diff options
-rw-r--r-- | arch/powerpc/Kconfig | 1 | ||||
-rw-r--r-- | arch/powerpc/mm/ioremap.c | 21 | ||||
-rw-r--r-- | arch/powerpc/platforms/pseries/papr_scm.c | 2 | ||||
-rw-r--r-- | drivers/acpi/nfit/core.c | 4 | ||||
-rw-r--r-- | drivers/nvdimm/dimm.c | 2 | ||||
-rw-r--r-- | drivers/nvdimm/dimm_devs.c | 95 | ||||
-rw-r--r-- | drivers/nvdimm/namespace_devs.c | 28 | ||||
-rw-r--r-- | drivers/nvdimm/nd.h | 3 | ||||
-rw-r--r-- | drivers/nvdimm/pfn.h | 12 | ||||
-rw-r--r-- | drivers/nvdimm/pfn_devs.c | 40 | ||||
-rw-r--r-- | drivers/nvdimm/region_devs.c | 130 | ||||
-rw-r--r-- | include/linux/io.h | 2 | ||||
-rw-r--r-- | include/linux/libnvdimm.h | 2 | ||||
-rw-r--r-- | include/linux/memremap.h | 8 | ||||
-rw-r--r-- | include/linux/mmzone.h | 1 | ||||
-rw-r--r-- | lib/Kconfig | 3 | ||||
-rw-r--r-- | mm/memremap.c | 23 |
17 files changed, 328 insertions, 49 deletions
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 497b7d0b2d7e..e6ffe905e2b9 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -122,6 +122,7 @@ config PPC select ARCH_HAS_GCOV_PROFILE_ALL select ARCH_HAS_KCOV select ARCH_HAS_HUGEPD if HUGETLB_PAGE + select ARCH_HAS_MEMREMAP_COMPAT_ALIGN select ARCH_HAS_MMIOWB if PPC64 select ARCH_HAS_PHYS_TO_DMA select ARCH_HAS_PMEM_API diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c index fc669643ce6a..b1a0aebe8c48 100644 --- a/arch/powerpc/mm/ioremap.c +++ b/arch/powerpc/mm/ioremap.c @@ -2,6 +2,7 @@ #include <linux/io.h> #include <linux/slab.h> +#include <linux/mmzone.h> #include <linux/vmalloc.h> #include <asm/io-workarounds.h> @@ -97,3 +98,23 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size, return NULL; } + +#ifdef CONFIG_ZONE_DEVICE +/* + * Override the generic version in mm/memremap.c. + * + * With hash translation, the direct-map range is mapped with just one + * page size selected by htab_init_page_sizes(). Consult + * mmu_psize_defs[] to determine the minimum page size alignment. +*/ +unsigned long memremap_compat_align(void) +{ + unsigned int shift = mmu_psize_defs[mmu_linear_psize].shift; + + if (radix_enabled()) + return SUBSECTION_SIZE; + return max(SUBSECTION_SIZE, 1UL << shift); + +} +EXPORT_SYMBOL_GPL(memremap_compat_align); +#endif diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c index 0b4467e378e5..589858cb3203 100644 --- a/arch/powerpc/platforms/pseries/papr_scm.c +++ b/arch/powerpc/platforms/pseries/papr_scm.c @@ -328,7 +328,7 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p) } dimm_flags = 0; - set_bit(NDD_ALIASING, &dimm_flags); + set_bit(NDD_LABELING, &dimm_flags); p->nvdimm = nvdimm_create(p->bus, p, NULL, dimm_flags, PAPR_SCM_DIMM_CMD_MASK, 0, NULL); diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c index d0090f71585c..fa4500f9cfd1 100644 --- a/drivers/acpi/nfit/core.c +++ b/drivers/acpi/nfit/core.c @@ -2027,8 +2027,10 @@ static int acpi_nfit_register_dimms(struct acpi_nfit_desc *acpi_desc) continue; } - if (nfit_mem->bdw && nfit_mem->memdev_pmem) + if (nfit_mem->bdw && nfit_mem->memdev_pmem) { set_bit(NDD_ALIASING, &flags); + set_bit(NDD_LABELING, &flags); + } /* collate flags across all memdevs for this dimm */ list_for_each_entry(nfit_memdev, &acpi_desc->memdevs, list) { diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c index 64776ed15bb3..7d4ddc4d9322 100644 --- a/drivers/nvdimm/dimm.c +++ b/drivers/nvdimm/dimm.c @@ -99,7 +99,7 @@ static int nvdimm_probe(struct device *dev) if (ndd->ns_current >= 0) { rc = nd_label_reserve_dpa(ndd); if (rc == 0) - nvdimm_set_aliasing(dev); + nvdimm_set_labeling(dev); } nvdimm_bus_unlock(dev); diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c index 94ea6dba6b4f..b7b77e8d9027 100644 --- a/drivers/nvdimm/dimm_devs.c +++ b/drivers/nvdimm/dimm_devs.c @@ -32,7 +32,7 @@ int nvdimm_check_config_data(struct device *dev) if (!nvdimm->cmd_mask || !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) { - if (test_bit(NDD_ALIASING, &nvdimm->flags)) + if (test_bit(NDD_LABELING, &nvdimm->flags)) return -ENXIO; else return -ENOTTY; @@ -173,11 +173,11 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, return rc; } -void nvdimm_set_aliasing(struct device *dev) +void nvdimm_set_labeling(struct device *dev) { struct nvdimm *nvdimm = to_nvdimm(dev); - set_bit(NDD_ALIASING, &nvdimm->flags); + set_bit(NDD_LABELING, &nvdimm->flags); } void nvdimm_set_locked(struct device *dev) @@ -312,8 +312,9 @@ static ssize_t flags_show(struct device *dev, { struct nvdimm *nvdimm = to_nvdimm(dev); - return sprintf(buf, "%s%s\n", + return sprintf(buf, "%s%s%s\n", test_bit(NDD_ALIASING, &nvdimm->flags) ? "alias " : "", + test_bit(NDD_LABELING, &nvdimm->flags) ? "label " : "", test_bit(NDD_LOCKED, &nvdimm->flags) ? "lock " : ""); } static DEVICE_ATTR_RO(flags); @@ -562,6 +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; @@ -570,6 +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)) @@ -607,13 +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; @@ -653,6 +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; @@ -660,10 +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; @@ -682,19 +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; @@ -722,24 +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 @@ -748,8 +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; @@ -759,7 +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: diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c index 032dc61725ff..ae155e860fdc 100644 --- a/drivers/nvdimm/namespace_devs.c +++ b/drivers/nvdimm/namespace_devs.c @@ -10,6 +10,7 @@ #include <linux/nd.h> #include "nd-core.h" #include "pmem.h" +#include "pfn.h" #include "nd.h" static void namespace_io_release(struct device *dev) @@ -541,6 +542,11 @@ static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd, { bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0; bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0; + unsigned long align; + + align = nd_region->align / nd_region->ndr_mappings; + valid->start = ALIGN(valid->start, align); + valid->end = ALIGN_DOWN(valid->end + 1, align) - 1; if (valid->start >= valid->end) goto invalid; @@ -980,10 +986,10 @@ static ssize_t __size_store(struct device *dev, unsigned long long val) return -ENXIO; } - div_u64_rem(val, PAGE_SIZE * nd_region->ndr_mappings, &remainder); + div_u64_rem(val, nd_region->align, &remainder); if (remainder) { dev_dbg(dev, "%llu is not %ldK aligned\n", val, - (PAGE_SIZE * nd_region->ndr_mappings) / SZ_1K); + nd_region->align / SZ_1K); return -EINVAL; } @@ -1739,6 +1745,22 @@ struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev) return ERR_PTR(-ENODEV); } + /* + * Note, alignment validation for fsdax and devdax mode + * namespaces happens in nd_pfn_validate() where infoblock + * padding parameters can be applied. + */ + if (pmem_should_map_pages(dev)) { + struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev); + struct resource *res = &nsio->res; + + if (!IS_ALIGNED(res->start | (res->end + 1), + memremap_compat_align())) { + dev_err(&ndns->dev, "%pr misaligned, unable to map\n", res); + return ERR_PTR(-EOPNOTSUPP); + } + } + if (is_namespace_pmem(&ndns->dev)) { struct nd_namespace_pmem *nspm; @@ -2521,7 +2543,7 @@ static int init_active_labels(struct nd_region *nd_region) if (!ndd) { if (test_bit(NDD_LOCKED, &nvdimm->flags)) /* fail, label data may be unreadable */; - else if (test_bit(NDD_ALIASING, &nvdimm->flags)) + else if (test_bit(NDD_LABELING, &nvdimm->flags)) /* fail, labels needed to disambiguate dpa */; else return 0; diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h index c9f6a5b5253a..c4d69c1cce55 100644 --- a/drivers/nvdimm/nd.h +++ b/drivers/nvdimm/nd.h @@ -146,6 +146,7 @@ struct nd_region { struct device *btt_seed; struct device *pfn_seed; struct device *dax_seed; + unsigned long align; u16 ndr_mappings; u64 ndr_size; u64 ndr_start; @@ -252,7 +253,7 @@ int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset, void *buf, size_t len); long nvdimm_clear_poison(struct device *dev, phys_addr_t phys, unsigned int len); -void nvdimm_set_aliasing(struct device *dev); +void nvdimm_set_labeling(struct device *dev); void nvdimm_set_locked(struct device *dev); void nvdimm_clear_locked(struct device *dev); int nvdimm_security_setup_events(struct device *dev); diff --git a/drivers/nvdimm/pfn.h b/drivers/nvdimm/pfn.h index acb19517f678..37cb1b8a2a39 100644 --- a/drivers/nvdimm/pfn.h +++ b/drivers/nvdimm/pfn.h @@ -24,6 +24,18 @@ struct nd_pfn_sb { __le64 npfns; __le32 mode; /* minor-version-1 additions for section alignment */ + /** + * @start_pad: Deprecated attribute to pad start-misaligned namespaces + * + * start_pad is deprecated because the original definition did + * not comprehend that dataoff is relative to the base address + * of the namespace not the start_pad adjusted base. The result + * is that the dax path is broken, but the block-I/O path is + * not. The kernel will no longer create namespaces using start + * padding, but it still supports block-I/O for legacy + * configurations mainly to allow a backup, reconfigure the + * namespace, and restore flow to repair dax operation. + */ __le32 start_pad; __le32 end_trunc; /* minor-version-2 record the base alignment of the mapping */ diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index b94f7a7e94b8..34db557dbad1 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -446,6 +446,7 @@ static bool nd_supported_alignment(unsigned long align) int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) { u64 checksum, offset; + struct resource *res; enum nd_pfn_mode mode; struct nd_namespace_io *nsio; unsigned long align, start_pad; @@ -561,14 +562,14 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n", nd_pfn->align, align, nd_pfn->mode, mode); - return -EINVAL; + return -EOPNOTSUPP; } } if (align > nvdimm_namespace_capacity(ndns)) { dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n", align, nvdimm_namespace_capacity(ndns)); - return -EINVAL; + return -EOPNOTSUPP; } /* @@ -578,18 +579,31 @@ int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig) * established. */ nsio = to_nd_namespace_io(&ndns->dev); - if (offset >= resource_size(&nsio->res)) { + res = &nsio->res; + if (offset >= resource_size(res)) { dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n", dev_name(&ndns->dev)); - return -EBUSY; + return -EOPNOTSUPP; } - if ((align && !IS_ALIGNED(nsio->res.start + offset + start_pad, align)) + if ((align && !IS_ALIGNED(res->start + offset + start_pad, align)) || !IS_ALIGNED(offset, PAGE_SIZE)) { dev_err(&nd_pfn->dev, "bad offset: %#llx dax disabled align: %#lx\n", offset, align); - return -ENXIO; + return -EOPNOTSUPP; + } + + if (!IS_ALIGNED(res->start + le32_to_cpu(pfn_sb->start_pad), + memremap_compat_align())) { + dev_err(&nd_pfn->dev, "resource start misaligned\n"); + return -EOPNOTSUPP; + } + + if (!IS_ALIGNED(res->end + 1 - le32_to_cpu(pfn_sb->end_trunc), + memremap_compat_align())) { + dev_err(&nd_pfn->dev, "resource end misaligned\n"); + return -EOPNOTSUPP; } return 0; @@ -750,7 +764,19 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) start = nsio->res.start; size = resource_size(&nsio->res); npfns = PHYS_PFN(size - SZ_8K); - align = max(nd_pfn->align, (1UL << SUBSECTION_SHIFT)); + align = max(nd_pfn->align, memremap_compat_align()); + + /* + * When @start is misaligned fail namespace creation. See + * the 'struct nd_pfn_sb' commentary on why ->start_pad is not + * an option. + */ + if (!IS_ALIGNED(start, memremap_compat_align())) { + dev_err(&nd_pfn->dev, "%s: start %pa misaligned to %#lx\n", + dev_name(&ndns->dev), &start, + memremap_compat_align()); + return -EINVAL; + } end_trunc = start + size - ALIGN_DOWN(start + size, align); if (nd_pfn->mode == PFN_MODE_PMEM) { /* diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c index a19e535830d9..ccbb5b43b8b2 100644 --- a/drivers/nvdimm/region_devs.c +++ b/drivers/nvdimm/region_devs.c @@ -195,16 +195,16 @@ EXPORT_SYMBOL_GPL(nd_blk_region_set_provider_data); int nd_region_to_nstype(struct nd_region *nd_region) { if (is_memory(&nd_region->dev)) { - u16 i, alias; + u16 i, label; - for (i = 0, alias = 0; i < nd_region->ndr_mappings; i++) { + for (i = 0, label = 0; i < nd_region->ndr_mappings; i++) { struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nvdimm *nvdimm = nd_mapping->nvdimm; - if (test_bit(NDD_ALIASING, &nvdimm->flags)) - alias++; + if (test_bit(NDD_LABELING, &nvdimm->flags)) + label++; } - if (alias) + if (label) return ND_DEVICE_NAMESPACE_PMEM; else return ND_DEVICE_NAMESPACE_IO; @@ -216,21 +216,25 @@ int nd_region_to_nstype(struct nd_region *nd_region) } EXPORT_SYMBOL(nd_region_to_nstype); -static ssize_t size_show(struct device *dev, - struct device_attribute *attr, char *buf) +static unsigned long long region_size(struct nd_region *nd_region) { - struct nd_region *nd_region = to_nd_region(dev); - unsigned long long size = 0; - - if (is_memory(dev)) { - size = nd_region->ndr_size; + if (is_memory(&nd_region->dev)) { + return nd_region->ndr_size; } else if (nd_region->ndr_mappings == 1) { struct nd_mapping *nd_mapping = &nd_region->mapping[0]; - size = nd_mapping->size; + return nd_mapping->size; } - return sprintf(buf, "%llu\n", size); + return 0; +} + +static ssize_t size_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%llu\n", region_size(nd_region)); } static DEVICE_ATTR_RO(size); @@ -529,6 +533,54 @@ static ssize_t read_only_store(struct device *dev, } static DEVICE_ATTR_RW(read_only); +static ssize_t align_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct nd_region *nd_region = to_nd_region(dev); + + return sprintf(buf, "%#lx\n", nd_region->align); +} + +static ssize_t align_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + struct nd_region *nd_region = to_nd_region(dev); + unsigned long val, dpa; + u32 remainder; + int rc; + + rc = kstrtoul(buf, 0, &val); + if (rc) + return rc; + + if (!nd_region->ndr_mappings) + return -ENXIO; + + /* + * Ensure space-align is evenly divisible by the region + * interleave-width because the kernel typically has no facility + * to determine which DIMM(s), dimm-physical-addresses, would + * contribute to the tail capacity in system-physical-address + * space for the namespace. + */ + dpa = div_u64_rem(val, nd_region->ndr_mappings, &remainder); + if (!is_power_of_2(dpa) || dpa < PAGE_SIZE + || val > region_size(nd_region) || remainder) + return -EINVAL; + + /* + * Given that space allocation consults this value multiple + * times ensure it does not change for the duration of the + * allocation. + */ + nvdimm_bus_lock(dev); + nd_region->align = val; + nvdimm_bus_unlock(dev); + + return len; +} +static DEVICE_ATTR_RW(align); + static ssize_t region_badblocks_show(struct device *dev, struct device_attribute *attr, char *buf) { @@ -571,6 +623,7 @@ static DEVICE_ATTR_RO(persistence_domain); static struct attribute *nd_region_attributes[] = { &dev_attr_size.attr, + &dev_attr_align.attr, &dev_attr_nstype.attr, &dev_attr_mappings.attr, &dev_attr_btt_seed.attr, @@ -626,6 +679,19 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) return a->mode; } + if (a == &dev_attr_align.attr) { + int i; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if (test_bit(NDD_LABELING, &nvdimm->flags)) + return a->mode; + } + return 0; + } + if (a != &dev_attr_set_cookie.attr && a != &dev_attr_available_size.attr) return a->mode; @@ -935,6 +1001,41 @@ void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane) } EXPORT_SYMBOL(nd_region_release_lane); +/* + * PowerPC requires this alignment for memremap_pages(). All other archs + * should be ok with SUBSECTION_SIZE (see memremap_compat_align()). + */ +#define MEMREMAP_COMPAT_ALIGN_MAX SZ_16M + +static unsigned long default_align(struct nd_region *nd_region) +{ + unsigned long align; + int i, mappings; + u32 remainder; + + if (is_nd_blk(&nd_region->dev)) + align = PAGE_SIZE; + else + align = MEMREMAP_COMPAT_ALIGN_MAX; + + for (i = 0; i < nd_region->ndr_mappings; i++) { + struct nd_mapping *nd_mapping = &nd_region->mapping[i]; + struct nvdimm *nvdimm = nd_mapping->nvdimm; + + if (test_bit(NDD_ALIASING, &nvdimm->flags)) { + align = MEMREMAP_COMPAT_ALIGN_MAX; + break; + } + } + + mappings = max_t(u16, 1, nd_region->ndr_mappings); + div_u64_rem(align, mappings, &remainder); + if (remainder) + align *= mappings; + + return align; +} + static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, struct nd_region_desc *ndr_desc, const struct device_type *dev_type, const char *caller) @@ -1039,6 +1140,7 @@ static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus, dev->of_node = ndr_desc->of_node; nd_region->ndr_size = resource_size(ndr_desc->res); nd_region->ndr_start = ndr_desc->res->start; + nd_region->align = default_align(nd_region); if (ndr_desc->flush) nd_region->flush = ndr_desc->flush; else diff --git a/include/linux/io.h b/include/linux/io.h index b1c44bb4b2d7..8394c56babc2 100644 --- a/include/linux/io.h +++ b/include/linux/io.h @@ -77,8 +77,6 @@ void *devm_memremap(struct device *dev, resource_size_t offset, size_t size, unsigned long flags); void devm_memunmap(struct device *dev, void *addr); -void *__devm_memremap_pages(struct device *dev, struct resource *res); - #ifdef CONFIG_PCI /* * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h index 9df091bd30ba..18da4059be09 100644 --- a/include/linux/libnvdimm.h +++ b/include/linux/libnvdimm.h @@ -37,6 +37,8 @@ enum { NDD_WORK_PENDING = 4, /* ignore / filter NSLABEL_FLAG_LOCAL for this DIMM, i.e. no aliasing */ NDD_NOBLK = 5, + /* dimm supports namespace labels */ + NDD_LABELING = 6, /* need to set a limit somewhere, but yes, this is likely overkill */ ND_IOCTL_MAX_BUFLEN = SZ_4M, diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 6fefb09af7c3..8af1cbd8f293 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -132,6 +132,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn, unsigned long vmem_altmap_offset(struct vmem_altmap *altmap); void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns); +unsigned long memremap_compat_align(void); #else static inline void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) @@ -165,6 +166,12 @@ static inline void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns) { } + +/* when memremap_pages() is disabled all archs can remap a single page */ +static inline unsigned long memremap_compat_align(void) +{ + return PAGE_SIZE; +} #endif /* CONFIG_ZONE_DEVICE */ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) @@ -172,4 +179,5 @@ static inline void put_dev_pagemap(struct dev_pagemap *pgmap) if (pgmap) percpu_ref_put(pgmap->ref); } + #endif /* _LINUX_MEMREMAP_H_ */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 462f6873905a..6b77f7239af5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -1170,6 +1170,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec) #define SECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SECTION_MASK) #define SUBSECTION_SHIFT 21 +#define SUBSECTION_SIZE (1UL << SUBSECTION_SHIFT) #define PFN_SUBSECTION_SHIFT (SUBSECTION_SHIFT - PAGE_SHIFT) #define PAGES_PER_SUBSECTION (1UL << PFN_SUBSECTION_SHIFT) diff --git a/lib/Kconfig b/lib/Kconfig index bc7e56370129..5d53f9609c25 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -615,6 +615,9 @@ config ARCH_HAS_PMEM_API config MEMREGION bool +config ARCH_HAS_MEMREMAP_COMPAT_ALIGN + bool + # use memcpy to implement user copies for nommu architectures config UACCESS_MEMCPY bool diff --git a/mm/memremap.c b/mm/memremap.c index 09b5b7adc773..3e7afaf05639 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -7,6 +7,7 @@ #include <linux/mm.h> #include <linux/pfn_t.h> #include <linux/swap.h> +#include <linux/mmzone.h> #include <linux/swapops.h> #include <linux/types.h> #include <linux/wait_bit.h> @@ -14,6 +15,28 @@ static DEFINE_XARRAY(pgmap_array); +/* + * The memremap() and memremap_pages() interfaces are alternately used + * to map persistent memory namespaces. These interfaces place different + * constraints on the alignment and size of the mapping (namespace). + * memremap() can map individual PAGE_SIZE pages. memremap_pages() can + * only map subsections (2MB), and at least one architecture (PowerPC) + * the minimum mapping granularity of memremap_pages() is 16MB. + * + * The role of memremap_compat_align() is to communicate the minimum + * arch supported alignment of a namespace such that it can freely + * switch modes without violating the arch constraint. Namely, do not + * allow a namespace to be PAGE_SIZE aligned since that namespace may be + * reconfigured into a mode that requires SUBSECTION_SIZE alignment. + */ +#ifndef CONFIG_ARCH_HAS_MEMREMAP_COMPAT_ALIGN +unsigned long memremap_compat_align(void) +{ + return SUBSECTION_SIZE; +} +EXPORT_SYMBOL_GPL(memremap_compat_align); +#endif + #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); EXPORT_SYMBOL(devmap_managed_key); |