Commit bf9bccc1 authored by Dan Williams's avatar Dan Williams

libnvdimm: pmem label sets and namespace instantiation.

A complete label set is a PMEM-label per-dimm per-interleave-set where
all the UUIDs match and the interleave set cookie matches the hosting
interleave set.

Present sysfs attributes for manipulation of a PMEM-namespace's
'alt_name', 'uuid', and 'size' attributes.  A later patch will make
these settings persistent by writing back the label.

Note that PMEM allocations grow forwards from the start of an interleave
set (lowest dimm-physical-address (DPA)).  BLK-namespaces that alias
with a PMEM interleave set will grow allocations backward from the
highest DPA.

Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Neil Brown <neilb@suse.de>
Acked-by: default avatarChristoph Hellwig <hch@lst.de>
Signed-off-by: default avatarDan Williams <dan.j.williams@intel.com>
parent 4a826c83
...@@ -97,6 +97,8 @@ static int nvdimm_bus_probe(struct device *dev) ...@@ -97,6 +97,8 @@ static int nvdimm_bus_probe(struct device *dev)
rc = nd_drv->probe(dev); rc = nd_drv->probe(dev);
if (rc == 0) if (rc == 0)
nd_region_probe_success(nvdimm_bus, dev); nd_region_probe_success(nvdimm_bus, dev);
else
nd_region_disable(nvdimm_bus, dev);
nvdimm_bus_probe_end(nvdimm_bus); nvdimm_bus_probe_end(nvdimm_bus);
dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name, dev_dbg(&nvdimm_bus->dev, "%s.probe(%s) = %d\n", dev->driver->name,
...@@ -381,8 +383,10 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd, ...@@ -381,8 +383,10 @@ u32 nd_cmd_out_size(struct nvdimm *nvdimm, int cmd,
} }
EXPORT_SYMBOL_GPL(nd_cmd_out_size); EXPORT_SYMBOL_GPL(nd_cmd_out_size);
static void wait_nvdimm_bus_probe_idle(struct nvdimm_bus *nvdimm_bus) void wait_nvdimm_bus_probe_idle(struct device *dev)
{ {
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
do { do {
if (nvdimm_bus->probe_active == 0) if (nvdimm_bus->probe_active == 0)
break; break;
...@@ -402,7 +406,7 @@ static int nd_cmd_clear_to_send(struct nvdimm *nvdimm, unsigned int cmd) ...@@ -402,7 +406,7 @@ static int nd_cmd_clear_to_send(struct nvdimm *nvdimm, unsigned int cmd)
return 0; return 0;
nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev); nvdimm_bus = walk_to_nvdimm_bus(&nvdimm->dev);
wait_nvdimm_bus_probe_idle(nvdimm_bus); wait_nvdimm_bus_probe_idle(&nvdimm_bus->dev);
if (atomic_read(&nvdimm->busy)) if (atomic_read(&nvdimm->busy))
return -EBUSY; return -EBUSY;
......
...@@ -14,6 +14,7 @@ ...@@ -14,6 +14,7 @@
#include <linux/export.h> #include <linux/export.h>
#include <linux/module.h> #include <linux/module.h>
#include <linux/device.h> #include <linux/device.h>
#include <linux/ctype.h>
#include <linux/ndctl.h> #include <linux/ndctl.h>
#include <linux/mutex.h> #include <linux/mutex.h>
#include <linux/slab.h> #include <linux/slab.h>
...@@ -109,6 +110,69 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev) ...@@ -109,6 +110,69 @@ struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
return NULL; return NULL;
} }
static bool is_uuid_sep(char sep)
{
if (sep == '\n' || sep == '-' || sep == ':' || sep == '\0')
return true;
return false;
}
static int nd_uuid_parse(struct device *dev, u8 *uuid_out, const char *buf,
size_t len)
{
const char *str = buf;
u8 uuid[16];
int i;
for (i = 0; i < 16; i++) {
if (!isxdigit(str[0]) || !isxdigit(str[1])) {
dev_dbg(dev, "%s: pos: %d buf[%zd]: %c buf[%zd]: %c\n",
__func__, i, str - buf, str[0],
str + 1 - buf, str[1]);
return -EINVAL;
}
uuid[i] = (hex_to_bin(str[0]) << 4) | hex_to_bin(str[1]);
str += 2;
if (is_uuid_sep(*str))
str++;
}
memcpy(uuid_out, uuid, sizeof(uuid));
return 0;
}
/**
* nd_uuid_store: common implementation for writing 'uuid' sysfs attributes
* @dev: container device for the uuid property
* @uuid_out: uuid buffer to replace
* @buf: raw sysfs buffer to parse
*
* Enforce that uuids can only be changed while the device is disabled
* (driver detached)
* LOCKING: expects device_lock() is held on entry
*/
int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
size_t len)
{
u8 uuid[16];
int rc;
if (dev->driver)
return -EBUSY;
rc = nd_uuid_parse(dev, uuid, buf, len);
if (rc)
return rc;
kfree(*uuid_out);
*uuid_out = kmemdup(uuid, sizeof(uuid), GFP_KERNEL);
if (!(*uuid_out))
return -ENOMEM;
return 0;
}
static ssize_t commands_show(struct device *dev, static ssize_t commands_show(struct device *dev,
struct device_attribute *attr, char *buf) struct device_attribute *attr, char *buf)
{ {
......
...@@ -21,18 +21,6 @@ ...@@ -21,18 +21,6 @@
#include "label.h" #include "label.h"
#include "nd.h" #include "nd.h"
static void free_data(struct nvdimm_drvdata *ndd)
{
if (!ndd)
return;
if (ndd->data && is_vmalloc_addr(ndd->data))
vfree(ndd->data);
else
kfree(ndd->data);
kfree(ndd);
}
static int nvdimm_probe(struct device *dev) static int nvdimm_probe(struct device *dev)
{ {
struct nvdimm_drvdata *ndd; struct nvdimm_drvdata *ndd;
...@@ -49,6 +37,8 @@ static int nvdimm_probe(struct device *dev) ...@@ -49,6 +37,8 @@ static int nvdimm_probe(struct device *dev)
ndd->dpa.start = 0; ndd->dpa.start = 0;
ndd->dpa.end = -1; ndd->dpa.end = -1;
ndd->dev = dev; ndd->dev = dev;
get_device(dev);
kref_init(&ndd->kref);
rc = nvdimm_init_nsarea(ndd); rc = nvdimm_init_nsarea(ndd);
if (rc) if (rc)
...@@ -74,21 +64,18 @@ static int nvdimm_probe(struct device *dev) ...@@ -74,21 +64,18 @@ static int nvdimm_probe(struct device *dev)
return 0; return 0;
err: err:
free_data(ndd); put_ndd(ndd);
return rc; return rc;
} }
static int nvdimm_remove(struct device *dev) static int nvdimm_remove(struct device *dev)
{ {
struct nvdimm_drvdata *ndd = dev_get_drvdata(dev); struct nvdimm_drvdata *ndd = dev_get_drvdata(dev);
struct resource *res, *_r;
nvdimm_bus_lock(dev); nvdimm_bus_lock(dev);
dev_set_drvdata(dev, NULL); dev_set_drvdata(dev, NULL);
for_each_dpa_resource_safe(ndd, res, _r)
nvdimm_free_dpa(ndd, res);
nvdimm_bus_unlock(dev); nvdimm_bus_unlock(dev);
free_data(ndd); put_ndd(ndd);
return 0; return 0;
} }
......
...@@ -159,6 +159,48 @@ struct nvdimm *to_nvdimm(struct device *dev) ...@@ -159,6 +159,48 @@ struct nvdimm *to_nvdimm(struct device *dev)
} }
EXPORT_SYMBOL_GPL(to_nvdimm); EXPORT_SYMBOL_GPL(to_nvdimm);
struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping)
{
struct nvdimm *nvdimm = nd_mapping->nvdimm;
WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm->dev));
return dev_get_drvdata(&nvdimm->dev);
}
EXPORT_SYMBOL(to_ndd);
void nvdimm_drvdata_release(struct kref *kref)
{
struct nvdimm_drvdata *ndd = container_of(kref, typeof(*ndd), kref);
struct device *dev = ndd->dev;
struct resource *res, *_r;
dev_dbg(dev, "%s\n", __func__);
nvdimm_bus_lock(dev);
for_each_dpa_resource_safe(ndd, res, _r)
nvdimm_free_dpa(ndd, res);
nvdimm_bus_unlock(dev);
if (ndd->data && is_vmalloc_addr(ndd->data))
vfree(ndd->data);
else
kfree(ndd->data);
kfree(ndd);
put_device(dev);
}
void get_ndd(struct nvdimm_drvdata *ndd)
{
kref_get(&ndd->kref);
}
void put_ndd(struct nvdimm_drvdata *ndd)
{
if (ndd)
kref_put(&ndd->kref, nvdimm_drvdata_release);
}
const char *nvdimm_name(struct nvdimm *nvdimm) const char *nvdimm_name(struct nvdimm *nvdimm)
{ {
return dev_name(&nvdimm->dev); return dev_name(&nvdimm->dev);
...@@ -247,6 +289,83 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data, ...@@ -247,6 +289,83 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
} }
EXPORT_SYMBOL_GPL(nvdimm_create); EXPORT_SYMBOL_GPL(nvdimm_create);
/**
* nd_pmem_available_dpa - for the given dimm+region account unallocated dpa
* @nd_mapping: container of dpa-resource-root + labels
* @nd_region: constrain available space check to this reference region
* @overlap: calculate available space assuming this level of overlap
*
* Validate that a PMEM label, if present, aligns with the start of an
* interleave set and truncate the available size at the lowest BLK
* overlap point.
*
* The expectation is that this routine is called multiple times as it
* probes for the largest BLK encroachment for any single member DIMM of
* the interleave set. Once that value is determined the PMEM-limit for
* the set can be established.
*/
resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, resource_size_t *overlap)
{
resource_size_t map_start, map_end, busy = 0, available, blk_start;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct resource *res;
const char *reason;
if (!ndd)
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) {
if (strncmp(res->name, "blk", 3) == 0)
blk_start = min(blk_start, res->start);
else if (res->start != map_start) {
reason = "misaligned to iset";
goto err;
} else {
if (busy) {
reason = "duplicate overlapping PMEM reservations?";
goto err;
}
busy += resource_size(res);
continue;
}
} else if (res->end >= map_start && res->end <= map_end) {
if (strncmp(res->name, "blk", 3) == 0) {
/*
* If a BLK allocation overlaps the start of
* PMEM the entire interleave set may now only
* be used for BLK.
*/
blk_start = map_start;
} else {
reason = "misaligned to iset";
goto err;
}
} else if (map_start > res->start && map_start < res->end) {
/* total eclipse of the mapping */
busy += nd_mapping->size;
blk_start = map_start;
}
*overlap = map_end + 1 - blk_start;
available = blk_start - map_start;
if (busy < available)
return available - busy;
return 0;
err:
/*
* Something is wrong, PMEM must align with the start of the
* interleave set, and there can only be one allocation per set.
*/
nd_dbg_dpa(nd_region, ndd, res, "%s\n", reason);
return 0;
}
void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res) void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res)
{ {
WARN_ON_ONCE(!is_nvdimm_bus_locked(ndd->dev)); WARN_ON_ONCE(!is_nvdimm_bus_locked(ndd->dev));
...@@ -271,6 +390,24 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, ...@@ -271,6 +390,24 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
return res; return res;
} }
/**
* nvdimm_allocated_dpa - sum up the dpa currently allocated to this label_id
* @nvdimm: container of dpa-resource-root + labels
* @label_id: dpa resource name of the form {pmem|blk}-<human readable uuid>
*/
resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
struct nd_label_id *label_id)
{
resource_size_t allocated = 0;
struct resource *res;
for_each_dpa_resource(ndd, res)
if (strcmp(res->name, label_id->id) == 0)
allocated += resource_size(res);
return allocated;
}
static int count_dimms(struct device *dev, void *c) static int count_dimms(struct device *dev, void *c)
{ {
int *count = c; int *count = c;
......
...@@ -230,7 +230,7 @@ static bool preamble_current(struct nvdimm_drvdata *ndd, ...@@ -230,7 +230,7 @@ static bool preamble_current(struct nvdimm_drvdata *ndd,
return true; return true;
} }
static char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags) char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags)
{ {
if (!label_id || !uuid) if (!label_id || !uuid)
return NULL; return NULL;
...@@ -288,3 +288,56 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd) ...@@ -288,3 +288,56 @@ int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd)
return 0; return 0;
} }
int nd_label_active_count(struct nvdimm_drvdata *ndd)
{
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot, slot;
int count = 0;
if (!preamble_current(ndd, &nsindex, &free, &nslot))
return 0;
for_each_clear_bit_le(slot, free, nslot) {
struct nd_namespace_label *nd_label;
nd_label = nd_label_base(ndd) + slot;
if (!slot_valid(nd_label, slot)) {
u32 label_slot = __le32_to_cpu(nd_label->slot);
u64 size = __le64_to_cpu(nd_label->rawsize);
u64 dpa = __le64_to_cpu(nd_label->dpa);
dev_dbg(ndd->dev,
"%s: slot%d invalid slot: %d dpa: %llx size: %llx\n",
__func__, slot, label_slot, dpa, size);
continue;
}
count++;
}
return count;
}
struct nd_namespace_label *nd_label_active(struct nvdimm_drvdata *ndd, int n)
{
struct nd_namespace_index *nsindex;
unsigned long *free;
u32 nslot, slot;
if (!preamble_current(ndd, &nsindex, &free, &nslot))
return NULL;
for_each_clear_bit_le(slot, free, nslot) {
struct nd_namespace_label *nd_label;
nd_label = nd_label_base(ndd) + slot;
if (!slot_valid(nd_label, slot))
continue;
if (n-- == 0)
return nd_label_base(ndd) + slot;
}
return NULL;
}
...@@ -125,4 +125,6 @@ int nd_label_validate(struct nvdimm_drvdata *ndd); ...@@ -125,4 +125,6 @@ int nd_label_validate(struct nvdimm_drvdata *ndd);
void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst, void nd_label_copy(struct nvdimm_drvdata *ndd, struct nd_namespace_index *dst,
struct nd_namespace_index *src); struct nd_namespace_index *src);
size_t sizeof_namespace_index(struct nvdimm_drvdata *ndd); 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);
#endif /* __LABEL_H__ */ #endif /* __LABEL_H__ */
This diff is collapsed.
...@@ -56,4 +56,16 @@ int nvdimm_bus_register_dimms(struct nvdimm_bus *nvdimm_bus); ...@@ -56,4 +56,16 @@ int nvdimm_bus_register_dimms(struct nvdimm_bus *nvdimm_bus);
int nvdimm_bus_register_regions(struct nvdimm_bus *nvdimm_bus); int nvdimm_bus_register_regions(struct nvdimm_bus *nvdimm_bus);
int nvdimm_bus_init_interleave_sets(struct nvdimm_bus *nvdimm_bus); int nvdimm_bus_init_interleave_sets(struct nvdimm_bus *nvdimm_bus);
int nd_match_dimm(struct device *dev, void *data); int nd_match_dimm(struct device *dev, void *data);
struct nd_label_id;
char *nd_label_gen_id(struct nd_label_id *label_id, u8 *uuid, u32 flags);
bool nd_is_uuid_unique(struct device *dev, u8 *uuid);
struct nd_region;
struct nvdimm_drvdata;
struct nd_mapping;
resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, resource_size_t *overlap);
resource_size_t nd_region_available_dpa(struct nd_region *nd_region);
resource_size_t nvdimm_allocated_dpa(struct nvdimm_drvdata *ndd,
struct nd_label_id *label_id);
void get_ndd(struct nvdimm_drvdata *ndd);
#endif /* __ND_CORE_H__ */ #endif /* __ND_CORE_H__ */
...@@ -16,6 +16,7 @@ ...@@ -16,6 +16,7 @@
#include <linux/device.h> #include <linux/device.h>
#include <linux/mutex.h> #include <linux/mutex.h>
#include <linux/ndctl.h> #include <linux/ndctl.h>
#include <linux/types.h>
#include "label.h" #include "label.h"
struct nvdimm_drvdata { struct nvdimm_drvdata {
...@@ -25,6 +26,7 @@ struct nvdimm_drvdata { ...@@ -25,6 +26,7 @@ struct nvdimm_drvdata {
void *data; void *data;
int ns_current, ns_next; int ns_current, ns_next;
struct resource dpa; struct resource dpa;
struct kref kref;
}; };
struct nd_region_namespaces { struct nd_region_namespaces {
...@@ -59,12 +61,19 @@ static inline struct nd_namespace_index *to_next_namespace_index( ...@@ -59,12 +61,19 @@ static inline struct nd_namespace_index *to_next_namespace_index(
(unsigned long long) (res ? resource_size(res) : 0), \ (unsigned long long) (res ? resource_size(res) : 0), \
(unsigned long long) (res ? res->start : 0), ##arg) (unsigned long long) (res ? res->start : 0), ##arg)
#define for_each_label(l, label, labels) \
for (l = 0; (label = labels ? labels[l] : NULL); l++)
#define for_each_dpa_resource(ndd, res) \
for (res = (ndd)->dpa.child; res; res = res->sibling)
#define for_each_dpa_resource_safe(ndd, res, next) \ #define for_each_dpa_resource_safe(ndd, res, next) \
for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \ for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \
res; res = next, next = next ? next->sibling : NULL) res; res = next, next = next ? next->sibling : NULL)
struct nd_region { struct nd_region {
struct device dev; struct device dev;
struct device *ns_seed;
u16 ndr_mappings; u16 ndr_mappings;
u64 ndr_size; u64 ndr_size;
u64 ndr_start; u64 ndr_start;
...@@ -88,20 +97,28 @@ enum nd_async_mode { ...@@ -88,20 +97,28 @@ enum nd_async_mode {
ND_ASYNC, ND_ASYNC,
}; };
void wait_nvdimm_bus_probe_idle(struct device *dev);
void nd_device_register(struct device *dev); void nd_device_register(struct device *dev);
void nd_device_unregister(struct device *dev, enum nd_async_mode mode); void nd_device_unregister(struct device *dev, enum nd_async_mode mode);
int nd_uuid_store(struct device *dev, u8 **uuid_out, const char *buf,
size_t len);
int __init nvdimm_init(void); int __init nvdimm_init(void);
int __init nd_region_init(void); int __init nd_region_init(void);
void nvdimm_exit(void); void nvdimm_exit(void);
void nd_region_exit(void); void nd_region_exit(void);
struct nvdimm;
struct nvdimm_drvdata *to_ndd(struct nd_mapping *nd_mapping);
int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd); int nvdimm_init_nsarea(struct nvdimm_drvdata *ndd);
int nvdimm_init_config_data(struct nvdimm_drvdata *ndd); int nvdimm_init_config_data(struct nvdimm_drvdata *ndd);
struct nd_region *to_nd_region(struct device *dev); struct nd_region *to_nd_region(struct device *dev);
int nd_region_to_nstype(struct nd_region *nd_region); int nd_region_to_nstype(struct nd_region *nd_region);
int nd_region_register_namespaces(struct nd_region *nd_region, int *err); int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
u64 nd_region_interleave_set_cookie(struct nd_region *nd_region);
void nvdimm_bus_lock(struct device *dev); void nvdimm_bus_lock(struct device *dev);
void nvdimm_bus_unlock(struct device *dev); void nvdimm_bus_unlock(struct device *dev);
bool is_nvdimm_bus_locked(struct device *dev); bool is_nvdimm_bus_locked(struct device *dev);
void nvdimm_drvdata_release(struct kref *kref);
void put_ndd(struct nvdimm_drvdata *ndd);
int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd); int nd_label_reserve_dpa(struct nvdimm_drvdata *ndd);
void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res); void nvdimm_free_dpa(struct nvdimm_drvdata *ndd, struct resource *res);
struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd, struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
......
...@@ -203,6 +203,23 @@ static int nd_pmem_probe(struct device *dev) ...@@ -203,6 +203,23 @@ static int nd_pmem_probe(struct device *dev)
struct nd_namespace_io *nsio = to_nd_namespace_io(dev); struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
struct pmem_device *pmem; struct pmem_device *pmem;
if (resource_size(&nsio->res) < ND_MIN_NAMESPACE_SIZE) {
resource_size_t size = resource_size(&nsio->res);
dev_dbg(dev, "%s: size: %pa, too small must be at least %#x\n",
__func__, &size, ND_MIN_NAMESPACE_SIZE);
return -ENODEV;
}
if (nd_region_to_nstype(nd_region) == ND_DEVICE_NAMESPACE_PMEM) {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
if (!nspm->uuid) {
dev_dbg(dev, "%s: uuid not set\n", __func__);
return -ENODEV;
}
}
pmem = pmem_alloc(dev, &nsio->res, nd_region->id); pmem = pmem_alloc(dev, &nsio->res, nd_region->id);
if (IS_ERR(pmem)) if (IS_ERR(pmem))
return PTR_ERR(pmem); return PTR_ERR(pmem);
...@@ -222,13 +239,14 @@ static int nd_pmem_remove(struct device *dev) ...@@ -222,13 +239,14 @@ static int nd_pmem_remove(struct device *dev)
MODULE_ALIAS("pmem"); MODULE_ALIAS("pmem");
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO); MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_IO);
MODULE_ALIAS_ND_DEVICE(ND_DEVICE_NAMESPACE_PMEM);
static struct nd_device_driver nd_pmem_driver = { static struct nd_device_driver nd_pmem_driver = {
.probe = nd_pmem_probe, .probe = nd_pmem_probe,
.remove = nd_pmem_remove, .remove = nd_pmem_remove,
.drv = { .drv = {
.name = "nd_pmem", .name = "nd_pmem",
}, },
.type = ND_DRIVER_NAMESPACE_IO, .type = ND_DRIVER_NAMESPACE_IO | ND_DRIVER_NAMESPACE_PMEM,
}; };
static int __init pmem_init(void) static int __init pmem_init(void)
......
...@@ -61,8 +61,11 @@ static int child_unregister(struct device *dev, void *data) ...@@ -61,8 +61,11 @@ static int child_unregister(struct device *dev, void *data)
static int nd_region_remove(struct device *dev) static int nd_region_remove(struct device *dev)
{ {
struct nd_region *nd_region = to_nd_region(dev);
/* flush attribute readers and disable */ /* flush attribute readers and disable */
nvdimm_bus_lock(dev); nvdimm_bus_lock(dev);
nd_region->ns_seed = NULL;
dev_set_drvdata(dev, NULL); dev_set_drvdata(dev, NULL);
nvdimm_bus_unlock(dev); nvdimm_bus_unlock(dev);
......
...@@ -15,6 +15,7 @@ ...@@ -15,6 +15,7 @@
#include <linux/slab.h> #include <linux/slab.h>
#include <linux/sort.h> #include <linux/sort.h>
#include <linux/io.h> #include <linux/io.h>
#include <linux/nd.h>
#include "nd-core.h" #include "nd-core.h"
#include "nd.h" #include "nd.h"
...@@ -99,6 +100,58 @@ int nd_region_to_nstype(struct nd_region *nd_region) ...@@ -99,6 +100,58 @@ int nd_region_to_nstype(struct nd_region *nd_region)
return 0; return 0;
} }
EXPORT_SYMBOL(nd_region_to_nstype);
static int is_uuid_busy(struct device *dev, void *data)
{
struct nd_region *nd_region = to_nd_region(dev->parent);
u8 *uuid = data;
switch (nd_region_to_nstype(nd_region)) {
case ND_DEVICE_NAMESPACE_PMEM: {
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
if (!nspm->uuid)
break;
if (memcmp(uuid, nspm->uuid, NSLABEL_UUID_LEN) == 0)
return -EBUSY;
break;
}
case ND_DEVICE_NAMESPACE_BLK: {
/* TODO: blk namespace support */
break;
}
default:
break;
}
return 0;
}
static int is_namespace_uuid_busy(struct device *dev, void *data)
{
if (is_nd_pmem(dev) || is_nd_blk(dev))
return device_for_each_child(dev, data, is_uuid_busy);
return 0;
}
/**
* nd_is_uuid_unique - verify that no other namespace has @uuid
* @dev: any device on a nvdimm_bus
* @uuid: uuid to check
*/
bool nd_is_uuid_unique(struct device *dev, u8 *uuid)
{
struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(dev);
if (!nvdimm_bus)
return false;
WARN_ON_ONCE(!is_nvdimm_bus_locked(&nvdimm_bus->dev));
if (device_for_each_child(&nvdimm_bus->dev, uuid,
is_namespace_uuid_busy) != 0)
return false;
return true;
}
static ssize_t size_show(struct device *dev, static ssize_t size_show(struct device *dev,
struct device_attribute *attr, char *buf) struct device_attribute *attr, char *buf)
...@@ -151,6 +204,60 @@ static ssize_t set_cookie_show(struct device *dev, ...@@ -151,6 +204,60 @@ static ssize_t set_cookie_show(struct device *dev,
} }
static DEVICE_ATTR_RO(set_cookie); static DEVICE_ATTR_RO(set_cookie);
resource_size_t nd_region_available_dpa(struct nd_region *nd_region)
{
resource_size_t blk_max_overlap = 0, available, overlap;
int i;
WARN_ON(!is_nvdimm_bus_locked(&nd_region->dev));
retry:
available = 0;
overlap = blk_max_overlap;
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
/* if a dimm is disabled the available capacity is zero */
if (!ndd)
return 0;
if (is_nd_pmem(&nd_region->dev)) {
available += nd_pmem_available_dpa(nd_region,
nd_mapping, &overlap);
if (overlap > blk_max_overlap) {
blk_max_overlap = overlap;
goto retry;
}
} else if (is_nd_blk(&nd_region->dev)) {
/* TODO: BLK Namespace support */
}
}
return available;
}
static ssize_t available_size_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
unsigned long long available = 0;
/*
* Flush in-flight updates and grab a snapshot of the available
* size. Of course, this value is potentially invalidated the
* memory nvdimm_bus_lock() is dropped, but that's userspace's
* problem to not race itself.
*/
nvdimm_bus_lock(dev);
wait_nvdimm_bus_probe_idle(dev);
available = nd_region_available_dpa(nd_region);
nvdimm_bus_unlock(dev);
return sprintf(buf, "%llu\n", available);
}
static DEVICE_ATTR_RO(available_size);
static ssize_t init_namespaces_show(struct device *dev, static ssize_t init_namespaces_show(struct device *dev,
struct device_attribute *attr, char *buf) struct device_attribute *attr, char *buf)
{ {
...@@ -168,11 +275,29 @@ static ssize_t init_namespaces_show(struct device *dev, ...@@ -168,11 +275,29 @@ static ssize_t init_namespaces_show(struct device *dev,
} }
static DEVICE_ATTR_RO(init_namespaces); static DEVICE_ATTR_RO(init_namespaces);
static ssize_t namespace_seed_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nd_region *nd_region = to_nd_region(dev);
ssize_t rc;
nvdimm_bus_lock(dev);
if (nd_region->ns_seed)
rc = sprintf(buf, "%s\n", dev_name(nd_region->ns_seed));
else
rc = sprintf(buf, "\n");
nvdimm_bus_unlock(dev);
return rc;
}
static DEVICE_ATTR_RO(namespace_seed);
static struct attribute *nd_region_attributes[] = { static struct attribute *nd_region_attributes[] = {
&dev_attr_size.attr, &dev_attr_size.attr,
&dev_attr_nstype.attr, &dev_attr_nstype.attr,
&dev_attr_mappings.attr, &dev_attr_mappings.attr,
&dev_attr_set_cookie.attr, &dev_attr_set_cookie.attr,
&dev_attr_available_size.attr,
&dev_attr_namespace_seed.attr,
&dev_attr_init_namespaces.attr, &dev_attr_init_namespaces.attr,
NULL, NULL,
}; };
...@@ -182,11 +307,17 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n) ...@@ -182,11 +307,17 @@ static umode_t region_visible(struct kobject *kobj, struct attribute *a, int n)
struct device *dev = container_of(kobj, typeof(*dev), kobj); struct device *dev = container_of(kobj, typeof(*dev), kobj);
struct nd_region *nd_region = to_nd_region(dev); struct nd_region *nd_region = to_nd_region(dev);
struct nd_interleave_set *nd_set = nd_region->nd_set; struct nd_interleave_set *nd_set = nd_region->nd_set;
int type = nd_region_to_nstype(nd_region);
if (a != &dev_attr_set_cookie.attr) if (a != &dev_attr_set_cookie.attr
&& a != &dev_attr_available_size.attr)
return a->mode; return a->mode;
if (is_nd_pmem(dev) && nd_set) if ((type == ND_DEVICE_NAMESPACE_PMEM
|| type == ND_DEVICE_NAMESPACE_BLK)
&& a == &dev_attr_available_size.attr)
return a->mode;
else if (is_nd_pmem(dev) && nd_set)
return a->mode; return a->mode;
return 0; return 0;
...@@ -198,6 +329,15 @@ struct attribute_group nd_region_attribute_group = { ...@@ -198,6 +329,15 @@ struct attribute_group nd_region_attribute_group = {
}; };
EXPORT_SYMBOL_GPL(nd_region_attribute_group); EXPORT_SYMBOL_GPL(nd_region_attribute_group);
u64 nd_region_interleave_set_cookie(struct nd_region *nd_region)
{
struct nd_interleave_set *nd_set = nd_region->nd_set;
if (nd_set)
return nd_set->cookie;
return 0;
}
/* /*
* Upon successful probe/remove, take/release a reference on the * Upon successful probe/remove, take/release a reference on the
* associated interleave set (if present) * associated interleave set (if present)
...@@ -205,17 +345,19 @@ EXPORT_SYMBOL_GPL(nd_region_attribute_group); ...@@ -205,17 +345,19 @@ EXPORT_SYMBOL_GPL(nd_region_attribute_group);
static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus, static void nd_region_notify_driver_action(struct nvdimm_bus *nvdimm_bus,
struct device *dev, bool probe) struct device *dev, bool probe)
{ {
if (is_nd_pmem(dev) || is_nd_blk(dev)) { if (!probe && (is_nd_pmem(dev) || is_nd_blk(dev))) {
struct nd_region *nd_region = to_nd_region(dev); struct nd_region *nd_region = to_nd_region(dev);
int i; int i;
for (i = 0; i < nd_region->ndr_mappings; i++) { for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i]; struct nd_mapping *nd_mapping = &nd_region->mapping[i];
struct nvdimm_drvdata *ndd = nd_mapping->ndd;
struct nvdimm *nvdimm = nd_mapping->nvdimm; struct nvdimm *nvdimm = nd_mapping->nvdimm;
if (probe) kfree(nd_mapping->labels);
atomic_inc(&nvdimm->busy); nd_mapping->labels = NULL;
else put_ndd(ndd);
nd_mapping->ndd = NULL;
atomic_dec(&nvdimm->busy); atomic_dec(&nvdimm->busy);
} }
} }
......
...@@ -41,10 +41,20 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc, ...@@ -41,10 +41,20 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
struct nvdimm *nvdimm, unsigned int cmd, void *buf, struct nvdimm *nvdimm, unsigned int cmd, void *buf,
unsigned int buf_len); unsigned int buf_len);
struct nd_namespace_label;
struct nvdimm_drvdata;
struct nd_mapping { struct nd_mapping {
struct nvdimm *nvdimm; struct nvdimm *nvdimm;
struct nd_namespace_label **labels;
u64 start; u64 start;
u64 size; u64 size;
/*
* @ndd is for private use at region enable / disable time for
* get_ndd() + put_ndd(), all other nd_mapping to ndd
* conversions use to_ndd() which respects enabled state of the
* nvdimm.
*/
struct nvdimm_drvdata *ndd;
}; };
struct nvdimm_bus_descriptor { struct nvdimm_bus_descriptor {
......
...@@ -28,16 +28,40 @@ static inline struct nd_device_driver *to_nd_device_driver( ...@@ -28,16 +28,40 @@ static inline struct nd_device_driver *to_nd_device_driver(
return container_of(drv, struct nd_device_driver, drv); return container_of(drv, struct nd_device_driver, drv);
}; };
/**
* struct nd_namespace_io - infrastructure for loading an nd_pmem instance
* @dev: namespace device created by the nd region driver
* @res: struct resource conversion of a NFIT SPA table
*/
struct nd_namespace_io { struct nd_namespace_io {
struct device dev; struct device dev;
struct resource res; struct resource res;
}; };
/**
* struct nd_namespace_pmem - namespace device for dimm-backed interleaved memory
* @nsio: device and system physical address range to drive
* @alt_name: namespace name supplied in the dimm label
* @uuid: namespace name supplied in the dimm label
*/
struct nd_namespace_pmem {
struct nd_namespace_io nsio;
char *alt_name;
u8 *uuid;
};
static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev) static inline struct nd_namespace_io *to_nd_namespace_io(struct device *dev)
{ {
return container_of(dev, struct nd_namespace_io, dev); return container_of(dev, struct nd_namespace_io, dev);
} }
static inline struct nd_namespace_pmem *to_nd_namespace_pmem(struct device *dev)
{
struct nd_namespace_io *nsio = to_nd_namespace_io(dev);
return container_of(nsio, struct nd_namespace_pmem, nsio);
}
#define MODULE_ALIAS_ND_DEVICE(type) \ #define MODULE_ALIAS_ND_DEVICE(type) \
MODULE_ALIAS("nd:t" __stringify(type) "*") MODULE_ALIAS("nd:t" __stringify(type) "*")
#define ND_DEVICE_MODALIAS_FMT "nd:t%d" #define ND_DEVICE_MODALIAS_FMT "nd:t%d"
......
...@@ -190,4 +190,8 @@ enum nd_driver_flags { ...@@ -190,4 +190,8 @@ enum nd_driver_flags {
ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM, ND_DRIVER_NAMESPACE_PMEM = 1 << ND_DEVICE_NAMESPACE_PMEM,
ND_DRIVER_NAMESPACE_BLK = 1 << ND_DEVICE_NAMESPACE_BLK, ND_DRIVER_NAMESPACE_BLK = 1 << ND_DEVICE_NAMESPACE_BLK,
}; };
enum {
ND_MIN_NAMESPACE_SIZE = 0x00400000,
};
#endif /* __NDCTL_H__ */ #endif /* __NDCTL_H__ */
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment