diff options
author | Dan Williams <dan.j.williams@intel.com> | 2020-01-30 23:06:23 +0300 |
---|---|---|
committer | Dan Williams <dan.j.williams@intel.com> | 2020-03-17 22:23:21 +0300 |
commit | 2522afb86a8cceba0f67dbf05772d21b76d79f06 (patch) | |
tree | 43ea32614b10933889836813b187d1e52eaf766d /drivers/nvdimm/dimm_devs.c | |
parent | a0e374525def2ef18a078523e1faefb5ce2b05e5 (diff) | |
download | linux-2522afb86a8cceba0f67dbf05772d21b76d79f06.tar.xz |
libnvdimm/region: Introduce an 'align' attribute
The align attribute applies an alignment constraint for namespace
creation in a region. Whereas the 'align' attribute of a namespace
applied alignment padding via an info block, the 'align' attribute
applies alignment constraints to the free space allocation.
The default for 'align' is the maximum known memremap_compat_align()
across all archs (16MiB from PowerPC at time of writing) multiplied by
the number of interleave ways if there is blk-aliasing. The minimum is
PAGE_SIZE and allows for the creation of cross-arch incompatible
namespaces, just as previous kernels allowed, but the expectation is
cross-arch and mode-independent compatibility by default.
The regression risk with this change is limited to cases that were
dependent on the ability to create unaligned namespaces, *and* for some
reason are unable to opt-out of aligned namespaces by writing to
'regionX/align'. If such a scenario arises the default can be flipped
from opt-out to opt-in of compat-aligned namespace creation, but that is
a last resort. The kernel will otherwise continue to support existing
defined misaligned namespaces.
Unfortunately this change needs to touch several parts of the
implementation at once:
- region/available_size: expand busy extents to current align
- region/max_available_extent: expand busy extents to current align
- namespace/size: trim free space to current align
...to keep the free space accounting conforming to the dynamic align
setting.
Reported-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reported-by: Jeff Moyer <jmoyer@redhat.com>
Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Reviewed-by: Jeff Moyer <jmoyer@redhat.com>
Link: https://lore.kernel.org/r/158041478371.3889308.14542630147672668068.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Diffstat (limited to 'drivers/nvdimm/dimm_devs.c')
-rw-r--r-- | drivers/nvdimm/dimm_devs.c | 86 |
1 files changed, 71 insertions, 15 deletions
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 39a61a514746..b7b77e8d9027 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -563,6 +563,21 @@ int nvdimm_security_freeze(struct nvdimm *nvdimm) return rc; } +static unsigned long dpa_align(struct nd_region *nd_region) +{ + struct device *dev = &nd_region->dev; + + if (dev_WARN_ONCE(dev, !is_nvdimm_bus_locked(dev), + "bus lock required for capacity provision\n")) + return 0; + if (dev_WARN_ONCE(dev, !nd_region->ndr_mappings || nd_region->align + % nd_region->ndr_mappings, + "invalid region align %#lx mappings: %d\n", + nd_region->align, nd_region->ndr_mappings)) + return 0; + return nd_region->align / nd_region->ndr_mappings; +} + int alias_dpa_busy(struct device *dev, void *data) { resource_size_t map_end, blk_start, new; @@ -571,6 +586,7 @@ int alias_dpa_busy(struct device *dev, void *data) struct nd_region *nd_region; struct nvdimm_drvdata *ndd; struct resource *res; + unsigned long align; int i; if (!is_memory(dev)) @@ -608,13 +624,21 @@ int alias_dpa_busy(struct device *dev, void *data) * Find the free dpa from the end of the last pmem allocation to * the end of the interleave-set mapping. */ + align = dpa_align(nd_region); + if (!align) + return 0; + for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strncmp(res->name, "pmem", 4) != 0) continue; - if ((res->start >= blk_start && res->start < map_end) - || (res->end >= blk_start - && res->end <= map_end)) { - new = max(blk_start, min(map_end + 1, res->end + 1)); + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if ((start >= blk_start && start < map_end) + || (end >= blk_start && end <= map_end)) { + new = max(blk_start, min(map_end, end) + 1); if (new != blk_start) { blk_start = new; goto retry; @@ -654,6 +678,7 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) .res = NULL, }; struct resource *res; + unsigned long align; if (!ndd) return 0; @@ -661,10 +686,20 @@ resource_size_t nd_blk_available_dpa(struct nd_region *nd_region) device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy); /* now account for busy blk allocations in unaliased dpa */ + align = dpa_align(nd_region); + if (!align) + return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end, size; + if (strncmp(res->name, "blk", 3) != 0) continue; - info.available -= resource_size(res); + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + size = end - start + 1; + if (size >= info.available) + return 0; + info.available -= size; } return info.available; @@ -683,19 +718,31 @@ resource_size_t nd_pmem_max_contiguous_dpa(struct nd_region *nd_region, struct nvdimm_bus *nvdimm_bus; resource_size_t max = 0; struct resource *res; + unsigned long align; /* if a dimm is disabled the available capacity is zero */ if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + nvdimm_bus = walk_to_nvdimm_bus(ndd->dev); if (__reserve_free_pmem(&nd_region->dev, nd_mapping->nvdimm)) return 0; for_each_dpa_resource(ndd, res) { + resource_size_t start, end; + if (strcmp(res->name, "pmem-reserve") != 0) continue; - if (resource_size(res) > max) - max = resource_size(res); + /* trim free space relative to current alignment setting */ + start = ALIGN(res->start, align); + end = ALIGN_DOWN(res->end + 1, align) - 1; + if (end < start) + continue; + if (end - start + 1 > max) + max = end - start + 1; } release_free_pmem(nvdimm_bus, nd_mapping); return max; @@ -723,24 +770,33 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, struct nvdimm_drvdata *ndd = to_ndd(nd_mapping); struct resource *res; const char *reason; + unsigned long align; if (!ndd) return 0; + align = dpa_align(nd_region); + if (!align) + return 0; + 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) { - if (res->start >= map_start && res->start < map_end) { + resource_size_t start, end; + + start = ALIGN_DOWN(res->start, align); + end = ALIGN(res->end + 1, align) - 1; + if (start >= map_start && start < map_end) { if (strncmp(res->name, "blk", 3) == 0) blk_start = min(blk_start, - max(map_start, res->start)); - else if (res->end > map_end) { + max(map_start, start)); + else if (end > map_end) { reason = "misaligned to iset"; goto err; } else - busy += resource_size(res); - } else if (res->end >= map_start && res->end <= map_end) { + busy += end - start + 1; + } else if (end >= map_start && end <= map_end) { if (strncmp(res->name, "blk", 3) == 0) { /* * If a BLK allocation overlaps the start of @@ -749,8 +805,8 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, */ blk_start = map_start; } else - busy += resource_size(res); - } else if (map_start > res->start && map_start < res->end) { + busy += end - start + 1; + } else if (map_start > start && map_start < end) { /* total eclipse of the mapping */ busy += nd_mapping->size; blk_start = map_start; @@ -760,7 +816,7 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region, *overlap = map_end + 1 - blk_start; available = blk_start - map_start; if (busy < available) - return available - busy; + return ALIGN_DOWN(available - busy, align); return 0; err: |