/**
* 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 int __nd_btt_probe(struct nd_btt *nd_btt,
struct nd_namespace_common *ndns, struct btt_sb *btt_sb)
{
if (!btt_sb || !ndns || !nd_btt)
return -ENODEV;
if (nvdimm_read_bytes(ndns, SZ_4K, btt_sb, sizeof(*btt_sb)))
return -ENXIO;
if (nvdimm_namespace_capacity(ndns) < SZ_16M)
return -ENXIO;
if (!nd_btt_arena_is_valid(nd_btt, btt_sb))
return -ENODEV;
nd_btt->lbasize = le32_to_cpu(btt_sb->external_lbasize);
nd_btt->uuid = kmemdup(btt_sb->uuid, 16, GFP_KERNEL);
if (!nd_btt->uuid)
return -ENOMEM;
__nd_device_register(&nd_btt->dev);
return 0;
}
static int nd_pfn_init(struct nd_pfn *nd_pfn)
{
struct nd_pfn_sb *pfn_sb = kzalloc(sizeof(*pfn_sb), GFP_KERNEL);
struct pmem_device *pmem = dev_get_drvdata(&nd_pfn->dev);
struct nd_namespace_common *ndns = nd_pfn->ndns;
struct nd_region *nd_region;
unsigned long npfns;
phys_addr_t offset;
u64 checksum;
int rc;
if (!pfn_sb)
return -ENOMEM;
nd_pfn->pfn_sb = pfn_sb;
rc = nd_pfn_validate(nd_pfn);
if (rc == 0 || rc == -EBUSY)
return rc;
/* section alignment for simple hotplug */
if (nvdimm_namespace_capacity(ndns) < ND_PFN_ALIGN
|| pmem->phys_addr & ND_PFN_MASK)
return -ENODEV;
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));
goto err;
}
memset(pfn_sb, 0, sizeof(*pfn_sb));
npfns = (pmem->size - SZ_8K) / SZ_4K;
/*
* 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.
*/
if (nd_pfn->mode == PFN_MODE_PMEM)
offset = ALIGN(SZ_8K + 64 * npfns, PMD_SIZE);
else if (nd_pfn->mode == PFN_MODE_RAM)
offset = SZ_8K;
else
goto err;
npfns = (pmem->size - offset) / 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, PFN_SIG, PFN_SIG_LEN);
memcpy(pfn_sb->uuid, nd_pfn->uuid, 16);
pfn_sb->version_major = cpu_to_le16(1);
checksum = nd_sb_checksum((struct nd_gen_sb *) pfn_sb);
pfn_sb->checksum = cpu_to_le64(checksum);
rc = nvdimm_write_bytes(ndns, SZ_4K, pfn_sb, sizeof(*pfn_sb));
if (rc)
goto err;
return 0;
err:
nd_pfn->pfn_sb = NULL;
kfree(pfn_sb);
return -ENXIO;
}
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;
}
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;
}
