QEMU must be careful when loading device state off migration streams to
prevent a malicious source from exploiting the emulator. Overdoing these
checks has the side effect of allowing a guest to "pin itself" in cloud
environments by messing with state which is entirely in its control.
Similarly to what f3081539 achieved in usb_device_post_load(), this
commit removes such a check from virtio_load(). Worth noting, the result
of a load without this check is the same as if a guest enables a VQ with
invalid indexes to begin with. That is, the virtual device is set in a
broken state (by the datapath handler) and must be reset.
Signed-off-by: Felipe Franciosi <felipe@nutanix.com>
Message-Id: <20201028134643.110698-1-felipe@nutanix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Virtqueue has split and packed, so before setting inflight,
you need to inform the back-end virtqueue format.
Signed-off-by: Jin Yu <jin.yu@intel.com>
Message-Id: <20200910134851.7817-1-jin.yu@intel.com>
Acked-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The first loop in vhost_get_log_size() computes the size of the dirty log
bitmap so that it allows to track changes in the entire guest memory, in
terms of GPA.
When not using a vIOMMU, the address of the vring's used structure,
vq->used_phys, is a GPA. It is thus already covered by the first loop.
When using a vIOMMU, vq->used_phys is a GIOVA that will be translated
to an HVA when the vhost backend needs to update the used structure. It
will log the corresponding GPAs into the bitmap but it certainly won't
log the GIOVA.
So in any case, vq->used_phys shouldn't be explicitly used to size the
bitmap. Drop the second loop.
This fixes a crash of the source when migrating a guest using in-kernel
vhost-net and iommu_platform=on on POWER, because DMA regions are put
over 0x800000000000000ULL. The resulting insanely huge log size causes
g_malloc0() to abort.
BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1879349
Signed-off-by: Greg Kurz <groug@kaod.org>
Message-Id: <160208823418.29027.15172801181796272300.stgit@bahia.lan>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Fix uninitialized value issues reported by Coverity:
Field 'msg.reserved' is uninitialized when calling write().
Fixes: a5bd05800f ("vhost-vdpa: batch updating IOTLB mappings")
Reported-by: Coverity (CID 1432864: UNINIT)
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20201028154004.776760-1-philmd@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
vhost IOTLB API uses read()/write() to exchange iotlb messages with
the kernel module.
The QEMU implementation expects a non-blocking fd, indeed commit
c471ad0e9b ("vhost_net: device IOTLB support") set it for vhost-net.
Without this patch, if we enable iommu for the vhost-vsock device,
QEMU can hang when exchanging IOTLB messages.
As commit 894022e616 ("net: check if the file descriptor is valid
before using it") did for tap, let's use qemu_try_set_nonblock()
when fd is provided by the user.
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20201029144849.70958-1-sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
cur_mon really needs to be coroutine-local as soon as we move monitor
command handlers to coroutines and let them yield. As a first step, just
remove all direct accesses to cur_mon so that we can implement this in
the getter function later.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Message-Id: <20201005155855.256490-4-kwolf@redhat.com>
Reviewed-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Only qemu-system-FOO and qemu-storage-daemon provide QMP
monitors, therefore such declarations and definitions are
irrelevant for user-mode emulation.
Restricting the memory commands to machine.json pulls less
QAPI-generated code into user-mode.
Acked-by: Igor Mammedov <imammedo@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20200913195348.1064154-7-philmd@redhat.com>
[Commit message tweaked]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Only qemu-system-FOO and qemu-storage-daemon provide QMP
monitors, therefore such declarations and definitions are
irrelevant for user-mode emulation.
Restricting the balloon-related commands to machine.json pulls less
QAPI-generated code into user-mode.
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Markus Armbruster <armbru@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-Id: <20200913195348.1064154-4-philmd@redhat.com>
[Commit message tweaked]
Signed-off-by: Markus Armbruster <armbru@redhat.com>
If error occurs while processing the virtio request we should call
'virtqueue_detach_element' to detach the element from the virtqueue
before free the elem.
Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20200813165125.59928-1-liq3ea@163.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Fixes: 5f503cd9f3 ("virtio-pmem: add virtio device")
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Current the 'virtio_set_features' only update the 'MemorRegionCaches'
when the 'virtio_set_features_nocheck' return '0' which means it is
not bad features. However the guest can still trigger the access of the
used vring after set bad features. In this situation it will cause assert
failure in 'ADDRESS_SPACE_ST_CACHED'.
Buglink: https://bugs.launchpad.net/qemu/+bug/1890333
Fixes: db812c4073 ("virtio: update MemoryRegionCaches when guest negotiates features")
Reported-by: Alexander Bulekov <alxndr@bu.edu>
Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20200919082706.6703-1-liq3ea@163.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Commit 9b3a35ec82 ("virtio: verify that legacy support is not
accidentally on") added a safety check that requires to set
'disable-legacy=on' on vhost-user-vsock-pci device:
$ ./qemu-system-x86_64 ... \
-chardev socket,id=char0,reconnect=0,path=/tmp/vhost4.socket \
-device vhost-user-vsock-pci,chardev=char0
qemu-system-x86_64: -device vhost-user-vsock-pci,chardev=char0:
device is modern-only, use disable-legacy=on
virtio-vsock was introduced after the release of VIRTIO 1.0
specifications, so it should be 'modern-only'.
This patch forces virtio version 1 and removes the 'transitional_name'
property, as done for vhost-vsock-pci, removing the need to specify
'disable-legacy=on' on vhost-user-vsock-pci device.
Cc: qemu-stable@nongnu.org
Suggested-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20200921122506.82515-4-sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Commit 9b3a35ec82 ("virtio: verify that legacy support is not
accidentally on") added a safety check that requires to set
'disable-legacy=on' on vhost-vsock-pci device:
$ ./qemu-system-x86_64 ... -device vhost-vsock-pci,guest-cid=5
qemu-system-x86_64: -device vhost-vsock-pci,guest-cid=5:
device is modern-only, use disable-legacy=on
virtio-vsock was introduced after the release of VIRTIO 1.0
specifications, so it should be 'modern-only'.
In addition Cornelia verified that forcing a legacy mode on
vhost-vsock-pci device using x86-64 host and s390x guest, so with
different endianness, produces strange behaviours.
This patch forces virtio version 1 and removes the 'transitional_name'
property removing the need to specify 'disable-legacy=on' on
vhost-vsock-pci device.
To avoid migration issues, we force virtio version 1 only when
legacy check is enabled in the new machine types (>= 5.1).
As the transitional device name is not commonly used, we do not
provide compatibility handling for it.
Cc: qemu-stable@nongnu.org
Reported-by: Qian Cai <caiqian@redhat.com>
Reported-by: Qinghua Cheng <qcheng@redhat.com>
Buglink: https://bugzilla.redhat.com/show_bug.cgi?id=1868449
Suggested-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20200921122506.82515-3-sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Commit 9b3a35ec82 ("virtio: verify that legacy support is not accidentally
on") added a check that returns an error if legacy support is on, but the
device does not support legacy.
Unfortunately some devices were wrongly declared legacy capable even if
they were not (e.g vhost-vsock).
To avoid migration issues, we add a virtio-device property
(x-disable-legacy-check) to skip the legacy error, printing a warning
instead, for machine types < 5.1.
Cc: qemu-stable@nongnu.org
Fixes: 9b3a35ec82 ("virtio: verify that legacy support is not accidentally on")
Suggested-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Suggested-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Message-Id: <20200921122506.82515-2-sgarzare@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Add trace functions in vhost-vdpa.c.
All traces from this file can be enabled with '-trace vhost_vdpa*'.
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20200925091055.186023-3-lvivier@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Qemu fails with below error when trying to run with virtio pmem:
(qemu) qemu-system-x86_64: -device virtio-pmem-pci,memdev=mem1,id=nv1:
device is modern-only, use disable-legacy=on
This patch fixes this by forcing virtio 1 with virtio-pmem.
fixes: adf0748a49 ("virtio-pci: Proxy for virtio-pmem")
Signed-off-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Message-Id: <20200925102251.7216-1-pankaj.gupta.linux@gmail.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Commit 9b3a35ec82 ("virtio: verify that legacy support is not
accidentally on") added a safety check that requires to set
'disable-legacy=on' on virtio-iommu-pci:
qemu-system-aarch64: -device virtio-iommu-pci: device is modern-only,
use disable-legacy=on
virtio-iommu was introduced after the release of VIRTIO 1.0
specifications, so it should be 'modern-only'.
This patch forces virtio version 1 and removes the 'transitional_name'
property removing the need to specify 'disable-legacy=on' on
virtio-iommu-pci device.
Cc: qemu-stable@nongnu.org
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <20200908193309.20569-3-eric.auger@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
If realize fails, domains and endpoints trees may be NULL. On
unrealize(), this produces assertions:
"GLib: g_tree_destroy: assertion 'tree != NULL' failed"
Check that the trees are non NULL before destroying them.
Cc: qemu-stable@nongnu.org
Signed-off-by: Eric Auger <eric.auger@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <20200908193309.20569-2-eric.auger@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
If the vhost-user-blk daemon provides only one virtqueue, but device was
added with several queues, then QEMU will send more VHOST-USER command
than expected by daemon side. The vhost_virtqueue_start() routine
handles such case by checking the return value from the
virtio_queue_get_desc_addr() function call. Add the same check to the
vhost_dev_set_log() routine.
Signed-off-by: Dima Stepanov <dimastep@yandex-team.ru>
Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Message-Id: <6232946d5af09e9775076645909964a6539b8ab5.1599813294.git.dimastep@yandex-team.ru>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
vhost-user devices can get a disconnect in the middle of the VHOST-USER
handshake on the migration start. If disconnect event happened right
before sending next VHOST-USER command, then the vhost_dev_set_log()
call in the vhost_migration_log() function will return error. This error
will lead to the assert() and close the QEMU migration source process.
For the vhost-user devices the disconnect event should not break the
migration process, because:
- the device will be in the stopped state, so it will not be changed
during migration
- if reconnect will be made the migration log will be reinitialized as
part of reconnect/init process:
#0 vhost_log_global_start (listener=0x563989cf7be0)
at hw/virtio/vhost.c:920
#1 0x000056398603d8bc in listener_add_address_space (listener=0x563989cf7be0,
as=0x563986ea4340 <address_space_memory>)
at softmmu/memory.c:2664
#2 0x000056398603dd30 in memory_listener_register (listener=0x563989cf7be0,
as=0x563986ea4340 <address_space_memory>)
at softmmu/memory.c:2740
#3 0x0000563985fd6956 in vhost_dev_init (hdev=0x563989cf7bd8,
opaque=0x563989cf7e30, backend_type=VHOST_BACKEND_TYPE_USER,
busyloop_timeout=0)
at hw/virtio/vhost.c:1385
#4 0x0000563985f7d0b8 in vhost_user_blk_connect (dev=0x563989cf7990)
at hw/block/vhost-user-blk.c:315
#5 0x0000563985f7d3f6 in vhost_user_blk_event (opaque=0x563989cf7990,
event=CHR_EVENT_OPENED)
at hw/block/vhost-user-blk.c:379
Update the vhost-user-blk device with the internal started_vu field which
will be used for initialization (vhost_user_blk_start) and clean up
(vhost_user_blk_stop). This additional flag in the VhostUserBlk structure
will be used to track whether the device really needs to be stopped and
cleaned up on a vhost-user level.
The disconnect event will set the overall VHOST device (not vhost-user) to
the stopped state, so it can be used by the general vhost_migration_log
routine.
Such approach could be propogated to the other vhost-user devices, but
better idea is just to make the same connect/disconnect code for all the
vhost-user devices.
This migration issue was slightly discussed earlier:
- https://lists.gnu.org/archive/html/qemu-devel/2020-05/msg01509.html
- https://lists.gnu.org/archive/html/qemu-devel/2020-05/msg05241.html
Signed-off-by: Dima Stepanov <dimastep@yandex-team.ru>
Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Message-Id: <9fbfba06791a87813fcee3e2315f0b904cc6789a.1599813294.git.dimastep@yandex-team.ru>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
If error occurs while processing the virtio request we should call
'virtqueue_detach_element' to detach the element from the virtqueue
before free the elem.
Signed-off-by: Li Qiang <liq3ea@163.com>
Message-Id: <20200816142245.17556-1-liq3ea@163.com>
Fixes: 910b25766b ("virtio-mem: Paravirtualized memory hot(un)plug")
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
To speed up the memory mapping updating between vhost-vDPA and vDPA
device driver, this patch passes the IOTLB batching flags via IOTLB
API. Two new flags was introduced, VHOST_IOTLB_BATCH_BEGIN is a hint
that a bathced IOTLB updating may be initiated from the
userspace. VHOST_IOTLB_BATCH_END is a hint that userspace has finished
the updating:
VHOST_IOTLB_BATCH_BEGIN
VHOST_IOTLB_UPDATE/VHOST_IOTLB_INVALIDATE
...
VHOST_IOTLB_BATCH_END
Vhost-vDPA can then know that all mappings has been set and can do
optimization like passing all the mappings to the vDPA device driver.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20200907104903.31551-4-jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
This patch tries to switch to use new kernel IOTLB format V2. Previous
version may have inconsistent ABI between 32bit and 64bit machines
because of the hole after type field. Refer kernel commit
("429711aec282 vhost: switch to use new message format") for more
information.
To enable this feature, qemu need to use a new ioctl
VHOST_SET_BACKEND_FEATURE with VHOST_BACKEND_F_IOTLB_MSG_V2 bit. A new
vhost setting backend features ops was introduced. And when we try to
set features for vhost dev, we will examine the support of new IOTLB
format and enable it. This process is total transparent to guest,
which means we can have different IOTLB message type in src and dst
during migration.
The conversion of IOTLB message is straightforward, just check the
type and behave accordingly.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Message-Id: <20200907104903.31551-3-jasowang@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
in vhost_vdpa_listener_region_del(), try_unmap is always true and so,
vhost_vdpa_dma_unmap() is always called. We can remove the variable
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Li Qiang <liq3ea@gmail.com>
Message-Id: <20200920152024.860172-1-lvivier@redhat.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
If g_malloc fails, the application will be terminated.
No need to check the return value of g_malloc.
Signed-off-by: Li Qiang <liq3ea@163.com>
Reviewed-by: Laurent Vivier <lvivier@redhat.com>
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20200819144309.67579-1-liq3ea@163.com>
Signed-off-by: Laurent Vivier <laurent@vivier.eu>
clang's C11 atomic_fetch_*() functions only take a C11 atomic type
pointer argument. QEMU uses direct types (int, etc) and this causes a
compiler error when a QEMU code calls these functions in a source file
that also included <stdatomic.h> via a system header file:
$ CC=clang CXX=clang++ ./configure ... && make
../util/async.c:79:17: error: address argument to atomic operation must be a pointer to _Atomic type ('unsigned int *' invalid)
Avoid using atomic_*() names in QEMU's atomic.h since that namespace is
used by <stdatomic.h>. Prefix QEMU's APIs with 'q' so that atomic.h
and <stdatomic.h> can co-exist. I checked /usr/include on my machine and
searched GitHub for existing "qatomic_" users but there seem to be none.
This patch was generated using:
$ git grep -h -o '\<atomic\(64\)\?_[a-z0-9_]\+' include/qemu/atomic.h | \
sort -u >/tmp/changed_identifiers
$ for identifier in $(</tmp/changed_identifiers); do
sed -i "s%\<$identifier\>%q$identifier%g" \
$(git grep -I -l "\<$identifier\>")
done
I manually fixed line-wrap issues and misaligned rST tables.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200923105646.47864-1-stefanha@redhat.com>
A number of iov_discard_front/back() operations are made by
virtio-crypto. The elem->in/out_sg iovec arrays are modified by these
operations, resulting virtqueue_unmap_sg() calls on different addresses
than were originally mapped.
This is problematic because dirty memory may not be logged correctly,
MemoryRegion refcounts may be leaked, and the non-RAM bounce buffer can
be leaked.
Take a copy of the elem->in/out_sg arrays so that the originals are
preserved. The iov_discard_undo() API could be used instead (with better
performance) but requires careful auditing of the code, so do the simple
thing instead.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Li Qiang <liq3ea@gmail.com>
Message-Id: <20200917094455.822379-4-stefanha@redhat.com>
Some trace points are attributed to the wrong source file. Happens
when we neglect to update trace-events for code motion, or add events
in the wrong place, or misspell the file name.
Clean up with help of scripts/cleanup-trace-events.pl. Funnies
requiring manual post-processing:
* accel/tcg/cputlb.c trace points are in trace-events.
* block.c and blockdev.c trace points are in block/trace-events.
* hw/block/nvme.c uses the preprocessor to hide its trace point use
from cleanup-trace-events.pl.
* hw/tpm/tpm_spapr.c uses pseudo trace point tpm_spapr_show_buffer to
guard debug code.
* include/hw/xen/xen_common.h trace points are in hw/xen/trace-events.
* linux-user/trace-events abbreviates a tedious list of filenames to
*/signal.c.
* net/colo-compare and net/filter-rewriter.c use pseudo trace points
colo_compare_miscompare and colo_filter_rewriter_debug to guard
debug code.
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200806141334.3646302-5-armbru@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Some typedefs and macros are defined after the type check macros.
This makes it difficult to automatically replace their
definitions with OBJECT_DECLARE_TYPE.
Patch generated using:
$ ./scripts/codeconverter/converter.py -i \
--pattern=QOMStructTypedefSplit $(git grep -l '' -- '*.[ch]')
which will split "typdef struct { ... } TypedefName"
declarations.
Followed by:
$ ./scripts/codeconverter/converter.py -i --pattern=MoveSymbols \
$(git grep -l '' -- '*.[ch]')
which will:
- move the typedefs and #defines above the type check macros
- add missing #include "qom/object.h" lines if necessary
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20200831210740.126168-9-ehabkost@redhat.com>
Reviewed-by: Juan Quintela <quintela@redhat.com>
Message-Id: <20200831210740.126168-10-ehabkost@redhat.com>
Message-Id: <20200831210740.126168-11-ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Both VirtioPCIBusClass and VirtioCcwBusClass are typedefs of
VirtioBusClass, but set .class_size in the TypeInfo anyway
to be safe if that changes in the future.
Reported-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Message-Id: <20200824122051.99432-1-cohuck@redhat.com>
Automatically size the number of request virtqueues to match the number
of vCPUs. This ensures that completion interrupts are handled on the
same vCPU that submitted the request. No IPI is necessary to complete
an I/O request and performance is improved. The maximum number of MSI-X
vectors and virtqueues limit are respected.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Message-Id: <20200818143348.310613-8-stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Automatically size the number of virtio-blk-pci request virtqueues to
match the number of vCPUs. Other transports continue to default to 1
request virtqueue.
A 1:1 virtqueue:vCPU mapping ensures that completion interrupts are
handled on the same vCPU that submitted the request. No IPI is
necessary to complete an I/O request and performance is improved. The
maximum number of MSI-X vectors and virtqueues limit are respected.
Performance improves from 78k to 104k IOPS on a 32 vCPU guest with 101
virtio-blk-pci devices (ioengine=libaio, iodepth=1, bs=4k, rw=randread
with NVMe storage).
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Message-Id: <20200818143348.310613-7-stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Automatically size the number of virtio-scsi-pci, vhost-scsi-pci, and
vhost-user-scsi-pci request virtqueues to match the number of vCPUs.
Other transports continue to default to 1 request virtqueue.
A 1:1 virtqueue:vCPU mapping ensures that completion interrupts are
handled on the same vCPU that submitted the request. No IPI is
necessary to complete an I/O request and performance is improved. The
maximum number of MSI-X vectors and virtqueues limit are respected.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-Id: <20200818143348.310613-6-stefanha@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
The event and control virtqueues are always present, regardless of the
multi-queue configuration. Define a constant so that virtqueue number
calculations are easier to read.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Reviewed-by: Raphael Norwitz <raphael.norwitz@nutanix.com>
Message-Id: <20200818143348.310613-5-stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Multi-queue devices achieve the best performance when each vCPU has a
dedicated queue. This ensures that virtqueue used notifications are
handled on the same vCPU that submitted virtqueue buffers. When another
vCPU handles the the notification an IPI will be necessary to wake the
submission vCPU and this incurs a performance overhead.
Provide a helper function that virtio-pci devices will use in later
patches to automatically select the optimal number of queues.
The function handles guests with large numbers of CPUs by limiting the
number of queues to fit within the following constraints:
1. The maximum number of MSI-X vectors.
2. The maximum number of virtqueues.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Message-Id: <20200818143348.310613-4-stefanha@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Meson doesn't enjoy the same flexibility we have with Make in choosing
the include path. In particular the tracing headers are using
$(build_root)/$(<D).
In order to keep the include directives unchanged,
the simplest solution is to generate headers with patterns like
"trace/trace-audio.h" and place forwarding headers in the source tree
such that for example "audio/trace.h" includes "trace/trace-audio.h".
This patch is too ugly to be applied to the Makefiles now. It's only
a way to separate the changes to the tracing header files from the
Meson rewrite of the tracing logic.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This likely affects other, less popular host architectures as well.
Less common host architectures under linux get QEMU_VMALLOC_ALIGN (from
which VIRTIO_MEM_MIN_BLOCK_SIZE is derived) define to a variable of
type uintptr, which isn't compatible with the format specifier used to
print a user message. Since this particular usage of the underlying data
seems unique to this file, the simple fix is to just cast
QEMU_VMALLOC_ALIGN to uint32_t, which corresponds to the format specifier
used.
Signed-off-by: Bruce Rogers <brogers@suse.com>
Message-Id: <20200730130519.168475-1-brogers@suse.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Pankaj Gupta <pankaj.gupta.linux@gmail.com>
We should use the index passed by the caller instead of the queue_sel
when checking the enablement of a specific virtqueue.
This is reported in https://bugzilla.redhat.com/show_bug.cgi?id=1702608
Fixes: f19bcdfedd ("virtio-pci: implement queue_enabled method")
Signed-off-by: Yuri Benditovich <yuri.benditovich@daynix.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
In legacy mode, virtio_pci_queue_enabled() falls back to
virtio_queue_enabled() to know if the queue is enabled.
But virtio_queue_enabled() calls again virtio_pci_queue_enabled()
if k->queue_enabled is set. This ends in a crash after a stack
overflow.
The problem can be reproduced with
"-device virtio-net-pci,disable-legacy=off,disable-modern=true
-net tap,vhost=on"
And a look to the backtrace is very explicit:
...
#4 0x000000010029a438 in virtio_queue_enabled ()
#5 0x0000000100497a9c in virtio_pci_queue_enabled ()
...
#130902 0x000000010029a460 in virtio_queue_enabled ()
#130903 0x0000000100497a9c in virtio_pci_queue_enabled ()
#130904 0x000000010029a460 in virtio_queue_enabled ()
#130905 0x0000000100454a20 in vhost_net_start ()
...
This patch fixes the problem by introducing a new function
for the legacy case and calls it from virtio_pci_queue_enabled().
It also calls it from virtio_queue_enabled() to avoid code duplication.
Fixes: f19bcdfedd ("virtio-pci: implement queue_enabled method")
Cc: Jason Wang <jasowang@redhat.com>
Cc: Cindy Lu <lulu@redhat.com>
CC: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Laurent Vivier <lvivier@redhat.com>
Message-Id: <20200727153319.43716-1-lvivier@redhat.com>
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
In the function vhost_vdpa_dma_map/unmap, The struct msg was not initialized all its fields.
Signed-off-by: Cindy Lu <lulu@redhat.com>
Message-Id: <20200710064642.24505-1-lulu@redhat.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Li Qiang <liq3ea@gmail.com>
Cc: qemu-stable@nongnu.org
Reviewed-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
