Most list head structs need not be given a name. In most cases the
name is given just in case one is going to use QTAILQ_LAST, QTAILQ_PREV
or reverse iteration, but this does not apply to lists of other kinds,
and even for QTAILQ in practice this is only rarely needed. In addition,
we will soon reimplement those macros completely so that they do not
need a name for the head struct. So clean up everything, not giving a
name except in the rare case where it is necessary.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
When issuing the qmp/hmp 'system_wakeup' command, what happens in a
nutshell is:
- qmp_system_wakeup_request set runstate to RUNNING, sets a wakeup_reason
and notify the event
- in the main_loop, all vcpus are paused, a system reset is issued, all
subscribers of wakeup_notifiers receives a notification, vcpus are then
resumed and the wake up QAPI event is fired
Note that this procedure alone doesn't ensure that the guest will awake
from SUSPENDED state - the subscribers of the wake up event must take
action to resume the guest, otherwise the guest will simply reboot. At
this moment, only the ACPI machines via acpi_pm1_cnt_init and xen_hvm_init
have wake-up from suspend support.
However, only the presence of 'system_wakeup' is required for QGA to
support 'guest-suspend-ram' and 'guest-suspend-hybrid' at this moment.
This means that the user/management will expect to suspend the guest using
one of those suspend commands and then resume execution using system_wakeup,
regardless of the support offered in system_wakeup in the first place.
This patch creates a new API called query-current-machine [1], that holds
a new flag called 'wakeup-suspend-support' that indicates if the guest
supports wake up from suspend via system_wakeup. The machine is considered
to implement wake-up support if a call to a new 'qemu_register_wakeup_support'
is made during its init, as it is now being done inside acpi_pm1_cnt_init
and xen_hvm_init. This allows for any other machine type to declare wake-up
support regardless of ACPI state or wakeup_notifiers subscription, making easier
for newer implementations that might have their own mechanisms in the future.
This is the expected output of query-current-machine when running a x86
guest:
{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": true}}
Running the same x86 guest, but with the --no-acpi option:
{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": false}}
This is the output when running a pseries guest:
{"execute" : "query-current-machine"}
{"return": {"wakeup-suspend-support": false}}
With this extra tool, management can avoid situations where a guest
that does not have proper suspend/wake capabilities ends up in
inconsistent state (e.g.
https://github.com/open-power-host-os/qemu/issues/31).
[1] the decision of creating the query-current-machine API is based
on discussions in the QEMU mailing list where it was decided that
query-target wasn't a proper place to store the wake-up flag, neither
was query-machines because this isn't a static property of the
machine object. This new API can then be used to store other
dynamic machine properties that are scattered around the code
ATM. More info at:
https://lists.gnu.org/archive/html/qemu-devel/2018-05/msg04235.html
Reported-by: Balamuruhan S <bala24@linux.vnet.ibm.com>
Signed-off-by: Daniel Henrique Barboza <danielhb413@gmail.com>
Message-Id: <20181205194701.17836-2-danielhb413@gmail.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
It eases code review, unit is explicit.
Patch generated using:
$ git grep -E '(1024|2048|4096|8192|(<<|>>).?(10|20|30))' hw/ include/hw/
and modified manually.
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Alan Robinson <Alan.Robinson@ts.fujitsu.com>
Message-Id: <20180625124238.25339-12-f4bug@amsat.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Remove those unneeded includes to speed up the compilation
process a little bit.
Code change produced with:
$ git grep '#include "sysemu/blockdev.h"' | \
cut -d: -f-1 | \
xargs egrep -L "(BlockInterfaceType|DriveInfo|drive_get|blk_legacy_dinfo|blockdev_mark_auto_del)" | \
xargs sed -i.bak '/#include "sysemu\/blockdev.h"/d'
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Message-Id: <20180528232719.4721-15-f4bug@amsat.org>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch removes the current hackery where IOREQ_TYPE_PCI_CONFIG
requests are handled by faking PIO to 0xcf8 and 0xcfc and replaces it
with direct calls to pci_host_config_read/write_common().
Doing so necessitates mapping BDFs to PCIDevices but maintaining a simple
QLIST in xen_device_realize/unrealize() will suffice.
NOTE: whilst config space accesses are currently limited to
PCI_CONFIG_SPACE_SIZE, this patch paves the way to increasing the
limit to PCIE_CONFIG_SPACE_SIZE when Xen gains the ability to
emulate MCFG table accesses.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Xen 4.11 has a new API to directly map guest resources. Among the resources
that can be mapped using this API are ioreq pages.
This patch modifies QEMU to attempt to use the new API should it exist,
falling back to the previous mechanism if it is unavailable.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
When global_log_dirty is enabled VRAM modification tracking never
worked correctly. The address that is passed to xen_hvm_modified_memory()
is not the effective PFN but RAM block address which is not the same
for VRAM.
We need to make a translation for this address into PFN using
physmap. Since there is no way to access physmap properly inside
xen_hvm_modified_memory() let's make it a global structure.
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
The code is sufficiently substantial that it improves code readability
to put it in a new function called by xen_hvm_init() rather than having
it inline.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Anthony Perard <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
This should help to avoid problems with accessing the device after
migration/resume without PV drivers by migrating its PCI configuration
space state. Without an explicitly defined state record it resets
every time a VM migrates which confuses the OS and makes every
access to xen-pvdevice MMIO region to fail. PV tools enable some
logic to save and restore PCI configuration state from within the VM
every time it migrates which basically hides the issue.
Older systems will acquire the new record when migrated which should
not change their state for worse.
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Xen unstable (to be in 4.11) has two new dmops, relocate_memory and
pin_memory_cacheattr. Use these to set up the VGA memory, replacing the
previous calls to libxc. This allows the VGA console to work properly
when QEMU is running restricted (-xen-domid-restrict).
Wrapper functions are provided to allow QEMU to work with older versions
of Xen.
Tweak the error handling while making this change:
* Report pin_memory_cacheattr errors.
* Report errors even when DEBUG_HVM is not set. This is useful for
trying to understand why VGA is not working, since otherwise it just
fails silently.
* Fix the return values when an error occurs. The functions now
consistently return -1 and set errno.
CC: Ian Jackson <ian.jackson@eu.citrix.com>
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Reviewed-by: Ian Jackson <ian.jackson@eu.citrix.com>
Signed-off-by: Ian Jackson <ian.jackson@eu.citrix.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
xc_interface_open etc. is not going to work if we have dropped
privilege, but xendevicemodel_shutdown will if everything is new
enough.
xendevicemodel_shutdown is only availabe in Xen 4.10 and later, so
provide a stub for earlier versions.
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
We are going to want to reuse this.
No functional change.
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Acked-by: Stefano Stabellini <sstabellini@kernel.org>
We need to restrict *all* the control fds that qemu opens. Looking in
/proc/PID/fd shows there are many; their allocation seems scattered
throughout Xen support code in qemu.
We must postpone the restrict call until roughly the same time as qemu
changes its uid, chroots (if applicable), and so on.
There doesn't seem to be an appropriate hook already. The RunState
change hook fires at different times depending on exactly what mode
qemu is operating in.
And it appears that no-one but the Xen code wants a hook at this phase
of execution. So, introduce a bare call to a new function
xen_setup_post, just before os_setup_post. Also provide the
appropriate stub for when Xen compilation is disabled.
We do the restriction before rather than after os_setup_post, because
xen_restrict may need to open /dev/null, and os_setup_post might have
called chroot.
Currently this does not work with migration, because when running as
the Xen device model qemu needs to signal to the toolstack that it is
ready. It currently does this using xenstore, and for incoming
migration (but not for ordinary startup) that happens after
os_setup_post.
It is correct that this happens late: we want the incoming migration
stream to be processed by a restricted qemu. The fix for this will be
to do the startup notification a different way, without using
xenstore. (QMP is probably a reasonable choice.)
So for now this restriction feature cannot be used in conjunction with
migration. (Note that this is not a regression in this patch, because
previously the -xen-restrict-domid call was, in fact, simply
ineffective!) We will revisit this in the Xen 4.11 release cycle.
Signed-off-by: Ian Jackson <Ian.Jackson@eu.citrix.com>
CC: Paolo Bonzini <pbonzini@redhat.com> (maintainer:X86)
CC: Richard Henderson <rth@twiddle.net> (maintainer:X86)
CC: Eduardo Habkost <ehabkost@redhat.com> (maintainer:X86)
CC: Michael S. Tsirkin <mst@redhat.com> (supporter:PC)
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
The previous commit improved compile time by including less of the
generated QAPI headers. This is impossible for stuff defined directly
in qapi-schema.json, because that ends up in headers that that pull in
everything.
Move everything but include directives from qapi-schema.json to new
sub-module qapi/misc.json, then include just the "misc" shard where
possible.
It's possible everywhere, except:
* monitor.c needs qmp-command.h to get qmp_init_marshal()
* monitor.c, ui/vnc.c and the generated qapi-event-FOO.c need
qapi-event.h to get enum QAPIEvent
Perhaps we'll get rid of those some other day.
Adding a type to qapi/migration.json now recompiles some 120 instead
of 2300 out of 5100 objects.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20180211093607.27351-25-armbru@redhat.com>
[eblake: rebase to master]
Signed-off-by: Eric Blake <eblake@redhat.com>
This cleanup makes the number of objects depending on qapi/error.h
drop from 1910 (out of 4743) to 1612 in my "build everything" tree.
While there, separate #include from file comment with a blank line,
and drop a useless comment on why qemu/osdep.h is included first.
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20180201111846.21846-5-armbru@redhat.com>
[Semantic conflict with commit 34e304e975 resolved, OSX breakage fixed]
Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
The bus pointer in PCIDevice is basically redundant with QOM information.
It's always initialized to the qdev_get_parent_bus(), the only difference
is the type.
Therefore this patch eliminates the field, instead creating a pci_get_bus()
helper to do the type mangling to derive it conveniently from the QOM
Device object underneath.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
xen_modified_memory() sets errno to communicate what went wrong so log
this rather than the return value which is not interesting.
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Add INTERFACE_CONVENTIONAL_PCI_DEVICE to all direct subtypes of
TYPE_PCI_DEVICE, except:
1) The ones that already have INTERFACE_PCIE_DEVICE set:
* base-xhci
* e1000e
* nvme
* pvscsi
* vfio-pci
* virtio-pci
* vmxnet3
2) base-pci-bridge
Not all PCI bridges are Conventional PCI devices, so
INTERFACE_CONVENTIONAL_PCI_DEVICE is added only to the subtypes
that are actually Conventional PCI:
* dec-21154-p2p-bridge
* i82801b11-bridge
* pbm-bridge
* pci-bridge
The direct subtypes of base-pci-bridge not touched by this patch
are:
* xilinx-pcie-root: Already marked as PCIe-only.
* pcie-pci-bridge: Already marked as PCIe-only.
* pcie-port: all non-abstract subtypes of pcie-port are already
marked as PCIe-only devices.
3) megasas-base
Not all megasas devices are Conventional PCI devices, so the
interface names are added to the subclasses registered by
megasas_register_types(), according to information in the
megasas_devices[] array.
"megasas-gen2" already implements INTERFACE_PCIE_DEVICE, so add
INTERFACE_CONVENTIONAL_PCI_DEVICE only to "megasas".
Acked-by: Alberto Garcia <berto@igalia.com>
Acked-by: John Snow <jsnow@redhat.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tidy up some of the warn_report() messages after having converted them
to use warn_report().
Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <9cb1d23551898c9c9a5f84da6773e99871285120.1505158760.git.alistair.francis@xilinx.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Convert all the multi-line uses of fprintf(stderr, "warning:"..."\n"...
to use warn_report() instead. This helps standardise on a single
method of printing warnings to the user.
All of the warnings were changed using these commands:
find ./* -type f -exec sed -i \
'N; {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N; {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N;N; {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N;N;N {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N;N;N;N {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N;N;N;N;N {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
find ./* -type f -exec sed -i \
'N;N;N;N;N;N;N; {s|fprintf(.*".*warning[,:] \(.*\)\\n"\(.*\));|warn_report("\1"\2);|Ig}' \
{} +
Indentation fixed up manually afterwards.
Some of the lines were manually edited to reduce the line length to below
80 charecters. Some of the lines with newlines in the middle of the
string were also manually edit to avoid checkpatch errrors.
The #include lines were manually updated to allow the code to compile.
Several of the warning messages can be improved after this patch, to
keep this patch mechanical this has been moved into a later patch.
Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Max Reitz <mreitz@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Anthony Perard <anthony.perard@citrix.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Yongbok Kim <yongbok.kim@imgtec.com>
Cc: Cornelia Huck <cohuck@redhat.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Jason Wang <jasowang@redhat.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <5def63849ca8f551630c6f2b45bcb1c482f765a6.1505158760.git.alistair.francis@xilinx.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The only exception are groups of numers separated by symbols
'.', ' ', ':', '/', like 'ab.09.7d'.
This patch is made by the following:
> find . -name trace-events | xargs python script.py
where script.py is the following python script:
=========================
#!/usr/bin/env python
import sys
import re
import fileinput
rhex = '%[-+ *.0-9]*(?:[hljztL]|ll|hh)?(?:x|X|"\s*PRI[xX][^"]*"?)'
rgroup = re.compile('((?:' + rhex + '[.:/ ])+' + rhex + ')')
rbad = re.compile('(?<!0x)' + rhex)
files = sys.argv[1:]
for fname in files:
for line in fileinput.input(fname, inplace=True):
arr = re.split(rgroup, line)
for i in range(0, len(arr), 2):
arr[i] = re.sub(rbad, '0x\g<0>', arr[i])
sys.stdout.write(''.join(arr))
=========================
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Message-id: 20170731160135.12101-5-vsementsov@virtuozzo.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
In trace format '#' flag of printf is forbidden. Fix it to '0x%'.
This patch is created by the following:
check that we have a problem
> find . -name trace-events | xargs grep '%#' | wc -l
56
check that there are no cases with additional printf flags before '#'
> find . -name trace-events | xargs grep "%[-+ 0'I]+#" | wc -l
0
check that there are no wrong usage of '#' and '0x' together
> find . -name trace-events | xargs grep '0x%#' | wc -l
0
fix the problem
> find . -name trace-events | xargs sed -i 's/%#/0x%/g'
[Eric Blake noted that xargs grep '%[-+ 0'I]+#' should be xargs grep
"%[-+ 0'I]+#" instead so the shell quoting is correct.
--Stefan]
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-id: 20170731160135.12101-3-vsementsov@virtuozzo.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Under certain circumstances normal xen-mapcache functioning may be broken
by guest's actions. This may lead to either QEMU performing exit() due to
a caught bad pointer (and with QEMU process gone the guest domain simply
appears hung afterwards) or actual use of the incorrect pointer inside
QEMU address space -- a write to unmapped memory is possible. The bug is
hard to reproduce on a i440 machine as multiple DMA sources are required
(though it's possible in theory, using multiple emulated devices), but can
be reproduced somewhat easily on a Q35 machine using an emulated AHCI
controller -- each NCQ queue command slot may be used as an independent
DMA source ex. using READ FPDMA QUEUED command, so a single storage
device on the AHCI controller port will be enough to produce multiple DMAs
(up to 32). The detailed description of the issue follows.
Xen-mapcache provides an ability to map parts of a guest memory into
QEMU's own address space to work with.
There are two types of cache lookups:
- translating a guest physical address into a pointer in QEMU's address
space, mapping a part of guest domain memory if necessary (while trying
to reduce a number of such (re)mappings to a minimum)
- translating a QEMU's pointer back to its physical address in guest RAM
These lookups are managed via two linked-lists of structures.
MapCacheEntry is used for forward cache lookups, while MapCacheRev -- for
reverse lookups.
Every guest physical address is broken down into 2 parts:
address_index = phys_addr >> MCACHE_BUCKET_SHIFT;
address_offset = phys_addr & (MCACHE_BUCKET_SIZE - 1);
MCACHE_BUCKET_SHIFT depends on a system (32/64) and is equal to 20 for
a 64-bit system (which assumed for the further description). Basically,
this means that we deal with 1 MB chunks and offsets within those 1 MB
chunks. All mappings are created with 1MB-granularity, i.e. 1MB/2MB/3MB
etc. Most DMA transfers typically are less than 1MB, however, if the
transfer crosses any 1MB border(s) - than a nearest larger mapping size
will be used, so ex. a 512-byte DMA transfer with the start address
700FFF80h will actually require a 2MB range.
Current implementation assumes that MapCacheEntries are unique for a given
address_index and size pair and that a single MapCacheEntry may be reused
by multiple requests -- in this case the 'lock' field will be larger than
1. On other hand, each requested guest physical address (with 'lock' flag)
is described by each own MapCacheRev. So there may be multiple MapCacheRev
entries corresponding to a single MapCacheEntry. The xen-mapcache code
uses MapCacheRev entries to retrieve the address_index & size pair which
in turn used to find a related MapCacheEntry. The 'lock' field within
a MapCacheEntry structure is actually a reference counter which shows
a number of corresponding MapCacheRev entries.
The bug lies in ability for the guest to indirectly manipulate with the
xen-mapcache MapCacheEntries list via a special sequence of DMA
operations, typically for storage devices. In order to trigger the bug,
guest needs to issue DMA operations in specific order and timing.
Although xen-mapcache is protected by the mutex lock -- this doesn't help
in this case, as the bug is not due to a race condition.
Suppose we have 3 DMA transfers, namely A, B and C, where
- transfer A crosses 1MB border and thus uses a 2MB mapping
- transfers B and C are normal transfers within 1MB range
- and all 3 transfers belong to the same address_index
In this case, if all these transfers are to be executed one-by-one
(without overlaps), no special treatment necessary -- each transfer's
mapping lock will be set and then cleared on unmap before starting
the next transfer.
The situation changes when DMA transfers overlap in time, ex. like this:
|===== transfer A (2MB) =====|
|===== transfer B (1MB) =====|
|===== transfer C (1MB) =====|
time --->
In this situation the following sequence of actions happens:
1. transfer A creates a mapping to 2MB area (lock=1)
2. transfer B (1MB) tries to find available mapping but cannot find one
because transfer A is still in progress, and it has 2MB size + non-zero
lock. So transfer B creates another mapping -- same address_index,
but 1MB size.
3. transfer A completes, making 1st mapping entry available by setting its
lock to 0
4. transfer C starts and tries to find available mapping entry and sees
that 1st entry has lock=0, so it uses this entry but remaps the mapping
to a 1MB size
5. transfer B completes and by this time
- there are two locked entries in the MapCacheEntry list with the SAME
values for both address_index and size
- the entry for transfer B actually resides farther in list while
transfer C's entry is first
6. xen_ram_addr_from_mapcache() for transfer B gets correct address_index
and size pair from corresponding MapCacheRev entry, but then it starts
looking for MapCacheEntry with these values and finds the first entry
-- which belongs to transfer C.
At this point there may be following possible (bad) consequences:
1. xen_ram_addr_from_mapcache() will use a wrong entry->vaddr_base value
in this statement:
raddr = (reventry->paddr_index << MCACHE_BUCKET_SHIFT) +
((unsigned long) ptr - (unsigned long) entry->vaddr_base);
resulting in an incorrent raddr value returned from the function. The
(ptr - entry->vaddr_base) expression may produce both positive and negative
numbers and its actual value may differ greatly as there are many
map/unmap operations take place. If the value will be beyond guest RAM
limits then a "Bad RAM offset" error will be triggered and logged,
followed by exit() in QEMU.
2. If raddr value won't exceed guest RAM boundaries, the same sequence
of actions will be performed for xen_invalidate_map_cache_entry() on DMA
unmap, resulting in a wrong MapCacheEntry being unmapped while DMA
operation which uses it is still active. The above example must
be extended by one more DMA transfer in order to allow unmapping as the
first mapping in the list is sort of resident.
The patch modifies the behavior in which MapCacheEntry's are added to the
list, avoiding duplicates.
Signed-off-by: Alexey Gerasimenko <x1917x@gmail.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
If we have a system with xenforeignmemory_map2() implemented
we don't need to save/restore physmap on suspend/restore
anymore. In case we resume a VM without physmap - try to
recreate the physmap during memory region restore phase and
remap map cache entries accordingly. The old code is left
for compatibility reasons.
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
This new call is trying to update a requested map cache entry
according to the changes in the physmap. The call is searching
for the entry, unmaps it and maps again at the same place using
a new guest address. If the mapping is dummy this call will
make it real.
This function makes use of a new xenforeignmemory_map2() call
with an extended interface that was recently introduced in
libxenforeignmemory [1].
[1] https://www.mail-archive.com/xen-devel@lists.xen.org/msg113007.html
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Dummys are simple anonymous mappings that are placed instead
of regular foreign mappings in certain situations when we need
to postpone the actual mapping but still have to give a
memory region to QEMU to play with.
This is planned to be used for restore on Xen.
Signed-off-by: Igor Druzhinin <igor.druzhinin@citrix.com>
Reviewed-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Commit 090fa1c8 "add support for unplugging NVMe disks..." extended the
existing disk unplug flag to cover NVMe disks as well as IDE and SCSI.
The recent thread on the xen-devel mailing list [1] has highlighted that
this is not desirable behaviour: PV frontends should be able to distinguish
NVMe disks from other types of disk and should have separate control over
whether they are unplugged.
This patch defines a new bit in the unplug mask for this purpose (see Xen
commit [2]) and also tidies up the definitions of, and improves the
comments regarding, the previously exiting bits in the protocol.
[1] https://lists.xen.org/archives/html/xen-devel/2017-03/msg02924.html
[2] http://xenbits.xen.org/gitweb/?p=xen.git;a=commit;h=1096aa02
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Use the new functions memory_region_init_{ram,rom,rom_device}()
instead of manually calling the _nomigrate() version and then
vmstate_register_ram_global().
Patch automatically created using coccinelle script:
spatch --in-place -sp_file scripts/coccinelle/memory-region-init-ram.cocci -dir hw
(As it turns out, there are no instances of the rom and
rom_device functions that are caught by this script.)
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1499438577-7674-8-git-send-email-peter.maydell@linaro.org
Rename memory_region_init_ram() to memory_region_init_ram_nomigrate().
This leaves the way clear for us to provide a memory_region_init_ram()
which does handle migration.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-id: 1499438577-7674-4-git-send-email-peter.maydell@linaro.org
When the guest unplugs the emulated NICs, cleanup the peer for each NIC
as it is not needed anymore. Most importantly, this allows the tap
interfaces which QEMU holds open to be closed and removed.
Signed-off-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Those are apparently unnecessary includes.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Time to wire up all the call sites that request a shutdown or
reset to use the enum added in the previous patch.
It would have been less churn to keep the common case with no
arguments as meaning guest-triggered, and only modified the
host-triggered code paths, via a wrapper function, but then we'd
still have to audit that I didn't miss any host-triggered spots;
changing the signature forces us to double-check that I correctly
categorized all callers.
Since command line options can change whether a guest reset request
causes an actual reset vs. a shutdown, it's easy to also add the
information to reset requests.
Signed-off-by: Eric Blake <eblake@redhat.com>
Acked-by: David Gibson <david@gibson.dropbear.id.au> [ppc parts]
Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> [SPARC part]
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com> [s390x parts]
Message-Id: <20170515214114.15442-5-eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
We want to track why a guest was shutdown; in particular, being able
to tell the difference between a guest request (such as ACPI request)
and host request (such as SIGINT) will prove useful to libvirt.
Since all requests eventually end up changing shutdown_requested in
vl.c, the logical change is to make that value track the reason,
rather than its current 0/1 contents.
Since command-line options control whether a reset request is turned
into a shutdown request instead, the same treatment is given to
reset_requested.
This patch adds an internal enum ShutdownCause that describes reasons
that a shutdown can be requested, and changes qemu_system_reset() to
pass the reason through, although for now nothing is actually changed
with regards to what gets reported. The enum could be exported via
QAPI at a later date, if deemed necessary, but for now, there has not
been a request to expose that much detail to end clients.
For the most part, we turn 0 into SHUTDOWN_CAUSE_NONE, and 1 into
SHUTDOWN_CAUSE_HOST_ERROR; the only specific case where we have enough
information right now to use a different value is when we are reacting
to a host signal. It will take a further patch to edit all call-sites
that can trigger a reset or shutdown request to properly pass in any
other reasons; this patch includes TODOs to point such places out.
qemu_system_reset() trades its 'bool report' parameter for a
'ShutdownCause reason', with all non-zero values having the same
effect; this lets us get rid of the weird #defines for VMRESET_*
as synonyms for bools.
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-Id: <20170515214114.15442-3-eblake@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
The Xen mapcache is able to create long term mappings, they are called
"locked" mappings. The third parameter of the xen_map_cache call
specifies if a mapping is a "locked" mapping.
>From the QEMU point of view there are two kinds of long term mappings:
[a] device memory mappings, such as option roms and video memory
[b] dma mappings, created by dma_memory_map & friends
After certain operations, ballooning a VM in particular, Xen asks QEMU
kindly to destroy all mappings. However, certainly [a] mappings are
present and cannot be removed. That's not a problem as they are not
affected by balloonning. The *real* problem is that if there are any
mappings of type [b], any outstanding dma operations could fail. This is
a known shortcoming. In other words, when Xen asks QEMU to destroy all
mappings, it is an error if any [b] mappings exist.
However today we have no way of distinguishing [a] from [b]. Because of
that, we cannot even print a decent warning.
This patch introduces a new "dma" bool field to MapCacheRev entires, to
remember if a given mapping is for dma or is a long term device memory
mapping. When xen_invalidate_map_cache is called, we print a warning if
any [b] mappings exist. We ignore [a] mappings.
Mappings created by qemu_map_ram_ptr are assumed to be [a], while
mappings created by address_space_map->qemu_ram_ptr_length are assumed
to be [b].
The goal of the patch is to make debugging and system understanding
easier.
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Anthony PERARD <anthony.perard@citrix.com>
This patch creates inline wrapper functions in xen_common.h for all open
coded calls to xc_hvm_XXX() functions outside of xen_common.h so that use
of xen_xc can be made implicit. This again is in preparation for the move
to using libxendevicemodel.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Anthony Perard <anthony.perard@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
The trace-events for a given source file should generally
always live in the same directory as the source file.
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Message-id: 20170125161417.31949-5-berrange@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
The Xen HVM unplug protocol [1] specifies a mechanism to allow guests to
request unplug of 'aux' disks (which is stated to mean all IDE disks,
except the primary master). This patch adds support for that unplug request.
NOTE: The semantics of what happens if unplug of all disks and 'aux' disks
is simultaneously requests is not clear. The patch makes that
assumption that an 'all' request overrides an 'aux' request.
[1] http://xenbits.xen.org/gitweb/?p=xen.git;a=blob;f=docs/misc/hvm-emulated-unplug.markdown
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
----
Cc: Stefano Stabellini <sstabellini@kernel.org>
Cc: Anthony Perard <anthony.perard@citrix.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: John Snow <jsnow@redhat.com>
...not just IDE and SCSI.
This patch allows the Xen tool-stack to fully support of NVMe as an
emulated disk type. See [1] for the relevant tool-stack patch discussion.
[1] https://lists.xen.org/archives/html/xen-devel/2017-01/msg01225.html
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
The current code is poorly structured and potentially leads to multiple
config space reads when one is sufficient. Also the UNPLUG_ALL_IDE_DISKS
flag is mis-named since it also results in SCSI disks being unplugged.
This patch renames the flag and re-structures the code to be more
efficient, and readable.
Signed-off-by: Paul Durrant <paul.durrant@citrix.com>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Implement SUSE specific unplug protocol for emulated PCI devices
in PVonHVM guests. Its a simple 'outl(1, (ioaddr + 4));'.
This protocol was implemented and used since Xen 3.0.4.
It is used in all SUSE/SLES/openSUSE releases up to SLES11SP3 and
openSUSE 12.3.
In addition old (pre-2011) VMDP versions are handled as well.
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Using 'vdev=sd[a-o]' will create an emulated LSI controller, which can
be used by the emulated BIOS to boot from disk. If the HVM domU has also
PV driver the disk may appear twice in the guest. To avoid this an
unplug of the emulated hardware is needed, similar to what is done for
IDE and NIC drivers already.
Since the SCSI controller provides only disks the entire controller can
be unplugged at once.
Impact of the change for classic and pvops based guest kernels:
vdev=sda:disk0
before: pvops: disk0=pv xvda + emulated sda
classic: disk0=pv sda + emulated sdq
after: pvops: disk0=pv xvda
classic: disk0=pv sda
vdev=hda:disk0, vdev=sda:disk1
before: pvops: disk0=pv xvda
disk1=emulated sda
classic: disk0=pv hda
disk1=pv sda + emulated sdq
after: pvops: disk0=pv xvda
disk1=not accessible by blkfront, index hda==index sda
classic: disk0=pv hda
disk1=pv sda
vdev=hda:disk0, vdev=sda:disk1, vdev=sdb:disk2
before: pvops: disk0=pv xvda
disk1=emulated sda
disk2=pv xvdb + emulated sdb
classic: disk0=pv hda
disk1=pv sda + emulated sdq
disk2=pv sdb + emulated sdr
after: pvops: disk0=pv xvda
disk1=not accessible by blkfront, index hda==index sda
disk2=pv xvdb
classic: disk0=pv hda
disk1=pv sda
disk2=pv sda
Signed-off-by: Olaf Hering <olaf@aepfle.de>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
The MMIO based interface to APIC doesn't work well with MSIs that have
upper address bits set (remapped x2APIC MSIs). A specialized interface
is a quick and dirty way to avoid the shortcoming.
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
We can teach Xen to drain and flush each device as it needs to, instead
of trying to flush ALL devices. This removes the last user of
blk_flush_all.
The function is therefore removed under the premise that any new uses
of blk_flush_all would be the wrong paradigm: either flush the single
device that requires flushing, or use an appropriate flush_all mechanism
from outside of the BlkBackend layer.
Signed-off-by: John Snow <jsnow@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Acked-by: Fam Zheng <famz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Commit 57cb38b included qapi/error.h into qemu/osdep.h to get the
Error typedef. Since then, we've moved to include qemu/osdep.h
everywhere. Its file comment explains: "To avoid getting into
possible circular include dependencies, this file should not include
any other QEMU headers, with the exceptions of config-host.h,
compiler.h, os-posix.h and os-win32.h, all of which are doing a
similar job to this file and are under similar constraints."
qapi/error.h doesn't do a similar job, and it doesn't adhere to
similar constraints: it includes qapi-types.h. That's in excess of
100KiB of crap most .c files don't actually need.
Add the typedef to qemu/typedefs.h, and include that instead of
qapi/error.h. Include qapi/error.h in .c files that need it and don't
get it now. Include qapi-types.h in qom/object.h for uint16List.
Update scripts/clean-includes accordingly. Update it further to match
reality: replace config.h by config-target.h, add sysemu/os-posix.h,
sysemu/os-win32.h. Update the list of includes in the qemu/osdep.h
comment quoted above similarly.
This reduces the number of objects depending on qapi/error.h from "all
of them" to less than a third. Unfortunately, the number depending on
qapi-types.h shrinks only a little. More work is needed for that one.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
[Fix compilation without the spice devel packages. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Xen 4.2 become unsupported upstream in 09/2015 (see
http://wiki.xen.org/wiki/Xen_Release_Features). However as far as the
interfaces provided by the toolstack libraries go 4.2 and 4.3 are
indistinguishable.
Therefore drop support for Xen 4.1 and earlier which removes a whole
pile of compatibility code which makes future work (to use stable
library interfaces provided by upstream) more difficult. In particular
all supported versions now use a pointer as a libxc handle (4.1 and
earlier used an integer, resulting in various shim layers).
Also Xen 4.2 was the first version of Xen to formally support upstream
QEMU (as a preview) so that makes sense as a cut-off now.
This change drops all the configure-y and resulting ifdefs in a mostly
mechanical way. A follow up will refactor wrappers which are now
unused.
Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Clean up includes so that osdep.h is included first and headers
which it implies are not included manually.
This commit was created with scripts/clean-includes.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 1453832250-766-11-git-send-email-peter.maydell@linaro.org
Use realize to initialize the xen_platform device
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The xen-platform code crashes on reset if the xen backend is not
initialized, because it calls xc_hvm_set_mem_type(). Ensure xen-platform
won't be created without initializing the xen backend.
The assert can't be triggered by the user because the device is not
hotpluggable, and the only code creating it (at pc_xen_hvm_init())
already checks xen_enabled().
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
A number of files were including assert.h but not using any
of the functions it provides
Signed-off-by: Daniel P. Berrange <berrange@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Device models should access their block backends only through the
block-backend.h API. Convert them, and drop direct includes of
inappropriate headers.
Just four uses of BlockDriverState are left:
* The Xen paravirtual block device backend (xen_disk.c) opens images
itself when set up via xenbus, bypassing blockdev.c. I figure it
should go through qmp_blockdev_add() instead.
* Device model "usb-storage" prompts for keys. No other device model
does, and this one probably shouldn't do it, either.
* ide_issue_trim_cb() uses bdrv_aio_discard() instead of
blk_aio_discard() because it fishes its backend out of a BlockAIOCB,
which has only the BlockDriverState.
* PC87312State has an unused BlockDriverState[] member.
The next two commits take care of the latter two.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Max Reitz <mreitz@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
qemu side patch to support xen HVM direct kernel boot:
if -kernel exists, calls xen_load_linux(), which will read kernel/initrd
and add a linuxboot.bin or multiboot.bin option rom. The
linuxboot.bin/multiboot.bin will load kernel/initrd and jump to execute
kernel directly. It's working when xen uses seabios.
During this work, found the 'kvmvapic' is in option_rom list, it should
not be there in xen case. Set s->vapic_control = 0 in xen_apic_realize()
to handle that.
Signed-off-by: Chunyan Liu <cyliu@suse.com>
Acked-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
After previous Peter patch, they are redundant. This way we don't
assign them except when needed. Once there, there were lots of case
where the ".fields" indentation was wrong:
.fields = (VMStateField []) {
and
.fields = (VMStateField []) {
Change all the combinations to:
.fields = (VMStateField[]){
The biggest problem (appart from aesthetics) was that checkpatch complained
when we copy&pasted the code from one place to another.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Acked-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Paolo Bonzini
Daniel Henrique Barboza
Philippe Mathieu-Daudé
Peter Maydell
Paul Durrant
Igor Druzhinin
Ross Lagerwall
Ian Jackson
Markus Armbruster
Michael S. Tsirkin
Michael McConville
David Gibson
Eduardo Habkost
Alistair Francis
Vladimir Sementsov-Ogievskiy
Alexey G
Stefano Stabellini
Marc-André Lureau
Eric Blake
Anthony Xu
Daniel P. Berrange
Olaf Hering
Radim Krčmář
John Snow
Ian Campbell
Cao jin
Stefano Stabellini
Chunyan Liu
Juan Quintela
Wei Liu