Device model uses polling mode to fetch the virtio blk request in RTVM.
When RTVM brings up with io uring, the threads handling io uring and vq are
not same, which would cause competition. To fix this issue, device
model should handle vq and io uring in the same thread to avoid conflict.
Tracked-On: #8737
Signed-off-by: YuanXin-Intel <xin.yuan@intel.com>
Reviewed-by: Jian Jun Chen <jian.jun.chen@intel.com>
When multiple virtio-blk instances are created for one VM,
using the same `static struct virtio_ops virtio_blk_ops` for all instances
is buggy. It only works when all instances are created with the same number
of the virtqueues.
This patch fixes this issue by introducing a member in `struct virtio_blk`
to store the ops info for each virtio-blk instance.
Tracked-On: #8612
Signed-off-by: Shiqing Gao <shiqing.gao@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
This patch updates the `iothread` option to specify the CPU affinity
of the iothread. Setting the iothread's CPU affinity could benefit the
Service VM's CPU utilization when Service VM owns limited dedicated CPUs.
It could be helpful to ensure the I/O mediator Quality of Service (QoS).
Once the performance tuning is done, the specific CPU affinity config could
pass to acrn-dm directly, letting the deployment more easily.
The format looks like below:
iothread=<num_iothread>@<cpu_affinity>
"@" is used to separate the following two settings:
- the number of iothread instances
- the CPU affinity settings for each iothread instance.
The format of `cpu_affinity` looks like below:
<cpu_affinity_0>/<cpu_affinity_1>/<cpu_affinity_2>/...
1. "/" is used to separate the CPU affinity setting for each iothread instance
(sequentially).
2. char '*' can be used to skip the setting for the specific iothread instance.
3. the number of cpu_affinity_x vs. the number of iothread instances
- If # of cpu_affinity_x is less than # of iothread instances,
no CPU affinity settings for the last few iothread instances.
- If # of cpu_affinity_x is more than # of iothread instances,
the extra cpu_affinity_x are discarded.
4. ":" is used to separate different CPU cores for each CPU affinity setting.
Examples to specify the CPU affinity of the iothread:
1. iothread=3@0:1:2/0:1
`add_virtual_device 9 virtio-blk iothread=3@0:1:2/0:1,mq=3,/dev/nvme1n1`
a) 3 iothread instances are created.
b) CPU affinity of iothread instances for this virtio-blk device:
- 1st iothread instance <-> pins to Service VM CPU 0,1,2
- 2nd iothread instance <-> pins to Service VM CPU 0,1
- 3rd iothread instance <-> No CPU affinity settings
2. iothread=3@0/*/1
`add_virtual_device 9 virtio-blk iothread=3@0/*/1,mq=3,/dev/nvme1n1`
a) 3 iothread instances are created.
b) CPU affinity of iothread instances for this virtio-blk device:
- 1st iothread instance <-> pins to Service VM CPU 0
- 2nd iothread instance <-> No CPU affinity settings
- 3rd iothread instance <-> pins to Service VM CPU 1
v1 -> v2:
* encapsulate one API in iothread.c to parse the iothread options, so that
other BE can also use it.
v2 -> v3:
* introduce one API iothread_free_options to free the elements that
are allocated dynamically in iothread_parse_options().
Tracked-On: #8612
Signed-off-by: Shiqing Gao <shiqing.gao@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
This patch renames the iothread for better readability. For instance,
the new name of the iothread for virtio-blk device looks like `iothr-0-blk9:0`.
It could be helpful when tuning the performance and the CPU utilization.
v1 -> v2:
* add `const` qualifier for the input parameter of `iothread_create`
Tracked-On: #8612
Signed-off-by: Shiqing Gao <shiqing.gao@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Prior to this patch, one single iothread instance is created and initialized
in the `main` function. This single iothread monitors all the registered fds
and handles all the corresponding requests. It leads to the limited flexibility
of the iothread support.
To improve the flexibility of the iothread support, this patch does:
- add the support of multiple iothread instances.
`iothread_create` is introduced to create a certain number of iothread
instances. It shall be called at first by each virtual device owner (such as
virtio-blk BE) on initialization phase. Then, `iothread_add` can be called
to add the to be monitored fd to the specified iothread.
- update virtio-blk BE to let the acrn-dm option `iothread` accept a number
as the number of iothread instances to be created.
If `iothread` is contained in the parameters, but the number is not specified,
one iothread instance would be created by default.
Examples to specify the number of iothread instances:
1. Create 2 iothread instances
`add_virtual_device 9 virtio-blk iothread=2,mq=2,/dev/nvme1n1,writeback,aio=io_uring`
2. Create 1 iothread instances (by default)
`add_virtual_device 9 virtio-blk iothread,mq=2,/dev/nvme1n1,writeback,aio=io_uring`
- update virtio-blk BE to separate the request handling of different virtqueues
to different iothreads.
The request from one or more virtqueues can be handled in one iothread.
The mapping between virtqueues and iothreads is based on round robin.
v1 -> v2:
* add a mutex to protect the free ioctx slot allocation
Tracked-On: #8612
Signed-off-by: Shiqing Gao <shiqing.gao@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
io_uring is a high-performance asynchronous I/O framework, primarily designed
to improve the efficiency of input and output (I/O) operations in user-space
applications.
This patch enables io_uring in block_if module. It utilizes the interfaces
provided by the user-space library `liburing` to interact with io_uring
in kernel-space.
To build the acrn-dm with io_uring support, `liburing-dev` package needs to be
installed. For example, it can be installed like below in Ubuntu 22.04.
sudo apt install liburing-dev
In order to support both the thread pool mechanism and the io_uring mechanism,
an acrn-dm option `aio` is introduced. By default, thread pool mechanism is
selected.
- Example to use io_uring:
`add_virtual_device 9 virtio-blk iothread,mq=2,/dev/nvme1n1,writeback,aio=io_uring`
- Example to use thread pool:
`add_virtual_device 9 virtio-blk iothread,mq=2,/dev/nvme1n1,writeback,aio=threads`
- Example to use thread pool (by default):
`add_virtual_device 9 virtio-blk iothread,mq=2,/dev/nvme1n1,writeback`
v2 -> v3:
* Update iothread_handler
- Use the unified eventfd interfaces to read the counter value of the
ioeventfd.
- Remove the while loop to read the ioeventfd. It is not necessary
because one read would reset the counter value to 0.
* Update iou_submit_sqe to return an error code
The caller of iou_submit_sqe shall check the return value.
If there is NO available submission queue entry in the submission queue,
need to break the while loop. Request can only be submitted when SQE is
available.
v1 -> v2:
* move the logic of reading out ioeventfd from iothread.c to virtio.c, because
it is specific to the virtqueue handling.
Tracked-On: #8612
Signed-off-by: Shiqing Gao <shiqing.gao@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
block_if is the backend of ahci and virtio-blk. Only one queue is
supported by block_if now. Several worker threads are created as
the thread pool for the queue. One BIG mutex is used for the queue
and thread operation. With this patch block_if can support multiple
queues and each queue is backed by several worker threads. blockif_req
can be submited/enqueued into one specified queue. By spliting into
several queues contention from the BIG mutex can be relieved/eliminated.
This is used to support virtio-blk multiple queues feature.
Tracked-On: #8612
Signed-off-by: Jian Jun Chen <jian.jun.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Virtio-blk can support multiple virtqueues (mq) which is negotiated
between FE and BE by the feature bit VIRTIO_BLK_F_MQ. The virtqueue
number of virtio-blk can be specified by "mq=x" in the parameter.
For example: "virtio-blk,iothread,mq=2,..."
Tracked-On: #8612
Signed-off-by: Jian Jun Chen <jian.jun.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
ACRN virtio devices are using a per device mutex to protect the
concurrent operations on the device's PIO/MMIO. This introduces
big contention in fast IO hence downgrades the IO performance,
for example virtio-blk with asyncio enabled. This patch introduces
per queue mutex to relieve such issues. Currently the per queue
mutex is only used in the asycio path when iothread is enabled.
Tracked-On: #8612
Signed-off-by: Jian Jun Chen <jian.jun.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
ACRN_IOEVENTFD_FLAG_ASYNCIO is not set when unregister ioeventfd
in the current implementation which will cause the old asyncio_desc
will be remained in hypervisor link list when switching from OVMF to
kernel.
Tracked-On: #8612
Signed-off-by: Jian Jun Chen <jian.jun.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
doxygen will warn that documented return type is found for functions
that does not return anything in 1.9.4 or later versions. 'None' is
not a special keyword in doxyge, it will recognize it as description
to the return value that does not exist in void functions.
Tracked-On: #8425
Signed-off-by: Jiaqing Zhao <jiaqing.zhao@linux.intel.com>
Reviewed-by: Junjie Mao <junjie.mao@intel.com>
In virtio_gpu_cmd_create_blob() and virtio_gpu_cmd_resource_attach_
backing(), entries may be accessed before initialization. Fix it by
using calloc() to allocate it instead of malloc().
Tracked-On: #8439
Signed-off-by: Jiaqing Zhao <jiaqing.zhao@linux.intel.com>
This patch fix several issues that NULL pointers possibly be
dereferenced in display module.
Tracked-On: #8439
Signed-off-by: Yonghua Huang <yonghua.huang@intel.com>
Signed-off-by: Jiaqing Zhao <jiaqing.zhao@linux.intel.com>
Reviewed-by: Jian Jun Chen <jian.jun.chen@intel.com>
Pointer 'vsock->vhost_vsock' returned from call to function
'vhost_vsock_init' may be NULL and will be dereferenced when
calling 'vhost_vsock_set_guest_cid()'.
Tracked-On: #8439
Signed-off-by: Yonghua Huang <yonghua.huang@intel.com>
Signed-off-by: Jiaqing Zhao <jiaqing.zhao@linux.intel.com>
Reviewed-by: Jian Jun Chen <jian.jun.chen@intel.com>
Add the new parameter for register ioevent function, let the vhost
vq and viothread vq can share the register ioevent common API.
Tracked-On: #8323
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Reviewed-by: Conghui <conghui.chen@intel.com>
To avoid assertions in devicemodel, remove all the assert() in vga.c,
use print error message to check errors.
All the behavior of registers follow this spec:
https://wiki.osdev.org/VGA_Hardware#Graphics_Mode
Tracked-On: #8125
Signed-off-by: Sun Peng <peng.p.sun@linux.intel.com>
Reviewed-by: Huang, Yonghua <yonghua.huang@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Add a new flag in ioeventfd ioctl to support asyncio. After that, the IO
request will be processed in asyncio path by kernel and hypervisor.
Tracked-On: #8209
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Fix the bug in iothread handler, the event should be read out so that the
next epoll_wait not return directly as the fd can still readable.
Tracked-On: #8181
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Change virtio-i2c from legacy to modern device according to virtio spec v1.2.
Tracked-On: #8055
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Return the parsed scanout_num to guest_vm so that the guest_vm can configure multi-display.
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
Sometimes the virtio_gpu in guest_vm doesn't pass the zero coord_x/y for the
displayed framebuffer. In such case the offset should be calibrated for pixman_image/dmabuf
so that it can display the image from the correct image.
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
The virtio-gpu display will be handled by the below cmd sequence:
1. Virtio_GPU_CMD_CREATE_RESOURCE
2. VIRTIO_GPU_CMD_SET_SCANOUT/SET_SCANOUT_BLOB
3. VIRTIO_GPU_CMD_FLUSH
And the VIRTIO_GPU_CMD_FLUSH will notify the vdisplay module to display the
framebuffer related with the scanout_id. But the virtio_gpu_cmd_flush doesn't
pass the scanout info.Instead it only passes the flushed_region and the
resource_id. So it needs to check whether the scanout_region is covered by the
flushed_region and then decide whether the scanout_win needs to be displayed.
v1->v2: Use the bpp instead of hardcode 4 for offset_calculation
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
The virtio-gpu in guest_vm also passes the scanout_id for cursor operation.
So this scanout_id should be used in course of handling cursor operation.
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
The scanout_id is included in the below virtio-gpu cmd request.
VIRTIO_GPU_GET_EDID
VIRTIO_GPU_SET_SCANOUT
VIRTIO_GPU_SET_SCANOUT_BLOB
VIRTIO_GPU_GET_DISPLAY_INFO
So the scanout_id and scanout_rect should be handled correctly. And it will
use the scanout_rect instead of resource width/height in course of handling
VIRTIO_GPU_SET_SCANOUT/SCANOUT_BLOB cmd.
v1->v2: change the position to zero when returning response for GET_DISPLAY_INFO
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
Now it only supports one scanout for virtio-gpu. So the scanout_id is ignored in
course of handling virtio-gpu cmd. In order to handle the virtio-gpu cmd correctly,
it adds the virtio_gpu_scanout structure so that it can record the scanout info.
v1->v2: Refine the field in virtio_gpu_scanout and error message for scanout_id
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
Vdisplay module will create the gui_window (vScreen) based on the virtio-gpu
parameter. When virtio-gpu device tries to establish the connection with
vdisplay module, it will return the supported number of vScreen.
Then the virtio-gpu device can initialize the correct info for the guest_vm.
BTW: The number is fixed to 1.
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
Currenly it can support only one display_win. When virtio-gpu wants to display
the framebuffer from Guest_vm, it will render it into the default win. In order
to support multi-window, the scanout_id is added for display API.
After display API is refined, the vdisplay and virtio-gpu can support the multi-win
independently.
BTW: Now the scanout_id is not implemented in vdisplay module and the virtio-gpu always
passes the zero. It will be implemeneted in the later patches.
Tracked-On: #7988
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Reviewed-by: Peng Sun <peng.p.sun@linux.intel.com>
There was some secure coding style violations of virtio net and tmp,
this patch add some NULL check to fix these violations.
Tracked-On: #6690
Signed-off-by: Chenli Wei <chenli.wei@linux.intel.com>
disable NOTIFY during getting requests from virtqueue. This will improve
the IO performance.
Tracked-On: #7940
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Add ioeventfd and iothread to virtio framework. When a virtio device
claim to support iothread, virtio framework will register a ioeventfd
and add it to iothread's epoll. After that, the new notify will come
through the iothread instead of the vcpu thread. The notify handler will
be called to process the request.
Tracked-On: #7940
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Use the VHOST_NET_F_VIRTIO_NET_HDR in linux system header file,
and set the correct feature bit for Virtio net header.
Tracked-On: #7790
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Free the virtio_vsock struct resource in virtio vsock deinit function
in case memory leak.
Tracked-On: #7759
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Replace the exclamation mark with period mark in debug info and fix
the Guest CID max value macro.
Tracked-On: #7456
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Modified the copyright year range in code, and corrected "int32_tel"
into "Intel" in two "hypervisor/include/debug/profiling.h" and
"hypervisor/include/debug/profiling_internal.h".
Tracked-On: #7559
Signed-off-by: Ziheng Li <ziheng.li@intel.com>
Fix the log format problem in devicemodel when using virtio-console with
'stdio' configuration.
In virtio-console, it will change the STDIO's attributes, and will case
the log message after that not align.
e.g:
for (i=0; i<3; i++)
printf('test\n');
The original output would be like this:
test
test
test
After add 'OPOST' to oflag of STDIO, the output would be like this:
test
test
test
(OPOST - Enable implementation-defined output processing)
Tracked-On: #7860
Signed-off-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Fix the memory leakage issue caused by incomplete deinit flow.
Tracked-On: #7759
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
The vsock cid type is u64, redefine the cid type to u64, and use
dm_strtoul API replace dm_strtoi.
Tracked-On: #7456
Signed-off-by: Liu Long <long.liu@linux.intel.com>
The virtio feature bits is 64bits but the access will be split
as two times 32bits access. This patch fixes the bug which overwrites
another side 32bits, and causes feature bits are lost.
Tracked-On: #7456
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Reviewed-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
This patch supports the user space logic of vhost vsock which
is majorly for its initialization phase.
Tracked-On: #7456
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Reviewed-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
The patch expose the vhost kernel ioctrl API and remove the virtio_net
operation functions to the virtio_net code module.
Tracked-On: #7456
Signed-off-by: Liu Long <long.liu@linux.intel.com>
Reviewed-by: Conghui <conghui.chen@intel.com>
Acked-by: Wang, Yu1 <yu1.wang@intel.com>
Use needed constants from libderm instead of directly using
kernel UAPI.
Tracked-On: #6688
Signed-off-by: Helmut Buchsbaum <helmut.buchsbaum@opensource.tttech-industrial.com>
Now vdpy_get_display_info/get_edid is called before vdpy_init.
This is incorrect. They should be called after setting up the
connection with vdisplay.
Tracked-On: #7376
Acked-by: Wang Yu <yu1.wang@intel.com>
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
The virtio_gpu in guest_vm will try to fetch the EDID to query
the supported resolution. Guest vm will send the cmd of
VIRTIO_GPU_CMD_GET_EDID and receive the response of VIRTIO_GPU_RESP_OK_EDID.
Now acrn-dm has some issues in course of handlding EDID request: Incorrect
resp type, the incorrect response. This will cause that the guest_vm fails
to fetch the EDID.
Tracked-On: #7376
Acked-by: Wang Yu <yu1.wang@intel.com>
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
In course of creating the udmabuf, udmabuf_create_list is allocated and
passed to kernel. After the dmabuf is returned, it is not used
any more. Need to free it otherwises it will cause the memory leak.
Tracked-On: #7337
Acked-by: Wang Yu <yu1.wang@intel.com>
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
It still tries to access the gpu->vdpy_handel after the gpu
is free. This is incorrect.
Tracked-On: #7337
Acked-by: Wang Yu <yu1.wang@intel.com>
Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
