Previously, numa_off was set unconditionally in dummy_numa_init()
even with a fake numa node. Then ACPI sets node id as NUMA_NO_NODE(-1)
after acpi_map_pxm_to_node() because it regards numa_off as turning
off the numa node. Hence dev_dax->target_node is NUMA_NO_NODE on
arm64 with fake numa case.
Without this patch, pmem can't be probed as RAM devices on arm64 if
SRAT table isn't present:
$ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s 1g -a 64K
kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff] with invalid node: -1
kmem: probe of dax0.0 failed with error -22
This fixes it by using fallback memory_add_physaddr_to_nid() as nid.
Suggested-by: David Hildenbrand <[email protected]>
Signed-off-by: Jia He <[email protected]>
---
v2: - rebase it based on David's "memory group" patch.
- drop the changes in dev_dax_kmem_remove() since nid had been
removed in remove_memory().
drivers/dax/kmem.c | 31 +++++++++++++++++--------------
1 file changed, 17 insertions(+), 14 deletions(-)
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index a37622060fff..e4836eb7539e 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -47,20 +47,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
unsigned long total_len = 0;
struct dax_kmem_data *data;
int i, rc, mapped = 0;
- int numa_node;
-
- /*
- * Ensure good NUMA information for the persistent memory.
- * Without this check, there is a risk that slow memory
- * could be mixed in a node with faster memory, causing
- * unavoidable performance issues.
- */
- numa_node = dev_dax->target_node;
- if (numa_node < 0) {
- dev_warn(dev, "rejecting DAX region with invalid node: %d\n",
- numa_node);
- return -EINVAL;
- }
+ int numa_node = dev_dax->target_node;
for (i = 0; i < dev_dax->nr_range; i++) {
struct range range;
@@ -71,6 +58,22 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
i, range.start, range.end);
continue;
}
+
+ /*
+ * Ensure good NUMA information for the persistent memory.
+ * Without this check, there is a risk but not fatal that slow
+ * memory could be mixed in a node with faster memory, causing
+ * unavoidable performance issues. Warn this and use fallback
+ * node id.
+ */
+ if (numa_node < 0) {
+ int new_node = memory_add_physaddr_to_nid(range.start);
+
+ dev_info(dev, "changing nid from %d to %d for DAX region [%#llx-%#llx]\n",
+ numa_node, new_node, range.start, range.end);
+ numa_node = new_node;
+ }
+
total_len += range_len(&range);
}
--
2.17.1
On Fri, Sep 10, 2021 at 5:46 AM Jia He <[email protected]> wrote:
>
> Previously, numa_off was set unconditionally in dummy_numa_init()
> even with a fake numa node. Then ACPI sets node id as NUMA_NO_NODE(-1)
> after acpi_map_pxm_to_node() because it regards numa_off as turning
> off the numa node. Hence dev_dax->target_node is NUMA_NO_NODE on
> arm64 with fake numa case.
>
> Without this patch, pmem can't be probed as RAM devices on arm64 if
> SRAT table isn't present:
> $ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s 1g -a 64K
> kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff] with invalid node: -1
> kmem: probe of dax0.0 failed with error -22
>
> This fixes it by using fallback memory_add_physaddr_to_nid() as nid.
>
> Suggested-by: David Hildenbrand <[email protected]>
> Signed-off-by: Jia He <[email protected]>
> ---
> v2: - rebase it based on David's "memory group" patch.
> - drop the changes in dev_dax_kmem_remove() since nid had been
> removed in remove_memory().
> drivers/dax/kmem.c | 31 +++++++++++++++++--------------
> 1 file changed, 17 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> index a37622060fff..e4836eb7539e 100644
> --- a/drivers/dax/kmem.c
> +++ b/drivers/dax/kmem.c
> @@ -47,20 +47,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> unsigned long total_len = 0;
> struct dax_kmem_data *data;
> int i, rc, mapped = 0;
> - int numa_node;
> -
> - /*
> - * Ensure good NUMA information for the persistent memory.
> - * Without this check, there is a risk that slow memory
> - * could be mixed in a node with faster memory, causing
> - * unavoidable performance issues.
> - */
> - numa_node = dev_dax->target_node;
> - if (numa_node < 0) {
> - dev_warn(dev, "rejecting DAX region with invalid node: %d\n",
> - numa_node);
> - return -EINVAL;
> - }
> + int numa_node = dev_dax->target_node;
>
> for (i = 0; i < dev_dax->nr_range; i++) {
> struct range range;
> @@ -71,6 +58,22 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> i, range.start, range.end);
> continue;
> }
> +
> + /*
> + * Ensure good NUMA information for the persistent memory.
> + * Without this check, there is a risk but not fatal that slow
> + * memory could be mixed in a node with faster memory, causing
> + * unavoidable performance issues. Warn this and use fallback
> + * node id.
> + */
> + if (numa_node < 0) {
> + int new_node = memory_add_physaddr_to_nid(range.start);
> +
> + dev_info(dev, "changing nid from %d to %d for DAX region [%#llx-%#llx]\n",
> + numa_node, new_node, range.start, range.end);
> + numa_node = new_node;
> + }
> +
> total_len += range_len(&range);
This fallback change belongs where the parent region for the namespace
adopts its target_node, because it's not clear
memory_add_physaddr_to_nid() is the right fallback in all situations.
Here is where this setting is happening currently:
drivers/acpi/nfit/core.c:3004: ndr_desc->target_node =
pxm_to_node(spa->proximity_domain);
drivers/acpi/nfit/core.c:3007: ndr_desc->target_node = NUMA_NO_NODE;
drivers/nvdimm/e820.c:29: ndr_desc.target_node = nid;
drivers/nvdimm/of_pmem.c:58: ndr_desc.target_node =
ndr_desc.numa_node;
drivers/nvdimm/region_devs.c:1127: nd_region->target_node =
ndr_desc->target_node;
...where is this pmem region originating on this arm64 platform?
Hi Dan,
> -----Original Message-----
> From: Dan Williams <[email protected]>
> Sent: Friday, September 10, 2021 11:42 PM
> To: Justin He <[email protected]>
> Cc: Vishal Verma <[email protected]>; Dave Jiang
> <[email protected]>; David Hildenbrand <[email protected]>; Linux NVDIMM
> <[email protected]>; Linux Kernel Mailing List <linux-
> [email protected]>
> Subject: Re: [PATCH v2] device-dax: use fallback nid when numa node is
> invalid
>
> On Fri, Sep 10, 2021 at 5:46 AM Jia He <[email protected]> wrote:
> >
> > Previously, numa_off was set unconditionally in dummy_numa_init()
> > even with a fake numa node. Then ACPI sets node id as NUMA_NO_NODE(-1)
> > after acpi_map_pxm_to_node() because it regards numa_off as turning
> > off the numa node. Hence dev_dax->target_node is NUMA_NO_NODE on
> > arm64 with fake numa case.
> >
> > Without this patch, pmem can't be probed as RAM devices on arm64 if
> > SRAT table isn't present:
> > $ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s 1g
> -a 64K
> > kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff] with
> invalid node: -1
> > kmem: probe of dax0.0 failed with error -22
> >
> > This fixes it by using fallback memory_add_physaddr_to_nid() as nid.
> >
> > Suggested-by: David Hildenbrand <[email protected]>
> > Signed-off-by: Jia He <[email protected]>
> > ---
> > v2: - rebase it based on David's "memory group" patch.
> > - drop the changes in dev_dax_kmem_remove() since nid had been
> > removed in remove_memory().
> > drivers/dax/kmem.c | 31 +++++++++++++++++--------------
> > 1 file changed, 17 insertions(+), 14 deletions(-)
> >
> > diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> > index a37622060fff..e4836eb7539e 100644
> > --- a/drivers/dax/kmem.c
> > +++ b/drivers/dax/kmem.c
> > @@ -47,20 +47,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> > unsigned long total_len = 0;
> > struct dax_kmem_data *data;
> > int i, rc, mapped = 0;
> > - int numa_node;
> > -
> > - /*
> > - * Ensure good NUMA information for the persistent memory.
> > - * Without this check, there is a risk that slow memory
> > - * could be mixed in a node with faster memory, causing
> > - * unavoidable performance issues.
> > - */
> > - numa_node = dev_dax->target_node;
> > - if (numa_node < 0) {
> > - dev_warn(dev, "rejecting DAX region with invalid
> node: %d\n",
> > - numa_node);
> > - return -EINVAL;
> > - }
> > + int numa_node = dev_dax->target_node;
> >
> > for (i = 0; i < dev_dax->nr_range; i++) {
> > struct range range;
> > @@ -71,6 +58,22 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> > i, range.start, range.end);
> > continue;
> > }
> > +
> > + /*
> > + * Ensure good NUMA information for the persistent
> memory.
> > + * Without this check, there is a risk but not fatal
> that slow
> > + * memory could be mixed in a node with faster memory,
> causing
> > + * unavoidable performance issues. Warn this and use
> fallback
> > + * node id.
> > + */
> > + if (numa_node < 0) {
> > + int new_node =
> memory_add_physaddr_to_nid(range.start);
> > +
> > + dev_info(dev, "changing nid from %d to %d for
> DAX region [%#llx-%#llx]\n",
> > + numa_node, new_node, range.start,
> range.end);
> > + numa_node = new_node;
> > + }
> > +
> > total_len += range_len(&range);
>
> This fallback change belongs where the parent region for the namespace
> adopts its target_node, because it's not clear
> memory_add_physaddr_to_nid() is the right fallback in all situations.
> Here is where this setting is happening currently:
>
> drivers/acpi/nfit/core.c:3004: ndr_desc->target_node =
> pxm_to_node(spa->proximity_domain);
On my local arm64 guest('virt' machine type), the target_node is
set to -1 at this line.
That is:
The condition "spa->flags & ACPI_NFIT_PROXIMITY_VALID" is hit.
> drivers/acpi/nfit/core.c:3007: ndr_desc->target_node =
> NUMA_NO_NODE;
> drivers/nvdimm/e820.c:29: ndr_desc.target_node = nid;
> drivers/nvdimm/of_pmem.c:58: ndr_desc.target_node =
> ndr_desc.numa_node;
> drivers/nvdimm/region_devs.c:1127: nd_region->target_node =
> ndr_desc->target_node;
Sorry,Dan. I thought I missed your previous mail:
=========================================
Looks like it is the NFIT driver, thanks.
If you're getting NUMA_NO_NODE in dax_kmem from the NFIT driver in
means your ACPI NFIT table is failing to populate correct numa
information. You could try the following to fix it up, but I think the
real problem is that your platform BIOS needs to add the proper numa
data.
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index fb775b967c52..d3a0cec635b1 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -3005,15 +3005,8 @@ static int acpi_nfit_register_region(struct
acpi_nfit_desc *acpi_desc,
ndr_desc->res = &res;
ndr_desc->provider_data = nfit_spa;
ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
- if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
- ndr_desc->numa_node = acpi_map_pxm_to_online_node(
- spa->proximity_domain);
- ndr_desc->target_node = acpi_map_pxm_to_node(
- spa->proximity_domain);
- } else {
- ndr_desc->numa_node = NUMA_NO_NODE;
- ndr_desc->target_node = NUMA_NO_NODE;
- }
+ ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
+ ndr_desc->target_node = phys_to_target_node(spa->address);
/*
* Persistence domain bits are hierarchical, if
===================================================
Do you still suggest fixing like this?
--
Cheers,
Justin (Jia He)
On Mon, Sep 13, 2021 at 7:06 PM Justin He <[email protected]> wrote:
>
> Hi Dan,
>
> > -----Original Message-----
> > From: Dan Williams <[email protected]>
> > Sent: Friday, September 10, 2021 11:42 PM
> > To: Justin He <[email protected]>
> > Cc: Vishal Verma <[email protected]>; Dave Jiang
> > <[email protected]>; David Hildenbrand <[email protected]>; Linux NVDIMM
> > <[email protected]>; Linux Kernel Mailing List <linux-
> > [email protected]>
> > Subject: Re: [PATCH v2] device-dax: use fallback nid when numa node is
> > invalid
> >
> > On Fri, Sep 10, 2021 at 5:46 AM Jia He <[email protected]> wrote:
> > >
> > > Previously, numa_off was set unconditionally in dummy_numa_init()
> > > even with a fake numa node. Then ACPI sets node id as NUMA_NO_NODE(-1)
> > > after acpi_map_pxm_to_node() because it regards numa_off as turning
> > > off the numa node. Hence dev_dax->target_node is NUMA_NO_NODE on
> > > arm64 with fake numa case.
> > >
> > > Without this patch, pmem can't be probed as RAM devices on arm64 if
> > > SRAT table isn't present:
> > > $ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s 1g
> > -a 64K
> > > kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff] with
> > invalid node: -1
> > > kmem: probe of dax0.0 failed with error -22
> > >
> > > This fixes it by using fallback memory_add_physaddr_to_nid() as nid.
> > >
> > > Suggested-by: David Hildenbrand <[email protected]>
> > > Signed-off-by: Jia He <[email protected]>
> > > ---
> > > v2: - rebase it based on David's "memory group" patch.
> > > - drop the changes in dev_dax_kmem_remove() since nid had been
> > > removed in remove_memory().
> > > drivers/dax/kmem.c | 31 +++++++++++++++++--------------
> > > 1 file changed, 17 insertions(+), 14 deletions(-)
> > >
> > > diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> > > index a37622060fff..e4836eb7539e 100644
> > > --- a/drivers/dax/kmem.c
> > > +++ b/drivers/dax/kmem.c
> > > @@ -47,20 +47,7 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> > > unsigned long total_len = 0;
> > > struct dax_kmem_data *data;
> > > int i, rc, mapped = 0;
> > > - int numa_node;
> > > -
> > > - /*
> > > - * Ensure good NUMA information for the persistent memory.
> > > - * Without this check, there is a risk that slow memory
> > > - * could be mixed in a node with faster memory, causing
> > > - * unavoidable performance issues.
> > > - */
> > > - numa_node = dev_dax->target_node;
> > > - if (numa_node < 0) {
> > > - dev_warn(dev, "rejecting DAX region with invalid
> > node: %d\n",
> > > - numa_node);
> > > - return -EINVAL;
> > > - }
> > > + int numa_node = dev_dax->target_node;
> > >
> > > for (i = 0; i < dev_dax->nr_range; i++) {
> > > struct range range;
> > > @@ -71,6 +58,22 @@ static int dev_dax_kmem_probe(struct dev_dax *dev_dax)
> > > i, range.start, range.end);
> > > continue;
> > > }
> > > +
> > > + /*
> > > + * Ensure good NUMA information for the persistent
> > memory.
> > > + * Without this check, there is a risk but not fatal
> > that slow
> > > + * memory could be mixed in a node with faster memory,
> > causing
> > > + * unavoidable performance issues. Warn this and use
> > fallback
> > > + * node id.
> > > + */
> > > + if (numa_node < 0) {
> > > + int new_node =
> > memory_add_physaddr_to_nid(range.start);
> > > +
> > > + dev_info(dev, "changing nid from %d to %d for
> > DAX region [%#llx-%#llx]\n",
> > > + numa_node, new_node, range.start,
> > range.end);
> > > + numa_node = new_node;
> > > + }
> > > +
> > > total_len += range_len(&range);
> >
> > This fallback change belongs where the parent region for the namespace
> > adopts its target_node, because it's not clear
> > memory_add_physaddr_to_nid() is the right fallback in all situations.
> > Here is where this setting is happening currently:
> >
> > drivers/acpi/nfit/core.c:3004: ndr_desc->target_node =
> > pxm_to_node(spa->proximity_domain);
> On my local arm64 guest('virt' machine type), the target_node is
> set to -1 at this line.
> That is:
> The condition "spa->flags & ACPI_NFIT_PROXIMITY_VALID" is hit.
>
> > drivers/acpi/nfit/core.c:3007: ndr_desc->target_node =
> > NUMA_NO_NODE;
> > drivers/nvdimm/e820.c:29: ndr_desc.target_node = nid;
> > drivers/nvdimm/of_pmem.c:58: ndr_desc.target_node =
> > ndr_desc.numa_node;
> > drivers/nvdimm/region_devs.c:1127: nd_region->target_node =
> > ndr_desc->target_node;
>
>
> Sorry,Dan. I thought I missed your previous mail:
>
> =========================================
> Looks like it is the NFIT driver, thanks.
>
> If you're getting NUMA_NO_NODE in dax_kmem from the NFIT driver in
> means your ACPI NFIT table is failing to populate correct numa
> information. You could try the following to fix it up, but I think the
> real problem is that your platform BIOS needs to add the proper numa
> data.
>
> diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> index fb775b967c52..d3a0cec635b1 100644
> --- a/drivers/acpi/nfit/core.c
> +++ b/drivers/acpi/nfit/core.c
> @@ -3005,15 +3005,8 @@ static int acpi_nfit_register_region(struct
> acpi_nfit_desc *acpi_desc,
> ndr_desc->res = &res;
> ndr_desc->provider_data = nfit_spa;
> ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
> - if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
> - ndr_desc->numa_node = acpi_map_pxm_to_online_node(
> - spa->proximity_domain);
> - ndr_desc->target_node = acpi_map_pxm_to_node(
> - spa->proximity_domain);
> - } else {
> - ndr_desc->numa_node = NUMA_NO_NODE;
> - ndr_desc->target_node = NUMA_NO_NODE;
> - }
> + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
> + ndr_desc->target_node = phys_to_target_node(spa->address);
>
> /*
> * Persistence domain bits are hierarchical, if
> ===================================================
>
> Do you still suggest fixing like this?
Are you saying that ACPI_NFIT_PROXIMITY_VALID is not set on your
platform, or that pxm_to_node() returns NUMA_NO_NODE?
I would expect something like this:
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index a3ef6cce644c..95de7dc18ed8 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -3007,6 +3007,15 @@ static int acpi_nfit_register_region(struct
acpi_nfit_desc *acpi_desc,
ndr_desc->target_node = NUMA_NO_NODE;
}
+ /*
+ * Fallback to address based numa information if node lookup
+ * failed
+ */
+ if (ndr_desc->numa_node == NUMA_NO_NODE)
+ ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
+ if (ndr_desc->target_node == NUMA_NO_NODE)
+ phys_to_target_node(spa->address);
+
/*
* Persistence domain bits are hierarchical, if
* ACPI_NFIT_CAPABILITY_CACHE_FLUSH is set then
> -----Original Message-----
> From: Dan Williams <[email protected]>
> Sent: Wednesday, September 15, 2021 1:16 PM
> To: Justin He <[email protected]>
> Cc: Vishal Verma <[email protected]>; Dave Jiang
> <[email protected]>; David Hildenbrand <[email protected]>; Linux NVDIMM
> <[email protected]>; Linux Kernel Mailing List <linux-
> [email protected]>; nd <[email protected]>
> Subject: Re: [PATCH v2] device-dax: use fallback nid when numa node is
> invalid
>
> On Mon, Sep 13, 2021 at 7:06 PM Justin He <[email protected]> wrote:
> >
> > Hi Dan,
> >
> > > -----Original Message-----
> > > From: Dan Williams <[email protected]>
> > > Sent: Friday, September 10, 2021 11:42 PM
> > > To: Justin He <[email protected]>
> > > Cc: Vishal Verma <[email protected]>; Dave Jiang
> > > <[email protected]>; David Hildenbrand <[email protected]>; Linux
> NVDIMM
> > > <[email protected]>; Linux Kernel Mailing List <linux-
> > > [email protected]>
> > > Subject: Re: [PATCH v2] device-dax: use fallback nid when numa node is
> > > invalid
> > >
> > > On Fri, Sep 10, 2021 at 5:46 AM Jia He <[email protected]> wrote:
> > > >
> > > > Previously, numa_off was set unconditionally in dummy_numa_init()
> > > > even with a fake numa node. Then ACPI sets node id as NUMA_NO_NODE(-1)
> > > > after acpi_map_pxm_to_node() because it regards numa_off as turning
> > > > off the numa node. Hence dev_dax->target_node is NUMA_NO_NODE on
> > > > arm64 with fake numa case.
> > > >
> > > > Without this patch, pmem can't be probed as RAM devices on arm64 if
> > > > SRAT table isn't present:
> > > > $ndctl create-namespace -fe namespace0.0 --mode=devdax --map=dev -s
> 1g
> > > -a 64K
> > > > kmem dax0.0: rejecting DAX region [mem 0x240400000-0x2bfffffff]
> with
> > > invalid node: -1
> > > > kmem: probe of dax0.0 failed with error -22
> > > >
> > > > This fixes it by using fallback memory_add_physaddr_to_nid() as nid.
> > > >
> > > > Suggested-by: David Hildenbrand <[email protected]>
> > > > Signed-off-by: Jia He <[email protected]>
> > > > ---
> > > > v2: - rebase it based on David's "memory group" patch.
> > > > - drop the changes in dev_dax_kmem_remove() since nid had been
> > > > removed in remove_memory().
> > > > drivers/dax/kmem.c | 31 +++++++++++++++++--------------
> > > > 1 file changed, 17 insertions(+), 14 deletions(-)
> > > >
> > > > diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
> > > > index a37622060fff..e4836eb7539e 100644
> > > > --- a/drivers/dax/kmem.c
> > > > +++ b/drivers/dax/kmem.c
> > > > @@ -47,20 +47,7 @@ static int dev_dax_kmem_probe(struct dev_dax
> *dev_dax)
> > > > unsigned long total_len = 0;
> > > > struct dax_kmem_data *data;
> > > > int i, rc, mapped = 0;
> > > > - int numa_node;
> > > > -
> > > > - /*
> > > > - * Ensure good NUMA information for the persistent memory.
> > > > - * Without this check, there is a risk that slow memory
> > > > - * could be mixed in a node with faster memory, causing
> > > > - * unavoidable performance issues.
> > > > - */
> > > > - numa_node = dev_dax->target_node;
> > > > - if (numa_node < 0) {
> > > > - dev_warn(dev, "rejecting DAX region with invalid
> > > node: %d\n",
> > > > - numa_node);
> > > > - return -EINVAL;
> > > > - }
> > > > + int numa_node = dev_dax->target_node;
> > > >
> > > > for (i = 0; i < dev_dax->nr_range; i++) {
> > > > struct range range;
> > > > @@ -71,6 +58,22 @@ static int dev_dax_kmem_probe(struct dev_dax
> *dev_dax)
> > > > i, range.start, range.end);
> > > > continue;
> > > > }
> > > > +
> > > > + /*
> > > > + * Ensure good NUMA information for the persistent
> > > memory.
> > > > + * Without this check, there is a risk but not fatal
> > > that slow
> > > > + * memory could be mixed in a node with faster memory,
> > > causing
> > > > + * unavoidable performance issues. Warn this and use
> > > fallback
> > > > + * node id.
> > > > + */
> > > > + if (numa_node < 0) {
> > > > + int new_node =
> > > memory_add_physaddr_to_nid(range.start);
> > > > +
> > > > + dev_info(dev, "changing nid from %d to %d for
> > > DAX region [%#llx-%#llx]\n",
> > > > + numa_node, new_node, range.start,
> > > range.end);
> > > > + numa_node = new_node;
> > > > + }
> > > > +
> > > > total_len += range_len(&range);
> > >
> > > This fallback change belongs where the parent region for the namespace
> > > adopts its target_node, because it's not clear
> > > memory_add_physaddr_to_nid() is the right fallback in all situations.
> > > Here is where this setting is happening currently:
> > >
> > > drivers/acpi/nfit/core.c:3004: ndr_desc->target_node =
> > > pxm_to_node(spa->proximity_domain);
> > On my local arm64 guest('virt' machine type), the target_node is
> > set to -1 at this line.
> > That is:
> > The condition "spa->flags & ACPI_NFIT_PROXIMITY_VALID" is hit.
> >
> > > drivers/acpi/nfit/core.c:3007: ndr_desc->target_node =
> > > NUMA_NO_NODE;
> > > drivers/nvdimm/e820.c:29: ndr_desc.target_node = nid;
> > > drivers/nvdimm/of_pmem.c:58: ndr_desc.target_node =
> > > ndr_desc.numa_node;
> > > drivers/nvdimm/region_devs.c:1127: nd_region->target_node =
> > > ndr_desc->target_node;
> >
> >
> > Sorry,Dan. I thought I missed your previous mail:
> >
> > =========================================
> > Looks like it is the NFIT driver, thanks.
> >
> > If you're getting NUMA_NO_NODE in dax_kmem from the NFIT driver in
> > means your ACPI NFIT table is failing to populate correct numa
> > information. You could try the following to fix it up, but I think the
> > real problem is that your platform BIOS needs to add the proper numa
> > data.
> >
> > diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> > index fb775b967c52..d3a0cec635b1 100644
> > --- a/drivers/acpi/nfit/core.c
> > +++ b/drivers/acpi/nfit/core.c
> > @@ -3005,15 +3005,8 @@ static int acpi_nfit_register_region(struct
> > acpi_nfit_desc *acpi_desc,
> > ndr_desc->res = &res;
> > ndr_desc->provider_data = nfit_spa;
> > ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
> > - if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
> > - ndr_desc->numa_node = acpi_map_pxm_to_online_node(
> > - spa->proximity_domain);
> > - ndr_desc->target_node = acpi_map_pxm_to_node(
> > - spa->proximity_domain);
> > - } else {
> > - ndr_desc->numa_node = NUMA_NO_NODE;
> > - ndr_desc->target_node = NUMA_NO_NODE;
> > - }
> > + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
> > + ndr_desc->target_node = phys_to_target_node(spa->address);
> >
> > /*
> > * Persistence domain bits are hierarchical, if
> > ===================================================
> >
> > Do you still suggest fixing like this?
>
> Are you saying that ACPI_NFIT_PROXIMITY_VALID is not set on your
> platform, or that pxm_to_node() returns NUMA_NO_NODE?
>
Latter, ACPI_NFIT_PROXIMITY_VALID is *set* in my case.
> I would expect something like this:
>
> diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> index a3ef6cce644c..95de7dc18ed8 100644
> --- a/drivers/acpi/nfit/core.c
> +++ b/drivers/acpi/nfit/core.c
> @@ -3007,6 +3007,15 @@ static int acpi_nfit_register_region(struct
> acpi_nfit_desc *acpi_desc,
> ndr_desc->target_node = NUMA_NO_NODE;
> }
>
> + /*
> + * Fallback to address based numa information if node lookup
> + * failed
> + */
> + if (ndr_desc->numa_node == NUMA_NO_NODE)
> + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa-
> >address);
> + if (ndr_desc->target_node == NUMA_NO_NODE)
> + phys_to_target_node(spa->address);
> +
Would it better to add a dev_info() here to report this node id changing?
--
Cheers,
Justin (Jia He)
On Tue, Sep 14, 2021 at 11:51 PM Justin He <[email protected]> wrote:
[..]
> > > diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> > > index fb775b967c52..d3a0cec635b1 100644
> > > --- a/drivers/acpi/nfit/core.c
> > > +++ b/drivers/acpi/nfit/core.c
> > > @@ -3005,15 +3005,8 @@ static int acpi_nfit_register_region(struct
> > > acpi_nfit_desc *acpi_desc,
> > > ndr_desc->res = &res;
> > > ndr_desc->provider_data = nfit_spa;
> > > ndr_desc->attr_groups = acpi_nfit_region_attribute_groups;
> > > - if (spa->flags & ACPI_NFIT_PROXIMITY_VALID) {
> > > - ndr_desc->numa_node = acpi_map_pxm_to_online_node(
> > > - spa->proximity_domain);
> > > - ndr_desc->target_node = acpi_map_pxm_to_node(
> > > - spa->proximity_domain);
> > > - } else {
> > > - ndr_desc->numa_node = NUMA_NO_NODE;
> > > - ndr_desc->target_node = NUMA_NO_NODE;
> > > - }
> > > + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa->address);
> > > + ndr_desc->target_node = phys_to_target_node(spa->address);
> > >
> > > /*
> > > * Persistence domain bits are hierarchical, if
> > > ===================================================
> > >
> > > Do you still suggest fixing like this?
> >
> > Are you saying that ACPI_NFIT_PROXIMITY_VALID is not set on your
> > platform, or that pxm_to_node() returns NUMA_NO_NODE?
> >
> Latter, ACPI_NFIT_PROXIMITY_VALID is *set* in my case.
>
> > I would expect something like this:
> >
> > diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
> > index a3ef6cce644c..95de7dc18ed8 100644
> > --- a/drivers/acpi/nfit/core.c
> > +++ b/drivers/acpi/nfit/core.c
> > @@ -3007,6 +3007,15 @@ static int acpi_nfit_register_region(struct
> > acpi_nfit_desc *acpi_desc,
> > ndr_desc->target_node = NUMA_NO_NODE;
> > }
> >
> > + /*
> > + * Fallback to address based numa information if node lookup
> > + * failed
> > + */
> > + if (ndr_desc->numa_node == NUMA_NO_NODE)
> > + ndr_desc->numa_node = memory_add_physaddr_to_nid(spa-
> > >address);
> > + if (ndr_desc->target_node == NUMA_NO_NODE)
> > + phys_to_target_node(spa->address);
> > +
>
> Would it better to add a dev_info() here to report this node id changing?
Yes, given all the possibilities here, a dev_info() reporting the
final result of the node mapping is justifiable.