When NUMA is disabled on a NUMA-capable platform, UPI and M3UPI PMON
units are not enumerated.
In this case, pcibus_to_node() always returns NUMA_NO_NODE, causing
uncore_device_to_die() to return -1 for all PCI devices. As a result,
the corresponding PMON units are not added to the RB tree.
These PMON units are per-die resources, and their utility when NUMA is
disabled is limited. The driver does not prohibit their use, and the
enumeration should still work correctly.
Fix this by using uncore_pcibus_to_dieid(), which works regardless of
whether NUMA is enabled. This requires calling
snbep_pci2phy_map_init() in spr_uncore_pci_init().
Since pci_init() is called before mmio_init(), remove the redundant
snbep_pci2phy_map_init() call from spr_uncore_mmio_init(). If
snbep_pci2phy_map_init() fails, uncore driver should be bailed out,
so the fallback path in spr_uncore_mmio_init() can be removed.
Signed-off-by: Zide Chen <zide.chen@intel.com>
---
V6:
- Split from patch v5 3/4.
- Remove the redundant call in spr_uncore_mmio_init().
- Update commit messages.
---
arch/x86/events/intel/uncore.c | 1 +
arch/x86/events/intel/uncore_snbep.c | 26 +++++++++++---------------
2 files changed, 12 insertions(+), 15 deletions(-)
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 786bd51a0d89..e9cc1ba921c5 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -67,6 +67,7 @@ int uncore_die_to_segment(int die)
return bus ? pci_domain_nr(bus) : -EINVAL;
}
+/* Note: This API can only be used when NUMA information is available. */
int uncore_device_to_die(struct pci_dev *dev)
{
int node = pcibus_to_node(dev->bus);
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 8ee06d4659bb..73da1e88e286 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -6415,7 +6415,7 @@ static void spr_update_device_location(int type_id)
while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
- die = uncore_device_to_die(dev);
+ die = uncore_pcibus_to_dieid(dev->bus);
if (die < 0)
continue;
@@ -6439,6 +6439,10 @@ static void spr_update_device_location(int type_id)
int spr_uncore_pci_init(void)
{
+ int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
+ if (ret)
+ return ret;
+
/*
* The discovery table of UPI on some SPR variant is broken,
* which impacts the detection of both UPI and M3UPI uncore PMON.
@@ -6460,21 +6464,13 @@ int spr_uncore_pci_init(void)
void spr_uncore_mmio_init(void)
{
- int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
+ uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
+ UNCORE_SPR_MMIO_EXTRA_UNCORES,
+ spr_mmio_uncores,
+ UNCORE_SPR_NUM_UNCORE_TYPES,
+ spr_uncores);
- if (ret) {
- uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL,
- UNCORE_SPR_NUM_UNCORE_TYPES,
- spr_uncores);
- } else {
- uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
- UNCORE_SPR_MMIO_EXTRA_UNCORES,
- spr_mmio_uncores,
- UNCORE_SPR_NUM_UNCORE_TYPES,
- spr_uncores);
-
- spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
- }
+ spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
}
/* end of SPR uncore support */
--
2.53.0
On 3/31/2026 5:24 AM, Zide Chen wrote:
> When NUMA is disabled on a NUMA-capable platform, UPI and M3UPI PMON
> units are not enumerated.
>
> In this case, pcibus_to_node() always returns NUMA_NO_NODE, causing
> uncore_device_to_die() to return -1 for all PCI devices. As a result,
> the corresponding PMON units are not added to the RB tree.
>
> These PMON units are per-die resources, and their utility when NUMA is
> disabled is limited. The driver does not prohibit their use, and the
> enumeration should still work correctly.
>
> Fix this by using uncore_pcibus_to_dieid(), which works regardless of
> whether NUMA is enabled. This requires calling
> snbep_pci2phy_map_init() in spr_uncore_pci_init().
>
> Since pci_init() is called before mmio_init(), remove the redundant
> snbep_pci2phy_map_init() call from spr_uncore_mmio_init(). If
> snbep_pci2phy_map_init() fails, uncore driver should be bailed out,
> so the fallback path in spr_uncore_mmio_init() can be removed.
>
> Signed-off-by: Zide Chen <zide.chen@intel.com>
> ---
> V6:
> - Split from patch v5 3/4.
> - Remove the redundant call in spr_uncore_mmio_init().
> - Update commit messages.
> ---
> arch/x86/events/intel/uncore.c | 1 +
> arch/x86/events/intel/uncore_snbep.c | 26 +++++++++++---------------
> 2 files changed, 12 insertions(+), 15 deletions(-)
>
> diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
> index 786bd51a0d89..e9cc1ba921c5 100644
> --- a/arch/x86/events/intel/uncore.c
> +++ b/arch/x86/events/intel/uncore.c
> @@ -67,6 +67,7 @@ int uncore_die_to_segment(int die)
> return bus ? pci_domain_nr(bus) : -EINVAL;
> }
>
> +/* Note: This API can only be used when NUMA information is available. */
> int uncore_device_to_die(struct pci_dev *dev)
> {
> int node = pcibus_to_node(dev->bus);
> diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
> index 8ee06d4659bb..73da1e88e286 100644
> --- a/arch/x86/events/intel/uncore_snbep.c
> +++ b/arch/x86/events/intel/uncore_snbep.c
> @@ -6415,7 +6415,7 @@ static void spr_update_device_location(int type_id)
>
> while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
>
> - die = uncore_device_to_die(dev);
> + die = uncore_pcibus_to_dieid(dev->bus);
> if (die < 0)
> continue;
>
> @@ -6439,6 +6439,10 @@ static void spr_update_device_location(int type_id)
>
> int spr_uncore_pci_init(void)
> {
> + int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
> + if (ret)
> + return ret;
> +
> /*
> * The discovery table of UPI on some SPR variant is broken,
> * which impacts the detection of both UPI and M3UPI uncore PMON.
> @@ -6460,21 +6464,13 @@ int spr_uncore_pci_init(void)
>
> void spr_uncore_mmio_init(void)
> {
> - int ret = snbep_pci2phy_map_init(0x3250, SKX_CPUNODEID, SKX_GIDNIDMAP, true);
> + uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
> + UNCORE_SPR_MMIO_EXTRA_UNCORES,
> + spr_mmio_uncores,
> + UNCORE_SPR_NUM_UNCORE_TYPES,
> + spr_uncores);
>
> - if (ret) {
> - uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO, 0, NULL,
> - UNCORE_SPR_NUM_UNCORE_TYPES,
> - spr_uncores);
> - } else {
> - uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
> - UNCORE_SPR_MMIO_EXTRA_UNCORES,
> - spr_mmio_uncores,
> - UNCORE_SPR_NUM_UNCORE_TYPES,
> - spr_uncores);
> -
> - spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
> - }
> + spr_uncore_imc_free_running.num_boxes = uncore_type_max_boxes(uncore_mmio_uncores, UNCORE_SPR_IMC) / 2;
I'm not sure if we can directly remove the snbep_pci2phy_map_init() call
here. In theory, the snbep_pci2phy_map_init() call in spr_uncore_pci_init()
could fail and then spr_uncore_mmio_init() doesn't know it and directly
initializes MMIO PMU, then it could lead to the MMIO initialization fails.
Currently the PCI, CPU and MMIO initialization are totally independent,
only when the 3 types initialization all fail, then uncore PMU can abort.
```
if (uncore_init->pci_init) {
pret = uncore_init->pci_init();
if (!pret)
pret = uncore_pci_init();
}
if (uncore_init->cpu_init) {
uncore_init->cpu_init();
cret = uncore_cpu_init();
}
if (uncore_init->mmio_init) {
uncore_init->mmio_init();
mret = uncore_mmio_init();
}
if (cret && pret && mret) {
ret = -ENODEV;
goto free_discovery;
}
```
> }
>
> /* end of SPR uncore support */
© 2016 - 2026 Red Hat, Inc.