This defines new QOM object - IOMMUMemoryRegion - with MemoryRegion
as a parent.
This moves IOMMU-related fields from MR to IOMMU MR. However to avoid
dymanic QOM casting in fast path (address_space_translate, etc),
this adds an @is_iommu boolean flag to MR and provides new helper to
do simple cast to IOMMU MR - memory_region_get_iommu. The flag
is set in the instance init callback. This defines
memory_region_is_iommu as memory_region_get_iommu()!=NULL.
This switches MemoryRegion to IOMMUMemoryRegion in most places except
the ones where MemoryRegion may be an alias.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Message-Id: <20170711035620.4232-2-aik@ozlabs.ru>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
pc.h and sysemu/kvm.h are also included from common code (where
CONFIG_KVM is not available), so the #defines that depend on CONFIG_KVM
should not be declared here to avoid that anybody is using them in a
wrong way. Since we're also going to poison CONFIG_KVM for common code,
let's move them to kvm_i386.h instead. Most of the dummy definitions
from sysemu/kvm.h are also unused since the code that uses them is
only compiled for CONFIG_KVM (e.g. target/i386/kvm.c), so the unused
defines are also simply dropped here instead of being moved.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <1498454578-18709-3-git-send-email-thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The q35 machine type currently lets the guest firmware select a 1MB, 2MB
or 8MB TSEG (basically, SMRAM) size. In edk2/OVMF, we use 8MB, but even
that is not enough when a lot of VCPUs (more than approx. 224) are
configured -- SMRAM footprint scales largely proportionally with VCPU
count.
Introduce a new property for "mch" called "extended-tseg-mbytes", which
expresses (in megabytes) the user's choice of TSEG (SMRAM) size.
Invent a new, QEMU-specific register in the config space of the DRAM
Controller, at offset 0x50, in order to allow guest firmware to query the
TSEG (SMRAM) size.
According to Intel Document Number 316966-002, Table 5-1 "DRAM Controller
Register Address Map (D0:F0)":
Warning: Address locations that are not listed are considered Intel
Reserved registers locations. Reads to Reserved registers may
return non-zero values. Writes to reserved locations may
cause system failures.
All registers that are defined in the PCI 2.3 specification,
but are not necessary or implemented in this component are
simply not included in this document. The
reserved/unimplemented space in the PCI configuration header
space is not documented as such in this summary.
Offsets 0x50 and 0x51 are not listed in Table 5-1. They are also not part
of the standard PCI config space header. And they precede the capability
list as well, which starts at 0xe0 for this device.
When the guest writes value 0xffff to this register, the value that can be
read back is that of "mch.extended-tseg-mbytes" -- unless it remains
0xffff. The guest is required to write 0xffff first (as opposed to a
read-only register) because PCI config space is generally not cleared on
QEMU reset, and after S3 resume or reboot, new guest firmware running on
old QEMU could read a guest OS-injected value from this register.
After reading the available "extended" TSEG size, the guest firmware may
actually request that TSEG size by writing pattern 11b to the ESMRAMC
register's TSEG_SZ bit-field. (The Intel spec referenced above defines
only patterns 00b (1MB), 01b (2MB) and 10b (8MB); 11b is reserved.)
On the QEMU command line, the value can be set with
-global mch.extended-tseg-mbytes=N
The default value for 2.10+ q35 machine types is 16. The value is limited
to 0xfff (4095) at the moment, purely so that the product (4095 MB) can be
stored to the uint32_t variable "tseg_size" in mch_update_smram(). Users
are responsible for choosing sensible TSEG sizes.
On 2.9 and earlier q35 machine types, the default value is 0. This lets
the 11b bit pattern in ESMRAMC.TSEG_SZ, and the register at offset 0x50,
keep their original behavior.
When "extended-tseg-mbytes" is nonzero, the new register at offset 0x50 is
set to that value on reset, for completeness.
PCI config space is migrated automatically, so no VMSD changes are
necessary.
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Ref: https://bugzilla.redhat.com/show_bug.cgi?id=1447027
Ref: https://lists.01.org/pipermail/edk2-devel/2017-May/010456.html
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Since the automatic cpuid-level code was introduced in commit
c39c0edf9b ("target-i386: Automatically
set level/xlevel/xlevel2 when needed"), the CPU model tables just define
the default CPUID level code (set using "min-level"). Setting
"[x]level" forces CPUID level to a specific value and disable the
automatic-level logic.
But the PC compat code was not updated and the existing "[x]level"
compat properties broke compatibility for people using features that
triggered the auto-level code. To keep previous behavior, we should set
"min-[x]level" instead of "[x]level" on compat_props.
This was not a problem for most cases, because old machine-types don't
have full-cpuid-auto-level enabled. The only common use case it broke
was the CPUID[7] auto-level code, that was already enabled since the
first CPUID[7] feature was introduced (in QEMU 1.4.0).
This causes the regression reported at:
https://bugzilla.redhat.com/show_bug.cgi?id=1454641
Change the PC compat code to use "min-[x]level" instead of "[x]level" on
compat_props, and add new test cases to ensure we don't break this
again.
Reported-by: "Guo, Zhiyi" <zhguo@redhat.com>
Fixes: c39c0edf9b ("target-i386: Automatically set level/xlevel/xlevel2 when needed")
Cc: qemu-stable@nongnu.org
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Hardware support for VT-d device passthrough. Although current Linux can
live with iommu=pt even without this, but this is faster than when using
software passthrough.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Liu, Yi L <yi.l.liu@linux.intel.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
CC: "Michael S. Tsirkin" <mst@redhat.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Since 2.7 commit (b2a575a Add optionrom compatible with fw_cfg DMA version)
regressed migration during firmware exection time by
abusing fwcfg.dma_enabled property to decide loading
dma version of option rom AND by mistake disabling DMA
for 2.6 and earlier globally instead of only for option rom.
so 2.6 machine type guest is broken when it already runs
firmware in DMA mode but migrated to qemu-2.7(pc-2.6)
at that time;
a) qemu-2.6:pc2.6 (fwcfg.dma=on,firmware=dma,oprom=ioport)
b) qemu-2.7:pc2.6 (fwcfg.dma=off,firmware=ioport,oprom=ioport)
to: a b
from
a OK FAIL
b OK OK
So we currently have broken forward migration from
qemu-2.6 to qemu-2.[789] that however could be fixed
for 2.10 by re-enabling DMA for 2.[56] machine types
and allowing dma capable option rom only since 2.7.
As result qemu should end up with:
c) qemu-2.10:pc2.6 (fwcfg.dma=on,firmware=dma,oprom=ioport)
to: a b c
from
a OK FAIL OK
b OK OK OK
c OK FAIL OK
where forward migration from qemu-2.6 to qemu-2.10 should
work again leaving only qemu-2.[789]:pc-2.6 broken.
Reported-by: Eduardo Habkost <ehabkost@redhat.com>
Analyzed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This adds a clarifying comment and build time assert to the FADT reset register field initialisation: the reset register is the same on both machine types.
Signed-off-by: Phil Dennis-Jordan <phil@philjordan.eu>
Message-Id: <1489558827-28971-3-git-send-email-phil@philjordan.eu>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch is based on Aviv Ben-David (<bd.aviv@gmail.com>)'s patch
upstream:
"IOMMU: enable intel_iommu map and unmap notifiers"
https://lists.gnu.org/archive/html/qemu-devel/2016-11/msg01453.html
However I removed/fixed some content, and added my own codes.
Instead of translate() every page for iotlb invalidations (which is
slower), we walk the pages when needed and notify in a hook function.
This patch enables vfio devices for VT-d emulation.
And, since we already have vhost DMAR support via device-iotlb, a
natural benefit that this patch brings is that vt-d enabled vhost can
live even without ATS capability now. Though more tests are needed.
Signed-off-by: Aviv Ben-David <bdaviv@cs.technion.ac.il>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: \"Michael S. Tsirkin\" <mst@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1491562755-23867-10-git-send-email-peterx@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This is preparation work to finally enabled dynamic switching ON/OFF for
VT-d protection. The old VT-d codes is using static IOMMU address space,
and that won't satisfy vfio-pci device listeners.
Let me explain.
vfio-pci devices depend on the memory region listener and IOMMU replay
mechanism to make sure the device mapping is coherent with the guest
even if there are domain switches. And there are two kinds of domain
switches:
(1) switch from domain A -> B
(2) switch from domain A -> no domain (e.g., turn DMAR off)
Case (1) is handled by the context entry invalidation handling by the
VT-d replay logic. What the replay function should do here is to replay
the existing page mappings in domain B.
However for case (2), we don't want to replay any domain mappings - we
just need the default GPA->HPA mappings (the address_space_memory
mapping). And this patch helps on case (2) to build up the mapping
automatically by leveraging the vfio-pci memory listeners.
Another important thing that this patch does is to seperate
IR (Interrupt Remapping) from DMAR (DMA Remapping). IR region should not
depend on the DMAR region (like before this patch). It should be a
standalone region, and it should be able to be activated without
DMAR (which is a common behavior of Linux kernel - by default it enables
IR while disabled DMAR).
Reviewed-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: \"Michael S. Tsirkin\" <mst@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <1491562755-23867-9-git-send-email-peterx@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This behavior is not indicated in the datasheet and can confuse the OS.
The TCO can trap NMIs from SERR# or IOCHK# and convert them to SMIs; but
any other TCO event is either delivered as an SMI or completely disabled.
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This reverts commit 07bfa35477.
The global variable is only read as part of a
apic_reset_irq_delivered();
qemu_irq_raise(s->irq);
if (!apic_get_irq_delivered()) {
sequence, so the value never matters at migration time.
Reported-by: Dr. David Alan Gilbert <dglibert@redhat.com>
Cc: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
glibc blacklists TSX on Haswell CPUs with model==60 and
stepping < 4. To make the Haswell CPU model more useful, make
those guests actually use TSX by changing CPU stepping to 4.
References:
* glibc commit 2702856bf45c82cf8e69f2064f5aa15c0ceb6359
https://sourceware.org/git/?p=glibc.git;a=commit;h=2702856bf45c82cf8e69f2064f5aa15c0ceb6359
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <20170309181212.18864-4-ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Migration from a 2.3.0 qemu results in a reboot on the receiving QEMU
due to a disagreement about SM (System management) interrupts.
2.3.0 didn't have much SMI support, but it did set CPU_INTERRUPT_SMI
and this gets into the migration stream, but on 2.3.0 it
never got delivered.
~2.4.0 SMI interrupt support was added but was broken - so
that when a 2.3.0 stream was received it cleared the CPU_INTERRUPT_SMI
but never actually caused an interrupt.
The SMI delivery was recently fixed by 68c6efe07a, but the
effect now is that an incoming 2.3.0 stream takes the interrupt it
had flagged but it's bios can't actually handle it(I think
partly due to the original interrupt not being taken during boot?).
The consequence is a triple(?) fault and a reboot.
Tested from:
2.3.1 -M 2.3.0
2.7.0 -M 2.3.0
2.8.0 -M 2.3.0
2.8.0 -M 2.8.0
This corresponds to RH bugzilla entry 1420679.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20170223133441.16010-1-dgilbert@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
so that it would be possible to reuse it with
spapr/virt-aarch64 targets.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
This capability asks the guest to invalidate cache before each map operation.
We can use this invalidation to trap map operations in the hypervisor.
Signed-off-by: Aviv Ben-David <bd.aviv@gmail.com>
[peterx: using "caching-mode" instead of "cache-mode" to align with spec]
[peterx: re-write the subject to make it short and clear]
Reviewed-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Aviv Ben-David <bd.aviv@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Pick a uniform chardev type name.
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Phil Dennis-Jordan <phil@philjordan.eu>
Message-Id: <1484921496-11257-4-git-send-email-phil@philjordan.eu>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The generic edk2 SMM infrastructure prefers
EFI_SMM_CONTROL2_PROTOCOL.Trigger() to inject an SMI on each processor. If
Trigger() only brings the current processor into SMM, then edk2 handles it
in the following ways:
(1) If Trigger() is executed by the BSP (which is guaranteed before
ExitBootServices(), but is not necessarily true at runtime), then:
(a) If edk2 has been configured for "traditional" SMM synchronization,
then the BSP sends directed SMIs to the APs with APIC delivery,
bringing them into SMM individually. Then the BSP runs the SMI
handler / dispatcher.
(b) If edk2 has been configured for "relaxed" SMM synchronization,
then the APs that are not already in SMM are not brought in, and
the BSP runs the SMI handler / dispatcher.
(2) If Trigger() is executed by an AP (which is possible after
ExitBootServices(), and can be forced e.g. by "taskset -c 1
efibootmgr"), then the AP in question brings in the BSP with a
directed SMI, and the BSP runs the SMI handler / dispatcher.
The smaller problem with (1a) and (2) is that the BSP and AP
synchronization is slow. For example, the "taskset -c 1 efibootmgr"
command from (2) can take more than 3 seconds to complete, because
efibootmgr accesses non-volatile UEFI variables intensively.
The larger problem is that QEMU's current behavior diverges from the
behavior usually seen on physical hardware, and that keeps exposing
obscure corner cases, race conditions and other instabilities in edk2,
which generally expects / prefers a software SMI to affect all CPUs at
once.
Therefore introduce the "broadcast SMI" feature that causes QEMU to inject
the SMI on all VCPUs.
While the original posting of this patch
<http://lists.nongnu.org/archive/html/qemu-devel/2015-10/msg05658.html>
only intended to speed up (2), based on our recent "stress testing" of SMM
this patch actually provides functional improvements.
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20170126014416.11211-3-lersek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Introduce the following fw_cfg files:
- "etc/smi/supported-features": a little endian uint64_t feature bitmap,
presenting the features known by the host to the guest. Read-only for
the guest.
The content of this file will be determined via bit-granularity ICH9-LPC
device properties, to be introduced later. For now, the bitmask is left
zeroed. The bits will be set from machine type compat properties and on
the QEMU command line, hence this file is not migrated.
- "etc/smi/requested-features": a little endian uint64_t feature bitmap,
representing the features the guest would like to request. Read-write
for the guest.
The guest can freely (re)write this file, it has no direct consequence.
Initial value is zero. A nonzero value causes the SMI-related fw_cfg
files and fields that are under guest influence to be migrated.
- "etc/smi/features-ok": contains a uint8_t value, and it is read-only for
the guest. When the guest selects the associated fw_cfg key, the guest
features are validated against the host features. In case of error, the
negotiation doesn't proceed, and the "features-ok" file remains zero. In
case of success, the "features-ok" file becomes (uint8_t)1, and the
negotiated features are locked down internally (to which no further
changes are possible until reset).
The initial value is zero. A nonzero value causes the SMI-related
fw_cfg files and fields that are under guest influence to be migrated.
The C-language fields backing the "supported-features" and
"requested-features" files are uint8_t arrays. This is because they carry
guest-side representation (our choice is little endian), while
VMSTATE_UINT64() assumes / implies host-side endianness for any uint64_t
fields. If we migrate a guest between hosts with different endiannesses
(which is possible with TCG), then the host-side value is preserved, and
the host-side representation is translated. This would be visible to the
guest through fw_cfg, unless we used plain byte arrays. So we do.
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <20170126014416.11211-2-lersek@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch implements saving/restoring of static apic_delivered variable.
v8: saving static variable only for one of the APICs
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Message-Id: <20170126123429.5412.94368.stgit@PASHA-ISP>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
make sure that external callers won't try to modify
possible_cpus and owner of possible_cpus can access
it directly when it modifies it.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <1484759609-264075-5-git-send-email-imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
As noticed by David Gilbert, commit 6053a86 'kvmclock: reduce kvmclock
differences on migration' added 'x-mach-use-reliable-get-clock' and a
compatibility entry that turns it off; however it got merged after 2.8.0
was released but the entry has gone into PC_COMPAT_2_7 where it should
have gone into PC_COMPAT_2_8.
Fix it by moving the entry to PC_COMPAT_2_8.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20170118175343.GA26873@amt.cnet>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This patch enables device IOTLB support for intel iommu. The major
work is to implement QI device IOTLB descriptor processing and notify
the device through iommu notifier.
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>
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>
Reviewed-by: Peter Xu <peterx@redhat.com>
Check for KVM_CAP_ADJUST_CLOCK capability KVM_CLOCK_TSC_STABLE, which
indicates that KVM_GET_CLOCK returns a value as seen by the guest at
that moment.
For new machine types, use this value rather than reading
from guest memory.
This reduces kvmclock difference on migration from 5s to 0.1s
(when max_downtime == 5s).
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <20161121105052.598267440@redhat.com>
[Add comment explaining what is going on. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
To keep backwards migration compatibility allow us to turn pcspk
migration off.
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Message-Id: <20161128133201.16104-3-dgilbert@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This reverts commit 080ac219cc.
Legacy FW_CFG_NB_CPUS will be reused instead of 'etc/boot-cpus'
fw_cfg file since it does the same and there is no point
to maintaing duplicate guest ABI, if it can be helped.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Message-Id: <1479212236-183810-2-git-send-email-imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Introduce this field to control whether ACPI build is enabled by a
particular machine or accelerator.
It defaults to true if the machine itself supports ACPI build. Xen
accelerator will disable it because Xen is in charge of building ACPI
tables for the guest.
Signed-off-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Stefano Stabellini <sstabellini@kernel.org>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Tested-by: Sander Eikelenboom <linux@eikelenboom.it>
Some files contain multiple #includes of the same header file.
Removed most of those unnecessary duplicate entries using
scripts/clean-includes.
Reviewed-by: Thomas Huth <thuth@redhat.com>
Signed-off-by: Anand J <anand.indukala@gmail.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Currently firmware uses 1 byte at 0x5F offset in RTC CMOS
to get number of CPUs present at boot. However 1 byte is
not enough to handle more than 255 CPUs. So add a new
fw_cfg file that would allow QEMU to tell it.
For compat reasons add file only for machine types that
support more than 255 CPUs.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
ACPI ID is 32 bit wide on CPUs with x2APIC support.
Extend 'id' property to support it.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Cluster x2APIC cannot work without KVM's x2apic API when the maximal
APIC ID is greater than 8 and only KVM's LAPIC can support x2APIC, so we
forbid other APICs and also the old KVM case with less than 9, to
simplify the code.
There is no point in enabling EIM in forbidden APICs, so we keep it
enabled only for the KVM APIC; unconditionally, because making the
option depend on KVM version would be a maintanance burden.
Old QEMUs would enable eim whenever intremap was on, which would trick
guests into thinking that they can enable cluster x2APIC even if any
interrupt destination would get clamped to 8 bits.
Depending on your configuration, QEMU could notice that the destination
LAPIC is not present and report it with a very non-obvious:
KVM: injection failed, MSI lost (Operation not permitted)
Or the guest could say something about unexpected interrupts, because
clamping leads to aliasing so interrupts were being delivered to
incorrect VCPUs.
KVM_X2APIC_API is the feature that allows us to enable EIM for KVM.
QEMU 2.7 allowed EIM whenever interrupt remapping was enabled. In order
to keep backward compatibility, we again allow guests to misbehave in
non-obvious ways, and make it the default for old machine types.
A user can enable the buggy mode it with "x-buggy-eim=on".
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The default (auto) emulates the current behavior.
A user can now control EIM like
-device intel-iommu,intremap=on,eim=off
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>
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>
Every configuration has only up to one APIC class and we'll be extending
the class with a function that can be called without an instanced
object, so a direct access to the class is convenient.
This patch will break compilation if some code uses apic_get_class()
with CONFIG_USER_ONLY.
Suggested-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@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>
Current CPU definition for AMD Opteron third generation includes
features like SSE4a and LAHF_LM support in emulated CPUID. These
features are present in K8 rev.E or K10 CPUs and later. However,
current G3 family and model describe 2nd generation K8 cores instead.
This is incorrect but was considered harmless until our tests found a
problem with linux kernels >= 3.10 (and maybe earlier) which specifically
check for Opteron K8 model when parsing CPUID leaf 0x80000001:
http://lxr.free-electrons.com/source/arch/x86/kernel/cpu/amd.c?v=3.16#L552
This code will disable LAHF_LM feature in /proc/cpuinfo if model number
is inconsistent.
This change sets Opteron_G3 family/model/stepping to 16/2/3 which is
a proper Opteron 3rd generation 2350 CPU.
Signed-off-by: Evgeny Yakovlev <eyakovlev@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Instead of requiring users and management software to be aware of
required CPUID level/xlevel/xlevel2 values for each feature,
automatically increase those values when features need them.
This was already done for CPUID[7].EBX, and is now made generic
for all CPUID feature flags. Unit test included, to make sure we
don't break ABI on older machine-types and don't mess with the
CPUID level values if they are explicitly set by the user.
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Add IVRS table for AMD IOMMU. Generate IVRS or DMAR
depending on emulated IOMMU.
Signed-off-by: David Kiarie <davidkiarie4@gmail.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
commit (14c985cff target-i386: present virtual L3 cache info for vcpus)
misplaced compat property putting it in new 2.8 machine type
which would effectively to disable feature until 2.9 is released.
Intent of commit probably should be to disable feature for 2.7
and older while allowing not yet released 2.8 to have feature
enabled by default.
Cc: qemu-stable@nongnu.org
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Marcel Apfelbaum <marcel@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Since commit
bacc344c ("machine: add properties to compat_props incrementaly")
there is no need to chain per machine type compat macro.
Clean up places where it was done anyway so it will be
consistent and won't confuse contributors during addtion
of new machine types.
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Unused function declarations were found using a simple gcc plugin and
manually verified by grepping the sources.
Signed-off-by: Ladi Prosek <lprosek@redhat.com>
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
Some software algorithms are based on the hardware's cache info, for example,
for x86 linux kernel, when cpu1 want to wakeup a task on cpu2, cpu1 will trigger
a resched IPI and told cpu2 to do the wakeup if they don't share low level
cache. Oppositely, cpu1 will access cpu2's runqueue directly if they share llc.
The relevant linux-kernel code as bellow:
static void ttwu_queue(struct task_struct *p, int cpu)
{
struct rq *rq = cpu_rq(cpu);
......
if (... && !cpus_share_cache(smp_processor_id(), cpu)) {
......
ttwu_queue_remote(p, cpu); /* will trigger RES IPI */
return;
}
......
ttwu_do_activate(rq, p, 0); /* access target's rq directly */
......
}
In real hardware, the cpus on the same socket share L3 cache, so one won't
trigger a resched IPIs when wakeup a task on others. But QEMU doesn't present a
virtual L3 cache info for VM, then the linux guest will trigger lots of RES IPIs
under some workloads even if the virtual cpus belongs to the same virtual socket.
For KVM, there will be lots of vmexit due to guest send IPIs.
The workload is a SAP HANA's testsuite, we run it one round(about 40 minuates)
and observe the (Suse11sp3)Guest's amounts of RES IPIs which triggering during
the period:
No-L3 With-L3(applied this patch)
cpu0: 363890 44582
cpu1: 373405 43109
cpu2: 340783 43797
cpu3: 333854 43409
cpu4: 327170 40038
cpu5: 325491 39922
cpu6: 319129 42391
cpu7: 306480 41035
cpu8: 161139 32188
cpu9: 164649 31024
cpu10: 149823 30398
cpu11: 149823 32455
cpu12: 164830 35143
cpu13: 172269 35805
cpu14: 179979 33898
cpu15: 194505 32754
avg: 268963.6 40129.8
The VM's topology is "1*socket 8*cores 2*threads".
After present virtual L3 cache info for VM, the amounts of RES IPIs in guest
reduce 85%.
For KVM, vcpus send IPIs will cause vmexit which is expensive, so it can cause
severe performance degradation. We had tested the overall system performance if
vcpus actually run on sparate physical socket. With L3 cache, the performance
improves 7.2%~33.1%(avg:15.7%).
Signed-off-by: Longpeng(Mike) <longpeng2@huawei.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
