Skip to contentSkip to conversation

libnvdimm: Use max contiguous area for namespace size

PATCH Superseded Keith Busch 2 participants 12 messages Jul 5, 2018 – Jul 12, 2018

Subsystems (2)

v2 of 4 Superseded Latest is v4 →

lore
Share & tools
lore
#0 lore raw

PATCH v2 1/2 libnvdimm: Use max contiguous area for namespace size

This patch will find the max contiguous area to determine the largest namespace size that can be created. If the requested size exceeds the largest available, ENOSPC error will be returned.

This fixes the allocation underrun error and wrong error return code that have otherwise been observed as the following kernel warning:

  WARNING: CPU: <CPU> PID: <PID> at drivers/nvdimm/namespace_devs.c:913 size_store
Fixes a1f3e4d6a0c3 ("libnvdimm, region: update nd_region_available_dpa() for multi-pmem support")

---
v1 -> v2:

Updated changelog to indicate the warning this patch fixes and copy stable.

Fixed code comments with the correct name of a function

 drivers/nvdimm/dimm_devs.c      | 29 +++++++++++++++++++++++++++++
 drivers/nvdimm/namespace_devs.c |  2 +-
 drivers/nvdimm/nd-core.h        |  3 +++
 drivers/nvdimm/region_devs.c    | 23 +++++++++++++++++++++++
 4 files changed, 56 insertions(+), 1 deletion(-)
drivers/nvdimm/dimm_devs.c +29 -0
index 8d348b22ba45..791a93cd8eb1 100644
@@ -536,6 +536,35 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 	return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *				contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+					   struct nd_mapping *nd_mapping)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	resource_size_t start, end, max = 0;
+	struct resource *res;
+
+	if (!ndd)
+		return 0;
+
+	start = nd_mapping->start;
+	end = start + nd_mapping->size;
+
+	for_each_dpa_resource(ndd, res) {
+		if ((res->start - start) > max)
+			max = res->start - start;
+		start = res->start + resource_size(res);
+	}
+	if (start < end && end - start > max)
+		max = end - start;
+	return max;
+}
+
 /**
  * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
  * @nd_mapping: container of dpa-resource-root + labels
drivers/nvdimm/namespace_devs.c +1 -1
index 28afdd668905..c00d1d2d48f9 100644
@@ -1032,7 +1032,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 
 		allocated += nvdimm_allocated_dpa(ndd, &label_id);
 	}
-	available = nd_region_available_dpa(nd_region);
+	available = nd_region_contiguous_max(nd_region);
 
 	if (val > available + allocated)
 		return -ENOSPC;
drivers/nvdimm/nd-core.h +3 -0
index 79274ead54fb..8e4acd075b0f 100644
@@ -100,6 +100,9 @@ struct nd_region;
 struct nvdimm_drvdata;
 struct nd_mapping;
 void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+					   struct nd_mapping *nd_mapping);
+resource_size_t nd_region_contiguous_max(struct nd_region *nd_region);
 resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, resource_size_t *overlap);
 resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
drivers/nvdimm/region_devs.c +23 -0
index ec3543b83330..8af483d7ef57 100644
@@ -357,6 +357,29 @@ static ssize_t set_cookie_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(set_cookie);
 
+resource_size_t nd_region_contiguous_max(struct nd_region *nd_region)
+{
+	resource_size_t available = 0;
+	int i;
+
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+
+		/* if a dimm is disabled the available capacity is zero */
+		if (!ndd)
+			return 0;
+
+		if (is_memory(&nd_region->dev))
+			available += nd_pmem_max_contiguous_dpa(nd_region,
+								nd_mapping);
+		else if (is_nd_blk(&nd_region->dev))
+			available += nd_blk_available_dpa(nd_region);
+	}
+	return available;
+}
+
 resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
 {
 	resource_size_t blk_max_overlap = 0, available, overlap;
Signature · 6 lines
2.14.3

_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm
#1 lore raw

PATCH v2 2/2 libnvdimm: Export max available extent

The 'available_size' attribute showing the combined total of all unallocated space isn't always useful to know how large of a namespace a user may be able to allocate if the region is fragmented. This patch will export the largest extent of contiguous unallocated space that may be allocated to create a new namespace.

---
 drivers/nvdimm/region_devs.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)
drivers/nvdimm/region_devs.c +16 -0
index 8af483d7ef57..82aaf7d6488d 100644
@@ -433,6 +433,21 @@ static ssize_t available_size_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(available_size);
 
+static ssize_t max_available_extent_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nd_region *nd_region = to_nd_region(dev);
+	unsigned long long available = 0;
+
+	nvdimm_bus_lock(dev);
+	wait_nvdimm_bus_probe_idle(dev);
+	available = nd_region_contiguous_max(nd_region);
+	nvdimm_bus_unlock(dev);
+
+	return sprintf(buf, "%llu\n", available);
+}
+static DEVICE_ATTR_RO(max_available_extent);
+
 static ssize_t init_namespaces_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
@@ -584,6 +599,7 @@ static struct attribute *nd_region_attributes[] = {
 	&dev_attr_read_only.attr,
 	&dev_attr_set_cookie.attr,
 	&dev_attr_available_size.attr,
+	&dev_attr_max_available_extent.attr,
 	&dev_attr_namespace_seed.attr,
 	&dev_attr_init_namespaces.attr,
 	&dev_attr_badblocks.attr,
Signature · 6 lines
2.14.3

_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm
#2 lore raw

Re: [PATCHv2 2/2] libnvdimm: Export max available extent

Quoted 7 lines · Keith Busch

The 'available_size' attribute showing the combined total of all unallocated space isn't always useful to know how large of a namespace a user may be able to allocate if the region is fragmented. This patch will export the largest extent of contiguous unallocated space that may be allocated to create a new namespace.

Looks good to me, applied to my for-4.19/libnvdimm tracking branch.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#3 lore raw
In reply to Keith Busch
Quoted 12 lines · Keith Busch

This patch will find the max contiguous area to determine the largest namespace size that can be created. If the requested size exceeds the largest available, ENOSPC error will be returned.

This fixes the allocation underrun error and wrong error return code that have otherwise been observed as the following kernel warning:

  WARNING: CPU: <CPU> PID: <PID> at drivers/nvdimm/namespace_devs.c:913 size_store
Fixes a1f3e4d6a0c3 ("libnvdimm, region: update nd_region_available_dpa() for multi-pmem support")
Quoted 7 lines

---
v1 -> v2:

Updated changelog to indicate the warning this patch fixes and copy stable.

Fixed code comments with the correct name of a function

Looks good to me, applied to my for-4.18/libnvdimm tracking branch.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#4 lore raw
Quoted 16 lines · Dan Williams
Quoted 15 lines · Keith Busch

This patch will find the max contiguous area to determine the largest namespace size that can be created. If the requested size exceeds the largest available, ENOSPC error will be returned.

This fixes the allocation underrun error and wrong error return code that have otherwise been observed as the following kernel warning:

  WARNING: CPU: <CPU> PID: <PID> at drivers/nvdimm/namespace_devs.c:913 size_store
Fixes a1f3e4d6a0c3 ("libnvdimm, region: update nd_region_available_dpa() for multi-pmem support")

---
v1 -> v2:

Quoted 6 lines
Quoted 4 lines

Updated changelog to indicate the warning this patch fixes and copy stable.

Fixed code comments with the correct name of a function

Looks good to me, applied to my for-4.18/libnvdimm tracking branch.

I take it back, this is causing the libndctl unit test to fail. debugging...
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#5 lore raw
In reply to Keith Busch
Quoted 52 lines · Keith Busch

This patch will find the max contiguous area to determine the largest namespace size that can be created. If the requested size exceeds the largest available, ENOSPC error will be returned.

This fixes the allocation underrun error and wrong error return code that have otherwise been observed as the following kernel warning:

  WARNING: CPU: <CPU> PID: <PID> at drivers/nvdimm/namespace_devs.c:913 size_store
Fixes a1f3e4d6a0c3 ("libnvdimm, region: update nd_region_available_dpa() for multi-pmem support")

---
v1 -> v2:

Updated changelog to indicate the warning this patch fixes and copy stable.

Fixed code comments with the correct name of a function

 drivers/nvdimm/dimm_devs.c      | 29 +++++++++++++++++++++++++++++
 drivers/nvdimm/namespace_devs.c |  2 +-
 drivers/nvdimm/nd-core.h        |  3 +++
 drivers/nvdimm/region_devs.c    | 23 +++++++++++++++++++++++
 4 files changed, 56 insertions(+), 1 deletion(-)
drivers/nvdimm/dimm_devs.c +1 -0
index 8d348b22ba45..791a93cd8eb1 100644
@@ -536,6 +536,35 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**

x + * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ * contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */

drivers/nvdimm/dimm_devs.c +12 -0
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+       resource_size_t start, end, max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       start = nd_mapping->start;
+       end = start + nd_mapping->size;

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 566

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+
+       for_each_dpa_resource(ndd, res) {
+               if ((res->start - start) > max)
+                       max = res->start - start;
+               start = res->start + resource_size(res);
+       }
+       if (start < end && end - start > max)
+               max = end - start;
+       return max;
+}

So, I liked how simple and straightforward this was, but the unit test reminded me how complicated the free space allocation could be given that we still might need to account for aliased BLK capacity.

A few things I now notice:

* It is possible for a dpa resource to start before nd_mapping->start and/or end after nd_mapping->size. See the diagram in tools/testing/nvdimm/test/nfit.c

* We need to be summing the max extents across all DIMMs in the set while also accounting for this BLK overlap problem that nd_pmem_available_dpa() handles.

The original bug arose from the fact that the nd_region_available_dpa() accounts for total busy capacity and the allocation path looks for extents. It would be nice to unify those two functions... or maybe standardize on scan_allocate() everywhere.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#6 lore raw
Quoted 74 lines · Dan Williams
Quoted 52 lines · Keith Busch

This patch will find the max contiguous area to determine the largest namespace size that can be created. If the requested size exceeds the largest available, ENOSPC error will be returned.

This fixes the allocation underrun error and wrong error return code that have otherwise been observed as the following kernel warning:

  WARNING: CPU: <CPU> PID: <PID> at drivers/nvdimm/namespace_devs.c:913 size_store
Fixes a1f3e4d6a0c3 ("libnvdimm, region: update nd_region_available_dpa() for multi-pmem support")

---
v1 -> v2:

Updated changelog to indicate the warning this patch fixes and copy stable.

Fixed code comments with the correct name of a function

 drivers/nvdimm/dimm_devs.c      | 29 +++++++++++++++++++++++++++++
 drivers/nvdimm/namespace_devs.c |  2 +-
 drivers/nvdimm/nd-core.h        |  3 +++
 drivers/nvdimm/region_devs.c    | 23 +++++++++++++++++++++++
 4 files changed, 56 insertions(+), 1 deletion(-)
drivers/nvdimm/dimm_devs.c +1 -0
index 8d348b22ba45..791a93cd8eb1 100644
@@ -536,6 +536,35 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**

x + * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ * contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */

drivers/nvdimm/dimm_devs.c +12 -0
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+       resource_size_t start, end, max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       start = nd_mapping->start;
+       end = start + nd_mapping->size;

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 566

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+
+       for_each_dpa_resource(ndd, res) {
+               if ((res->start - start) > max)
+                       max = res->start - start;
+               start = res->start + resource_size(res);
+       }
+       if (start < end && end - start > max)
+               max = end - start;
+       return max;
+}

So, I liked how simple and straightforward this was, but the unit test reminded me how complicated the free space allocation could be given that we still might need to account for aliased BLK capacity.

A few things I now notice:

* It is possible for a dpa resource to start before nd_mapping->start and/or end after nd_mapping->size. See the diagram in tools/testing/nvdimm/test/nfit.c

Quoted 8 lines

* We need to be summing the max extents across all DIMMs in the set while also accounting for this BLK overlap problem that nd_pmem_available_dpa() handles.

The original bug arose from the fact that the nd_region_available_dpa() accounts for total busy capacity and the allocation path looks for extents. It would be nice to unify those two functions... or maybe standardize on scan_allocate() everywhere.

I think you can redo this using reserve_free_pmem() and then find the largest free space reservation after accounting for blk_max_overlap as calculated by nd_region_available_dpa().

reserve_free_pmem() inserts resources into the dpa resource tree with the name "pmem-reserve" then you need to filter those against blk_max_overlap to find which ones might appear free, but shadowed by a BLK allocation on one of the DIMMs in the set. Yes, it allocates memory and is heavy handed, but I'm having a hard time thinking of something better at the moment.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#7 lore raw
Quoted 24 lines · Dan Williams
Quoted 10 lines · Dan Williams

So, I liked how simple and straightforward this was, but the unit test reminded me how complicated the free space allocation could be given that we still might need to account for aliased BLK capacity.

A few things I now notice:

* It is possible for a dpa resource to start before nd_mapping->start and/or end after nd_mapping->size. See the diagram in tools/testing/nvdimm/test/nfit.c

Quoted 8 lines

* We need to be summing the max extents across all DIMMs in the set while also accounting for this BLK overlap problem that nd_pmem_available_dpa() handles.

The original bug arose from the fact that the nd_region_available_dpa() accounts for total busy capacity and the allocation path looks for extents. It would be nice to unify those two functions... or maybe standardize on scan_allocate() everywhere.

I think you can redo this using reserve_free_pmem() and then find the largest free space reservation after accounting for blk_max_overlap as calculated by nd_region_available_dpa().

Quoted 6 lines

reserve_free_pmem() inserts resources into the dpa resource tree with the name "pmem-reserve" then you need to filter those against blk_max_overlap to find which ones might appear free, but shadowed by a BLK allocation on one of the DIMMs in the set. Yes, it allocates memory and is heavy handed, but I'm having a hard time thinking of something better at the moment.

Okay, I think I follow what you're saying, but let me just see if the following is what you had in mind before sending a v3:

---

drivers/nvdimm/dimm_devs.c +25 -0
index 8d348b22ba45..f30e0c3b0282 100644
@@ -536,6 +536,31 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
 	return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *				contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+					   struct nd_mapping *nd_mapping)
+{
+	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+	resource_size_t max = 0;
+	struct resource *res;
+
+	if (!ndd)
+		return 0;
+
+	for_each_dpa_resource(ndd, res) {
+		if (strcmp(res->name, "pmem-reserve") != 0)
+			continue;
+		if (resource_size(res) > max)
+			max = resource_size(res);
+	}
+	return max;
+}
+
 /**
  * nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
  * @nd_mapping: container of dpa-resource-root + labels
drivers/nvdimm/namespace_devs.c +3 -3
index 28afdd668905..ba5120aba9bf 100644
@@ -836,7 +836,7 @@ static int __reserve_free_pmem(struct device *dev, void *data)
 	return 0;
 }
 
-static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
+void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
 		struct nd_mapping *nd_mapping)
 {
 	struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
@@ -847,7 +847,7 @@ static void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
 			nvdimm_free_dpa(ndd, res);
 }
 
-static int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
+int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
 		struct nd_mapping *nd_mapping)
 {
 	struct nvdimm *nvdimm = nd_mapping->nvdimm;
@@ -1032,7 +1032,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
 
 		allocated += nvdimm_allocated_dpa(ndd, &label_id);
 	}
-	available = nd_region_available_dpa(nd_region);
+	available = nd_region_contiguous_max(nd_region);
 
 	if (val > available + allocated)
 		return -ENOSPC;
drivers/nvdimm/nd-core.h +9 -0
index 79274ead54fb..391b97e5c820 100644
@@ -100,6 +100,15 @@ struct nd_region;
 struct nvdimm_drvdata;
 struct nd_mapping;
 void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
+
+int reserve_free_pmem(struct nvdimm_bus *nvdimm_bus,
+		      struct nd_mapping *nd_mapping);
+void release_free_pmem(struct nvdimm_bus *nvdimm_bus,
+		       struct nd_mapping *nd_mapping);
+
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+					   struct nd_mapping *nd_mapping);
+resource_size_t nd_region_contiguous_max(struct nd_region *nd_region);
 resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
 		struct nd_mapping *nd_mapping, resource_size_t *overlap);
 resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
drivers/nvdimm/region_devs.c +29 -0
index ec3543b83330..48b3bd5219d2 100644
@@ -357,6 +357,35 @@ static ssize_t set_cookie_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(set_cookie);
 
+resource_size_t nd_region_contiguous_max(struct nd_region *nd_region)
+{
+	struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+	resource_size_t available = 0;
+	int i, rc;
+
+	WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
+	for (i = 0; i < nd_region->ndr_mappings; i++) {
+		struct nd_mapping *nd_mapping = &nd_region->mapping[i];
+		struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+
+		/* if a dimm is disabled the available capacity is zero */
+		if (!ndd)
+			return 0;
+
+
+		if (is_memory(&nd_region->dev)) {
+			rc = reserve_free_pmem(nvdimm_bus, nd_mapping);
+			if (rc)
+				return 0;
+			available += nd_pmem_max_contiguous_dpa(nd_region,
+								nd_mapping);
+			release_free_pmem(nvdimm_bus, nd_mapping);
+		} else if (is_nd_blk(&nd_region->dev))
+			available += nd_blk_available_dpa(nd_region);
+	}
+	return available;
+}
+
 resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
 {
 	resource_size_t blk_max_overlap = 0, available, overlap;

--
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#8 lore raw
Quoted 32 lines · Keith Busch
Quoted 24 lines · Dan Williams
Quoted 10 lines · Dan Williams

So, I liked how simple and straightforward this was, but the unit test reminded me how complicated the free space allocation could be given that we still might need to account for aliased BLK capacity.

A few things I now notice:

* It is possible for a dpa resource to start before nd_mapping->start and/or end after nd_mapping->size. See the diagram in tools/testing/nvdimm/test/nfit.c

Quoted 8 lines

* We need to be summing the max extents across all DIMMs in the set while also accounting for this BLK overlap problem that nd_pmem_available_dpa() handles.

The original bug arose from the fact that the nd_region_available_dpa() accounts for total busy capacity and the allocation path looks for extents. It would be nice to unify those two functions... or maybe standardize on scan_allocate() everywhere.

I think you can redo this using reserve_free_pmem() and then find the largest free space reservation after accounting for blk_max_overlap as calculated by nd_region_available_dpa().

Quoted 6 lines

reserve_free_pmem() inserts resources into the dpa resource tree with the name "pmem-reserve" then you need to filter those against blk_max_overlap to find which ones might appear free, but shadowed by a BLK allocation on one of the DIMMs in the set. Yes, it allocates memory and is heavy handed, but I'm having a hard time thinking of something better at the moment.

Quoted 2 lines

Okay, I think I follow what you're saying, but let me just see if the following is what you had in mind before sending a v3:

This is going in the right direction... but still needs to account for the blk_overlap.

So, on a given DIMM BLK capacity is allocated from the top of DPA space going down and PMEM capacity is allocated from the bottom of the DPA space going up.

Since BLK capacity is single DIMM, and PMEM capacity is striped you could get into the situation where one DIMM is fully allocated for BLK usage and that would shade / remove the possibility to use the PMEM capacity on the other DIMMs in the PMEM set. PMEM needs all the same DPAs in all the DIMMs to be free.

Quoted 20 lines

---

drivers/nvdimm/dimm_devs.c +10 -0
index 8d348b22ba45..f30e0c3b0282 100644
@@ -536,6 +536,31 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *                             contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 558

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+       resource_size_t max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       for_each_dpa_resource(ndd, res) {
+               if (strcmp(res->name, "pmem-reserve") != 0)
+                       continue;
+               if (resource_size(res) > max)

...so instead straight resource_size() here you need trim the end of this "pmem-reserve" resource to the start of the first BLK allocation in any of the DIMMs in the set.

See blk_start calculation in nd_pmem_available_dpa().
_______________________________________________
Linux-nvdimm mailing list [email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#9 lore raw
Quoted 48 lines · Dan Williams

This is going in the right direction... but still needs to account for the blk_overlap.

So, on a given DIMM BLK capacity is allocated from the top of DPA space going down and PMEM capacity is allocated from the bottom of the DPA space going up.

Since BLK capacity is single DIMM, and PMEM capacity is striped you could get into the situation where one DIMM is fully allocated for BLK usage and that would shade / remove the possibility to use the PMEM capacity on the other DIMMs in the PMEM set. PMEM needs all the same DPAs in all the DIMMs to be free.

Quoted 20 lines

---

drivers/nvdimm/dimm_devs.c +10 -0
index 8d348b22ba45..f30e0c3b0282 100644
@@ -536,6 +536,31 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *                             contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 558

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+       resource_size_t max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       for_each_dpa_resource(ndd, res) {
+               if (strcmp(res->name, "pmem-reserve") != 0)
+                       continue;
+               if (resource_size(res) > max)

...so instead straight resource_size() here you need trim the end of this "pmem-reserve" resource to the start of the first BLK allocation in any of the DIMMs in the set.

Quoted 1 line

See blk_start calculation in nd_pmem_available_dpa().

Hmm, the resources defining this are a bit inconvenient given these constraints. If an unallocated portion of a DIMM may only be used for BLK because an overlapping range in another DIMM is allocated that way, would it make since to insert something like a "blk-reserve" resource in all the other DIMMs so we don't need multiple iterations to calculate which DPAs can be used for PMEM?
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm

#10 lore raw
Quoted 49 lines · Keith Busch
Quoted 48 lines · Dan Williams

This is going in the right direction... but still needs to account for the blk_overlap.

So, on a given DIMM BLK capacity is allocated from the top of DPA space going down and PMEM capacity is allocated from the bottom of the DPA space going up.

Since BLK capacity is single DIMM, and PMEM capacity is striped you could get into the situation where one DIMM is fully allocated for BLK usage and that would shade / remove the possibility to use the PMEM capacity on the other DIMMs in the PMEM set. PMEM needs all the same DPAs in all the DIMMs to be free.

Quoted 20 lines

---

drivers/nvdimm/dimm_devs.c +10 -0
index 8d348b22ba45..f30e0c3b0282 100644
@@ -536,6 +536,31 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *                             contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 558

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+       resource_size_t max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       for_each_dpa_resource(ndd, res) {
+               if (strcmp(res->name, "pmem-reserve") != 0)
+                       continue;
+               if (resource_size(res) > max)

...so instead straight resource_size() here you need trim the end of this "pmem-reserve" resource to the start of the first BLK allocation in any of the DIMMs in the set.

Quoted 8 lines
Quoted 1 line

See blk_start calculation in nd_pmem_available_dpa().

Hmm, the resources defining this are a bit inconvenient given these constraints. If an unallocated portion of a DIMM may only be used for BLK because an overlapping range in another DIMM is allocated that way, would it make since to insert something like a "blk-reserve" resource in all the other DIMMs so we don't need multiple iterations to calculate which DPAs can be used for PMEM?

Do you mean temporarily allocate the blk-reserve? You could have a different sized / offset BLK allocation on each DIMM in the PMEM set.

#11 lore raw
Quoted 50 lines · Dan Williams
Quoted 49 lines · Keith Busch
Quoted 48 lines · Dan Williams

This is going in the right direction... but still needs to account for the blk_overlap.

So, on a given DIMM BLK capacity is allocated from the top of DPA space going down and PMEM capacity is allocated from the bottom of the DPA space going up.

Since BLK capacity is single DIMM, and PMEM capacity is striped you could get into the situation where one DIMM is fully allocated for BLK usage and that would shade / remove the possibility to use the PMEM capacity on the other DIMMs in the PMEM set. PMEM needs all the same DPAs in all the DIMMs to be free.

Quoted 20 lines

---

drivers/nvdimm/dimm_devs.c +10 -0
index 8d348b22ba45..f30e0c3b0282 100644
@@ -536,6 +536,31 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
        return info.available;
 }
 
+/**
+ * nd_pmem_max_contiguous_dpa - For the given dimm+region, return the max
+ *                             contiguous unallocated dpa range.
+ * @nd_region: constrain available space check to this reference region
+ * @nd_mapping: container of dpa-resource-root + labels
+ */
+resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region,
+                                          struct nd_mapping *nd_mapping)
+{
+       struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);

drivers/nvdimm/dimm_devs.c resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) · line 558

Quoted 10 lines
drivers/nvdimm/dimm_devs.c +10 -0
+       resource_size_t max = 0;
+       struct resource *res;
+
+       if (!ndd)
+               return 0;
+
+       for_each_dpa_resource(ndd, res) {
+               if (strcmp(res->name, "pmem-reserve") != 0)
+                       continue;
+               if (resource_size(res) > max)

...so instead straight resource_size() here you need trim the end of this "pmem-reserve" resource to the start of the first BLK allocation in any of the DIMMs in the set.

Quoted 1 line
Quoted 1 line
Quoted 1 line

See blk_start calculation in nd_pmem_available_dpa().

Okay, I think I've got it this time. __reserve_free_pmem won't reserve a resource above the first blk resource, so we can't get some fragmented alternating mix of blk and pmem within a dimm. With that in mind, if we reserve pmem across all dimms in a region, take the largest reserved pmem within each dimm, then take the smallest of those across all dimms, that should be the largest allocatable pmem extent.
_______________________________________________
Linux-nvdimm mailing list
[email protected]
https://lists.01.org/mailman/listinfo/linux-nvdimm