| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
|
|
|
|
| |
On x86 userspace delivers interrupts to the kernel asynchronously
(and therefore VCPU idle management is done in the kernel) if and
only if there is an in-kernel irqchip. On other architectures this
isn't necessarily true (they may always send interrupts
asynchronously), so define a new kvm_async_interrupts_enabled()
function instead of misusing kvm_irqchip_in_kernel().
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The -numa option to qemu is used to create [fake] numa nodes
and expose them to the guest OS instance.
There are a couple of issues with the -numa option:
a) Max VCPU's that can be specified for a guest while using
the qemu's -numa option is 64. Due to a typecasting issue
when the number of VCPUs is > 32 the VCPUs don't show up
under the specified [fake] numa nodes.
b) KVM currently has support for 160VCPUs per guest. The
qemu's -numa option has only support for upto 64VCPUs
per guest.
This patch addresses these two issues.
Below are examples of (a) and (b)
a) >32 VCPUs are specified with the -numa option:
/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
71:01:01 \
-net tap,ifname=tap0,script=no,downscript=no \
-vnc :4
...
Upstream qemu :
--------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9 32 33 34 35 36 37 38 39 40 41
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59
node 2 size: 131072 MB
node 3 cpus: 30
node 3 size: 131072 MB
node 4 cpus:
node 4 size: 131072 MB
node 5 cpus: 31
node 5 size: 131072 MB
With the patch applied :
-----------------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
6 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 131072 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 131072 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 131072 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 131072 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 131072 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 131072 MB
b) >64 VCPUs specified with -numa option:
/usr/local/bin/qemu-system-x86_64 \
-enable-kvm \
-cpu Westmere,+rdtscp,+pdpe1gb,+dca,+pdcm,+xtpr,+tm2,+est,+smx,+vmx,+ds_cpl,+monitor,+dtes64,+pclmuldq,+pbe,+tm,+ht,+ss,+acpi,+d-vnc :4
...
Upstream qemu :
--------------
only 63 CPUs in NUMA mode supported.
only 64 CPUs in NUMA mode supported.
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 6 7 8 9 38 39 40 41 70 71 72 73
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19 42 43 44 45 46 47 48 49 50 51 74 75 76 77 78 79
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29 52 53 54 55 56 57 58 59 60 61
node 2 size: 65536 MB
node 3 cpus: 30 62
node 3 size: 65536 MB
node 4 cpus:
node 4 size: 65536 MB
node 5 cpus:
node 5 size: 65536 MB
node 6 cpus: 31 63
node 6 size: 65536 MB
node 7 cpus: 0 1 2 3 4 5 32 33 34 35 36 37 64 65 66 67 68 69
node 7 size: 65536 MB
With the patch applied :
-----------------------
QEMU 1.1.50 monitor - type 'help' for more information
(qemu) info numa
8 nodes
node 0 cpus: 0 1 2 3 4 5 6 7 8 9
node 0 size: 65536 MB
node 1 cpus: 10 11 12 13 14 15 16 17 18 19
node 1 size: 65536 MB
node 2 cpus: 20 21 22 23 24 25 26 27 28 29
node 2 size: 65536 MB
node 3 cpus: 30 31 32 33 34 35 36 37 38 39
node 3 size: 65536 MB
node 4 cpus: 40 41 42 43 44 45 46 47 48 49
node 4 size: 65536 MB
node 5 cpus: 50 51 52 53 54 55 56 57 58 59
node 5 size: 65536 MB
node 6 cpus: 60 61 62 63 64 65 66 67 68 69
node 6 size: 65536 MB
node 7 cpus: 70 71 72 73 74 75 76 77 78 79
Signed-off-by: Chegu Vinod <chegu_vinod@hp.com>, Jim Hull <jim.hull@hp.com>, Craig Hada <craig.hada@hp.com>
Tested-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
|
|
|
|
|
|
| |
Change field type to bool.
Signed-off-by: Andreas Färber <afaerber@suse.de>
|
|
|
|
| |
Signed-off-by: Andreas Färber <afaerber@suse.de>
|
|
|
|
|
|
|
|
|
|
|
| |
CPU_COMMON_THREAD was only used for Windows, adding an hThread field
to CPU_COMMON.
Move the field into QOM CPUState and change its type to HANDLE,
which it is assigned from. This requires Windows headers, pulled in
through qemu-thread.h.
Signed-off-by: Andreas Färber <afaerber@suse.de>
|
|
|
|
|
|
|
|
|
| |
Commit 946fb27c1 moved all the uses of all_cpu_threads_idle()
into cpus.c. This means we can mark the function 'static'
(again), if we shuffle it a bit earlier in the source file.
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
|
|
|
|
|
|
|
| |
This is now implied by kvm_irqchip_in_kernel.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
This patch combines qtest and -icount together to turn the vm_clock
into a source that can be fully managed by the client. To this end new
commands clock_step and clock_set are added. Hooking them with libqtest
is left as an exercise to the reader.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The idea behind qtest is pretty simple. Instead of executing a CPU via TCG or
KVM, rely on an external process to send events to the device model that the CPU
would normally generate.
qtest presents itself as an accelerator. In addition, a new option is added to
establish a qtest server (-qtest) that takes a character device. This is what
allows the external process to send CPU events to the device model.
qtest uses a simple line based protocol to send the events. Documentation of
that protocol is in qtest.c.
I considered reusing the monitor for this job. Adding interrupts would be a bit
difficult. In addition, logging would also be difficult.
qtest has extensive logging support. All protocol commands are logged with
time stamps using a new command line option (-qtest-log). Logging is important
since ultimately, this is a feature for debugging.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Scripted conversion:
for file in *.[hc] hw/*.[hc] hw/kvm/*.[hc] linux-user/*.[hc] linux-user/m68k/*.[hc] bsd-user/*.[hc] darwin-user/*.[hc] tcg/*/*.[hc] target-*/cpu.h; do
sed -i "s/CPUState/CPUArchState/g" $file
done
All occurrences of CPUArchState are expected to be replaced by QOM CPUState,
once all targets are QOM'ified and common fields have been extracted.
Signed-off-by: Andreas Färber <afaerber@suse.de>
Reviewed-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
| |
In order to perform critical manipulations on the VM state in the
context of a VCPU, specifically code patching, stopping and resuming of
all VCPUs may be necessary. resume_all_vcpus is already compatible, now
enable pause_all_vcpus for this use case by stopping the calling context
before starting to wait for the whole gang.
CC: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
|
|
|
| |
When the TCG thread is started but not yet the machine, we wait in
qemu_tcg_cpu_thread_fn on tcg_halt_cond. To allow run_on_cpu already at
this time, we need to process pending request in that loop.
CC: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
| |
CPUState::next_cpu is already CPUState *.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
|
|
| |
As we have thread-local cpu_single_env now and KVM uses exactly one
thread per VCPU, we can drop the cpu_single_env updates from the loop
and initialize this variable only once during setup.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
On real hardware, NMI button events are injected via the LINT1 line of
the APICs. E.g. kdump expect this wiring and gets upset if the per-APIC
LINT1 mask is not respected, i.e. if NMIs are injected to VCPUs that
should not receive them. Change the APIC emulation code to reflect this.
Based on qemu-kvm patch by Lai Jiangshan.
CC: Lai Jiangshan <laijs@cn.fujitsu.com>
Reported-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
|
|
|
|
|
|
|
|
| |
These two blocks of code are exactly the same, remove one.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
| |
On Windows, cpus.c needs access to the hThread. Add a Windows-specific
function to grab it. This requires changing the CPU threads to
joinable. There is no substantial change because the threads run
in an infinite loop.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|\ |
|
| |
| |
| |
| |
| |
| |
| | |
Double semicolons should be single.
Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Split from Jan's original qemu-thread-posix.c patch. No semantic change,
just introduce the new API that POSIX and Win32 implementations will
conform to.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
| |
| |
| |
| | |
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
| |
| |
| |
| |
| | |
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|/
|
|
|
|
|
| |
Please, note that the QMP command has a new 'cpu-index' parameter.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|\ |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Many places in QEMU call qemu_aio_flush() to complete all pending
asynchronous I/O. Most of these places actually want to drain all block
requests but there is no block layer API to do so.
This patch introduces the bdrv_drain_all() API to wait for requests
across all BlockDriverStates to complete. As a bonus we perform checks
after qemu_aio_wait() to ensure that requests really have finished.
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
|
|/
|
|
|
| |
Signed-off-by: Dong Xu Wang <wdongxu@linux.vnet.ibm.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
| |
We disable vm_clock when pausing all vcpus, but we forget to
reenable it when resuming all vcpus. It will cause that the
guest can not be rebooted.
Tested-by: Zhi Yong Wu <zwu.kernel@gmai.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
| |
After the removal of the non-threaded mode cpu_exec_all is now only used
by TCG. Refactor it accordingly, also dropping its unused return value.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
| |
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|
|
|
|
|
| |
Provide a clean example of how to use the main loop in the tools.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
| |
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
| |
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
| |
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
|
|
|
| |
None of this is needed by tools, and most of it can even be made static
inside cpus.c.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
It should be a matter of allowing the transition POSTMIGRATE ->
FINISH_MIGRATE, but it turns out that the VM won't do the
transition the second time because it's already stopped.
So this commit also adds vm_stop_force_state() which performs
the transition even if the VM is already stopped.
While there also allow other states to migrate.
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|\ |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Now that iothread is always compiled sending a signal seems only an
additional step. This patch also avoid writing to two pipe (one from signal
and one in qemu_service_io).
Work with kvm enabled or disabled. strace output is more readable (less syscalls).
[ kwolf: Merged build fix by Paolo Bonzini ]
Signed-off-by: Frediano Ziglio <freddy77@gmail.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
|
| |
| |
| |
| |
| |
| | |
Use runstate_is_running() instead, which is introduced by this commit.
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Currently, only vm_start() and vm_stop() change the VM state.
That's, the state is only changed when starting or stopping the VM.
This commit adds the runstate_set() function, which makes it possible
to also do state transitions when the VM is stopped or running.
Additional states are also added and the current state is stored.
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|/
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Today, when notifying a VM state change with vm_state_notify(),
we pass a VMSTOP macro as the 'reason' argument. This is not ideal
because the VMSTOP macros tell why qemu stopped and not exactly
what the current VM state is.
One example to demonstrate this problem is that vm_start() calls
vm_state_notify() with reason=0, which turns out to be VMSTOP_USER.
This commit fixes that by replacing the VMSTOP macros with a proper
state type called RunState.
Signed-off-by: Luiz Capitulino <lcapitulino@redhat.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Enabling the I/O thread by default seems like an important part of declaring
1.0. Besides allowing true SMP support with KVM, the I/O thread means that the
TCG VCPU doesn't have to multiplex itself with the I/O dispatch routines which
currently requires a (racey) signal based alarm system.
I know there have been concerns about performance. I think so far the ones that
have come up (virtio-net) are most likely due to secondary reasons like
decreased batching.
I think we ought to force enabling I/O thread early in 1.0 development and
commit to resolving any lingering issues.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
We can express the VCPU thread wakeup with the stop mechanism, saving
both qemu_system_ready and the qemu_system_cond. For KVM threads, we can
just enter the main loop as long as the thread is stopped. The central
TCG thread is better held back before the loop as there can be side
effects of the services called even when all CPUs are stopped.
Creating VCPUs in stopped state will also be required for proper CPU
hotplugging support.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
| |
In TCG mode, iothread and vcpus run in lock-step. So it's pointless to
send a signal from qemu_cpu_kick to the vcpu thread - if we got here,
the receiver already left the vcpu loop.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
| |
qemu_malloc/qemu_free no longer exist after this commit.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This conveys the intention better, and scales to more than >1
threads contending the mutex with the iothread (as long as all
of them have a "quiescent point" like the TCG thread has).
Also, on Mac OS X the fair_mutex somehow didn't work as intended
and deadlocked.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Both the signal thread (via sigwait()) and the cpu thread (via
a normal signal handler) were attempting to catch SIG_IPI.
This resulted in random freezes under Darwin.
This patch separates SIG_IPI from the rest of the signals handled
by the signal thread, because it is independently caught by the cpu
thread.
Signed-off-by: Alexandre Raymond <cerbere@gmail.com>
Acked-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Changes since v1:
- take pthread_sigmask() out of the ifdef as it is now common
to both parts.
This fix effectively blocks, in the main thread, the signals handled
by signalfd or the compatibility signal thread.
This way, such signals are received synchronously in the main thread
through sigfd_handler() instead of triggering the signal handler
directly, asynchronously.
Signed-off-by: Alexandre Raymond <cerbere@gmail.com>
Acked-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
|
|\ |
|
| |
| |
| |
| |
| |
| |
| | |
sigset_t, used by that header, is not available in mingw32 environments.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
|
|/
|
|
|
|
| |
Most exec-all.h include directives are now useless, remove them.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
|