Commit Graph

38 Commits

Author SHA1 Message Date
Yong He
0149e65081 vm-device: support batch update interrupt source group GSI
Split interrupt source group restore into two steps, first restore
the irqfd for each interrupt source entry, and second restore the
GSI routing of the entire interrupt source group.

This patch will reduce restore latency of interrupt source group,
and in a 200-concurrent restore test, the patch reduced the
average IOAPIC restore time from 15ms to 1ms.

Signed-off-by: Yong He <alexyonghe@tencent.com>
2023-08-03 15:58:36 +01:00
Jianyong Wu
a718716831 vfio: fix vfio device fail to initialize issue for 64k page size
Currently, vfio device fails to initialize as the msix-cap region in BAR
is mapped as RW region.

To resolve the initialization issue, this commit avoids mapping the
msix-cap region in the BAR. However, this solution introduces another
problem where aligning the msix table offset in the BAR to the page
size may cause overlap with the MMIO RW region, leading to reduced
performance. By enlarging the entire region in the BAR and relocating
the msix table to achieve page size alignment, this problem can be
overcomed effectively.

Fixes: #5292
Signed-off-by: Jianyong Wu <jianyong.wu@arm.com>
2023-06-19 10:29:23 +08:00
Sebastien Boeuf
748018ace3 vm-migration: Don't store the id as part of Snapshot structure
The information about the identifier related to a Snapshot is only
relevant from the BTreeMap perspective, which is why we can get rid of
the duplicated identifier in every Snapshot structure.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2022-12-09 10:26:06 +01:00
Sebastien Boeuf
30e421d2e5 pci: Remove unused restore() implementations
Now that VirtioPciDevice, VfioPciDevice and VfioUserPciDevice have all
been moved to the new restore design, there's no need to keep the old
way around, therefore the restore() implementations for MsiConfig,
MsixConfig and PciConfiguration can be removed.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2022-11-29 13:46:30 +01:00
Sebastien Boeuf
eae8043890 pci, virtio-devices: Move VirtioPciDevice to the new restore design
The code for restoring a VirtioPciDevice has been updated, including the
dependencies VirtioPciCommonConfig, MsixConfig and PciConfiguration.

It's important to note that both PciConfiguration and MsixConfig still
have restore() implementations because Vfio and VfioUser devices still
rely on the old way for restore.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2022-11-23 18:37:40 +00:00
Rob Bradford
89a2562c5a pci: Optimise MSI-X table programming
With an updated Linux kernel the kernel reprograms the same table entry
in the MSI-X table multiple times. Fortunately it does so with entry
masked (the default.)

The costly part of MSI-X table reprogramming is going out to the host
kernel to update the GSI routing entries. This change makes three
optimisations.

1. If the table entry is unchanged: skip handking updates
2. Only update the GSI routing table if the table entry is unmasked
   (this skips extra calls to the ioctl() for reprogramming the
    entries.)
3. Only generate a message on entry unmasking if the global MSI-X enable
   bit is set.

Fixes: #4273

Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2022-10-07 09:57:27 -07:00
Sebastien Boeuf
8eaefa6e8e pci: msix: Derive Versionize for MsixCap
So that we can save and restore the whole structure through snapshot and
restore operations.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2022-06-09 09:19:58 +02:00
Rob Bradford
ed87e42e6f vm-device, pci, devices: Remove InterruptSourceGroup::{un}mask
The calls to these functions are always preceded by a call to
InterruptSourceGroup::update(). By adding a masked boolean to that
function call it possible to remove 50% of the calls to the
KVM_SET_GSI_ROUTING ioctl as the the update will correctly handle the
masked or unmasked case.

This causes the ioctl to disappear from the perf report for a boot of
the VM.

Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2022-04-11 22:56:48 +01:00
Wei Liu
6f571d5c07 pci: add debug output for enabling and disabling MSI-X
This helps debugging MSI-X issues.

Signed-off-by: Wei Liu <liuwe@microsoft.com>
2022-02-17 17:33:40 +01:00
Wei Liu
d2d6eb0591 pci: slightly change safety comment style
Make them start with "SAFETY" so it is more concise and easy to spot.

Signed-off-by: Wei Liu <liuwe@microsoft.com>
2021-11-17 14:40:51 +00:00
Sebastien Boeuf
ed5f25446a pci: vfio: Support mapping BAR containing MSI-X
In order to get proper performance out of hardware that might be passed
through the VM with VFIO, we decide to try mapping any region marked as
mappable, ignoring the failure and moving on to the next region. When
the mapping succeeds, we establish a list of user memory regions so that
we enable only subparts of the global mapping through the hypervisor.
This allows MSI-X table and PBA to keep trapping accesses from the guest
so that the VMM can properly emulate MSI-X.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2021-10-28 06:10:12 -07:00
Sebastien Boeuf
dcc646f5b1 clippy: Fix redundant allocations
With the new beta version, clippy complains about redundant allocation
when using Arc<Box<dyn T>>, and suggests replacing it simply with
Arc<dyn T>.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2021-07-29 13:28:57 +02:00
Rob Bradford
3ffd2cb9be pci: Versionize PCI state
Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2021-05-26 22:29:35 +02:00
Rob Bradford
496ceed1d0 misc: Remove unnecessary "extern crate"
Now all crates use edition = "2018" then the majority of the "extern
crate" statements can be removed. Only those for importing macros need
to remain.

Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2021-05-12 17:26:11 +02:00
Rob Bradford
6f5d4702d4 misc: Simplify snapshot/restore by using helper functions
Simplify snapshot & restore code by using generics to specify helper
functions that take / make a Serialize / Deserialize struct

Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2021-04-08 16:17:14 +01:00
Rob Bradford
827229d8e4 pci: Address Rust 1.51.0 clippy issue (upper_case_acroynms)
warning: name `IORegion` contains a capitalized acronym
   --> pci/src/configuration.rs:320:5
    |
320 |     IORegion = 0x01,
    |     ^^^^^^^^ help: consider making the acronym lowercase, except the initial letter (notice the capitalization): `IoRegion`
    |
    = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#upper_case_acronyms

Signed-off-by: Rob Bradford <robert.bradford@intel.com>
2021-03-26 11:32:09 +00:00
Sebastien Boeuf
de88bef429 pci: msix: Fix masking/enabling semantics
By looking at Linux kernel boot time, we identified that a lot of time
was spent registering and unregistering IRQ fds to KVM. This is not
efficient and certainly not a wrong behavior from the Linux kernel,
but rather a problem with the Cloud-Hypervisor's implementation of
MSI-X.

The way to fix this issue is by ensuring the initial conditions are
correct, which means the entire MSI-X vector table must be disabled
and masked. Additionally, each vector must be individually masked.

With these correct conditions, Linux won't start masking interrupt
vectors, and later unmask them since they will be seen as masked from
the beginning. This means the OS will simply have to unmask them when
needed, avoiding the extra operation.

Another aspect of this patch is to prevent Cloud-Hypervisor from
enabling (by registering IRQ fd) all vectors when either the global
'mask' or 'enable' bits are set. Instead, we can simply let the mask()
and unmask() operations take care of it if needed.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-09-24 22:29:16 +02:00
Sebastien Boeuf
871138d5cc vm-migration: Make snapshot() mutable
There will be some cases where the implementation of the snapshot()
function from the Snapshottable trait will require to modify some
internal data, therefore we make this possible by updating the trait
definition with snapshot(&mut self).

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-08-25 16:43:10 +02:00
Wei Liu
47e8f5475e pci/msix: remove reference to KVM from a comment
Signed-off-by: Wei Liu <liuwe@microsoft.com>
2020-08-21 16:23:41 +02:00
Michael Zhao
cce6237536 pci: Enable GSI routing (MSI type) for AArch64
In this commit we saved the BDF of a PCI device and set it to "devid"
in GSI routing entry, because this field is mandatory for GICv3-ITS.

Signed-off-by: Michael Zhao <michael.zhao@arm.com>
2020-07-14 14:34:54 +01:00
Sebastien Boeuf
376db31107 pci: Implement Snapshottable trait for MsixConfig
In order to restore devices relying on MSI-X, the MsixConfig structure
must be restored with the correct values. Additionally, the KVM routes
must be restored so that interrupts can be delivered through KVM the way
they were configured before the snapshot was taken.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-05-11 11:38:16 +01:00
Sebastien Boeuf
b77fdeba2d msi/msi-x: Prevent from losing masked interrupts
We want to prevent from losing interrupts while they are masked. The
way they can be lost is due to the internals of how they are connected
through KVM. An eventfd is registered to a specific GSI, and then a
route is associated with this same GSI.

The current code adds/removes a route whenever a mask/unmask action
happens. Problem with this approach, KVM will consume the eventfd but
it won't be able to find an associated route and eventually it won't
be able to deliver the interrupt.

That's why this patch introduces a different way of masking/unmasking
the interrupts, simply by registering/unregistering the eventfd with the
GSI. This way, when the vector is masked, the eventfd is going to be
written but nothing will happen because KVM won't consume the event.
Whenever the unmask happens, the eventfd will be registered with a
specific GSI, and if there's some pending events, KVM will trigger them,
based on the route associated with the GSI.

Suggested-by: Liu Jiang <gerry@linux.alibaba.com>
Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-02-25 08:31:14 +00:00
Sebastien Boeuf
4bb12a2d8d interrupt: Reorganize all interrupt management with InterruptManager
Based on all the previous changes, we can at this point replace the
entire interrupt management with the implementation of InterruptManager
and InterruptSourceGroup traits.

By using KvmInterruptManager from the DeviceManager, we can provide both
VirtioPciDevice and VfioPciDevice a way to pick the kind of
InterruptSourceGroup they want to create. Because they choose the type
of interrupt to be MSI/MSI-X, they will be given a MsiInterruptGroup.

Both MsixConfig and MsiConfig are responsible for the update of the GSI
routes, which is why, by passing the MsiInterruptGroup to them, they can
still perform the GSI route management without knowing implementation
details. That's where the InterruptSourceGroup is powerful, as it
provides a generic way to manage interrupt, no matter the type of
interrupt and no matter which hypervisor might be in use.

Once the full replacement has been achieved, both SystemAllocator and
KVM specific dependencies can be removed.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
1e5e02801f msix: Perform interrupt enabling/disabling
In order to factorize one step further, we let MsixConfig perform the
interrupt enabling/disabling. This is done by registering/unregistering
the KVM irq_fds of all GSI routes related to this device.

And now that MsixConfig is in charge of the irq_fds, vfio-pci must rely
on it to retrieve them and provide them to the vfio driver.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
19aeac40c9 msix: Remove the need for interrupt callback
Now that MsixConfig has access to the irq_fd descriptors associated with
each vector, it can directly write to it anytime it needs to trigger an
interrupt.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
3fe362e3bd msix: Set KVM routes from MsixConfig instead of VFIO
Now that MsixConfig has access to both KVM VmFd and the list of GSI
routes, the update of the KVM GSI routes can be directly done from
MsixConfig instead of specifically from the vfio-pci implementation.

By moving the KVM GSI routes update at the MsixConfig level, both
vfio-pci and virtio-pci (or any other emulated PCI device) can benefit
from it, without having to implement it on their own.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
2381f32ae0 msix: Add gsi_msi_routes to MsixConfig
Because MsixConfig will be responsible for updating KVM GSI routes at
some point, it is necessary that it can access the list of routes
contained by gsi_msi_routes.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
9b60fcdc39 msix: Add VmFd to MsixConfig
Because MsixConfig will be responsible for updating the KVM GSI routes
at some point, it must have access to the VmFd to invoke the KVM ioctl
KVM_SET_GSI_ROUTING.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
86c760a0d9 msix: Add SystemAllocator to MsixConfig
The point here is to let MsixConfig take care of the GSI allocation,
which means the SystemAllocator must be passed from the vmm crate all
the way down to the pci crate.

Once this is done, the GSI allocation and irq_fd creation is performed
by MsixConfig directly.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2020-01-17 23:43:45 +01:00
Sebastien Boeuf
c0e2bbb23f pci: Add MSI-X helper to check if interrupts are enabled
In order to check if device's interrupts are enabled, this patch adds
a helper function to the MsixConfig structure so that at any point in
time we can check if an interrupt should be delivered or not.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-08-08 17:38:47 +01:00
Sebastien Boeuf
87195c9ccc pci: Fix vector control read/write from/to MSI-X table
The vector control offset is at the 4th byte of each MSI-X table entry.
For that reason, it is located at 0xc, and not 0x10 as implemented.

This commit fixes the current MSI-X code, allowing proper reading and
writing of each vector control register in the MSI-X table.

Fixes #156

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-08-08 08:10:18 +01:00
Sebastien Boeuf
a548a01423 pci: Fix MSI-X table and PBA offsets
The offsets returned by the table_offset() and pba_offset() function
were wrong as they were shifting the value by 3 bits. The MSI-X spec
defines the MSI-X table and PBA offsets as being defined on 3-31 bits,
but this does not mean it has to be shifted. Instead, the address is
still on 32 bits and assumes the LSB bits 0-2 are set to 0.

VFIO was working fine with devices were the MSI-X offset were 0x0, but
the bug was found on a device where the offset was non-null.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-08-02 09:45:20 +02:00
Sebastien Boeuf
72007f016a pci: Improve MSI-X code to let VFIO rely on it
This commit enhances the current msi-x code hosted in the pci crate
in order to be reused by the vfio crate. Specifically, it creates
several useful methods for the MsixCap structure that can simplify
the caller's code.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-07-22 09:50:10 -07:00
Sebastien Boeuf
4d98dcb077 msix: Handle MSI-X device masking
As mentioned in the PCI specification, the Function Mask from the
Message Control Register can be set to prevent a device from injecting
MSI-X messages. This supersedes the vector masking as it interacts at
the device level.

Here quoted from the specification:
For MSI and MSI-X, while a vector is masked, the function is prohibited
from sending the associated message, and the function must set the
associated Pending bit whenever the function would otherwise send the
message. When software unmasks a vector whose associated Pending bit is
set, the function must schedule sending the associated message, and
clear the Pending bit as soon as the message has been sent. Note that
clearing the MSI-X Function Mask bit may result in many messages
needing to be sent.

This commit implements the behavior described above by reorganizing
the way the PCI configuration space is being written. It is indeed
important to be able to catch a change in the Message Control
Register without having to implement it for every PciDevice
implementation. Instead, the PciConfiguration has been modified to
take care of handling any update made to this register.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-06-07 13:33:53 +01:00
Sebastien Boeuf
d810c7712d msix: Handle MSI-X vector masking
The current MSI-X implementation completely ignores the values found
in the Vector Control register related to a specific vector, and never
updates the Pending Bit Array.

According to the PCI specification, MSI-X vectors can be masked
through the Vector Control register on bit 0. If this bit is set,
the device should not inject any MSI message. When the device
runs into such situation, it must not inject the interrupt, but
instead it must update the bit corresponding to the vector number
in the Pending Bit Array.

Later on, if/when the Vector Control register is updated, and if
the bit 0 is flipped from 0 to 1, the device must look into the PBA
to find out if there was a pending interrupt for this specific
vector. If that's the case, an MSI message is injected and the
bit from the PBA is cleared.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-06-07 13:33:53 +01:00
Sebastien Boeuf
edd1279609 pci: Allow QWORD read and write to MSI-X table
As mentioned in the PCI specification, MSI-X table supports both
DWORD and QWORD accesses:

For all accesses to MSI-X Table and MSI-X PBA fields, software must
use aligned full DWORD or aligned full QWORD transactions; otherwise,
the result is undefined.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-06-07 13:33:53 +01:00
Sebastien Boeuf
00cdbbc673 pci: Make MSI-X PBA read only
Relying on the PCI specification, the Pending Bit Array is read only.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-06-07 13:33:53 +01:00
Sebastien Boeuf
4b53dc4921 pci: Add MSI-X implementation
In order to support MSI-X, this commit adds to the pci crate a new
module called "msix". This module brings all the necessary pieces
to let any PCI device implement MSI-X support.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
2019-06-06 15:27:35 +01:00