static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_pfn *nd_pfn = to_nd_pfn_safe(dev);
ssize_t rc;
device_lock(dev);
if (dev->driver) {
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = __le64_to_cpu(pfn_sb->dataoff);
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
rc = sprintf(buf, "%llu\n", (unsigned long long)
resource_size(&nsio->res) - start_pad
- end_trunc - offset);
} else {
/* no size to convey if the pfn instance is disabled */
rc = -ENXIO;
}
device_unlock(dev);
return rc;
}
/**
* nvdimm_namespace_add_poison() - Convert a list of poison ranges to badblocks
* @ndns: the namespace containing poison ranges
* @bb: badblocks instance to populate
* @offset: offset at the start of the namespace before 'sector 0'
*
* The poison list generated during NFIT initialization may contain multiple,
* possibly overlapping ranges in the SPA (System Physical Address) space.
* Compare each of these ranges to the namespace currently being initialized,
* and add badblocks to the gendisk for all matching sub-ranges
*/
void nvdimm_namespace_add_poison(struct nd_namespace_common *ndns,
struct badblocks *bb, resource_size_t offset)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
struct nvdimm_bus *nvdimm_bus;
struct list_head *poison_list;
u64 ns_start, ns_end, ns_size;
struct nd_poison *pl;
ns_size = nvdimm_namespace_capacity(ndns) - offset;
ns_start = nsio->res.start + offset;
ns_end = nsio->res.end;
nvdimm_bus = to_nvdimm_bus(nd_region->dev.parent);
poison_list = &nvdimm_bus->poison_list;
if (list_empty(poison_list))
return;
list_for_each_entry(pl, poison_list, list) {
u64 pl_end = pl->start + pl->length - 1;
/* Discard intervals with no intersection */
if (pl_end < ns_start)
continue;
if (pl->start > ns_end)
continue;
/* Deal with any overlap after start of the namespace */
if (pl->start >= ns_start) {
u64 start = pl->start;
u64 len;
if (pl_end <= ns_end)
len = pl->length;
else
len = ns_start + ns_size - pl->start;
__add_badblock_range(bb, start - ns_start, len);
continue;
}
/* Deal with overlap for poison starting before the namespace */
if (pl->start < ns_start) {
u64 len;
if (pl_end < ns_end)
len = pl->start + pl->length - ns_start;
else
len = ns_size;
__add_badblock_range(bb, 0, len);
}
}
static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn,
struct resource *res, struct vmem_altmap *altmap)
{
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
u64 offset = le64_to_cpu(pfn_sb->dataoff);
u32 start_pad = __le32_to_cpu(pfn_sb->start_pad);
u32 end_trunc = __le32_to_cpu(pfn_sb->end_trunc);
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
resource_size_t base = nsio->res.start + start_pad;
struct vmem_altmap __altmap = {
.base_pfn = init_altmap_base(base),
.reserve = init_altmap_reserve(base),
};
memcpy(res, &nsio->res, sizeof(*res));
res->start += start_pad;
res->end -= end_trunc;
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset < SZ_8K)
return ERR_PTR(-EINVAL);
nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
altmap = NULL;
} else if (nd_pfn->mode == PFN_MODE_PMEM) {
nd_pfn->npfns = PFN_SECTION_ALIGN_UP((resource_size(res)
- offset) / PAGE_SIZE);
if (le64_to_cpu(nd_pfn->pfn_sb->npfns) > nd_pfn->npfns)
dev_info(&nd_pfn->dev,
"number of pfns truncated from %lld to %ld\n",
le64_to_cpu(nd_pfn->pfn_sb->npfns),
nd_pfn->npfns);
memcpy(altmap, &__altmap, sizeof(*altmap));
altmap->free = PHYS_PFN(offset - SZ_8K);
altmap->alloc = 0;
} else
return ERR_PTR(-ENXIO);
return altmap;
}
static int nd_pmem_probe(struct device *dev)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
struct nd_namespace_common *ndns;
struct nd_namespace_io *nsio;
struct pmem_device *pmem;
ndns = nvdimm_namespace_common_probe(dev);
if (IS_ERR(ndns))
return PTR_ERR(ndns);
nsio = to_nd_namespace_io(&ndns->dev);
pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
if (IS_ERR(pmem))
return PTR_ERR(pmem);
pmem->ndns = ndns;
dev_set_drvdata(dev, pmem);
ndns->rw_bytes = pmem_rw_bytes;
if (is_nd_btt(dev))
return nvdimm_namespace_attach_btt(ndns);
if (is_nd_pfn(dev))
return nvdimm_namespace_attach_pfn(ndns);
if (nd_btt_probe(ndns, pmem) == 0) {
/* we'll come back as btt-pmem */
return -ENXIO;
}
if (nd_pfn_probe(ndns, pmem) == 0) {
/* we'll come back as pfn-pmem */
return -ENXIO;
}
return pmem_attach_disk(dev, ndns, pmem);
}
static int nsio_rw_bytes(struct nd_namespace_common *ndns,
resource_size_t offset, void *buf, size_t size, int rw)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
if (unlikely(offset + size > nsio->size)) {
dev_WARN_ONCE(&ndns->dev, 1, "request out of range\n");
return -EFAULT;
}
if (rw == READ) {
unsigned int sz_align = ALIGN(size + (offset & (512 - 1)), 512);
if (unlikely(is_bad_pmem(&nsio->bb, offset / 512, sz_align)))
return -EIO;
return memcpy_from_pmem(buf, nsio->addr + offset, size);
} else {
memcpy_to_pmem(nsio->addr + offset, buf, size);
nvdimm_flush(to_nd_region(ndns->dev.parent));
}
return 0;
}
static int nvdimm_namespace_attach_pfn(struct nd_namespace_common *ndns)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(&ndns->dev);
struct nd_pfn *nd_pfn = to_nd_pfn(ndns->claim);
struct device *dev = &nd_pfn->dev;
struct vmem_altmap *altmap;
struct nd_region *nd_region;
struct nd_pfn_sb *pfn_sb;
struct pmem_device *pmem;
phys_addr_t offset;
int rc;
if (!nd_pfn->uuid || !nd_pfn->ndns)
return -ENODEV;
nd_region = to_nd_region(dev->parent);
rc = nd_pfn_init(nd_pfn);
if (rc)
return rc;
if (PAGE_SIZE != SZ_4K) {
dev_err(dev, "only supported on systems with 4K PAGE_SIZE\n");
return -ENXIO;
}
if (nsio->res.start & ND_PFN_MASK) {
dev_err(dev, "%s not memory hotplug section aligned\n",
dev_name(&ndns->dev));
return -ENXIO;
}
pfn_sb = nd_pfn->pfn_sb;
offset = le64_to_cpu(pfn_sb->dataoff);
nd_pfn->mode = le32_to_cpu(nd_pfn->pfn_sb->mode);
if (nd_pfn->mode == PFN_MODE_RAM) {
if (offset != SZ_8K)
return -EINVAL;
nd_pfn->npfns = le64_to_cpu(pfn_sb->npfns);
altmap = NULL;
} else {
rc = -ENXIO;
goto err;
}
/* establish pfn range for lookup, and switch to direct map */
pmem = dev_get_drvdata(dev);
memunmap_pmem(dev, pmem->virt_addr);
pmem->virt_addr = (void __pmem *)devm_memremap_pages(dev, &nsio->res);
if (IS_ERR(pmem->virt_addr)) {
rc = PTR_ERR(pmem->virt_addr);
goto err;
}
/* attach pmem disk in "pfn-mode" */
pmem->data_offset = offset;
rc = pmem_attach_disk(dev, ndns, pmem);
if (rc)
goto err;
return rc;
err:
nvdimm_namespace_detach_pfn(ndns);
return rc;
}
int nd_pfn_validate(struct nd_pfn *nd_pfn)
{
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
struct nd_namespace_io *nsio;
u64 checksum, offset;
if (!pfn_sb || !ndns)
return -ENODEV;
if (!is_nd_pmem(nd_pfn->dev.parent))
return -ENODEV;
/* section alignment for simple hotplug */
if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN)
return -ENODEV;
if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb)))
return -ENXIO;
if (memcmp(pfn_sb->signature, PFN_SIG, PFN_SIG_LEN) != 0)
return -ENODEV;
checksum = le64_to_cpu(pfn_sb->checksum);
pfn_sb->checksum = 0;
if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
return -ENODEV;
pfn_sb->checksum = cpu_to_le64(checksum);
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
break;
case PFN_MODE_PMEM:
/* TODO: allocate from PMEM support */
return -ENOTTY;
default:
return -ENXIO;
}
if (!nd_pfn->uuid) {
/* from probe we allocate */
nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
if (!nd_pfn->uuid)
return -ENOMEM;
} else {
/* from init we validate */
if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
return -ENODEV;
}
/*
* These warnings are verbose because they can only trigger in
* the case where the physical address alignment of the
* namespace has changed since the pfn superblock was
* established.
*/
offset = le64_to_cpu(pfn_sb->dataoff);
nsio = to_nd_namespace_io(&ndns->dev);
if (nsio->res.start & ND_PFN_MASK) {
dev_err(&nd_pfn->dev,
"init failed: %s not section aligned\n",
dev_name(&ndns->dev));
return -EBUSY;
} else if (offset >= resource_size(&nsio->res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
dev_name(&ndns->dev));
return -EBUSY;
}
return 0;
}
static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0;
struct nd_namespace_common *ndns = nd_pfn->ndns;
u32 start_pad = 0, end_trunc = 0;
resource_size_t start, size;
struct nd_namespace_io *nsio;
struct nd_region *nd_region;
struct nd_pfn_sb *pfn_sb;
unsigned long npfns;
phys_addr_t offset;
const char *sig;
u64 checksum;
int rc;
pfn_sb = devm_kzalloc(&nd_pfn->dev, sizeof(*pfn_sb), GFP_KERNEL);
if (!pfn_sb)
return -ENOMEM;
nd_pfn->pfn_sb = pfn_sb;
if (is_nd_dax(&nd_pfn->dev))
sig = DAX_SIG;
else
sig = PFN_SIG;
rc = nd_pfn_validate(nd_pfn, sig);
if (rc != -ENODEV)
return rc;
/* no info block, do init */;
nd_region = to_nd_region(nd_pfn->dev.parent);
if (nd_region->ro) {
dev_info(&nd_pfn->dev,
"%s is read-only, unable to init metadata\n",
dev_name(&nd_region->dev));
return -ENXIO;
}
memset(pfn_sb, 0, sizeof(*pfn_sb));
/*
* Check if pmem collides with 'System RAM' when section aligned and
* trim it accordingly
*/
nsio = to_nd_namespace_io(&ndns->dev);
start = PHYS_SECTION_ALIGN_DOWN(nsio->res.start);
size = resource_size(&nsio->res);
if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
IORES_DESC_NONE) == REGION_MIXED) {
start = nsio->res.start;
start_pad = PHYS_SECTION_ALIGN_UP(start) - start;
}
start = nsio->res.start;
size = PHYS_SECTION_ALIGN_UP(start + size) - start;
if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM,
IORES_DESC_NONE) == REGION_MIXED) {
size = resource_size(&nsio->res);
end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size);
}
if (start_pad + end_trunc)
dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n",
dev_name(&ndns->dev), start_pad + end_trunc);
/*
* Note, we use 64 here for the standard size of struct page,
* debugging options may cause it to be larger in which case the
* implementation will limit the pfns advertised through
* ->direct_access() to those that are included in the memmap.
*/
start += start_pad;
size = resource_size(&nsio->res);
npfns = PFN_SECTION_ALIGN_UP((size - start_pad - end_trunc - SZ_8K)
/ PAGE_SIZE);
if (nd_pfn->mode == PFN_MODE_PMEM) {
/*
* The altmap should be padded out to the block size used
* when populating the vmemmap. This *should* be equal to
* PMD_SIZE for most architectures.
*/
offset = ALIGN(start + SZ_8K + 64 * npfns + dax_label_reserve,
max(nd_pfn->align, PMD_SIZE)) - start;
} else if (nd_pfn->mode == PFN_MODE_RAM)
offset = ALIGN(start + SZ_8K + dax_label_reserve,
nd_pfn->align) - start;
else
return -ENXIO;
if (offset + start_pad + end_trunc >= size) {
dev_err(&nd_pfn->dev, "%s unable to satisfy requested alignment\n",
dev_name(&ndns->dev));
return -ENXIO;
}
npfns = (size - offset - start_pad - end_trunc) / SZ_4K;
pfn_sb->mode = cpu_to_le32(nd_pfn->mode);
pfn_sb->dataoff = cpu_to_le64(offset);
pfn_sb->npfns = cpu_to_le64(npfns);
memcpy(pfn_sb->signature, sig, PFN_SIG_LEN);
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
memcpy(pfn_sb->parent_uuid, nd_dev_to_uuid(&ndns->dev), 16);
pfn_sb->version_major = cpu_to_le16(1);
pfn_sb->version_minor = cpu_to_le16(2);
pfn_sb->start_pad = cpu_to_le32(start_pad);
pfn_sb->end_trunc = cpu_to_le32(end_trunc);
pfn_sb->align = cpu_to_le32(nd_pfn->align);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
return nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0);
}
int nd_pfn_validate(struct nd_pfn *nd_pfn, const char *sig)
{
u64 checksum, offset;
unsigned long align;
enum nd_pfn_mode mode;
struct nd_namespace_io *nsio;
struct nd_pfn_sb *pfn_sb = nd_pfn->pfn_sb;
struct nd_namespace_common *ndns = nd_pfn->ndns;
const u8 *parent_uuid = nd_dev_to_uuid(&ndns->dev);
if (!pfn_sb || !ndns)
return -ENODEV;
if (!is_memory(nd_pfn->dev.parent))
return -ENODEV;
if (nvdimm_read_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb), 0))
return -ENXIO;
if (memcmp(pfn_sb->signature, sig, PFN_SIG_LEN) != 0)
return -ENODEV;
checksum = le64_to_cpu(pfn_sb->checksum);
pfn_sb->checksum = 0;
if (checksum != nd_sb_checksum((struct nd_gen_sb *) pfn_sb))
return -ENODEV;
pfn_sb->checksum = cpu_to_le64(checksum);
if (memcmp(pfn_sb->parent_uuid, parent_uuid, 16) != 0)
return -ENODEV;
if (__le16_to_cpu(pfn_sb->version_minor) < 1) {
pfn_sb->start_pad = 0;
pfn_sb->end_trunc = 0;
}
if (__le16_to_cpu(pfn_sb->version_minor) < 2)
pfn_sb->align = 0;
switch (le32_to_cpu(pfn_sb->mode)) {
case PFN_MODE_RAM:
case PFN_MODE_PMEM:
break;
default:
return -ENXIO;
}
align = le32_to_cpu(pfn_sb->align);
offset = le64_to_cpu(pfn_sb->dataoff);
if (align == 0)
align = 1UL << ilog2(offset);
mode = le32_to_cpu(pfn_sb->mode);
if (!nd_pfn->uuid) {
/*
* When probing a namepace via nd_pfn_probe() the uuid
* is NULL (see: nd_pfn_devinit()) we init settings from
* pfn_sb
*/
nd_pfn->uuid = kmemdup(pfn_sb->uuid, 16, GFP_KERNEL);
if (!nd_pfn->uuid)
return -ENOMEM;
nd_pfn->align = align;
nd_pfn->mode = mode;
} else {
/*
* When probing a pfn / dax instance we validate the
* live settings against the pfn_sb
*/
if (memcmp(nd_pfn->uuid, pfn_sb->uuid, 16) != 0)
return -ENODEV;
/*
* If the uuid validates, but other settings mismatch
* return EINVAL because userspace has managed to change
* the configuration without specifying new
* identification.
*/
if (nd_pfn->align != align || nd_pfn->mode != mode) {
dev_err(&nd_pfn->dev,
"init failed, settings mismatch\n");
dev_dbg(&nd_pfn->dev, "align: %lx:%lx mode: %d:%d\n",
nd_pfn->align, align, nd_pfn->mode,
mode);
return -EINVAL;
}
}
if (align > nvdimm_namespace_capacity(ndns)) {
dev_err(&nd_pfn->dev, "alignment: %lx exceeds capacity %llx\n",
align, nvdimm_namespace_capacity(ndns));
return -EINVAL;
}
/*
* These warnings are verbose because they can only trigger in
* the case where the physical address alignment of the
* namespace has changed since the pfn superblock was
* established.
*/
nsio = to_nd_namespace_io(&ndns->dev);
if (offset >= resource_size(&nsio->res)) {
dev_err(&nd_pfn->dev, "pfn array size exceeds capacity of %s\n",
dev_name(&ndns->dev));
return -EBUSY;
}
if ((align && !IS_ALIGNED(offset, align))
|| !IS_ALIGNED(offset, PAGE_SIZE)) {
dev_err(&nd_pfn->dev,
"bad offset: %#llx dax disabled align: %#lx\n",
offset, align);
return -ENXIO;
}
return 0;
}
static void namespace_io_release(struct device *dev)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
kfree(nsio);
}
