UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

PCI/IOV: Add sysfs MSI-X vector assignment interface 

A typical cloud provider SR-IOV use case is to create many VFs for use by
guest VMs. The VFs may not be assigned to a VM until a customer requests a
VM of a certain size, e.g., number of CPUs. A VF may need MSI-X vectors
proportional to the number of CPUs in the VM, but there is no standard way
to change the number of MSI-X vectors supported by a VF.

Some Mellanox ConnectX devices support dynamic assignment of MSI-X vectors
to SR-IOV VFs. This can be done by the PF driver after VFs are enabled,
and it can be done without affecting VFs that are already in use. The
hardware supports a limited pool of MSI-X vectors that can be assigned to
the PF or to individual VFs.  This is device-specific behavior that
requires support in the PF driver.

Add a read-only "sriov_vf_total_msix" sysfs file for the PF and a writable
"sriov_vf_msix_count" file for each VF. Management software may use these
to learn how many MSI-X vectors are available and to dynamically assign
them to VFs before the VFs are passed through to a VM.

If the PF driver implements the ->sriov_get_vf_total_msix() callback,
"sriov_vf_total_msix" contains the total number of MSI-X vectors available
for distribution among VFs.

If no driver is bound to the VF, writing "N" to "sriov_vf_msix_count" uses
the PF driver ->sriov_set_msix_vec_count() callback to assign "N" MSI-X
vectors to the VF.  When a VF driver subsequently reads the MSI-X Message
Control register, it will see the new Table Size "N".

Link: https://lore.kernel.org/linux-pci/20210314124256.70253-2-leon@kernel.org
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
This commit is contained in:
Leon Romanovsky 2021-04-04 10:22:18 +03:00
parent 26bf30902c
commit c3d5c2d96d
5 changed files with 137 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

29
Documentation/ABI/testing/sysfs-bus-pci
View File

@ -375,3 +375,32 @@ Description:
The value comes from the PCI kernel device state and can be one
of: "unknown", "error", "D0", D1", "D2", "D3hot", "D3cold".
The file is read only.
What: /sys/bus/pci/devices/.../sriov_vf_total_msix
Date: January 2021
Contact: Leon Romanovsky <leonro@nvidia.com>
Description:
This file is associated with a SR-IOV physical function (PF).
It contains the total number of MSI-X vectors available for
assignment to all virtual functions (VFs) associated with PF.
The value will be zero if the device doesn't support this
functionality. For supported devices, the value will be
constant and won't be changed after MSI-X vectors assignment.
What: /sys/bus/pci/devices/.../sriov_vf_msix_count
Date: January 2021
Contact: Leon Romanovsky <leonro@nvidia.com>
Description:
This file is associated with a SR-IOV virtual function (VF).
It allows configuration of the number of MSI-X vectors for
the VF. This allows devices that have a global pool of MSI-X
vectors to optimally divide them between VFs based on VF usage.
The values accepted are:
* > 0 - this number will be reported as the Table Size in the
VF's MSI-X capability
* < 0 - not valid
* = 0 - will reset to the device default value
The file is writable if the PF is bound to a driver that
implements ->sriov_set_msix_vec_count().

102
drivers/pci/iov.c
View File

@ -31,6 +31,7 @@ int pci_iov_virtfn_devfn(struct pci_dev *dev, int vf_id)
return (dev->devfn + dev->sriov->offset +
dev->sriov->stride * vf_id) & 0xff;
}
EXPORT_SYMBOL_GPL(pci_iov_virtfn_devfn);
/*
* Per SR-IOV spec sec 3.3.10 and 3.3.11, First VF Offset and VF Stride may
@ -157,6 +158,92 @@ failed:
return rc;
}
#ifdef CONFIG_PCI_MSI
static ssize_t sriov_vf_total_msix_show(struct device *dev,
struct device_attribute *attr,
char *buf)
{
struct pci_dev *pdev = to_pci_dev(dev);
u32 vf_total_msix = 0;
device_lock(dev);
if (!pdev->driver || !pdev->driver->sriov_get_vf_total_msix)
goto unlock;
vf_total_msix = pdev->driver->sriov_get_vf_total_msix(pdev);
unlock:
device_unlock(dev);
return sysfs_emit(buf, "%u\n", vf_total_msix);
}
static DEVICE_ATTR_RO(sriov_vf_total_msix);
static ssize_t sriov_vf_msix_count_store(struct device *dev,
struct device_attribute *attr,
const char *buf, size_t count)
{
struct pci_dev *vf_dev = to_pci_dev(dev);
struct pci_dev *pdev = pci_physfn(vf_dev);
int val, ret;
ret = kstrtoint(buf, 0, &val);
if (ret)
return ret;
if (val < 0)
return -EINVAL;
device_lock(&pdev->dev);
if (!pdev->driver || !pdev->driver->sriov_set_msix_vec_count) {
ret = -EOPNOTSUPP;
goto err_pdev;
}
device_lock(&vf_dev->dev);
if (vf_dev->driver) {
/*
* A driver is already attached to this VF and has configured
* itself based on the current MSI-X vector count. Changing
* the vector size could mess up the driver, so block it.
*/
ret = -EBUSY;
goto err_dev;
}
ret = pdev->driver->sriov_set_msix_vec_count(vf_dev, val);
err_dev:
device_unlock(&vf_dev->dev);
err_pdev:
device_unlock(&pdev->dev);
return ret ? : count;
}
static DEVICE_ATTR_WO(sriov_vf_msix_count);
#endif
static struct attribute *sriov_vf_dev_attrs[] = {
#ifdef CONFIG_PCI_MSI
&dev_attr_sriov_vf_msix_count.attr,
#endif
NULL,
};
static umode_t sriov_vf_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = kobj_to_dev(kobj);
struct pci_dev *pdev = to_pci_dev(dev);
if (!pdev->is_virtfn)
return 0;
return a->mode;
}
const struct attribute_group sriov_vf_dev_attr_group = {
.attrs = sriov_vf_dev_attrs,
.is_visible = sriov_vf_attrs_are_visible,
};
int pci_iov_add_virtfn(struct pci_dev *dev, int id)
{
int i;
@ -400,18 +487,21 @@ static DEVICE_ATTR_RO(sriov_stride);
static DEVICE_ATTR_RO(sriov_vf_device);
static DEVICE_ATTR_RW(sriov_drivers_autoprobe);
static struct attribute *sriov_dev_attrs[] = {
static struct attribute *sriov_pf_dev_attrs[] = {
&dev_attr_sriov_totalvfs.attr,
&dev_attr_sriov_numvfs.attr,
&dev_attr_sriov_offset.attr,
&dev_attr_sriov_stride.attr,
&dev_attr_sriov_vf_device.attr,
&dev_attr_sriov_drivers_autoprobe.attr,
#ifdef CONFIG_PCI_MSI
&dev_attr_sriov_vf_total_msix.attr,
#endif
NULL,
};
static umode_t sriov_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
static umode_t sriov_pf_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = kobj_to_dev(kobj);
@ -421,9 +511,9 @@ static umode_t sriov_attrs_are_visible(struct kobject *kobj,
return a->mode;
}
const struct attribute_group sriov_dev_attr_group = {
.attrs = sriov_dev_attrs,
.is_visible = sriov_attrs_are_visible,
const struct attribute_group sriov_pf_dev_attr_group = {
.attrs = sriov_pf_dev_attrs,
.is_visible = sriov_pf_attrs_are_visible,
};
int __weak pcibios_sriov_enable(struct pci_dev *pdev, u16 num_vfs)

3
drivers/pci/pci-sysfs.c
View File

@ -1567,7 +1567,8 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
&pci_dev_attr_group,
&pci_dev_hp_attr_group,
#ifdef CONFIG_PCI_IOV
&sriov_dev_attr_group,
&sriov_pf_dev_attr_group,
&sriov_vf_dev_attr_group,
#endif
&pci_bridge_attr_group,
&pcie_dev_attr_group,

3
drivers/pci/pci.h
View File

@ -501,7 +501,8 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno);
resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno);
void pci_restore_iov_state(struct pci_dev *dev);
int pci_iov_bus_range(struct pci_bus *bus);
extern const struct attribute_group sriov_dev_attr_group;
extern const struct attribute_group sriov_pf_dev_attr_group;
extern const struct attribute_group sriov_vf_dev_attr_group;
#else
static inline int pci_iov_init(struct pci_dev *dev)
{

8
include/linux/pci.h
View File

@ -856,6 +856,12 @@ struct module;
* e.g. drivers/net/e100.c.
* @sriov_configure: Optional driver callback to allow configuration of
* number of VFs to enable via sysfs "sriov_numvfs" file.
* @sriov_set_msix_vec_count: PF Driver callback to change number of MSI-X
* vectors on a VF. Triggered via sysfs "sriov_vf_msix_count".
* This will change MSI-X Table Size in the VF Message Control
* registers.
* @sriov_get_vf_total_msix: PF driver callback to get the total number of
* MSI-X vectors available for distribution to the VFs.
* @err_handler: See Documentation/PCI/pci-error-recovery.rst
* @groups: Sysfs attribute groups.
* @driver: Driver model structure.
@ -871,6 +877,8 @@ struct pci_driver {
int (*resume)(struct pci_dev *dev); /* Device woken up */
void (*shutdown)(struct pci_dev *dev);
int (*sriov_configure)(struct pci_dev *dev, int num_vfs); /* On PF */
int (*sriov_set_msix_vec_count)(struct pci_dev *vf, int msix_vec_count); /* On PF */
u32 (*sriov_get_vf_total_msix)(struct pci_dev *pf);
const struct pci_error_handlers *err_handler;
const struct attribute_group **groups;
struct device_driver driver;