After a LPM, the device tree node ibm,dynamic-reconfiguration-memory may be
updated by the hypervisor in the case the NUMA topology of the LPAR's
memory is updated.
This is caught by the kernel, but the memory's node is updated because
there is no way to move a memory block between nodes.
If later a memory block is added or removed, drmem_update_dt() is called
and it is overwriting the DT node to match the added or removed LMB. But
the LMB's associativity node has not been updated after the DT node update
and thus the node is overwritten by the Linux's topology instead of the
hypervisor one.
Introduce a hook called when the ibm,dynamic-reconfiguration-memory node is
updated to force an update of the LMB's associativity.
Cc: Tyrel Datwyler <[email protected]>
Signed-off-by: Laurent Dufour <[email protected]>
Change since V1:
- Take Tyrel's idea to rely on OF_RECONFIG_UPDATE_PROPERTY instead of
introducing a new hook mechanism.
---
arch/powerpc/include/asm/drmem.h | 1 +
arch/powerpc/mm/drmem.c | 35 +++++++++++++++++++
.../platforms/pseries/hotplug-memory.c | 4 +++
3 files changed, 40 insertions(+)
diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
index bf2402fed3e0..4265d5e95c2c 100644
--- a/arch/powerpc/include/asm/drmem.h
+++ b/arch/powerpc/include/asm/drmem.h
@@ -111,6 +111,7 @@ int drmem_update_dt(void);
int __init
walk_drmem_lmbs_early(unsigned long node, void *data,
int (*func)(struct drmem_lmb *, const __be32 **, void *));
+void drmem_update_lmbs(struct property *prop);
#endif
static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb)
diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
index 9af3832c9d8d..f0a6633132af 100644
--- a/arch/powerpc/mm/drmem.c
+++ b/arch/powerpc/mm/drmem.c
@@ -307,6 +307,41 @@ int __init walk_drmem_lmbs_early(unsigned long node, void *data,
return ret;
}
+/*
+ * Update the LMB associativity index.
+ */
+static int update_lmb(struct drmem_lmb *updated_lmb,
+ __maybe_unused const __be32 **usm,
+ __maybe_unused void *data)
+{
+ struct drmem_lmb *lmb;
+
+ /*
+ * Brut force there may be better way to fetch the LMB
+ */
+ for_each_drmem_lmb(lmb) {
+ if (lmb->drc_index != updated_lmb->drc_index)
+ continue;
+
+ lmb->aa_index = updated_lmb->aa_index;
+ break;
+ }
+ return 0;
+}
+
+/*
+ * Update the LMB associativity index.
+ *
+ * This needs to be called when the hypervisor is updating the
+ * dynamic-reconfiguration-memory node property.
+ */
+void drmem_update_lmbs(struct property *prop)
+{
+ if (!strcmp(prop->name, "ibm,dynamic-memory"))
+ __walk_drmem_v1_lmbs(prop->value, NULL, NULL, update_lmb);
+ else if (!strcmp(prop->name, "ibm,dynamic-memory-v2"))
+ __walk_drmem_v2_lmbs(prop->value, NULL, NULL, update_lmb);
+}
#endif
static int init_drmem_lmb_size(struct device_node *dn)
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 8377f1f7c78e..8aabaafc484b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -949,6 +949,10 @@ static int pseries_memory_notifier(struct notifier_block *nb,
case OF_RECONFIG_DETACH_NODE:
err = pseries_remove_mem_node(rd->dn);
break;
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ if (!strcmp(rd->dn->full_name,
+ "ibm,dynamic-reconfiguration-memory"))
+ drmem_update_lmbs(rd->prop);
}
return notifier_from_errno(err);
}
--
2.31.1
Michael, this is a v2 despite the mail's subject, sorry for the mess.
On 4/27/21 11:13 AM, Laurent Dufour wrote:
> After a LPM, the device tree node ibm,dynamic-reconfiguration-memory may be
> updated by the hypervisor in the case the NUMA topology of the LPAR's
> memory is updated.
>
> This is caught by the kernel, but the memory's node is updated because
> there is no way to move a memory block between nodes.
>
> If later a memory block is added or removed, drmem_update_dt() is called
> and it is overwriting the DT node to match the added or removed LMB. But
> the LMB's associativity node has not been updated after the DT node update
> and thus the node is overwritten by the Linux's topology instead of the
> hypervisor one.
>
> Introduce a hook called when the ibm,dynamic-reconfiguration-memory node is
> updated to force an update of the LMB's associativity.
>
> Cc: Tyrel Datwyler <[email protected]>
> Signed-off-by: Laurent Dufour <[email protected]>
>
> Change since V1:
> - Take Tyrel's idea to rely on OF_RECONFIG_UPDATE_PROPERTY instead of
> introducing a new hook mechanism.
> ---
> arch/powerpc/include/asm/drmem.h | 1 +
> arch/powerpc/mm/drmem.c | 35 +++++++++++++++++++
> .../platforms/pseries/hotplug-memory.c | 4 +++
> 3 files changed, 40 insertions(+)
>
> diff --git a/arch/powerpc/include/asm/drmem.h b/arch/powerpc/include/asm/drmem.h
> index bf2402fed3e0..4265d5e95c2c 100644
> --- a/arch/powerpc/include/asm/drmem.h
> +++ b/arch/powerpc/include/asm/drmem.h
> @@ -111,6 +111,7 @@ int drmem_update_dt(void);
> int __init
> walk_drmem_lmbs_early(unsigned long node, void *data,
> int (*func)(struct drmem_lmb *, const __be32 **, void *));
> +void drmem_update_lmbs(struct property *prop);
> #endif
>
> static inline void invalidate_lmb_associativity_index(struct drmem_lmb *lmb)
> diff --git a/arch/powerpc/mm/drmem.c b/arch/powerpc/mm/drmem.c
> index 9af3832c9d8d..f0a6633132af 100644
> --- a/arch/powerpc/mm/drmem.c
> +++ b/arch/powerpc/mm/drmem.c
> @@ -307,6 +307,41 @@ int __init walk_drmem_lmbs_early(unsigned long node, void *data,
> return ret;
> }
>
> +/*
> + * Update the LMB associativity index.
> + */
> +static int update_lmb(struct drmem_lmb *updated_lmb,
> + __maybe_unused const __be32 **usm,
> + __maybe_unused void *data)
> +{
> + struct drmem_lmb *lmb;
> +
> + /*
> + * Brut force there may be better way to fetch the LMB
> + */
> + for_each_drmem_lmb(lmb) {
> + if (lmb->drc_index != updated_lmb->drc_index)
> + continue;
> +
> + lmb->aa_index = updated_lmb->aa_index;
> + break;
> + }
> + return 0;
> +}
> +
> +/*
> + * Update the LMB associativity index.
> + *
> + * This needs to be called when the hypervisor is updating the
> + * dynamic-reconfiguration-memory node property.
> + */
> +void drmem_update_lmbs(struct property *prop)
> +{
> + if (!strcmp(prop->name, "ibm,dynamic-memory"))
> + __walk_drmem_v1_lmbs(prop->value, NULL, NULL, update_lmb);
> + else if (!strcmp(prop->name, "ibm,dynamic-memory-v2"))
> + __walk_drmem_v2_lmbs(prop->value, NULL, NULL, update_lmb);
> +}
> #endif
>
> static int init_drmem_lmb_size(struct device_node *dn)
> diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
> index 8377f1f7c78e..8aabaafc484b 100644
> --- a/arch/powerpc/platforms/pseries/hotplug-memory.c
> +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
> @@ -949,6 +949,10 @@ static int pseries_memory_notifier(struct notifier_block *nb,
> case OF_RECONFIG_DETACH_NODE:
> err = pseries_remove_mem_node(rd->dn);
> break;
> + case OF_RECONFIG_UPDATE_PROPERTY:
> + if (!strcmp(rd->dn->full_name,
Pretty much a self nit on myself since I just copied the device node name field
from your initial patch into my suggested code block.
It used to be that dn->full_name was intended to store the full device-tree path
name of the device node ane dn->name simply the base name. These days the values
of both name fields are simply the basename for pseries. Regardless,
rd->dn->name is technically correct and shorter.
-Tyrel
> + "ibm,dynamic-reconfiguration-memory"))
> + drmem_update_lmbs(rd->prop);
> }
> return notifier_from_errno(err);
> }
>