Currently, the amdvi_validate_dte() assumes that a valid DTE will
always have V=1. This is not true. The V=1 means that bit[127:1] are
valid. A valid DTE can have IV=1 and V=0 (i.e address translation
disabled and interrupt remapping enabled)
Remove the V=1 check from amdvi_validate_dte(), make the caller
responsible to check for V or IV bits.
This also fixes a bug in existing code that when error is
detected during the translation we'll fail the translation
instead of assuming a passthrough mode.
Signed-off-by: Brijesh Singh <brijesh.singh@amd.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Peter Xu <peterx@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>
Cc: Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Cc: Tom Lendacky <Thomas.Lendacky@amd.com>
Cc: Suravee Suthikulpanit <Suravee.Suthikulpanit@amd.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
We should handle VTD_FR_CONTEXT_ENTRY_P properly when synchronizing
shadow page tables. Having invalid context entry there is perfectly
valid when we move a device out of an existing domain. When that
happens, instead of posting an error we invalidate the whole region.
Without this patch, QEMU will crash if we do these steps:
(1) start QEMU with VT-d IOMMU and two 10G NICs (ixgbe)
(2) bind the NICs with vfio-pci in the guest
(3) start testpmd with the NICs applied
(4) stop testpmd
(5) rebind the NIC back to ixgbe kernel driver
The patch should fix it.
Reported-by: Pei Zhang <pezhang@redhat.com>
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1627272
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
There are two callers for vtd_sync_shadow_page_table_range(): one
provided a valid context entry and one not. Move that fetching
operation into the caller vtd_sync_shadow_page_table() where we need to
fetch the context entry.
Meanwhile, remove the error_report_once() directly since we're already
tracing all the error cases in the previous call. Instead, return error
number back to caller. This will not change anything functional since
callers are dropping it after all.
We do this move majorly because we want to do something more later in
vtd_sync_shadow_page_table().
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
QEMU is not handling the global DMAR switch well, especially when from
"on" to "off".
Let's first take the example of system reset.
Assuming that a guest has IOMMU enabled. When it reboots, we will drop
all the existing DMAR mappings to handle the system reset, however we'll
still keep the existing memory layouts which has the IOMMU memory region
enabled. So after the reboot and before the kernel reloads again, there
will be no mapping at all for the host device. That's problematic since
any software (for example, SeaBIOS) that runs earlier than the kernel
after the reboot will assume the IOMMU is disabled, so any DMA from the
software will fail.
For example, a guest that boots on an assigned NVMe device might fail to
find the boot device after a system reboot/reset and we'll be able to
observe SeaBIOS errors if we capture the debugging log:
WARNING - Timeout at nvme_wait:144!
Meanwhile, we should see DMAR errors on the host of that NVMe device.
It's the DMA fault that caused a NVMe driver timeout.
The correct fix should be that we do proper switching of device DMA
address spaces when system resets, which will setup correct memory
regions and notify the backend of the devices. This might not affect
much on non-assigned devices since QEMU VT-d emulation will assume a
default passthrough mapping if DMAR is not enabled in the GCMD
register (please refer to vtd_iommu_translate). However that's required
for an assigned devices, since that'll rebuild the correct GPA to HPA
mapping that is needed for any DMA operation during guest bootstrap.
Besides the system reset, we have some other places that might change
the global DMAR status and we'd better do the same thing there. For
example, when we change the state of GCMD register, or the DMAR root
pointer. Do the same refresh for all these places. For these two
places we'll also need to explicitly invalidate the context entry cache
and iotlb cache.
Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1625173
CC: QEMU Stable <qemu-stable@nongnu.org>
Reported-by: Cong Li <coli@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
--
v2:
- do the same for GCMD write, or root pointer update [Alex]
- test is carried out by me this time, by observing the
vtd_switch_address_space tracepoint after system reboot
v3:
- rewrite commit message as suggested by Alex
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Provide the function and use it in vtd_init(). Used to reset both
context entry cache and iotlb cache for the whole IOMMU unit.
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Previously, if the size of initrd >=2G, qemu exits with error:
root@haswell-OptiPlex-9020:/home/lizj# /home/lizhijian/lkp/qemu-colo/x86_64-softmmu/qemu-system-x86_64 -kernel ./vmlinuz-4.16.0-rc4 -initrd large.cgz -nographic
qemu: error reading initrd large.cgz: No such file or directory
root@haswell-OptiPlex-9020:/home/lizj# du -sh large.cgz
2.5G large.cgz
this patch changes the caller side that use this function to calculate
size of initrd file as well.
v2: update error message and int64_t printing format
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Message-Id: <1536833233-14121-1-git-send-email-lizhijian@cn.fujitsu.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit
10efd7e108 "pc: acpi: fix memory hotplug regression by reducing stub SRAT entry size"
attemped to fix hotplug regression introduced by
848a1cc1e "hw/acpi-build: build SRAT memory affinity structures for DIMM devices"
fixed issue for Windows/3.0+ linux kernels, however it regressed 2.6 based
kernels (RHEL6) to the point where guest might crash at boot.
Reason is that 2.6 kernel discards SRAT table due too small last entry
which down the road leads to crashes. Hack I've tried in 10efd7e108 is also
not ACPI spec compliant according to which whole possible RAM should be
described in SRAT. Revert 10efd7e108 to fix regression for 2.6 based kernels.
With 10efd7e108 reverted, I've also tried splitting SRAT table statically
in different ways %/node and %/slot but Windows still fails to online
2nd pc-dimm hot-plugged into node 0 (as described in 10efd7e108) and
sometimes even coldplugged pc-dimms where affected with static SRAT
partitioning.
The only known so far way where Windows stays happy is when we have 1
SRAT entry in the last node covering all hotplug area.
Revert 848a1cc1e until we come up with a way to avoid regression
on Windows with hotplug area split in several entries.
Tested this with 2.6/3.0 based kernels (RHEL6/7) and WS20[08/12/12R2/16]).
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Acked-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>
Replace all the trace_vtd_err_*() hooks with the new error_report_once()
since they are similar to trace_vtd_err() - dumping the first error
would be mostly enough, then we have them on by default too.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20180815095328.32414-4-peterx@redhat.com>
[Use "%x" instead of "%" PRIx16 to print uint16_t, whitespace tidied up]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Replace existing trace_vtd_err() with error_report_once() then stderr
will capture something if any of the error happens, meanwhile we don't
suffer from any DDOS. Then remove the trace point. Since at it,
provide more information where proper (now we can pass parameters into
the report function).
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20180815095328.32414-3-peterx@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
[Two format strings fixed, whitespace tidied up]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
We can assign and verify the address before realizing and trying to plug.
reading/writing the address property should never fail for DIMMs, so let's
reduce error handling a bit by using &error_abort. Getting access to the
memory region now might however fail. So forward errors from
get_memory_region() properly.
As all memory devices should use the alignment of the underlying memory
region for guest physical address asignment, do detection of the
alignment in pc_dimm_pre_plug(), but allow pc.c to overwrite the
alignment for compatibility handling.
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180801133444.11269-5-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
All applicable memory regions always have an alignment > 0. All memory
backends result in file_ram_alloc() or qemu_anon_ram_alloc() getting
called, setting the alignment to > 0.
So a PCDIMM memory region always has an alignment > 0. NVDIMM copy the
alignment of the original memory memory region into the handcrafted memory
region that will be used at this place.
So the check for 0 can be dropped and we can reduce the special
handling.
Dropping this check makes factoring out of alignment handling easier as
compat handling only has to look at pcmc->enforce_aligned_dimm and not
care about the alignment of the memory region.
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180801133444.11269-4-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We can assign and verify the slot before realizing and trying to plug.
reading/writing the slot property should never fail, so let's reduce
error handling a bit by using &error_abort.
To do this during pre_plug, add and use (x86, ppc) pc_dimm_pre_plug().
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Eric Auger <eric.auger@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180801133444.11269-2-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Commit 848a1cc1e (hw/acpi-build: build SRAT memory affinity structures for DIMM devices)
broke the first dimm hotplug in following cases:
1: there is no coldplugged dimm in the last numa node
but there is a coldplugged dimm in another node
-m 4096,slots=4,maxmem=32G \
-object memory-backend-ram,id=m0,size=2G \
-device pc-dimm,memdev=m0,node=0 \
-numa node,nodeid=0 \
-numa node,nodeid=1
2: if order of dimms on CLI is:
1st plugged dimm in node1
2nd plugged dimm in node0
-m 4096,slots=4,maxmem=32G \
-object memory-backend-ram,size=2G,id=m0 \
-device pc-dimm,memdev=m0,node=1 \
-object memory-backend-ram,id=m1,size=2G \
-device pc-dimm,memdev=m1,node=0 \
-numa node,nodeid=0 \
-numa node,nodeid=1
(qemu) object_add memory-backend-ram,id=m2,size=1G
(qemu) device_add pc-dimm,memdev=m2,node=0
the first DIMM hotplug to any node except the last one
fails (Windows is unable to online it).
Length reduction of stub hotplug memory SRAT entry,
fixes issue for some reason.
RHBZ: 1609234
Signed-off-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The multiboot code parses the initrd_filename twice, first to count how
many entries there are, and second to process each entry. This changes
the first loop to store the parse module names in a list, and the second
loop can now use these names. This avoids having to pass NULL to the
get_opt_value() method which means it can safely assume a non-NULL param.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20180514171913.17664-3-berrange@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Tested-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The logic for parsing the multiboot initrd modules was messed up in
commit 950c4e6c94
Author: Daniel P. Berrangé <berrange@redhat.com>
Date: Mon Apr 16 12:17:43 2018 +0100
opts: don't silently truncate long option values
Causing the length to be undercounter, and the number of modules over
counted. It also passes NULL to get_opt_value() which was not robust
at accepting a NULL value.
Signed-off-by: Daniel P. Berrangé <berrange@redhat.com>
Message-Id: <20180514171913.17664-2-berrange@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Tested-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Hyper-V identifies vCPUs by Virtual Processor (VP) index which can be
queried by the guest via HV_X64_MSR_VP_INDEX msr. It is defined by the
spec as a sequential number which can't exceed the maximum number of
vCPUs per VM.
It has to be owned by QEMU in order to preserve it across migration.
However, the initial implementation in KVM didn't allow to set this
msr, and KVM used its own notion of VP index. Fortunately, the way
vCPUs are created in QEMU/KVM makes it likely that the KVM value is
equal to QEMU cpu_index.
So choose cpu_index as the value for vp_index, and push that to KVM on
kernels that support setting the msr. On older ones that don't, query
the kernel value and assert that it's in sync with QEMU.
Besides, since handling errors from vCPU init at hotplug time is
impossible, disable vCPU hotplug.
This patch also introduces accessor functions to encapsulate the mapping
between a vCPU and its vp_index.
Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Message-Id: <20180702134156.13404-3-rkagan@virtuozzo.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
It eases code review, unit is explicit.
Patch generated using:
$ git grep -E '[<>][<>]=? ?[1-5]0' hw/ include/hw/
and modified manually.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Let's start to use "info pic" just like other platforms. For now we
keep the command for a while so that old users can know what is the new
command to use.
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20171229073104.3810-6-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This include both userspace and in-kernel ioapic. Note that the numbers
can be inaccurate for kvm-ioapic. One reason is the same with
kvm-i8259, that when irqfd is used, irqs can be delivered all inside
kernel without our notice. Meanwhile, kvm-ioapic is specially treated
when irq numbers <ISA_NUM_IRQS, those irqs will be delivered in kernel
too via kvm-i8259 (please refer to kvm_pc_gsi_handler).
Signed-off-by: Peter Xu <peterx@redhat.com>
Message-Id: <20171229073104.3810-5-peterx@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Let's try to reduce error handling a bit. In the plug/unplug case, the
device was realized and therefore we can assume that getting access to
the memory region will not fail.
For get_vmstate_memory_region() this is already handled that way.
Document both cases.
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: David Hildenbrand <david@redhat.com>
Message-Id: <20180619134141.29478-13-david@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
We support up to 6 levels, but those are encoded as 10b according to the
AMD IOMMU spec (chapter 3.3.1, Extended Feature Register).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Counting from the IVHD ID field to the all-devices entry, we have 28
bytes, not 36.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The oldest machine type which is still used in a still maintained distro
is a pc-0.12 based machine type in RHEL6, so everything that is older
than pc-0.12 should not be used anymore. Thus let's deprecate pc-0.10
and pc-0.11 so that we can finally remove them in a future release.
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <1529917512-10528-1-git-send-email-thuth@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Add support for multiple IOMMU indexes to the IOMMU notifier APIs.
When initializing a notifier with iommu_notifier_init(), the caller
must pass the IOMMU index that it is interested in. When a change
happens, the IOMMU implementation must pass
memory_region_notify_iommu() the IOMMU index that has changed and
that notifiers must be called for.
IOMMUs which support only a single index don't need to change.
Callers which only really support working with IOMMUs with a single
index can use the result of passing MEMTXATTRS_UNSPECIFIED to
memory_region_iommu_attrs_to_index().
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-id: 20180604152941.20374-3-peter.maydell@linaro.org
A link property can be set during creation, with
object_property_add_link() and later with object_property_set_link().
add_link() doesn't add a reference to the target object, while
set_link() does.
Furthemore, OBJ_PROP_LINK_UNREF_ON_RELEASE flags, set during add_link,
says whether a reference must be released when the property is destroyed.
This can lead to leaks if the property was later set_link(), as the
added reference is never released.
Instead, rename OBJ_PROP_LINK_UNREF_ON_RELEASE to OBJ_PROP_LINK_STRONG
and use that has an indication on how the link handle reference
management in set_link().
Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Message-id: 20180531195119.22021-3-marcandre.lureau@redhat.com
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Replace the "nvdimm-cap" option which took numeric arguments such as "2"
with a more user friendly "nvdimm-persistence" option which takes symbolic
arguments "cpu" or "mem-ctrl".
Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Suggested-by: Michael S. Tsirkin <mst@redhat.com>
Suggested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
acpi, vhost, misc: fixes, features
vDPA support, fix to vhost blk RO bit handling, some include path
cleanups, NFIT ACPI table.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
# gpg: Signature made Fri 01 Jun 2018 17:25:19 BST
# gpg: using RSA key 281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg: aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17 0970 C350 3912 AFBE 8E67
# Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA 8A0D 281F 0DB8 D28D 5469
* remotes/mst/tags/for_upstream: (31 commits)
vhost-blk: turn on pre-defined RO feature bit
ACPI testing: test NFIT platform capabilities
nvdimm, acpi: support NFIT platform capabilities
tests/.gitignore: add entry for generated file
arch_init: sort architectures
ui: use local path for local headers
qga: use local path for local headers
colo: use local path for local headers
migration: use local path for local headers
usb: use local path for local headers
sd: fix up include
vhost-scsi: drop an unused include
ppc: use local path for local headers
rocker: drop an unused include
e1000e: use local path for local headers
ioapic: fix up includes
ide: use local path for local headers
display: use local path for local headers
trace: use local path for local headers
migration: drop an unused include
...
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
QEMU 3.0 enables strict check for compression & decompression to
make the migration more robust, that depends on the source to fix
the internal design which triggers the unexpected error conditions
To make it work for migrating old version QEMU to 2.13 QEMU, we
introduce this parameter to disable the error check on the
destination which is the default behavior of the machine type
which is older than 2.13, alternately, the strict check can be
enabled explicitly as followings:
-M pc-q35-2.11 -global migration.decompress-error-check=true
Signed-off-by: Xiao Guangrong <xiaoguangrong@tencent.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
