Age | Commit message (Collapse) | Author |
|
|
|
On Windows os_handle is of type void*, can't use Into::into to cast to
i64. Use as i64 instead.
Test: launch_cvd
Link: https://crrev.com/c/3448217
Change-Id: I7fe44dbadf5214ff9bfd81482f5b598091a8f692
|
|
* changes:
rutabaga_gfx: change os_handle type
rutabaga_gfx: stream_renderer_create_blob and related functions
rutabaga_gfx: get component from context type
|
|
https://r.android.com/1975268 attempted to do this but would be lost the
next time cargo2android.py is run. Adding the option to
cargo2android.json will make it stick.
Bug: 218105368
Bug: 218218997
Test: Ran cargo2android.py
Change-Id: I629feb8f454fd1ad2e02559d6fdbfeebeba35a91
|
|
Windows HANDLE is defined as void* which is incompatible with current
os_handle type i32. Change that to i64.
TEST=launch_cvd --gpu_mode=gfxstream
BUG=b:217977329
Change-Id: I78c6c4c0d7573773ed530d8987b932438222144f
|
|
This CL adds stream_renderer_create_blob and export_blob
support.
BUG=b:208516032
TEST=run gfxstream
Change-Id: I312e266df04e0291ecefce05d3a63c527e6d87af
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3429702
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Auto-Submit: Gurchetan Singh <gurchetansingh@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Gurchetan Singh <gurchetansingh@chromium.org>
|
|
The component type information is useful from time to time.
BUG=b:208516032
TEST=run gfxstream
Change-Id: I16be012064f2c764f021ae52c09c2371f2a29ccc
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3429701
Reviewed-by: Kaiyi Li <kaiyili@google.com>
Auto-Submit: Gurchetan Singh <gurchetansingh@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Commit-Queue: Dennis Kempin <denniskempin@google.com>
|
|
These tests are buggy unless run on kernels with all the necessary
io_uring fixes. Until these tests are stabilized upstream, disable them
for host TEST_MAPPING.
Bug: 218105368
Bug: 218218997
Change-Id: I5da18616bf58ce9a1b6ad7039602e0edbf69d004
|
|
Bug: 211704107
Bug: 215517095
Change-Id: I8a4fb850353725c2431e217c91106085d44a6e6e
|
|
This should have been updated with the pKVM ABI change in
https://crrev.com/c/3330204, as protected mode is now selected when
creating the VM, and pVM firmmware is optional.
BUG=b:209794844
Change-Id: I2850b4c2ef523a15b8215df070eb9da066a67cb5
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3420330
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Andrew Walbran <qwandor@google.com>
|
|
BUG=b:211704107
TEST=tools/dev_container tools/run_tests
TEST=tools/dev_container tools/run_tests --target=vm:aarch64
Change-Id: I383be89becefe300d9dc94b7d67d35269c628a39
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3412772
Reviewed-by: Dmitry Torokhov <dtor@chromium.org>
Auto-Submit: Andrew Walbran <qwandor@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Andrew Walbran <qwandor@google.com>
|
|
BUG=b:211704107
TEST=Ran VMs with Android vm tool on Oriole
Change-Id: I3525cb03ab325ac35aea8f318faa4ebab8250b83
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3395416
Reviewed-by: Dmitry Torokhov <dtor@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Andrew Walbran <qwandor@google.com>
|
|
It's a simple enum, so it should be Copy.
TEST=tools/dev_container tools/run_tests
TEST=tools/dev_container tools/run_tests --target=vm:aarch64
Change-Id: Ieeacedb10fa6a93d6cdd9878097c66aa936f8e30
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3420329
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Andrew Walbran <qwandor@google.com>
|
|
Add socket to allow external process to directly control the balloon
device via the balloon_control API. When the option is used, the vm
control socket cannot control the balloon.
BUG=b:213962590
TEST=manual testing with crrev.com/c/3394436
Change-Id: I3feea811e39a5b09afcc44420fc644935fdc6ebf
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3394441
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: David Stevens <stevensd@chromium.org>
|
|
Add a crate containing an API for controlling the balloon. This is done
by reusing the API between the control socket and the balloon device.
BUG=b:213962590
TEST=compiles
Change-Id: I5d89d5ebee55162d28ba45ca2c49b7083561b916
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3394440
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: David Stevens <stevensd@chromium.org>
|
|
Fix a few compilation warnings in our tests:
* The PCI device had an unused argument without a leading underscore in
the name ;
* The virtio queue is dereferencing null pointers, which is UB albeit
technically ok in this case (bindgen generates similar tests too [1]).
[1] https://github.com/rust-lang/rust-bindgen/issues/1651
BUG=None
TEST=cargo test in devices/ does not show these warnings anymore.
Change-Id: Id272b5381f80bb72d96839a5a6da8bb0c644502d
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3418623
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Commit-Queue: Alexandre Courbot <acourbot@chromium.org>
|
|
Otherwise we end up with this: https://crrev.com/c/3422185
BUG=None
TEST=None
Change-Id: I8abd0e3f4465e9ae2ae34630dde5a3b15e190b09
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3421734
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
crosvm seems to be adding an extra mptable entry for irq0 that points to
a non-existent ioapic (with apic_id=0 where the ioapic's id is not 0).
The bad irq0 and valid irq0 entries are the first two listed when using
apic=debug and show_lapic=all kernel params:
```
[ 0.756044] Int: type 0, pol 0, trig 0, bus 01, IRQ 00, APIC ID 0, APIC INT 00
[ 0.764474] Int: type 0, pol 0, trig 0, bus 01, IRQ 00, APIC ID 5, APIC INT 00
```
If the bad irq0 entry exists, and if check_timer is called in io_apic.c
in the kernel, it can cause an invalid opcode exception in some kernels,
seemingly because it ends up calling find_irq_entry(-1, -1, 0) which
does a -1 index on the static "ioapics" struct in io_apic.c. It seems
like a kernel bug that such an index could happen, but this also seems
like a bad entry in mptables.
A similar irq entry exists in kvmtool, but it it's a local interrupt. If
this entry is adjusted to match then the invalid opcode kernel panic
stops.
BUG=b:211912415
TEST=ran linux image, booted fine
Change-Id: I125dd2458f86de65553577b8d1c4d1366d778de9
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3405332
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Colin Downs-Razouk <colindr@google.com>
|
|
The patch also adds files to skip building and testing crates on
windows. When we run
```
tools/windows/build_test.py --skip_file_name .windows_build_test_skip
```
the build/test succeeds without actually doing anything as build/test
for all crates is skipped by creating '.windows_build_test_skip'.
Bug: 213170957
Test: Ran script on downstream repo
Change-Id: Iebd2cea463ee722be4feaed88229e1fb5e9fd6c5
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3417918
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Vikram Auradkar <auradkar@google.com>
|
|
This should allow the bot to submit dry-runs to the CQ.
BUG=chromium:1290646
TEST=None
Change-Id: I44fc74c94129e7d136a161c1ba11445d7bf675c1
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3421730
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
The tool is added to ./tools/fmt which will be called during
./tools/presubmit as well as by Kokoro during testing.
This requires a new dev container version to bundle the mdformat
tool in the container.
Note: mdformat does not have any IDE integrations, but the prettier
plugin with prose-wrap enabled and a line length of 100 provides
almost identical results.
BUG=None
TEST=./tools/fmt --check
Change-Id: I0ae5659eff8555df7c85c70e62095a1e116b98da
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3416098
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dennis Kempin <denniskempin@google.com>
|
|
BUG=b:214104901
TEST=mdbook serve
Change-Id: I7039493212912cb698f74967abef228df278f4c7
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3399872
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dennis Kempin <denniskempin@google.com>
|
|
The latency reduces to 50-100ms max from over 1 second, when we overload
the system.
BUG=b:208138181
TEST=run stress-ng inside and outside VM.
Change-Id: I10a22807b47a1ed2dd181c2ddcc995eebef7f652
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3383936
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Vineeth Pillai <vineethrp@google.com>
|
|
The previous multifunction change removed this option entirely, but that
makes the transition difficult, since the caller and crosvm need to be
updated simultaneously. To make the changeover simpler, allow the
multifunction option but make it do nothing, since the PCI root code
will already do the right thing.
BUG=b:210795995
TEST=Run crosvm with --stub-pci-device with multifunction enabled
Change-Id: I5d378001d495ec54bd4c1869de796ba6a418f43a
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3421006
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Daniel Verkamp <dverkamp@chromium.org>
|
|
This is an experiment to figure out the permissions needed by
crosvm-bot.
See https://crbug.com/1289780 for details.
BUG=chromium:1289780
TEST=None
Change-Id: Ic202532ceaa2b0d86f51c8670137bde2d8f16868
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3419296
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
Add an init-mem parameter that limits how much memory the VM can use on
startup. If set, the balloon is inflated on startup to (mem - init-mem).
BUG=b:213962590
TEST=set param and verify balloon inflates on startup
Change-Id: I920bf9cfa26081ee544219406f8cf9827ff84bfa
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3394439
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: David Stevens <stevensd@chromium.org>
|
|
It is not compatible with pKVM and leads to RCU stalls on the host due
to the virtio_balloon thread getting stuck.
BUG=b:215517095
Change-Id: Ibd1c9db53bfa001e07ba6399ff50e9073476017d
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3412776
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Andrew Walbran <qwandor@google.com>
|
|
Do not map RAM to where the coreboot regions are.
Shift boot time GDT and IDT a bit to make way for coreboot region at
0..fff.
BUG=b:188011323
TEST=boot volteer-manatee
TEST=tast run rammus-arc-r arc.Boot.vm # ARCVM still boots.
TEST=tast run rammus-arc-r crostini.Basic.bullseye_stable
volteer-manatee memory map:
after:
localhost ~ # dmesg | grep e820
[ 0.000000] BIOS-e820: [mem 0x0000000000000000-0x000000000009fbff] usable
[ 0.000000] BIOS-e820: [mem 0x0000000000200000-0x00000000cfffffff] usable
[ 0.000000] BIOS-e820: [mem 0x00000000f4000000-0x00000000f7ffffff] reserved
[ 0.000000] BIOS-e820: [mem 0x0000000100000000-0x00000003f05fffff] usable
before:
localhost ~ # dmesg | grep e820
[ 0.000000] BIOS-e820: [mem 0x0000000000001000-0x000000000009fbff] usable
[ 0.000000] BIOS-e820: [mem 0x0000000000200000-0x000000005fffffff] usable
[ 0.000000] BIOS-e820: [mem 0x00000000f4000000-0x00000000f7ffffff] reserved
[ 0.000000] BIOS-e820: [mem 0x0000000100000000-0x0000000460600fff] usable
Change-Id: Ifa19988c444d79dc81eb77c59e5b5434abf883fb
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3405402
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Junichi Uekawa <uekawa@chromium.org>
|
|
BUG=None
TEST=build
Change-Id: Ibd101c10ccc9425c389bbf3d43a1d44e3ebea7f6
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3405401
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Junichi Uekawa <uekawa@chromium.org>
|
|
Rearrange the code that creates devices and starts the VM so that the
jail object is not destroyed while VM is running and also make sure we
kill the process when vm stops.
BUG=b:177267762
TEST=./tools/presubmit
Change-Id: Id35791e7264a52e34d2ddfac86425ad4b3c2d059
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3416101
Reviewed-by: Chia-I Wu <olv@google.com>
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dmitry Torokhov <dtor@chromium.org>
|
|
Now that resize_with() has stabilized and is available in version of
Rust we are using we can switch to it instead of implementing the same
by hand.
BUG=None
TEST=./tools/presubmit
Change-Id: I08b418ad898ecbc52c63bd7a47f6470af30c8a66
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3417961
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dmitry Torokhov <dtor@chromium.org>
|
|
The dry run merge is re-created every day and automatically
set to CQ+1. This allows us to check for bad crosvm changes
while we submit parts of the merge chain.
BUG=b:215741244
TEST=./tools/ci/simulate merge-into-chromeos.sh
Change-Id: I0773a99f9858962e9f25bebff1b233d455d33cdd
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3417508
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
Add an accept_with_timeout method to UnixSeqpacket and implement a few
basic traits for UnixSeqpacket.
BUG=b:213962590
TEST=cargo test
Change-Id: I1b8461e54aac2be31604213b252c15ce2195e33a
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3394438
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: David Stevens <stevensd@chromium.org>
|
|
This is a generalization of the existing --direct-mmio option with the
following improvements:
* Memory is mapped directly into the guest namespace rather than
handled via MMIO exits.
* The --file-backed-mapping option can be specified multiple times to
set up mappings backed by different files.
* Command line option format is extensible, allowing to add further
parameters in the future as needed.
* O_SYNC mapping is configurable from the command line, making this
useful for mapping both MMIO regions and regular system memory into
the VM.
One limitation that this new implementation brings is that mappings
need to be page-aligned (which isn't the case for --direct-mmio). I'm
not aware of existing users that require fine-granular file-backed
MMIO mappings though, so this is hopefully OK.
The existing --direct-mmio option code is left untouched, but will be
removed later after converting over existing usage.
BUG=b:184815519, b:188011323
TEST=unit tests for command line parsing, manual test to specify --file-backed-mapping and observe that the backing file content is accessible from the guest.
Change-Id: I86aee74d2032caaf9130569203d5749994a4413d
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3328602
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Reviewed-by: Junichi Uekawa <uekawa@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Mattias Nissler <mnissler@chromium.org>
|
|
The picture buffer size was computed from the size of the visible
rectangle, which is potentially incorrect: if the origin of the visible
rectangle is not (0, 0) then the buffer is going to be larger.
Fix this by using the provided coded width and height, which correspond
to the actual size of the buffer and not just its visible area.
BUG=b:161774071
TEST=Android Youtube decodes properly on zork-arc-r.
Change-Id: I80e15248f41d6202190456d2ab61f8f50d3b6ebb
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3412457
Reviewed-by: Chih-Yu Huang <akahuang@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: Keiichi Watanabe <keiichiw@chromium.org>
Reviewed-by: David Staessens <dstaessens@chromium.org>
Commit-Queue: Alexandre Courbot <acourbot@chromium.org>
|
|
Docs are scattered around, and README.chromeos isn't markdown. Merge to
CONTRIBUTING doc and update the relevant parts. Rename to
README.chromeos.md and make it point to the other doc.
BUG=None
TEST=read it.
Change-Id: Ib1df58e1a7c48d6faad71faffc9527da5f3218be
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3405403
Reviewed-by: Dennis Kempin <denniskempin@google.com>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Junichi Uekawa <uekawa@chromium.org>
|
|
Switching to anyhow allows us to get rid of the unwieldy error enum in
places where we do not care about error codes.
BUG=None
TEST=./tools/presubmit and run Parallels VM on CrOS
Change-Id: I4b9636801a7daa1d1289ce1bc4f9a92d47efaeb0
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3416093
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dmitry Torokhov <dtor@chromium.org>
|
|
Instead of having to adjust this after the fact, let's teach
create_base_minijail() handle this request.
BUG=None
TEST=./tools/presubmit
Change-Id: Iabfd583f1d198c243d7d073785066a343ceac94e
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3416094
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dmitry Torokhov <dtor@chromium.org>
|
|
This causes problems with repo and should only be set on the crosvm
repo.
BUG=None
TEST=None
Change-Id: Id63a60f9ccebf3f7785a1473d15d6a9f88f8cdd0
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3414497
Reviewed-by: Dmitry Torokhov <dtor@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
The container was pretty much untested. Now that vscode supports dev
containers via SSH I got to test this properly.
This provides a workable dev environment out of the box.
./tools/presubmit passes and
common extensions for rust, python and bash are added.
BUG=None
TEST=Open in vscode, re-open in dev container. Run ./tools/presubmit
Change-Id: I542f3d26c29c4051000e6ec8b81d77d297bcad7d
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3402447
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dennis Kempin <denniskempin@google.com>
|
|
Let's pass host's processor brand string to guests, so that lscpu and
/proc/cpuinfo do not fall back to printing numeric model numbers
but rather print vendor string, such as:
Intel(R) Core(TM) i3-10110U CPU @ 2.10GHz
or
AMD Ryzen 3 3250C 15W with Radeon Graphics
BUG=None
TEST=boot zork and hatch, examine lscpu in crostini
Change-Id: I7cd3ccd4a6328695cc180ee4c13d19d2e48f3def
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3410647
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Commit-Queue: Dmitry Torokhov <dtor@chromium.org>
|
|
The pages which are frequently used by the VM are likely not to be
unpinned. So an optimization is to skip the unpin scan for those pages
in the LRU unpin policy. The unpin_gen_threshold defines a threshold
number that, if a page cannot be unpinned in a period of
(unpin_gen_threshold* unpin_interval) seconds, then this page will be
marked as inactive. Those inactive pages will be scanned every
(unpin_gen_threshold* unpin_interval) seconds if there is no enough
active pages to unpin.
BUG=b:188481989
TEST=Boot a VM with coiommu lru unpin policy + pass through devices.
Change-Id: Ie020173097b6f4f925cafc121a802243ef65f165
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292941
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
Unpin is handled indepently with the coiommu frontend driver. To
support the DTT shrinker happened in coiommu, it needs a way to
park the unpin thread for a while in case unpin is also accessing
the DTT. When the shrink is done, frontend can unpark to make unpin
thread work again.
BUG=b:188481989
TEST=Boot a VM with coiommu lru unpin policy + pass through devices.
In VM, use command #echo 2 > /proc/sys/vm/drop_caches to trigger
shrink.
Change-Id: Icea6aee6424f09339b549eb2735c73551a87a505
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292940
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
Deactivate command is used when the CoIOMMU driver in the guest
is failed to probe, or CoIOMMU device is removed by the guest.
But these are not expected to happen. Once this happened, the
guest won't be functional as all the pass-through devices on top
of CoIOMMU will not work. So in the backend side, just panic when
receive such command.
BUG=b:188481989
TEST=Boot a VM with coiommu and remove it in the guest.
Change-Id: I912c71d80e6cbd02bf7edc6bfb30ef11051dc490
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292939
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
Add a crosvm parameter to allow user to sepcify the coiommu unpin
policy. Besides unpin the pages when balloon inflate, coiommu also
supports to periodically unpin with a LRU policy.
The usage is like this:
"--coiommu unpin_policy=lru,unpin_interval=10,unpin_limit=8192"
which means to use LRU unpin policy with unpin interval is 10 seconds
and the unpin count limit for each cycle is 8192 pages.
Without specify the parameter, coiommu will use the default
configuration which is to turn off the periodically unpin.
BUG=b:188481989
TEST=Boot a VM with coiommu lru unpin policy + pass through devices.
Change-Id: I10414cc6b2520b804685450dfd1560cfe49455a7
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292938
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
LRU unpin policy is an internal unpin policy which is triggered by
a timer. This policy can be used when there is no external balloon
unpin request.
BUG=b:188481989
TEST=Boot a VM with coiommu enabled + pass through devices.
Change-Id: Icb6e19073cb668fa954aec97e02be77f1b8f6a04
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292937
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
Put the VFIO pass-through devices and coIOMMU creating earlier
than the virtio device so that when creating virtio-balloon
it can use the tube from coIOMMU to send the unpining request
when processing the inflate.
BUG=b:188481989
TEST=Boot a VM with Network device pass through w/ coiommu, and do
the iperf test. Then perform balloon inflate/deflate.
Change-Id: If3ff9b3b0293ce49a39498a18feae1d697523f92
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292936
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
vIOMMU will dynamically pin VM's memory and in the extreme case they
might pin the entire VM's memory. RLIMIT_MEMLOCK will control how
much memory can be pinned by the process. So set the RLIMIT_MEMLOCK
to be allow pinning the entire VM's memory in the extreme case.
BUG=b:188481989
TEST=Boot a VM with Network device pass through w/ coiommu, and perform
the iperf test.
Change-Id: Ibceaa274646d5a0afac183d30c8df75c44c92775
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292935
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|
|
Coiommu can be enabled through the command line. E.g.
To enable coiommu for a VFIO pass-through device:
--vfio=/sys/bus/pci/devices/0000:00:02.0,iommu=coiommu
BUG=b:188481989
TEST=Boot a VM with a VFIO pass through device w/ coiommu
TEST=Boot a VM with a VFIO pass through device w/o coiommu
Change-Id: Ica6145d7bc6a4c398f0fc10899f8ee24138615c4
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292934
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Reviewed-by: David Stevens <stevensd@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
|
|
When balloon to do inflate to release some memory to hypervisor, such
memory should also be unpinned by the component(e.g. coiommu) which
has pinned these memory. This tube will be used by balloon to send
the unpin request to the components(e.g. coiommu) to do the unpin
before releasing the memory.
BUG=b:188481989
TEST=Boot a VM and check balloon inflate/deflate
Change-Id: I06aa8bd8c11deeac9f133adbefa6442cf1b722de
Reviewed-on: https://chromium-review.googlesource.com/c/chromiumos/platform/crosvm/+/3292932
Reviewed-by: Daniel Verkamp <dverkamp@chromium.org>
Tested-by: kokoro <noreply+kokoro@google.com>
Reviewed-by: David Stevens <stevensd@chromium.org>
|