/**
* nd_btt_arena_is_valid - check if the metadata layout is valid
* @nd_btt: device with BTT geometry and backing device info
* @super: pointer to the arena's info block being tested
*
* Check consistency of the btt info block with itself by validating
* the checksum, and with the parent namespace by verifying the
* parent_uuid contained in the info block with the one supplied in.
*
* Returns:
* false for an invalid info block, true for a valid one
*/
bool nd_btt_arena_is_valid(struct nd_btt *nd_btt, struct btt_sb *super)
{
const u8 *parent_uuid = nd_dev_to_uuid(&nd_btt->ndns->dev);
u64 checksum;
if (memcmp(super->signature, BTT_SIG, BTT_SIG_LEN) != 0)
return false;
if (!uuid_is_null(super->parent_uuid))
if (memcmp(super->parent_uuid, parent_uuid, 16) != 0)
return false;
checksum = le64_to_cpu(super->checksum);
super->checksum = 0;
if (checksum != nd_btt_sb_checksum(super))
return false;
super->checksum = cpu_to_le64(checksum);
/* TODO: figure out action for this */
if ((le32_to_cpu(super->flags) & IB_FLAG_ERROR_MASK) != 0)
dev_info(&nd_btt->dev, "Found arena with an error flag\n");
return true;
}
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;
}
