libnvdimm: write pmem label set

After 'uuid', 'size', and optionally 'alt_name' have been set to valid
values the labels on the dimms can be updated.

Write procedure is:
1/ Allocate and write new labels in the "next" index
2/ Free the old labels in the working copy
3/ Write the bitmap and the label space on the dimm
4/ Write the index to make the update valid

Label ranges directly mirror the dpa resource values for the given
label_id of the namespace.

Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Neil Brown <neilb@suse.de>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Dan Williams 2015-05-30 12:36:02 -04:00
parent 1b40e09a12
commit f524bf271a
5 changed files with 455 additions and 14 deletions

View File

@ -132,6 +132,55 @@ int nvdimm_init_config_data(struct nvdimm_drvdata *ndd)
return rc;
}
int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
void *buf, size_t len)
{
int rc = validate_dimm(ndd);
size_t max_cmd_size, buf_offset;
struct nd_cmd_set_config_hdr *cmd;
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(ndd->dev);
struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc;
if (rc)
return rc;
if (!ndd->data)
return -ENXIO;
if (offset + len > ndd->nsarea.config_size)
return -ENXIO;
max_cmd_size = min_t(u32, PAGE_SIZE, len);
max_cmd_size = min_t(u32, max_cmd_size, ndd->nsarea.max_xfer);
cmd = kzalloc(max_cmd_size + sizeof(*cmd) + sizeof(u32), GFP_KERNEL);
if (!cmd)
return -ENOMEM;
for (buf_offset = 0; len; len -= cmd->in_length,
buf_offset += cmd->in_length) {
size_t cmd_size;
u32 *status;
cmd->in_offset = offset + buf_offset;
cmd->in_length = min(max_cmd_size, len);
memcpy(cmd->in_buf, buf + buf_offset, cmd->in_length);
/* status is output in the last 4-bytes of the command buffer */
cmd_size = sizeof(*cmd) + cmd->in_length + sizeof(u32);
status = ((void *) cmd) + cmd_size - sizeof(u32);
rc = nd_desc->ndctl(nd_desc, to_nvdimm(ndd->dev),
ND_CMD_SET_CONFIG_DATA, cmd, cmd_size);
if (rc || *status) {
rc = rc ? rc : -ENXIO;
break;
}
}
kfree(cmd);
return rc;
}
static void nvdimm_release(struct device *dev)
{
struct nvdimm *nvdimm = to_nvdimm(dev);

View File

@ -12,6 +12,7 @@
*/
#include <linux/device.h>
#include <linux/ndctl.h>
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/nd.h>
#include "nd-core.h"
@ -55,6 +56,11 @@ size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd)
return ndd->nsindex_size;
}
static int nvdimm_num_label_slots(struct nvdimm_drvdata *ndd)
{
return ndd->nsarea.config_size / 129;
}
int nd_label_validate(struct nvdimm_drvdata *ndd)
{
/*
@ -201,25 +207,32 @@ static struct nd_namespace_label *nd_label_base(struct nvdimm_drvdata *ndd)
return base + 2 * sizeof_namespace_index(ndd);
}
static int to_slot(struct nvdimm_drvdata *ndd,
struct nd_namespace_label *nd_label)
{
return nd_label - nd_label_base(ndd);
}
#define for_each_clear_bit_le(bit, addr, size) \
for ((bit) = find_next_zero_bit_le((addr), (size), 0); \
(bit) < (size); \
(bit) = find_next_zero_bit_le((addr), (size), (bit) + 1))
/**
* preamble_current - common variable initialization for nd_label_* routines
* preamble_index - common variable initialization for nd_label_* routines
* @ndd: dimm container for the relevant label set
* @idx: namespace_index index
* @nsindex_out: on return set to the currently active namespace index
* @free: on return set to the free label bitmap in the index
* @nslot: on return set to the number of slots in the label space
*/
static bool preamble_current(struct nvdimm_drvdata *ndd,
static bool preamble_index(struct nvdimm_drvdata *ndd, int idx,
struct nd_namespace_index **nsindex_out,
unsigned long **free, u32 *nslot)
{
struct nd_namespace_index *nsindex;
nsindex = to_current_namespace_index(ndd);
nsindex = to_namespace_index(ndd, idx);
if (nsindex == NULL)
return false;
@ -239,6 +252,22 @@ char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags)
return label_id->id;
}
static bool preamble_current(struct nvdimm_drvdata *ndd,
struct nd_namespace_index **nsindex,
unsigned long **free, u32 *nslot)
{
return preamble_index(ndd, ndd->ns_current, nsindex,
free, nslot);
}
static bool preamble_next(struct nvdimm_drvdata *ndd,
struct nd_namespace_index **nsindex,
unsigned long **free, u32 *nslot)
{
return preamble_index(ndd, ndd->ns_next, nsindex,
free, nslot);
}
static bool slot_valid(struct nd_namespace_label *nd_label, u32 slot)
{
/* check that we are written where we expect to be written */
@ -341,3 +370,296 @@ struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n)
return NULL;
}
static u32 nd_label_alloc_slot(struct nvdimm_drvdata *ndd)
{
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot, slot;
if (!preamble_next(ndd, &nsindex, &free, &nslot))
return UINT_MAX;
WARN_ON(!is_nvdimm_bus_locked(ndd->dev));
slot = find_next_bit_le(free, nslot, 0);
if (slot == nslot)
return UINT_MAX;
clear_bit_le(slot, free);
return slot;
}
static bool nd_label_free_slot(struct nvdimm_drvdata *ndd, u32 slot)
{
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot;
if (!preamble_next(ndd, &nsindex, &free, &nslot))
return false;
WARN_ON(!is_nvdimm_bus_locked(ndd->dev));
if (slot < nslot)
return !test_and_set_bit_le(slot, free);
return false;
}
u32 nd_label_nfree(struct nvdimm_drvdata *ndd)
{
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot;
WARN_ON(!is_nvdimm_bus_locked(ndd->dev));
if (!preamble_next(ndd, &nsindex, &free, &nslot))
return 0;
return bitmap_weight(free, nslot);
}
static int nd_label_write_index(struct nvdimm_drvdata *ndd, int index, u32 seq,
unsigned long flags)
{
struct nd_namespace_index *nsindex;
unsigned long offset;
u64 checksum;
u32 nslot;
int rc;
nsindex = to_namespace_index(ndd, index);
if (flags & ND_NSINDEX_INIT)
nslot = nvdimm_num_label_slots(ndd);
else
nslot = __le32_to_cpu(nsindex->nslot);
memcpy(nsindex->sig, NSINDEX_SIGNATURE, NSINDEX_SIG_LEN);
nsindex->flags = __cpu_to_le32(0);
nsindex->seq = __cpu_to_le32(seq);
offset = (unsigned long) nsindex
- (unsigned long) to_namespace_index(ndd, 0);
nsindex->myoff = __cpu_to_le64(offset);
nsindex->mysize = __cpu_to_le64(sizeof_namespace_index(ndd));
offset = (unsigned long) to_namespace_index(ndd,
nd_label_next_nsindex(index))
- (unsigned long) to_namespace_index(ndd, 0);
nsindex->otheroff = __cpu_to_le64(offset);
offset = (unsigned long) nd_label_base(ndd)
- (unsigned long) to_namespace_index(ndd, 0);
nsindex->labeloff = __cpu_to_le64(offset);
nsindex->nslot = __cpu_to_le32(nslot);
nsindex->major = __cpu_to_le16(1);
nsindex->minor = __cpu_to_le16(1);
nsindex->checksum = __cpu_to_le64(0);
if (flags & ND_NSINDEX_INIT) {
unsigned long *free = (unsigned long *) nsindex->free;
u32 nfree = ALIGN(nslot, BITS_PER_LONG);
int last_bits, i;
memset(nsindex->free, 0xff, nfree / 8);
for (i = 0, last_bits = nfree - nslot; i < last_bits; i++)
clear_bit_le(nslot + i, free);
}
checksum = nd_fletcher64(nsindex, sizeof_namespace_index(ndd), 1);
nsindex->checksum = __cpu_to_le64(checksum);
rc = nvdimm_set_config_data(ndd, __le64_to_cpu(nsindex->myoff),
nsindex, sizeof_namespace_index(ndd));
if (rc < 0)
return rc;
if (flags & ND_NSINDEX_INIT)
return 0;
/* copy the index we just wrote to the new 'next' */
WARN_ON(index != ndd->ns_next);
nd_label_copy(ndd, to_current_namespace_index(ndd), nsindex);
ndd->ns_current = nd_label_next_nsindex(ndd->ns_current);
ndd->ns_next = nd_label_next_nsindex(ndd->ns_next);
WARN_ON(ndd->ns_current == ndd->ns_next);
return 0;
}
static unsigned long nd_label_offset(struct nvdimm_drvdata *ndd,
struct nd_namespace_label *nd_label)
{
return (unsigned long) nd_label
- (unsigned long) to_namespace_index(ndd, 0);
}
static int __pmem_label_update(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, struct nd_namespace_pmem *nspm,
int pos)
{
u64 cookie = nd_region_interleave_set_cookie(nd_region), rawsize;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_namespace_label *victim_label;
struct nd_namespace_label *nd_label;
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot, slot;
size_t offset;
int rc;
if (!preamble_next(ndd, &nsindex, &free, &nslot))
return -ENXIO;
/* allocate and write the label to the staging (next) index */
slot = nd_label_alloc_slot(ndd);
if (slot == UINT_MAX)
return -ENXIO;
dev_dbg(ndd->dev, "%s: allocated: %d\n", __func__, slot);
nd_label = nd_label_base(ndd) + slot;
memset(nd_label, 0, sizeof(struct nd_namespace_label));
memcpy(nd_label->uuid, nspm->uuid, NSLABEL_UUID_LEN);
if (nspm->alt_name)
memcpy(nd_label->name, nspm->alt_name, NSLABEL_NAME_LEN);
nd_label->flags = __cpu_to_le32(NSLABEL_FLAG_UPDATING);
nd_label->nlabel = __cpu_to_le16(nd_region->ndr_mappings);
nd_label->position = __cpu_to_le16(pos);
nd_label->isetcookie = __cpu_to_le64(cookie);
rawsize = div_u64(resource_size(&nspm->nsio.res),
nd_region->ndr_mappings);
nd_label->rawsize = __cpu_to_le64(rawsize);
nd_label->dpa = __cpu_to_le64(nd_mapping->start);
nd_label->slot = __cpu_to_le32(slot);
/* update label */
offset = nd_label_offset(ndd, nd_label);
rc = nvdimm_set_config_data(ndd, offset, nd_label,
sizeof(struct nd_namespace_label));
if (rc < 0)
return rc;
/* Garbage collect the previous label */
victim_label = nd_mapping->labels[0];
if (victim_label) {
slot = to_slot(ndd, victim_label);
nd_label_free_slot(ndd, slot);
dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
}
/* update index */
rc = nd_label_write_index(ndd, ndd->ns_next,
nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
if (rc < 0)
return rc;
nd_mapping->labels[0] = nd_label;
return 0;
}
static int init_labels(struct nd_mapping *nd_mapping)
{
int i;
struct nd_namespace_index *nsindex;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
if (!nd_mapping->labels)
nd_mapping->labels = kcalloc(2, sizeof(void *), GFP_KERNEL);
if (!nd_mapping->labels)
return -ENOMEM;
if (ndd->ns_current == -1 || ndd->ns_next == -1)
/* pass */;
else
return 0;
nsindex = to_namespace_index(ndd, 0);
memset(nsindex, 0, ndd->nsarea.config_size);
for (i = 0; i < 2; i++) {
int rc = nd_label_write_index(ndd, i, i*2, ND_NSINDEX_INIT);
if (rc)
return rc;
}
ndd->ns_next = 1;
ndd->ns_current = 0;
return 0;
}
static int del_labels(struct nd_mapping *nd_mapping, u8 *uuid)
{
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_namespace_label *nd_label;
struct nd_namespace_index *nsindex;
u8 label_uuid[NSLABEL_UUID_LEN];
int l, num_freed = 0;
unsigned long *free;
u32 nslot, slot;
if (!uuid)
return 0;
/* no index || no labels == nothing to delete */
if (!preamble_next(ndd, &nsindex, &free, &nslot)
|| !nd_mapping->labels)
return 0;
for_each_label(l, nd_label, nd_mapping->labels) {
int j;
memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN);
if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0)
continue;
slot = to_slot(ndd, nd_label);
nd_label_free_slot(ndd, slot);
dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
for (j = l; nd_mapping->labels[j + 1]; j++) {
struct nd_namespace_label *next_label;
next_label = nd_mapping->labels[j + 1];
nd_mapping->labels[j] = next_label;
}
nd_mapping->labels[j] = NULL;
num_freed++;
}
if (num_freed > l) {
/*
* num_freed will only ever be > l when we delete the last
* label
*/
kfree(nd_mapping->labels);
nd_mapping->labels = NULL;
dev_dbg(ndd->dev, "%s: no more labels\n", __func__);
}
return nd_label_write_index(ndd, ndd->ns_next,
nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
}
int nd_pmem_namespace_label_update(struct nd_region *nd_region,
struct nd_namespace_pmem *nspm, resource_size_t size)
{
int i;
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
int rc;
if (size == 0) {
rc = del_labels(nd_mapping, nspm->uuid);
if (rc)
return rc;
continue;
}
rc = init_labels(nd_mapping);
if (rc)
return rc;
rc = __pmem_label_update(nd_region, nd_mapping, nspm, i);
if (rc)
return rc;
}
return 0;
}

View File

@ -34,6 +34,7 @@ enum {
BTTINFO_MAJOR_VERSION = 1,
ND_LABEL_MIN_SIZE = 512 * 129, /* see sizeof_namespace_index() */
ND_LABEL_ID_SIZE = 50,
ND_NSINDEX_INIT = 0x1,
};
static const char NSINDEX_SIGNATURE[] = "NAMESPACE_INDEX\0";
@ -127,4 +128,9 @@ void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst,
size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd);
int nd_label_active_count(struct nvdimm_drvdata *ndd);
struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n);
u32 nd_label_nfree(struct nvdimm_drvdata *ndd);
struct nd_region;
struct nd_namespace_pmem;
int nd_pmem_namespace_label_update(struct nd_region *nd_region,
struct nd_namespace_pmem *nspm, resource_size_t size);
#endif /* __LABEL_H__ */

View File

@ -149,20 +149,53 @@ static resource_size_t nd_namespace_blk_size(struct nd_namespace_blk *nsblk)
return size;
}
static int nd_namespace_label_update(struct nd_region *nd_region,
struct device *dev)
{
dev_WARN_ONCE(dev, dev->driver,
"namespace must be idle during label update\n");
if (dev->driver)
return 0;
/*
* Only allow label writes that will result in a valid namespace
* or deletion of an existing namespace.
*/
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
struct resource *res = &nspm->nsio.res;
resource_size_t size = resource_size(res);
if (size == 0 && nspm->uuid)
/* delete allocation */;
else if (!nspm->uuid)
return 0;
return nd_pmem_namespace_label_update(nd_region, nspm, size);
} else if (is_namespace_blk(dev)) {
/* TODO: implement blk labels */
return 0;
} else
return -ENXIO;
}
static ssize_t alt_name_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
device_lock(dev);
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __alt_name_store(dev, buf, len);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s: %s(%zd)\n", __func__, rc < 0 ? "fail " : "", rc);
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc;
return rc < 0 ? rc : len;
}
static ssize_t alt_name_show(struct device *dev,
@ -709,6 +742,7 @@ static ssize_t __size_store(struct device *dev, unsigned long long val)
static ssize_t size_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
unsigned long long val;
u8 **uuid = NULL;
int rc;
@ -721,6 +755,8 @@ static ssize_t size_store(struct device *dev,
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
rc = __size_store(dev, val);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
if (is_namespace_pmem(dev)) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
@ -744,7 +780,7 @@ static ssize_t size_store(struct device *dev,
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc ? rc : len;
return rc < 0 ? rc : len;
}
static ssize_t size_show(struct device *dev,
@ -804,17 +840,34 @@ static int namespace_update_uuid(struct nd_region *nd_region,
u32 flags = is_namespace_blk(dev) ? NSLABEL_FLAG_LOCAL : 0;
struct nd_label_id old_label_id;
struct nd_label_id new_label_id;
int i, rc;
int i;
rc = nd_is_uuid_unique(dev, new_uuid) ? 0 : -EINVAL;
if (rc) {
kfree(new_uuid);
return rc;
}
if (!nd_is_uuid_unique(dev, new_uuid))
return -EINVAL;
if (*old_uuid == NULL)
goto out;
/*
* If we've already written a label with this uuid, then it's
* too late to rename because we can't reliably update the uuid
* without losing the old namespace. Userspace must delete this
* namespace to abandon the old uuid.
*/
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
/*
* This check by itself is sufficient because old_uuid
* would be NULL above if this uuid did not exist in the
* currently written set.
*
* FIXME: can we delete uuid with zero dpa allocated?
*/
if (nd_mapping->labels)
return -EBUSY;
}
nd_label_gen_id(&old_label_id, *old_uuid, flags);
nd_label_gen_id(&new_label_id, new_uuid, flags);
for (i = 0; i < nd_region->ndr_mappings; i++) {
@ -858,12 +911,16 @@ static ssize_t uuid_store(struct device *dev,
rc = nd_uuid_store(dev, &uuid, buf, len);
if (rc >= 0)
rc = namespace_update_uuid(nd_region, dev, uuid, ns_uuid);
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
else
kfree(uuid);
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
device_unlock(dev);
return rc ? rc : len;
return rc < 0 ? rc : len;
}
static DEVICE_ATTR_RW(uuid);
@ -907,6 +964,7 @@ static ssize_t sector_size_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t len)
{
struct nd_namespace_blk *nsblk = to_nd_namespace_blk(dev);
struct nd_region *nd_region = to_nd_region(dev->parent);
ssize_t rc;
if (!is_namespace_blk(dev))
@ -916,8 +974,11 @@ static ssize_t sector_size_store(struct device *dev,
nvdimm_bus_lock(dev);
rc = nd_sector_size_store(dev, buf, &nsblk->lbasize,
ns_lbasize_supported);
dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
rc, buf, buf[len - 1] == '\n' ? "" : "\n");
if (rc >= 0)
rc = nd_namespace_label_update(nd_region, dev);
dev_dbg(dev, "%s: result: %zd %s: %s%s", __func__,
rc, rc < 0 ? "tried" : "wrote", buf,
buf[len - 1] == '\n' ? "" : "\n");
nvdimm_bus_unlock(dev);
device_unlock(dev);

View File

@ -93,6 +93,7 @@ static inline unsigned nd_inc_seq(unsigned seq)
return next[seq & 3];
}
enum nd_async_mode {
ND_SYNC,
ND_ASYNC,
@ -115,6 +116,8 @@ struct nvdimm;
struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping);
int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd);
int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
int nvdimm_set_config_data(struct nvdimm_drvdata *ndd, size_t offset,
void *buf, size_t len);
struct nd_region *to_nd_region(struct device *dev);
int nd_region_to_nstype(struct nd_region *nd_region);
int nd_region_register_namespaces(struct nd_region *nd_region, int *err);