@@ -386,40 +386,148 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
}
EXPORT_SYMBOL_GPL(nvdimm_create);
+struct blk_alloc_info {
+ struct nd_mapping *nd_mapping;
+ resource_size_t available, busy;
+ struct resource *res;
+};
+
+static int alias_dpa_busy(struct device *dev, void *data)
+{
+ resource_size_t map_end, blk_start, new, busy;
+ struct blk_alloc_info *info = data;
+ struct nd_mapping *nd_mapping;
+ struct nd_region *nd_region;
+ struct nvdimm_drvdata *ndd;
+ struct resource *res;
+ int i;
+
+ if (!is_nd_pmem(dev))
+ return 0;
+
+ nd_region = to_nd_region(dev);
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ nd_mapping = &nd_region->mapping[i];
+ if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+ break;
+ }
+
+ if (i >= nd_region->ndr_mappings)
+ return 0;
+
+ ndd = to_ndd(nd_mapping);
+ map_end = nd_mapping->start + nd_mapping->size - 1;
+ blk_start = nd_mapping->start;
+ retry:
+ /*
+ * Find the free dpa from the end of the last pmem allocation to
+ * the end of the interleave-set mapping that is not already
+ * covered by a blk allocation.
+ */
+ busy = 0;
+ for_each_dpa_resource(ndd, res) {
+ if ((res->start >= blk_start && res->start < map_end)
+ || (res->end >= blk_start
+ && res->end <= map_end)) {
+ if (strncmp(res->name, "pmem", 4) == 0) {
+ new = max(blk_start, min(map_end + 1,
+ res->end + 1));
+ if (new != blk_start) {
+ blk_start = new;
+ goto retry;
+ }
+ } else
+ busy += min(map_end, res->end)
+ - max(nd_mapping->start, res->start) + 1;
+ } else if (nd_mapping->start > res->start
+ && map_end < res->end) {
+ /* total eclipse of the PMEM region mapping */
+ busy += nd_mapping->size;
+ break;
+ }
+ }
+
+ info->available -= blk_start - nd_mapping->start + busy;
+ return 0;
+}
+
+static int blk_dpa_busy(struct device *dev, void *data)
+{
+ struct blk_alloc_info *info = data;
+ struct nd_mapping *nd_mapping;
+ struct nd_region *nd_region;
+ resource_size_t map_end;
+ int i;
+
+ if (!is_nd_pmem(dev))
+ return 0;
+
+ nd_region = to_nd_region(dev);
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ nd_mapping = &nd_region->mapping[i];
+ if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+ break;
+ }
+
+ if (i >= nd_region->ndr_mappings)
+ return 0;
+
+ map_end = nd_mapping->start + nd_mapping->size - 1;
+ if (info->res->start >= nd_mapping->start
+ && info->res->start < map_end) {
+ if (info->res->end <= map_end) {
+ info->busy = 0;
+ return 1;
+ } else {
+ info->busy -= info->res->end - map_end;
+ return 0;
+ }
+ } else if (info->res->end >= nd_mapping->start
+ && info->res->end <= map_end) {
+ info->busy -= nd_mapping->start - info->res->start;
+ return 0;
+ } else {
+ info->busy -= nd_mapping->size;
+ return 0;
+ }
+}
+
/**
* nd_blk_available_dpa - account the unused dpa of BLK region
* @nd_mapping: container of dpa-resource-root + labels
*
- * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges.
+ * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges, but
+ * we arrange for them to never start at an lower dpa than the last
+ * PMEM allocation in an aliased region.
*/
-resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping)
+resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
{
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+ struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
- resource_size_t map_end, busy = 0, available;
+ struct blk_alloc_info info = {
+ .nd_mapping = nd_mapping,
+ .available = nd_mapping->size,
+ };
struct resource *res;
if (!ndd)
return 0;
- map_end = nd_mapping->start + nd_mapping->size - 1;
- for_each_dpa_resource(ndd, res)
- if (res->start >= nd_mapping->start && res->start < map_end) {
- resource_size_t end = min(map_end, res->end);
+ device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
- busy += end - res->start + 1;
- } else if (res->end >= nd_mapping->start
- && res->end <= map_end) {
- busy += res->end - nd_mapping->start;
- } else if (nd_mapping->start > res->start
- && nd_mapping->start < res->end) {
- /* total eclipse of the BLK region mapping */
- busy += nd_mapping->size;
- }
+ /* now account for busy blk allocations in unaliased dpa */
+ for_each_dpa_resource(ndd, res) {
+ if (strncmp(res->name, "blk", 3) != 0)
+ continue;
- available = map_end - nd_mapping->start + 1;
- if (busy < available)
- return available - busy;
- return 0;
+ info.res = res;
+ info.busy = resource_size(res);
+ device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
+ info.available -= info.busy;
+ }
+
+ return info.available;
}
/**
@@ -451,21 +559,16 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
map_start = nd_mapping->start;
map_end = map_start + nd_mapping->size - 1;
blk_start = max(map_start, map_end + 1 - *overlap);
- for_each_dpa_resource(ndd, res)
+ for_each_dpa_resource(ndd, res) {
if (res->start >= map_start && res->start < map_end) {
if (strncmp(res->name, "blk", 3) == 0)
- blk_start = min(blk_start, res->start);
- else if (res->start != map_start) {
+ blk_start = min(blk_start,
+ max(map_start, res->start));
+ else if (res->end > map_end) {
reason = "misaligned to iset";
goto err;
- } else {
- if (busy) {
- reason = "duplicate overlapping PMEM reservations?";
- goto err;
- }
+ } else
busy += resource_size(res);
- continue;
- }
} else if (res->end >= map_start && res->end <= map_end) {
if (strncmp(res->name, "blk", 3) == 0) {
/*
@@ -474,15 +577,14 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
* be used for BLK.
*/
blk_start = map_start;
- } else {
- reason = "misaligned to iset";
- goto err;
- }
+ } else
+ busy += resource_size(res);
} else if (map_start > res->start && map_start < res->end) {
/* total eclipse of the mapping */
busy += nd_mapping->size;
blk_start = map_start;
}
+ }
*overlap = map_end + 1 - blk_start;
available = blk_start - map_start;
@@ -491,10 +593,6 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
return 0;
err:
- /*
- * Something is wrong, PMEM must align with the start of the
- * interleave set, and there can only be one allocation per set.
- */
nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason);
return 0;
}
@@ -76,7 +76,7 @@ struct nd_mapping;
void nd_mapping_free_labels(struct nd_mapping *nd_mapping);
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_mapping *nd_mapping);
+resource_size_t nd_blk_available_dpa(struct nd_region *nd_region);
resource_size_t nd_region_available_dpa(struct nd_region *nd_region);
resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
struct nd_label_id *label_id);
@@ -294,9 +294,8 @@ resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
blk_max_overlap = overlap;
goto retry;
}
- } else if (is_nd_blk(&nd_region->dev)) {
- available += nd_blk_available_dpa(nd_mapping);
- }
+ } else if (is_nd_blk(&nd_region->dev))
+ available += nd_blk_available_dpa(nd_region);
}
return available;
The free dpa (dimm-physical-address) space calculation reports how much free space is available with consideration for aliased BLK + PMEM regions. Recall that BLK capacity is allocated from high addresses and PMEM is allocated from low addresses in their respective regions. nd_region_available_dpa() accounts for the fact that the largest encroachment (lowest starting address) into PMEM capacity by a BLK allocation limits the available capacity to that point, regardless if there is BLK allocation hole at a higher address. Similarly, for the multi-pmem case we need to track the largest encroachment (highest ending address) of a PMEM allocation in BLK capacity regardless of whether there is an allocation hole that a BLK allocation could fill at a lower address. Signed-off-by: Dan Williams <dan.j.williams@intel.com> --- drivers/nvdimm/dimm_devs.c | 174 +++++++++++++++++++++++++++++++++--------- drivers/nvdimm/nd-core.h | 2 drivers/nvdimm/region_devs.c | 5 - 3 files changed, 139 insertions(+), 42 deletions(-)