The setup_data links are appended to the compressed kernel image. Since
the kernel image is typically loaded at 0x100000, setup_data lives at
`0x100000 + compressed_size`, which does not get relocated during the
kernel's boot process.
The kernel typically decompresses the image starting at address
0x1000000 (note: there's one more zero there than the compressed image
above). This usually is fine for most kernels.
However, if the compressed image is actually quite large, then
setup_data will live at a `0x100000 + compressed_size` that extends into
the decompressed zone at 0x1000000. In other words, if compressed_size
is larger than `0x1000000 - 0x100000`, then the decompression step will
clobber setup_data, resulting in crashes.
Visually, what happens now is that QEMU appends setup_data to the kernel
image:
kernel image setup_data
|--------------------------||----------------|
0x100000 0x100000+l1 0x100000+l1+l2
The problem is that this decompresses to 0x1000000 (one more zero). So
if l1 is > (0x1000000-0x100000), then this winds up looking like:
kernel image setup_data
|--------------------------||----------------|
0x100000 0x100000+l1 0x100000+l1+l2
d e c o m p r e s s e d k e r n e l
|-------------------------------------------------------------|
0x1000000 0x1000000+l3
The decompressed kernel seemingly overwriting the compressed kernel
image isn't a problem, because that gets relocated to a higher address
early on in the boot process, at the end of startup_64. setup_data,
however, stays in the same place, since those links are self referential
and nothing fixes them up. So the decompressed kernel clobbers it.
Fix this by appending setup_data to the cmdline blob rather than the
kernel image blob, which remains at a lower address that won't get
clobbered.
This could have been done by overwriting the initrd blob instead, but
that poses big difficulties, such as no longer being able to use memory
mapped files for initrd, hurting performance, and, more importantly, the
initrd address calculation is hard coded in qboot, and it always grows
down rather than up, which means lots of brittle semantics would have to
be changed around, incurring more complexity. In contrast, using cmdline
is simple and doesn't interfere with anything.
The microvm machine has a gross hack where it fiddles with fw_cfg data
after the fact. So this hack is updated to account for this appending,
by reserving some bytes.
Fixup-by: Michael S. Tsirkin <mst@redhat.com>
Cc: x86@kernel.org
Cc: Philippe Mathieu-Daudé <philmd@linaro.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Eric Biggers <ebiggers@kernel.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Message-Id: <20221230220725.618763-1-Jason@zx2c4.com>
Message-ID: <20230128061015-mutt-send-email-mst@kernel.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Eric Biggers <ebiggers@google.com>
Tested-by: Mathias Krause <minipli@grsecurity.net>
Specify maximum possible APIC ID assigned for current VM session to KVM
prior to the creation of vCPUs. By this setting, KVM can set up VM-scoped
data structure indexed by the APIC ID, e.g. Posted-Interrupt Descriptor
pointer table to support Intel IPI virtualization, with the most optimal
memory footprint.
It can be achieved by calling KVM_ENABLE_CAP for KVM_CAP_MAX_VCPU_ID
capability once KVM has enabled it. Ignoring the return error if KVM
doesn't support this capability yet.
Signed-off-by: Zeng Guang <guang.zeng@intel.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20220825025246.26618-1-guang.zeng@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We don't want it to be possible to re-read the RNG seed after ingesting
it, because this ruins forward secrecy. Currently, however, the setup
data section can just be re-read. Since the kernel is always read after
the setup data, use the selection of the kernel as a trigger to
re-initialize the RNG seed, just like we do on reboot, to preserve
forward secrecy.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Message-Id: <20220922152847.3670513-1-Jason@zx2c4.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Since this is read from fw_cfg on each boot, the kernel zeroing it out
alone is insufficient to prevent it from being used twice. And indeed on
reboot we always want a new seed, not the old one. So re-fill it in this
circumstance.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Message-Id: <20220921093134.2936487-3-Jason@zx2c4.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
If setup_data is being read into a specific memory location, then
generally the setup_data address parameter is read first, so that the
caller knows where to read it into. In that case, we should return
setup_data containing the absolute addresses that are hard coded and
determined a priori. This is the case when kernels are loaded by BIOS,
for example. In contrast, when setup_data is read as a file, then we
shouldn't modify setup_data, since the absolute address will be wrong by
definition. This is the case when OVMF loads the image.
This allows setup_data to be used like normal, without crashing when EFI
tries to use it.
(As a small development note, strangely, fw_cfg_add_file_callback() was
exported but fw_cfg_add_bytes_callback() wasn't, so this makes that
consistent.)
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Laurent Vivier <laurent@vivier.eu>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Philippe Mathieu-Daudé <f4bug@amsat.org>
Cc: Richard Henderson <richard.henderson@linaro.org>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Message-Id: <20220921093134.2936487-1-Jason@zx2c4.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rather than hardcoding the 4G boundary everywhere, introduce a
X86MachineState field @above_4g_mem_start and use it
accordingly.
This is in preparation for relocating ram-above-4g to be
dynamically start at 1T on AMD platforms.
Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20220719170014.27028-2-joao.m.martins@oracle.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Legacy PIC (8259) cannot be supported for TDX guests since TDX module
doesn't allow directly interrupt injection. Using posted interrupts
for the PIC is not a viable option as the guest BIOS/kernel will not
do EOI for PIC IRQs, i.e. will leave the vIRR bit set.
Make PIC the property of common x86 machine type. Hence all x86
machines, including microvm, can disable it.
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Message-Id: <20220310122811.807794-3-xiaoyao.li@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The check on x86ms->apic_id_limit in pc_machine_done() had two problems.
Firstly, we need KVM to support the X2APIC API in order to allow IRQ
delivery to APICs >= 255. So we need to call/check kvm_enable_x2apic(),
which was done elsewhere in *some* cases but not all.
Secondly, microvm needs the same check. So move it from pc_machine_done()
to x86_cpus_init() where it will work for both.
The check in kvm_cpu_instance_init() is now redundant and can be dropped.
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Acked-by: Claudio Fontana <cfontana@suse.de>
Message-Id: <20220314142544.150555-1-dwmw2@infradead.org>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
commit
f862ddbb1a (hw/i386: Remove the deprecated pc-1.x machine types)
removed the last user of broken APIC ID compat knob,
but compat_apic_id_mode itself was forgotten.
Clean it up and simplify x86_cpu_apic_id_from_index()
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20220228131634.3389805-1-imammedo@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Reviewed-by: Thomas Huth <thuth@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
As long as fw_cfg supports DMA, the new ROM can be used also on older
machine types because it has the same size as the existing one.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This removes a parameter from x86_load_linux, and will avoid code
duplication between the linux and multiboot cases once multiboot
starts to support DMA.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
SEV is a x86 specific feature, and the "sev_i386.h" header
is already in target/i386/. Rename it as "sev.h" to simplify.
Patch created mechanically using:
$ git mv target/i386/sev_i386.h target/i386/sev.h
$ sed -i s/sev_i386.h/sev.h/ $(git grep -l sev_i386.h)
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20211007161716.453984-15-philmd@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Because SGX EPC is enumerated through CPUID, EPC "devices" need to be
realized prior to realizing the vCPUs themselves, i.e. long before
generic devices are parsed and realized. From a virtualization
perspective, the CPUID aspect also means that EPC sections cannot be
hotplugged without paravirtualizing the guest kernel (hardware does
not support hotplugging as EPC sections must be locked down during
pre-boot to provide EPC's security properties).
So even though EPC sections could be realized through the generic
-devices command, they need to be created much earlier for them to
actually be usable by the guest. Place all EPC sections in a
contiguous block, somewhat arbitrarily starting after RAM above 4g.
Ensuring EPC is in a contiguous region simplifies calculations, e.g.
device memory base, PCI hole, etc..., allows dynamic calculation of the
total EPC size, e.g. exposing EPC to guests does not require -maxmem,
and last but not least allows all of EPC to be enumerated in a single
ACPI entry, which is expected by some kernels, e.g. Windows 7 and 8.
The new compound properties command for sgx like below:
......
-object memory-backend-epc,id=mem1,size=28M,prealloc=on \
-object memory-backend-epc,id=mem2,size=10M \
-M sgx-epc.0.memdev=mem1,sgx-epc.1.memdev=mem2
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <20210719112136.57018-6-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In order to make SMP configuration a Machine property, we need a getter as
well as a setter. To simplify the implementation put everything that the
getter needs in the CpuTopology struct.
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210617155308.928754-7-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
A bus lock is acquired through either split locked access to writeback
(WB) memory or any locked access to non-WB memory. It is typically >1000
cycles slower than an atomic operation within a cache and can also
disrupts performance on other cores.
Virtual Machines can exploit bus locks to degrade the performance of
system. To address this kind of performance DOS attack coming from the
VMs, bus lock VM exit is introduced in KVM and it can report the bus
locks detected in guest. If enabled in KVM, it would exit to the
userspace to let the user enforce throttling policies once bus locks
acquired in VMs.
The availability of bus lock VM exit can be detected through the
KVM_CAP_X86_BUS_LOCK_EXIT. The returned bitmap contains the potential
policies supported by KVM. The field KVM_BUS_LOCK_DETECTION_EXIT in
bitmap is the only supported strategy at present. It indicates that KVM
will exit to userspace to handle the bus locks.
This patch adds a ratelimit on the bus locks acquired in guest as a
mitigation policy.
Introduce a new field "bus_lock_ratelimit" to record the limited speed
of bus locks in the target VM. The user can specify it through the
"bus-lock-ratelimit" as a machine property. In current implementation,
the default value of the speed is 0 per second, which means no
restrictions on the bus locks.
As for ratelimit on detected bus locks, simply set the ratelimit
interval to 1s and restrict the quota of bus lock occurence to the value
of "bus_lock_ratelimit". A potential alternative is to introduce the
time slice as a property which can help the user achieve more precise
control.
The detail of bus lock VM exit can be found in spec:
https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html
Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
Message-Id: <20210521043820.29678-1-chenyi.qiang@intel.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The code that sets/gets oem fields is duplicated in both PC and MICROVM
variants. This commit moves it to X86MachineState so that all x86
variants can use it and duplication is removed.
Signed-off-by: Marian Postevca <posteuca@mutex.one>
Message-Id: <20210221001737.24499-2-posteuca@mutex.one>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch adds support the kernel-irqchip option for
WHPX with on or off value. 'split' value is not supported
for the option. The option only works for the latest version
of Windows (ones that are coming out on Insiders). The
change maintains backward compatibility on older version of
Windows where this option is not supported.
Signed-off-by: Sunil Muthuswamy <sunilmut@microsoft.com>
Message-Id: <SN4PR2101MB0880B13258DA9251F8459F4DC0170@SN4PR2101MB0880.namprd21.prod.outlook.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rewrite function to use switch() for IRQ number mapping.
Check i8259_irq exists before raising it so the function
also works in case no i8259 (aka pic) is present.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Message-id: 20201203105423.10431-3-kraxel@redhat.com
The new interface starts unused, will start being used by the
next patches.
It provides methods for each accelerator to start a vcpu, kick a vcpu,
synchronize state, get cpu virtual clock and elapsed ticks.
In qemu_wait_io_event, make it clear that APC is used only for HAX
on Windows.
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
refactoring of cpus.c continues with cpu timer state extraction.
cpu-timers: responsible for the softmmu cpu timers state,
including cpu clocks and ticks.
icount: counts the TCG instructions executed. As such it is specific to
the TCG accelerator. Therefore, it is built only under CONFIG_TCG.
One complication is due to qtest, which uses an icount field to warp time
as part of qtest (qtest_clock_warp).
In order to solve this problem, provide a separate counter for qtest.
This requires fixing assumptions scattered in the code that
qtest_enabled() implies icount_enabled(), checking each specific case.
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
[remove redundant initialization with qemu_spice_init]
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
[fix lingering calls to icount_get]
Signed-off-by: Claudio Fontana <cfontana@suse.de>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
There were reports of guest crash on CPU hotplug, when using q35 machine
type and OVMF with SMM, due to hotplugged CPU trying to process SMI at
default SMI handler location without it being relocated by firmware first.
Fix it by refusing hotplug if firmware hasn't negotiated CPU hotplug with
SMI support while SMI broadcast is in use.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Message-Id: <20200923094650.1301166-3-imammedo@redhat.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The cpu hotplug code handles the initialization of coldplugged cpus
too, so it is needed even in case cpu hotplug is not supported.
Move the code from pc to x86, so microvm can use it.
Move both plug and unplug to keep everything in one place, even
though microvm needs plug only.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Sergio Lopez <slp@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Message-id: 20200915120909.20838-16-kraxel@redhat.com
When all we do with an Error we receive into a local variable is
propagating to somewhere else, we can just as well receive it there
right away. The previous two commits did that for sufficiently simple
cases with Coccinelle. Do it for several more manually.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Message-Id: <20200707160613.848843-37-armbru@redhat.com>
The previous commit enables conversion of
foo(..., &err);
if (err) {
...
}
to
if (!foo(..., errp)) {
...
}
for QOM functions that now return true / false on success / error.
Coccinelle script:
@@
identifier fun = {
object_apply_global_props, object_initialize_child_with_props,
object_initialize_child_with_propsv, object_property_get,
object_property_get_bool, object_property_parse, object_property_set,
object_property_set_bool, object_property_set_int,
object_property_set_link, object_property_set_qobject,
object_property_set_str, object_property_set_uint, object_set_props,
object_set_propv, user_creatable_add_dict,
user_creatable_complete, user_creatable_del
};
expression list args, args2;
typedef Error;
Error *err;
@@
- fun(args, &err, args2);
- if (err)
+ if (!fun(args, &err, args2))
{
...
}
Fails to convert hw/arm/armsse.c, because Coccinelle gets confused by
ARMSSE being used both as typedef and function-like macro there.
Convert manually.
Line breaks tidied up manually.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20200707160613.848843-29-armbru@redhat.com>
The object_property_set_FOO() setters take property name and value in
an unusual order:
void object_property_set_FOO(Object *obj, FOO_TYPE value,
const char *name, Error **errp)
Having to pass value before name feels grating. Swap them.
Same for object_property_set(), object_property_get(), and
object_property_parse().
Convert callers with this Coccinelle script:
@@
identifier fun = {
object_property_get, object_property_parse, object_property_set_str,
object_property_set_link, object_property_set_bool,
object_property_set_int, object_property_set_uint, object_property_set,
object_property_set_qobject
};
expression obj, v, name, errp;
@@
- fun(obj, v, name, errp)
+ fun(obj, name, v, errp)
Chokes on hw/arm/musicpal.c's lcd_refresh() with the unhelpful error
message "no position information". Convert that one manually.
Fails to convert hw/arm/armsse.c, because Coccinelle gets confused by
ARMSSE being used both as typedef and function-like macro there.
Convert manually.
Fails to convert hw/rx/rx-gdbsim.c, because Coccinelle gets confused
by RXCPU being used both as typedef and function-like macro there.
Convert manually. The other files using RXCPU that way don't need
conversion.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
Message-Id: <20200707160613.848843-27-armbru@redhat.com>
[Straightforwad conflict with commit 2336172d9b "audio: set default
value for pcspk.iobase property" resolved]
The Error ** argument must be NULL, &error_abort, &error_fatal, or a
pointer to a variable containing NULL. Passing an argument of the
latter kind twice without clearing it in between is wrong: if the
first call sets an error, it no longer points to NULL for the second
call.
x86_cpu_new() is wrong that way: it passes &local_err to
object_property_set_uint() without checking it, and then to
qdev_realize(). If both fail, we'll trip error_setv()'s assertion.
To assess the bug's impact, we'd need to figure out how to make both
calls fail. Too much work for ignorant me, sorry.
Fix by checking for failure right away.
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Message-Id: <20200630090351.1247703-21-armbru@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
All remaining conversions to qdev_realize() are for bus-less devices.
Coccinelle script:
// only correct for bus-less @dev!
@@
expression errp;
expression dev;
@@
- qdev_init_nofail(dev);
+ qdev_realize(dev, NULL, &error_fatal);
@ depends on !(file in "hw/core/qdev.c") && !(file in "hw/core/bus.c")@
expression errp;
expression dev;
symbol true;
@@
- object_property_set_bool(OBJECT(dev), true, "realized", errp);
+ qdev_realize(DEVICE(dev), NULL, errp);
@ depends on !(file in "hw/core/qdev.c") && !(file in "hw/core/bus.c")@
expression errp;
expression dev;
symbol true;
@@
- object_property_set_bool(dev, true, "realized", errp);
+ qdev_realize(DEVICE(dev), NULL, errp);
Note that Coccinelle chokes on ARMSSE typedef vs. macro in
hw/arm/armsse.c. Worked around by temporarily renaming the macro for
the spatch run.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200610053247.1583243-57-armbru@redhat.com>
