys
rm -f qemu-doc.log qemu-doc.pdf qemu-doc.pg qemu-doc.toc qemu-doc.tp
rm -f qemu-doc.vr qemu-doc.txt
rm -f qemu-doc.vr
rm -f config.log
rm -f linux-headers/asm
rm -f qemu-ga-qapi.texi qemu-qapi.texi version.texi
rm -f docs/qemu-qmp-ref.7 docs/qemu-ga-ref.7
rm -f docs/qemu-qmp-ref.txt docs/qemu-ga-ref.txt
rm -f docs/qemu-qmp-ref.pdf docs/qemu-ga-ref.pdf
rm -f docs/qemu-qmp-ref.html docs/qemu-ga-ref.html
for d in $(TARGET_DIRS); do \
rm -rf $$d || exit 1 ; \
done
@@ -557,14 +431,10 @@ endif
install-doc: $(DOCS)
$(INSTALL_DIR) "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) qemu-doc.html "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) qemu-doc.txt "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) docs/qemu-qmp-ref.html "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) docs/qemu-qmp-ref.txt "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) $(SRC_PATH)/docs/qmp-commands.txt "$(DESTDIR)$(qemu_docdir)"
ifdef CONFIG_POSIX
$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man1"
$(INSTALL_DATA) qemu.1 "$(DESTDIR)$(mandir)/man1"
$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man7"
$(INSTALL_DATA) docs/qemu-qmp-ref.7 "$(DESTDIR)$(mandir)/man7"
ifneq ($(TOOLS),)
$(INSTALL_DATA) qemu-img.1 "$(DESTDIR)$(mandir)/man1"
$(INSTALL_DIR) "$(DESTDIR)$(mandir)/man8"
@@ -572,9 +442,6 @@ ifneq ($(TOOLS),)
endif
ifneq (,$(findstring qemu-ga,$(TOOLS)))
$(INSTALL_DATA) qemu-ga.8 "$(DESTDIR)$(mandir)/man8"
$(INSTALL_DATA) docs/qemu-ga-ref.html "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) docs/qemu-ga-ref.txt "$(DESTDIR)$(qemu_docdir)"
$(INSTALL_DATA) docs/qemu-ga-ref.7 "$(DESTDIR)$(mandir)/man7"
endif
endif
ifdef CONFIG_VIRTFS
@@ -593,7 +460,7 @@ endif
endif
install: all $(if $(BUILD_DOCS),install-doc) $(BUILD_DIR)/trace-events-all \
install: all $(if $(BUILD_DOCS),install-doc) \
install-datadir install-localstatedir
ifneq ($(TOOLS),)
$(call install-prog,$(subst qemu-ga,qemu-ga$(EXESUF),$(TOOLS)),$(DESTDIR)$(bindir))
@@ -663,25 +530,20 @@ ui/console-gl.o: $(SRC_PATH)/ui/console-gl.c \
# documentation
MAKEINFO=makeinfo
MAKEINFOFLAGS=--no-split --number-sections
MAKEINFOFLAGS=--no-headers --no-split --number-sections
TEXIFLAG=$(if $(V),,--quiet)
%.dvi: %.texi
$(call quiet-command,texi2dvi $(TEXIFLAG) -I . $<,"GEN","$@")
version.texi: $(SRC_PATH)/VERSION
$(call quiet-command,echo "@set VERSION $(VERSION)" > $@,"GEN","$@")
%.html: %.texi
$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --html $< -o $@, \
"GEN","$@")
%.html: %.texi version.texi
$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --no-headers \
--html $< -o $@,"GEN","$@")
%.info: %.texi
$(call quiet-command,$(MAKEINFO) $< -o $@,"GEN","$@")
%.info: %.texi version.texi
$(call quiet-command,$(MAKEINFO) $(MAKEINFOFLAGS) $< -o $@,"GEN","$@")
%.txt: %.texi version.texi
$(call quiet-command,LC_ALL=C $(MAKEINFO) $(MAKEINFOFLAGS) --no-headers \
--plaintext $< -o $@,"GEN","$@")
%.pdf: %.texi version.texi
$(call quiet-command,texi2pdf $(TEXIFLAG) -I $(SRC_PATH) -I . $< -o $@,"GEN","$@")
%.pdf: %.texi
$(call quiet-command,texi2pdf $(TEXIFLAG) -I . $<,"GEN","$@")
qemu-options.texi: $(SRC_PATH)/qemu-options.hx $(SRC_PATH)/scripts/hxtool
$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
@@ -695,36 +557,47 @@ qemu-monitor-info.texi: $(SRC_PATH)/hmp-commands-info.hx $(SRC_PATH)/scripts/hxt
qemu-img-cmds.texi: $(SRC_PATH)/qemu-img-cmds.hx $(SRC_PATH)/scripts/hxtool
$(call quiet-command,sh $(SRC_PATH)/scripts/hxtool -t < $< > $@,"GEN","$@")
qemu-qapi.texi: $(qapi-modules) $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi2texi.py $< > $@,"GEN","$@")
qemu-ga-qapi.texi: $(SRC_PATH)/qga/qapi-schema.json $(qapi-py)
$(call quiet-command,$(PYTHON) $(SRC_PATH)/scripts/qapi2texi.py $< > $@,"GEN","$@")
qemu.1: qemu-doc.texi qemu-options.texi qemu-monitor.texi qemu-monitor-info.texi
$(call quiet-command, \
perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu.pod && \
$(POD2MAN) --section=1 --center=" " --release=" " qemu.pod > $@, \
"GEN","$@")
qemu.1: qemu-option-trace.texi
qemu-img.1: qemu-img.texi qemu-option-trace.texi qemu-img-cmds.texi
$(call quiet-command, \
perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-img.pod && \
$(POD2MAN) --section=1 --center=" " --release=" " qemu-img.pod > $@, \
"GEN","$@")
fsdev/virtfs-proxy-helper.1: fsdev/virtfs-proxy-helper.texi
$(call quiet-command, \
perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< fsdev/virtfs-proxy-helper.pod && \
$(POD2MAN) --section=1 --center=" " --release=" " fsdev/virtfs-proxy-helper.pod > $@, \
"GEN","$@")
qemu-nbd.8: qemu-nbd.texi qemu-option-trace.texi
$(call quiet-command, \
perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-nbd.pod && \
$(POD2MAN) --section=8 --center=" " --release=" " qemu-nbd.pod > $@, \
"GEN","$@")
qemu-ga.8: qemu-ga.texi
$(call quiet-command, \
perl -Ww -- $(SRC_PATH)/scripts/texi2pod.pl $< qemu-ga.pod && \
$(POD2MAN) --section=8 --center=" " --release=" " qemu-ga.pod > $@, \
"GEN","$@")
html: qemu-doc.html docs/qemu-qmp-ref.html docs/qemu-ga-ref.html
info: qemu-doc.info docs/qemu-qmp-ref.info docs/qemu-ga-ref.info
pdf: qemu-doc.pdf docs/qemu-qmp-ref.pdf docs/qemu-ga-ref.pdf
txt: qemu-doc.txt docs/qemu-qmp-ref.txt docs/qemu-ga-ref.txt
dvi: qemu-doc.dvi
html: qemu-doc.html
info: qemu-doc.info
pdf: qemu-doc.pdf
qemu-doc.html qemu-doc.info qemu-doc.pdf qemu-doc.txt: \
qemu-doc.dvi qemu-doc.html qemu-doc.info qemu-doc.pdf: \
qemu-img.texi qemu-nbd.texi qemu-options.texi qemu-option-trace.texi \
qemu-monitor.texi qemu-img-cmds.texi qemu-ga.texi \
qemu-monitor-info.texi
docs/qemu-ga-ref.dvi docs/qemu-ga-ref.html docs/qemu-ga-ref.info docs/qemu-ga-ref.pdf docs/qemu-ga-ref.txt docs/qemu-ga-ref.7: \
docs/qemu-ga-ref.texi qemu-ga-qapi.texi
docs/qemu-qmp-ref.dvi docs/qemu-qmp-ref.html docs/qemu-qmp-ref.info docs/qemu-qmp-ref.pdf docs/qemu-qmp-ref.txt docs/qemu-qmp-ref.7: \
docs/qemu-qmp-ref.texi qemu-qapi.texi
ifdef CONFIG_WIN32
INSTALLER = qemu-setup-$(VERSION)$(EXESUF)
@@ -787,10 +660,6 @@ ifneq ($(filter-out $(UNCHECKED_GOALS),$(MAKECMDGOALS)),$(if $(MAKECMDGOALS),,fa
Makefile: $(GENERATED_HEADERS)
endif
.SECONDARY: $(TRACE_HEADERS) $(TRACE_HEADERS:%=%-timestamp) \
$(TRACE_SOURCES) $(TRACE_SOURCES:%=%-timestamp) \
$(TRACE_DTRACE) $(TRACE_DTRACE:%=%-timestamp)
# Include automatically generated dependency files
# Dependencies in Makefile.objs files come from our recursive subdir rules
-include $(wildcard *.d tests/*.d)
@@ -821,7 +690,7 @@ help:
@echo ' docker - Help about targets running tests inside Docker containers'
@echo ''
@echo 'Documentation targets:'
@echo ' html info pdf txt'
@echo ' dvi html info pdf'
@echo ' - Build documentation in specified format'
@echo ''
ifdef CONFIG_WIN32

View File

@@ -4,13 +4,15 @@ stub-obj-y = stubs/ crypto/
util-obj-y = util/ qobject/ qapi/
util-obj-y += qmp-introspect.o qapi-types.o qapi-visit.o qapi-event.o
chardev-obj-y = chardev/
#######################################################################
# block-obj-y is code used by both qemu system emulation and qemu-img
block-obj-y = async.o thread-pool.o
block-obj-y += nbd/
block-obj-y += block.o blockjob.o
block-obj-y += 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 += qemu-io-cmds.o
block-obj-$(CONFIG_REPLICATION) += replication.o
@@ -49,7 +51,8 @@ common-obj-$(CONFIG_POSIX) += os-posix.o
common-obj-$(CONFIG_LINUX) += fsdev/
common-obj-y += migration/
common-obj-y += page_cache.o #aio.o
common-obj-y += qemu-char.o #aio.o
common-obj-y += page_cache.o
common-obj-$(CONFIG_SPICE) += spice-qemu-char.o
@@ -94,6 +97,7 @@ common-obj-y += disas/
######################################################################
# Resource file for Windows executables
version-obj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.o
version-lobj-$(CONFIG_WIN32) += $(BUILD_DIR)/version.lo
######################################################################
# tracing
@@ -112,62 +116,50 @@ qga-vss-dll-obj-y = qga/
# contrib
ivshmem-client-obj-y = contrib/ivshmem-client/
ivshmem-server-obj-y = contrib/ivshmem-server/
libvhost-user-obj-y = contrib/libvhost-user/
######################################################################
trace-events-subdirs =
trace-events-subdirs += util
trace-events-subdirs += crypto
trace-events-subdirs += io
trace-events-subdirs += migration
trace-events-subdirs += block
trace-events-subdirs += backends
trace-events-subdirs += hw/block
trace-events-subdirs += hw/block/dataplane
trace-events-subdirs += hw/char
trace-events-subdirs += hw/intc
trace-events-subdirs += hw/net
trace-events-subdirs += hw/virtio
trace-events-subdirs += hw/audio
trace-events-subdirs += hw/misc
trace-events-subdirs += hw/usb
trace-events-subdirs += hw/scsi
trace-events-subdirs += hw/nvram
trace-events-subdirs += hw/display
trace-events-subdirs += hw/input
trace-events-subdirs += hw/timer
trace-events-subdirs += hw/dma
trace-events-subdirs += hw/sparc
trace-events-subdirs += hw/sd
trace-events-subdirs += hw/isa
trace-events-subdirs += hw/mem
trace-events-subdirs += hw/i386
trace-events-subdirs += hw/i386/xen
trace-events-subdirs += hw/9pfs
trace-events-subdirs += hw/ppc
trace-events-subdirs += hw/pci
trace-events-subdirs += hw/s390x
trace-events-subdirs += hw/vfio
trace-events-subdirs += hw/acpi
trace-events-subdirs += hw/arm
trace-events-subdirs += hw/alpha
trace-events-subdirs += hw/xen
trace-events-subdirs += ui
trace-events-subdirs += audio
trace-events-subdirs += net
trace-events-subdirs += target/arm
trace-events-subdirs += target/i386
trace-events-subdirs += target/sparc
trace-events-subdirs += target/s390x
trace-events-subdirs += target/ppc
trace-events-subdirs += qom
trace-events-subdirs += linux-user
trace-events-subdirs += qapi
trace-events-files = $(SRC_PATH)/trace-events $(trace-events-subdirs:%=$(SRC_PATH)/%/trace-events)
trace-obj-y = trace-root.o
trace-obj-y += $(trace-events-subdirs:%=%/trace.o)
trace-obj-$(CONFIG_TRACE_UST) += trace-ust-all.o
trace-obj-$(CONFIG_TRACE_DTRACE) += trace-dtrace-root.o
trace-obj-$(CONFIG_TRACE_DTRACE) += $(trace-events-subdirs:%=%/trace-dtrace.o)
trace-events-y = trace-events
trace-events-y += util/trace-events
trace-events-y += crypto/trace-events
trace-events-y += io/trace-events
trace-events-y += migration/trace-events
trace-events-y += block/trace-events
trace-events-y += hw/block/trace-events
trace-events-y += hw/char/trace-events
trace-events-y += hw/intc/trace-events
trace-events-y += hw/net/trace-events
trace-events-y += hw/virtio/trace-events
trace-events-y += hw/audio/trace-events
trace-events-y += hw/misc/trace-events
trace-events-y += hw/usb/trace-events
trace-events-y += hw/scsi/trace-events
trace-events-y += hw/nvram/trace-events
trace-events-y += hw/display/trace-events
trace-events-y += hw/input/trace-events
trace-events-y += hw/timer/trace-events
trace-events-y += hw/dma/trace-events
trace-events-y += hw/sparc/trace-events
trace-events-y += hw/sd/trace-events
trace-events-y += hw/isa/trace-events
trace-events-y += hw/mem/trace-events
trace-events-y += hw/i386/trace-events
trace-events-y += hw/9pfs/trace-events
trace-events-y += hw/ppc/trace-events
trace-events-y += hw/pci/trace-events
trace-events-y += hw/s390x/trace-events
trace-events-y += hw/vfio/trace-events
trace-events-y += hw/acpi/trace-events
trace-events-y += hw/arm/trace-events
trace-events-y += hw/alpha/trace-events
trace-events-y += ui/trace-events
trace-events-y += audio/trace-events
trace-events-y += net/trace-events
trace-events-y += target-arm/trace-events
trace-events-y += target-i386/trace-events
trace-events-y += target-sparc/trace-events
trace-events-y += target-s390x/trace-events
trace-events-y += target-ppc/trace-events
trace-events-y += qom/trace-events
trace-events-y += linux-user/trace-events
trace-events-y += qapi/trace-events

View File

@@ -11,7 +11,7 @@ $(call set-vpath, $(SRC_PATH):$(BUILD_DIR))
ifdef CONFIG_LINUX
QEMU_CFLAGS += -I../linux-headers
endif
QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target/$(TARGET_BASE_ARCH) -DNEED_CPU_H
QEMU_CFLAGS += -I.. -I$(SRC_PATH)/target-$(TARGET_BASE_ARCH) -DNEED_CPU_H
QEMU_CFLAGS+=-I$(SRC_PATH)/include
@@ -50,7 +50,6 @@ endif
$(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all
$(call quiet-command,$(TRACETOOL) \
--group=all \
--format=stap \
--backends=$(TRACE_BACKENDS) \
--binary=$(bindir)/$(QEMU_PROG) \
@@ -60,7 +59,6 @@ $(QEMU_PROG).stp-installed: $(BUILD_DIR)/trace-events-all
$(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all
$(call quiet-command,$(TRACETOOL) \
--group=all \
--format=stap \
--backends=$(TRACE_BACKENDS) \
--binary=$(realpath .)/$(QEMU_PROG) \
@@ -70,7 +68,6 @@ $(QEMU_PROG).stp: $(BUILD_DIR)/trace-events-all
$(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all
$(call quiet-command,$(TRACETOOL) \
--group=all \
--format=simpletrace-stap \
--backends=$(TRACE_BACKENDS) \
--probe-prefix=qemu.$(TARGET_TYPE).$(TARGET_NAME) \
@@ -79,7 +76,6 @@ $(QEMU_PROG)-simpletrace.stp: $(BUILD_DIR)/trace-events-all
else
stap:
endif
.PHONY: stap
all: $(PROGS) stap
@@ -96,11 +92,10 @@ obj-$(CONFIG_TCG_INTERPRETER) += tci.o
obj-y += tcg/tcg-common.o
obj-$(CONFIG_TCG_INTERPRETER) += disas/tci.o
obj-y += fpu/softfloat.o
obj-y += target/$(TARGET_BASE_ARCH)/
obj-y += target-$(TARGET_BASE_ARCH)/
obj-y += disas.o
obj-y += tcg-runtime.o
obj-$(call notempty,$(TARGET_XML_FILES)) += gdbstub-xml.o
obj-$(call lnot,$(CONFIG_HAX)) += hax-stub.o
obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o
obj-$(CONFIG_LIBDECNUMBER) += libdecnumber/decContext.o
@@ -119,7 +114,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/linux-user/$(TARGET_ABI_DIR) \
-I$(SRC_PATH)/linux-user
obj-y += linux-user/
obj-y += gdbstub.o thunk.o user-exec.o user-exec-stub.o
obj-y += gdbstub.o thunk.o user-exec.o
endif #CONFIG_LINUX_USER
@@ -132,7 +127,7 @@ QEMU_CFLAGS+=-I$(SRC_PATH)/bsd-user -I$(SRC_PATH)/bsd-user/$(TARGET_ABI_DIR) \
-I$(SRC_PATH)/bsd-user/$(HOST_VARIANT_DIR)
obj-y += bsd-user/
obj-y += gdbstub.o user-exec.o user-exec-stub.o
obj-y += gdbstub.o user-exec.o
endif #CONFIG_BSD_USER
@@ -175,36 +170,31 @@ all-obj-y := $(obj-y)
target-obj-y :=
block-obj-y :=
common-obj-y :=
chardev-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 \
chardev-obj-y \
crypto-obj-y \
crypto-aes-obj-y \
qom-obj-y \
io-obj-y \
common-obj-y \
common-obj-m \
trace-obj-y)
common-obj-m)
target-obj-y := $(target-obj-y-save)
all-obj-y += $(common-obj-y)
all-obj-y += $(target-obj-y)
all-obj-y += $(qom-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y) $(chardev-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(block-obj-y)
all-obj-$(CONFIG_USER_ONLY) += $(crypto-aes-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(crypto-obj-y)
all-obj-$(CONFIG_SOFTMMU) += $(io-obj-y)
$(QEMU_PROG_BUILD): config-devices.mak
COMMON_LDADDS = $(trace-obj-y) ../libqemuutil.a ../libqemustub.a
# build either PROG or PROGW
$(QEMU_PROG_BUILD): $(all-obj-y) $(COMMON_LDADDS)
$(QEMU_PROG_BUILD): $(all-obj-y) ../libqemuutil.a ../libqemustub.a
$(call LINK, $(filter-out %.mak, $^))
ifdef CONFIG_DARWIN
$(call quiet-command,Rez -append $(SRC_PATH)/pc-bios/qemu.rsrc -o $@,"REZ","$(TARGET_DIR)$@")

1
README
View File

@@ -45,7 +45,6 @@ of other UNIX targets. The simple steps to build QEMU are:
Additional information can also be found online via the QEMU website:
http://qemu-project.org/Hosts/Linux
http://qemu-project.org/Hosts/Mac
http://qemu-project.org/Hosts/W32

View File

@@ -1 +1 @@
2.8.50
2.8.1.1

View File

@@ -16,10 +16,8 @@
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "block/block.h"
#include "qemu/rcu_queue.h"
#include "qemu/queue.h"
#include "qemu/sockets.h"
#include "qemu/cutils.h"
#include "trace.h"
#ifdef CONFIG_EPOLL_CREATE1
#include <sys/epoll.h>
#endif
@@ -29,9 +27,6 @@ struct AioHandler
GPollFD pfd;
IOHandler *io_read;
IOHandler *io_write;
AioPollFn *io_poll;
IOHandler *io_poll_begin;
IOHandler *io_poll_end;
int deleted;
void *opaque;
bool is_external;
@@ -66,7 +61,7 @@ static bool aio_epoll_try_enable(AioContext *ctx)
AioHandler *node;
struct epoll_event event;
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
int r;
if (node->deleted || !node->pfd.events) {
continue;
@@ -205,61 +200,47 @@ void aio_set_fd_handler(AioContext *ctx,
bool is_external,
IOHandler *io_read,
IOHandler *io_write,
AioPollFn *io_poll,
void *opaque)
{
AioHandler *node;
bool is_new = false;
bool deleted = false;
qemu_lockcnt_lock(&ctx->list_lock);
node = find_aio_handler(ctx, fd);
/* Are we deleting the fd handler? */
if (!io_read && !io_write && !io_poll) {
if (!io_read && !io_write) {
if (node == NULL) {
qemu_lockcnt_unlock(&ctx->list_lock);
return;
}
g_source_remove_poll(&ctx->source, &node->pfd);
/* If the lock is held, just mark the node as deleted */
if (qemu_lockcnt_count(&ctx->list_lock)) {
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 while
* no one is walking the handlers list.
* deleted because deleted nodes are only cleaned up after
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
deleted = true;
}
if (!node->io_poll) {
ctx->poll_disable_cnt--;
}
} else {
if (node == NULL) {
/* Alloc and insert if it's not already there */
node = g_new0(AioHandler, 1);
node->pfd.fd = fd;
QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, node, node);
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
g_source_add_poll(&ctx->source, &node->pfd);
is_new = true;
ctx->poll_disable_cnt += !io_poll;
} else {
ctx->poll_disable_cnt += !io_poll - !node->io_poll;
}
/* Update handler with latest information */
node->io_read = io_read;
node->io_write = io_write;
node->io_poll = io_poll;
node->opaque = opaque;
node->is_external = is_external;
@@ -268,127 +249,72 @@ void aio_set_fd_handler(AioContext *ctx,
}
aio_epoll_update(ctx, node, is_new);
qemu_lockcnt_unlock(&ctx->list_lock);
aio_notify(ctx);
if (deleted) {
g_free(node);
}
}
void aio_set_fd_poll(AioContext *ctx, int fd,
IOHandler *io_poll_begin,
IOHandler *io_poll_end)
{
AioHandler *node = find_aio_handler(ctx, fd);
if (!node) {
return;
}
node->io_poll_begin = io_poll_begin;
node->io_poll_end = io_poll_end;
}
void aio_set_event_notifier(AioContext *ctx,
EventNotifier *notifier,
bool is_external,
EventNotifierHandler *io_read,
AioPollFn *io_poll)
EventNotifierHandler *io_read)
{
aio_set_fd_handler(ctx, event_notifier_get_fd(notifier), is_external,
(IOHandler *)io_read, NULL, io_poll, notifier);
aio_set_fd_handler(ctx, event_notifier_get_fd(notifier),
is_external, (IOHandler *)io_read, NULL, notifier);
}
void aio_set_event_notifier_poll(AioContext *ctx,
EventNotifier *notifier,
EventNotifierHandler *io_poll_begin,
EventNotifierHandler *io_poll_end)
{
aio_set_fd_poll(ctx, event_notifier_get_fd(notifier),
(IOHandler *)io_poll_begin,
(IOHandler *)io_poll_end);
}
static void poll_set_started(AioContext *ctx, bool started)
{
AioHandler *node;
if (started == ctx->poll_started) {
return;
}
ctx->poll_started = started;
qemu_lockcnt_inc(&ctx->list_lock);
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
IOHandler *fn;
if (node->deleted) {
continue;
}
if (started) {
fn = node->io_poll_begin;
} else {
fn = node->io_poll_end;
}
if (fn) {
fn(node->opaque);
}
}
qemu_lockcnt_dec(&ctx->list_lock);
}
bool aio_prepare(AioContext *ctx)
{
/* Poll mode cannot be used with glib's event loop, disable it. */
poll_set_started(ctx, false);
return false;
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
bool result = false;
/*
* We have to walk very carefully in case aio_set_fd_handler is
* called while we're walking.
*/
qemu_lockcnt_inc(&ctx->list_lock);
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
int revents;
revents = node->pfd.revents & node->pfd.events;
if (revents & (G_IO_IN | G_IO_HUP | G_IO_ERR) && node->io_read &&
aio_node_check(ctx, node->is_external)) {
result = true;
break;
return true;
}
if (revents & (G_IO_OUT | G_IO_ERR) && node->io_write &&
aio_node_check(ctx, node->is_external)) {
result = true;
break;
return true;
}
}
qemu_lockcnt_dec(&ctx->list_lock);
return result;
return false;
}
static bool aio_dispatch_handlers(AioContext *ctx)
bool aio_dispatch(AioContext *ctx)
{
AioHandler *node, *tmp;
AioHandler *node;
bool progress = false;
QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) {
/*
* 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
* called while we're walking.
*/
node = QLIST_FIRST(&ctx->aio_handlers);
while (node) {
AioHandler *tmp;
int revents;
ctx->walking_handlers++;
revents = node->pfd.revents & node->pfd.events;
node->pfd.revents = 0;
@@ -411,28 +337,23 @@ static bool aio_dispatch_handlers(AioContext *ctx)
progress = true;
}
if (node->deleted) {
if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
QLIST_REMOVE(node, node);
g_free(node);
qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
/* Run our timers */
progress |= timerlistgroup_run_timers(&ctx->tlg);
return progress;
}
void aio_dispatch(AioContext *ctx)
{
qemu_lockcnt_inc(&ctx->list_lock);
aio_bh_poll(ctx);
aio_dispatch_handlers(ctx);
qemu_lockcnt_dec(&ctx->list_lock);
timerlistgroup_run_timers(&ctx->tlg);
}
/* These thread-local variables are used only in a small part of aio_poll
* around the call to the poll() system call. In particular they are not
* used while aio_poll is performing callbacks, which makes it much easier
@@ -479,101 +400,15 @@ static void add_pollfd(AioHandler *node)
npfd++;
}
static bool run_poll_handlers_once(AioContext *ctx)
{
bool progress = false;
AioHandler *node;
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->io_poll &&
aio_node_check(ctx, node->is_external) &&
node->io_poll(node->opaque)) {
progress = true;
}
/* Caller handles freeing deleted nodes. Don't do it here. */
}
return progress;
}
/* run_poll_handlers:
* @ctx: the AioContext
* @max_ns: maximum time to poll for, in nanoseconds
*
* Polls for a given time.
*
* Note that ctx->notify_me must be non-zero so this function can detect
* aio_notify().
*
* Note that the caller must have incremented ctx->list_lock.
*
* Returns: true if progress was made, false otherwise
*/
static bool run_poll_handlers(AioContext *ctx, int64_t max_ns)
{
bool progress;
int64_t end_time;
assert(ctx->notify_me);
assert(qemu_lockcnt_count(&ctx->list_lock) > 0);
assert(ctx->poll_disable_cnt == 0);
trace_run_poll_handlers_begin(ctx, max_ns);
end_time = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) + max_ns;
do {
progress = run_poll_handlers_once(ctx);
} while (!progress && qemu_clock_get_ns(QEMU_CLOCK_REALTIME) < end_time);
trace_run_poll_handlers_end(ctx, progress);
return progress;
}
/* try_poll_mode:
* @ctx: the AioContext
* @blocking: busy polling is only attempted when blocking is true
*
* ctx->notify_me must be non-zero so this function can detect aio_notify().
*
* Note that the caller must have incremented ctx->list_lock.
*
* Returns: true if progress was made, false otherwise
*/
static bool try_poll_mode(AioContext *ctx, bool blocking)
{
if (blocking && ctx->poll_max_ns && ctx->poll_disable_cnt == 0) {
/* See qemu_soonest_timeout() uint64_t hack */
int64_t max_ns = MIN((uint64_t)aio_compute_timeout(ctx),
(uint64_t)ctx->poll_ns);
if (max_ns) {
poll_set_started(ctx, true);
if (run_poll_handlers(ctx, max_ns)) {
return true;
}
}
}
poll_set_started(ctx, false);
/* Even if we don't run busy polling, try polling once in case it can make
* progress and the caller will be able to avoid ppoll(2)/epoll_wait(2).
*/
return run_poll_handlers_once(ctx);
}
bool aio_poll(AioContext *ctx, bool blocking)
{
AioHandler *node;
int i;
int ret = 0;
int i, ret;
bool progress;
int64_t timeout;
int64_t start = 0;
aio_context_acquire(ctx);
progress = false;
/* aio_notify can avoid the expensive event_notifier_set if
* everything (file descriptors, bottom halves, timers) will
@@ -586,86 +421,43 @@ bool aio_poll(AioContext *ctx, bool blocking)
atomic_add(&ctx->notify_me, 2);
}
qemu_lockcnt_inc(&ctx->list_lock);
ctx->walking_handlers++;
if (ctx->poll_max_ns) {
start = qemu_clock_get_ns(QEMU_CLOCK_REALTIME);
}
assert(npfd == 0);
progress = try_poll_mode(ctx, blocking);
if (!progress) {
assert(npfd == 0);
/* fill pollfds */
/* fill pollfds */
if (!aio_epoll_enabled(ctx)) {
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->pfd.events
&& aio_node_check(ctx, node->is_external)) {
add_pollfd(node);
}
if (!aio_epoll_enabled(ctx)) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->pfd.events
&& aio_node_check(ctx, node->is_external)) {
add_pollfd(node);
}
}
timeout = blocking ? aio_compute_timeout(ctx) : 0;
/* wait until next event */
if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
AioHandler epoll_handler;
epoll_handler.pfd.fd = ctx->epollfd;
epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR;
npfd = 0;
add_pollfd(&epoll_handler);
ret = aio_epoll(ctx, pollfds, npfd, timeout);
} else {
ret = qemu_poll_ns(pollfds, npfd, timeout);
}
}
timeout = blocking ? aio_compute_timeout(ctx) : 0;
/* wait until next event */
if (timeout) {
aio_context_release(ctx);
}
if (aio_epoll_check_poll(ctx, pollfds, npfd, timeout)) {
AioHandler epoll_handler;
epoll_handler.pfd.fd = ctx->epollfd;
epoll_handler.pfd.events = G_IO_IN | G_IO_OUT | G_IO_HUP | G_IO_ERR;
npfd = 0;
add_pollfd(&epoll_handler);
ret = aio_epoll(ctx, pollfds, npfd, timeout);
} else {
ret = qemu_poll_ns(pollfds, npfd, timeout);
}
if (blocking) {
atomic_sub(&ctx->notify_me, 2);
}
/* Adjust polling time */
if (ctx->poll_max_ns) {
int64_t block_ns = qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start;
if (block_ns <= ctx->poll_ns) {
/* This is the sweet spot, no adjustment needed */
} else if (block_ns > ctx->poll_max_ns) {
/* We'd have to poll for too long, poll less */
int64_t old = ctx->poll_ns;
if (ctx->poll_shrink) {
ctx->poll_ns /= ctx->poll_shrink;
} else {
ctx->poll_ns = 0;
}
trace_poll_shrink(ctx, old, ctx->poll_ns);
} else if (ctx->poll_ns < ctx->poll_max_ns &&
block_ns < ctx->poll_max_ns) {
/* There is room to grow, poll longer */
int64_t old = ctx->poll_ns;
int64_t grow = ctx->poll_grow;
if (grow == 0) {
grow = 2;
}
if (ctx->poll_ns) {
ctx->poll_ns *= grow;
} else {
ctx->poll_ns = 4000; /* start polling at 4 microseconds */
}
if (ctx->poll_ns > ctx->poll_max_ns) {
ctx->poll_ns = ctx->poll_max_ns;
}
trace_poll_grow(ctx, old, ctx->poll_ns);
}
if (timeout) {
aio_context_acquire(ctx);
}
aio_notify_accept(ctx);
@@ -678,29 +470,20 @@ bool aio_poll(AioContext *ctx, bool blocking)
}
npfd = 0;
ctx->walking_handlers--;
progress |= aio_bh_poll(ctx);
if (ret > 0) {
progress |= aio_dispatch_handlers(ctx);
/* Run dispatch even if there were no readable fds to run timers */
if (aio_dispatch(ctx)) {
progress = true;
}
qemu_lockcnt_dec(&ctx->list_lock);
progress |= timerlistgroup_run_timers(&ctx->tlg);
aio_context_release(ctx);
return progress;
}
void aio_context_setup(AioContext *ctx)
{
/* TODO remove this in final patch submission */
if (getenv("QEMU_AIO_POLL_MAX_NS")) {
fprintf(stderr, "The QEMU_AIO_POLL_MAX_NS environment variable has "
"been replaced with -object iothread,poll-max-ns=NUM\n");
exit(1);
}
#ifdef CONFIG_EPOLL_CREATE1
assert(!ctx->epollfd);
ctx->epollfd = epoll_create1(EPOLL_CLOEXEC);
@@ -712,17 +495,3 @@ void aio_context_setup(AioContext *ctx)
}
#endif
}
void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
int64_t grow, int64_t shrink, Error **errp)
{
/* No thread synchronization here, it doesn't matter if an incorrect value
* is used once.
*/
ctx->poll_max_ns = max_ns;
ctx->poll_ns = 0;
ctx->poll_grow = grow;
ctx->poll_shrink = shrink;
aio_notify(ctx);
}

View File

@@ -20,8 +20,6 @@
#include "block/block.h"
#include "qemu/queue.h"
#include "qemu/sockets.h"
#include "qapi/error.h"
#include "qemu/rcu_queue.h"
struct AioHandler {
EventNotifier *e;
@@ -40,13 +38,11 @@ void aio_set_fd_handler(AioContext *ctx,
bool is_external,
IOHandler *io_read,
IOHandler *io_write,
AioPollFn *io_poll,
void *opaque)
{
/* fd is a SOCKET in our case */
AioHandler *node;
qemu_lockcnt_lock(&ctx->list_lock);
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->pfd.fd == fd && !node->deleted) {
break;
@@ -56,14 +52,14 @@ void aio_set_fd_handler(AioContext *ctx,
/* Are we deleting the fd handler? */
if (!io_read && !io_write) {
if (node) {
/* If aio_poll is in progress, just mark the node as deleted */
if (qemu_lockcnt_count(&ctx->list_lock)) {
/* 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 list_lock.
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
g_free(node);
@@ -76,7 +72,7 @@ void aio_set_fd_handler(AioContext *ctx,
/* Alloc and insert if it's not already there */
node = g_new0(AioHandler, 1);
node->pfd.fd = fd;
QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, node, node);
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
}
node->pfd.events = 0;
@@ -101,26 +97,16 @@ void aio_set_fd_handler(AioContext *ctx,
FD_CONNECT | FD_WRITE | FD_OOB);
}
qemu_lockcnt_unlock(&ctx->list_lock);
aio_notify(ctx);
}
void aio_set_fd_poll(AioContext *ctx, int fd,
IOHandler *io_poll_begin,
IOHandler *io_poll_end)
{
/* Not implemented */
}
void aio_set_event_notifier(AioContext *ctx,
EventNotifier *e,
bool is_external,
EventNotifierHandler *io_notify,
AioPollFn *io_poll)
EventNotifierHandler *io_notify)
{
AioHandler *node;
qemu_lockcnt_lock(&ctx->list_lock);
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->e == e && !node->deleted) {
break;
@@ -132,14 +118,14 @@ void aio_set_event_notifier(AioContext *ctx,
if (node) {
g_source_remove_poll(&ctx->source, &node->pfd);
/* aio_poll is in progress, just mark the node as deleted */
if (qemu_lockcnt_count(&ctx->list_lock)) {
/* 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 list_lock.
* releasing the walking_handlers lock.
*/
QLIST_REMOVE(node, node);
g_free(node);
@@ -153,7 +139,7 @@ void aio_set_event_notifier(AioContext *ctx,
node->pfd.fd = (uintptr_t)event_notifier_get_handle(e);
node->pfd.events = G_IO_IN;
node->is_external = is_external;
QLIST_INSERT_HEAD_RCU(&ctx->aio_handlers, node, node);
QLIST_INSERT_HEAD(&ctx->aio_handlers, node, node);
g_source_add_poll(&ctx->source, &node->pfd);
}
@@ -161,18 +147,9 @@ void aio_set_event_notifier(AioContext *ctx,
node->io_notify = io_notify;
}
qemu_lockcnt_unlock(&ctx->list_lock);
aio_notify(ctx);
}
void aio_set_event_notifier_poll(AioContext *ctx,
EventNotifier *notifier,
EventNotifierHandler *io_poll_begin,
EventNotifierHandler *io_poll_end)
{
/* Not implemented */
}
bool aio_prepare(AioContext *ctx)
{
static struct timeval tv0;
@@ -180,16 +157,10 @@ bool aio_prepare(AioContext *ctx)
bool have_select_revents = false;
fd_set rfds, wfds;
/*
* We have to walk very carefully in case aio_set_fd_handler is
* called while we're walking.
*/
qemu_lockcnt_inc(&ctx->list_lock);
/* fill fd sets */
FD_ZERO(&rfds);
FD_ZERO(&wfds);
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->io_read) {
FD_SET ((SOCKET)node->pfd.fd, &rfds);
}
@@ -199,7 +170,7 @@ bool aio_prepare(AioContext *ctx)
}
if (select(0, &rfds, &wfds, NULL, &tv0) > 0) {
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
node->pfd.revents = 0;
if (FD_ISSET(node->pfd.fd, &rfds)) {
node->pfd.revents |= G_IO_IN;
@@ -213,53 +184,45 @@ bool aio_prepare(AioContext *ctx)
}
}
qemu_lockcnt_dec(&ctx->list_lock);
return have_select_revents;
}
bool aio_pending(AioContext *ctx)
{
AioHandler *node;
bool result = false;
/*
* We have to walk very carefully in case aio_set_fd_handler is
* called while we're walking.
*/
qemu_lockcnt_inc(&ctx->list_lock);
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (node->pfd.revents && node->io_notify) {
result = true;
break;
return true;
}
if ((node->pfd.revents & G_IO_IN) && node->io_read) {
result = true;
break;
return true;
}
if ((node->pfd.revents & G_IO_OUT) && node->io_write) {
result = true;
break;
return true;
}
}
qemu_lockcnt_dec(&ctx->list_lock);
return result;
return false;
}
static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
{
AioHandler *node;
bool progress = false;
AioHandler *tmp;
/*
* We have to walk very carefully in case aio_set_fd_handler is
* called while we're walking.
*/
QLIST_FOREACH_SAFE_RCU(node, &ctx->aio_handlers, node, tmp) {
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) {
@@ -294,25 +257,28 @@ static bool aio_dispatch_handlers(AioContext *ctx, HANDLE event)
}
}
if (node->deleted) {
if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
QLIST_REMOVE(node, node);
g_free(node);
qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
}
tmp = node;
node = QLIST_NEXT(node, node);
ctx->walking_handlers--;
if (!ctx->walking_handlers && tmp->deleted) {
QLIST_REMOVE(tmp, node);
g_free(tmp);
}
}
return progress;
}
void aio_dispatch(AioContext *ctx)
bool aio_dispatch(AioContext *ctx)
{
qemu_lockcnt_inc(&ctx->list_lock);
aio_bh_poll(ctx);
aio_dispatch_handlers(ctx, INVALID_HANDLE_VALUE);
qemu_lockcnt_dec(&ctx->list_lock);
timerlistgroup_run_timers(&ctx->tlg);
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)
@@ -323,6 +289,7 @@ bool aio_poll(AioContext *ctx, bool blocking)
int count;
int timeout;
aio_context_acquire(ctx);
progress = false;
/* aio_notify can avoid the expensive event_notifier_set if
@@ -336,18 +303,20 @@ bool aio_poll(AioContext *ctx, bool blocking)
atomic_add(&ctx->notify_me, 2);
}
qemu_lockcnt_inc(&ctx->list_lock);
have_select_revents = aio_prepare(ctx);
ctx->walking_handlers++;
/* fill fd sets */
count = 0;
QLIST_FOREACH_RCU(node, &ctx->aio_handlers, node) {
QLIST_FOREACH(node, &ctx->aio_handlers, node) {
if (!node->deleted && node->io_notify
&& aio_node_check(ctx, node->is_external)) {
events[count++] = event_notifier_get_handle(node->e);
}
}
ctx->walking_handlers--;
first = true;
/* ctx->notifier is always registered. */
@@ -363,11 +332,17 @@ bool aio_poll(AioContext *ctx, bool blocking)
timeout = blocking && !have_select_revents
? qemu_timeout_ns_to_ms(aio_compute_timeout(ctx)) : 0;
if (timeout) {
aio_context_release(ctx);
}
ret = WaitForMultipleObjects(count, events, FALSE, timeout);
if (blocking) {
assert(first);
atomic_sub(&ctx->notify_me, 2);
}
if (timeout) {
aio_context_acquire(ctx);
}
if (first) {
aio_notify_accept(ctx);
@@ -390,18 +365,12 @@ bool aio_poll(AioContext *ctx, bool blocking)
progress |= aio_dispatch_handlers(ctx, event);
} while (count > 0);
qemu_lockcnt_dec(&ctx->list_lock);
progress |= timerlistgroup_run_timers(&ctx->tlg);
aio_context_release(ctx);
return progress;
}
void aio_context_setup(AioContext *ctx)
{
}
void aio_context_set_poll_params(AioContext *ctx, int64_t max_ns,
int64_t grow, int64_t shrink, Error **errp)
{
error_setg(errp, "AioContext polling is not implemented on Windows");
}

View File

@@ -28,6 +28,7 @@
#include "sysemu/arch_init.h"
#include "hw/pci/pci.h"
#include "hw/audio/audio.h"
#include "hw/smbios/smbios.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qmp-commands.h"
@@ -63,8 +64,6 @@ int graphic_depth = 32;
#define QEMU_ARCH QEMU_ARCH_MIPS
#elif defined(TARGET_MOXIE)
#define QEMU_ARCH QEMU_ARCH_MOXIE
#elif defined(TARGET_NIOS2)
#define QEMU_ARCH QEMU_ARCH_NIOS2
#elif defined(TARGET_OPENRISC)
#define QEMU_ARCH QEMU_ARCH_OPENRISC
#elif defined(TARGET_PPC)
@@ -85,6 +84,33 @@ int graphic_depth = 32;
const uint32_t arch_type = QEMU_ARCH;
static struct defconfig_file {
const char *filename;
/* Indicates it is an user config file (disabled by -no-user-config) */
bool userconfig;
} default_config_files[] = {
{ CONFIG_QEMU_CONFDIR "/qemu.conf", true },
{ NULL }, /* end of list */
};
int qemu_read_default_config_files(bool userconfig)
{
int ret;
struct defconfig_file *f;
for (f = default_config_files; f->filename; f++) {
if (!userconfig && f->userconfig) {
continue;
}
ret = qemu_read_config_file(f->filename);
if (ret < 0 && ret != -ENOENT) {
return ret;
}
}
return 0;
}
struct soundhw {
const char *name;
const char *descr;
@@ -209,6 +235,26 @@ void audio_init(void)
}
}
void do_acpitable_option(const QemuOpts *opts)
{
#ifdef TARGET_I386
Error *err = NULL;
acpi_table_add(opts, &err);
if (err) {
error_reportf_err(err, "Wrong acpi table provided: ");
exit(1);
}
#endif
}
void do_smbios_option(QemuOpts *opts)
{
#ifdef TARGET_I386
smbios_entry_add(opts);
#endif
}
int kvm_available(void)
{
#ifdef CONFIG_KVM

View File

@@ -1,8 +1,7 @@
/*
* Data plane event loop
* QEMU System Emulator
*
* Copyright (c) 2003-2008 Fabrice Bellard
* Copyright (c) 2009-2017 QEMU contributors
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
@@ -31,8 +30,6 @@
#include "qemu/main-loop.h"
#include "qemu/atomic.h"
#include "block/raw-aio.h"
#include "qemu/coroutine_int.h"
#include "trace.h"
/***********************************************************/
/* bottom halves (can be seen as timers which expire ASAP) */
@@ -56,14 +53,14 @@ void aio_bh_schedule_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
.cb = cb,
.opaque = opaque,
};
qemu_lockcnt_lock(&ctx->list_lock);
qemu_mutex_lock(&ctx->bh_lock);
bh->next = ctx->first_bh;
bh->scheduled = 1;
bh->deleted = 1;
/* Make sure that the members are ready before putting bh into list */
smp_wmb();
ctx->first_bh = bh;
qemu_lockcnt_unlock(&ctx->list_lock);
qemu_mutex_unlock(&ctx->bh_lock);
aio_notify(ctx);
}
@@ -76,12 +73,12 @@ QEMUBH *aio_bh_new(AioContext *ctx, QEMUBHFunc *cb, void *opaque)
.cb = cb,
.opaque = opaque,
};
qemu_lockcnt_lock(&ctx->list_lock);
qemu_mutex_lock(&ctx->bh_lock);
bh->next = ctx->first_bh;
/* Make sure that the members are ready before putting bh into list */
smp_wmb();
ctx->first_bh = bh;
qemu_lockcnt_unlock(&ctx->list_lock);
qemu_mutex_unlock(&ctx->bh_lock);
return bh;
}
@@ -90,19 +87,19 @@ void aio_bh_call(QEMUBH *bh)
bh->cb(bh->opaque);
}
/* Multiple occurrences of aio_bh_poll cannot be called concurrently.
* The count in ctx->list_lock is incremented before the call, and is
* not affected by the call.
*/
/* Multiple occurrences of aio_bh_poll cannot be called concurrently */
int aio_bh_poll(AioContext *ctx)
{
QEMUBH *bh, **bhp, *next;
int ret;
bool deleted = false;
ctx->walking_bh++;
ret = 0;
for (bh = atomic_rcu_read(&ctx->first_bh); bh; bh = next) {
next = atomic_rcu_read(&bh->next);
for (bh = ctx->first_bh; bh; bh = next) {
/* Make sure that fetching bh happens before accessing its members */
smp_read_barrier_depends();
next = bh->next;
/* The atomic_xchg is paired with the one in qemu_bh_schedule. The
* implicit memory barrier ensures that the callback sees all writes
* done by the scheduling thread. It also ensures that the scheduling
@@ -117,17 +114,13 @@ int aio_bh_poll(AioContext *ctx)
bh->idle = 0;
aio_bh_call(bh);
}
if (bh->deleted) {
deleted = true;
}
}
ctx->walking_bh--;
/* remove deleted bhs */
if (!deleted) {
return ret;
}
if (qemu_lockcnt_dec_if_lock(&ctx->list_lock)) {
if (!ctx->walking_bh) {
qemu_mutex_lock(&ctx->bh_lock);
bhp = &ctx->first_bh;
while (*bhp) {
bh = *bhp;
@@ -138,8 +131,9 @@ int aio_bh_poll(AioContext *ctx)
bhp = &bh->next;
}
}
qemu_lockcnt_inc_and_unlock(&ctx->list_lock);
qemu_mutex_unlock(&ctx->bh_lock);
}
return ret;
}
@@ -193,8 +187,7 @@ aio_compute_timeout(AioContext *ctx)
int timeout = -1;
QEMUBH *bh;
for (bh = atomic_rcu_read(&ctx->first_bh); bh;
bh = atomic_rcu_read(&bh->next)) {
for (bh = ctx->first_bh; bh; bh = bh->next) {
if (bh->scheduled) {
if (bh->idle) {
/* idle bottom halves will be polled at least
@@ -277,11 +270,7 @@ aio_ctx_finalize(GSource *source)
}
#endif
assert(QSLIST_EMPTY(&ctx->scheduled_coroutines));
qemu_bh_delete(ctx->co_schedule_bh);
qemu_lockcnt_lock(&ctx->list_lock);
assert(!qemu_lockcnt_count(&ctx->list_lock));
qemu_mutex_lock(&ctx->bh_lock);
while (ctx->first_bh) {
QEMUBH *next = ctx->first_bh->next;
@@ -291,12 +280,12 @@ aio_ctx_finalize(GSource *source)
g_free(ctx->first_bh);
ctx->first_bh = next;
}
qemu_lockcnt_unlock(&ctx->list_lock);
qemu_mutex_unlock(&ctx->bh_lock);
aio_set_event_notifier(ctx, &ctx->notifier, false, NULL, NULL);
aio_set_event_notifier(ctx, &ctx->notifier, false, NULL);
event_notifier_cleanup(&ctx->notifier);
qemu_rec_mutex_destroy(&ctx->lock);
qemu_lockcnt_destroy(&ctx->list_lock);
qemu_mutex_destroy(&ctx->bh_lock);
timerlistgroup_deinit(&ctx->tlg);
}
@@ -360,39 +349,6 @@ static void event_notifier_dummy_cb(EventNotifier *e)
{
}
/* Returns true if aio_notify() was called (e.g. a BH was scheduled) */
static bool event_notifier_poll(void *opaque)
{
EventNotifier *e = opaque;
AioContext *ctx = container_of(e, AioContext, notifier);
return atomic_read(&ctx->notified);
}
static void co_schedule_bh_cb(void *opaque)
{
AioContext *ctx = opaque;
QSLIST_HEAD(, Coroutine) straight, reversed;
QSLIST_MOVE_ATOMIC(&reversed, &ctx->scheduled_coroutines);
QSLIST_INIT(&straight);
while (!QSLIST_EMPTY(&reversed)) {
Coroutine *co = QSLIST_FIRST(&reversed);
QSLIST_REMOVE_HEAD(&reversed, co_scheduled_next);
QSLIST_INSERT_HEAD(&straight, co, co_scheduled_next);
}
while (!QSLIST_EMPTY(&straight)) {
Coroutine *co = QSLIST_FIRST(&straight);
QSLIST_REMOVE_HEAD(&straight, co_scheduled_next);
trace_aio_co_schedule_bh_cb(ctx, co);
aio_context_acquire(ctx);
qemu_coroutine_enter(co);
aio_context_release(ctx);
}
}
AioContext *aio_context_new(Error **errp)
{
int ret;
@@ -407,68 +363,24 @@ AioContext *aio_context_new(Error **errp)
goto fail;
}
g_source_set_can_recurse(&ctx->source, true);
qemu_lockcnt_init(&ctx->list_lock);
ctx->co_schedule_bh = aio_bh_new(ctx, co_schedule_bh_cb, ctx);
QSLIST_INIT(&ctx->scheduled_coroutines);
aio_set_event_notifier(ctx, &ctx->notifier,
false,
(EventNotifierHandler *)
event_notifier_dummy_cb,
event_notifier_poll);
event_notifier_dummy_cb);
#ifdef CONFIG_LINUX_AIO
ctx->linux_aio = NULL;
#endif
ctx->thread_pool = NULL;
qemu_mutex_init(&ctx->bh_lock);
qemu_rec_mutex_init(&ctx->lock);
timerlistgroup_init(&ctx->tlg, aio_timerlist_notify, ctx);
ctx->poll_ns = 0;
ctx->poll_max_ns = 0;
ctx->poll_grow = 0;
ctx->poll_shrink = 0;
return ctx;
fail:
g_source_destroy(&ctx->source);
return NULL;
}
void aio_co_schedule(AioContext *ctx, Coroutine *co)
{
trace_aio_co_schedule(ctx, co);
QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines,
co, co_scheduled_next);
qemu_bh_schedule(ctx->co_schedule_bh);
}
void aio_co_wake(struct Coroutine *co)
{
AioContext *ctx;
/* Read coroutine before co->ctx. Matches smp_wmb in
* qemu_coroutine_enter.
*/
smp_read_barrier_depends();
ctx = atomic_read(&co->ctx);
if (ctx != qemu_get_current_aio_context()) {
aio_co_schedule(ctx, co);
return;
}
if (qemu_in_coroutine()) {
Coroutine *self = qemu_coroutine_self();
assert(self != co);
QSIMPLEQ_INSERT_TAIL(&self->co_queue_wakeup, co, co_queue_next);
} else {
aio_context_acquire(ctx);
qemu_coroutine_enter(co);
aio_context_release(ctx);
}
}
void aio_context_ref(AioContext *ctx)
{
g_source_ref(&ctx->source);

View File

@@ -1,7 +1,7 @@
common-obj-y += rng.o rng-egd.o
common-obj-$(CONFIG_POSIX) += rng-random.o
common-obj-y += msmouse.o wctablet.o testdev.o
common-obj-y += msmouse.o testdev.o
common-obj-$(CONFIG_BRLAPI) += baum.o
baum.o-cflags := $(SDL_CFLAGS)

View File

@@ -27,10 +27,12 @@
#include "sysemu/char.h"
#include "qemu/timer.h"
#include "hw/usb.h"
#include "ui/console.h"
#include <brlapi.h>
#include <brlapi_constants.h>
#include <brlapi_keycodes.h>
#ifdef CONFIG_SDL
#include <SDL_syswm.h>
#endif
#if 0
#define DPRINTF(fmt, ...) \
@@ -85,7 +87,7 @@
#define BUF_SIZE 256
typedef struct {
Chardev parent;
CharDriverState *chr;
brlapi_handle_t *brlapi;
int brlapi_fd;
@@ -98,10 +100,7 @@ typedef struct {
uint8_t out_buf_used, out_buf_ptr;
QEMUTimer *cellCount_timer;
} BaumChardev;
#define TYPE_CHARDEV_BRAILLE "chardev-braille"
#define BAUM_CHARDEV(obj) OBJECT_CHECK(BaumChardev, (obj), TYPE_CHARDEV_BRAILLE)
} BaumDriverState;
/* Let's assume NABCC by default */
enum way {
@@ -226,10 +225,14 @@ static const uint8_t nabcc_translation[2][256] = {
};
/* The guest OS has started discussing with us, finish initializing BrlAPI */
static int baum_deferred_init(BaumChardev *baum)
static int baum_deferred_init(BaumDriverState *baum)
{
int tty = BRLAPI_TTY_DEFAULT;
QemuConsole *con;
#if defined(CONFIG_SDL)
#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
SDL_SysWMinfo info;
#endif
#endif
int tty;
if (baum->deferred_init) {
return 1;
@@ -240,12 +243,21 @@ static int baum_deferred_init(BaumChardev *baum)
return 0;
}
con = qemu_console_lookup_by_index(0);
if (con && qemu_console_is_graphic(con)) {
tty = qemu_console_get_window_id(con);
if (tty == -1)
tty = BRLAPI_TTY_DEFAULT;
#if defined(CONFIG_SDL)
#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
memset(&info, 0, sizeof(info));
SDL_VERSION(&info.version);
if (SDL_GetWMInfo(&info)) {
tty = info.info.x11.wmwindow;
} else {
#endif
#endif
tty = BRLAPI_TTY_DEFAULT;
#if defined(CONFIG_SDL)
#if SDL_COMPILEDVERSION < SDL_VERSIONNUM(2, 0, 0)
}
#endif
#endif
if (brlapi__enterTtyMode(baum->brlapi, tty, NULL) == -1) {
brlapi_perror("baum: brlapi__enterTtyMode");
@@ -256,9 +268,9 @@ static int baum_deferred_init(BaumChardev *baum)
}
/* The serial port can receive more of our data */
static void baum_chr_accept_input(struct Chardev *chr)
static void baum_accept_input(struct CharDriverState *chr)
{
BaumChardev *baum = BAUM_CHARDEV(chr);
BaumDriverState *baum = chr->opaque;
int room, first;
if (!baum->out_buf_used)
@@ -282,25 +294,24 @@ static void baum_chr_accept_input(struct Chardev *chr)
}
/* We want to send a packet */
static void baum_write_packet(BaumChardev *baum, const uint8_t *buf, int len)
static void baum_write_packet(BaumDriverState *baum, const uint8_t *buf, int len)
{
Chardev *chr = CHARDEV(baum);
uint8_t io_buf[1 + 2 * len], *cur = io_buf;
int room;
*cur++ = ESC;
while (len--)
if ((*cur++ = *buf++) == ESC)
*cur++ = ESC;
room = qemu_chr_be_can_write(chr);
room = qemu_chr_be_can_write(baum->chr);
len = cur - io_buf;
if (len <= room) {
/* Fits */
qemu_chr_be_write(chr, io_buf, len);
qemu_chr_be_write(baum->chr, io_buf, len);
} else {
int first;
uint8_t out;
/* Can't fit all, send what can be, and store the rest. */
qemu_chr_be_write(chr, io_buf, room);
qemu_chr_be_write(baum->chr, io_buf, room);
len -= room;
cur = io_buf + room;
if (len > BUF_SIZE - baum->out_buf_used) {
@@ -325,14 +336,14 @@ static void baum_write_packet(BaumChardev *baum, const uint8_t *buf, int len)
/* Called when the other end seems to have a wrong idea of our display size */
static void baum_cellCount_timer_cb(void *opaque)
{
BaumChardev *baum = BAUM_CHARDEV(opaque);
BaumDriverState *baum = opaque;
uint8_t cell_count[] = { BAUM_RSP_CellCount, baum->x * baum->y };
DPRINTF("Timeout waiting for DisplayData, sending cell count\n");
baum_write_packet(baum, cell_count, sizeof(cell_count));
}
/* Try to interpret a whole incoming packet */
static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
static int baum_eat_packet(BaumDriverState *baum, const uint8_t *buf, int len)
{
const uint8_t *cur = buf;
uint8_t req = 0;
@@ -473,9 +484,9 @@ static int baum_eat_packet(BaumChardev *baum, const uint8_t *buf, int len)
}
/* The other end is writing some data. Store it and try to interpret */
static int baum_chr_write(Chardev *chr, const uint8_t *buf, int len)
static int baum_write(CharDriverState *chr, const uint8_t *buf, int len)
{
BaumChardev *baum = BAUM_CHARDEV(chr);
BaumDriverState *baum = chr->opaque;
int tocopy, cur, eaten, orig_len = len;
if (!len)
@@ -514,16 +525,14 @@ static int baum_chr_write(Chardev *chr, const uint8_t *buf, int len)
}
/* Send the key code to the other end */
static void baum_send_key(BaumChardev *baum, uint8_t type, uint8_t value)
{
static void baum_send_key(BaumDriverState *baum, uint8_t type, uint8_t value) {
uint8_t packet[] = { type, value };
DPRINTF("writing key %x %x\n", type, value);
baum_write_packet(baum, packet, sizeof(packet));
}
static void baum_send_key2(BaumChardev *baum, uint8_t type, uint8_t value,
uint8_t value2)
{
static void baum_send_key2(BaumDriverState *baum, uint8_t type, uint8_t value,
uint8_t value2) {
uint8_t packet[] = { type, value, value2 };
DPRINTF("writing key %x %x\n", type, value);
baum_write_packet(baum, packet, sizeof(packet));
@@ -532,7 +541,7 @@ static void baum_send_key2(BaumChardev *baum, uint8_t type, uint8_t value,
/* We got some data on the BrlAPI socket */
static void baum_chr_read(void *opaque)
{
BaumChardev *baum = BAUM_CHARDEV(opaque);
BaumDriverState *baum = opaque;
brlapi_keyCode_t code;
int ret;
if (!baum->brlapi)
@@ -616,25 +625,41 @@ static void baum_chr_read(void *opaque)
}
}
static void char_braille_finalize(Object *obj)
static void baum_free(struct CharDriverState *chr)
{
BaumChardev *baum = BAUM_CHARDEV(obj);
BaumDriverState *baum = chr->opaque;
timer_free(baum->cellCount_timer);
if (baum->brlapi) {
brlapi__closeConnection(baum->brlapi);
g_free(baum->brlapi);
}
g_free(baum);
}
static void baum_chr_open(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
static CharDriverState *chr_baum_init(const char *id,
ChardevBackend *backend,
ChardevReturn *ret,
bool *be_opened,
Error **errp)
{
BaumChardev *baum = BAUM_CHARDEV(chr);
ChardevCommon *common = backend->u.braille.data;
BaumDriverState *baum;
CharDriverState *chr;
brlapi_handle_t *handle;
chr = qemu_chr_alloc(common, errp);
if (!chr) {
return NULL;
}
baum = g_malloc0(sizeof(BaumDriverState));
baum->chr = chr;
chr->opaque = baum;
chr->chr_write = baum_write;
chr->chr_accept_input = baum_accept_input;
chr->chr_free = baum_free;
handle = g_malloc0(brlapi_getHandleSize());
baum->brlapi = handle;
@@ -642,36 +667,27 @@ static void baum_chr_open(Chardev *chr,
if (baum->brlapi_fd == -1) {
error_setg(errp, "brlapi__openConnection: %s",
brlapi_strerror(brlapi_error_location()));
g_free(handle);
return;
goto fail_handle;
}
baum->deferred_init = 0;
baum->cellCount_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, baum_cellCount_timer_cb, baum);
qemu_set_fd_handler(baum->brlapi_fd, baum_chr_read, NULL, baum);
return chr;
fail_handle:
g_free(handle);
g_free(chr);
g_free(baum);
return NULL;
}
static void char_braille_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = baum_chr_open;
cc->chr_write = baum_chr_write;
cc->chr_accept_input = baum_chr_accept_input;
}
static const TypeInfo char_braille_type_info = {
.name = TYPE_CHARDEV_BRAILLE,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(BaumChardev),
.instance_finalize = char_braille_finalize,
.class_init = char_braille_class_init,
};
static void register_types(void)
{
type_register_static(&char_braille_type_info);
register_char_driver("braille", CHARDEV_BACKEND_KIND_BRAILLE, NULL,
chr_baum_init);
}
type_init(register_types);

View File

@@ -94,8 +94,6 @@ static void cryptodev_builtin_init(
backend->conf.max_size = LONG_MAX - sizeof(CryptoDevBackendSymOpInfo);
backend->conf.max_cipher_key_len = CRYPTODEV_BUITLIN_MAX_CIPHER_KEY_LEN;
backend->conf.max_auth_key_len = CRYPTODEV_BUITLIN_MAX_AUTH_KEY_LEN;
cryptodev_backend_set_ready(backend, true);
}
static int
@@ -113,42 +111,23 @@ cryptodev_builtin_get_unused_session_index(
return -1;
}
#define AES_KEYSIZE_128 16
#define AES_KEYSIZE_192 24
#define AES_KEYSIZE_256 32
#define AES_KEYSIZE_128_XTS AES_KEYSIZE_256
#define AES_KEYSIZE_256_XTS 64
static int
cryptodev_builtin_get_aes_algo(uint32_t key_len, int mode, Error **errp)
cryptodev_builtin_get_aes_algo(uint32_t key_len, Error **errp)
{
int algo;
if (key_len == AES_KEYSIZE_128) {
if (key_len == 128 / 8) {
algo = QCRYPTO_CIPHER_ALG_AES_128;
} else if (key_len == AES_KEYSIZE_192) {
} else if (key_len == 192 / 8) {
algo = QCRYPTO_CIPHER_ALG_AES_192;
} else if (key_len == AES_KEYSIZE_256) { /* equals AES_KEYSIZE_128_XTS */
if (mode == QCRYPTO_CIPHER_MODE_XTS) {
algo = QCRYPTO_CIPHER_ALG_AES_128;
} else {
algo = QCRYPTO_CIPHER_ALG_AES_256;
}
} else if (key_len == AES_KEYSIZE_256_XTS) {
if (mode == QCRYPTO_CIPHER_MODE_XTS) {
algo = QCRYPTO_CIPHER_ALG_AES_256;
} else {
goto err;
}
} else if (key_len == 256 / 8) {
algo = QCRYPTO_CIPHER_ALG_AES_256;
} else {
goto err;
error_setg(errp, "Unsupported key length :%u", key_len);
return -1;
}
return algo;
err:
error_setg(errp, "Unsupported key length :%u", key_len);
return -1;
}
static int cryptodev_builtin_create_cipher_session(
@@ -176,48 +155,32 @@ static int cryptodev_builtin_create_cipher_session(
switch (sess_info->cipher_alg) {
case VIRTIO_CRYPTO_CIPHER_AES_ECB:
mode = QCRYPTO_CIPHER_MODE_ECB;
algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
mode, errp);
errp);
if (algo < 0) {
return -1;
}
mode = QCRYPTO_CIPHER_MODE_ECB;
break;
case VIRTIO_CRYPTO_CIPHER_AES_CBC:
mode = QCRYPTO_CIPHER_MODE_CBC;
algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
mode, errp);
errp);
if (algo < 0) {
return -1;
}
mode = QCRYPTO_CIPHER_MODE_CBC;
break;
case VIRTIO_CRYPTO_CIPHER_AES_CTR:
algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
errp);
if (algo < 0) {
return -1;
}
mode = QCRYPTO_CIPHER_MODE_CTR;
algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
mode, errp);
if (algo < 0) {
return -1;
}
break;
case VIRTIO_CRYPTO_CIPHER_AES_XTS:
mode = QCRYPTO_CIPHER_MODE_XTS;
algo = cryptodev_builtin_get_aes_algo(sess_info->key_len,
mode, errp);
if (algo < 0) {
return -1;
}
break;
case VIRTIO_CRYPTO_CIPHER_3DES_ECB:
case VIRTIO_CRYPTO_CIPHER_DES_ECB:
algo = QCRYPTO_CIPHER_ALG_DES_RFB;
mode = QCRYPTO_CIPHER_MODE_ECB;
algo = QCRYPTO_CIPHER_ALG_3DES;
break;
case VIRTIO_CRYPTO_CIPHER_3DES_CBC:
mode = QCRYPTO_CIPHER_MODE_CBC;
algo = QCRYPTO_CIPHER_ALG_3DES;
break;
case VIRTIO_CRYPTO_CIPHER_3DES_CTR:
mode = QCRYPTO_CIPHER_MODE_CTR;
algo = QCRYPTO_CIPHER_ALG_3DES;
break;
default:
error_setg(errp, "Unsupported cipher alg :%u",
@@ -368,8 +331,6 @@ static void cryptodev_builtin_cleanup(
backend->conf.peers.ccs[i] = NULL;
}
}
cryptodev_backend_set_ready(backend, false);
}
static void

View File

@@ -73,6 +73,8 @@ void cryptodev_backend_cleanup(
if (bc->cleanup) {
bc->cleanup(backend, errp);
}
backend->ready = false;
}
int64_t cryptodev_backend_sym_create_session(
@@ -187,39 +189,14 @@ cryptodev_backend_complete(UserCreatable *uc, Error **errp)
goto out;
}
}
backend->ready = true;
return;
out:
backend->ready = false;
error_propagate(errp, local_err);
}
void cryptodev_backend_set_used(CryptoDevBackend *backend, bool used)
{
backend->is_used = used;
}
bool cryptodev_backend_is_used(CryptoDevBackend *backend)
{
return backend->is_used;
}
void cryptodev_backend_set_ready(CryptoDevBackend *backend, bool ready)
{
backend->ready = ready;
}
bool cryptodev_backend_is_ready(CryptoDevBackend *backend)
{
return backend->ready;
}
static bool
cryptodev_backend_can_be_deleted(UserCreatable *uc, Error **errp)
{
return !cryptodev_backend_is_used(CRYPTODEV_BACKEND(uc));
}
static void cryptodev_backend_instance_init(Object *obj)
{
object_property_add(obj, "queues", "int",
@@ -232,9 +209,7 @@ static void cryptodev_backend_instance_init(Object *obj)
static void cryptodev_backend_finalize(Object *obj)
{
CryptoDevBackend *backend = CRYPTODEV_BACKEND(obj);
cryptodev_backend_cleanup(backend, NULL);
}
static void
@@ -243,7 +218,6 @@ cryptodev_backend_class_init(ObjectClass *oc, void *data)
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
ucc->complete = cryptodev_backend_complete;
ucc->can_be_deleted = cryptodev_backend_can_be_deleted;
QTAILQ_INIT(&crypto_clients);
}

View File

@@ -348,24 +348,6 @@ host_memory_backend_can_be_deleted(UserCreatable *uc, Error **errp)
}
}
static char *get_id(Object *o, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
return g_strdup(backend->id);
}
static void set_id(Object *o, const char *str, Error **errp)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
if (backend->id) {
error_setg(errp, "cannot change property value");
return;
}
backend->id = g_strdup(str);
}
static void
host_memory_backend_class_init(ObjectClass *oc, void *data)
{
@@ -395,13 +377,6 @@ host_memory_backend_class_init(ObjectClass *oc, void *data)
HostMemPolicy_lookup,
host_memory_backend_get_policy,
host_memory_backend_set_policy, &error_abort);
object_class_property_add_str(oc, "id", get_id, set_id, &error_abort);
}
static void host_memory_backend_finalize(Object *o)
{
HostMemoryBackend *backend = MEMORY_BACKEND(o);
g_free(backend->id);
}
static const TypeInfo host_memory_backend_info = {
@@ -412,7 +387,6 @@ static const TypeInfo host_memory_backend_info = {
.class_init = host_memory_backend_class_init,
.instance_size = sizeof(HostMemoryBackend),
.instance_init = host_memory_backend_init,
.instance_finalize = host_memory_backend_finalize,
.interfaces = (InterfaceInfo[]) {
{ TYPE_USER_CREATABLE },
{ }

View File

@@ -31,23 +31,18 @@
#define MSMOUSE_HI2(n) (((n) & 0xc0) >> 6)
typedef struct {
Chardev parent;
CharDriverState *chr;
QemuInputHandlerState *hs;
int axis[INPUT_AXIS__MAX];
bool btns[INPUT_BUTTON__MAX];
bool btnc[INPUT_BUTTON__MAX];
uint8_t outbuf[32];
int outlen;
} MouseChardev;
} MouseState;
#define TYPE_CHARDEV_MSMOUSE "chardev-msmouse"
#define MOUSE_CHARDEV(obj) \
OBJECT_CHECK(MouseChardev, (obj), TYPE_CHARDEV_MSMOUSE)
static void msmouse_chr_accept_input(Chardev *chr)
static void msmouse_chr_accept_input(CharDriverState *chr)
{
MouseChardev *mouse = MOUSE_CHARDEV(chr);
MouseState *mouse = chr->opaque;
int len;
len = qemu_chr_be_can_write(chr);
@@ -65,7 +60,7 @@ static void msmouse_chr_accept_input(Chardev *chr)
}
}
static void msmouse_queue_event(MouseChardev *mouse)
static void msmouse_queue_event(MouseState *mouse)
{
unsigned char bytes[4] = { 0x40, 0x00, 0x00, 0x00 };
int dx, dy, count = 3;
@@ -102,7 +97,7 @@ static void msmouse_queue_event(MouseChardev *mouse)
static void msmouse_input_event(DeviceState *dev, QemuConsole *src,
InputEvent *evt)
{
MouseChardev *mouse = MOUSE_CHARDEV(dev);
MouseState *mouse = (MouseState *)dev;
InputMoveEvent *move;
InputBtnEvent *btn;
@@ -126,24 +121,24 @@ static void msmouse_input_event(DeviceState *dev, QemuConsole *src,
static void msmouse_input_sync(DeviceState *dev)
{
MouseChardev *mouse = MOUSE_CHARDEV(dev);
Chardev *chr = CHARDEV(dev);
MouseState *mouse = (MouseState *)dev;
msmouse_queue_event(mouse);
msmouse_chr_accept_input(chr);
msmouse_chr_accept_input(mouse->chr);
}
static int msmouse_chr_write(struct Chardev *s, const uint8_t *buf, int len)
static int msmouse_chr_write (struct CharDriverState *s, const uint8_t *buf, int len)
{
/* Ignore writes to mouse port */
return len;
}
static void char_msmouse_finalize(Object *obj)
static void msmouse_chr_free(struct CharDriverState *chr)
{
MouseChardev *mouse = MOUSE_CHARDEV(obj);
MouseState *mouse = chr->opaque;
qemu_input_handler_unregister(mouse->hs);
g_free(mouse);
}
static QemuInputHandler msmouse_handler = {
@@ -153,38 +148,39 @@ static QemuInputHandler msmouse_handler = {
.sync = msmouse_input_sync,
};
static void msmouse_chr_open(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
static CharDriverState *qemu_chr_open_msmouse(const char *id,
ChardevBackend *backend,
ChardevReturn *ret,
bool *be_opened,
Error **errp)
{
MouseChardev *mouse = MOUSE_CHARDEV(chr);
ChardevCommon *common = backend->u.msmouse.data;
MouseState *mouse;
CharDriverState *chr;
chr = qemu_chr_alloc(common, errp);
if (!chr) {
return NULL;
}
chr->chr_write = msmouse_chr_write;
chr->chr_free = msmouse_chr_free;
chr->chr_accept_input = msmouse_chr_accept_input;
*be_opened = false;
mouse = g_new0(MouseState, 1);
mouse->hs = qemu_input_handler_register((DeviceState *)mouse,
&msmouse_handler);
mouse->chr = chr;
chr->opaque = mouse;
return chr;
}
static void char_msmouse_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = msmouse_chr_open;
cc->chr_write = msmouse_chr_write;
cc->chr_accept_input = msmouse_chr_accept_input;
}
static const TypeInfo char_msmouse_type_info = {
.name = TYPE_CHARDEV_MSMOUSE,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(MouseChardev),
.instance_finalize = char_msmouse_finalize,
.class_init = char_msmouse_class_init,
};
static void register_types(void)
{
type_register_static(&char_msmouse_type_info);
register_char_driver("msmouse", CHARDEV_BACKEND_KIND_MSMOUSE, NULL,
qemu_chr_open_msmouse);
}
type_init(register_types);

View File

@@ -86,7 +86,7 @@ static void rng_egd_chr_read(void *opaque, const uint8_t *buf, int size)
static void rng_egd_opened(RngBackend *b, Error **errp)
{
RngEgd *s = RNG_EGD(b);
Chardev *chr;
CharDriverState *chr;
if (s->chr_name == NULL) {
error_setg(errp, QERR_INVALID_PARAMETER_VALUE,
@@ -125,7 +125,7 @@ static void rng_egd_set_chardev(Object *obj, const char *value, Error **errp)
static char *rng_egd_get_chardev(Object *obj, Error **errp)
{
RngEgd *s = RNG_EGD(obj);
Chardev *chr = qemu_chr_fe_get_driver(&s->chr);
CharDriverState *chr = qemu_chr_fe_get_driver(&s->chr);
if (chr && chr->label) {
return g_strdup(chr->label);

View File

@@ -30,18 +30,13 @@
#define BUF_SIZE 32
typedef struct {
Chardev parent;
CharDriverState *chr;
uint8_t in_buf[32];
int in_buf_used;
} TestdevChardev;
#define TYPE_CHARDEV_TESTDEV "chardev-testdev"
#define TESTDEV_CHARDEV(obj) \
OBJECT_CHECK(TestdevChardev, (obj), TYPE_CHARDEV_TESTDEV)
} TestdevCharState;
/* Try to interpret a whole incoming packet */
static int testdev_eat_packet(TestdevChardev *testdev)
static int testdev_eat_packet(TestdevCharState *testdev)
{
const uint8_t *cur = testdev->in_buf;
int len = testdev->in_buf_used;
@@ -82,9 +77,9 @@ static int testdev_eat_packet(TestdevChardev *testdev)
}
/* The other end is writing some data. Store it and try to interpret */
static int testdev_chr_write(Chardev *chr, const uint8_t *buf, int len)
static int testdev_write(CharDriverState *chr, const uint8_t *buf, int len)
{
TestdevChardev *testdev = TESTDEV_CHARDEV(chr);
TestdevCharState *testdev = chr->opaque;
int tocopy, eaten, orig_len = len;
while (len) {
@@ -107,23 +102,36 @@ static int testdev_chr_write(Chardev *chr, const uint8_t *buf, int len)
return orig_len;
}
static void char_testdev_class_init(ObjectClass *oc, void *data)
static void testdev_free(struct CharDriverState *chr)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
TestdevCharState *testdev = chr->opaque;
cc->chr_write = testdev_chr_write;
g_free(testdev);
}
static const TypeInfo char_testdev_type_info = {
.name = TYPE_CHARDEV_TESTDEV,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(TestdevChardev),
.class_init = char_testdev_class_init,
};
static CharDriverState *chr_testdev_init(const char *id,
ChardevBackend *backend,
ChardevReturn *ret,
bool *be_opened,
Error **errp)
{
TestdevCharState *testdev;
CharDriverState *chr;
testdev = g_new0(TestdevCharState, 1);
testdev->chr = chr = g_new0(CharDriverState, 1);
chr->opaque = testdev;
chr->chr_write = testdev_write;
chr->chr_free = testdev_free;
return chr;
}
static void register_types(void)
{
type_register_static(&char_testdev_type_info);
register_char_driver("testdev", CHARDEV_BACKEND_KIND_TESTDEV, NULL,
chr_testdev_init);
}
type_init(register_types);

View File

@@ -1,10 +0,0 @@
# See docs/tracing.txt for syntax documentation.
# backends/wctablet.c
wct_init(void) ""
wct_cmd_re(void) ""
wct_cmd_st(void) ""
wct_cmd_sp(void) ""
wct_cmd_ts(int input) "0x%02x"
wct_cmd_other(const char *cmd) "%s"
wct_speed(int speed) "%d"

View File

@@ -1,369 +0,0 @@
/*
* QEMU Wacom Penpartner serial tablet emulation
*
* some protocol details:
* http://linuxwacom.sourceforge.net/wiki/index.php/Serial_Protocol_IV
*
* Copyright (c) 2016 Anatoli Huseu1
* Copyright (c) 2016,17 Gerd Hoffmann
*
* 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 <stdlib.h>
#include <string.h>
#include <sys/time.h>
#include <time.h>
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#include "ui/console.h"
#include "ui/input.h"
#include "trace.h"
#define WC_OUTPUT_BUF_MAX_LEN 512
#define WC_COMMAND_MAX_LEN 60
#define WC_L7(n) ((n) & 127)
#define WC_M7(n) (((n) >> 7) & 127)
#define WC_H2(n) ((n) >> 14)
#define WC_L4(n) ((n) & 15)
#define WC_H4(n) (((n) >> 4) & 15)
/* Model string and config string */
#define WC_MODEL_STRING_LENGTH 18
uint8_t WC_MODEL_STRING[WC_MODEL_STRING_LENGTH + 1] = "~#CT-0045R,V1.3-5,";
#define WC_CONFIG_STRING_LENGTH 8
uint8_t WC_CONFIG_STRING[WC_CONFIG_STRING_LENGTH + 1] = "96,N,8,0";
#define WC_FULL_CONFIG_STRING_LENGTH 61
uint8_t WC_FULL_CONFIG_STRING[WC_FULL_CONFIG_STRING_LENGTH + 1] = {
0x5c, 0x39, 0x36, 0x2c, 0x4e, 0x2c, 0x38, 0x2c,
0x31, 0x28, 0x01, 0x24, 0x57, 0x41, 0x43, 0x30,
0x30, 0x34, 0x35, 0x5c, 0x5c, 0x50, 0x45, 0x4e, 0x5c,
0x57, 0x41, 0x43, 0x30, 0x30, 0x30, 0x30, 0x5c,
0x54, 0x61, 0x62, 0x6c, 0x65, 0x74, 0x0d, 0x0a,
0x43, 0x54, 0x2d, 0x30, 0x30, 0x34, 0x35, 0x52,
0x2c, 0x56, 0x31, 0x2e, 0x33, 0x2d, 0x35, 0x0d,
0x0a, 0x45, 0x37, 0x29
};
/* This structure is used to save private info for Wacom Tablet. */
typedef struct {
Chardev parent;
QemuInputHandlerState *hs;
/* Query string from serial */
uint8_t query[100];
int query_index;
/* Command to be sent to serial port */
uint8_t outbuf[WC_OUTPUT_BUF_MAX_LEN];
int outlen;
int line_speed;
bool send_events;
int axis[INPUT_AXIS__MAX];
bool btns[INPUT_BUTTON__MAX];
} TabletChardev;
#define TYPE_CHARDEV_WCTABLET "chardev-wctablet"
#define WCTABLET_CHARDEV(obj) \
OBJECT_CHECK(TabletChardev, (obj), TYPE_CHARDEV_WCTABLET)
static void wctablet_chr_accept_input(Chardev *chr);
static void wctablet_shift_input(TabletChardev *tablet, int count)
{
tablet->query_index -= count;
memmove(tablet->query, tablet->query + count, tablet->query_index);
tablet->query[tablet->query_index] = 0;
}
static void wctablet_queue_output(TabletChardev *tablet, uint8_t *buf, int count)
{
if (tablet->outlen + count > sizeof(tablet->outbuf)) {
return;
}
memcpy(tablet->outbuf + tablet->outlen, buf, count);
tablet->outlen += count;
wctablet_chr_accept_input(CHARDEV(tablet));
}
static void wctablet_reset(TabletChardev *tablet)
{
/* clear buffers */
tablet->query_index = 0;
tablet->outlen = 0;
/* reset state */
tablet->send_events = false;
}
static void wctablet_queue_event(TabletChardev *tablet)
{
uint8_t codes[8] = { 0xe0, 0, 0, 0, 0, 0, 0 };
if (tablet->line_speed != 9600) {
return;
}
int newX = tablet->axis[INPUT_AXIS_X] * 0.1537;
int nexY = tablet->axis[INPUT_AXIS_Y] * 0.1152;
codes[0] = codes[0] | WC_H2(newX);
codes[1] = codes[1] | WC_M7(newX);
codes[2] = codes[2] | WC_L7(newX);
codes[3] = codes[3] | WC_H2(nexY);
codes[4] = codes[4] | WC_M7(nexY);
codes[5] = codes[5] | WC_L7(nexY);
if (tablet->btns[INPUT_BUTTON_LEFT]) {
codes[0] = 0xa0;
}
wctablet_queue_output(tablet, codes, 7);
}
static void wctablet_input_event(DeviceState *dev, QemuConsole *src,
InputEvent *evt)
{
TabletChardev *tablet = (TabletChardev *)dev;
InputMoveEvent *move;
InputBtnEvent *btn;
switch (evt->type) {
case INPUT_EVENT_KIND_ABS:
move = evt->u.abs.data;
tablet->axis[move->axis] = move->value;
break;
case INPUT_EVENT_KIND_BTN:
btn = evt->u.btn.data;
tablet->btns[btn->button] = btn->down;
break;
default:
/* keep gcc happy */
break;
}
}
static void wctablet_input_sync(DeviceState *dev)
{
TabletChardev *tablet = (TabletChardev *)dev;
if (tablet->send_events) {
wctablet_queue_event(tablet);
}
}
static QemuInputHandler wctablet_handler = {
.name = "QEMU Wacome Pen Tablet",
.mask = INPUT_EVENT_MASK_BTN | INPUT_EVENT_MASK_ABS,
.event = wctablet_input_event,
.sync = wctablet_input_sync,
};
static void wctablet_chr_accept_input(Chardev *chr)
{
TabletChardev *tablet = WCTABLET_CHARDEV(chr);
int len, canWrite;
canWrite = qemu_chr_be_can_write(chr);
len = canWrite;
if (len > tablet->outlen) {
len = tablet->outlen;
}
if (len) {
qemu_chr_be_write(chr, tablet->outbuf, len);
tablet->outlen -= len;
if (tablet->outlen) {
memmove(tablet->outbuf, tablet->outbuf + len, tablet->outlen);
}
}
}
static int wctablet_chr_write(struct Chardev *chr,
const uint8_t *buf, int len)
{
TabletChardev *tablet = WCTABLET_CHARDEV(chr);
unsigned int i, clen;
char *pos;
if (tablet->line_speed != 9600) {
return len;
}
for (i = 0; i < len && tablet->query_index < sizeof(tablet->query) - 1; i++) {
tablet->query[tablet->query_index++] = buf[i];
}
tablet->query[tablet->query_index] = 0;
while (tablet->query_index > 0 && (tablet->query[0] == '@' ||
tablet->query[0] == '\r' ||
tablet->query[0] == '\n')) {
wctablet_shift_input(tablet, 1);
}
if (!tablet->query_index) {
return len;
}
if (strncmp((char *)tablet->query, "~#", 2) == 0) {
/* init / detect sequence */
trace_wct_init();
wctablet_shift_input(tablet, 2);
wctablet_queue_output(tablet, WC_MODEL_STRING,
WC_MODEL_STRING_LENGTH);
return len;
}
/* detect line */
pos = strchr((char *)tablet->query, '\r');
if (!pos) {
pos = strchr((char *)tablet->query, '\n');
}
if (!pos) {
return len;
}
clen = pos - (char *)tablet->query;
/* process commands */
if (strncmp((char *)tablet->query, "RE", 2) == 0 &&
clen == 2) {
trace_wct_cmd_re();
wctablet_shift_input(tablet, 3);
wctablet_queue_output(tablet, WC_CONFIG_STRING,
WC_CONFIG_STRING_LENGTH);
} else if (strncmp((char *)tablet->query, "ST", 2) == 0 &&
clen == 2) {
trace_wct_cmd_st();
wctablet_shift_input(tablet, 3);
tablet->send_events = true;
wctablet_queue_event(tablet);
} else if (strncmp((char *)tablet->query, "SP", 2) == 0 &&
clen == 2) {
trace_wct_cmd_sp();
wctablet_shift_input(tablet, 3);
tablet->send_events = false;
} else if (strncmp((char *)tablet->query, "TS", 2) == 0 &&
clen == 3) {
unsigned int input = tablet->query[2];
uint8_t codes[7] = {
0xa3,
((input & 0x80) == 0) ? 0x7e : 0x7f,
(((WC_H4(input) & 0x7) ^ 0x5) << 4) | (WC_L4(input) ^ 0x7),
0x03,
0x7f,
0x7f,
0x00,
};
trace_wct_cmd_ts(input);
wctablet_shift_input(tablet, 4);
wctablet_queue_output(tablet, codes, 7);
} else {
tablet->query[clen] = 0; /* terminate line for printing */
trace_wct_cmd_other((char *)tablet->query);
wctablet_shift_input(tablet, clen + 1);
}
return len;
}
static int wctablet_chr_ioctl(Chardev *chr, int cmd, void *arg)
{
TabletChardev *tablet = WCTABLET_CHARDEV(chr);
QEMUSerialSetParams *ssp;
switch (cmd) {
case CHR_IOCTL_SERIAL_SET_PARAMS:
ssp = arg;
if (tablet->line_speed != ssp->speed) {
trace_wct_speed(ssp->speed);
wctablet_reset(tablet);
tablet->line_speed = ssp->speed;
}
break;
default:
return -ENOTSUP;
}
return 0;
}
static void wctablet_chr_finalize(Object *obj)
{
TabletChardev *tablet = WCTABLET_CHARDEV(obj);
qemu_input_handler_unregister(tablet->hs);
g_free(tablet);
}
static void wctablet_chr_open(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
TabletChardev *tablet = WCTABLET_CHARDEV(chr);
*be_opened = true;
/* init state machine */
memcpy(tablet->outbuf, WC_FULL_CONFIG_STRING, WC_FULL_CONFIG_STRING_LENGTH);
tablet->outlen = WC_FULL_CONFIG_STRING_LENGTH;
tablet->query_index = 0;
tablet->hs = qemu_input_handler_register((DeviceState *)tablet,
&wctablet_handler);
}
static void wctablet_chr_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = wctablet_chr_open;
cc->chr_write = wctablet_chr_write;
cc->chr_ioctl = wctablet_chr_ioctl;
cc->chr_accept_input = wctablet_chr_accept_input;
}
static const TypeInfo wctablet_type_info = {
.name = TYPE_CHARDEV_WCTABLET,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(TabletChardev),
.instance_finalize = wctablet_chr_finalize,
.class_init = wctablet_chr_class_init,
};
static void register_types(void)
{
type_register_static(&wctablet_type_info);
}
type_init(register_types);

View File

@@ -29,7 +29,7 @@
#include "exec/cpu-common.h"
#include "sysemu/kvm.h"
#include "sysemu/balloon.h"
#include "trace-root.h"
#include "trace.h"
#include "qmp-commands.h"
#include "qapi/qmp/qerror.h"
#include "qapi/qmp/qjson.h"

301
block.c
View File

@@ -22,7 +22,7 @@
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "block/trace.h"
#include "trace.h"
#include "block/block_int.h"
#include "block/blockjob.h"
#include "block/nbd.h"
@@ -588,20 +588,21 @@ BlockDriver *bdrv_probe_all(const uint8_t *buf, int buf_size,
return drv;
}
static int find_image_format(BlockBackend *file, const char *filename,
static int find_image_format(BdrvChild *file, const char *filename,
BlockDriver **pdrv, Error **errp)
{
BlockDriverState *bs = file->bs;
BlockDriver *drv;
uint8_t buf[BLOCK_PROBE_BUF_SIZE];
int ret = 0;
/* Return the raw BlockDriver * to scsi-generic devices or empty drives */
if (blk_is_sg(file) || !blk_is_inserted(file) || blk_getlength(file) == 0) {
if (bdrv_is_sg(bs) || !bdrv_is_inserted(bs) || bdrv_getlength(bs) == 0) {
*pdrv = &bdrv_raw;
return ret;
}
ret = blk_pread(file, 0, buf, sizeof(buf));
ret = bdrv_pread(file, 0, buf, sizeof(buf));
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not read image for determining its "
"format");
@@ -925,95 +926,6 @@ out:
g_free(gen_node_name);
}
static int bdrv_open_driver(BlockDriverState *bs, BlockDriver *drv,
const char *node_name, QDict *options,
int open_flags, Error **errp)
{
Error *local_err = NULL;
int ret;
bdrv_assign_node_name(bs, node_name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
return -EINVAL;
}
bs->drv = drv;
bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
bs->opaque = g_malloc0(drv->instance_size);
if (drv->bdrv_file_open) {
assert(!drv->bdrv_needs_filename || bs->filename[0]);
ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
} else if (drv->bdrv_open) {
ret = drv->bdrv_open(bs, options, open_flags, &local_err);
} else {
ret = 0;
}
if (ret < 0) {
if (local_err) {
error_propagate(errp, local_err);
} else if (bs->filename[0]) {
error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
} else {
error_setg_errno(errp, -ret, "Could not open image");
}
goto free_and_fail;
}
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
goto free_and_fail;
}
bdrv_refresh_limits(bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto free_and_fail;
}
assert(bdrv_opt_mem_align(bs) != 0);
assert(bdrv_min_mem_align(bs) != 0);
assert(is_power_of_2(bs->bl.request_alignment));
return 0;
free_and_fail:
/* FIXME Close bs first if already opened*/
g_free(bs->opaque);
bs->opaque = NULL;
bs->drv = NULL;
return ret;
}
BlockDriverState *bdrv_new_open_driver(BlockDriver *drv, const char *node_name,
int flags, Error **errp)
{
BlockDriverState *bs;
int ret;
bs = bdrv_new();
bs->open_flags = flags;
bs->explicit_options = qdict_new();
bs->options = qdict_new();
bs->opaque = NULL;
update_options_from_flags(bs->options, flags);
ret = bdrv_open_driver(bs, drv, node_name, bs->options, flags, errp);
if (ret < 0) {
QDECREF(bs->explicit_options);
QDECREF(bs->options);
bdrv_unref(bs);
return NULL;
}
return bs;
}
QemuOptsList bdrv_runtime_opts = {
.name = "bdrv_common",
.head = QTAILQ_HEAD_INITIALIZER(bdrv_runtime_opts.head),
@@ -1062,7 +974,7 @@ QemuOptsList bdrv_runtime_opts = {
*
* Removes all processed options from *options.
*/
static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
static int bdrv_open_common(BlockDriverState *bs, BdrvChild *file,
QDict *options, Error **errp)
{
int ret, open_flags;
@@ -1093,7 +1005,7 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
assert(drv != NULL);
if (file != NULL) {
filename = blk_bs(file)->filename;
filename = file->bs->filename;
} else {
filename = qdict_get_try_str(options, "filename");
}
@@ -1108,6 +1020,14 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
trace_bdrv_open_common(bs, filename ?: "", bs->open_flags,
drv->format_name);
node_name = qemu_opt_get(opts, "node-name");
bdrv_assign_node_name(bs, node_name, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto fail_opts;
}
bs->read_only = !(bs->open_flags & BDRV_O_RDWR);
if (use_bdrv_whitelist && !bdrv_is_whitelisted(drv, bs->read_only)) {
@@ -1173,19 +1093,62 @@ static int bdrv_open_common(BlockDriverState *bs, BlockBackend *file,
}
pstrcpy(bs->exact_filename, sizeof(bs->exact_filename), bs->filename);
bs->drv = drv;
bs->opaque = g_malloc0(drv->instance_size);
/* Open the image, either directly or using a protocol */
open_flags = bdrv_open_flags(bs, bs->open_flags);
node_name = qemu_opt_get(opts, "node-name");
assert(!drv->bdrv_file_open || file == NULL);
ret = bdrv_open_driver(bs, drv, node_name, options, open_flags, errp);
if (ret < 0) {
goto fail_opts;
if (drv->bdrv_file_open) {
assert(file == NULL);
assert(!drv->bdrv_needs_filename || filename != NULL);
ret = drv->bdrv_file_open(bs, options, open_flags, &local_err);
} else {
if (file == NULL) {
error_setg(errp, "Can't use '%s' as a block driver for the "
"protocol level", drv->format_name);
ret = -EINVAL;
goto free_and_fail;
}
bs->file = file;
ret = drv->bdrv_open(bs, options, open_flags, &local_err);
}
if (ret < 0) {
if (local_err) {
error_propagate(errp, local_err);
} else if (bs->filename[0]) {
error_setg_errno(errp, -ret, "Could not open '%s'", bs->filename);
} else {
error_setg_errno(errp, -ret, "Could not open image");
}
goto free_and_fail;
}
ret = refresh_total_sectors(bs, bs->total_sectors);
if (ret < 0) {
error_setg_errno(errp, -ret, "Could not refresh total sector count");
goto free_and_fail;
}
bdrv_refresh_limits(bs, &local_err);
if (local_err) {
error_propagate(errp, local_err);
ret = -EINVAL;
goto free_and_fail;
}
assert(bdrv_opt_mem_align(bs) != 0);
assert(bdrv_min_mem_align(bs) != 0);
assert(is_power_of_2(bs->bl.request_alignment));
qemu_opts_del(opts);
return 0;
free_and_fail:
bs->file = NULL;
g_free(bs->opaque);
bs->opaque = NULL;
bs->drv = NULL;
fail_opts:
qemu_opts_del(opts);
return ret;
@@ -1206,13 +1169,13 @@ static QDict *parse_json_filename(const char *filename, Error **errp)
return NULL;
}
options = qobject_to_qdict(options_obj);
if (!options) {
if (qobject_type(options_obj) != QTYPE_QDICT) {
qobject_decref(options_obj);
error_setg(errp, "Invalid JSON object given");
return NULL;
}
options = qobject_to_qdict(options_obj);
qdict_flatten(options);
return options;
@@ -1405,18 +1368,7 @@ void bdrv_unref_child(BlockDriverState *parent, BdrvChild *child)
}
if (child->bs->inherits_from == parent) {
BdrvChild *c;
/* Remove inherits_from only when the last reference between parent and
* child->bs goes away. */
QLIST_FOREACH(c, &parent->children, next) {
if (c != child && c->bs == child->bs) {
break;
}
}
if (c == NULL) {
child->bs->inherits_from = NULL;
}
child->bs->inherits_from = NULL;
}
bdrv_root_unref_child(child);
@@ -1591,12 +1543,28 @@ free_exit:
return ret;
}
static BlockDriverState *
bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
BlockDriverState *parent, const BdrvChildRole *child_role,
bool allow_none, Error **errp)
/*
* Opens a disk image whose options are given as BlockdevRef in another block
* device's options.
*
* If allow_none is true, no image will be opened if filename is false and no
* BlockdevRef is given. NULL will be returned, but errp remains unset.
*
* bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
* That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
* The BlockdevRef will be removed from the options QDict.
*/
BdrvChild *bdrv_open_child(const char *filename,
QDict *options, const char *bdref_key,
BlockDriverState* parent,
const BdrvChildRole *child_role,
bool allow_none, Error **errp)
{
BlockDriverState *bs = NULL;
BdrvChild *c = NULL;
BlockDriverState *bs;
QDict *image_options;
char *bdref_key_dot;
const char *reference;
@@ -1623,40 +1591,11 @@ bdrv_open_child_bs(const char *filename, QDict *options, const char *bdref_key,
goto done;
}
c = bdrv_attach_child(parent, bs, bdref_key, child_role);
done:
qdict_del(options, bdref_key);
return bs;
}
/*
* Opens a disk image whose options are given as BlockdevRef in another block
* device's options.
*
* If allow_none is true, no image will be opened if filename is false and no
* BlockdevRef is given. NULL will be returned, but errp remains unset.
*
* bdrev_key specifies the key for the image's BlockdevRef in the options QDict.
* That QDict has to be flattened; therefore, if the BlockdevRef is a QDict
* itself, all options starting with "${bdref_key}." are considered part of the
* BlockdevRef.
*
* The BlockdevRef will be removed from the options QDict.
*/
BdrvChild *bdrv_open_child(const char *filename,
QDict *options, const char *bdref_key,
BlockDriverState *parent,
const BdrvChildRole *child_role,
bool allow_none, Error **errp)
{
BlockDriverState *bs;
bs = bdrv_open_child_bs(filename, options, bdref_key, parent, child_role,
allow_none, errp);
if (bs == NULL) {
return NULL;
}
return bdrv_attach_child(parent, bs, bdref_key, child_role);
return c;
}
static BlockDriverState *bdrv_append_temp_snapshot(BlockDriverState *bs,
@@ -1752,7 +1691,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
Error **errp)
{
int ret;
BlockBackend *file = NULL;
BdrvChild *file = NULL;
BlockDriverState *bs;
BlockDriver *drv = NULL;
const char *drvname;
@@ -1850,25 +1789,13 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
qdict_del(options, "backing");
}
/* Open image file without format layer. This BlockBackend is only used for
* probing, the block drivers will do their own bdrv_open_child() for the
* same BDS, which is why we put the node name back into options. */
/* Open image file without format layer */
if ((flags & BDRV_O_PROTOCOL) == 0) {
BlockDriverState *file_bs;
file_bs = bdrv_open_child_bs(filename, options, "file", bs,
&child_file, true, &local_err);
file = bdrv_open_child(filename, options, "file", bs,
&child_file, true, &local_err);
if (local_err) {
goto fail;
}
if (file_bs != NULL) {
file = blk_new();
blk_insert_bs(file, file_bs);
bdrv_unref(file_bs);
qdict_put(options, "file",
qstring_from_str(bdrv_get_node_name(file_bs)));
}
}
/* Image format probing */
@@ -1908,8 +1835,8 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
goto fail;
}
if (file) {
blk_unref(file);
if (file && (bs->file != file)) {
bdrv_unref_child(bs, file);
file = NULL;
}
@@ -1924,7 +1851,7 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
bdrv_refresh_filename(bs);
/* Check if any unknown options were used */
if (qdict_size(options) != 0) {
if (options && (qdict_size(options) != 0)) {
const QDictEntry *entry = qdict_first(options);
if (flags & BDRV_O_PROTOCOL) {
error_setg(errp, "Block protocol '%s' doesn't support the option "
@@ -1971,9 +1898,8 @@ static BlockDriverState *bdrv_open_inherit(const char *filename,
return bs;
fail:
blk_unref(file);
if (bs->file != NULL) {
bdrv_unref_child(bs, bs->file);
if (file != NULL) {
bdrv_unref_child(bs, file);
}
QDECREF(snapshot_options);
QDECREF(bs->explicit_options);
@@ -2700,9 +2626,8 @@ exit:
/**
* Truncate file to 'offset' bytes (needed only for file protocols)
*/
int bdrv_truncate(BdrvChild *child, int64_t offset)
int bdrv_truncate(BlockDriverState *bs, int64_t offset)
{
BlockDriverState *bs = child->bs;
BlockDriver *drv = bs->drv;
int ret;
if (!drv)
@@ -3220,7 +3145,6 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
int is_protocol = 0;
BlockDriverState *curr_bs = NULL;
BlockDriverState *retval = NULL;
Error *local_error = NULL;
if (!bs || !bs->drv || !backing_file) {
return NULL;
@@ -3241,18 +3165,6 @@ BlockDriverState *bdrv_find_backing_image(BlockDriverState *bs,
retval = curr_bs->backing->bs;
break;
}
/* Also check against the full backing filename for the image */
bdrv_get_full_backing_filename(curr_bs, backing_file_full, PATH_MAX,
&local_error);
if (local_error == NULL) {
if (strcmp(backing_file, backing_file_full) == 0) {
retval = curr_bs->backing->bs;
break;
}
} else {
error_free(local_error);
local_error = NULL;
}
} else {
/* If not an absolute filename path, make it relative to the current
* image's filename path */
@@ -3323,18 +3235,19 @@ void bdrv_invalidate_cache(BlockDriverState *bs, Error **errp)
if (!(bs->open_flags & BDRV_O_INACTIVE)) {
return;
}
bs->open_flags &= ~BDRV_O_INACTIVE;
QLIST_FOREACH(child, &bs->children, next) {
bdrv_invalidate_cache(child->bs, &local_err);
if (bs->drv->bdrv_invalidate_cache) {
bs->drv->bdrv_invalidate_cache(bs, &local_err);
if (local_err) {
bs->open_flags |= BDRV_O_INACTIVE;
error_propagate(errp, local_err);
return;
}
}
bs->open_flags &= ~BDRV_O_INACTIVE;
if (bs->drv->bdrv_invalidate_cache) {
bs->drv->bdrv_invalidate_cache(bs, &local_err);
QLIST_FOREACH(child, &bs->children, next) {
bdrv_invalidate_cache(child->bs, &local_err);
if (local_err) {
bs->open_flags |= BDRV_O_INACTIVE;
error_propagate(errp, local_err);

View File

@@ -1,4 +1,4 @@
block-obj-y += raw-format.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o dmg.o
block-obj-y += raw_bsd.o qcow.o vdi.o vmdk.o cloop.o bochs.o vpc.o vvfat.o dmg.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
@@ -6,15 +6,14 @@ block-obj-y += vhdx.o vhdx-endian.o vhdx-log.o
block-obj-y += quorum.o
block-obj-y += parallels.o blkdebug.o blkverify.o blkreplay.o
block-obj-y += block-backend.o snapshot.o qapi.o
block-obj-$(CONFIG_WIN32) += file-win32.o win32-aio.o
block-obj-$(CONFIG_POSIX) += file-posix.o
block-obj-$(CONFIG_WIN32) += raw-win32.o win32-aio.o
block-obj-$(CONFIG_POSIX) += raw-posix.o
block-obj-$(CONFIG_LINUX_AIO) += linux-aio.o
block-obj-y += null.o mirror.o commit.o io.o
block-obj-y += throttle-groups.o
block-obj-y += nbd.o nbd-client.o sheepdog.o
block-obj-$(CONFIG_LIBISCSI) += iscsi.o
block-obj-$(if $(CONFIG_LIBISCSI),y,n) += iscsi-opts.o
block-obj-$(CONFIG_LIBNFS) += nfs.o
block-obj-$(CONFIG_CURL) += curl.o
block-obj-$(CONFIG_RBD) += rbd.o

View File

@@ -64,7 +64,7 @@ static void coroutine_fn wait_for_overlapping_requests(BackupBlockJob *job,
retry = false;
QLIST_FOREACH(req, &job->inflight_reqs, list) {
if (end > req->start && start < req->end) {
qemu_co_queue_wait(&req->wait_queue, NULL);
qemu_co_queue_wait(&req->wait_queue);
retry = true;
break;
}

View File

@@ -58,6 +58,10 @@ typedef struct BlkdebugSuspendedReq {
QLIST_ENTRY(BlkdebugSuspendedReq) next;
} BlkdebugSuspendedReq;
static const AIOCBInfo blkdebug_aiocb_info = {
.aiocb_size = sizeof(BlkdebugAIOCB),
};
enum {
ACTION_INJECT_ERROR,
ACTION_SET_STATE,
@@ -73,7 +77,7 @@ typedef struct BlkdebugRule {
int error;
int immediately;
int once;
int64_t offset;
int64_t sector;
} inject;
struct {
int new_state;
@@ -170,7 +174,6 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
const char* event_name;
BlkdebugEvent event;
struct BlkdebugRule *rule;
int64_t sector;
/* Find the right event for the rule */
event_name = qemu_opt_get(opts, "event");
@@ -197,9 +200,7 @@ static int add_rule(void *opaque, QemuOpts *opts, Error **errp)
rule->options.inject.once = qemu_opt_get_bool(opts, "once", 0);
rule->options.inject.immediately =
qemu_opt_get_bool(opts, "immediately", 0);
sector = qemu_opt_get_number(opts, "sector", -1);
rule->options.inject.offset =
sector == -1 ? -1 : sector * BDRV_SECTOR_SIZE;
rule->options.inject.sector = qemu_opt_get_number(opts, "sector", -1);
break;
case ACTION_SET_STATE:
@@ -405,10 +406,19 @@ out:
return ret;
}
static int inject_error(BlockDriverState *bs, BlkdebugRule *rule)
static void error_callback_bh(void *opaque)
{
struct BlkdebugAIOCB *acb = opaque;
acb->common.cb(acb->common.opaque, acb->ret);
qemu_aio_unref(acb);
}
static BlockAIOCB *inject_error(BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque, BlkdebugRule *rule)
{
BDRVBlkdebugState *s = bs->opaque;
int error = rule->options.inject.error;
struct BlkdebugAIOCB *acb;
bool immediately = rule->options.inject.immediately;
if (rule->options.inject.once) {
@@ -416,78 +426,81 @@ static int inject_error(BlockDriverState *bs, BlkdebugRule *rule)
remove_rule(rule);
}
if (!immediately) {
aio_co_schedule(qemu_get_current_aio_context(), qemu_coroutine_self());
qemu_coroutine_yield();
if (immediately) {
return NULL;
}
return -error;
acb = qemu_aio_get(&blkdebug_aiocb_info, bs, cb, opaque);
acb->ret = -error;
aio_bh_schedule_oneshot(bdrv_get_aio_context(bs), error_callback_bh, acb);
return &acb->common;
}
static int coroutine_fn
blkdebug_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
QEMUIOVector *qiov, int flags)
static BlockAIOCB *blkdebug_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugRule *rule = NULL;
QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
uint64_t inject_offset = rule->options.inject.offset;
if (inject_offset == -1 ||
(inject_offset >= offset && inject_offset < offset + bytes))
{
if (rule->options.inject.sector == -1 ||
(rule->options.inject.sector >= sector_num &&
rule->options.inject.sector < sector_num + nb_sectors)) {
break;
}
}
if (rule && rule->options.inject.error) {
return inject_error(bs, rule);
return inject_error(bs, cb, opaque, rule);
}
return bdrv_co_preadv(bs->file, offset, bytes, qiov, flags);
return bdrv_aio_readv(bs->file, sector_num, qiov, nb_sectors,
cb, opaque);
}
static int coroutine_fn
blkdebug_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
QEMUIOVector *qiov, int flags)
static BlockAIOCB *blkdebug_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
BDRVBlkdebugState *s = bs->opaque;
BlkdebugRule *rule = NULL;
QSIMPLEQ_FOREACH(rule, &s->active_rules, active_next) {
uint64_t inject_offset = rule->options.inject.offset;
if (inject_offset == -1 ||
(inject_offset >= offset && inject_offset < offset + bytes))
{
if (rule->options.inject.sector == -1 ||
(rule->options.inject.sector >= sector_num &&
rule->options.inject.sector < sector_num + nb_sectors)) {
break;
}
}
if (rule && rule->options.inject.error) {
return inject_error(bs, rule);
return inject_error(bs, cb, opaque, rule);
}
return bdrv_co_pwritev(bs->file, offset, bytes, qiov, flags);
return bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
cb, opaque);
}
static int blkdebug_co_flush(BlockDriverState *bs)
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.offset == -1) {
if (rule->options.inject.sector == -1) {
break;
}
}
if (rule && rule->options.inject.error) {
return inject_error(bs, rule);
return inject_error(bs, cb, opaque, rule);
}
return bdrv_co_flush(bs->file->bs);
return bdrv_aio_flush(bs->file->bs, cb, opaque);
}
@@ -663,7 +676,7 @@ static int64_t blkdebug_getlength(BlockDriverState *bs)
static int blkdebug_truncate(BlockDriverState *bs, int64_t offset)
{
return bdrv_truncate(bs->file, offset);
return bdrv_truncate(bs->file->bs, offset);
}
static void blkdebug_refresh_filename(BlockDriverState *bs, QDict *options)
@@ -739,9 +752,9 @@ static BlockDriver bdrv_blkdebug = {
.bdrv_refresh_filename = blkdebug_refresh_filename,
.bdrv_refresh_limits = blkdebug_refresh_limits,
.bdrv_co_preadv = blkdebug_co_preadv,
.bdrv_co_pwritev = blkdebug_co_pwritev,
.bdrv_co_flush_to_disk = blkdebug_co_flush,
.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

@@ -60,7 +60,7 @@ static int64_t blkreplay_getlength(BlockDriverState *bs)
static void blkreplay_bh_cb(void *opaque)
{
Request *req = opaque;
aio_co_wake(req->co);
qemu_coroutine_enter(req->co);
qemu_bh_delete(req->bh);
g_free(req);
}

View File

@@ -19,36 +19,38 @@ typedef struct {
BdrvChild *test_file;
} BDRVBlkverifyState;
typedef struct BlkverifyRequest {
Coroutine *co;
BlockDriverState *bs;
typedef struct BlkverifyAIOCB BlkverifyAIOCB;
struct BlkverifyAIOCB {
BlockAIOCB common;
/* Request metadata */
bool is_write;
uint64_t offset;
uint64_t bytes;
int flags;
int (*request_fn)(BdrvChild *, int64_t, unsigned int, QEMUIOVector *,
BdrvRequestFlags);
int ret; /* test image result */
int raw_ret; /* raw image result */
int64_t sector_num;
int nb_sectors;
int ret; /* first completed request's result */
unsigned int done; /* completion counter */
QEMUIOVector *qiov; /* user I/O vector */
QEMUIOVector *raw_qiov; /* cloned I/O vector for raw file */
} BlkverifyRequest;
QEMUIOVector raw_qiov; /* cloned I/O vector for raw file */
void *buf; /* buffer for raw file I/O */
static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyRequest *r,
void (*verify)(BlkverifyAIOCB *acb);
};
static const AIOCBInfo blkverify_aiocb_info = {
.aiocb_size = sizeof(BlkverifyAIOCB),
};
static void GCC_FMT_ATTR(2, 3) blkverify_err(BlkverifyAIOCB *acb,
const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
fprintf(stderr, "blkverify: %s offset=%" PRId64 " bytes=%" PRId64 " ",
r->is_write ? "write" : "read", r->offset, r->bytes);
fprintf(stderr, "blkverify: %s sector_num=%" PRId64 " nb_sectors=%d ",
acb->is_write ? "write" : "read", acb->sector_num,
acb->nb_sectors);
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
va_end(ap);
@@ -164,106 +166,113 @@ static int64_t blkverify_getlength(BlockDriverState *bs)
return bdrv_getlength(s->test_file->bs);
}
static void coroutine_fn blkverify_do_test_req(void *opaque)
static BlkverifyAIOCB *blkverify_aio_get(BlockDriverState *bs, bool is_write,
int64_t sector_num, QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
BlkverifyRequest *r = opaque;
BDRVBlkverifyState *s = r->bs->opaque;
BlkverifyAIOCB *acb = qemu_aio_get(&blkverify_aiocb_info, bs, cb, opaque);
r->ret = r->request_fn(s->test_file, r->offset, r->bytes, r->qiov,
r->flags);
r->done++;
qemu_coroutine_enter_if_inactive(r->co);
acb->is_write = is_write;
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
acb->ret = -EINPROGRESS;
acb->done = 0;
acb->qiov = qiov;
acb->buf = NULL;
acb->verify = NULL;
return acb;
}
static void coroutine_fn blkverify_do_raw_req(void *opaque)
static void blkverify_aio_bh(void *opaque)
{
BlkverifyRequest *r = opaque;
BlkverifyAIOCB *acb = opaque;
r->raw_ret = r->request_fn(r->bs->file, r->offset, r->bytes, r->raw_qiov,
r->flags);
r->done++;
qemu_coroutine_enter_if_inactive(r->co);
}
static int coroutine_fn
blkverify_co_prwv(BlockDriverState *bs, BlkverifyRequest *r, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, QEMUIOVector *raw_qiov,
int flags, bool is_write)
{
Coroutine *co_a, *co_b;
*r = (BlkverifyRequest) {
.co = qemu_coroutine_self(),
.bs = bs,
.offset = offset,
.bytes = bytes,
.qiov = qiov,
.raw_qiov = raw_qiov,
.flags = flags,
.is_write = is_write,
.request_fn = is_write ? bdrv_co_pwritev : bdrv_co_preadv,
};
co_a = qemu_coroutine_create(blkverify_do_test_req, r);
co_b = qemu_coroutine_create(blkverify_do_raw_req, r);
qemu_coroutine_enter(co_a);
qemu_coroutine_enter(co_b);
while (r->done < 2) {
qemu_coroutine_yield();
if (acb->buf) {
qemu_iovec_destroy(&acb->raw_qiov);
qemu_vfree(acb->buf);
}
if (r->ret != r->raw_ret) {
blkverify_err(r, "return value mismatch %d != %d", r->ret, r->raw_ret);
}
return r->ret;
acb->common.cb(acb->common.opaque, acb->ret);
qemu_aio_unref(acb);
}
static int coroutine_fn
blkverify_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
QEMUIOVector *qiov, int flags)
static void blkverify_aio_cb(void *opaque, int ret)
{
BlkverifyRequest r;
QEMUIOVector raw_qiov;
void *buf;
ssize_t cmp_offset;
int ret;
BlkverifyAIOCB *acb = opaque;
buf = qemu_blockalign(bs->file->bs, qiov->size);
qemu_iovec_init(&raw_qiov, qiov->niov);
qemu_iovec_clone(&raw_qiov, qiov, buf);
switch (++acb->done) {
case 1:
acb->ret = ret;
break;
ret = blkverify_co_prwv(bs, &r, offset, bytes, qiov, &raw_qiov, flags,
false);
case 2:
if (acb->ret != ret) {
blkverify_err(acb, "return value mismatch %d != %d", acb->ret, ret);
}
cmp_offset = qemu_iovec_compare(qiov, &raw_qiov);
if (cmp_offset != -1) {
blkverify_err(&r, "contents mismatch at offset %" PRId64,
offset + cmp_offset);
if (acb->verify) {
acb->verify(acb);
}
aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
blkverify_aio_bh, acb);
break;
}
qemu_iovec_destroy(&raw_qiov);
qemu_vfree(buf);
return ret;
}
static int coroutine_fn
blkverify_co_pwritev(BlockDriverState *bs, uint64_t offset, uint64_t bytes,
QEMUIOVector *qiov, int flags)
static void blkverify_verify_readv(BlkverifyAIOCB *acb)
{
BlkverifyRequest r;
return blkverify_co_prwv(bs, &r, offset, bytes, qiov, qiov, flags, true);
ssize_t offset = qemu_iovec_compare(acb->qiov, &acb->raw_qiov);
if (offset != -1) {
blkverify_err(acb, "contents mismatch in sector %" PRId64,
acb->sector_num + (int64_t)(offset / BDRV_SECTOR_SIZE));
}
}
static int blkverify_co_flush(BlockDriverState *bs)
static BlockAIOCB *blkverify_aio_readv(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, false, sector_num, qiov,
nb_sectors, cb, opaque);
acb->verify = blkverify_verify_readv;
acb->buf = qemu_blockalign(bs->file->bs, qiov->size);
qemu_iovec_init(&acb->raw_qiov, acb->qiov->niov);
qemu_iovec_clone(&acb->raw_qiov, qiov, acb->buf);
bdrv_aio_readv(s->test_file, sector_num, qiov, nb_sectors,
blkverify_aio_cb, acb);
bdrv_aio_readv(bs->file, sector_num, &acb->raw_qiov, nb_sectors,
blkverify_aio_cb, acb);
return &acb->common;
}
static BlockAIOCB *blkverify_aio_writev(BlockDriverState *bs,
int64_t sector_num, QEMUIOVector *qiov, int nb_sectors,
BlockCompletionFunc *cb, void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
BlkverifyAIOCB *acb = blkverify_aio_get(bs, true, sector_num, qiov,
nb_sectors, cb, opaque);
bdrv_aio_writev(s->test_file, sector_num, qiov, nb_sectors,
blkverify_aio_cb, acb);
bdrv_aio_writev(bs->file, sector_num, qiov, nb_sectors,
blkverify_aio_cb, acb);
return &acb->common;
}
static BlockAIOCB *blkverify_aio_flush(BlockDriverState *bs,
BlockCompletionFunc *cb,
void *opaque)
{
BDRVBlkverifyState *s = bs->opaque;
/* Only flush test file, the raw file is not important */
return bdrv_co_flush(s->test_file->bs);
return bdrv_aio_flush(s->test_file->bs, cb, opaque);
}
static bool blkverify_recurse_is_first_non_filter(BlockDriverState *bs,
@@ -323,9 +332,9 @@ static BlockDriver bdrv_blkverify = {
.bdrv_getlength = blkverify_getlength,
.bdrv_refresh_filename = blkverify_refresh_filename,
.bdrv_co_preadv = blkverify_co_preadv,
.bdrv_co_pwritev = blkverify_co_pwritev,
.bdrv_co_flush = blkverify_co_flush,
.bdrv_aio_readv = blkverify_aio_readv,
.bdrv_aio_writev = blkverify_aio_writev,
.bdrv_aio_flush = blkverify_aio_flush,
.is_filter = true,
.bdrv_recurse_is_first_non_filter = blkverify_recurse_is_first_non_filter,

View File

@@ -880,6 +880,7 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
{
QEMUIOVector qiov;
struct iovec iov;
Coroutine *co;
BlkRwCo rwco;
iov = (struct iovec) {
@@ -896,14 +897,9 @@ static int blk_prw(BlockBackend *blk, int64_t offset, uint8_t *buf,
.ret = NOT_DONE,
};
if (qemu_in_coroutine()) {
/* Fast-path if already in coroutine context */
co_entry(&rwco);
} else {
Coroutine *co = qemu_coroutine_create(co_entry, &rwco);
qemu_coroutine_enter(co);
BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
}
co = qemu_coroutine_create(co_entry, &rwco);
qemu_coroutine_enter(co);
BDRV_POLL_WHILE(blk_bs(blk), rwco.ret == NOT_DONE);
return rwco.ret;
}
@@ -983,6 +979,7 @@ static void blk_aio_complete(BlkAioEmAIOCB *acb)
static void blk_aio_complete_bh(void *opaque)
{
BlkAioEmAIOCB *acb = opaque;
assert(acb->has_returned);
blk_aio_complete(acb);
}
@@ -1605,7 +1602,7 @@ int blk_truncate(BlockBackend *blk, int64_t offset)
return -ENOMEDIUM;
}
return bdrv_truncate(blk->root, offset);
return bdrv_truncate(blk_bs(blk), offset);
}
static void blk_pdiscard_entry(void *opaque)

View File

@@ -104,12 +104,6 @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
struct bochs_header bochs;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
bs->read_only = true; /* no write support yet */
ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));

View File

@@ -66,12 +66,6 @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
uint32_t offsets_size, max_compressed_block_size = 1, i;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
bs->read_only = true;
/* read header */

View File

@@ -300,12 +300,6 @@ static int block_crypto_open_generic(QCryptoBlockFormat format,
QCryptoBlockOpenOptions *open_opts = NULL;
unsigned int cflags = 0;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
opts = qemu_opts_create(opts_spec, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
@@ -389,7 +383,7 @@ static int block_crypto_truncate(BlockDriverState *bs, int64_t offset)
offset += payload_offset;
return bdrv_truncate(bs->file, offset);
return bdrv_truncate(bs->file->bs, offset);
}
static void block_crypto_close(BlockDriverState *bs)

View File

@@ -192,19 +192,19 @@ static int curl_sock_cb(CURL *curl, curl_socket_t fd, int action,
switch (action) {
case CURL_POLL_IN:
aio_set_fd_handler(s->aio_context, fd, false,
curl_multi_read, NULL, NULL, state);
curl_multi_read, NULL, state);
break;
case CURL_POLL_OUT:
aio_set_fd_handler(s->aio_context, fd, false,
NULL, curl_multi_do, NULL, state);
NULL, curl_multi_do, state);
break;
case CURL_POLL_INOUT:
aio_set_fd_handler(s->aio_context, fd, false,
curl_multi_read, curl_multi_do, NULL, state);
curl_multi_read, curl_multi_do, state);
break;
case CURL_POLL_REMOVE:
aio_set_fd_handler(s->aio_context, fd, false,
NULL, NULL, NULL, NULL);
NULL, NULL, NULL);
break;
}
@@ -386,8 +386,9 @@ static void curl_multi_check_completion(BDRVCURLState *s)
}
}
static void curl_multi_do_locked(CURLState *s)
static void curl_multi_do(void *arg)
{
CURLState *s = (CURLState *)arg;
CURLSocket *socket, *next_socket;
int running;
int r;
@@ -405,23 +406,12 @@ static void curl_multi_do_locked(CURLState *s)
}
}
static void curl_multi_do(void *arg)
{
CURLState *s = (CURLState *)arg;
aio_context_acquire(s->s->aio_context);
curl_multi_do_locked(s);
aio_context_release(s->s->aio_context);
}
static void curl_multi_read(void *arg)
{
CURLState *s = (CURLState *)arg;
aio_context_acquire(s->s->aio_context);
curl_multi_do_locked(s);
curl_multi_do(arg);
curl_multi_check_completion(s->s);
aio_context_release(s->s->aio_context);
}
static void curl_multi_timeout_do(void *arg)
@@ -434,11 +424,9 @@ static void curl_multi_timeout_do(void *arg)
return;
}
aio_context_acquire(s->aio_context);
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
curl_multi_check_completion(s);
aio_context_release(s->aio_context);
#else
abort();
#endif
@@ -796,18 +784,13 @@ static void curl_readv_bh_cb(void *p)
{
CURLState *state;
int running;
int ret = -EINPROGRESS;
CURLAIOCB *acb = p;
BlockDriverState *bs = acb->common.bs;
BDRVCURLState *s = bs->opaque;
AioContext *ctx = bdrv_get_aio_context(bs);
BDRVCURLState *s = acb->common.bs->opaque;
size_t start = acb->sector_num * BDRV_SECTOR_SIZE;
size_t end;
aio_context_acquire(ctx);
// In case we have the requested data already (e.g. read-ahead),
// we can just call the callback and be done.
switch (curl_find_buf(s, start, acb->nb_sectors * BDRV_SECTOR_SIZE, acb)) {
@@ -815,7 +798,7 @@ static void curl_readv_bh_cb(void *p)
qemu_aio_unref(acb);
// fall through
case FIND_RET_WAIT:
goto out;
return;
default:
break;
}
@@ -823,8 +806,9 @@ 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);
if (!state) {
ret = -EIO;
goto out;
acb->common.cb(acb->common.opaque, -EIO);
qemu_aio_unref(acb);
return;
}
acb->start = 0;
@@ -838,8 +822,9 @@ static void curl_readv_bh_cb(void *p)
state->orig_buf = g_try_malloc(state->buf_len);
if (state->buf_len && state->orig_buf == NULL) {
curl_clean_state(state);
ret = -ENOMEM;
goto out;
acb->common.cb(acb->common.opaque, -ENOMEM);
qemu_aio_unref(acb);
return;
}
state->acb[0] = acb;
@@ -852,13 +837,6 @@ static void curl_readv_bh_cb(void *p)
/* Tell curl it needs to kick things off */
curl_multi_socket_action(s->multi, CURL_SOCKET_TIMEOUT, 0, &running);
out:
aio_context_release(ctx);
if (ret != -EINPROGRESS) {
acb->common.cb(acb->common.opaque, ret);
qemu_aio_unref(acb);
}
}
static BlockAIOCB *curl_aio_readv(BlockDriverState *bs,

View File

@@ -413,12 +413,6 @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
int64_t offset;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
block_module_load_one("dmg-bz2");
bs->read_only = true;

View File

@@ -698,6 +698,13 @@ static struct glfs *qemu_gluster_init(BlockdevOptionsGluster *gconf,
return qemu_gluster_glfs_init(gconf, errp);
}
static void qemu_gluster_complete_aio(void *opaque)
{
GlusterAIOCB *acb = (GlusterAIOCB *)opaque;
qemu_coroutine_enter(acb->coroutine);
}
/*
* AIO callback routine called from GlusterFS thread.
*/
@@ -713,7 +720,7 @@ static void gluster_finish_aiocb(struct glfs_fd *fd, ssize_t ret, void *arg)
acb->ret = -EIO; /* Partial read/write - fail it */
}
aio_co_schedule(acb->aio_context, acb->coroutine);
aio_bh_schedule_oneshot(acb->aio_context, qemu_gluster_complete_aio, acb);
}
static void qemu_gluster_parse_flags(int bdrv_flags, int *open_flags)
@@ -1246,7 +1253,7 @@ static int qemu_gluster_has_zero_init(BlockDriverState *bs)
* If @start is in a trailing hole or beyond EOF, return -ENXIO.
* If we can't find out, return a negative errno other than -ENXIO.
*
* (Shamefully copied from file-posix.c, only miniscule adaptions.)
* (Shamefully copied from raw-posix.c, only miniscule adaptions.)
*/
static int find_allocation(BlockDriverState *bs, off_t start,
off_t *data, off_t *hole)
@@ -1342,7 +1349,7 @@ exit:
* 'nb_sectors' is the max value 'pnum' should be set to. If nb_sectors goes
* beyond the end of the disk image it will be clamped.
*
* (Based on raw_co_get_block_status() from file-posix.c.)
* (Based on raw_co_get_block_status() from raw-posix.c.)
*/
static int64_t coroutine_fn qemu_gluster_co_get_block_status(
BlockDriverState *bs, int64_t sector_num, int nb_sectors, int *pnum,

View File

@@ -189,7 +189,7 @@ static void bdrv_co_drain_bh_cb(void *opaque)
bdrv_dec_in_flight(bs);
bdrv_drained_begin(bs);
data->done = true;
aio_co_wake(co);
qemu_coroutine_enter(co);
}
static void coroutine_fn bdrv_co_yield_to_drain(BlockDriverState *bs)
@@ -228,7 +228,9 @@ void bdrv_drained_begin(BlockDriverState *bs)
bdrv_parent_drained_begin(bs);
}
bdrv_io_unplugged_begin(bs);
bdrv_drain_recurse(bs);
bdrv_io_unplugged_end(bs);
}
void bdrv_drained_end(BlockDriverState *bs)
@@ -300,6 +302,7 @@ void bdrv_drain_all_begin(void)
aio_context_acquire(aio_context);
bdrv_parent_drained_begin(bs);
bdrv_io_unplugged_begin(bs);
aio_disable_external(aio_context);
aio_context_release(aio_context);
@@ -344,6 +347,7 @@ void bdrv_drain_all_end(void)
aio_context_acquire(aio_context);
aio_enable_external(aio_context);
bdrv_io_unplugged_end(bs);
bdrv_parent_drained_end(bs);
aio_context_release(aio_context);
}
@@ -539,7 +543,7 @@ static bool coroutine_fn wait_serialising_requests(BdrvTrackedRequest *self)
* (instead of producing a deadlock in the former case). */
if (!req->waiting_for) {
self->waiting_for = req;
qemu_co_queue_wait(&req->wait_queue, NULL);
qemu_co_queue_wait(&req->wait_queue);
self->waiting_for = NULL;
retry = true;
waited = true;
@@ -813,7 +817,7 @@ static void bdrv_co_io_em_complete(void *opaque, int ret)
CoroutineIOCompletion *co = opaque;
co->ret = ret;
aio_co_wake(co->coroutine);
qemu_coroutine_enter(co->coroutine);
}
static int coroutine_fn bdrv_driver_preadv(BlockDriverState *bs,
@@ -2080,11 +2084,6 @@ void bdrv_aio_cancel(BlockAIOCB *acb)
if (acb->aiocb_info->get_aio_context) {
aio_poll(acb->aiocb_info->get_aio_context(acb), true);
} else if (acb->bs) {
/* qemu_aio_ref and qemu_aio_unref are not thread-safe, so
* assert that we're not using an I/O thread. Thread-safe
* code should use bdrv_aio_cancel_async exclusively.
*/
assert(bdrv_get_aio_context(acb->bs) == qemu_get_aio_context());
aio_poll(bdrv_get_aio_context(acb->bs), true);
} else {
abort();
@@ -2244,6 +2243,35 @@ BlockAIOCB *bdrv_aio_flush(BlockDriverState *bs,
return &acb->common;
}
void *qemu_aio_get(const AIOCBInfo *aiocb_info, BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque)
{
BlockAIOCB *acb;
acb = g_malloc(aiocb_info->aiocb_size);
acb->aiocb_info = aiocb_info;
acb->bs = bs;
acb->cb = cb;
acb->opaque = opaque;
acb->refcnt = 1;
return acb;
}
void qemu_aio_ref(void *p)
{
BlockAIOCB *acb = p;
acb->refcnt++;
}
void qemu_aio_unref(void *p)
{
BlockAIOCB *acb = p;
assert(acb->refcnt > 0);
if (--acb->refcnt == 0) {
g_free(acb);
}
}
/**************************************************************/
/* Coroutine block device emulation */
@@ -2275,7 +2303,7 @@ int coroutine_fn bdrv_co_flush(BlockDriverState *bs)
/* Wait until any previous flushes are completed */
while (bs->active_flush_req) {
qemu_co_queue_wait(&bs->flush_queue, NULL);
qemu_co_queue_wait(&bs->flush_queue);
}
bs->active_flush_req = true;
@@ -2622,7 +2650,7 @@ void bdrv_io_plug(BlockDriverState *bs)
bdrv_io_plug(child->bs);
}
if (bs->io_plugged++ == 0) {
if (bs->io_plugged++ == 0 && bs->io_plug_disabled == 0) {
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_io_plug) {
drv->bdrv_io_plug(bs);
@@ -2635,7 +2663,7 @@ void bdrv_io_unplug(BlockDriverState *bs)
BdrvChild *child;
assert(bs->io_plugged);
if (--bs->io_plugged == 0) {
if (--bs->io_plugged == 0 && bs->io_plug_disabled == 0) {
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_io_unplug) {
drv->bdrv_io_unplug(bs);
@@ -2646,3 +2674,36 @@ void bdrv_io_unplug(BlockDriverState *bs)
bdrv_io_unplug(child->bs);
}
}
void bdrv_io_unplugged_begin(BlockDriverState *bs)
{
BdrvChild *child;
if (bs->io_plug_disabled++ == 0 && bs->io_plugged > 0) {
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_io_unplug) {
drv->bdrv_io_unplug(bs);
}
}
QLIST_FOREACH(child, &bs->children, next) {
bdrv_io_unplugged_begin(child->bs);
}
}
void bdrv_io_unplugged_end(BlockDriverState *bs)
{
BdrvChild *child;
assert(bs->io_plug_disabled);
QLIST_FOREACH(child, &bs->children, next) {
bdrv_io_unplugged_end(child->bs);
}
if (--bs->io_plug_disabled == 0 && bs->io_plugged > 0) {
BlockDriver *drv = bs->drv;
if (drv && drv->bdrv_io_plug) {
drv->bdrv_io_plug(bs);
}
}
}

View File

@@ -1,69 +0,0 @@
/*
* QEMU Block driver for iSCSI images (static options)
*
* Copyright (c) 2017 Peter Lieven <pl@kamp.de>
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "qemu/config-file.h"
static QemuOptsList qemu_iscsi_opts = {
.name = "iscsi",
.head = QTAILQ_HEAD_INITIALIZER(qemu_iscsi_opts.head),
.desc = {
{
.name = "user",
.type = QEMU_OPT_STRING,
.help = "username for CHAP authentication to target",
},{
.name = "password",
.type = QEMU_OPT_STRING,
.help = "password for CHAP authentication to target",
},{
.name = "password-secret",
.type = QEMU_OPT_STRING,
.help = "ID of the secret providing password for CHAP "
"authentication to target",
},{
.name = "header-digest",
.type = QEMU_OPT_STRING,
.help = "HeaderDigest setting. "
"{CRC32C|CRC32C-NONE|NONE-CRC32C|NONE}",
},{
.name = "initiator-name",
.type = QEMU_OPT_STRING,
.help = "Initiator iqn name to use when connecting",
},{
.name = "timeout",
.type = QEMU_OPT_NUMBER,
.help = "Request timeout in seconds (default 0 = no timeout)",
},
{ /* end of list */ }
},
};
static void iscsi_block_opts_init(void)
{
qemu_add_opts(&qemu_iscsi_opts);
}
block_init(iscsi_block_opts_init);

View File

@@ -165,9 +165,8 @@ iscsi_schedule_bh(IscsiAIOCB *acb)
static void iscsi_co_generic_bh_cb(void *opaque)
{
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
aio_co_wake(iTask->co);
qemu_coroutine_enter(iTask->co);
}
static void iscsi_retry_timer_expired(void *opaque)
@@ -175,7 +174,7 @@ static void iscsi_retry_timer_expired(void *opaque)
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
if (iTask->co) {
aio_co_wake(iTask->co);
qemu_coroutine_enter(iTask->co);
}
}
@@ -363,7 +362,6 @@ iscsi_set_events(IscsiLun *iscsilun)
false,
(ev & POLLIN) ? iscsi_process_read : NULL,
(ev & POLLOUT) ? iscsi_process_write : NULL,
NULL,
iscsilun);
iscsilun->events = ev;
}
@@ -395,10 +393,8 @@ iscsi_process_read(void *arg)
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
aio_context_acquire(iscsilun->aio_context);
iscsi_service(iscsi, POLLIN);
iscsi_set_events(iscsilun);
aio_context_release(iscsilun->aio_context);
}
static void
@@ -407,10 +403,8 @@ iscsi_process_write(void *arg)
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
aio_context_acquire(iscsilun->aio_context);
iscsi_service(iscsi, POLLOUT);
iscsi_set_events(iscsilun);
aio_context_release(iscsilun->aio_context);
}
static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun)
@@ -1245,14 +1239,29 @@ retry:
return 0;
}
static void apply_chap(struct iscsi_context *iscsi, QemuOpts *opts,
static void parse_chap(struct iscsi_context *iscsi, const char *target,
Error **errp)
{
QemuOptsList *list;
QemuOpts *opts;
const char *user = NULL;
const char *password = NULL;
const char *secretid;
char *secret = NULL;
list = qemu_find_opts("iscsi");
if (!list) {
return;
}
opts = qemu_opts_find(list, target);
if (opts == NULL) {
opts = QTAILQ_FIRST(&list->head);
if (!opts) {
return;
}
}
user = qemu_opt_get(opts, "user");
if (!user) {
return;
@@ -1283,36 +1292,64 @@ static void apply_chap(struct iscsi_context *iscsi, QemuOpts *opts,
g_free(secret);
}
static void apply_header_digest(struct iscsi_context *iscsi, QemuOpts *opts,
static void parse_header_digest(struct iscsi_context *iscsi, const char *target,
Error **errp)
{
QemuOptsList *list;
QemuOpts *opts;
const char *digest = NULL;
list = qemu_find_opts("iscsi");
if (!list) {
return;
}
opts = qemu_opts_find(list, target);
if (opts == NULL) {
opts = QTAILQ_FIRST(&list->head);
if (!opts) {
return;
}
}
digest = qemu_opt_get(opts, "header-digest");
if (!digest) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
} else if (!strcmp(digest, "crc32c")) {
return;
}
if (!strcmp(digest, "CRC32C")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C);
} else if (!strcmp(digest, "none")) {
} else if (!strcmp(digest, "NONE")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE);
} else if (!strcmp(digest, "crc32c-none")) {
} else if (!strcmp(digest, "CRC32C-NONE")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_CRC32C_NONE);
} else if (!strcmp(digest, "none-crc32c")) {
} else if (!strcmp(digest, "NONE-CRC32C")) {
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
} else {
error_setg(errp, "Invalid header-digest setting : %s", digest);
}
}
static char *get_initiator_name(QemuOpts *opts)
static char *parse_initiator_name(const char *target)
{
QemuOptsList *list;
QemuOpts *opts;
const char *name;
char *iscsi_name;
UuidInfo *uuid_info;
name = qemu_opt_get(opts, "initiator-name");
if (name) {
return g_strdup(name);
list = qemu_find_opts("iscsi");
if (list) {
opts = qemu_opts_find(list, target);
if (!opts) {
opts = QTAILQ_FIRST(&list->head);
}
if (opts) {
name = qemu_opt_get(opts, "initiator-name");
if (name) {
return g_strdup(name);
}
}
}
uuid_info = qmp_query_uuid(NULL);
@@ -1327,24 +1364,43 @@ static char *get_initiator_name(QemuOpts *opts)
return iscsi_name;
}
static int parse_timeout(const char *target)
{
QemuOptsList *list;
QemuOpts *opts;
const char *timeout;
list = qemu_find_opts("iscsi");
if (list) {
opts = qemu_opts_find(list, target);
if (!opts) {
opts = QTAILQ_FIRST(&list->head);
}
if (opts) {
timeout = qemu_opt_get(opts, "timeout");
if (timeout) {
return atoi(timeout);
}
}
}
return 0;
}
static void iscsi_nop_timed_event(void *opaque)
{
IscsiLun *iscsilun = opaque;
aio_context_acquire(iscsilun->aio_context);
if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
error_report("iSCSI: NOP timeout. Reconnecting...");
iscsilun->request_timed_out = true;
} else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages.");
goto out;
return;
}
timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
iscsi_set_events(iscsilun);
out:
aio_context_release(iscsilun->aio_context);
}
static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
@@ -1417,6 +1473,20 @@ static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
}
}
/* TODO Convert to fine grained options */
static QemuOptsList runtime_opts = {
.name = "iscsi",
.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
.desc = {
{
.name = "filename",
.type = QEMU_OPT_STRING,
.help = "URL to the iscsi image",
},
{ /* end of list */ }
},
};
static struct scsi_task *iscsi_do_inquiry(struct iscsi_context *iscsi, int lun,
int evpd, int pc, void **inq, Error **errp)
{
@@ -1460,7 +1530,7 @@ static void iscsi_detach_aio_context(BlockDriverState *bs)
IscsiLun *iscsilun = bs->opaque;
aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsilun->iscsi),
false, NULL, NULL, NULL, NULL);
false, NULL, NULL, NULL);
iscsilun->events = 0;
if (iscsilun->nop_timer) {
@@ -1534,178 +1604,24 @@ out:
}
}
static void iscsi_parse_iscsi_option(const char *target, QDict *options)
{
QemuOptsList *list;
QemuOpts *opts;
const char *user, *password, *password_secret, *initiator_name,
*header_digest, *timeout;
list = qemu_find_opts("iscsi");
if (!list) {
return;
}
opts = qemu_opts_find(list, target);
if (opts == NULL) {
opts = QTAILQ_FIRST(&list->head);
if (!opts) {
return;
}
}
user = qemu_opt_get(opts, "user");
if (user) {
qdict_set_default_str(options, "user", user);
}
password = qemu_opt_get(opts, "password");
if (password) {
qdict_set_default_str(options, "password", password);
}
password_secret = qemu_opt_get(opts, "password-secret");
if (password_secret) {
qdict_set_default_str(options, "password-secret", password_secret);
}
initiator_name = qemu_opt_get(opts, "initiator-name");
if (initiator_name) {
qdict_set_default_str(options, "initiator-name", initiator_name);
}
header_digest = qemu_opt_get(opts, "header-digest");
if (header_digest) {
/* -iscsi takes upper case values, but QAPI only supports lower case
* enum constant names, so we have to convert here. */
char *qapi_value = g_ascii_strdown(header_digest, -1);
qdict_set_default_str(options, "header-digest", qapi_value);
g_free(qapi_value);
}
timeout = qemu_opt_get(opts, "timeout");
if (timeout) {
qdict_set_default_str(options, "timeout", timeout);
}
}
/*
* We support iscsi url's on the form
* iscsi://[<username>%<password>@]<host>[:<port>]/<targetname>/<lun>
*/
static void iscsi_parse_filename(const char *filename, QDict *options,
Error **errp)
{
struct iscsi_url *iscsi_url;
const char *transport_name;
char *lun_str;
iscsi_url = iscsi_parse_full_url(NULL, filename);
if (iscsi_url == NULL) {
error_setg(errp, "Failed to parse URL : %s", filename);
return;
}
#if LIBISCSI_API_VERSION >= (20160603)
switch (iscsi_url->transport) {
case TCP_TRANSPORT:
transport_name = "tcp";
break;
case ISER_TRANSPORT:
transport_name = "iser";
break;
default:
error_setg(errp, "Unknown transport type (%d)",
iscsi_url->transport);
return;
}
#else
transport_name = "tcp";
#endif
qdict_set_default_str(options, "transport", transport_name);
qdict_set_default_str(options, "portal", iscsi_url->portal);
qdict_set_default_str(options, "target", iscsi_url->target);
lun_str = g_strdup_printf("%d", iscsi_url->lun);
qdict_set_default_str(options, "lun", lun_str);
g_free(lun_str);
/* User/password from -iscsi take precedence over those from the URL */
iscsi_parse_iscsi_option(iscsi_url->target, options);
if (iscsi_url->user[0] != '\0') {
qdict_set_default_str(options, "user", iscsi_url->user);
qdict_set_default_str(options, "password", iscsi_url->passwd);
}
iscsi_destroy_url(iscsi_url);
}
static QemuOptsList runtime_opts = {
.name = "iscsi",
.head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
.desc = {
{
.name = "transport",
.type = QEMU_OPT_STRING,
},
{
.name = "portal",
.type = QEMU_OPT_STRING,
},
{
.name = "target",
.type = QEMU_OPT_STRING,
},
{
.name = "user",
.type = QEMU_OPT_STRING,
},
{
.name = "password",
.type = QEMU_OPT_STRING,
},
{
.name = "password-secret",
.type = QEMU_OPT_STRING,
},
{
.name = "lun",
.type = QEMU_OPT_NUMBER,
},
{
.name = "initiator-name",
.type = QEMU_OPT_STRING,
},
{
.name = "header-digest",
.type = QEMU_OPT_STRING,
},
{
.name = "timeout",
.type = QEMU_OPT_NUMBER,
},
{ /* end of list */ }
},
};
static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = NULL;
struct iscsi_url *iscsi_url = NULL;
struct scsi_task *task = NULL;
struct scsi_inquiry_standard *inq = NULL;
struct scsi_inquiry_supported_pages *inq_vpd;
char *initiator_name = NULL;
QemuOpts *opts;
Error *local_err = NULL;
const char *transport_name, *portal, *target;
#if LIBISCSI_API_VERSION >= (20160603)
enum iscsi_transport_type transport;
#endif
int i, ret = 0, timeout = 0, lun;
const char *filename;
int i, ret = 0, timeout = 0;
opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
@@ -1715,34 +1631,18 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
transport_name = qemu_opt_get(opts, "transport");
portal = qemu_opt_get(opts, "portal");
target = qemu_opt_get(opts, "target");
lun = qemu_opt_get_number(opts, "lun", 0);
filename = qemu_opt_get(opts, "filename");
if (!transport_name || !portal || !target) {
error_setg(errp, "Need all of transport, portal and target options");
ret = -EINVAL;
goto out;
}
if (!strcmp(transport_name, "tcp")) {
#if LIBISCSI_API_VERSION >= (20160603)
transport = TCP_TRANSPORT;
} else if (!strcmp(transport_name, "iser")) {
transport = ISER_TRANSPORT;
#else
/* TCP is what older libiscsi versions always use */
#endif
} else {
error_setg(errp, "Unknown transport: %s", transport_name);
iscsi_url = iscsi_parse_full_url(iscsi, filename);
if (iscsi_url == NULL) {
error_setg(errp, "Failed to parse URL : %s", filename);
ret = -EINVAL;
goto out;
}
memset(iscsilun, 0, sizeof(IscsiLun));
initiator_name = get_initiator_name(opts);
initiator_name = parse_initiator_name(iscsi_url->target);
iscsi = iscsi_create_context(initiator_name);
if (iscsi == NULL) {
@@ -1751,20 +1651,30 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
#if LIBISCSI_API_VERSION >= (20160603)
if (iscsi_init_transport(iscsi, transport)) {
if (iscsi_init_transport(iscsi, iscsi_url->transport)) {
error_setg(errp, ("Error initializing transport."));
ret = -EINVAL;
goto out;
}
#endif
if (iscsi_set_targetname(iscsi, target)) {
if (iscsi_set_targetname(iscsi, iscsi_url->target)) {
error_setg(errp, "iSCSI: Failed to set target name.");
ret = -EINVAL;
goto out;
}
if (iscsi_url->user[0] != '\0') {
ret = iscsi_set_initiator_username_pwd(iscsi, iscsi_url->user,
iscsi_url->passwd);
if (ret != 0) {
error_setg(errp, "Failed to set initiator username and password");
ret = -EINVAL;
goto out;
}
}
/* check if we got CHAP username/password via the options */
apply_chap(iscsi, opts, &local_err);
parse_chap(iscsi, iscsi_url->target, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
ret = -EINVAL;
@@ -1777,8 +1687,10 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
goto out;
}
iscsi_set_header_digest(iscsi, ISCSI_HEADER_DIGEST_NONE_CRC32C);
/* check if we got HEADER_DIGEST via the options */
apply_header_digest(iscsi, opts, &local_err);
parse_header_digest(iscsi, iscsi_url->target, &local_err);
if (local_err != NULL) {
error_propagate(errp, local_err);
ret = -EINVAL;
@@ -1786,7 +1698,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
}
/* timeout handling is broken in libiscsi before 1.15.0 */
timeout = qemu_opt_get_number(opts, "timeout", 0);
timeout = parse_timeout(iscsi_url->target);
#if LIBISCSI_API_VERSION >= 20150621
iscsi_set_timeout(iscsi, timeout);
#else
@@ -1795,7 +1707,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
}
#endif
if (iscsi_full_connect_sync(iscsi, portal, lun) != 0) {
if (iscsi_full_connect_sync(iscsi, iscsi_url->portal, iscsi_url->lun) != 0) {
error_setg(errp, "iSCSI: Failed to connect to LUN : %s",
iscsi_get_error(iscsi));
ret = -EINVAL;
@@ -1804,7 +1716,7 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
iscsilun->iscsi = iscsi;
iscsilun->aio_context = bdrv_get_aio_context(bs);
iscsilun->lun = lun;
iscsilun->lun = iscsi_url->lun;
iscsilun->has_write_same = true;
task = iscsi_do_inquiry(iscsilun->iscsi, iscsilun->lun, 0, 0,
@@ -1907,6 +1819,9 @@ static int iscsi_open(BlockDriverState *bs, QDict *options, int flags,
out:
qemu_opts_del(opts);
g_free(initiator_name);
if (iscsi_url != NULL) {
iscsi_destroy_url(iscsi_url);
}
if (task != NULL) {
scsi_free_scsi_task(task);
}
@@ -2115,15 +2030,15 @@ static BlockDriver bdrv_iscsi = {
.format_name = "iscsi",
.protocol_name = "iscsi",
.instance_size = sizeof(IscsiLun),
.bdrv_parse_filename = iscsi_parse_filename,
.bdrv_file_open = iscsi_open,
.bdrv_close = iscsi_close,
.bdrv_create = iscsi_create,
.create_opts = &iscsi_create_opts,
.bdrv_reopen_prepare = iscsi_reopen_prepare,
.bdrv_reopen_commit = iscsi_reopen_commit,
.bdrv_invalidate_cache = iscsi_invalidate_cache,
.instance_size = sizeof(IscsiLun),
.bdrv_needs_filename = true,
.bdrv_file_open = iscsi_open,
.bdrv_close = iscsi_close,
.bdrv_create = iscsi_create,
.create_opts = &iscsi_create_opts,
.bdrv_reopen_prepare = iscsi_reopen_prepare,
.bdrv_reopen_commit = iscsi_reopen_commit,
.bdrv_invalidate_cache = iscsi_invalidate_cache,
.bdrv_getlength = iscsi_getlength,
.bdrv_get_info = iscsi_get_info,
@@ -2150,15 +2065,15 @@ static BlockDriver bdrv_iser = {
.format_name = "iser",
.protocol_name = "iser",
.instance_size = sizeof(IscsiLun),
.bdrv_parse_filename = iscsi_parse_filename,
.bdrv_file_open = iscsi_open,
.bdrv_close = iscsi_close,
.bdrv_create = iscsi_create,
.create_opts = &iscsi_create_opts,
.bdrv_reopen_prepare = iscsi_reopen_prepare,
.bdrv_reopen_commit = iscsi_reopen_commit,
.bdrv_invalidate_cache = iscsi_invalidate_cache,
.instance_size = sizeof(IscsiLun),
.bdrv_needs_filename = true,
.bdrv_file_open = iscsi_open,
.bdrv_close = iscsi_close,
.bdrv_create = iscsi_create,
.create_opts = &iscsi_create_opts,
.bdrv_reopen_prepare = iscsi_reopen_prepare,
.bdrv_reopen_commit = iscsi_reopen_commit,
.bdrv_invalidate_cache = iscsi_invalidate_cache,
.bdrv_getlength = iscsi_getlength,
.bdrv_get_info = iscsi_get_info,

View File

@@ -54,10 +54,10 @@ struct LinuxAioState {
io_context_t ctx;
EventNotifier e;
/* io queue for submit at batch. Protected by AioContext lock. */
/* io queue for submit at batch */
LaioQueue io_q;
/* I/O completion processing. Only runs in I/O thread. */
/* I/O completion processing */
QEMUBH *completion_bh;
int event_idx;
int event_max;
@@ -100,7 +100,7 @@ static void qemu_laio_process_completion(struct qemu_laiocb *laiocb)
* that!
*/
if (!qemu_coroutine_entered(laiocb->co)) {
aio_co_wake(laiocb->co);
qemu_coroutine_enter(laiocb->co);
}
} else {
laiocb->common.cb(laiocb->common.opaque, ret);
@@ -234,12 +234,9 @@ static void qemu_laio_process_completions(LinuxAioState *s)
static void qemu_laio_process_completions_and_submit(LinuxAioState *s)
{
qemu_laio_process_completions(s);
aio_context_acquire(s->aio_context);
if (!s->io_q.plugged && !QSIMPLEQ_EMPTY(&s->io_q.pending)) {
ioq_submit(s);
}
aio_context_release(s->aio_context);
}
static void qemu_laio_completion_bh(void *opaque)
@@ -258,20 +255,6 @@ static void qemu_laio_completion_cb(EventNotifier *e)
}
}
static bool qemu_laio_poll_cb(void *opaque)
{
EventNotifier *e = opaque;
LinuxAioState *s = container_of(e, LinuxAioState, e);
struct io_event *events;
if (!io_getevents_peek(s->ctx, &events)) {
return false;
}
qemu_laio_process_completions_and_submit(s);
return true;
}
static void laio_cancel(BlockAIOCB *blockacb)
{
struct qemu_laiocb *laiocb = (struct qemu_laiocb *)blockacb;
@@ -456,9 +439,8 @@ BlockAIOCB *laio_submit(BlockDriverState *bs, LinuxAioState *s, int fd,
void laio_detach_aio_context(LinuxAioState *s, AioContext *old_context)
{
aio_set_event_notifier(old_context, &s->e, false, NULL, NULL);
aio_set_event_notifier(old_context, &s->e, false, NULL);
qemu_bh_delete(s->completion_bh);
s->aio_context = NULL;
}
void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)
@@ -466,8 +448,7 @@ void laio_attach_aio_context(LinuxAioState *s, AioContext *new_context)
s->aio_context = new_context;
s->completion_bh = aio_bh_new(new_context, qemu_laio_completion_bh, s);
aio_set_event_notifier(new_context, &s->e, false,
qemu_laio_completion_cb,
qemu_laio_poll_cb);
qemu_laio_completion_cb);
}
LinuxAioState *laio_init(void)

View File

@@ -69,7 +69,6 @@ typedef struct MirrorBlockJob {
bool waiting_for_io;
int target_cluster_sectors;
int max_iov;
bool initial_zeroing_ongoing;
} MirrorBlockJob;
typedef struct MirrorOp {
@@ -118,10 +117,9 @@ static void mirror_iteration_done(MirrorOp *op, int ret)
if (s->cow_bitmap) {
bitmap_set(s->cow_bitmap, chunk_num, nb_chunks);
}
if (!s->initial_zeroing_ongoing) {
s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
}
s->common.offset += (uint64_t)op->nb_sectors * BDRV_SECTOR_SIZE;
}
qemu_iovec_destroy(&op->qiov);
g_free(op);
@@ -134,8 +132,6 @@ static void mirror_write_complete(void *opaque, int ret)
{
MirrorOp *op = opaque;
MirrorBlockJob *s = op->s;
aio_context_acquire(blk_get_aio_context(s->common.blk));
if (ret < 0) {
BlockErrorAction action;
@@ -146,15 +142,12 @@ static void mirror_write_complete(void *opaque, int ret)
}
}
mirror_iteration_done(op, ret);
aio_context_release(blk_get_aio_context(s->common.blk));
}
static void mirror_read_complete(void *opaque, int ret)
{
MirrorOp *op = opaque;
MirrorBlockJob *s = op->s;
aio_context_acquire(blk_get_aio_context(s->common.blk));
if (ret < 0) {
BlockErrorAction action;
@@ -165,11 +158,10 @@ static void mirror_read_complete(void *opaque, int ret)
}
mirror_iteration_done(op, ret);
} else {
blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov,
0, mirror_write_complete, op);
return;
}
aio_context_release(blk_get_aio_context(s->common.blk));
blk_aio_pwritev(s->target, op->sector_num * BDRV_SECTOR_SIZE, &op->qiov,
0, mirror_write_complete, op);
}
static inline void mirror_clip_sectors(MirrorBlockJob *s,
@@ -574,7 +566,6 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
return 0;
}
s->initial_zeroing_ongoing = true;
for (sector_num = 0; sector_num < end; ) {
int nb_sectors = MIN(end - sector_num,
QEMU_ALIGN_DOWN(INT_MAX, s->granularity) >> BDRV_SECTOR_BITS);
@@ -582,7 +573,6 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
mirror_throttle(s);
if (block_job_is_cancelled(&s->common)) {
s->initial_zeroing_ongoing = false;
return 0;
}
@@ -597,7 +587,6 @@ static int coroutine_fn mirror_dirty_init(MirrorBlockJob *s)
}
mirror_wait_for_all_io(s);
s->initial_zeroing_ongoing = false;
}
/* First part, loop on the sectors and initialize the dirty bitmap. */
@@ -662,28 +651,7 @@ static void coroutine_fn mirror_run(void *opaque)
if (s->bdev_length < 0) {
ret = s->bdev_length;
goto immediate_exit;
}
/* Active commit must resize the base image if its size differs from the
* active layer. */
if (s->base == blk_bs(s->target)) {
int64_t base_length;
base_length = blk_getlength(s->target);
if (base_length < 0) {
ret = base_length;
goto immediate_exit;
}
if (s->bdev_length > base_length) {
ret = blk_truncate(s->target, s->bdev_length);
if (ret < 0) {
goto immediate_exit;
}
}
}
if (s->bdev_length == 0) {
} else if (s->bdev_length == 0) {
/* Report BLOCK_JOB_READY and wait for complete. */
block_job_event_ready(&s->common);
s->synced = true;
@@ -1084,7 +1052,9 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
BlockCompletionFunc *cb, void *opaque, Error **errp,
bool auto_complete)
{
int64_t length, base_length;
int orig_base_flags;
int ret;
Error *local_err = NULL;
orig_base_flags = bdrv_get_flags(base);
@@ -1093,6 +1063,31 @@ void commit_active_start(const char *job_id, BlockDriverState *bs,
return;
}
length = bdrv_getlength(bs);
if (length < 0) {
error_setg_errno(errp, -length,
"Unable to determine length of %s", bs->filename);
goto error_restore_flags;
}
base_length = bdrv_getlength(base);
if (base_length < 0) {
error_setg_errno(errp, -base_length,
"Unable to determine length of %s", base->filename);
goto error_restore_flags;
}
if (length > base_length) {
ret = bdrv_truncate(base, length);
if (ret < 0) {
error_setg_errno(errp, -ret,
"Top image %s is larger than base image %s, and "
"resize of base image failed",
bs->filename, base->filename);
goto error_restore_flags;
}
}
mirror_start_job(job_id, bs, creation_flags, base, NULL, speed, 0, 0,
MIRROR_LEAVE_BACKING_CHAIN,
on_error, on_error, true, cb, opaque, &local_err,

View File

@@ -33,9 +33,8 @@
#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
#define INDEX_TO_HANDLE(bs, index) ((index) ^ ((uint64_t)(intptr_t)bs))
static void nbd_recv_coroutines_enter_all(BlockDriverState *bs)
static void nbd_recv_coroutines_enter_all(NBDClientSession *s)
{
NBDClientSession *s = nbd_get_client_session(bs);
int i;
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
@@ -43,7 +42,6 @@ static void nbd_recv_coroutines_enter_all(BlockDriverState *bs)
qemu_coroutine_enter(s->recv_coroutine[i]);
}
}
BDRV_POLL_WHILE(bs, s->read_reply_co);
}
static void nbd_teardown_connection(BlockDriverState *bs)
@@ -58,7 +56,7 @@ static void nbd_teardown_connection(BlockDriverState *bs)
qio_channel_shutdown(client->ioc,
QIO_CHANNEL_SHUTDOWN_BOTH,
NULL);
nbd_recv_coroutines_enter_all(bs);
nbd_recv_coroutines_enter_all(client);
nbd_client_detach_aio_context(bs);
object_unref(OBJECT(client->sioc));
@@ -67,43 +65,54 @@ static void nbd_teardown_connection(BlockDriverState *bs)
client->ioc = NULL;
}
static coroutine_fn void nbd_read_reply_entry(void *opaque)
static void nbd_reply_ready(void *opaque)
{
NBDClientSession *s = opaque;
BlockDriverState *bs = opaque;
NBDClientSession *s = nbd_get_client_session(bs);
uint64_t i;
int ret;
for (;;) {
assert(s->reply.handle == 0);
ret = nbd_receive_reply(s->ioc, &s->reply);
if (ret < 0) {
break;
}
/* There's no need for a mutex on the receive side, because the
* handler acts as a synchronization point and ensures that only
* one coroutine is called until the reply finishes.
*/
i = HANDLE_TO_INDEX(s, s->reply.handle);
if (i >= MAX_NBD_REQUESTS || !s->recv_coroutine[i]) {
break;
}
/* We're woken up by the recv_coroutine itself. Note that there
* is no race between yielding and reentering read_reply_co. This
* is because:
*
* - if recv_coroutine[i] runs on the same AioContext, it is only
* entered after we yield
*
* - if recv_coroutine[i] runs on a different AioContext, reentering
* read_reply_co happens through a bottom half, which can only
* run after we yield.
*/
aio_co_wake(s->recv_coroutine[i]);
qemu_coroutine_yield();
if (!s->ioc) { /* Already closed */
return;
}
s->read_reply_co = NULL;
if (s->reply.handle == 0) {
/* No reply already in flight. Fetch a header. It is possible
* that another thread has done the same thing in parallel, so
* the socket is not readable anymore.
*/
ret = nbd_receive_reply(s->ioc, &s->reply);
if (ret == -EAGAIN) {
return;
}
if (ret < 0) {
s->reply.handle = 0;
goto fail;
}
}
/* There's no need for a mutex on the receive side, because the
* handler acts as a synchronization point and ensures that only
* one coroutine is called until the reply finishes. */
i = HANDLE_TO_INDEX(s, s->reply.handle);
if (i >= MAX_NBD_REQUESTS) {
goto fail;
}
if (s->recv_coroutine[i]) {
qemu_coroutine_enter(s->recv_coroutine[i]);
return;
}
fail:
nbd_teardown_connection(bs);
}
static void nbd_restart_write(void *opaque)
{
BlockDriverState *bs = opaque;
qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine);
}
static int nbd_co_send_request(BlockDriverState *bs,
@@ -111,6 +120,7 @@ static int nbd_co_send_request(BlockDriverState *bs,
QEMUIOVector *qiov)
{
NBDClientSession *s = nbd_get_client_session(bs);
AioContext *aio_context;
int rc, ret, i;
qemu_co_mutex_lock(&s->send_mutex);
@@ -131,6 +141,11 @@ static int nbd_co_send_request(BlockDriverState *bs,
return -EPIPE;
}
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(bs);
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, nbd_restart_write, bs);
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
@@ -145,6 +160,9 @@ static int nbd_co_send_request(BlockDriverState *bs,
} else {
rc = nbd_send_request(s->ioc, request);
}
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, NULL, bs);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
@@ -156,7 +174,8 @@ static void nbd_co_receive_reply(NBDClientSession *s,
{
int ret;
/* Wait until we're woken up by nbd_read_reply_entry. */
/* Wait until we're woken up by the read handler. TODO: perhaps
* peek at the next reply and avoid yielding if it's ours? */
qemu_coroutine_yield();
*reply = s->reply;
if (reply->handle != request->handle ||
@@ -182,7 +201,7 @@ static void nbd_coroutine_start(NBDClientSession *s,
/* Poor man semaphore. The free_sema is locked when no other request
* can be accepted, and unlocked after receiving one reply. */
if (s->in_flight == MAX_NBD_REQUESTS) {
qemu_co_queue_wait(&s->free_sema, NULL);
qemu_co_queue_wait(&s->free_sema);
assert(s->in_flight < MAX_NBD_REQUESTS);
}
s->in_flight++;
@@ -190,19 +209,13 @@ static void nbd_coroutine_start(NBDClientSession *s,
/* s->recv_coroutine[i] is set as soon as we get the send_lock. */
}
static void nbd_coroutine_end(BlockDriverState *bs,
static void nbd_coroutine_end(NBDClientSession *s,
NBDRequest *request)
{
NBDClientSession *s = nbd_get_client_session(bs);
int i = HANDLE_TO_INDEX(s, request->handle);
s->recv_coroutine[i] = NULL;
s->in_flight--;
qemu_co_queue_next(&s->free_sema);
/* Kick the read_reply_co to get the next reply. */
if (s->read_reply_co) {
aio_co_wake(s->read_reply_co);
if (s->in_flight-- == MAX_NBD_REQUESTS) {
qemu_co_queue_next(&s->free_sema);
}
}
@@ -228,7 +241,7 @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset,
} else {
nbd_co_receive_reply(client, &request, &reply, qiov);
}
nbd_coroutine_end(bs, &request);
nbd_coroutine_end(client, &request);
return -reply.error;
}
@@ -258,7 +271,7 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset,
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
nbd_coroutine_end(client, &request);
return -reply.error;
}
@@ -293,7 +306,7 @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset,
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
nbd_coroutine_end(client, &request);
return -reply.error;
}
@@ -318,7 +331,7 @@ int nbd_client_co_flush(BlockDriverState *bs)
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
nbd_coroutine_end(client, &request);
return -reply.error;
}
@@ -344,23 +357,23 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int count)
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(bs, &request);
nbd_coroutine_end(client, &request);
return -reply.error;
}
void nbd_client_detach_aio_context(BlockDriverState *bs)
{
NBDClientSession *client = nbd_get_client_session(bs);
qio_channel_detach_aio_context(QIO_CHANNEL(client->sioc));
aio_set_fd_handler(bdrv_get_aio_context(bs),
nbd_get_client_session(bs)->sioc->fd,
false, NULL, NULL, NULL);
}
void nbd_client_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
NBDClientSession *client = nbd_get_client_session(bs);
qio_channel_attach_aio_context(QIO_CHANNEL(client->sioc), new_context);
aio_co_schedule(new_context, client->read_reply_co);
aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sioc->fd,
false, nbd_reply_ready, NULL, bs);
}
void nbd_client_close(BlockDriverState *bs)
@@ -421,7 +434,7 @@ int nbd_client_init(BlockDriverState *bs,
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
client->read_reply_co = qemu_coroutine_create(nbd_read_reply_entry, client);
nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
logout("Established connection with NBD server\n");

View File

@@ -25,7 +25,7 @@ typedef struct NBDClientSession {
CoMutex send_mutex;
CoQueue free_sema;
Coroutine *read_reply_co;
Coroutine *send_coroutine;
int in_flight;
Coroutine *recv_coroutine[MAX_NBD_REQUESTS];

View File

@@ -537,6 +537,8 @@ static void nbd_refresh_filename(BlockDriverState *bs, QDict *options)
visit_type_SocketAddress(ov, NULL, &s->saddr, &error_abort);
visit_complete(ov, &saddr_qdict);
visit_free(ov);
assert(qobject_type(saddr_qdict) == QTYPE_QDICT);
qdict_put_obj(opts, "server", saddr_qdict);
if (s->export) {

View File

@@ -198,8 +198,7 @@ static void nfs_set_events(NFSClient *client)
aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
false,
(ev & POLLIN) ? nfs_process_read : NULL,
(ev & POLLOUT) ? nfs_process_write : NULL,
NULL, client);
(ev & POLLOUT) ? nfs_process_write : NULL, client);
}
client->events = ev;
@@ -208,21 +207,15 @@ static void nfs_set_events(NFSClient *client)
static void nfs_process_read(void *arg)
{
NFSClient *client = arg;
aio_context_acquire(client->aio_context);
nfs_service(client->context, POLLIN);
nfs_set_events(client);
aio_context_release(client->aio_context);
}
static void nfs_process_write(void *arg)
{
NFSClient *client = arg;
aio_context_acquire(client->aio_context);
nfs_service(client->context, POLLOUT);
nfs_set_events(client);
aio_context_release(client->aio_context);
}
static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
@@ -237,9 +230,8 @@ static void nfs_co_init_task(BlockDriverState *bs, NFSRPC *task)
static void nfs_co_generic_bh_cb(void *opaque)
{
NFSRPC *task = opaque;
task->complete = 1;
aio_co_wake(task->co);
qemu_coroutine_enter(task->co);
}
static void
@@ -263,9 +255,9 @@ nfs_co_generic_cb(int ret, struct nfs_context *nfs, void *data,
nfs_co_generic_bh_cb, task);
}
static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *iov,
int flags)
static int coroutine_fn nfs_co_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *iov)
{
NFSClient *client = bs->opaque;
NFSRPC task;
@@ -274,7 +266,9 @@ static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
task.iov = iov;
if (nfs_pread_async(client->context, client->fh,
offset, bytes, nfs_co_generic_cb, &task) != 0) {
sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE,
nfs_co_generic_cb, &task) != 0) {
return -ENOMEM;
}
@@ -295,34 +289,28 @@ static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
return 0;
}
static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *iov,
int flags)
static int coroutine_fn nfs_co_writev(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *iov)
{
NFSClient *client = bs->opaque;
NFSRPC task;
char *buf = NULL;
bool my_buffer = false;
nfs_co_init_task(bs, &task);
if (iov->niov != 1) {
buf = g_try_malloc(bytes);
if (bytes && buf == NULL) {
return -ENOMEM;
}
qemu_iovec_to_buf(iov, 0, buf, bytes);
my_buffer = true;
} else {
buf = iov->iov[0].iov_base;
buf = g_try_malloc(nb_sectors * BDRV_SECTOR_SIZE);
if (nb_sectors && buf == NULL) {
return -ENOMEM;
}
qemu_iovec_to_buf(iov, 0, buf, nb_sectors * BDRV_SECTOR_SIZE);
if (nfs_pwrite_async(client->context, client->fh,
offset, bytes, buf,
nfs_co_generic_cb, &task) != 0) {
if (my_buffer) {
g_free(buf);
}
sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE,
buf, nfs_co_generic_cb, &task) != 0) {
g_free(buf);
return -ENOMEM;
}
@@ -331,11 +319,9 @@ static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
qemu_coroutine_yield();
}
if (my_buffer) {
g_free(buf);
}
g_free(buf);
if (task.ret != bytes) {
if (task.ret != nb_sectors * BDRV_SECTOR_SIZE) {
return task.ret < 0 ? task.ret : -EIO;
}
@@ -410,7 +396,7 @@ static void nfs_detach_aio_context(BlockDriverState *bs)
NFSClient *client = bs->opaque;
aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
false, NULL, NULL, NULL, NULL);
false, NULL, NULL, NULL);
client->events = 0;
}
@@ -430,7 +416,7 @@ static void nfs_client_close(NFSClient *client)
nfs_close(client->context, client->fh);
}
aio_set_fd_handler(client->aio_context, nfs_get_fd(client->context),
false, NULL, NULL, NULL, NULL);
false, NULL, NULL, NULL);
nfs_destroy_context(client->context);
}
memset(client, 0, sizeof(NFSClient));
@@ -811,6 +797,8 @@ static void nfs_refresh_filename(BlockDriverState *bs, QDict *options)
ov = qobject_output_visitor_new(&server_qdict);
visit_type_NFSServer(ov, NULL, &client->server, &error_abort);
visit_complete(ov, &server_qdict);
assert(qobject_type(server_qdict) == QTYPE_QDICT);
qdict_put_obj(opts, "server", server_qdict);
qdict_put(opts, "path", qstring_from_str(client->path));
@@ -867,8 +855,8 @@ static BlockDriver bdrv_nfs = {
.bdrv_create = nfs_file_create,
.bdrv_reopen_prepare = nfs_reopen_prepare,
.bdrv_co_preadv = nfs_co_preadv,
.bdrv_co_pwritev = nfs_co_pwritev,
.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,

View File

@@ -215,7 +215,7 @@ static int64_t allocate_clusters(BlockDriverState *bs, int64_t sector_num,
s->data_end << BDRV_SECTOR_BITS,
space << BDRV_SECTOR_BITS, 0);
} else {
ret = bdrv_truncate(bs->file,
ret = bdrv_truncate(bs->file->bs,
(s->data_end + space) << BDRV_SECTOR_BITS);
}
if (ret < 0) {
@@ -449,7 +449,7 @@ static int parallels_check(BlockDriverState *bs, BdrvCheckResult *res,
size - res->image_end_offset);
res->leaks += count;
if (fix & BDRV_FIX_LEAKS) {
ret = bdrv_truncate(bs->file, res->image_end_offset);
ret = bdrv_truncate(bs->file->bs, res->image_end_offset);
if (ret < 0) {
res->check_errors++;
return ret;
@@ -581,12 +581,6 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
Error *local_err = NULL;
char *buf;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
ret = bdrv_pread(bs->file, 0, &ph, sizeof(ph));
if (ret < 0) {
goto fail;
@@ -687,7 +681,7 @@ static int parallels_open(BlockDriverState *bs, QDict *options, int flags,
goto fail_options;
}
if (!bdrv_has_zero_init(bs->file->bs) ||
bdrv_truncate(bs->file, bdrv_getlength(bs->file->bs)) != 0) {
bdrv_truncate(bs->file->bs, bdrv_getlength(bs->file->bs)) != 0) {
s->prealloc_mode = PRL_PREALLOC_MODE_FALLOCATE;
}
@@ -730,7 +724,7 @@ static void parallels_close(BlockDriverState *bs)
}
if (bs->open_flags & BDRV_O_RDWR) {
bdrv_truncate(bs->file, s->data_end << BDRV_SECTOR_BITS);
bdrv_truncate(bs->file->bs, s->data_end << BDRV_SECTOR_BITS);
}
g_free(s->bat_dirty_bmap);

View File

@@ -237,8 +237,8 @@ void bdrv_query_image_info(BlockDriverState *bs,
size = bdrv_getlength(bs);
if (size < 0) {
error_setg_errno(errp, -size, "Can't get image size '%s'",
bs->exact_filename);
error_setg_errno(errp, -size, "Can't get size of device '%s'",
bdrv_get_device_name(bs));
goto out;
}
@@ -357,6 +357,10 @@ static void bdrv_query_info(BlockBackend *blk, BlockInfo **p_info,
qapi_free_BlockInfo(info);
}
static BlockStats *bdrv_query_stats(BlockBackend *blk,
const BlockDriverState *bs,
bool query_backing);
static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
{
BlockAcctStats *stats = blk_get_stats(blk);
@@ -424,18 +428,9 @@ static void bdrv_query_blk_stats(BlockDeviceStats *ds, BlockBackend *blk)
}
}
static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
static void bdrv_query_bds_stats(BlockStats *s, const BlockDriverState *bs,
bool query_backing)
{
BlockStats *s = NULL;
s = g_malloc0(sizeof(*s));
s->stats = g_malloc0(sizeof(*s->stats));
if (!bs) {
return s;
}
if (bdrv_get_node_name(bs)[0]) {
s->has_node_name = true;
s->node_name = g_strdup(bdrv_get_node_name(bs));
@@ -445,12 +440,32 @@ static BlockStats *bdrv_query_bds_stats(const BlockDriverState *bs,
if (bs->file) {
s->has_parent = true;
s->parent = bdrv_query_bds_stats(bs->file->bs, query_backing);
s->parent = bdrv_query_stats(NULL, bs->file->bs, query_backing);
}
if (query_backing && bs->backing) {
s->has_backing = true;
s->backing = bdrv_query_bds_stats(bs->backing->bs, query_backing);
s->backing = bdrv_query_stats(NULL, bs->backing->bs, query_backing);
}
}
static BlockStats *bdrv_query_stats(BlockBackend *blk,
const BlockDriverState *bs,
bool query_backing)
{
BlockStats *s;
s = g_malloc0(sizeof(*s));
s->stats = g_malloc0(sizeof(*s->stats));
if (blk) {
s->has_device = true;
s->device = g_strdup(blk_name(blk));
bdrv_query_blk_stats(s->stats, blk);
}
if (bs) {
bdrv_query_bds_stats(s, bs, query_backing);
}
return s;
@@ -479,44 +494,42 @@ BlockInfoList *qmp_query_block(Error **errp)
return head;
}
static bool next_query_bds(BlockBackend **blk, BlockDriverState **bs,
bool query_nodes)
{
if (query_nodes) {
*bs = bdrv_next_node(*bs);
return !!*bs;
}
*blk = blk_next(*blk);
*bs = *blk ? blk_bs(*blk) : NULL;
return !!*blk;
}
BlockStatsList *qmp_query_blockstats(bool has_query_nodes,
bool query_nodes,
Error **errp)
{
BlockStatsList *head = NULL, **p_next = &head;
BlockBackend *blk;
BlockDriverState *bs;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
/* Just to be safe if query_nodes is not always initialized */
if (has_query_nodes && query_nodes) {
for (bs = bdrv_next_node(NULL); bs; bs = bdrv_next_node(bs)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = bdrv_get_aio_context(bs);
query_nodes = has_query_nodes && query_nodes;
aio_context_acquire(ctx);
info->value = bdrv_query_bds_stats(bs, false);
aio_context_release(ctx);
while (next_query_bds(&blk, &bs, query_nodes)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk ? blk_get_aio_context(blk)
: bdrv_get_aio_context(bs);
*p_next = info;
p_next = &info->next;
}
} else {
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
BlockStatsList *info = g_malloc0(sizeof(*info));
AioContext *ctx = blk_get_aio_context(blk);
BlockStats *s;
aio_context_acquire(ctx);
info->value = bdrv_query_stats(blk, bs, !query_nodes);
aio_context_release(ctx);
aio_context_acquire(ctx);
s = bdrv_query_bds_stats(blk_bs(blk), true);
s->has_device = true;
s->device = g_strdup(blk_name(blk));
bdrv_query_blk_stats(s->stats, blk);
aio_context_release(ctx);
info->value = s;
*p_next = info;
p_next = &info->next;
}
*p_next = info;
p_next = &info->next;
}
return head;
@@ -682,6 +695,7 @@ void bdrv_image_info_specific_dump(fprintf_function func_fprintf, void *f,
visit_type_ImageInfoSpecific(v, NULL, &info_spec, &error_abort);
visit_complete(v, &obj);
assert(qobject_type(obj) == QTYPE_QDICT);
data = qdict_get(qobject_to_qdict(obj), "data");
dump_qobject(func_fprintf, f, 1, data);
qobject_decref(obj);

View File

@@ -104,13 +104,6 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
unsigned int len, i, shift;
int ret;
QCowHeader header;
Error *local_err = NULL;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
ret = bdrv_pread(bs->file, 0, &header, sizeof(header));
if (ret < 0) {
@@ -259,12 +252,7 @@ static int qcow_open(BlockDriverState *bs, QDict *options, int flags,
error_setg(&s->migration_blocker, "The qcow format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail;
}
migrate_add_blocker(s->migration_blocker);
qemu_co_mutex_init(&s->lock);
return 0;
@@ -473,7 +461,7 @@ static uint64_t get_cluster_offset(BlockDriverState *bs,
/* round to cluster size */
cluster_offset = (cluster_offset + s->cluster_size - 1) &
~(s->cluster_size - 1);
bdrv_truncate(bs->file, cluster_offset + s->cluster_size);
bdrv_truncate(bs->file->bs, cluster_offset + s->cluster_size);
/* if encrypted, we must initialize the cluster
content which won't be written */
if (bs->encrypted &&
@@ -915,7 +903,7 @@ static int qcow_make_empty(BlockDriverState *bs)
if (bdrv_pwrite_sync(bs->file, s->l1_table_offset, s->l1_table,
l1_length) < 0)
return -1;
ret = bdrv_truncate(bs->file, s->l1_table_offset + l1_length);
ret = bdrv_truncate(bs->file->bs, s->l1_table_offset + l1_length);
if (ret < 0)
return ret;

View File

@@ -932,7 +932,9 @@ static int handle_dependencies(BlockDriverState *bs, uint64_t guest_offset,
if (bytes == 0) {
/* Wait for the dependency to complete. We need to recheck
* the free/allocated clusters when we continue. */
qemu_co_queue_wait(&old_alloc->dependent_requests, &s->lock);
qemu_co_mutex_unlock(&s->lock);
qemu_co_queue_wait(&old_alloc->dependent_requests);
qemu_co_mutex_lock(&s->lock);
return -EAGAIN;
}
}

View File

@@ -83,16 +83,6 @@ static Qcow2SetRefcountFunc *const set_refcount_funcs[] = {
/*********************************************************/
/* refcount handling */
static void update_max_refcount_table_index(BDRVQcow2State *s)
{
unsigned i = s->refcount_table_size - 1;
while (i > 0 && (s->refcount_table[i] & REFT_OFFSET_MASK) == 0) {
i--;
}
/* Set s->max_refcount_table_index to the index of the last used entry */
s->max_refcount_table_index = i;
}
int qcow2_refcount_init(BlockDriverState *bs)
{
BDRVQcow2State *s = bs->opaque;
@@ -121,7 +111,6 @@ int qcow2_refcount_init(BlockDriverState *bs)
}
for(i = 0; i < s->refcount_table_size; i++)
be64_to_cpus(&s->refcount_table[i]);
update_max_refcount_table_index(s);
}
return 0;
fail:
@@ -450,10 +439,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
}
s->refcount_table[refcount_table_index] = new_block;
/* If there's a hole in s->refcount_table then it can happen
* that refcount_table_index < s->max_refcount_table_index */
s->max_refcount_table_index =
MAX(s->max_refcount_table_index, refcount_table_index);
/* The new refcount block may be where the caller intended to put its
* data, so let it restart the search. */
@@ -595,7 +580,6 @@ static int alloc_refcount_block(BlockDriverState *bs,
s->refcount_table = new_table;
s->refcount_table_size = table_size;
s->refcount_table_offset = table_offset;
update_max_refcount_table_index(s);
/* Free old table. */
qcow2_free_clusters(bs, old_table_offset, old_table_size * sizeof(uint64_t),
@@ -1734,7 +1718,7 @@ static int check_refblocks(BlockDriverState *bs, BdrvCheckResult *res,
goto resize_fail;
}
ret = bdrv_truncate(bs->file, offset + s->cluster_size);
ret = bdrv_truncate(bs->file->bs, offset + s->cluster_size);
if (ret < 0) {
goto resize_fail;
}
@@ -2187,7 +2171,6 @@ write_refblocks:
s->refcount_table = on_disk_reftable;
s->refcount_table_offset = reftable_offset;
s->refcount_table_size = reftable_size;
update_max_refcount_table_index(s);
return 0;
@@ -2400,11 +2383,7 @@ int qcow2_check_metadata_overlap(BlockDriverState *bs, int ign, int64_t offset,
}
if ((chk & QCOW2_OL_REFCOUNT_BLOCK) && s->refcount_table) {
unsigned last_entry = s->max_refcount_table_index;
assert(last_entry < s->refcount_table_size);
assert(last_entry + 1 == s->refcount_table_size ||
(s->refcount_table[last_entry + 1] & REFT_OFFSET_MASK) == 0);
for (i = 0; i <= last_entry; i++) {
for (i = 0; i < s->refcount_table_size; i++) {
if ((s->refcount_table[i] & REFT_OFFSET_MASK) &&
overlaps_with(s->refcount_table[i] & REFT_OFFSET_MASK,
s->cluster_size)) {
@@ -2892,7 +2871,6 @@ int qcow2_change_refcount_order(BlockDriverState *bs, int refcount_order,
/* Now update the rest of the in-memory information */
old_reftable = s->refcount_table;
s->refcount_table = new_reftable;
update_max_refcount_table_index(s);
s->refcount_bits = 1 << refcount_order;
s->refcount_max = UINT64_C(1) << (s->refcount_bits - 1);

View File

@@ -814,8 +814,8 @@ static int qcow2_update_options(BlockDriverState *bs, QDict *options,
return ret;
}
static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVQcow2State *s = bs->opaque;
unsigned int len, i;
@@ -1205,18 +1205,6 @@ static int qcow2_do_open(BlockDriverState *bs, QDict *options, int flags,
return ret;
}
static int qcow2_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
return qcow2_do_open(bs, options, flags, errp);
}
static void qcow2_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVQcow2State *s = bs->opaque;
@@ -1797,7 +1785,7 @@ static void qcow2_invalidate_cache(BlockDriverState *bs, Error **errp)
options = qdict_clone_shallow(bs->options);
flags &= ~BDRV_O_INACTIVE;
ret = qcow2_do_open(bs, options, flags, &local_err);
ret = qcow2_open(bs, options, flags, &local_err);
QDECREF(options);
if (local_err) {
error_propagate(errp, local_err);
@@ -2582,7 +2570,7 @@ qcow2_co_pwritev_compressed(BlockDriverState *bs, uint64_t offset,
/* align end of file to a sector boundary to ease reading with
sector based I/Os */
cluster_offset = bdrv_getlength(bs->file->bs);
return bdrv_truncate(bs->file, cluster_offset);
return bdrv_truncate(bs->file->bs, cluster_offset);
}
buf = qemu_blockalign(bs, s->cluster_size);
@@ -2755,7 +2743,6 @@ static int make_completely_empty(BlockDriverState *bs)
s->refcount_table_offset = s->cluster_size;
s->refcount_table_size = s->cluster_size / sizeof(uint64_t);
s->max_refcount_table_index = 0;
g_free(s->refcount_table);
s->refcount_table = new_reftable;
@@ -2796,7 +2783,7 @@ static int make_completely_empty(BlockDriverState *bs)
goto fail;
}
ret = bdrv_truncate(bs->file, (3 + l1_clusters) * s->cluster_size);
ret = bdrv_truncate(bs->file->bs, (3 + l1_clusters) * s->cluster_size);
if (ret < 0) {
goto fail;
}
@@ -3262,11 +3249,7 @@ static int qcow2_amend_options(BlockDriverState *bs, QemuOpts *opts,
}
if (new_size) {
BlockBackend *blk = blk_new();
blk_insert_bs(blk, bs);
ret = blk_truncate(blk, new_size);
blk_unref(blk);
ret = bdrv_truncate(bs, new_size);
if (ret < 0) {
return ret;
}

View File

@@ -251,7 +251,6 @@ typedef struct BDRVQcow2State {
uint64_t *refcount_table;
uint64_t refcount_table_offset;
uint32_t refcount_table_size;
uint32_t max_refcount_table_index; /* Last used entry in refcount_table */
uint64_t free_cluster_index;
uint64_t free_byte_offset;

View File

@@ -83,7 +83,6 @@ static void qed_find_cluster_cb(void *opaque, int ret)
unsigned int index;
unsigned int n;
qed_acquire(s);
if (ret) {
goto out;
}
@@ -110,7 +109,6 @@ static void qed_find_cluster_cb(void *opaque, int ret)
out:
find_cluster_cb->cb(find_cluster_cb->opaque, ret, offset, len);
qed_release(s);
g_free(find_cluster_cb);
}

View File

@@ -31,7 +31,6 @@ static void qed_read_table_cb(void *opaque, int ret)
{
QEDReadTableCB *read_table_cb = opaque;
QEDTable *table = read_table_cb->table;
BDRVQEDState *s = read_table_cb->s;
int noffsets = read_table_cb->qiov.size / sizeof(uint64_t);
int i;
@@ -41,15 +40,13 @@ static void qed_read_table_cb(void *opaque, int ret)
}
/* Byteswap offsets */
qed_acquire(s);
for (i = 0; i < noffsets; i++) {
table->offsets[i] = le64_to_cpu(table->offsets[i]);
}
qed_release(s);
out:
/* Completion */
trace_qed_read_table_cb(s, read_table_cb->table, ret);
trace_qed_read_table_cb(read_table_cb->s, read_table_cb->table, ret);
gencb_complete(&read_table_cb->gencb, ret);
}
@@ -87,9 +84,8 @@ typedef struct {
static void qed_write_table_cb(void *opaque, int ret)
{
QEDWriteTableCB *write_table_cb = opaque;
BDRVQEDState *s = write_table_cb->s;
trace_qed_write_table_cb(s,
trace_qed_write_table_cb(write_table_cb->s,
write_table_cb->orig_table,
write_table_cb->flush,
ret);
@@ -101,10 +97,8 @@ static void qed_write_table_cb(void *opaque, int ret)
if (write_table_cb->flush) {
/* We still need to flush first */
write_table_cb->flush = false;
qed_acquire(s);
bdrv_aio_flush(write_table_cb->s->bs, qed_write_table_cb,
write_table_cb);
qed_release(s);
return;
}
@@ -219,7 +213,6 @@ static void qed_read_l2_table_cb(void *opaque, int ret)
CachedL2Table *l2_table = request->l2_table;
uint64_t l2_offset = read_l2_table_cb->l2_offset;
qed_acquire(s);
if (ret) {
/* can't trust loaded L2 table anymore */
qed_unref_l2_cache_entry(l2_table);
@@ -235,7 +228,6 @@ static void qed_read_l2_table_cb(void *opaque, int ret)
request->l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
assert(request->l2_table != NULL);
}
qed_release(s);
gencb_complete(&read_l2_table_cb->gencb, ret);
}

View File

@@ -273,19 +273,7 @@ static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
return l2_table;
}
static void qed_aio_next_io(QEDAIOCB *acb, int ret);
static void qed_aio_start_io(QEDAIOCB *acb)
{
qed_aio_next_io(acb, 0);
}
static void qed_aio_next_io_cb(void *opaque, int ret)
{
QEDAIOCB *acb = opaque;
qed_aio_next_io(acb, ret);
}
static void qed_aio_next_io(void *opaque, int ret);
static void qed_plug_allocating_write_reqs(BDRVQEDState *s)
{
@@ -304,7 +292,7 @@ static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
if (acb) {
qed_aio_start_io(acb);
qed_aio_next_io(acb, 0);
}
}
@@ -345,22 +333,10 @@ static void qed_need_check_timer_cb(void *opaque)
trace_qed_need_check_timer_cb(s);
qed_acquire(s);
qed_plug_allocating_write_reqs(s);
/* Ensure writes are on disk before clearing flag */
bdrv_aio_flush(s->bs->file->bs, qed_clear_need_check, s);
qed_release(s);
}
void qed_acquire(BDRVQEDState *s)
{
aio_context_acquire(bdrv_get_aio_context(s->bs));
}
void qed_release(BDRVQEDState *s)
{
aio_context_release(bdrv_get_aio_context(s->bs));
}
static void qed_start_need_check_timer(BDRVQEDState *s)
@@ -415,8 +391,8 @@ static void bdrv_qed_drain(BlockDriverState *bs)
}
}
static int bdrv_qed_do_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
BDRVQEDState *s = bs->opaque;
QEDHeader le_header;
@@ -550,18 +526,6 @@ out:
return ret;
}
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
return bdrv_qed_do_open(bs, options, flags, errp);
}
static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVQEDState *s = bs->opaque;
@@ -757,7 +721,7 @@ static void qed_is_allocated_cb(void *opaque, int ret, uint64_t offset, size_t l
}
if (cb->co) {
aio_co_wake(cb->co);
qemu_coroutine_enter(cb->co);
}
}
@@ -954,7 +918,6 @@ static void qed_update_l2_table(BDRVQEDState *s, QEDTable *table, int index,
static void qed_aio_complete_bh(void *opaque)
{
QEDAIOCB *acb = opaque;
BDRVQEDState *s = acb_to_s(acb);
BlockCompletionFunc *cb = acb->common.cb;
void *user_opaque = acb->common.opaque;
int ret = acb->bh_ret;
@@ -962,9 +925,7 @@ static void qed_aio_complete_bh(void *opaque)
qemu_aio_unref(acb);
/* Invoke callback */
qed_acquire(s);
cb(user_opaque, ret);
qed_release(s);
}
static void qed_aio_complete(QEDAIOCB *acb, int ret)
@@ -998,7 +959,7 @@ static void qed_aio_complete(QEDAIOCB *acb, int ret)
QSIMPLEQ_REMOVE_HEAD(&s->allocating_write_reqs, next);
acb = QSIMPLEQ_FIRST(&s->allocating_write_reqs);
if (acb) {
qed_aio_start_io(acb);
qed_aio_next_io(acb, 0);
} else if (s->header.features & QED_F_NEED_CHECK) {
qed_start_need_check_timer(s);
}
@@ -1023,7 +984,7 @@ static void qed_commit_l2_update(void *opaque, int ret)
acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
assert(acb->request.l2_table != NULL);
qed_aio_next_io(acb, ret);
qed_aio_next_io(opaque, ret);
}
/**
@@ -1071,11 +1032,11 @@ static void qed_aio_write_l2_update(QEDAIOCB *acb, int ret, uint64_t offset)
if (need_alloc) {
/* Write out the whole new L2 table */
qed_write_l2_table(s, &acb->request, 0, s->table_nelems, true,
qed_aio_write_l1_update, acb);
qed_aio_write_l1_update, acb);
} else {
/* Write out only the updated part of the L2 table */
qed_write_l2_table(s, &acb->request, index, acb->cur_nclusters, false,
qed_aio_next_io_cb, acb);
qed_aio_next_io, acb);
}
return;
@@ -1127,7 +1088,7 @@ static void qed_aio_write_main(void *opaque, int ret)
}
if (acb->find_cluster_ret == QED_CLUSTER_FOUND) {
next_fn = qed_aio_next_io_cb;
next_fn = qed_aio_next_io;
} else {
if (s->bs->backing) {
next_fn = qed_aio_write_flush_before_l2_update;
@@ -1240,7 +1201,7 @@ static void qed_aio_write_alloc(QEDAIOCB *acb, size_t len)
if (acb->flags & QED_AIOCB_ZERO) {
/* Skip ahead if the clusters are already zero */
if (acb->find_cluster_ret == QED_CLUSTER_ZERO) {
qed_aio_start_io(acb);
qed_aio_next_io(acb, 0);
return;
}
@@ -1360,18 +1321,18 @@ static void qed_aio_read_data(void *opaque, int ret,
/* Handle zero cluster and backing file reads */
if (ret == QED_CLUSTER_ZERO) {
qemu_iovec_memset(&acb->cur_qiov, 0, 0, acb->cur_qiov.size);
qed_aio_start_io(acb);
qed_aio_next_io(acb, 0);
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_cb, acb);
&acb->backing_qiov, qed_aio_next_io, acb);
return;
}
BLKDBG_EVENT(bs->file, BLKDBG_READ_AIO);
bdrv_aio_readv(bs->file, offset / BDRV_SECTOR_SIZE,
&acb->cur_qiov, acb->cur_qiov.size / BDRV_SECTOR_SIZE,
qed_aio_next_io_cb, acb);
qed_aio_next_io, acb);
return;
err:
@@ -1381,8 +1342,9 @@ err:
/**
* Begin next I/O or complete the request
*/
static void qed_aio_next_io(QEDAIOCB *acb, int ret)
static void qed_aio_next_io(void *opaque, int ret)
{
QEDAIOCB *acb = opaque;
BDRVQEDState *s = acb_to_s(acb);
QEDFindClusterFunc *io_fn = (acb->flags & QED_AIOCB_WRITE) ?
qed_aio_write_data : qed_aio_read_data;
@@ -1438,7 +1400,7 @@ static BlockAIOCB *qed_aio_setup(BlockDriverState *bs,
qemu_iovec_init(&acb->cur_qiov, qiov->niov);
/* Start request */
qed_aio_start_io(acb);
qed_aio_next_io(acb, 0);
return &acb->common;
}
@@ -1474,7 +1436,7 @@ static void coroutine_fn qed_co_pwrite_zeroes_cb(void *opaque, int ret)
cb->done = true;
cb->ret = ret;
if (cb->co) {
aio_co_wake(cb->co);
qemu_coroutine_enter(cb->co);
}
}
@@ -1641,7 +1603,7 @@ static void bdrv_qed_invalidate_cache(BlockDriverState *bs, Error **errp)
bdrv_qed_close(bs);
memset(s, 0, sizeof(BDRVQEDState));
ret = bdrv_qed_do_open(bs, NULL, bs->open_flags, &local_err);
ret = bdrv_qed_open(bs, NULL, bs->open_flags, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_prepend(errp, "Could not reopen qed layer: ");

View File

@@ -198,9 +198,6 @@ enum {
*/
typedef void QEDFindClusterFunc(void *opaque, int ret, uint64_t offset, size_t len);
void qed_acquire(BDRVQEDState *s);
void qed_release(BDRVQEDState *s);
/**
* Generic callback for chaining async callbacks
*/

View File

@@ -97,7 +97,7 @@ typedef struct QuorumAIOCB QuorumAIOCB;
* $children_count QuorumChildRequest.
*/
typedef struct QuorumChildRequest {
BlockDriverState *bs;
BlockAIOCB *aiocb;
QEMUIOVector qiov;
uint8_t *buf;
int ret;
@@ -110,12 +110,11 @@ typedef struct QuorumChildRequest {
* used to do operations on each children and track overall progress.
*/
struct QuorumAIOCB {
BlockDriverState *bs;
Coroutine *co;
BlockAIOCB common;
/* Request metadata */
uint64_t offset;
uint64_t bytes;
uint64_t sector_num;
int nb_sectors;
QEMUIOVector *qiov; /* calling IOV */
@@ -134,15 +133,32 @@ struct QuorumAIOCB {
int children_read; /* how many children have been read from */
};
typedef struct QuorumCo {
QuorumAIOCB *acb;
int idx;
} QuorumCo;
static bool quorum_vote(QuorumAIOCB *acb);
static void quorum_aio_cancel(BlockAIOCB *blockacb)
{
QuorumAIOCB *acb = container_of(blockacb, QuorumAIOCB, common);
BDRVQuorumState *s = acb->common.bs->opaque;
int i;
/* cancel all callbacks */
for (i = 0; i < s->num_children; i++) {
if (acb->qcrs[i].aiocb) {
bdrv_aio_cancel_async(acb->qcrs[i].aiocb);
}
}
}
static AIOCBInfo quorum_aiocb_info = {
.aiocb_size = sizeof(QuorumAIOCB),
.cancel_async = quorum_aio_cancel,
};
static void quorum_aio_finalize(QuorumAIOCB *acb)
{
acb->common.cb(acb->common.opaque, acb->vote_ret);
g_free(acb->qcrs);
g_free(acb);
qemu_aio_unref(acb);
}
static bool quorum_sha256_compare(QuorumVoteValue *a, QuorumVoteValue *b)
@@ -155,26 +171,30 @@ static bool quorum_64bits_compare(QuorumVoteValue *a, QuorumVoteValue *b)
return a->l == b->l;
}
static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
static QuorumAIOCB *quorum_aio_get(BDRVQuorumState *s,
BlockDriverState *bs,
QEMUIOVector *qiov,
uint64_t offset,
uint64_t bytes)
uint64_t sector_num,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
BDRVQuorumState *s = bs->opaque;
QuorumAIOCB *acb = g_new(QuorumAIOCB, 1);
QuorumAIOCB *acb = qemu_aio_get(&quorum_aiocb_info, bs, cb, opaque);
int i;
*acb = (QuorumAIOCB) {
.co = qemu_coroutine_self(),
.bs = bs,
.offset = offset,
.bytes = bytes,
.qiov = qiov,
.votes.compare = quorum_sha256_compare,
.votes.vote_list = QLIST_HEAD_INITIALIZER(acb.votes.vote_list),
};
acb->common.bs->opaque = s;
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
acb->qiov = qiov;
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;
acb->vote_ret = 0;
for (i = 0; i < s->num_children; i++) {
acb->qcrs[i].buf = NULL;
acb->qcrs[i].ret = 0;
@@ -184,37 +204,30 @@ static QuorumAIOCB *quorum_aio_get(BlockDriverState *bs,
return acb;
}
static void quorum_report_bad(QuorumOpType type, uint64_t offset,
uint64_t bytes, char *node_name, int ret)
static void quorum_report_bad(QuorumOpType type, uint64_t sector_num,
int nb_sectors, char *node_name, int ret)
{
const char *msg = NULL;
int64_t start_sector = offset / BDRV_SECTOR_SIZE;
int64_t end_sector = DIV_ROUND_UP(offset + bytes, BDRV_SECTOR_SIZE);
if (ret < 0) {
msg = strerror(-ret);
}
qapi_event_send_quorum_report_bad(type, !!msg, msg, node_name, start_sector,
end_sector - start_sector, &error_abort);
qapi_event_send_quorum_report_bad(type, !!msg, msg, node_name,
sector_num, nb_sectors, &error_abort);
}
static void quorum_report_failure(QuorumAIOCB *acb)
{
const char *reference = bdrv_get_device_or_node_name(acb->bs);
int64_t start_sector = acb->offset / BDRV_SECTOR_SIZE;
int64_t end_sector = DIV_ROUND_UP(acb->offset + acb->bytes,
BDRV_SECTOR_SIZE);
qapi_event_send_quorum_failure(reference, start_sector,
end_sector - start_sector, &error_abort);
const char *reference = bdrv_get_device_or_node_name(acb->common.bs);
qapi_event_send_quorum_failure(reference, acb->sector_num,
acb->nb_sectors, &error_abort);
}
static int quorum_vote_error(QuorumAIOCB *acb);
static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->bs->opaque;
BDRVQuorumState *s = acb->common.bs->opaque;
if (acb->success_count < s->threshold) {
acb->vote_ret = quorum_vote_error(acb);
@@ -225,7 +238,22 @@ static bool quorum_has_too_much_io_failed(QuorumAIOCB *acb)
return false;
}
static int read_fifo_child(QuorumAIOCB *acb);
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)
{
@@ -244,7 +272,70 @@ static void quorum_report_bad_acb(QuorumChildRequest *sacb, int ret)
{
QuorumAIOCB *acb = sacb->parent;
QuorumOpType type = acb->is_read ? QUORUM_OP_TYPE_READ : QUORUM_OP_TYPE_WRITE;
quorum_report_bad(type, acb->offset, acb->bytes, sacb->bs->node_name, ret);
quorum_report_bad(type, acb->sector_num, acb->nb_sectors,
sacb->aiocb->bs->node_name, ret);
}
static void quorum_fifo_aio_cb(void *opaque, int ret)
{
QuorumChildRequest *sacb = opaque;
QuorumAIOCB *acb = sacb->parent;
BDRVQuorumState *s = acb->common.bs->opaque;
assert(acb->is_read && s->read_pattern == QUORUM_READ_PATTERN_FIFO);
if (ret < 0) {
quorum_report_bad_acb(sacb, ret);
/* We try to read next child in FIFO order if we fail to read */
if (acb->children_read < s->num_children) {
read_fifo_child(acb);
return;
}
}
acb->vote_ret = ret;
/* FIXME: rewrite failed children if acb->children_read > 1? */
quorum_aio_finalize(acb);
}
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;
int i;
sacb->ret = ret;
if (ret == 0) {
acb->success_count++;
} else {
quorum_report_bad_acb(sacb, ret);
}
acb->count++;
assert(acb->count <= s->num_children);
assert(acb->success_count <= s->num_children);
if (acb->count < s->num_children) {
return;
}
/* Do the vote on read */
if (acb->is_read) {
rewrite = quorum_vote(acb);
for (i = 0; i < s->num_children; i++) {
qemu_vfree(acb->qcrs[i].buf);
qemu_iovec_destroy(&acb->qcrs[i].qiov);
}
} 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);
}
}
static void quorum_report_bad_versions(BDRVQuorumState *s,
@@ -259,31 +350,14 @@ static void quorum_report_bad_versions(BDRVQuorumState *s,
continue;
}
QLIST_FOREACH(item, &version->items, next) {
quorum_report_bad(QUORUM_OP_TYPE_READ, acb->offset, acb->bytes,
quorum_report_bad(QUORUM_OP_TYPE_READ, acb->sector_num,
acb->nb_sectors,
s->children[item->index]->bs->node_name, 0);
}
}
}
static void quorum_rewrite_entry(void *opaque)
{
QuorumCo *co = opaque;
QuorumAIOCB *acb = co->acb;
BDRVQuorumState *s = acb->bs->opaque;
/* Ignore any errors, it's just a correction attempt for already
* corrupted data. */
bdrv_co_pwritev(s->children[co->idx], acb->offset, acb->bytes,
acb->qiov, 0);
/* Wake up the caller after the last rewrite */
acb->rewrite_count--;
if (!acb->rewrite_count) {
qemu_coroutine_enter_if_inactive(acb->co);
}
}
static bool quorum_rewrite_bad_versions(QuorumAIOCB *acb,
static bool quorum_rewrite_bad_versions(BDRVQuorumState *s, QuorumAIOCB *acb,
QuorumVoteValue *value)
{
QuorumVoteVersion *version;
@@ -302,7 +376,7 @@ static bool quorum_rewrite_bad_versions(QuorumAIOCB *acb,
}
}
/* quorum_rewrite_entry will count down this to zero */
/* quorum_rewrite_aio_cb will count down this to zero */
acb->rewrite_count = count;
/* now fire the correcting rewrites */
@@ -311,14 +385,9 @@ static bool quorum_rewrite_bad_versions(QuorumAIOCB *acb,
continue;
}
QLIST_FOREACH(item, &version->items, next) {
Coroutine *co;
QuorumCo data = {
.acb = acb,
.idx = item->index,
};
co = qemu_coroutine_create(quorum_rewrite_entry, &data);
qemu_coroutine_enter(co);
bdrv_aio_writev(s->children[item->index], acb->sector_num,
acb->qiov, acb->nb_sectors, quorum_rewrite_aio_cb,
acb);
}
}
@@ -438,8 +507,8 @@ static void GCC_FMT_ATTR(2, 3) quorum_err(QuorumAIOCB *acb,
va_list ap;
va_start(ap, fmt);
fprintf(stderr, "quorum: offset=%" PRIu64 " bytes=%" PRIu64 " ",
acb->offset, acb->bytes);
fprintf(stderr, "quorum: sector_num=%" PRId64 " nb_sectors=%d ",
acb->sector_num, acb->nb_sectors);
vfprintf(stderr, fmt, ap);
fprintf(stderr, "\n");
va_end(ap);
@@ -450,15 +519,16 @@ static bool quorum_compare(QuorumAIOCB *acb,
QEMUIOVector *a,
QEMUIOVector *b)
{
BDRVQuorumState *s = acb->bs->opaque;
BDRVQuorumState *s = acb->common.bs->opaque;
ssize_t offset;
/* This driver will replace blkverify in this particular case */
if (s->is_blkverify) {
offset = qemu_iovec_compare(a, b);
if (offset != -1) {
quorum_err(acb, "contents mismatch at offset %" PRIu64,
acb->offset + offset);
quorum_err(acb, "contents mismatch in sector %" PRId64,
acb->sector_num +
(uint64_t)(offset / BDRV_SECTOR_SIZE));
}
return true;
}
@@ -469,7 +539,7 @@ static bool quorum_compare(QuorumAIOCB *acb,
/* Do a vote to get the error code */
static int quorum_vote_error(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->bs->opaque;
BDRVQuorumState *s = acb->common.bs->opaque;
QuorumVoteVersion *winner = NULL;
QuorumVotes error_votes;
QuorumVoteValue result_value;
@@ -498,16 +568,17 @@ static int quorum_vote_error(QuorumAIOCB *acb)
return ret;
}
static void quorum_vote(QuorumAIOCB *acb)
static bool quorum_vote(QuorumAIOCB *acb)
{
bool quorum = true;
bool rewrite = false;
int i, j, ret;
QuorumVoteValue hash;
BDRVQuorumState *s = acb->bs->opaque;
BDRVQuorumState *s = acb->common.bs->opaque;
QuorumVoteVersion *winner;
if (quorum_has_too_much_io_failed(acb)) {
return;
return false;
}
/* get the index of the first successful read */
@@ -535,7 +606,7 @@ static void quorum_vote(QuorumAIOCB *acb)
/* Every successful read agrees */
if (quorum) {
quorum_copy_qiov(acb->qiov, &acb->qcrs[i].qiov);
return;
return false;
}
/* compute hashes for each successful read, also store indexes */
@@ -570,46 +641,19 @@ static void quorum_vote(QuorumAIOCB *acb)
/* corruption correction is enabled */
if (s->rewrite_corrupted) {
quorum_rewrite_bad_versions(acb, &winner->value);
rewrite = quorum_rewrite_bad_versions(s, acb, &winner->value);
}
free_exit:
/* free lists */
quorum_free_vote_list(&acb->votes);
return rewrite;
}
static void read_quorum_children_entry(void *opaque)
static BlockAIOCB *read_quorum_children(QuorumAIOCB *acb)
{
QuorumCo *co = opaque;
QuorumAIOCB *acb = co->acb;
BDRVQuorumState *s = acb->bs->opaque;
int i = co->idx;
QuorumChildRequest *sacb = &acb->qcrs[i];
sacb->bs = s->children[i]->bs;
sacb->ret = bdrv_co_preadv(s->children[i], acb->offset, acb->bytes,
&acb->qcrs[i].qiov, 0);
if (sacb->ret == 0) {
acb->success_count++;
} else {
quorum_report_bad_acb(sacb, sacb->ret);
}
acb->count++;
assert(acb->count <= s->num_children);
assert(acb->success_count <= s->num_children);
/* Wake up the caller after the last read */
if (acb->count == s->num_children) {
qemu_coroutine_enter_if_inactive(acb->co);
}
}
static int read_quorum_children(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->bs->opaque;
int i, ret;
BDRVQuorumState *s = acb->common.bs->opaque;
int i;
acb->children_read = s->num_children;
for (i = 0; i < s->num_children; i++) {
@@ -619,131 +663,65 @@ static int read_quorum_children(QuorumAIOCB *acb)
}
for (i = 0; i < s->num_children; i++) {
Coroutine *co;
QuorumCo data = {
.acb = acb,
.idx = i,
};
co = qemu_coroutine_create(read_quorum_children_entry, &data);
qemu_coroutine_enter(co);
acb->qcrs[i].aiocb = bdrv_aio_readv(s->children[i], acb->sector_num,
&acb->qcrs[i].qiov, acb->nb_sectors,
quorum_aio_cb, &acb->qcrs[i]);
}
while (acb->count < s->num_children) {
qemu_coroutine_yield();
}
/* Do the vote on read */
quorum_vote(acb);
for (i = 0; i < s->num_children; i++) {
qemu_vfree(acb->qcrs[i].buf);
qemu_iovec_destroy(&acb->qcrs[i].qiov);
}
while (acb->rewrite_count) {
qemu_coroutine_yield();
}
ret = acb->vote_ret;
return ret;
return &acb->common;
}
static int read_fifo_child(QuorumAIOCB *acb)
static BlockAIOCB *read_fifo_child(QuorumAIOCB *acb)
{
BDRVQuorumState *s = acb->bs->opaque;
int n, ret;
BDRVQuorumState *s = acb->common.bs->opaque;
int n = acb->children_read++;
/* We try to read the next child in FIFO order if we failed to read */
do {
n = acb->children_read++;
acb->qcrs[n].bs = s->children[n]->bs;
ret = bdrv_co_preadv(s->children[n], acb->offset, acb->bytes,
acb->qiov, 0);
if (ret < 0) {
quorum_report_bad_acb(&acb->qcrs[n], ret);
}
} while (ret < 0 && acb->children_read < s->num_children);
acb->qcrs[n].aiocb = bdrv_aio_readv(s->children[n], acb->sector_num,
acb->qiov, acb->nb_sectors,
quorum_fifo_aio_cb, &acb->qcrs[n]);
/* FIXME: rewrite failed children if acb->children_read > 1? */
return ret;
return &acb->common;
}
static int quorum_co_preadv(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, int flags)
static BlockAIOCB *quorum_aio_readv(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
BDRVQuorumState *s = bs->opaque;
QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
int ret;
QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num,
nb_sectors, cb, opaque);
acb->is_read = true;
acb->children_read = 0;
if (s->read_pattern == QUORUM_READ_PATTERN_QUORUM) {
ret = read_quorum_children(acb);
} else {
ret = read_fifo_child(acb);
return read_quorum_children(acb);
}
quorum_aio_finalize(acb);
return ret;
return read_fifo_child(acb);
}
static void write_quorum_entry(void *opaque)
{
QuorumCo *co = opaque;
QuorumAIOCB *acb = co->acb;
BDRVQuorumState *s = acb->bs->opaque;
int i = co->idx;
QuorumChildRequest *sacb = &acb->qcrs[i];
sacb->bs = s->children[i]->bs;
sacb->ret = bdrv_co_pwritev(s->children[i], acb->offset, acb->bytes,
acb->qiov, 0);
if (sacb->ret == 0) {
acb->success_count++;
} else {
quorum_report_bad_acb(sacb, sacb->ret);
}
acb->count++;
assert(acb->count <= s->num_children);
assert(acb->success_count <= s->num_children);
/* Wake up the caller after the last write */
if (acb->count == s->num_children) {
qemu_coroutine_enter_if_inactive(acb->co);
}
}
static int quorum_co_pwritev(BlockDriverState *bs, uint64_t offset,
uint64_t bytes, QEMUIOVector *qiov, int flags)
static BlockAIOCB *quorum_aio_writev(BlockDriverState *bs,
int64_t sector_num,
QEMUIOVector *qiov,
int nb_sectors,
BlockCompletionFunc *cb,
void *opaque)
{
BDRVQuorumState *s = bs->opaque;
QuorumAIOCB *acb = quorum_aio_get(bs, qiov, offset, bytes);
int i, ret;
QuorumAIOCB *acb = quorum_aio_get(s, bs, qiov, sector_num, nb_sectors,
cb, opaque);
int i;
for (i = 0; i < s->num_children; i++) {
Coroutine *co;
QuorumCo data = {
.acb = acb,
.idx = i,
};
co = qemu_coroutine_create(write_quorum_entry, &data);
qemu_coroutine_enter(co);
acb->qcrs[i].aiocb = bdrv_aio_writev(s->children[i], sector_num,
qiov, nb_sectors, &quorum_aio_cb,
&acb->qcrs[i]);
}
while (acb->count < s->num_children) {
qemu_coroutine_yield();
}
quorum_has_too_much_io_failed(acb);
ret = acb->vote_ret;
quorum_aio_finalize(acb);
return ret;
return &acb->common;
}
static int64_t quorum_getlength(BlockDriverState *bs)
@@ -787,7 +765,7 @@ static coroutine_fn int quorum_co_flush(BlockDriverState *bs)
result = bdrv_co_flush(s->children[i]->bs);
if (result) {
quorum_report_bad(QUORUM_OP_TYPE_FLUSH, 0,
bdrv_getlength(s->children[i]->bs),
bdrv_nb_sectors(s->children[i]->bs),
s->children[i]->bs->node_name, result);
result_value.l = result;
quorum_count_vote(&error_votes, &result_value, i);
@@ -1120,8 +1098,8 @@ static BlockDriver bdrv_quorum = {
.bdrv_getlength = quorum_getlength,
.bdrv_co_preadv = quorum_co_preadv,
.bdrv_co_pwritev = quorum_co_pwritev,
.bdrv_aio_readv = quorum_aio_readv,
.bdrv_aio_writev = quorum_aio_writev,
.bdrv_add_child = quorum_add_child,
.bdrv_del_child = quorum_del_child,

View File

@@ -651,15 +651,12 @@ static void raw_reopen_abort(BDRVReopenState *state)
state->opaque = NULL;
}
static int hdev_get_max_transfer_length(BlockDriverState *bs, int fd)
static int hdev_get_max_transfer_length(int fd)
{
#ifdef BLKSECTGET
int max_bytes = 0;
short max_sectors = 0;
if (bs->sg && ioctl(fd, BLKSECTGET, &max_bytes) == 0) {
return max_bytes;
} else if (!bs->sg && ioctl(fd, BLKSECTGET, &max_sectors) == 0) {
return max_sectors << BDRV_SECTOR_BITS;
int max_sectors = 0;
if (ioctl(fd, BLKSECTGET, &max_sectors) == 0) {
return max_sectors;
} else {
return -errno;
}
@@ -674,10 +671,10 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
struct stat st;
if (!fstat(s->fd, &st)) {
if (S_ISBLK(st.st_mode) || S_ISCHR(st.st_mode)) {
int ret = hdev_get_max_transfer_length(bs, s->fd);
if (ret > 0 && ret <= BDRV_REQUEST_MAX_BYTES) {
bs->bl.max_transfer = pow2floor(ret);
if (S_ISBLK(st.st_mode)) {
int ret = hdev_get_max_transfer_length(s->fd);
if (ret > 0 && ret <= BDRV_REQUEST_MAX_SECTORS) {
bs->bl.max_transfer = pow2floor(ret << BDRV_SECTOR_BITS);
}
}
}
@@ -1591,17 +1588,18 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
#endif
}
if (ftruncate(fd, total_size) != 0) {
result = -errno;
error_setg_errno(errp, -result, "Could not resize file");
goto out_close;
}
switch (prealloc) {
#ifdef CONFIG_POSIX_FALLOCATE
case PREALLOC_MODE_FALLOC:
/*
* Truncating before posix_fallocate() makes it about twice slower on
* file systems that do not support fallocate(), trying to check if a
* block is allocated before allocating it, so don't do that here.
*/
/* posix_fallocate() doesn't set errno. */
result = -posix_fallocate(fd, 0, total_size);
if (result != 0) {
/* posix_fallocate() doesn't set errno. */
error_setg_errno(errp, -result,
"Could not preallocate data for the new file");
}
@@ -1609,17 +1607,6 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
#endif
case PREALLOC_MODE_FULL:
{
/*
* Knowing the final size from the beginning could allow the file
* system driver to do less allocations and possibly avoid
* fragmentation of the file.
*/
if (ftruncate(fd, total_size) != 0) {
result = -errno;
error_setg_errno(errp, -result, "Could not resize file");
goto out_close;
}
int64_t num = 0, left = total_size;
buf = g_malloc0(65536);
@@ -1646,10 +1633,6 @@ static int raw_create(const char *filename, QemuOpts *opts, Error **errp)
break;
}
case PREALLOC_MODE_OFF:
if (ftruncate(fd, total_size) != 0) {
result = -errno;
error_setg_errno(errp, -result, "Could not resize file");
}
break;
default:
result = -EINVAL;

View File

@@ -1,4 +1,4 @@
/* BlockDriver implementation for "raw" format driver
/* BlockDriver implementation for "raw"
*
* Copyright (C) 2010-2016 Red Hat, Inc.
* Copyright (C) 2010, Blue Swirl <blauwirbel@gmail.com>
@@ -341,7 +341,7 @@ static int raw_truncate(BlockDriverState *bs, int64_t offset)
s->size = offset;
offset += s->offset;
return bdrv_truncate(bs->file, offset);
return bdrv_truncate(bs->file->bs, offset);
}
static int raw_media_changed(BlockDriverState *bs)
@@ -384,12 +384,6 @@ static int raw_open(BlockDriverState *bs, QDict *options, int flags,
BDRVRawState *s = bs->opaque;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
bs->sg = bs->file->bs->sg;
bs->supported_write_flags = BDRV_REQ_FUA &
bs->file->bs->supported_write_flags;

View File

@@ -62,13 +62,6 @@
#define RBD_MAX_SNAP_NAME_SIZE 128
#define RBD_MAX_SNAPS 100
/* The LIBRBD_SUPPORTS_IOVEC is defined in librbd.h */
#ifdef LIBRBD_SUPPORTS_IOVEC
#define LIBRBD_USE_IOVEC 1
#else
#define LIBRBD_USE_IOVEC 0
#endif
typedef enum {
RBD_AIO_READ,
RBD_AIO_WRITE,
@@ -317,17 +310,6 @@ static int qemu_rbd_set_conf(rados_t cluster, const char *conf,
return ret;
}
static void qemu_rbd_memset(RADOSCB *rcb, int64_t offs)
{
if (LIBRBD_USE_IOVEC) {
RBDAIOCB *acb = rcb->acb;
iov_memset(acb->qiov->iov, acb->qiov->niov, offs, 0,
acb->qiov->size - offs);
} else {
memset(rcb->buf + offs, 0, rcb->size - offs);
}
}
static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
{
Error *local_err = NULL;
@@ -444,11 +426,11 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
}
} else {
if (r < 0) {
qemu_rbd_memset(rcb, 0);
memset(rcb->buf, 0, rcb->size);
acb->ret = r;
acb->error = 1;
} else if (r < rcb->size) {
qemu_rbd_memset(rcb, r);
memset(rcb->buf + r, 0, rcb->size - r);
if (!acb->error) {
acb->ret = rcb->size;
}
@@ -459,13 +441,10 @@ static void qemu_rbd_complete_aio(RADOSCB *rcb)
g_free(rcb);
if (!LIBRBD_USE_IOVEC) {
if (acb->cmd == RBD_AIO_READ) {
qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
}
qemu_vfree(acb->bounce);
if (acb->cmd == RBD_AIO_READ) {
qemu_iovec_from_buf(acb->qiov, 0, acb->bounce, acb->qiov->size);
}
qemu_vfree(acb->bounce);
acb->common.cb(acb->common.opaque, (acb->ret > 0 ? 0 : acb->ret));
qemu_aio_unref(acb);
@@ -676,6 +655,7 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
RBDAIOCB *acb;
RADOSCB *rcb = NULL;
rbd_completion_t c;
char *buf;
int r;
BDRVRBDState *s = bs->opaque;
@@ -684,29 +664,27 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
acb->cmd = cmd;
acb->qiov = qiov;
assert(!qiov || qiov->size == size);
rcb = g_new(RADOSCB, 1);
if (!LIBRBD_USE_IOVEC) {
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;
}
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;
}
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
rcb->buf = acb->bounce;
}
acb->ret = 0;
acb->error = 0;
acb->s = s;
if (cmd == RBD_AIO_WRITE) {
qemu_iovec_to_buf(acb->qiov, 0, acb->bounce, qiov->size);
}
buf = acb->bounce;
rcb = g_new(RADOSCB, 1);
rcb->acb = acb;
rcb->buf = buf;
rcb->s = acb->s;
rcb->size = size;
r = rbd_aio_create_completion(rcb, (rbd_callback_t) rbd_finish_aiocb, &c);
@@ -716,18 +694,10 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
switch (cmd) {
case RBD_AIO_WRITE:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_writev(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_write(s->image, off, size, rcb->buf, c);
#endif
r = rbd_aio_write(s->image, off, size, buf, c);
break;
case RBD_AIO_READ:
#ifdef LIBRBD_SUPPORTS_IOVEC
r = rbd_aio_readv(s->image, qiov->iov, qiov->niov, off, c);
#else
r = rbd_aio_read(s->image, off, size, rcb->buf, c);
#endif
r = rbd_aio_read(s->image, off, size, buf, c);
break;
case RBD_AIO_DISCARD:
r = rbd_aio_discard_wrapper(s->image, off, size, c);
@@ -742,16 +712,14 @@ static BlockAIOCB *rbd_start_aio(BlockDriverState *bs,
if (r < 0) {
goto failed_completion;
}
return &acb->common;
failed_completion:
rbd_aio_release(c);
failed:
g_free(rcb);
if (!LIBRBD_USE_IOVEC) {
qemu_vfree(acb->bounce);
}
qemu_vfree(acb->bounce);
qemu_aio_unref(acb);
return NULL;
}

View File

@@ -86,12 +86,6 @@ static int replication_open(BlockDriverState *bs, QDict *options,
const char *mode;
const char *top_id;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
ret = -EINVAL;
opts = qemu_opts_create(&replication_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);

View File

@@ -306,7 +306,6 @@ static inline size_t count_data_objs(const struct SheepdogInode *inode)
} while (0)
typedef struct SheepdogAIOCB SheepdogAIOCB;
typedef struct BDRVSheepdogState BDRVSheepdogState;
typedef struct AIOReq {
SheepdogAIOCB *aiocb;
@@ -335,7 +334,7 @@ enum AIOCBState {
|| y->max_affect_data_idx < x->min_affect_data_idx))
struct SheepdogAIOCB {
BDRVSheepdogState *s;
BlockAIOCB common;
QEMUIOVector *qiov;
@@ -346,6 +345,9 @@ struct SheepdogAIOCB {
enum AIOCBState aiocb_type;
Coroutine *coroutine;
void (*aio_done_func)(SheepdogAIOCB *);
bool cancelable;
int nr_pending;
uint32_t min_affect_data_idx;
@@ -363,7 +365,7 @@ struct SheepdogAIOCB {
QLIST_ENTRY(SheepdogAIOCB) aiocb_siblings;
};
struct BDRVSheepdogState {
typedef struct BDRVSheepdogState {
BlockDriverState *bs;
AioContext *aio_context;
@@ -390,7 +392,7 @@ struct BDRVSheepdogState {
CoQueue overlapping_queue;
QLIST_HEAD(inflight_aiocb_head, SheepdogAIOCB) inflight_aiocb_head;
};
} BDRVSheepdogState;
typedef struct BDRVSheepdogReopenState {
int fd;
@@ -448,13 +450,14 @@ static const char * sd_strerror(int err)
*
* 1. In sd_co_rw_vector, we send the I/O requests to the server and
* link the requests to the inflight_list in the
* BDRVSheepdogState. The function yields while waiting for
* BDRVSheepdogState. The function exits without waiting for
* receiving the response.
*
* 2. We receive the response in aio_read_response, the fd handler to
* the sheepdog connection. We switch back to sd_co_readv/sd_writev
* after all the requests belonging to the AIOCB are finished. If
* needed, sd_co_writev will send another requests for the vdi object.
* the sheepdog connection. If metadata update is needed, we send
* the write request to the vdi object in sd_write_done, the write
* completion function. We switch back to sd_co_readv/writev after
* all the requests belonging to the AIOCB are finished.
*/
static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
@@ -479,34 +482,94 @@ static inline AIOReq *alloc_aio_req(BDRVSheepdogState *s, SheepdogAIOCB *acb,
return aio_req;
}
static void wait_for_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *acb)
static inline void free_aio_req(BDRVSheepdogState *s, AIOReq *aio_req)
{
SheepdogAIOCB *cb;
SheepdogAIOCB *acb = aio_req->aiocb;
retry:
QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) {
if (AIOCBOverlapping(acb, cb)) {
qemu_co_queue_wait(&s->overlapping_queue, NULL);
goto retry;
acb->cancelable = false;
QLIST_REMOVE(aio_req, aio_siblings);
g_free(aio_req);
acb->nr_pending--;
}
static void coroutine_fn sd_finish_aiocb(SheepdogAIOCB *acb)
{
qemu_coroutine_enter(acb->coroutine);
qemu_aio_unref(acb);
}
/*
* Check whether the specified acb can be canceled
*
* We can cancel aio when any request belonging to the acb is:
* - Not processed by the sheepdog server.
* - Not linked to the inflight queue.
*/
static bool sd_acb_cancelable(const SheepdogAIOCB *acb)
{
BDRVSheepdogState *s = acb->common.bs->opaque;
AIOReq *aioreq;
if (!acb->cancelable) {
return false;
}
QLIST_FOREACH(aioreq, &s->inflight_aio_head, aio_siblings) {
if (aioreq->aiocb == acb) {
return false;
}
}
return true;
}
static void sd_aio_cancel(BlockAIOCB *blockacb)
{
SheepdogAIOCB *acb = (SheepdogAIOCB *)blockacb;
BDRVSheepdogState *s = acb->common.bs->opaque;
AIOReq *aioreq, *next;
if (sd_acb_cancelable(acb)) {
/* Remove outstanding requests from failed queue. */
QLIST_FOREACH_SAFE(aioreq, &s->failed_aio_head, aio_siblings,
next) {
if (aioreq->aiocb == acb) {
free_aio_req(s, aioreq);
}
}
assert(acb->nr_pending == 0);
if (acb->common.cb) {
acb->common.cb(acb->common.opaque, -ECANCELED);
}
sd_finish_aiocb(acb);
}
}
static void sd_aio_setup(SheepdogAIOCB *acb, BDRVSheepdogState *s,
QEMUIOVector *qiov, int64_t sector_num, int nb_sectors,
int type)
static const AIOCBInfo sd_aiocb_info = {
.aiocb_size = sizeof(SheepdogAIOCB),
.cancel_async = sd_aio_cancel,
};
static SheepdogAIOCB *sd_aio_setup(BlockDriverState *bs, QEMUIOVector *qiov,
int64_t sector_num, int nb_sectors)
{
SheepdogAIOCB *acb;
uint32_t object_size;
BDRVSheepdogState *s = bs->opaque;
object_size = (UINT32_C(1) << s->inode.block_size_shift);
acb->s = s;
acb = qemu_aio_get(&sd_aiocb_info, bs, NULL, NULL);
acb->qiov = qiov;
acb->sector_num = sector_num;
acb->nb_sectors = nb_sectors;
acb->aio_done_func = NULL;
acb->cancelable = true;
acb->coroutine = qemu_coroutine_self();
acb->ret = 0;
acb->nr_pending = 0;
@@ -517,14 +580,8 @@ static void sd_aio_setup(SheepdogAIOCB *acb, BDRVSheepdogState *s,
acb->min_dirty_data_idx = UINT32_MAX;
acb->max_dirty_data_idx = 0;
acb->aiocb_type = type;
if (type == AIOCB_FLUSH_CACHE) {
return;
}
wait_for_overlapping_aiocb(s, acb);
QLIST_INSERT_HEAD(&s->inflight_aiocb_head, acb, aiocb_siblings);
return acb;
}
/* Return -EIO in case of error, file descriptor on success */
@@ -575,6 +632,13 @@ static coroutine_fn int send_co_req(int sockfd, SheepdogReq *hdr, void *data,
return ret;
}
static void restart_co_req(void *opaque)
{
Coroutine *co = opaque;
qemu_coroutine_enter(co);
}
typedef struct SheepdogReqCo {
int sockfd;
BlockDriverState *bs;
@@ -585,19 +649,12 @@ typedef struct SheepdogReqCo {
unsigned int *rlen;
int ret;
bool finished;
Coroutine *co;
} SheepdogReqCo;
static void restart_co_req(void *opaque)
{
SheepdogReqCo *srco = opaque;
aio_co_wake(srco->co);
}
static coroutine_fn void do_co_req(void *opaque)
{
int ret;
Coroutine *co;
SheepdogReqCo *srco = opaque;
int sockfd = srco->sockfd;
SheepdogReq *hdr = srco->hdr;
@@ -605,9 +662,9 @@ static coroutine_fn void do_co_req(void *opaque)
unsigned int *wlen = srco->wlen;
unsigned int *rlen = srco->rlen;
srco->co = qemu_coroutine_self();
co = qemu_coroutine_self();
aio_set_fd_handler(srco->aio_context, sockfd, false,
NULL, restart_co_req, NULL, srco);
NULL, restart_co_req, co);
ret = send_co_req(sockfd, hdr, data, wlen);
if (ret < 0) {
@@ -615,7 +672,7 @@ static coroutine_fn void do_co_req(void *opaque)
}
aio_set_fd_handler(srco->aio_context, sockfd, false,
restart_co_req, NULL, NULL, srco);
restart_co_req, NULL, co);
ret = qemu_co_recv(sockfd, hdr, sizeof(*hdr));
if (ret != sizeof(*hdr)) {
@@ -641,9 +698,8 @@ out:
/* there is at most one request for this sockfd, so it is safe to
* set each handler to NULL. */
aio_set_fd_handler(srco->aio_context, sockfd, false,
NULL, NULL, NULL, NULL);
NULL, NULL, NULL);
srco->co = NULL;
srco->ret = ret;
srco->finished = true;
if (srco->bs) {
@@ -704,7 +760,7 @@ static coroutine_fn void reconnect_to_sdog(void *opaque)
AIOReq *aio_req, *next;
aio_set_fd_handler(s->aio_context, s->fd, false, NULL,
NULL, NULL, NULL);
NULL, NULL);
close(s->fd);
s->fd = -1;
@@ -741,6 +797,7 @@ static coroutine_fn void reconnect_to_sdog(void *opaque)
while (!QLIST_EMPTY(&s->failed_aio_head)) {
aio_req = QLIST_FIRST(&s->failed_aio_head);
QLIST_REMOVE(aio_req, aio_siblings);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
resend_aioreq(s, aio_req);
}
}
@@ -783,6 +840,9 @@ static void coroutine_fn aio_read_response(void *opaque)
switch (acb->aiocb_type) {
case AIOCB_WRITE_UDATA:
/* this coroutine context is no longer suitable for co_recv
* because we may send data to update vdi objects */
s->co_recv = NULL;
if (!is_data_obj(aio_req->oid)) {
break;
}
@@ -830,12 +890,6 @@ static void coroutine_fn aio_read_response(void *opaque)
}
}
/* No more data for this aio_req (reload_inode below uses its own file
* descriptor handler which doesn't use co_recv).
*/
s->co_recv = NULL;
QLIST_REMOVE(aio_req, aio_siblings);
switch (rsp.result) {
case SD_RES_SUCCESS:
break;
@@ -853,26 +907,26 @@ static void coroutine_fn aio_read_response(void *opaque)
aio_req->oid = vid_to_vdi_oid(s->inode.vdi_id);
}
resend_aioreq(s, aio_req);
return;
goto out;
default:
acb->ret = -EIO;
error_report("%s", sd_strerror(rsp.result));
break;
}
g_free(aio_req);
if (!--acb->nr_pending) {
free_aio_req(s, aio_req);
if (!acb->nr_pending) {
/*
* We've finished all requests which belong to the AIOCB, so
* we can switch back to sd_co_readv/writev now.
*/
aio_co_wake(acb->coroutine);
acb->aio_done_func(acb);
}
out:
s->co_recv = NULL;
return;
err:
s->co_recv = NULL;
reconnect_to_sdog(opaque);
}
@@ -884,14 +938,14 @@ static void co_read_response(void *opaque)
s->co_recv = qemu_coroutine_create(aio_read_response, opaque);
}
aio_co_wake(s->co_recv);
qemu_coroutine_enter(s->co_recv);
}
static void co_write_request(void *opaque)
{
BDRVSheepdogState *s = opaque;
aio_co_wake(s->co_send);
qemu_coroutine_enter(s->co_send);
}
/*
@@ -910,7 +964,7 @@ static int get_sheep_fd(BDRVSheepdogState *s, Error **errp)
}
aio_set_fd_handler(s->aio_context, fd, false,
co_read_response, NULL, NULL, s);
co_read_response, NULL, s);
return fd;
}
@@ -1122,8 +1176,6 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
uint64_t old_oid = aio_req->base_oid;
bool create = aio_req->create;
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
if (!nr_copies) {
error_report("bug");
}
@@ -1174,7 +1226,7 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
qemu_co_mutex_lock(&s->lock);
s->co_send = qemu_coroutine_self();
aio_set_fd_handler(s->aio_context, s->fd, false,
co_read_response, co_write_request, NULL, s);
co_read_response, co_write_request, s);
socket_set_cork(s->fd, 1);
/* send a header */
@@ -1193,7 +1245,7 @@ static void coroutine_fn add_aio_request(BDRVSheepdogState *s, AIOReq *aio_req,
out:
socket_set_cork(s->fd, 0);
aio_set_fd_handler(s->aio_context, s->fd, false,
co_read_response, NULL, NULL, s);
co_read_response, NULL, s);
s->co_send = NULL;
qemu_co_mutex_unlock(&s->lock);
}
@@ -1344,7 +1396,7 @@ static void sd_detach_aio_context(BlockDriverState *bs)
BDRVSheepdogState *s = bs->opaque;
aio_set_fd_handler(s->aio_context, s->fd, false, NULL,
NULL, NULL, NULL);
NULL, NULL);
}
static void sd_attach_aio_context(BlockDriverState *bs,
@@ -1354,7 +1406,7 @@ static void sd_attach_aio_context(BlockDriverState *bs,
s->aio_context = new_context;
aio_set_fd_handler(new_context, s->fd, false,
co_read_response, NULL, NULL, s);
co_read_response, NULL, s);
}
/* TODO Convert to fine grained options */
@@ -1468,7 +1520,7 @@ static int sd_open(BlockDriverState *bs, QDict *options, int flags,
return 0;
out:
aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd,
false, NULL, NULL, NULL, NULL);
false, NULL, NULL, NULL);
if (s->fd >= 0) {
closesocket(s->fd);
}
@@ -1507,7 +1559,7 @@ static void sd_reopen_commit(BDRVReopenState *state)
if (s->fd) {
aio_set_fd_handler(s->aio_context, s->fd, false,
NULL, NULL, NULL, NULL);
NULL, NULL, NULL);
closesocket(s->fd);
}
@@ -1531,7 +1583,7 @@ static void sd_reopen_abort(BDRVReopenState *state)
if (re_s->fd) {
aio_set_fd_handler(s->aio_context, re_s->fd, false,
NULL, NULL, NULL, NULL);
NULL, NULL, NULL);
closesocket(re_s->fd);
}
@@ -1920,7 +1972,7 @@ static void sd_close(BlockDriverState *bs)
}
aio_set_fd_handler(bdrv_get_aio_context(bs), s->fd,
false, NULL, NULL, NULL, NULL);
false, NULL, NULL, NULL);
closesocket(s->fd);
g_free(s->host_spec);
}
@@ -1973,10 +2025,11 @@ static int sd_truncate(BlockDriverState *bs, int64_t offset)
/*
* This function is called after writing data objects. If we need to
* update metadata, this sends a write request to the vdi object.
* Otherwise, this switches back to sd_co_readv/writev.
*/
static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
{
BDRVSheepdogState *s = acb->s;
BDRVSheepdogState *s = acb->common.bs->opaque;
struct iovec iov;
AIOReq *aio_req;
uint32_t offset, data_len, mn, mx;
@@ -1985,7 +2038,6 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
mx = acb->max_dirty_data_idx;
if (mn <= mx) {
/* we need to update the vdi object. */
++acb->nr_pending;
offset = sizeof(s->inode) - sizeof(s->inode.data_vdi_id) +
mn * sizeof(s->inode.data_vdi_id[0]);
data_len = (mx - mn + 1) * sizeof(s->inode.data_vdi_id[0]);
@@ -1997,11 +2049,15 @@ static void coroutine_fn sd_write_done(SheepdogAIOCB *acb)
iov.iov_len = sizeof(s->inode);
aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
data_len, offset, 0, false, 0, offset);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
add_aio_request(s, aio_req, &iov, 1, AIOCB_WRITE_UDATA);
if (--acb->nr_pending) {
qemu_coroutine_yield();
}
acb->aio_done_func = sd_finish_aiocb;
acb->aiocb_type = AIOCB_WRITE_UDATA;
return;
}
sd_finish_aiocb(acb);
}
/* Delete current working VDI on the snapshot chain */
@@ -2113,15 +2169,16 @@ out:
* Returns 1 when we need to wait a response, 0 when there is no sent
* request and -errno in error cases.
*/
static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb)
static int coroutine_fn sd_co_rw_vector(void *p)
{
SheepdogAIOCB *acb = p;
int ret = 0;
unsigned long len, done = 0, total = acb->nb_sectors * BDRV_SECTOR_SIZE;
unsigned long idx;
uint32_t object_size;
uint64_t oid;
uint64_t offset;
BDRVSheepdogState *s = acb->s;
BDRVSheepdogState *s = acb->common.bs->opaque;
SheepdogInode *inode = &s->inode;
AIOReq *aio_req;
@@ -2133,7 +2190,7 @@ static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb)
ret = sd_create_branch(s);
if (ret) {
acb->ret = -EIO;
return;
goto out;
}
}
@@ -2198,6 +2255,8 @@ static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb)
old_oid,
acb->aiocb_type == AIOCB_DISCARD_OBJ ?
0 : done);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
add_aio_request(s, aio_req, acb->qiov->iov, acb->qiov->niov,
acb->aiocb_type);
done:
@@ -2205,25 +2264,31 @@ static void coroutine_fn sd_co_rw_vector(SheepdogAIOCB *acb)
idx++;
done += len;
}
if (--acb->nr_pending) {
qemu_coroutine_yield();
out:
if (!--acb->nr_pending) {
return acb->ret;
}
return 1;
}
static void sd_aio_complete(SheepdogAIOCB *acb)
static bool check_overlapping_aiocb(BDRVSheepdogState *s, SheepdogAIOCB *aiocb)
{
if (acb->aiocb_type == AIOCB_FLUSH_CACHE) {
return;
SheepdogAIOCB *cb;
QLIST_FOREACH(cb, &s->inflight_aiocb_head, aiocb_siblings) {
if (AIOCBOverlapping(aiocb, cb)) {
return true;
}
}
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&acb->s->overlapping_queue);
QLIST_INSERT_HEAD(&s->inflight_aiocb_head, aiocb, aiocb_siblings);
return false;
}
static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov)
{
SheepdogAIOCB acb;
SheepdogAIOCB *acb;
int ret;
int64_t offset = (sector_num + nb_sectors) * BDRV_SECTOR_SIZE;
BDRVSheepdogState *s = bs->opaque;
@@ -2235,50 +2300,85 @@ static coroutine_fn int sd_co_writev(BlockDriverState *bs, int64_t sector_num,
}
}
sd_aio_setup(&acb, s, qiov, sector_num, nb_sectors, AIOCB_WRITE_UDATA);
sd_co_rw_vector(&acb);
sd_write_done(&acb);
sd_aio_complete(&acb);
acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
acb->aio_done_func = sd_write_done;
acb->aiocb_type = AIOCB_WRITE_UDATA;
return acb.ret;
retry:
if (check_overlapping_aiocb(s, acb)) {
qemu_co_queue_wait(&s->overlapping_queue);
goto retry;
}
ret = sd_co_rw_vector(acb);
if (ret <= 0) {
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
qemu_aio_unref(acb);
return ret;
}
qemu_coroutine_yield();
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
return acb->ret;
}
static coroutine_fn int sd_co_readv(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov)
{
SheepdogAIOCB acb;
SheepdogAIOCB *acb;
int ret;
BDRVSheepdogState *s = bs->opaque;
sd_aio_setup(&acb, s, qiov, sector_num, nb_sectors, AIOCB_READ_UDATA);
sd_co_rw_vector(&acb);
sd_aio_complete(&acb);
acb = sd_aio_setup(bs, qiov, sector_num, nb_sectors);
acb->aiocb_type = AIOCB_READ_UDATA;
acb->aio_done_func = sd_finish_aiocb;
return acb.ret;
retry:
if (check_overlapping_aiocb(s, acb)) {
qemu_co_queue_wait(&s->overlapping_queue);
goto retry;
}
ret = sd_co_rw_vector(acb);
if (ret <= 0) {
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
qemu_aio_unref(acb);
return ret;
}
qemu_coroutine_yield();
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
return acb->ret;
}
static int coroutine_fn sd_co_flush_to_disk(BlockDriverState *bs)
{
BDRVSheepdogState *s = bs->opaque;
SheepdogAIOCB acb;
SheepdogAIOCB *acb;
AIOReq *aio_req;
if (s->cache_flags != SD_FLAG_CMD_CACHE) {
return 0;
}
sd_aio_setup(&acb, s, NULL, 0, 0, AIOCB_FLUSH_CACHE);
acb = sd_aio_setup(bs, NULL, 0, 0);
acb->aiocb_type = AIOCB_FLUSH_CACHE;
acb->aio_done_func = sd_finish_aiocb;
acb.nr_pending++;
aio_req = alloc_aio_req(s, &acb, vid_to_vdi_oid(s->inode.vdi_id),
aio_req = alloc_aio_req(s, acb, vid_to_vdi_oid(s->inode.vdi_id),
0, 0, 0, false, 0, 0);
add_aio_request(s, aio_req, NULL, 0, acb.aiocb_type);
QLIST_INSERT_HEAD(&s->inflight_aio_head, aio_req, aio_siblings);
add_aio_request(s, aio_req, NULL, 0, acb->aiocb_type);
if (--acb.nr_pending) {
qemu_coroutine_yield();
}
sd_aio_complete(&acb);
return acb.ret;
qemu_coroutine_yield();
return acb->ret;
}
static int sd_snapshot_create(BlockDriverState *bs, QEMUSnapshotInfo *sn_info)
@@ -2712,8 +2812,9 @@ static int sd_load_vmstate(BlockDriverState *bs, QEMUIOVector *qiov,
static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset,
int count)
{
SheepdogAIOCB acb;
SheepdogAIOCB *acb;
BDRVSheepdogState *s = bs->opaque;
int ret;
QEMUIOVector discard_iov;
struct iovec iov;
uint32_t zero = 0;
@@ -2731,12 +2832,31 @@ static coroutine_fn int sd_co_pdiscard(BlockDriverState *bs, int64_t offset,
if (!QEMU_IS_ALIGNED(offset | count, BDRV_SECTOR_SIZE)) {
return -ENOTSUP;
}
sd_aio_setup(&acb, s, &discard_iov, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS, AIOCB_DISCARD_OBJ);
sd_co_rw_vector(&acb);
sd_aio_complete(&acb);
acb = sd_aio_setup(bs, &discard_iov, offset >> BDRV_SECTOR_BITS,
count >> BDRV_SECTOR_BITS);
acb->aiocb_type = AIOCB_DISCARD_OBJ;
acb->aio_done_func = sd_finish_aiocb;
return acb.ret;
retry:
if (check_overlapping_aiocb(s, acb)) {
qemu_co_queue_wait(&s->overlapping_queue);
goto retry;
}
ret = sd_co_rw_vector(acb);
if (ret <= 0) {
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
qemu_aio_unref(acb);
return ret;
}
qemu_coroutine_yield();
QLIST_REMOVE(acb, aiocb_siblings);
qemu_co_queue_restart_all(&s->overlapping_queue);
return acb->ret;
}
static coroutine_fn int64_t

View File

@@ -889,14 +889,10 @@ static void restart_coroutine(void *opaque)
DPRINTF("co=%p", co);
aio_co_wake(co);
qemu_coroutine_enter(co);
}
/* 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 set_fd_handler(BDRVSSHState *s, BlockDriverState *bs)
{
int r;
IOHandler *rd_handler = NULL, *wr_handler = NULL;
@@ -915,11 +911,26 @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
rd_handler, wr_handler);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
false, rd_handler, wr_handler, NULL, co);
false, rd_handler, wr_handler, co);
}
static coroutine_fn void clear_fd_handler(BDRVSSHState *s,
BlockDriverState *bs)
{
DPRINTF("s->sock=%d", s->sock);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock,
false, 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)
{
set_fd_handler(s, bs);
qemu_coroutine_yield();
DPRINTF("s->sock=%d - back", s->sock);
aio_set_fd_handler(bdrv_get_aio_context(bs), s->sock, false,
NULL, NULL, NULL, NULL);
clear_fd_handler(s, bs);
}
/* SFTP has a function `libssh2_sftp_seek64' which seeks to a position

View File

@@ -326,7 +326,7 @@ void coroutine_fn throttle_group_co_io_limits_intercept(BlockBackend *blk,
if (must_wait || blkp->pending_reqs[is_write]) {
blkp->pending_reqs[is_write]++;
qemu_mutex_unlock(&tg->lock);
qemu_co_queue_wait(&blkp->throttled_reqs[is_write], NULL);
qemu_co_queue_wait(&blkp->throttled_reqs[is_write]);
qemu_mutex_lock(&tg->lock);
blkp->pending_reqs[is_write]--;
}
@@ -416,9 +416,7 @@ static void timer_cb(BlockBackend *blk, bool is_write)
qemu_mutex_unlock(&tg->lock);
/* Run the request that was waiting for this timer */
aio_context_acquire(blk_get_aio_context(blk));
empty_queue = !qemu_co_enter_next(&blkp->throttled_reqs[is_write]);
aio_context_release(blk_get_aio_context(blk));
/* If the request queue was empty then we have to take care of
* scheduling the next one */

View File

@@ -35,6 +35,8 @@ mirror_one_iteration(void *s, int64_t sector_num, int nb_sectors) "s %p sector_n
mirror_iteration_done(void *s, int64_t sector_num, int nb_sectors, int ret) "s %p sector_num %"PRId64" nb_sectors %d ret %d"
mirror_yield(void *s, int64_t cnt, int buf_free_count, int in_flight) "s %p dirty count %"PRId64" free buffers %d in_flight %d"
mirror_yield_in_flight(void *s, int64_t sector_num, int in_flight) "s %p sector_num %"PRId64" in_flight %d"
mirror_yield_buf_busy(void *s, int nb_chunks, int in_flight) "s %p requested chunks %d in_flight %d"
mirror_break_buf_busy(void *s, int nb_chunks, int in_flight) "s %p requested chunks %d in_flight %d"
# block/backup.c
backup_do_cow_enter(void *job, int64_t start, int64_t sector_num, int nb_sectors) "job %p start %"PRId64" sector_num %"PRId64" nb_sectors %d"
@@ -51,8 +53,8 @@ qmp_block_job_resume(void *job) "job %p"
qmp_block_job_complete(void *job) "job %p"
qmp_block_stream(void *bs, void *job) "bs %p job %p"
# block/file-win32.c
# block/file-posix.c
# block/raw-win32.c
# block/raw-posix.c
paio_submit_co(int64_t offset, int count, int type) "offset %"PRId64" count %d type %d"
paio_submit(void *acb, void *opaque, int64_t offset, int count, int type) "acb %p opaque %p offset %"PRId64" count %d type %d"

View File

@@ -361,13 +361,6 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
VdiHeader header;
size_t bmap_size;
int ret;
Error *local_err = NULL;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
logout("\n");
@@ -478,12 +471,7 @@ static int vdi_open(BlockDriverState *bs, QDict *options, int flags,
error_setg(&s->migration_blocker, "The vdi format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail_free_bmap;
}
migrate_add_blocker(s->migration_blocker);
qemu_co_mutex_init(&s->write_lock);

View File

@@ -548,7 +548,7 @@ static int vhdx_log_flush(BlockDriverState *bs, BDRVVHDXState *s,
if (new_file_size % (1024*1024)) {
/* round up to nearest 1MB boundary */
new_file_size = ((new_file_size >> 20) + 1) << 20;
bdrv_truncate(bs->file, new_file_size);
bdrv_truncate(bs->file->bs, new_file_size);
}
}
qemu_vfree(desc_entries);

View File

@@ -898,12 +898,6 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
uint64_t signature;
Error *local_err = NULL;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
s->bat = NULL;
s->first_visible_write = true;
@@ -997,17 +991,6 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
}
}
/* Disable migration when VHDX images are used */
error_setg(&s->migration_blocker, "The vhdx format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail;
}
if (flags & BDRV_O_RDWR) {
ret = vhdx_update_headers(bs, s, false, NULL);
if (ret < 0) {
@@ -1017,6 +1000,12 @@ static int vhdx_open(BlockDriverState *bs, QDict *options, int flags,
/* TODO: differencing files */
/* Disable migration when VHDX images are used */
error_setg(&s->migration_blocker, "The vhdx format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
migrate_add_blocker(s->migration_blocker);
return 0;
fail:
vhdx_close(bs);
@@ -1171,7 +1160,7 @@ static int vhdx_allocate_block(BlockDriverState *bs, BDRVVHDXState *s,
/* per the spec, the address for a block is in units of 1MB */
*new_offset = ROUND_UP(*new_offset, 1024 * 1024);
return bdrv_truncate(bs->file, *new_offset + s->block_size);
return bdrv_truncate(bs->file->bs, *new_offset + s->block_size);
}
/*

View File

@@ -941,13 +941,6 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
int ret;
BDRVVmdkState *s = bs->opaque;
uint32_t magic;
Error *local_err = NULL;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
buf = vmdk_read_desc(bs->file, 0, errp);
if (!buf) {
@@ -983,13 +976,7 @@ static int vmdk_open(BlockDriverState *bs, QDict *options, int flags,
error_setg(&s->migration_blocker, "The vmdk format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail;
}
migrate_add_blocker(s->migration_blocker);
g_free(buf);
return 0;

View File

@@ -220,12 +220,6 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
int disk_type = VHD_DYNAMIC;
int ret;
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_file,
false, errp);
if (!bs->file) {
return -EINVAL;
}
opts = qemu_opts_create(&vpc_runtime_opts, NULL, 0, &error_abort);
qemu_opts_absorb_qdict(opts, options, &local_err);
if (local_err) {
@@ -428,18 +422,13 @@ static int vpc_open(BlockDriverState *bs, QDict *options, int flags,
#endif
}
qemu_co_mutex_init(&s->lock);
/* Disable migration when VHD images are used */
error_setg(&s->migration_blocker, "The vpc format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail;
}
qemu_co_mutex_init(&s->lock);
migrate_add_blocker(s->migration_blocker);
return 0;

View File

@@ -1185,26 +1185,22 @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
s->sector_count = s->faked_sectors + s->sectors_per_cluster*s->cluster_count;
if (s->first_sectors_number == 0x40) {
init_mbr(s, cyls, heads, secs);
}
// assert(is_consistent(s));
qemu_co_mutex_init(&s->lock);
/* Disable migration when vvfat is used rw */
if (s->qcow) {
error_setg(&s->migration_blocker,
"The vvfat (rw) format used by node '%s' "
"does not support live migration",
bdrv_get_device_or_node_name(bs));
ret = migrate_add_blocker(s->migration_blocker, &local_err);
if (local_err) {
error_propagate(errp, local_err);
error_free(s->migration_blocker);
goto fail;
}
migrate_add_blocker(s->migration_blocker);
}
if (s->first_sectors_number == 0x40) {
init_mbr(s, cyls, heads, secs);
}
qemu_co_mutex_init(&s->lock);
ret = 0;
fail:
qemu_opts_del(opts);
@@ -2968,7 +2964,6 @@ static void write_target_close(BlockDriverState *bs) {
static BlockDriver vvfat_write_target = {
.format_name = "vvfat_write_target",
.instance_size = sizeof(void*),
.bdrv_co_pwritev = write_target_commit,
.bdrv_close = write_target_close,
};
@@ -3037,13 +3032,14 @@ static int enable_write_target(BlockDriverState *bs, Error **errp)
unlink(s->qcow_filename);
#endif
backing = bdrv_new_open_driver(&vvfat_write_target, NULL, BDRV_O_ALLOW_RDWR,
&error_abort);
*(void**) backing->opaque = s;
backing = bdrv_new();
bdrv_set_backing_hd(s->bs, backing);
bdrv_unref(backing);
s->bs->backing->bs->drv = &vvfat_write_target;
s->bs->backing->bs->opaque = g_new(void *, 1);
*(void**)s->bs->backing->bs->opaque = s;
return 0;
err:

View File

@@ -41,7 +41,7 @@ struct QEMUWin32AIOState {
HANDLE hIOCP;
EventNotifier e;
int count;
AioContext *aio_ctx;
bool is_aio_context_attached;
};
typedef struct QEMUWin32AIOCB {
@@ -87,6 +87,7 @@ static void win32_aio_process_completion(QEMUWin32AIOState *s,
qemu_vfree(waiocb->buf);
}
waiocb->common.cb(waiocb->common.opaque, ret);
qemu_aio_unref(waiocb);
}
@@ -174,16 +175,16 @@ 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, false, NULL, NULL);
aio->aio_ctx = NULL;
aio_set_event_notifier(old_context, &aio->e, false, NULL);
aio->is_aio_context_attached = false;
}
void win32_aio_attach_aio_context(QEMUWin32AIOState *aio,
AioContext *new_context)
{
aio->aio_ctx = new_context;
aio->is_aio_context_attached = true;
aio_set_event_notifier(new_context, &aio->e, false,
win32_aio_completion_cb, NULL);
win32_aio_completion_cb);
}
QEMUWin32AIOState *win32_aio_init(void)
@@ -211,7 +212,7 @@ out_free_state:
void win32_aio_cleanup(QEMUWin32AIOState *aio)
{
assert(!aio->aio_ctx);
assert(!aio->is_aio_context_attached);
CloseHandle(aio->hIOCP);
event_notifier_cleanup(&aio->e);
g_free(aio);

View File

@@ -16,6 +16,7 @@
#include "qapi/qmp/qerror.h"
#include "sysemu/sysemu.h"
#include "qmp-commands.h"
#include "trace.h"
#include "block/nbd.h"
#include "io/channel-socket.h"

View File

@@ -48,7 +48,7 @@
#include "sysemu/sysemu.h"
#include "block/block_int.h"
#include "qmp-commands.h"
#include "block/trace.h"
#include "trace.h"
#include "sysemu/arch_init.h"
#include "qemu/cutils.h"
#include "qemu/help_option.h"
@@ -227,30 +227,27 @@ DriveInfo *drive_get(BlockInterfaceType type, int bus, int unit)
return NULL;
}
void drive_check_orphaned(void)
bool drive_check_orphaned(void)
{
BlockBackend *blk;
DriveInfo *dinfo;
Location loc;
bool orphans = false;
bool rs = false;
for (blk = blk_next(NULL); blk; blk = blk_next(blk)) {
dinfo = blk_legacy_dinfo(blk);
/* If dinfo->bdrv->dev is NULL, it has no device attached. */
/* Unless this is a default drive, this may be an oversight. */
if (!blk_get_attached_dev(blk) && !dinfo->is_default &&
dinfo->type != IF_NONE) {
loc_push_none(&loc);
qemu_opts_loc_restore(dinfo->opts);
error_report("machine type does not support"
" if=%s,bus=%d,unit=%d",
if_name[dinfo->type], dinfo->bus, dinfo->unit);
loc_pop(&loc);
orphans = true;
fprintf(stderr, "Warning: Orphaned drive without device: "
"id=%s,file=%s,if=%s,bus=%d,unit=%d\n",
blk_name(blk), blk_bs(blk) ? blk_bs(blk)->filename : "",
if_name[dinfo->type], dinfo->bus, dinfo->unit);
rs = true;
}
}
if (orphans) {
exit(1);
}
return rs;
}
DriveInfo *drive_get_by_index(BlockInterfaceType type, int index)
@@ -2858,7 +2855,6 @@ void qmp_block_resize(bool has_device, const char *device,
int64_t size, Error **errp)
{
Error *local_err = NULL;
BlockBackend *blk = NULL;
BlockDriverState *bs;
AioContext *aio_context;
int ret;
@@ -2889,13 +2885,10 @@ void qmp_block_resize(bool has_device, const char *device,
goto out;
}
blk = blk_new();
blk_insert_bs(blk, bs);
/* complete all in-flight operations before resizing the device */
bdrv_drain_all();
ret = blk_truncate(blk, size);
ret = bdrv_truncate(bs, size);
switch (ret) {
case 0:
break;
@@ -2917,7 +2910,6 @@ void qmp_block_resize(bool has_device, const char *device,
}
out:
blk_unref(blk);
aio_context_release(aio_context);
}

View File

@@ -25,6 +25,7 @@
#include "qemu/osdep.h"
#include "qemu-common.h"
#include "trace.h"
#include "block/block.h"
#include "block/blockjob_int.h"
#include "block/block_int.h"

View File

@@ -1,17 +0,0 @@
chardev-obj-y += char.o
chardev-obj-$(CONFIG_WIN32) += char-console.o
chardev-obj-$(CONFIG_POSIX) += char-fd.o
chardev-obj-y += char-file.o
chardev-obj-y += char-io.o
chardev-obj-y += char-mux.o
chardev-obj-y += char-null.o
chardev-obj-$(CONFIG_POSIX) += char-parallel.o
chardev-obj-y += char-pipe.o
chardev-obj-$(CONFIG_POSIX) += char-pty.o
chardev-obj-y += char-ringbuf.o
chardev-obj-y += char-serial.o
chardev-obj-y += char-socket.o
chardev-obj-y += char-stdio.o
chardev-obj-y += char-udp.o
chardev-obj-$(CONFIG_WIN32) += char-win.o
chardev-obj-$(CONFIG_WIN32) += char-win-stdio.o

View File

@@ -1,53 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "char-win.h"
static void qemu_chr_open_win_con(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
qemu_chr_open_win_file(chr, GetStdHandle(STD_OUTPUT_HANDLE));
}
static void char_console_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = qemu_chr_open_win_con;
}
static const TypeInfo char_console_type_info = {
.name = TYPE_CHARDEV_CONSOLE,
.parent = TYPE_CHARDEV_WIN,
.class_init = char_console_class_init,
};
static void register_types(void)
{
type_register_static(&char_console_type_info);
}
type_init(register_types);

View File

@@ -1,170 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qemu/sockets.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#include "io/channel-file.h"
#include "char-fd.h"
#include "char-io.h"
/* Called with chr_write_lock held. */
static int fd_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
FDChardev *s = FD_CHARDEV(chr);
return io_channel_send(s->ioc_out, buf, len);
}
static gboolean fd_chr_read(QIOChannel *chan, GIOCondition cond, void *opaque)
{
Chardev *chr = CHARDEV(opaque);
FDChardev *s = FD_CHARDEV(opaque);
int len;
uint8_t buf[CHR_READ_BUF_LEN];
ssize_t ret;
len = sizeof(buf);
if (len > s->max_size) {
len = s->max_size;
}
if (len == 0) {
return TRUE;
}
ret = qio_channel_read(
chan, (gchar *)buf, len, NULL);
if (ret == 0) {
remove_fd_in_watch(chr);
qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
return FALSE;
}
if (ret > 0) {
qemu_chr_be_write(chr, buf, ret);
}
return TRUE;
}
static int fd_chr_read_poll(void *opaque)
{
Chardev *chr = CHARDEV(opaque);
FDChardev *s = FD_CHARDEV(opaque);
s->max_size = qemu_chr_be_can_write(chr);
return s->max_size;
}
static GSource *fd_chr_add_watch(Chardev *chr, GIOCondition cond)
{
FDChardev *s = FD_CHARDEV(chr);
return qio_channel_create_watch(s->ioc_out, cond);
}
static void fd_chr_update_read_handler(Chardev *chr,
GMainContext *context)
{
FDChardev *s = FD_CHARDEV(chr);
remove_fd_in_watch(chr);
if (s->ioc_in) {
chr->fd_in_tag = io_add_watch_poll(chr, s->ioc_in,
fd_chr_read_poll,
fd_chr_read, chr,
context);
}
}
static void char_fd_finalize(Object *obj)
{
Chardev *chr = CHARDEV(obj);
FDChardev *s = FD_CHARDEV(obj);
remove_fd_in_watch(chr);
if (s->ioc_in) {
object_unref(OBJECT(s->ioc_in));
}
if (s->ioc_out) {
object_unref(OBJECT(s->ioc_out));
}
qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
}
int qmp_chardev_open_file_source(char *src, int flags, Error **errp)
{
int fd = -1;
TFR(fd = qemu_open(src, flags, 0666));
if (fd == -1) {
error_setg_file_open(errp, errno, src);
}
return fd;
}
/* open a character device to a unix fd */
void qemu_chr_open_fd(Chardev *chr,
int fd_in, int fd_out)
{
FDChardev *s = FD_CHARDEV(chr);
char *name;
s->ioc_in = QIO_CHANNEL(qio_channel_file_new_fd(fd_in));
name = g_strdup_printf("chardev-file-in-%s", chr->label);
qio_channel_set_name(QIO_CHANNEL(s->ioc_in), name);
g_free(name);
s->ioc_out = QIO_CHANNEL(qio_channel_file_new_fd(fd_out));
name = g_strdup_printf("chardev-file-out-%s", chr->label);
qio_channel_set_name(QIO_CHANNEL(s->ioc_out), name);
g_free(name);
qemu_set_nonblock(fd_out);
s->chr = chr;
}
static void char_fd_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->chr_add_watch = fd_chr_add_watch;
cc->chr_write = fd_chr_write;
cc->chr_update_read_handler = fd_chr_update_read_handler;
}
static const TypeInfo char_fd_type_info = {
.name = TYPE_CHARDEV_FD,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(FDChardev),
.instance_finalize = char_fd_finalize,
.class_init = char_fd_class_init,
.abstract = true,
};
static void register_types(void)
{
type_register_static(&char_fd_type_info);
}
type_init(register_types);

View File

@@ -1,44 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_FD_H
#define CHAR_FD_H
#include "io/channel.h"
#include "sysemu/char.h"
typedef struct FDChardev {
Chardev parent;
Chardev *chr;
QIOChannel *ioc_in, *ioc_out;
int max_size;
} FDChardev;
#define TYPE_CHARDEV_FD "chardev-fd"
#define FD_CHARDEV(obj) OBJECT_CHECK(FDChardev, (obj), TYPE_CHARDEV_FD)
void qemu_chr_open_fd(Chardev *chr, int fd_in, int fd_out);
int qmp_chardev_open_file_source(char *src, int flags, Error **errp);
#endif /* CHAR_FD_H */

View File

@@ -1,139 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#ifdef _WIN32
#include "char-win.h"
#else
#include "char-fd.h"
#endif
static void qmp_chardev_open_file(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevFile *file = backend->u.file.data;
#ifdef _WIN32
HANDLE out;
DWORD accessmode;
DWORD flags;
if (file->has_in) {
error_setg(errp, "input file not supported");
return;
}
if (file->has_append && file->append) {
/* Append to file if it already exists. */
accessmode = FILE_GENERIC_WRITE & ~FILE_WRITE_DATA;
flags = OPEN_ALWAYS;
} else {
/* Truncate file if it already exists. */
accessmode = GENERIC_WRITE;
flags = CREATE_ALWAYS;
}
out = CreateFile(file->out, accessmode, FILE_SHARE_READ, NULL, flags,
FILE_ATTRIBUTE_NORMAL, NULL);
if (out == INVALID_HANDLE_VALUE) {
error_setg(errp, "open %s failed", file->out);
return;
}
qemu_chr_open_win_file(chr, out);
#else
int flags, in = -1, out;
flags = O_WRONLY | O_CREAT | O_BINARY;
if (file->has_append && file->append) {
flags |= O_APPEND;
} else {
flags |= O_TRUNC;
}
out = qmp_chardev_open_file_source(file->out, flags, errp);
if (out < 0) {
return;
}
if (file->has_in) {
flags = O_RDONLY;
in = qmp_chardev_open_file_source(file->in, flags, errp);
if (in < 0) {
qemu_close(out);
return;
}
}
qemu_chr_open_fd(chr, in, out);
#endif
}
static void qemu_chr_parse_file_out(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *path = qemu_opt_get(opts, "path");
ChardevFile *file;
backend->type = CHARDEV_BACKEND_KIND_FILE;
if (path == NULL) {
error_setg(errp, "chardev: file: no filename given");
return;
}
file = backend->u.file.data = g_new0(ChardevFile, 1);
qemu_chr_parse_common(opts, qapi_ChardevFile_base(file));
file->out = g_strdup(path);
file->has_append = true;
file->append = qemu_opt_get_bool(opts, "append", false);
}
static void char_file_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_file_out;
cc->open = qmp_chardev_open_file;
}
static const TypeInfo char_file_type_info = {
.name = TYPE_CHARDEV_FILE,
#ifdef _WIN32
.parent = TYPE_CHARDEV_WIN,
#else
.parent = TYPE_CHARDEV_FD,
#endif
.class_init = char_file_class_init,
};
static void register_types(void)
{
type_register_static(&char_file_type_info);
}
type_init(register_types);

View File

@@ -1,192 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "char-io.h"
typedef struct IOWatchPoll {
GSource parent;
QIOChannel *ioc;
GSource *src;
IOCanReadHandler *fd_can_read;
GSourceFunc fd_read;
void *opaque;
GMainContext *context;
} IOWatchPoll;
static IOWatchPoll *io_watch_poll_from_source(GSource *source)
{
return container_of(source, IOWatchPoll, parent);
}
static gboolean io_watch_poll_prepare(GSource *source,
gint *timeout)
{
IOWatchPoll *iwp = io_watch_poll_from_source(source);
bool now_active = iwp->fd_can_read(iwp->opaque) > 0;
bool was_active = iwp->src != NULL;
if (was_active == now_active) {
return FALSE;
}
if (now_active) {
iwp->src = qio_channel_create_watch(
iwp->ioc, G_IO_IN | G_IO_ERR | G_IO_HUP | G_IO_NVAL);
g_source_set_callback(iwp->src, iwp->fd_read, iwp->opaque, NULL);
g_source_attach(iwp->src, iwp->context);
} else {
g_source_destroy(iwp->src);
g_source_unref(iwp->src);
iwp->src = NULL;
}
return FALSE;
}
static gboolean io_watch_poll_check(GSource *source)
{
return FALSE;
}
static gboolean io_watch_poll_dispatch(GSource *source, GSourceFunc callback,
gpointer user_data)
{
abort();
}
static void io_watch_poll_finalize(GSource *source)
{
/* Due to a glib bug, removing the last reference to a source
* inside a finalize callback causes recursive locking (and a
* deadlock). This is not a problem inside other callbacks,
* including dispatch callbacks, so we call io_remove_watch_poll
* to remove this source. At this point, iwp->src must
* be NULL, or we would leak it.
*
* This would be solved much more elegantly by child sources,
* but we support older glib versions that do not have them.
*/
IOWatchPoll *iwp = io_watch_poll_from_source(source);
assert(iwp->src == NULL);
}
static GSourceFuncs io_watch_poll_funcs = {
.prepare = io_watch_poll_prepare,
.check = io_watch_poll_check,
.dispatch = io_watch_poll_dispatch,
.finalize = io_watch_poll_finalize,
};
guint io_add_watch_poll(Chardev *chr,
QIOChannel *ioc,
IOCanReadHandler *fd_can_read,
QIOChannelFunc fd_read,
gpointer user_data,
GMainContext *context)
{
IOWatchPoll *iwp;
int tag;
char *name;
iwp = (IOWatchPoll *) g_source_new(&io_watch_poll_funcs,
sizeof(IOWatchPoll));
iwp->fd_can_read = fd_can_read;
iwp->opaque = user_data;
iwp->ioc = ioc;
iwp->fd_read = (GSourceFunc) fd_read;
iwp->src = NULL;
iwp->context = context;
name = g_strdup_printf("chardev-iowatch-%s", chr->label);
g_source_set_name((GSource *)iwp, name);
g_free(name);
tag = g_source_attach(&iwp->parent, context);
g_source_unref(&iwp->parent);
return tag;
}
static void io_remove_watch_poll(guint tag)
{
GSource *source;
IOWatchPoll *iwp;
g_return_if_fail(tag > 0);
source = g_main_context_find_source_by_id(NULL, tag);
g_return_if_fail(source != NULL);
iwp = io_watch_poll_from_source(source);
if (iwp->src) {
g_source_destroy(iwp->src);
g_source_unref(iwp->src);
iwp->src = NULL;
}
g_source_destroy(&iwp->parent);
}
void remove_fd_in_watch(Chardev *chr)
{
if (chr->fd_in_tag) {
io_remove_watch_poll(chr->fd_in_tag);
chr->fd_in_tag = 0;
}
}
int io_channel_send_full(QIOChannel *ioc,
const void *buf, size_t len,
int *fds, size_t nfds)
{
size_t offset = 0;
while (offset < len) {
ssize_t ret = 0;
struct iovec iov = { .iov_base = (char *)buf + offset,
.iov_len = len - offset };
ret = qio_channel_writev_full(
ioc, &iov, 1,
fds, nfds, NULL);
if (ret == QIO_CHANNEL_ERR_BLOCK) {
if (offset) {
return offset;
}
errno = EAGAIN;
return -1;
} else if (ret < 0) {
errno = EINVAL;
return -1;
}
offset += ret;
}
return offset;
}
int io_channel_send(QIOChannel *ioc, const void *buf, size_t len)
{
return io_channel_send_full(ioc, buf, len, NULL, 0);
}

View File

@@ -1,46 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_IO_H
#define CHAR_IO_H
#include "qemu-common.h"
#include "io/channel.h"
#include "sysemu/char.h"
/* Can only be used for read */
guint io_add_watch_poll(Chardev *chr,
QIOChannel *ioc,
IOCanReadHandler *fd_can_read,
QIOChannelFunc fd_read,
gpointer user_data,
GMainContext *context);
void remove_fd_in_watch(Chardev *chr);
int io_channel_send(QIOChannel *ioc, const void *buf, size_t len);
int io_channel_send_full(QIOChannel *ioc, const void *buf, size_t len,
int *fds, size_t nfds);
#endif /* CHAR_IO_H */

View File

@@ -1,358 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#include "sysemu/block-backend.h"
#include "char-mux.h"
/* MUX driver for serial I/O splitting */
/* Called with chr_write_lock held. */
static int mux_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
MuxChardev *d = MUX_CHARDEV(chr);
int ret;
if (!d->timestamps) {
ret = qemu_chr_fe_write(&d->chr, buf, len);
} else {
int i;
ret = 0;
for (i = 0; i < len; i++) {
if (d->linestart) {
char buf1[64];
int64_t ti;
int secs;
ti = qemu_clock_get_ms(QEMU_CLOCK_REALTIME);
if (d->timestamps_start == -1) {
d->timestamps_start = ti;
}
ti -= d->timestamps_start;
secs = ti / 1000;
snprintf(buf1, sizeof(buf1),
"[%02d:%02d:%02d.%03d] ",
secs / 3600,
(secs / 60) % 60,
secs % 60,
(int)(ti % 1000));
/* XXX this blocks entire thread. Rewrite to use
* qemu_chr_fe_write and background I/O callbacks */
qemu_chr_fe_write_all(&d->chr,
(uint8_t *)buf1, strlen(buf1));
d->linestart = 0;
}
ret += qemu_chr_fe_write(&d->chr, buf + i, 1);
if (buf[i] == '\n') {
d->linestart = 1;
}
}
}
return ret;
}
static const char * const mux_help[] = {
"% h print this help\n\r",
"% x exit emulator\n\r",
"% s save disk data back to file (if -snapshot)\n\r",
"% t toggle console timestamps\n\r",
"% b send break (magic sysrq)\n\r",
"% c switch between console and monitor\n\r",
"% % sends %\n\r",
NULL
};
int term_escape_char = 0x01; /* ctrl-a is used for escape */
static void mux_print_help(Chardev *chr)
{
int i, j;
char ebuf[15] = "Escape-Char";
char cbuf[50] = "\n\r";
if (term_escape_char > 0 && term_escape_char < 26) {
snprintf(cbuf, sizeof(cbuf), "\n\r");
snprintf(ebuf, sizeof(ebuf), "C-%c", term_escape_char - 1 + 'a');
} else {
snprintf(cbuf, sizeof(cbuf),
"\n\rEscape-Char set to Ascii: 0x%02x\n\r\n\r",
term_escape_char);
}
/* XXX this blocks entire thread. Rewrite to use
* qemu_chr_fe_write and background I/O callbacks */
qemu_chr_write_all(chr, (uint8_t *)cbuf, strlen(cbuf));
for (i = 0; mux_help[i] != NULL; i++) {
for (j = 0; mux_help[i][j] != '\0'; j++) {
if (mux_help[i][j] == '%') {
qemu_chr_write_all(chr, (uint8_t *)ebuf, strlen(ebuf));
} else {
qemu_chr_write_all(chr, (uint8_t *)&mux_help[i][j], 1);
}
}
}
}
void mux_chr_send_event(MuxChardev *d, int mux_nr, int event)
{
CharBackend *be = d->backends[mux_nr];
if (be && be->chr_event) {
be->chr_event(be->opaque, event);
}
}
static int mux_proc_byte(Chardev *chr, MuxChardev *d, int ch)
{
if (d->term_got_escape) {
d->term_got_escape = 0;
if (ch == term_escape_char) {
goto send_char;
}
switch (ch) {
case '?':
case 'h':
mux_print_help(chr);
break;
case 'x':
{
const char *term = "QEMU: Terminated\n\r";
qemu_chr_write_all(chr, (uint8_t *)term, strlen(term));
exit(0);
break;
}
case 's':
blk_commit_all();
break;
case 'b':
qemu_chr_be_event(chr, CHR_EVENT_BREAK);
break;
case 'c':
assert(d->mux_cnt > 0); /* handler registered with first fe */
/* Switch to the next registered device */
mux_set_focus(chr, (d->focus + 1) % d->mux_cnt);
break;
case 't':
d->timestamps = !d->timestamps;
d->timestamps_start = -1;
d->linestart = 0;
break;
}
} else if (ch == term_escape_char) {
d->term_got_escape = 1;
} else {
send_char:
return 1;
}
return 0;
}
static void mux_chr_accept_input(Chardev *chr)
{
MuxChardev *d = MUX_CHARDEV(chr);
int m = d->focus;
CharBackend *be = d->backends[m];
while (be && d->prod[m] != d->cons[m] &&
be->chr_can_read && be->chr_can_read(be->opaque)) {
be->chr_read(be->opaque,
&d->buffer[m][d->cons[m]++ & MUX_BUFFER_MASK], 1);
}
}
static int mux_chr_can_read(void *opaque)
{
MuxChardev *d = MUX_CHARDEV(opaque);
int m = d->focus;
CharBackend *be = d->backends[m];
if ((d->prod[m] - d->cons[m]) < MUX_BUFFER_SIZE) {
return 1;
}
if (be && be->chr_can_read) {
return be->chr_can_read(be->opaque);
}
return 0;
}
static void mux_chr_read(void *opaque, const uint8_t *buf, int size)
{
Chardev *chr = CHARDEV(opaque);
MuxChardev *d = MUX_CHARDEV(opaque);
int m = d->focus;
CharBackend *be = d->backends[m];
int i;
mux_chr_accept_input(opaque);
for (i = 0; i < size; i++)
if (mux_proc_byte(chr, d, buf[i])) {
if (d->prod[m] == d->cons[m] &&
be && be->chr_can_read &&
be->chr_can_read(be->opaque)) {
be->chr_read(be->opaque, &buf[i], 1);
} else {
d->buffer[m][d->prod[m]++ & MUX_BUFFER_MASK] = buf[i];
}
}
}
bool muxes_realized;
static void mux_chr_event(void *opaque, int event)
{
MuxChardev *d = MUX_CHARDEV(opaque);
int i;
if (!muxes_realized) {
return;
}
/* Send the event to all registered listeners */
for (i = 0; i < d->mux_cnt; i++) {
mux_chr_send_event(d, i, event);
}
}
static GSource *mux_chr_add_watch(Chardev *s, GIOCondition cond)
{
MuxChardev *d = MUX_CHARDEV(s);
Chardev *chr = qemu_chr_fe_get_driver(&d->chr);
ChardevClass *cc = CHARDEV_GET_CLASS(chr);
if (!cc->chr_add_watch) {
return NULL;
}
return cc->chr_add_watch(chr, cond);
}
static void char_mux_finalize(Object *obj)
{
MuxChardev *d = MUX_CHARDEV(obj);
int i;
for (i = 0; i < d->mux_cnt; i++) {
CharBackend *be = d->backends[i];
if (be) {
be->chr = NULL;
}
}
qemu_chr_fe_deinit(&d->chr);
}
void mux_chr_set_handlers(Chardev *chr, GMainContext *context)
{
MuxChardev *d = MUX_CHARDEV(chr);
/* Fix up the real driver with mux routines */
qemu_chr_fe_set_handlers(&d->chr,
mux_chr_can_read,
mux_chr_read,
mux_chr_event,
chr,
context, true);
}
void mux_set_focus(Chardev *chr, int focus)
{
MuxChardev *d = MUX_CHARDEV(chr);
assert(focus >= 0);
assert(focus < d->mux_cnt);
if (d->focus != -1) {
mux_chr_send_event(d, d->focus, CHR_EVENT_MUX_OUT);
}
d->focus = focus;
mux_chr_send_event(d, d->focus, CHR_EVENT_MUX_IN);
}
static void qemu_chr_open_mux(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevMux *mux = backend->u.mux.data;
Chardev *drv;
MuxChardev *d = MUX_CHARDEV(chr);
drv = qemu_chr_find(mux->chardev);
if (drv == NULL) {
error_setg(errp, "mux: base chardev %s not found", mux->chardev);
return;
}
d->focus = -1;
/* only default to opened state if we've realized the initial
* set of muxes
*/
*be_opened = muxes_realized;
qemu_chr_fe_init(&d->chr, drv, errp);
}
static void qemu_chr_parse_mux(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *chardev = qemu_opt_get(opts, "chardev");
ChardevMux *mux;
if (chardev == NULL) {
error_setg(errp, "chardev: mux: no chardev given");
return;
}
backend->type = CHARDEV_BACKEND_KIND_MUX;
mux = backend->u.mux.data = g_new0(ChardevMux, 1);
qemu_chr_parse_common(opts, qapi_ChardevMux_base(mux));
mux->chardev = g_strdup(chardev);
}
static void char_mux_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_mux;
cc->open = qemu_chr_open_mux;
cc->chr_write = mux_chr_write;
cc->chr_accept_input = mux_chr_accept_input;
cc->chr_add_watch = mux_chr_add_watch;
}
static const TypeInfo char_mux_type_info = {
.name = TYPE_CHARDEV_MUX,
.parent = TYPE_CHARDEV,
.class_init = char_mux_class_init,
.instance_size = sizeof(MuxChardev),
.instance_finalize = char_mux_finalize,
};
static void register_types(void)
{
type_register_static(&char_mux_type_info);
}
type_init(register_types);

View File

@@ -1,63 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_MUX_H
#define CHAR_MUX_H
#include "sysemu/char.h"
extern bool muxes_realized;
#define MAX_MUX 4
#define MUX_BUFFER_SIZE 32 /* Must be a power of 2. */
#define MUX_BUFFER_MASK (MUX_BUFFER_SIZE - 1)
typedef struct MuxChardev {
Chardev parent;
CharBackend *backends[MAX_MUX];
CharBackend chr;
int focus;
int mux_cnt;
int term_got_escape;
int max_size;
/* Intermediate input buffer catches escape sequences even if the
currently active device is not accepting any input - but only until it
is full as well. */
unsigned char buffer[MAX_MUX][MUX_BUFFER_SIZE];
int prod[MAX_MUX];
int cons[MAX_MUX];
int timestamps;
/* Protected by the Chardev chr_write_lock. */
int linestart;
int64_t timestamps_start;
} MuxChardev;
#define MUX_CHARDEV(obj) OBJECT_CHECK(MuxChardev, (obj), TYPE_CHARDEV_MUX)
#define CHARDEV_IS_MUX(chr) \
object_dynamic_cast(OBJECT(chr), TYPE_CHARDEV_MUX)
void mux_chr_set_handlers(Chardev *chr, GMainContext *context);
void mux_set_focus(Chardev *chr, int focus);
void mux_chr_send_event(MuxChardev *d, int mux_nr, int event);
#endif /* CHAR_MUX_H */

View File

@@ -1,54 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "sysemu/char.h"
static void null_chr_open(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
*be_opened = false;
}
static void char_null_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = null_chr_open;
}
static const TypeInfo char_null_type_info = {
.name = TYPE_CHARDEV_NULL,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(Chardev),
.class_init = char_null_class_init,
};
static void register_types(void)
{
type_register_static(&char_null_type_info);
}
type_init(register_types);

View File

@@ -1,316 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "sysemu/char.h"
#include "qapi/error.h"
#include <sys/ioctl.h>
#ifdef CONFIG_BSD
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__)
#include <dev/ppbus/ppi.h>
#include <dev/ppbus/ppbconf.h>
#elif defined(__DragonFly__)
#include <dev/misc/ppi/ppi.h>
#include <bus/ppbus/ppbconf.h>
#endif
#else
#ifdef __linux__
#include <linux/ppdev.h>
#include <linux/parport.h>
#endif
#endif
#include "char-fd.h"
#include "char-parallel.h"
#if defined(__linux__)
typedef struct {
Chardev parent;
int fd;
int mode;
} ParallelChardev;
#define PARALLEL_CHARDEV(obj) \
OBJECT_CHECK(ParallelChardev, (obj), TYPE_CHARDEV_PARALLEL)
static int pp_hw_mode(ParallelChardev *s, uint16_t mode)
{
if (s->mode != mode) {
int m = mode;
if (ioctl(s->fd, PPSETMODE, &m) < 0) {
return 0;
}
s->mode = mode;
}
return 1;
}
static int pp_ioctl(Chardev *chr, int cmd, void *arg)
{
ParallelChardev *drv = PARALLEL_CHARDEV(chr);
int fd = drv->fd;
uint8_t b;
switch (cmd) {
case CHR_IOCTL_PP_READ_DATA:
if (ioctl(fd, PPRDATA, &b) < 0) {
return -ENOTSUP;
}
*(uint8_t *)arg = b;
break;
case CHR_IOCTL_PP_WRITE_DATA:
b = *(uint8_t *)arg;
if (ioctl(fd, PPWDATA, &b) < 0) {
return -ENOTSUP;
}
break;
case CHR_IOCTL_PP_READ_CONTROL:
if (ioctl(fd, PPRCONTROL, &b) < 0) {
return -ENOTSUP;
}
/* Linux gives only the lowest bits, and no way to know data
direction! For better compatibility set the fixed upper
bits. */
*(uint8_t *)arg = b | 0xc0;
break;
case CHR_IOCTL_PP_WRITE_CONTROL:
b = *(uint8_t *)arg;
if (ioctl(fd, PPWCONTROL, &b) < 0) {
return -ENOTSUP;
}
break;
case CHR_IOCTL_PP_READ_STATUS:
if (ioctl(fd, PPRSTATUS, &b) < 0) {
return -ENOTSUP;
}
*(uint8_t *)arg = b;
break;
case CHR_IOCTL_PP_DATA_DIR:
if (ioctl(fd, PPDATADIR, (int *)arg) < 0) {
return -ENOTSUP;
}
break;
case CHR_IOCTL_PP_EPP_READ_ADDR:
if (pp_hw_mode(drv, IEEE1284_MODE_EPP | IEEE1284_ADDR)) {
struct ParallelIOArg *parg = arg;
int n = read(fd, parg->buffer, parg->count);
if (n != parg->count) {
return -EIO;
}
}
break;
case CHR_IOCTL_PP_EPP_READ:
if (pp_hw_mode(drv, IEEE1284_MODE_EPP)) {
struct ParallelIOArg *parg = arg;
int n = read(fd, parg->buffer, parg->count);
if (n != parg->count) {
return -EIO;
}
}
break;
case CHR_IOCTL_PP_EPP_WRITE_ADDR:
if (pp_hw_mode(drv, IEEE1284_MODE_EPP | IEEE1284_ADDR)) {
struct ParallelIOArg *parg = arg;
int n = write(fd, parg->buffer, parg->count);
if (n != parg->count) {
return -EIO;
}
}
break;
case CHR_IOCTL_PP_EPP_WRITE:
if (pp_hw_mode(drv, IEEE1284_MODE_EPP)) {
struct ParallelIOArg *parg = arg;
int n = write(fd, parg->buffer, parg->count);
if (n != parg->count) {
return -EIO;
}
}
break;
default:
return -ENOTSUP;
}
return 0;
}
static void qemu_chr_open_pp_fd(Chardev *chr,
int fd,
bool *be_opened,
Error **errp)
{
ParallelChardev *drv = PARALLEL_CHARDEV(chr);
if (ioctl(fd, PPCLAIM) < 0) {
error_setg_errno(errp, errno, "not a parallel port");
close(fd);
return;
}
drv->fd = fd;
drv->mode = IEEE1284_MODE_COMPAT;
}
#endif /* __linux__ */
#if defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || defined(__DragonFly__)
typedef struct {
Chardev parent;
int fd;
} ParallelChardev;
#define PARALLEL_CHARDEV(obj) \
OBJECT_CHECK(ParallelChardev, (obj), TYPE_CHARDEV_PARALLEL)
static int pp_ioctl(Chardev *chr, int cmd, void *arg)
{
ParallelChardev *drv = PARALLEL_CHARDEV(chr);
uint8_t b;
switch (cmd) {
case CHR_IOCTL_PP_READ_DATA:
if (ioctl(drv->fd, PPIGDATA, &b) < 0) {
return -ENOTSUP;
}
*(uint8_t *)arg = b;
break;
case CHR_IOCTL_PP_WRITE_DATA:
b = *(uint8_t *)arg;
if (ioctl(drv->fd, PPISDATA, &b) < 0) {
return -ENOTSUP;
}
break;
case CHR_IOCTL_PP_READ_CONTROL:
if (ioctl(drv->fd, PPIGCTRL, &b) < 0) {
return -ENOTSUP;
}
*(uint8_t *)arg = b;
break;
case CHR_IOCTL_PP_WRITE_CONTROL:
b = *(uint8_t *)arg;
if (ioctl(drv->fd, PPISCTRL, &b) < 0) {
return -ENOTSUP;
}
break;
case CHR_IOCTL_PP_READ_STATUS:
if (ioctl(drv->fd, PPIGSTATUS, &b) < 0) {
return -ENOTSUP;
}
*(uint8_t *)arg = b;
break;
default:
return -ENOTSUP;
}
return 0;
}
static void qemu_chr_open_pp_fd(Chardev *chr,
int fd,
bool *be_opened,
Error **errp)
{
ParallelChardev *drv = PARALLEL_CHARDEV(chr);
drv->fd = fd;
*be_opened = false;
}
#endif
#ifdef HAVE_CHARDEV_PARPORT
static void qmp_chardev_open_parallel(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevHostdev *parallel = backend->u.parallel.data;
int fd;
fd = qmp_chardev_open_file_source(parallel->device, O_RDWR, errp);
if (fd < 0) {
return;
}
qemu_chr_open_pp_fd(chr, fd, be_opened, errp);
}
static void qemu_chr_parse_parallel(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *device = qemu_opt_get(opts, "path");
ChardevHostdev *parallel;
if (device == NULL) {
error_setg(errp, "chardev: parallel: no device path given");
return;
}
backend->type = CHARDEV_BACKEND_KIND_PARALLEL;
parallel = backend->u.parallel.data = g_new0(ChardevHostdev, 1);
qemu_chr_parse_common(opts, qapi_ChardevHostdev_base(parallel));
parallel->device = g_strdup(device);
}
static void char_parallel_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_parallel;
cc->open = qmp_chardev_open_parallel;
#if defined(__linux__)
cc->chr_ioctl = pp_ioctl;
#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || \
defined(__DragonFly__)
cc->chr_ioctl = pp_ioctl;
#endif
}
static void char_parallel_finalize(Object *obj)
{
#if defined(__linux__)
Chardev *chr = CHARDEV(obj);
ParallelChardev *drv = PARALLEL_CHARDEV(chr);
int fd = drv->fd;
pp_hw_mode(drv, IEEE1284_MODE_COMPAT);
ioctl(fd, PPRELEASE);
close(fd);
qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
#elif defined(__FreeBSD__) || defined(__FreeBSD_kernel__) || \
defined(__DragonFly__)
/* FIXME: close fd? */
#endif
}
static const TypeInfo char_parallel_type_info = {
.name = TYPE_CHARDEV_PARALLEL,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(ParallelChardev),
.instance_finalize = char_parallel_finalize,
.class_init = char_parallel_class_init,
};
static void register_types(void)
{
type_register_static(&char_parallel_type_info);
}
type_init(register_types);
#endif

View File

@@ -1,32 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_PARALLEL_H
#define CHAR_PARALLEL_H
#if defined(__linux__) || defined(__FreeBSD__) || \
defined(__FreeBSD_kernel__) || defined(__DragonFly__)
#define HAVE_CHARDEV_PARPORT 1
#endif
#endif /* CHAR_PARALLEL_H */

View File

@@ -1,191 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qapi/error.h"
#include "sysemu/char.h"
#ifdef _WIN32
#include "char-win.h"
#else
#include "char-fd.h"
#endif
#ifdef _WIN32
#define MAXCONNECT 1
#define NTIMEOUT 5000
static int win_chr_pipe_init(Chardev *chr, const char *filename,
Error **errp)
{
WinChardev *s = WIN_CHARDEV(chr);
OVERLAPPED ov;
int ret;
DWORD size;
char *openname;
s->fpipe = TRUE;
s->hsend = CreateEvent(NULL, TRUE, FALSE, NULL);
if (!s->hsend) {
error_setg(errp, "Failed CreateEvent");
goto fail;
}
s->hrecv = CreateEvent(NULL, TRUE, FALSE, NULL);
if (!s->hrecv) {
error_setg(errp, "Failed CreateEvent");
goto fail;
}
openname = g_strdup_printf("\\\\.\\pipe\\%s", filename);
s->hcom = CreateNamedPipe(openname,
PIPE_ACCESS_DUPLEX | FILE_FLAG_OVERLAPPED,
PIPE_TYPE_BYTE | PIPE_READMODE_BYTE |
PIPE_WAIT,
MAXCONNECT, NSENDBUF, NRECVBUF, NTIMEOUT, NULL);
g_free(openname);
if (s->hcom == INVALID_HANDLE_VALUE) {
error_setg(errp, "Failed CreateNamedPipe (%lu)", GetLastError());
s->hcom = NULL;
goto fail;
}
ZeroMemory(&ov, sizeof(ov));
ov.hEvent = CreateEvent(NULL, TRUE, FALSE, NULL);
ret = ConnectNamedPipe(s->hcom, &ov);
if (ret) {
error_setg(errp, "Failed ConnectNamedPipe");
goto fail;
}
ret = GetOverlappedResult(s->hcom, &ov, &size, TRUE);
if (!ret) {
error_setg(errp, "Failed GetOverlappedResult");
if (ov.hEvent) {
CloseHandle(ov.hEvent);
ov.hEvent = NULL;
}
goto fail;
}
if (ov.hEvent) {
CloseHandle(ov.hEvent);
ov.hEvent = NULL;
}
qemu_add_polling_cb(win_chr_pipe_poll, chr);
return 0;
fail:
return -1;
}
static void qemu_chr_open_pipe(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevHostdev *opts = backend->u.pipe.data;
const char *filename = opts->device;
if (win_chr_pipe_init(chr, filename, errp) < 0) {
return;
}
}
#else
static void qemu_chr_open_pipe(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevHostdev *opts = backend->u.pipe.data;
int fd_in, fd_out;
char *filename_in;
char *filename_out;
const char *filename = opts->device;
filename_in = g_strdup_printf("%s.in", filename);
filename_out = g_strdup_printf("%s.out", filename);
TFR(fd_in = qemu_open(filename_in, O_RDWR | O_BINARY));
TFR(fd_out = qemu_open(filename_out, O_RDWR | O_BINARY));
g_free(filename_in);
g_free(filename_out);
if (fd_in < 0 || fd_out < 0) {
if (fd_in >= 0) {
close(fd_in);
}
if (fd_out >= 0) {
close(fd_out);
}
TFR(fd_in = fd_out = qemu_open(filename, O_RDWR | O_BINARY));
if (fd_in < 0) {
error_setg_file_open(errp, errno, filename);
return;
}
}
qemu_chr_open_fd(chr, fd_in, fd_out);
}
#endif /* !_WIN32 */
static void qemu_chr_parse_pipe(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *device = qemu_opt_get(opts, "path");
ChardevHostdev *dev;
if (device == NULL) {
error_setg(errp, "chardev: pipe: no device path given");
return;
}
backend->type = CHARDEV_BACKEND_KIND_PIPE;
dev = backend->u.pipe.data = g_new0(ChardevHostdev, 1);
qemu_chr_parse_common(opts, qapi_ChardevHostdev_base(dev));
dev->device = g_strdup(device);
}
static void char_pipe_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_pipe;
cc->open = qemu_chr_open_pipe;
}
static const TypeInfo char_pipe_type_info = {
.name = TYPE_CHARDEV_PIPE,
#ifdef _WIN32
.parent = TYPE_CHARDEV_WIN,
#else
.parent = TYPE_CHARDEV_FD,
#endif
.class_init = char_pipe_class_init,
};
static void register_types(void)
{
type_register_static(&char_pipe_type_info);
}
type_init(register_types);

View File

@@ -1,300 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#include "io/channel-file.h"
#include "qemu/sockets.h"
#include "qemu/error-report.h"
#include "char-io.h"
#if defined(__linux__) || defined(__sun__) || defined(__FreeBSD__) \
|| defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) \
|| defined(__GLIBC__)
typedef struct {
Chardev parent;
QIOChannel *ioc;
int read_bytes;
/* Protected by the Chardev chr_write_lock. */
int connected;
guint timer_tag;
guint open_tag;
} PtyChardev;
#define PTY_CHARDEV(obj) OBJECT_CHECK(PtyChardev, (obj), TYPE_CHARDEV_PTY)
static void pty_chr_update_read_handler_locked(Chardev *chr);
static void pty_chr_state(Chardev *chr, int connected);
static gboolean pty_chr_timer(gpointer opaque)
{
struct Chardev *chr = CHARDEV(opaque);
PtyChardev *s = PTY_CHARDEV(opaque);
qemu_mutex_lock(&chr->chr_write_lock);
s->timer_tag = 0;
s->open_tag = 0;
if (!s->connected) {
/* Next poll ... */
pty_chr_update_read_handler_locked(chr);
}
qemu_mutex_unlock(&chr->chr_write_lock);
return FALSE;
}
/* Called with chr_write_lock held. */
static void pty_chr_rearm_timer(Chardev *chr, int ms)
{
PtyChardev *s = PTY_CHARDEV(chr);
char *name;
if (s->timer_tag) {
g_source_remove(s->timer_tag);
s->timer_tag = 0;
}
if (ms == 1000) {
name = g_strdup_printf("pty-timer-secs-%s", chr->label);
s->timer_tag = g_timeout_add_seconds(1, pty_chr_timer, chr);
} else {
name = g_strdup_printf("pty-timer-ms-%s", chr->label);
s->timer_tag = g_timeout_add(ms, pty_chr_timer, chr);
}
g_source_set_name_by_id(s->timer_tag, name);
g_free(name);
}
/* Called with chr_write_lock held. */
static void pty_chr_update_read_handler_locked(Chardev *chr)
{
PtyChardev *s = PTY_CHARDEV(chr);
GPollFD pfd;
int rc;
QIOChannelFile *fioc = QIO_CHANNEL_FILE(s->ioc);
pfd.fd = fioc->fd;
pfd.events = G_IO_OUT;
pfd.revents = 0;
do {
rc = g_poll(&pfd, 1, 0);
} while (rc == -1 && errno == EINTR);
assert(rc >= 0);
if (pfd.revents & G_IO_HUP) {
pty_chr_state(chr, 0);
} else {
pty_chr_state(chr, 1);
}
}
static void pty_chr_update_read_handler(Chardev *chr,
GMainContext *context)
{
qemu_mutex_lock(&chr->chr_write_lock);
pty_chr_update_read_handler_locked(chr);
qemu_mutex_unlock(&chr->chr_write_lock);
}
/* Called with chr_write_lock held. */
static int char_pty_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
PtyChardev *s = PTY_CHARDEV(chr);
if (!s->connected) {
/* guest sends data, check for (re-)connect */
pty_chr_update_read_handler_locked(chr);
if (!s->connected) {
return len;
}
}
return io_channel_send(s->ioc, buf, len);
}
static GSource *pty_chr_add_watch(Chardev *chr, GIOCondition cond)
{
PtyChardev *s = PTY_CHARDEV(chr);
if (!s->connected) {
return NULL;
}
return qio_channel_create_watch(s->ioc, cond);
}
static int pty_chr_read_poll(void *opaque)
{
Chardev *chr = CHARDEV(opaque);
PtyChardev *s = PTY_CHARDEV(opaque);
s->read_bytes = qemu_chr_be_can_write(chr);
return s->read_bytes;
}
static gboolean pty_chr_read(QIOChannel *chan, GIOCondition cond, void *opaque)
{
Chardev *chr = CHARDEV(opaque);
PtyChardev *s = PTY_CHARDEV(opaque);
gsize len;
uint8_t buf[CHR_READ_BUF_LEN];
ssize_t ret;
len = sizeof(buf);
if (len > s->read_bytes) {
len = s->read_bytes;
}
if (len == 0) {
return TRUE;
}
ret = qio_channel_read(s->ioc, (char *)buf, len, NULL);
if (ret <= 0) {
pty_chr_state(chr, 0);
return FALSE;
} else {
pty_chr_state(chr, 1);
qemu_chr_be_write(chr, buf, ret);
}
return TRUE;
}
static gboolean qemu_chr_be_generic_open_func(gpointer opaque)
{
Chardev *chr = CHARDEV(opaque);
PtyChardev *s = PTY_CHARDEV(opaque);
s->open_tag = 0;
qemu_chr_be_generic_open(chr);
return FALSE;
}
/* Called with chr_write_lock held. */
static void pty_chr_state(Chardev *chr, int connected)
{
PtyChardev *s = PTY_CHARDEV(chr);
if (!connected) {
if (s->open_tag) {
g_source_remove(s->open_tag);
s->open_tag = 0;
}
remove_fd_in_watch(chr);
s->connected = 0;
/* (re-)connect poll interval for idle guests: once per second.
* We check more frequently in case the guests sends data to
* the virtual device linked to our pty. */
pty_chr_rearm_timer(chr, 1000);
} else {
if (s->timer_tag) {
g_source_remove(s->timer_tag);
s->timer_tag = 0;
}
if (!s->connected) {
g_assert(s->open_tag == 0);
s->connected = 1;
s->open_tag = g_idle_add(qemu_chr_be_generic_open_func, chr);
}
if (!chr->fd_in_tag) {
chr->fd_in_tag = io_add_watch_poll(chr, s->ioc,
pty_chr_read_poll,
pty_chr_read,
chr, NULL);
}
}
}
static void char_pty_finalize(Object *obj)
{
Chardev *chr = CHARDEV(obj);
PtyChardev *s = PTY_CHARDEV(obj);
qemu_mutex_lock(&chr->chr_write_lock);
pty_chr_state(chr, 0);
object_unref(OBJECT(s->ioc));
if (s->timer_tag) {
g_source_remove(s->timer_tag);
s->timer_tag = 0;
}
qemu_mutex_unlock(&chr->chr_write_lock);
qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
}
static void char_pty_open(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
PtyChardev *s;
int master_fd, slave_fd;
char pty_name[PATH_MAX];
char *name;
master_fd = qemu_openpty_raw(&slave_fd, pty_name);
if (master_fd < 0) {
error_setg_errno(errp, errno, "Failed to create PTY");
return;
}
close(slave_fd);
qemu_set_nonblock(master_fd);
chr->filename = g_strdup_printf("pty:%s", pty_name);
error_report("char device redirected to %s (label %s)",
pty_name, chr->label);
s = PTY_CHARDEV(chr);
s->ioc = QIO_CHANNEL(qio_channel_file_new_fd(master_fd));
name = g_strdup_printf("chardev-pty-%s", chr->label);
qio_channel_set_name(QIO_CHANNEL(s->ioc), name);
g_free(name);
s->timer_tag = 0;
*be_opened = false;
}
static void char_pty_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = char_pty_open;
cc->chr_write = char_pty_chr_write;
cc->chr_update_read_handler = pty_chr_update_read_handler;
cc->chr_add_watch = pty_chr_add_watch;
}
static const TypeInfo char_pty_type_info = {
.name = TYPE_CHARDEV_PTY,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(PtyChardev),
.instance_finalize = char_pty_finalize,
.class_init = char_pty_class_init,
};
static void register_types(void)
{
type_register_static(&char_pty_type_info);
}
type_init(register_types);
#endif

View File

@@ -1,249 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "sysemu/char.h"
#include "qmp-commands.h"
#include "qemu/base64.h"
/* Ring buffer chardev */
typedef struct {
Chardev parent;
size_t size;
size_t prod;
size_t cons;
uint8_t *cbuf;
} RingBufChardev;
#define RINGBUF_CHARDEV(obj) \
OBJECT_CHECK(RingBufChardev, (obj), TYPE_CHARDEV_RINGBUF)
static size_t ringbuf_count(const Chardev *chr)
{
const RingBufChardev *d = RINGBUF_CHARDEV(chr);
return d->prod - d->cons;
}
static int ringbuf_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
RingBufChardev *d = RINGBUF_CHARDEV(chr);
int i;
if (!buf || (len < 0)) {
return -1;
}
for (i = 0; i < len; i++) {
d->cbuf[d->prod++ & (d->size - 1)] = buf[i];
if (d->prod - d->cons > d->size) {
d->cons = d->prod - d->size;
}
}
return len;
}
static int ringbuf_chr_read(Chardev *chr, uint8_t *buf, int len)
{
RingBufChardev *d = RINGBUF_CHARDEV(chr);
int i;
qemu_mutex_lock(&chr->chr_write_lock);
for (i = 0; i < len && d->cons != d->prod; i++) {
buf[i] = d->cbuf[d->cons++ & (d->size - 1)];
}
qemu_mutex_unlock(&chr->chr_write_lock);
return i;
}
static void char_ringbuf_finalize(Object *obj)
{
RingBufChardev *d = RINGBUF_CHARDEV(obj);
g_free(d->cbuf);
}
static void qemu_chr_open_ringbuf(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevRingbuf *opts = backend->u.ringbuf.data;
RingBufChardev *d = RINGBUF_CHARDEV(chr);
d->size = opts->has_size ? opts->size : 65536;
/* The size must be power of 2 */
if (d->size & (d->size - 1)) {
error_setg(errp, "size of ringbuf chardev must be power of two");
return;
}
d->prod = 0;
d->cons = 0;
d->cbuf = g_malloc0(d->size);
}
void qmp_ringbuf_write(const char *device, const char *data,
bool has_format, enum DataFormat format,
Error **errp)
{
Chardev *chr;
const uint8_t *write_data;
int ret;
gsize write_count;
chr = qemu_chr_find(device);
if (!chr) {
error_setg(errp, "Device '%s' not found", device);
return;
}
if (!CHARDEV_IS_RINGBUF(chr)) {
error_setg(errp, "%s is not a ringbuf device", device);
return;
}
if (has_format && (format == DATA_FORMAT_BASE64)) {
write_data = qbase64_decode(data, -1,
&write_count,
errp);
if (!write_data) {
return;
}
} else {
write_data = (uint8_t *)data;
write_count = strlen(data);
}
ret = ringbuf_chr_write(chr, write_data, write_count);
if (write_data != (uint8_t *)data) {
g_free((void *)write_data);
}
if (ret < 0) {
error_setg(errp, "Failed to write to device %s", device);
return;
}
}
char *qmp_ringbuf_read(const char *device, int64_t size,
bool has_format, enum DataFormat format,
Error **errp)
{
Chardev *chr;
uint8_t *read_data;
size_t count;
char *data;
chr = qemu_chr_find(device);
if (!chr) {
error_setg(errp, "Device '%s' not found", device);
return NULL;
}
if (!CHARDEV_IS_RINGBUF(chr)) {
error_setg(errp, "%s is not a ringbuf device", device);
return NULL;
}
if (size <= 0) {
error_setg(errp, "size must be greater than zero");
return NULL;
}
count = ringbuf_count(chr);
size = size > count ? count : size;
read_data = g_malloc(size + 1);
ringbuf_chr_read(chr, read_data, size);
if (has_format && (format == DATA_FORMAT_BASE64)) {
data = g_base64_encode(read_data, size);
g_free(read_data);
} else {
/*
* FIXME should read only complete, valid UTF-8 characters up
* to @size bytes. Invalid sequences should be replaced by a
* suitable replacement character. Except when (and only
* when) ring buffer lost characters since last read, initial
* continuation characters should be dropped.
*/
read_data[size] = 0;
data = (char *)read_data;
}
return data;
}
static void qemu_chr_parse_ringbuf(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
int val;
ChardevRingbuf *ringbuf;
backend->type = CHARDEV_BACKEND_KIND_RINGBUF;
ringbuf = backend->u.ringbuf.data = g_new0(ChardevRingbuf, 1);
qemu_chr_parse_common(opts, qapi_ChardevRingbuf_base(ringbuf));
val = qemu_opt_get_size(opts, "size", 0);
if (val != 0) {
ringbuf->has_size = true;
ringbuf->size = val;
}
}
static void char_ringbuf_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_ringbuf;
cc->open = qemu_chr_open_ringbuf;
cc->chr_write = ringbuf_chr_write;
}
static const TypeInfo char_ringbuf_type_info = {
.name = TYPE_CHARDEV_RINGBUF,
.parent = TYPE_CHARDEV,
.class_init = char_ringbuf_class_init,
.instance_size = sizeof(RingBufChardev),
.instance_finalize = char_ringbuf_finalize,
};
/* Bug-compatibility: */
static const TypeInfo char_memory_type_info = {
.name = TYPE_CHARDEV_MEMORY,
.parent = TYPE_CHARDEV_RINGBUF,
};
static void register_types(void)
{
type_register_static(&char_ringbuf_type_info);
type_register_static(&char_memory_type_info);
}
type_init(register_types);

View File

@@ -1,318 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qemu/sockets.h"
#include "io/channel-file.h"
#include "qapi/error.h"
#ifdef _WIN32
#include "char-win.h"
#else
#include <sys/ioctl.h>
#include <termios.h>
#include "char-fd.h"
#endif
#include "char-serial.h"
#ifdef _WIN32
static void qmp_chardev_open_serial(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevHostdev *serial = backend->u.serial.data;
win_chr_init(chr, serial->device, errp);
}
#elif defined(__linux__) || defined(__sun__) || defined(__FreeBSD__) \
|| defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) \
|| defined(__GLIBC__)
static void tty_serial_init(int fd, int speed,
int parity, int data_bits, int stop_bits)
{
struct termios tty;
speed_t spd;
#if 0
printf("tty_serial_init: speed=%d parity=%c data=%d stop=%d\n",
speed, parity, data_bits, stop_bits);
#endif
tcgetattr(fd, &tty);
#define check_speed(val) if (speed <= val) { spd = B##val; break; }
speed = speed * 10 / 11;
do {
check_speed(50);
check_speed(75);
check_speed(110);
check_speed(134);
check_speed(150);
check_speed(200);
check_speed(300);
check_speed(600);
check_speed(1200);
check_speed(1800);
check_speed(2400);
check_speed(4800);
check_speed(9600);
check_speed(19200);
check_speed(38400);
/* Non-Posix values follow. They may be unsupported on some systems. */
check_speed(57600);
check_speed(115200);
#ifdef B230400
check_speed(230400);
#endif
#ifdef B460800
check_speed(460800);
#endif
#ifdef B500000
check_speed(500000);
#endif
#ifdef B576000
check_speed(576000);
#endif
#ifdef B921600
check_speed(921600);
#endif
#ifdef B1000000
check_speed(1000000);
#endif
#ifdef B1152000
check_speed(1152000);
#endif
#ifdef B1500000
check_speed(1500000);
#endif
#ifdef B2000000
check_speed(2000000);
#endif
#ifdef B2500000
check_speed(2500000);
#endif
#ifdef B3000000
check_speed(3000000);
#endif
#ifdef B3500000
check_speed(3500000);
#endif
#ifdef B4000000
check_speed(4000000);
#endif
spd = B115200;
} while (0);
cfsetispeed(&tty, spd);
cfsetospeed(&tty, spd);
tty.c_iflag &= ~(IGNBRK | BRKINT | PARMRK | ISTRIP
| INLCR | IGNCR | ICRNL | IXON);
tty.c_oflag |= OPOST;
tty.c_lflag &= ~(ECHO | ECHONL | ICANON | IEXTEN | ISIG);
tty.c_cflag &= ~(CSIZE | PARENB | PARODD | CRTSCTS | CSTOPB);
switch (data_bits) {
default:
case 8:
tty.c_cflag |= CS8;
break;
case 7:
tty.c_cflag |= CS7;
break;
case 6:
tty.c_cflag |= CS6;
break;
case 5:
tty.c_cflag |= CS5;
break;
}
switch (parity) {
default:
case 'N':
break;
case 'E':
tty.c_cflag |= PARENB;
break;
case 'O':
tty.c_cflag |= PARENB | PARODD;
break;
}
if (stop_bits == 2) {
tty.c_cflag |= CSTOPB;
}
tcsetattr(fd, TCSANOW, &tty);
}
static int tty_serial_ioctl(Chardev *chr, int cmd, void *arg)
{
FDChardev *s = FD_CHARDEV(chr);
QIOChannelFile *fioc = QIO_CHANNEL_FILE(s->ioc_in);
switch (cmd) {
case CHR_IOCTL_SERIAL_SET_PARAMS:
{
QEMUSerialSetParams *ssp = arg;
tty_serial_init(fioc->fd,
ssp->speed, ssp->parity,
ssp->data_bits, ssp->stop_bits);
}
break;
case CHR_IOCTL_SERIAL_SET_BREAK:
{
int enable = *(int *)arg;
if (enable) {
tcsendbreak(fioc->fd, 1);
}
}
break;
case CHR_IOCTL_SERIAL_GET_TIOCM:
{
int sarg = 0;
int *targ = (int *)arg;
ioctl(fioc->fd, TIOCMGET, &sarg);
*targ = 0;
if (sarg & TIOCM_CTS) {
*targ |= CHR_TIOCM_CTS;
}
if (sarg & TIOCM_CAR) {
*targ |= CHR_TIOCM_CAR;
}
if (sarg & TIOCM_DSR) {
*targ |= CHR_TIOCM_DSR;
}
if (sarg & TIOCM_RI) {
*targ |= CHR_TIOCM_RI;
}
if (sarg & TIOCM_DTR) {
*targ |= CHR_TIOCM_DTR;
}
if (sarg & TIOCM_RTS) {
*targ |= CHR_TIOCM_RTS;
}
}
break;
case CHR_IOCTL_SERIAL_SET_TIOCM:
{
int sarg = *(int *)arg;
int targ = 0;
ioctl(fioc->fd, TIOCMGET, &targ);
targ &= ~(CHR_TIOCM_CTS | CHR_TIOCM_CAR | CHR_TIOCM_DSR
| CHR_TIOCM_RI | CHR_TIOCM_DTR | CHR_TIOCM_RTS);
if (sarg & CHR_TIOCM_CTS) {
targ |= TIOCM_CTS;
}
if (sarg & CHR_TIOCM_CAR) {
targ |= TIOCM_CAR;
}
if (sarg & CHR_TIOCM_DSR) {
targ |= TIOCM_DSR;
}
if (sarg & CHR_TIOCM_RI) {
targ |= TIOCM_RI;
}
if (sarg & CHR_TIOCM_DTR) {
targ |= TIOCM_DTR;
}
if (sarg & CHR_TIOCM_RTS) {
targ |= TIOCM_RTS;
}
ioctl(fioc->fd, TIOCMSET, &targ);
}
break;
default:
return -ENOTSUP;
}
return 0;
}
static void qmp_chardev_open_serial(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevHostdev *serial = backend->u.serial.data;
int fd;
fd = qmp_chardev_open_file_source(serial->device, O_RDWR, errp);
if (fd < 0) {
return;
}
qemu_set_nonblock(fd);
tty_serial_init(fd, 115200, 'N', 8, 1);
qemu_chr_open_fd(chr, fd, fd);
}
#endif /* __linux__ || __sun__ */
#ifdef HAVE_CHARDEV_SERIAL
static void qemu_chr_parse_serial(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *device = qemu_opt_get(opts, "path");
ChardevHostdev *serial;
if (device == NULL) {
error_setg(errp, "chardev: serial/tty: no device path given");
return;
}
backend->type = CHARDEV_BACKEND_KIND_SERIAL;
serial = backend->u.serial.data = g_new0(ChardevHostdev, 1);
qemu_chr_parse_common(opts, qapi_ChardevHostdev_base(serial));
serial->device = g_strdup(device);
}
static void char_serial_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_serial;
cc->open = qmp_chardev_open_serial;
#ifndef _WIN32
cc->chr_ioctl = tty_serial_ioctl;
#endif
}
static const TypeInfo char_serial_type_info = {
.name = TYPE_CHARDEV_SERIAL,
#ifdef _WIN32
.parent = TYPE_CHARDEV_WIN,
#else
.parent = TYPE_CHARDEV_FD,
#endif
.class_init = char_serial_class_init,
};
static void register_types(void)
{
type_register_static(&char_serial_type_info);
}
type_init(register_types);
#endif

View File

@@ -1,35 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_SERIAL_H
#define CHAR_SERIAL_H
#ifdef _WIN32
#define HAVE_CHARDEV_SERIAL 1
#elif defined(__linux__) || defined(__sun__) || defined(__FreeBSD__) \
|| defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__) \
|| defined(__GLIBC__)
#define HAVE_CHARDEV_SERIAL 1
#endif
#endif

File diff suppressed because it is too large Load Diff

View File

@@ -1,164 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qemu/sockets.h"
#include "qapi/error.h"
#include "qemu-common.h"
#include "sysemu/char.h"
#ifdef _WIN32
#include "char-win.h"
#include "char-win-stdio.h"
#else
#include <termios.h>
#include "char-fd.h"
#endif
#ifndef _WIN32
/* init terminal so that we can grab keys */
static struct termios oldtty;
static int old_fd0_flags;
static bool stdio_in_use;
static bool stdio_allow_signal;
static bool stdio_echo_state;
static void term_exit(void)
{
tcsetattr(0, TCSANOW, &oldtty);
fcntl(0, F_SETFL, old_fd0_flags);
}
static void qemu_chr_set_echo_stdio(Chardev *chr, bool echo)
{
struct termios tty;
stdio_echo_state = echo;
tty = oldtty;
if (!echo) {
tty.c_iflag &= ~(IGNBRK | BRKINT | PARMRK | ISTRIP
| INLCR | IGNCR | ICRNL | IXON);
tty.c_oflag |= OPOST;
tty.c_lflag &= ~(ECHO | ECHONL | ICANON | IEXTEN);
tty.c_cflag &= ~(CSIZE | PARENB);
tty.c_cflag |= CS8;
tty.c_cc[VMIN] = 1;
tty.c_cc[VTIME] = 0;
}
if (!stdio_allow_signal) {
tty.c_lflag &= ~ISIG;
}
tcsetattr(0, TCSANOW, &tty);
}
static void term_stdio_handler(int sig)
{
/* restore echo after resume from suspend. */
qemu_chr_set_echo_stdio(NULL, stdio_echo_state);
}
static void qemu_chr_open_stdio(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevStdio *opts = backend->u.stdio.data;
struct sigaction act;
if (is_daemonized()) {
error_setg(errp, "cannot use stdio with -daemonize");
return;
}
if (stdio_in_use) {
error_setg(errp, "cannot use stdio by multiple character devices");
return;
}
stdio_in_use = true;
old_fd0_flags = fcntl(0, F_GETFL);
tcgetattr(0, &oldtty);
qemu_set_nonblock(0);
atexit(term_exit);
memset(&act, 0, sizeof(act));
act.sa_handler = term_stdio_handler;
sigaction(SIGCONT, &act, NULL);
qemu_chr_open_fd(chr, 0, 1);
if (opts->has_signal) {
stdio_allow_signal = opts->signal;
}
qemu_chr_set_echo_stdio(chr, false);
}
#endif
static void qemu_chr_parse_stdio(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
ChardevStdio *stdio;
backend->type = CHARDEV_BACKEND_KIND_STDIO;
stdio = backend->u.stdio.data = g_new0(ChardevStdio, 1);
qemu_chr_parse_common(opts, qapi_ChardevStdio_base(stdio));
stdio->has_signal = true;
stdio->signal = qemu_opt_get_bool(opts, "signal", true);
}
static void char_stdio_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_stdio;
#ifndef _WIN32
cc->open = qemu_chr_open_stdio;
cc->chr_set_echo = qemu_chr_set_echo_stdio;
#endif
}
static void char_stdio_finalize(Object *obj)
{
#ifndef _WIN32
term_exit();
#endif
}
static const TypeInfo char_stdio_type_info = {
.name = TYPE_CHARDEV_STDIO,
#ifdef _WIN32
.parent = TYPE_CHARDEV_WIN_STDIO,
#else
.parent = TYPE_CHARDEV_FD,
#endif
.instance_finalize = char_stdio_finalize,
.class_init = char_stdio_class_init,
};
static void register_types(void)
{
type_register_static(&char_stdio_type_info);
}
type_init(register_types);

View File

@@ -1,233 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "sysemu/char.h"
#include "io/channel-socket.h"
#include "qapi/error.h"
#include "char-io.h"
/***********************************************************/
/* UDP Net console */
typedef struct {
Chardev parent;
QIOChannel *ioc;
uint8_t buf[CHR_READ_BUF_LEN];
int bufcnt;
int bufptr;
int max_size;
} UdpChardev;
#define UDP_CHARDEV(obj) OBJECT_CHECK(UdpChardev, (obj), TYPE_CHARDEV_UDP)
/* Called with chr_write_lock held. */
static int udp_chr_write(Chardev *chr, const uint8_t *buf, int len)
{
UdpChardev *s = UDP_CHARDEV(chr);
return qio_channel_write(
s->ioc, (const char *)buf, len, NULL);
}
static int udp_chr_read_poll(void *opaque)
{
Chardev *chr = CHARDEV(opaque);
UdpChardev *s = UDP_CHARDEV(opaque);
s->max_size = qemu_chr_be_can_write(chr);
/* If there were any stray characters in the queue process them
* first
*/
while (s->max_size > 0 && s->bufptr < s->bufcnt) {
qemu_chr_be_write(chr, &s->buf[s->bufptr], 1);
s->bufptr++;
s->max_size = qemu_chr_be_can_write(chr);
}
return s->max_size;
}
static gboolean udp_chr_read(QIOChannel *chan, GIOCondition cond, void *opaque)
{
Chardev *chr = CHARDEV(opaque);
UdpChardev *s = UDP_CHARDEV(opaque);
ssize_t ret;
if (s->max_size == 0) {
return TRUE;
}
ret = qio_channel_read(
s->ioc, (char *)s->buf, sizeof(s->buf), NULL);
if (ret <= 0) {
remove_fd_in_watch(chr);
return FALSE;
}
s->bufcnt = ret;
s->bufptr = 0;
while (s->max_size > 0 && s->bufptr < s->bufcnt) {
qemu_chr_be_write(chr, &s->buf[s->bufptr], 1);
s->bufptr++;
s->max_size = qemu_chr_be_can_write(chr);
}
return TRUE;
}
static void udp_chr_update_read_handler(Chardev *chr,
GMainContext *context)
{
UdpChardev *s = UDP_CHARDEV(chr);
remove_fd_in_watch(chr);
if (s->ioc) {
chr->fd_in_tag = io_add_watch_poll(chr, s->ioc,
udp_chr_read_poll,
udp_chr_read, chr,
context);
}
}
static void char_udp_finalize(Object *obj)
{
Chardev *chr = CHARDEV(obj);
UdpChardev *s = UDP_CHARDEV(obj);
remove_fd_in_watch(chr);
if (s->ioc) {
object_unref(OBJECT(s->ioc));
}
qemu_chr_be_event(chr, CHR_EVENT_CLOSED);
}
static void qemu_chr_parse_udp(QemuOpts *opts, ChardevBackend *backend,
Error **errp)
{
const char *host = qemu_opt_get(opts, "host");
const char *port = qemu_opt_get(opts, "port");
const char *localaddr = qemu_opt_get(opts, "localaddr");
const char *localport = qemu_opt_get(opts, "localport");
bool has_local = false;
SocketAddress *addr;
ChardevUdp *udp;
backend->type = CHARDEV_BACKEND_KIND_UDP;
if (host == NULL || strlen(host) == 0) {
host = "localhost";
}
if (port == NULL || strlen(port) == 0) {
error_setg(errp, "chardev: udp: remote port not specified");
return;
}
if (localport == NULL || strlen(localport) == 0) {
localport = "0";
} else {
has_local = true;
}
if (localaddr == NULL || strlen(localaddr) == 0) {
localaddr = "";
} else {
has_local = true;
}
udp = backend->u.udp.data = g_new0(ChardevUdp, 1);
qemu_chr_parse_common(opts, qapi_ChardevUdp_base(udp));
addr = g_new0(SocketAddress, 1);
addr->type = SOCKET_ADDRESS_KIND_INET;
addr->u.inet.data = g_new(InetSocketAddress, 1);
*addr->u.inet.data = (InetSocketAddress) {
.host = g_strdup(host),
.port = g_strdup(port),
.has_ipv4 = qemu_opt_get(opts, "ipv4"),
.ipv4 = qemu_opt_get_bool(opts, "ipv4", 0),
.has_ipv6 = qemu_opt_get(opts, "ipv6"),
.ipv6 = qemu_opt_get_bool(opts, "ipv6", 0),
};
udp->remote = addr;
if (has_local) {
udp->has_local = true;
addr = g_new0(SocketAddress, 1);
addr->type = SOCKET_ADDRESS_KIND_INET;
addr->u.inet.data = g_new(InetSocketAddress, 1);
*addr->u.inet.data = (InetSocketAddress) {
.host = g_strdup(localaddr),
.port = g_strdup(localport),
};
udp->local = addr;
}
}
static void qmp_chardev_open_udp(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
ChardevUdp *udp = backend->u.udp.data;
QIOChannelSocket *sioc = qio_channel_socket_new();
char *name;
UdpChardev *s = UDP_CHARDEV(chr);
if (qio_channel_socket_dgram_sync(sioc,
udp->local, udp->remote,
errp) < 0) {
object_unref(OBJECT(sioc));
return;
}
name = g_strdup_printf("chardev-udp-%s", chr->label);
qio_channel_set_name(QIO_CHANNEL(sioc), name);
g_free(name);
s->ioc = QIO_CHANNEL(sioc);
/* be isn't opened until we get a connection */
*be_opened = false;
}
static void char_udp_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->parse = qemu_chr_parse_udp;
cc->open = qmp_chardev_open_udp;
cc->chr_write = udp_chr_write;
cc->chr_update_read_handler = udp_chr_update_read_handler;
}
static const TypeInfo char_udp_type_info = {
.name = TYPE_CHARDEV_UDP,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(UdpChardev),
.instance_finalize = char_udp_finalize,
.class_init = char_udp_class_init,
};
static void register_types(void)
{
type_register_static(&char_udp_type_info);
}
type_init(register_types);

View File

@@ -1,266 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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/osdep.h"
#include "qapi/error.h"
#include "char-win.h"
#include "char-win-stdio.h"
typedef struct {
Chardev parent;
HANDLE hStdIn;
HANDLE hInputReadyEvent;
HANDLE hInputDoneEvent;
HANDLE hInputThread;
uint8_t win_stdio_buf;
} WinStdioChardev;
#define WIN_STDIO_CHARDEV(obj) \
OBJECT_CHECK(WinStdioChardev, (obj), TYPE_CHARDEV_WIN_STDIO)
static void win_stdio_wait_func(void *opaque)
{
Chardev *chr = CHARDEV(opaque);
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(opaque);
INPUT_RECORD buf[4];
int ret;
DWORD dwSize;
int i;
ret = ReadConsoleInput(stdio->hStdIn, buf, ARRAY_SIZE(buf), &dwSize);
if (!ret) {
/* Avoid error storm */
qemu_del_wait_object(stdio->hStdIn, NULL, NULL);
return;
}
for (i = 0; i < dwSize; i++) {
KEY_EVENT_RECORD *kev = &buf[i].Event.KeyEvent;
if (buf[i].EventType == KEY_EVENT && kev->bKeyDown) {
int j;
if (kev->uChar.AsciiChar != 0) {
for (j = 0; j < kev->wRepeatCount; j++) {
if (qemu_chr_be_can_write(chr)) {
uint8_t c = kev->uChar.AsciiChar;
qemu_chr_be_write(chr, &c, 1);
}
}
}
}
}
}
static DWORD WINAPI win_stdio_thread(LPVOID param)
{
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(param);
int ret;
DWORD dwSize;
while (1) {
/* Wait for one byte */
ret = ReadFile(stdio->hStdIn, &stdio->win_stdio_buf, 1, &dwSize, NULL);
/* Exit in case of error, continue if nothing read */
if (!ret) {
break;
}
if (!dwSize) {
continue;
}
/* Some terminal emulator returns \r\n for Enter, just pass \n */
if (stdio->win_stdio_buf == '\r') {
continue;
}
/* Signal the main thread and wait until the byte was eaten */
if (!SetEvent(stdio->hInputReadyEvent)) {
break;
}
if (WaitForSingleObject(stdio->hInputDoneEvent, INFINITE)
!= WAIT_OBJECT_0) {
break;
}
}
qemu_del_wait_object(stdio->hInputReadyEvent, NULL, NULL);
return 0;
}
static void win_stdio_thread_wait_func(void *opaque)
{
Chardev *chr = CHARDEV(opaque);
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(opaque);
if (qemu_chr_be_can_write(chr)) {
qemu_chr_be_write(chr, &stdio->win_stdio_buf, 1);
}
SetEvent(stdio->hInputDoneEvent);
}
static void qemu_chr_set_echo_win_stdio(Chardev *chr, bool echo)
{
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(chr);
DWORD dwMode = 0;
GetConsoleMode(stdio->hStdIn, &dwMode);
if (echo) {
SetConsoleMode(stdio->hStdIn, dwMode | ENABLE_ECHO_INPUT);
} else {
SetConsoleMode(stdio->hStdIn, dwMode & ~ENABLE_ECHO_INPUT);
}
}
static void qemu_chr_open_stdio(Chardev *chr,
ChardevBackend *backend,
bool *be_opened,
Error **errp)
{
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(chr);
DWORD dwMode;
int is_console = 0;
stdio->hStdIn = GetStdHandle(STD_INPUT_HANDLE);
if (stdio->hStdIn == INVALID_HANDLE_VALUE) {
error_setg(errp, "cannot open stdio: invalid handle");
return;
}
is_console = GetConsoleMode(stdio->hStdIn, &dwMode) != 0;
if (is_console) {
if (qemu_add_wait_object(stdio->hStdIn,
win_stdio_wait_func, chr)) {
error_setg(errp, "qemu_add_wait_object: failed");
goto err1;
}
} else {
DWORD dwId;
stdio->hInputReadyEvent = CreateEvent(NULL, FALSE, FALSE, NULL);
stdio->hInputDoneEvent = CreateEvent(NULL, FALSE, FALSE, NULL);
if (stdio->hInputReadyEvent == INVALID_HANDLE_VALUE
|| stdio->hInputDoneEvent == INVALID_HANDLE_VALUE) {
error_setg(errp, "cannot create event");
goto err2;
}
if (qemu_add_wait_object(stdio->hInputReadyEvent,
win_stdio_thread_wait_func, chr)) {
error_setg(errp, "qemu_add_wait_object: failed");
goto err2;
}
stdio->hInputThread = CreateThread(NULL, 0, win_stdio_thread,
chr, 0, &dwId);
if (stdio->hInputThread == INVALID_HANDLE_VALUE) {
error_setg(errp, "cannot create stdio thread");
goto err3;
}
}
dwMode |= ENABLE_LINE_INPUT;
if (is_console) {
/* set the terminal in raw mode */
/* ENABLE_QUICK_EDIT_MODE | ENABLE_EXTENDED_FLAGS */
dwMode |= ENABLE_PROCESSED_INPUT;
}
SetConsoleMode(stdio->hStdIn, dwMode);
qemu_chr_set_echo_win_stdio(chr, false);
return;
err3:
qemu_del_wait_object(stdio->hInputReadyEvent, NULL, NULL);
err2:
CloseHandle(stdio->hInputReadyEvent);
CloseHandle(stdio->hInputDoneEvent);
err1:
qemu_del_wait_object(stdio->hStdIn, NULL, NULL);
}
static void char_win_stdio_finalize(Object *obj)
{
WinStdioChardev *stdio = WIN_STDIO_CHARDEV(obj);
if (stdio->hInputReadyEvent != INVALID_HANDLE_VALUE) {
CloseHandle(stdio->hInputReadyEvent);
}
if (stdio->hInputDoneEvent != INVALID_HANDLE_VALUE) {
CloseHandle(stdio->hInputDoneEvent);
}
if (stdio->hInputThread != INVALID_HANDLE_VALUE) {
TerminateThread(stdio->hInputThread, 0);
}
}
static int win_stdio_write(Chardev *chr, const uint8_t *buf, int len)
{
HANDLE hStdOut = GetStdHandle(STD_OUTPUT_HANDLE);
DWORD dwSize;
int len1;
len1 = len;
while (len1 > 0) {
if (!WriteFile(hStdOut, buf, len1, &dwSize, NULL)) {
break;
}
buf += dwSize;
len1 -= dwSize;
}
return len - len1;
}
static void char_win_stdio_class_init(ObjectClass *oc, void *data)
{
ChardevClass *cc = CHARDEV_CLASS(oc);
cc->open = qemu_chr_open_stdio;
cc->chr_write = win_stdio_write;
cc->chr_set_echo = qemu_chr_set_echo_win_stdio;
}
static const TypeInfo char_win_stdio_type_info = {
.name = TYPE_CHARDEV_WIN_STDIO,
.parent = TYPE_CHARDEV,
.instance_size = sizeof(WinStdioChardev),
.instance_finalize = char_win_stdio_finalize,
.class_init = char_win_stdio_class_init,
.abstract = true,
};
static void register_types(void)
{
type_register_static(&char_win_stdio_type_info);
}
type_init(register_types);

View File

@@ -1,29 +0,0 @@
/*
* QEMU System Emulator
*
* Copyright (c) 2003-2008 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.
*/
#ifndef CHAR_WIN_STDIO_H
#define CHAR_WIN_STDIO_H
#define TYPE_CHARDEV_WIN_STDIO "chardev-win-stdio"
#endif /* CHAR_WIN_STDIO_H */

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