From: Long Li <[email protected]>
When kernel boots with a NUMA topology with some NUMA nodes offline, the PCI
driver should only set an online NUMA node on the device. This can happen
during KDUMP where some NUMA nodes are not made online by the KDUMP kernel.
This patch also fixes the case where kernel is booting with "numa=off".
Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2")
Signed-off-by: Long Li <[email protected]>
Change log:
v2: use numa_map_to_online_node() to assign a node to device (suggested by
Michael Kelly <[email protected]>)
v3: add "Fixes" and check for num_possible_nodes()
---
drivers/pci/controller/pci-hyperv.c | 13 +++++++++++--
1 file changed, 11 insertions(+), 2 deletions(-)
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6c9efeefae1b..b5276e81bb44 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -2129,8 +2129,17 @@ static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
if (!hv_dev)
continue;
- if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
- set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node);
+ if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY &&
+ hv_dev->desc.virtual_numa_node < num_possible_nodes())
+ /*
+ * The kernel may boot with some NUMA nodes offline
+ * (e.g. in a KDUMP kernel) or with NUMA disabled via
+ * "numa=off". In those cases, adjust the host provided
+ * NUMA node to a valid NUMA node used by the kernel.
+ */
+ set_dev_node(&dev->dev,
+ numa_map_to_online_node(
+ hv_dev->desc.virtual_numa_node));
put_pcichild(hv_dev);
}
--
2.25.1
From: [email protected] <[email protected]> Sent: Wednesday, January 19, 2022 11:59 AM
>
> When kernel boots with a NUMA topology with some NUMA nodes offline, the PCI
> driver should only set an online NUMA node on the device. This can happen
> during KDUMP where some NUMA nodes are not made online by the KDUMP kernel.
>
> This patch also fixes the case where kernel is booting with "numa=off".
>
> Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2")
>
> Signed-off-by: Long Li <[email protected]>
>
> Change log:
> v2: use numa_map_to_online_node() to assign a node to device (suggested by
> Michael Kelly <[email protected]>)
>
> v3: add "Fixes" and check for num_possible_nodes()
> ---
> drivers/pci/controller/pci-hyperv.c | 13 +++++++++++--
> 1 file changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 6c9efeefae1b..b5276e81bb44 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -2129,8 +2129,17 @@ static void hv_pci_assign_numa_node(struct
> hv_pcibus_device *hbus)
> if (!hv_dev)
> continue;
>
> - if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
> - set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node);
> + if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY &&
> + hv_dev->desc.virtual_numa_node < num_possible_nodes())
> + /*
> + * The kernel may boot with some NUMA nodes offline
> + * (e.g. in a KDUMP kernel) or with NUMA disabled via
> + * "numa=off". In those cases, adjust the host provided
> + * NUMA node to a valid NUMA node used by the kernel.
> + */
> + set_dev_node(&dev->dev,
> + numa_map_to_online_node(
> + hv_dev->desc.virtual_numa_node));
>
> put_pcichild(hv_dev);
> }
> --
> 2.25.1
Reviewed-by: Michael Kelley <[email protected]>
On Wed, Jan 19, 2022 at 11:59:06AM -0800, [email protected] wrote:
> From: Long Li <[email protected]>
>
> When kernel boots with a NUMA topology with some NUMA nodes offline, the PCI
> driver should only set an online NUMA node on the device. This can happen
> during KDUMP where some NUMA nodes are not made online by the KDUMP kernel.
>
> This patch also fixes the case where kernel is booting with "numa=off".
>
> Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and support PCI_BUS_RELATIONS2")
>
No blank line here, please
> Signed-off-by: Long Li <[email protected]>
Everything below needs to be under "---" marker.
Thanks
>
> Change log:
> v2: use numa_map_to_online_node() to assign a node to device (suggested by
> Michael Kelly <[email protected]>)
>
> v3: add "Fixes" and check for num_possible_nodes()
> ---
> drivers/pci/controller/pci-hyperv.c | 13 +++++++++++--
> 1 file changed, 11 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
> index 6c9efeefae1b..b5276e81bb44 100644
> --- a/drivers/pci/controller/pci-hyperv.c
> +++ b/drivers/pci/controller/pci-hyperv.c
> @@ -2129,8 +2129,17 @@ static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
> if (!hv_dev)
> continue;
>
> - if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
> - set_dev_node(&dev->dev, hv_dev->desc.virtual_numa_node);
> + if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY &&
> + hv_dev->desc.virtual_numa_node < num_possible_nodes())
> + /*
> + * The kernel may boot with some NUMA nodes offline
> + * (e.g. in a KDUMP kernel) or with NUMA disabled via
> + * "numa=off". In those cases, adjust the host provided
> + * NUMA node to a valid NUMA node used by the kernel.
> + */
> + set_dev_node(&dev->dev,
> + numa_map_to_online_node(
> + hv_dev->desc.virtual_numa_node));
>
> put_pcichild(hv_dev);
> }
> --
> 2.25.1
>
> Subject: Re: [Patch v3] PCI: hv: Fix NUMA node assignment when kernel boots
> with custom NUMA topology
>
> On Wed, Jan 19, 2022 at 11:59:06AM -0800, [email protected] wrote:
> > From: Long Li <[email protected]>
> >
> > When kernel boots with a NUMA topology with some NUMA nodes offline,
> > the PCI driver should only set an online NUMA node on the device. This
> > can happen during KDUMP where some NUMA nodes are not made online by
> the KDUMP kernel.
> >
> > This patch also fixes the case where kernel is booting with "numa=off".
> >
> > Fixes: 999dd956d838 ("PCI: hv: Add support for protocol 1.3 and
> > support PCI_BUS_RELATIONS2")
> >
>
> No blank line here, please
>
> > Signed-off-by: Long Li <[email protected]>
>
> Everything below needs to be under "---" marker.
I'm sending v4 to address the comments.
Long
>
> Thanks
>
> >
> > Change log:
> > v2: use numa_map_to_online_node() to assign a node to device
> > (suggested by Michael Kelly <[email protected]>)
> >
> > v3: add "Fixes" and check for num_possible_nodes()
> > ---
> > drivers/pci/controller/pci-hyperv.c | 13 +++++++++++--
> > 1 file changed, 11 insertions(+), 2 deletions(-)
> >
> > diff --git a/drivers/pci/controller/pci-hyperv.c
> > b/drivers/pci/controller/pci-hyperv.c
> > index 6c9efeefae1b..b5276e81bb44 100644
> > --- a/drivers/pci/controller/pci-hyperv.c
> > +++ b/drivers/pci/controller/pci-hyperv.c
> > @@ -2129,8 +2129,17 @@ static void hv_pci_assign_numa_node(struct
> hv_pcibus_device *hbus)
> > if (!hv_dev)
> > continue;
> >
> > - if (hv_dev->desc.flags &
> HV_PCI_DEVICE_FLAG_NUMA_AFFINITY)
> > - set_dev_node(&dev->dev, hv_dev-
> >desc.virtual_numa_node);
> > + if (hv_dev->desc.flags &
> HV_PCI_DEVICE_FLAG_NUMA_AFFINITY &&
> > + hv_dev->desc.virtual_numa_node < num_possible_nodes())
> > + /*
> > + * The kernel may boot with some NUMA nodes offline
> > + * (e.g. in a KDUMP kernel) or with NUMA disabled via
> > + * "numa=off". In those cases, adjust the host provided
> > + * NUMA node to a valid NUMA node used by the kernel.
> > + */
> > + set_dev_node(&dev->dev,
> > + numa_map_to_online_node(
> > + hv_dev->desc.virtual_numa_node));
> >
> > put_pcichild(hv_dev);
> > }
> > --
> > 2.25.1
> >