summaryrefslogtreecommitdiff
path: root/drivers/nvdimm
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/nvdimm')
-rw-r--r--drivers/nvdimm/bus.c2
-rw-r--r--drivers/nvdimm/core.c73
-rw-r--r--drivers/nvdimm/dimm.c11
-rw-r--r--drivers/nvdimm/dimm_devs.c226
-rw-r--r--drivers/nvdimm/label.c192
-rw-r--r--drivers/nvdimm/namespace_devs.c792
-rw-r--r--drivers/nvdimm/nd-core.h24
-rw-r--r--drivers/nvdimm/nd.h29
-rw-r--r--drivers/nvdimm/pmem.c28
-rw-r--r--drivers/nvdimm/region_devs.c58
10 files changed, 1035 insertions, 400 deletions
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 935866fe5ec2..a8b6949a8778 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -217,6 +217,8 @@ long nvdimm_clear_poison(struct device *dev, phys_addr_t phys,
return rc;
if (cmd_rc < 0)
return cmd_rc;
+
+ nvdimm_clear_from_poison_list(nvdimm_bus, phys, len);
return clear_err.cleared;
}
EXPORT_SYMBOL_GPL(nvdimm_clear_poison);
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index 4d7bbd2df5c0..7ceba08774b6 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -547,11 +547,12 @@ void nvdimm_badblocks_populate(struct nd_region *nd_region,
}
EXPORT_SYMBOL_GPL(nvdimm_badblocks_populate);
-static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
+static int add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length,
+ gfp_t flags)
{
struct nd_poison *pl;
- pl = kzalloc(sizeof(*pl), GFP_KERNEL);
+ pl = kzalloc(sizeof(*pl), flags);
if (!pl)
return -ENOMEM;
@@ -567,7 +568,7 @@ static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
struct nd_poison *pl;
if (list_empty(&nvdimm_bus->poison_list))
- return add_poison(nvdimm_bus, addr, length);
+ return add_poison(nvdimm_bus, addr, length, GFP_KERNEL);
/*
* There is a chance this is a duplicate, check for those first.
@@ -587,7 +588,7 @@ static int bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
* as any overlapping ranges will get resolved when the list is consumed
* and converted to badblocks
*/
- return add_poison(nvdimm_bus, addr, length);
+ return add_poison(nvdimm_bus, addr, length, GFP_KERNEL);
}
int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
@@ -602,6 +603,70 @@ int nvdimm_bus_add_poison(struct nvdimm_bus *nvdimm_bus, u64 addr, u64 length)
}
EXPORT_SYMBOL_GPL(nvdimm_bus_add_poison);
+void nvdimm_clear_from_poison_list(struct nvdimm_bus *nvdimm_bus,
+ phys_addr_t start, unsigned int len)
+{
+ struct list_head *poison_list = &nvdimm_bus->poison_list;
+ u64 clr_end = start + len - 1;
+ struct nd_poison *pl, *next;
+
+ nvdimm_bus_lock(&nvdimm_bus->dev);
+ WARN_ON_ONCE(list_empty(poison_list));
+
+ /*
+ * [start, clr_end] is the poison interval being cleared.
+ * [pl->start, pl_end] is the poison_list entry we're comparing
+ * the above interval against. The poison list entry may need
+ * to be modified (update either start or length), deleted, or
+ * split into two based on the overlap characteristics
+ */
+
+ list_for_each_entry_safe(pl, next, poison_list, list) {
+ u64 pl_end = pl->start + pl->length - 1;
+
+ /* Skip intervals with no intersection */
+ if (pl_end < start)
+ continue;
+ if (pl->start > clr_end)
+ continue;
+ /* Delete completely overlapped poison entries */
+ if ((pl->start >= start) && (pl_end <= clr_end)) {
+ list_del(&pl->list);
+ kfree(pl);
+ continue;
+ }
+ /* Adjust start point of partially cleared entries */
+ if ((start <= pl->start) && (clr_end > pl->start)) {
+ pl->length -= clr_end - pl->start + 1;
+ pl->start = clr_end + 1;
+ continue;
+ }
+ /* Adjust pl->length for partial clearing at the tail end */
+ if ((pl->start < start) && (pl_end <= clr_end)) {
+ /* pl->start remains the same */
+ pl->length = start - pl->start;
+ continue;
+ }
+ /*
+ * If clearing in the middle of an entry, we split it into
+ * two by modifying the current entry to represent one half of
+ * the split, and adding a new entry for the second half.
+ */
+ if ((pl->start < start) && (pl_end > clr_end)) {
+ u64 new_start = clr_end + 1;
+ u64 new_len = pl_end - new_start + 1;
+
+ /* Add new entry covering the right half */
+ add_poison(nvdimm_bus, new_start, new_len, GFP_NOIO);
+ /* Adjust this entry to cover the left half */
+ pl->length = start - pl->start;
+ continue;
+ }
+ }
+ nvdimm_bus_unlock(&nvdimm_bus->dev);
+}
+EXPORT_SYMBOL_GPL(nvdimm_clear_from_poison_list);
+
#ifdef CONFIG_BLK_DEV_INTEGRITY
int nd_integrity_init(struct gendisk *disk, unsigned long meta_size)
{
diff --git a/drivers/nvdimm/dimm.c b/drivers/nvdimm/dimm.c
index 71d12bb67339..619834e144d1 100644
--- a/drivers/nvdimm/dimm.c
+++ b/drivers/nvdimm/dimm.c
@@ -26,6 +26,14 @@ static int nvdimm_probe(struct device *dev)
struct nvdimm_drvdata *ndd;
int rc;
+ rc = nvdimm_check_config_data(dev);
+ if (rc) {
+ /* not required for non-aliased nvdimm, ex. NVDIMM-N */
+ if (rc == -ENOTTY)
+ rc = 0;
+ return rc;
+ }
+
ndd = kzalloc(sizeof(*ndd), GFP_KERNEL);
if (!ndd)
return -ENOMEM;
@@ -72,6 +80,9 @@ static int nvdimm_remove(struct device *dev)
{
struct nvdimm_drvdata *ndd = dev_get_drvdata(dev);
+ if (!ndd)
+ return 0;
+
nvdimm_bus_lock(dev);
dev_set_drvdata(dev, NULL);
nvdimm_bus_unlock(dev);
diff --git a/drivers/nvdimm/dimm_devs.c b/drivers/nvdimm/dimm_devs.c
index d9bba5edd8dc..d614493ad5ac 100644
--- a/drivers/nvdimm/dimm_devs.c
+++ b/drivers/nvdimm/dimm_devs.c
@@ -28,28 +28,30 @@ static DEFINE_IDA(dimm_ida);
* Retrieve bus and dimm handle and return if this bus supports
* get_config_data commands
*/
-static int __validate_dimm(struct nvdimm_drvdata *ndd)
+int nvdimm_check_config_data(struct device *dev)
{
- struct nvdimm *nvdimm;
-
- if (!ndd)
- return -EINVAL;
-
- nvdimm = to_nvdimm(ndd->dev);
+ struct nvdimm *nvdimm = to_nvdimm(dev);
- if (!nvdimm->cmd_mask)
- return -ENXIO;
- if (!test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask))
- return -ENXIO;
+ if (!nvdimm->cmd_mask ||
+ !test_bit(ND_CMD_GET_CONFIG_DATA, &nvdimm->cmd_mask)) {
+ if (nvdimm->flags & NDD_ALIASING)
+ return -ENXIO;
+ else
+ return -ENOTTY;
+ }
return 0;
}
static int validate_dimm(struct nvdimm_drvdata *ndd)
{
- int rc = __validate_dimm(ndd);
+ int rc;
- if (rc && ndd)
+ if (!ndd)
+ return -EINVAL;
+
+ rc = nvdimm_check_config_data(ndd->dev);
+ if (rc)
dev_dbg(ndd->dev, "%pf: %s error: %d\n",
__builtin_return_address(0), __func__, rc);
return rc;
@@ -263,6 +265,12 @@ const char *nvdimm_name(struct nvdimm *nvdimm)
}
EXPORT_SYMBOL_GPL(nvdimm_name);
+struct kobject *nvdimm_kobj(struct nvdimm *nvdimm)
+{
+ return &nvdimm->dev.kobj;
+}
+EXPORT_SYMBOL_GPL(nvdimm_kobj);
+
unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm)
{
return nvdimm->cmd_mask;
@@ -378,40 +386,166 @@ struct nvdimm *nvdimm_create(struct nvdimm_bus *nvdimm_bus, void *provider_data,
}
EXPORT_SYMBOL_GPL(nvdimm_create);
+int alias_dpa_busy(struct device *dev, void *data)
+{
+ resource_size_t map_end, blk_start, new, busy;
+ struct blk_alloc_info *info = data;
+ struct nd_mapping *nd_mapping;
+ struct nd_region *nd_region;
+ struct nvdimm_drvdata *ndd;
+ struct resource *res;
+ int i;
+
+ if (!is_nd_pmem(dev))
+ return 0;
+
+ nd_region = to_nd_region(dev);
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ nd_mapping = &nd_region->mapping[i];
+ if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+ break;
+ }
+
+ if (i >= nd_region->ndr_mappings)
+ return 0;
+
+ ndd = to_ndd(nd_mapping);
+ map_end = nd_mapping->start + nd_mapping->size - 1;
+ blk_start = nd_mapping->start;
+
+ /*
+ * In the allocation case ->res is set to free space that we are
+ * looking to validate against PMEM aliasing collision rules
+ * (i.e. BLK is allocated after all aliased PMEM).
+ */
+ if (info->res) {
+ if (info->res->start >= nd_mapping->start
+ && info->res->start < map_end)
+ /* pass */;
+ else
+ return 0;
+ }
+
+ retry:
+ /*
+ * Find the free dpa from the end of the last pmem allocation to
+ * the end of the interleave-set mapping that is not already
+ * covered by a blk allocation.
+ */
+ busy = 0;
+ for_each_dpa_resource(ndd, res) {
+ if ((res->start >= blk_start && res->start < map_end)
+ || (res->end >= blk_start
+ && res->end <= map_end)) {
+ if (strncmp(res->name, "pmem", 4) == 0) {
+ new = max(blk_start, min(map_end + 1,
+ res->end + 1));
+ if (new != blk_start) {
+ blk_start = new;
+ goto retry;
+ }
+ } else
+ busy += min(map_end, res->end)
+ - max(nd_mapping->start, res->start) + 1;
+ } else if (nd_mapping->start > res->start
+ && map_end < res->end) {
+ /* total eclipse of the PMEM region mapping */
+ busy += nd_mapping->size;
+ break;
+ }
+ }
+
+ /* update the free space range with the probed blk_start */
+ if (info->res && blk_start > info->res->start) {
+ info->res->start = max(info->res->start, blk_start);
+ if (info->res->start > info->res->end)
+ info->res->end = info->res->start - 1;
+ return 1;
+ }
+
+ info->available -= blk_start - nd_mapping->start + busy;
+
+ return 0;
+}
+
+static int blk_dpa_busy(struct device *dev, void *data)
+{
+ struct blk_alloc_info *info = data;
+ struct nd_mapping *nd_mapping;
+ struct nd_region *nd_region;
+ resource_size_t map_end;
+ int i;
+
+ if (!is_nd_pmem(dev))
+ return 0;
+
+ nd_region = to_nd_region(dev);
+ for (i = 0; i < nd_region->ndr_mappings; i++) {
+ nd_mapping = &nd_region->mapping[i];
+ if (nd_mapping->nvdimm == info->nd_mapping->nvdimm)
+ break;
+ }
+
+ if (i >= nd_region->ndr_mappings)
+ return 0;
+
+ map_end = nd_mapping->start + nd_mapping->size - 1;
+ if (info->res->start >= nd_mapping->start
+ && info->res->start < map_end) {
+ if (info->res->end <= map_end) {
+ info->busy = 0;
+ return 1;
+ } else {
+ info->busy -= info->res->end - map_end;
+ return 0;
+ }
+ } else if (info->res->end >= nd_mapping->start
+ && info->res->end <= map_end) {
+ info->busy -= nd_mapping->start - info->res->start;
+ return 0;
+ } else {
+ info->busy -= nd_mapping->size;
+ return 0;
+ }
+}
+
/**
* nd_blk_available_dpa - account the unused dpa of BLK region
* @nd_mapping: container of dpa-resource-root + labels
*
- * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges.
+ * Unlike PMEM, BLK namespaces can occupy discontiguous DPA ranges, but
+ * we arrange for them to never start at an lower dpa than the last
+ * PMEM allocation in an aliased region.
*/
-resource_size_t nd_blk_available_dpa(struct nd_mapping *nd_mapping)
+resource_size_t nd_blk_available_dpa(struct nd_region *nd_region)
{
+ struct nvdimm_bus *nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+ struct nd_mapping *nd_mapping = &nd_region->mapping[0];
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
- resource_size_t map_end, busy = 0, available;
+ struct blk_alloc_info info = {
+ .nd_mapping = nd_mapping,
+ .available = nd_mapping->size,
+ .res = NULL,
+ };
struct resource *res;
if (!ndd)
return 0;
- map_end = nd_mapping->start + nd_mapping->size - 1;
- for_each_dpa_resource(ndd, res)
- if (res->start >= nd_mapping->start && res->start < map_end) {
- resource_size_t end = min(map_end, res->end);
+ device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
- busy += end - res->start + 1;
- } else if (res->end >= nd_mapping->start
- && res->end <= map_end) {
- busy += res->end - nd_mapping->start;
- } else if (nd_mapping->start > res->start
- && nd_mapping->start < res->end) {
- /* total eclipse of the BLK region mapping */
- busy += nd_mapping->size;
- }
+ /* now account for busy blk allocations in unaliased dpa */
+ for_each_dpa_resource(ndd, res) {
+ if (strncmp(res->name, "blk", 3) != 0)
+ continue;
- available = map_end - nd_mapping->start + 1;
- if (busy < available)
- return available - busy;
- return 0;
+ info.res = res;
+ info.busy = resource_size(res);
+ device_for_each_child(&nvdimm_bus->dev, &info, blk_dpa_busy);
+ info.available -= info.busy;
+ }
+
+ return info.available;
}
/**
@@ -443,21 +577,16 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
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)
+ 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) {
+ blk_start = min(blk_start,
+ max(map_start, res->start));
+ else if (res->end > map_end) {
reason = "misaligned to iset";
goto err;
- } else {
- if (busy) {
- reason = "duplicate overlapping PMEM reservations?";
- goto err;
- }
+ } else
busy += resource_size(res);
- continue;
- }
} else if (res->end >= map_start && res->end <= map_end) {
if (strncmp(res->name, "blk", 3) == 0) {
/*
@@ -466,15 +595,14 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
* be used for BLK.
*/
blk_start = map_start;
- } else {
- reason = "misaligned to iset";
- goto err;
- }
+ } else
+ busy += resource_size(res);
} 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;
@@ -483,10 +611,6 @@ resource_size_t nd_pmem_available_dpa(struct nd_region *nd_region,
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;
}
diff --git a/drivers/nvdimm/label.c b/drivers/nvdimm/label.c
index 96526dcfdd37..fac7cabe8f56 100644
--- a/drivers/nvdimm/label.c
+++ b/drivers/nvdimm/label.c
@@ -494,11 +494,13 @@ 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;
+ u64 cookie = nd_region_interleave_set_cookie(nd_region);
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
- struct nd_namespace_label *victim_label;
+ struct nd_label_ent *label_ent, *victim = NULL;
struct nd_namespace_label *nd_label;
struct nd_namespace_index *nsindex;
+ struct nd_label_id label_id;
+ struct resource *res;
unsigned long *free;
u32 nslot, slot;
size_t offset;
@@ -507,6 +509,16 @@ static int __pmem_label_update(struct nd_region *nd_region,
if (!preamble_next(ndd, &nsindex, &free, &nslot))
return -ENXIO;
+ nd_label_gen_id(&label_id, nspm->uuid, 0);
+ for_each_dpa_resource(ndd, res)
+ if (strcmp(res->name, label_id.id) == 0)
+ break;
+
+ if (!res) {
+ WARN_ON_ONCE(1);
+ return -ENXIO;
+ }
+
/* allocate and write the label to the staging (next) index */
slot = nd_label_alloc_slot(ndd);
if (slot == UINT_MAX)
@@ -522,11 +534,10 @@ static int __pmem_label_update(struct nd_region *nd_region,
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->rawsize = __cpu_to_le64(resource_size(res));
+ nd_label->dpa = __cpu_to_le64(res->start);
nd_label->slot = __cpu_to_le32(slot);
+ nd_dbg_dpa(nd_region, ndd, res, "%s\n", __func__);
/* update label */
offset = nd_label_offset(ndd, nd_label);
@@ -536,38 +547,43 @@ static int __pmem_label_update(struct nd_region *nd_region,
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);
+ mutex_lock(&nd_mapping->lock);
+ list_for_each_entry(label_ent, &nd_mapping->labels, list) {
+ if (!label_ent->label)
+ continue;
+ if (memcmp(nspm->uuid, label_ent->label->uuid,
+ NSLABEL_UUID_LEN) != 0)
+ continue;
+ victim = label_ent;
+ list_move_tail(&victim->list, &nd_mapping->labels);
+ break;
+ }
+ if (victim) {
dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
+ slot = to_slot(ndd, victim->label);
+ nd_label_free_slot(ndd, slot);
+ victim->label = NULL;
}
/* 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 void del_label(struct nd_mapping *nd_mapping, int l)
-{
- struct nd_namespace_label *next_label, *nd_label;
- struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
- unsigned int slot;
- int j;
-
- nd_label = nd_mapping->labels[l];
- slot = to_slot(ndd, nd_label);
- dev_vdbg(ndd->dev, "%s: clear: %d\n", __func__, slot);
+ if (rc == 0) {
+ list_for_each_entry(label_ent, &nd_mapping->labels, list)
+ if (!label_ent->label) {
+ label_ent->label = nd_label;
+ nd_label = NULL;
+ break;
+ }
+ dev_WARN_ONCE(&nspm->nsio.common.dev, nd_label,
+ "failed to track label: %d\n",
+ to_slot(ndd, nd_label));
+ if (nd_label)
+ rc = -ENXIO;
+ }
+ mutex_unlock(&nd_mapping->lock);
- for (j = l; (next_label = nd_mapping->labels[j + 1]); j++)
- nd_mapping->labels[j] = next_label;
- nd_mapping->labels[j] = NULL;
+ return rc;
}
static bool is_old_resource(struct resource *res, struct resource **list, int n)
@@ -607,14 +623,16 @@ static int __blk_label_update(struct nd_region *nd_region,
struct nd_mapping *nd_mapping, struct nd_namespace_blk *nsblk,
int num_labels)
{
- int i, l, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
+ int i, alloc, victims, nfree, old_num_resources, nlabel, rc = -ENXIO;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
struct nd_namespace_label *nd_label;
+ struct nd_label_ent *label_ent, *e;
struct nd_namespace_index *nsindex;
unsigned long *free, *victim_map = NULL;
struct resource *res, **old_res_list;
struct nd_label_id label_id;
u8 uuid[NSLABEL_UUID_LEN];
+ LIST_HEAD(list);
u32 nslot, slot;
if (!preamble_next(ndd, &nsindex, &free, &nslot))
@@ -736,15 +754,22 @@ static int __blk_label_update(struct nd_region *nd_region,
* entries in nd_mapping->labels
*/
nlabel = 0;
- for_each_label(l, nd_label, nd_mapping->labels) {
+ mutex_lock(&nd_mapping->lock);
+ list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+ nd_label = label_ent->label;
+ if (!nd_label)
+ continue;
nlabel++;
memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
if (memcmp(uuid, nsblk->uuid, NSLABEL_UUID_LEN) != 0)
continue;
nlabel--;
- del_label(nd_mapping, l);
- l--; /* retry with the new label at this index */
+ list_move(&label_ent->list, &list);
+ label_ent->label = NULL;
}
+ list_splice_tail_init(&list, &nd_mapping->labels);
+ mutex_unlock(&nd_mapping->lock);
+
if (nlabel + nsblk->num_resources > num_labels) {
/*
* Bug, we can't end up with more resources than
@@ -755,6 +780,15 @@ static int __blk_label_update(struct nd_region *nd_region,
goto out;
}
+ mutex_lock(&nd_mapping->lock);
+ label_ent = list_first_entry_or_null(&nd_mapping->labels,
+ typeof(*label_ent), list);
+ if (!label_ent) {
+ WARN_ON(1);
+ mutex_unlock(&nd_mapping->lock);
+ rc = -ENXIO;
+ goto out;
+ }
for_each_clear_bit_le(slot, free, nslot) {
nd_label = nd_label_base(ndd) + slot;
memcpy(uuid, nd_label->uuid, NSLABEL_UUID_LEN);
@@ -762,11 +796,19 @@ static int __blk_label_update(struct nd_region *nd_region,
continue;
res = to_resource(ndd, nd_label);
res->flags &= ~DPA_RESOURCE_ADJUSTED;
- dev_vdbg(&nsblk->common.dev, "assign label[%d] slot: %d\n",
- l, slot);
- nd_mapping->labels[l++] = nd_label;
+ dev_vdbg(&nsblk->common.dev, "assign label slot: %d\n", slot);
+ list_for_each_entry_from(label_ent, &nd_mapping->labels, list) {
+ if (label_ent->label)
+ continue;
+ label_ent->label = nd_label;
+ nd_label = NULL;
+ break;
+ }
+ if (nd_label)
+ dev_WARN(&nsblk->common.dev,
+ "failed to track label slot%d\n", slot);
}
- nd_mapping->labels[l] = NULL;
+ mutex_unlock(&nd_mapping->lock);
out:
kfree(old_res_list);
@@ -788,32 +830,28 @@ static int __blk_label_update(struct nd_region *nd_region,
static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
{
- int i, l, old_num_labels = 0;
+ int i, old_num_labels = 0;
+ struct nd_label_ent *label_ent;
struct nd_namespace_index *nsindex;
- struct nd_namespace_label *nd_label;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
- size_t size = (num_labels + 1) * sizeof(struct nd_namespace_label *);
- for_each_label(l, nd_label, nd_mapping->labels)
+ mutex_lock(&nd_mapping->lock);
+ list_for_each_entry(label_ent, &nd_mapping->labels, list)
old_num_labels++;
+ mutex_unlock(&nd_mapping->lock);
/*
* We need to preserve all the old labels for the mapping so
* they can be garbage collected after writing the new labels.
*/
- if (num_labels > old_num_labels) {
- struct nd_namespace_label **labels;
-
- labels = krealloc(nd_mapping->labels, size, GFP_KERNEL);
- if (!labels)
+ for (i = old_num_labels; i < num_labels; i++) {
+ label_ent = kzalloc(sizeof(*label_ent), GFP_KERNEL);
+ if (!label_ent)
return -ENOMEM;
- nd_mapping->labels = labels;
+ mutex_lock(&nd_mapping->lock);
+ list_add_tail(&label_ent->list, &nd_mapping->labels);
+ mutex_unlock(&nd_mapping->lock);
}
- if (!nd_mapping->labels)
- return -ENOMEM;
-
- for (i = old_num_labels; i <= num_labels; i++)
- nd_mapping->labels[i] = NULL;
if (ndd->ns_current == -1 || ndd->ns_next == -1)
/* pass */;
@@ -837,42 +875,45 @@ static int init_labels(struct nd_mapping *nd_mapping, int num_labels)
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_label_ent *label_ent, *e;
struct nd_namespace_index *nsindex;
u8 label_uuid[NSLABEL_UUID_LEN];
- int l, num_freed = 0;
unsigned long *free;
+ LIST_HEAD(list);
u32 nslot, slot;
+ int active = 0;
if (!uuid)
return 0;
/* no index || no labels == nothing to delete */
- if (!preamble_next(ndd, &nsindex, &free, &nslot)
- || !nd_mapping->labels)
+ if (!preamble_next(ndd, &nsindex, &free, &nslot))
return 0;
- for_each_label(l, nd_label, nd_mapping->labels) {
+ mutex_lock(&nd_mapping->lock);
+ list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+ struct nd_namespace_label *nd_label = label_ent->label;
+
+ if (!nd_label)
+ continue;
+ active++;
memcpy(label_uuid, nd_label->uuid, NSLABEL_UUID_LEN);
if (memcmp(label_uuid, uuid, NSLABEL_UUID_LEN) != 0)
continue;
+ active--;
slot = to_slot(ndd, nd_label);
nd_label_free_slot(ndd, slot);
dev_dbg(ndd->dev, "%s: free: %d\n", __func__, slot);
- del_label(nd_mapping, l);
- num_freed++;
- l--; /* retry with new label at this index */
+ list_move_tail(&label_ent->list, &list);
+ label_ent->label = NULL;
}
+ list_splice_tail_init(&list, &nd_mapping->labels);
- 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__);
+ if (active == 0) {
+ nd_mapping_free_labels(nd_mapping);
+ dev_dbg(ndd->dev, "%s: no more active labels\n", __func__);
}
+ mutex_unlock(&nd_mapping->lock);
return nd_label_write_index(ndd, ndd->ns_next,
nd_inc_seq(__le32_to_cpu(nsindex->seq)), 0);
@@ -885,7 +926,9 @@ int nd_pmem_namespace_label_update(struct nd_region *nd_region,
for (i = 0; i < nd_region->ndr_mappings; i++) {
struct nd_mapping *nd_mapping = &nd_region->mapping[i];
- int rc;
+ struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+ struct resource *res;
+ int rc, count = 0;
if (size == 0) {
rc = del_labels(nd_mapping, nspm->uuid);
@@ -894,7 +937,12 @@ int nd_pmem_namespace_label_update(struct nd_region *nd_region,
continue;
}
- rc = init_labels(nd_mapping, 1);
+ for_each_dpa_resource(ndd, res)
+ if (strncmp(res->name, "pmem", 3) == 0)
+ count++;
+ WARN_ON_ONCE(!count);
+
+ rc = init_labels(nd_mapping, count);
if (rc < 0)
return rc;
diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
index c5e3196c45b0..3509cff68ef9 100644
--- a/drivers/nvdimm/namespace_devs.c
+++ b/drivers/nvdimm/namespace_devs.c
@@ -12,8 +12,10 @@
*/
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/sort.h>
#include <linux/slab.h>
#include <linux/pmem.h>
+#include <linux/list.h>
#include <linux/nd.h>
#include "nd-core.h"
#include "nd.h"
@@ -28,7 +30,10 @@ static void namespace_io_release(struct device *dev)
static void namespace_pmem_release(struct device *dev)
{
struct nd_namespace_pmem *nspm = to_nd_namespace_pmem(dev);
+ struct nd_region *nd_region = to_nd_region(dev->parent);
+ if (nspm->id >= 0)
+ ida_simple_remove(&nd_region->ns_ida, nspm->id);
kfree(nspm->alt_name);
kfree(nspm->uuid);
kfree(nspm);
@@ -62,17 +67,17 @@ static struct device_type namespace_blk_device_type = {
.release = namespace_blk_release,
};
-static bool is_namespace_pmem(struct device *dev)
+static bool is_namespace_pmem(const struct device *dev)
{
return dev ? dev->type == &namespace_pmem_device_type : false;
}
-static bool is_namespace_blk(struct device *dev)
+static bool is_namespace_blk(const struct device *dev)
{
return dev ? dev->type == &namespace_blk_device_type : false;
}
-static bool is_namespace_io(struct device *dev)
+static bool is_namespace_io(const struct device *dev)
{
return dev ? dev->type == &namespace_io_device_type : false;
}
@@ -168,7 +173,21 @@ const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
suffix = "s";
if (is_namespace_pmem(&ndns->dev) || is_namespace_io(&ndns->dev)) {
- sprintf(name, "pmem%d%s", nd_region->id, suffix ? suffix : "");
+ int nsidx = 0;
+
+ if (is_namespace_pmem(&ndns->dev)) {
+ struct nd_namespace_pmem *nspm;
+
+ nspm = to_nd_namespace_pmem(&ndns->dev);
+ nsidx = nspm->id;
+ }
+
+ if (nsidx)
+ sprintf(name, "pmem%d.%d%s", nd_region->id, nsidx,
+ suffix ? suffix : "");
+ else
+ sprintf(name, "pmem%d%s", nd_region->id,
+ suffix ? suffix : "");
} else if (is_namespace_blk(&ndns->dev)) {
struct nd_namespace_blk *nsblk;
@@ -294,7 +313,7 @@ static bool __nd_namespace_blk_validate(struct nd_namespace_blk *nsblk)
if (strcmp(res->name, label_id.id) != 0)
continue;
/*
- * Resources with unacknoweldged adjustments indicate a
+ * Resources with unacknowledged adjustments indicate a
* failure to update labels
*/
if (res->flags & DPA_RESOURCE_ADJUSTED)
@@ -510,19 +529,68 @@ static resource_size_t init_dpa_allocation(struct nd_label_id *label_id,
return rc ? n : 0;
}
-static bool space_valid(bool is_pmem, bool is_reserve,
- struct nd_label_id *label_id, struct resource *res)
+
+/**
+ * space_valid() - validate free dpa space against constraints
+ * @nd_region: hosting region of the free space
+ * @ndd: dimm device data for debug
+ * @label_id: namespace id to allocate space
+ * @prev: potential allocation that precedes free space
+ * @next: allocation that follows the given free space range
+ * @exist: first allocation with same id in the mapping
+ * @n: range that must satisfied for pmem allocations
+ * @valid: free space range to validate
+ *
+ * BLK-space is valid as long as it does not precede a PMEM
+ * allocation in a given region. PMEM-space must be contiguous
+ * and adjacent to an existing existing allocation (if one
+ * exists). If reserving PMEM any space is valid.
+ */
+static void space_valid(struct nd_region *nd_region, struct nvdimm_drvdata *ndd,
+ struct nd_label_id *label_id, struct resource *prev,
+ struct resource *next, struct resource *exist,
+ resource_size_t n, struct resource *valid)
{
- /*
- * For BLK-space any space is valid, for PMEM-space, it must be
- * contiguous with an existing allocation unless we are
- * reserving pmem.
- */
- if (is_reserve || !is_pmem)
- return true;
- if (!res || strcmp(res->name, label_id->id) == 0)
- return true;
- return false;
+ bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
+ bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
+
+ if (valid->start >= valid->end)
+ goto invalid;
+
+ if (is_reserve)
+ return;
+
+ if (!is_pmem) {
+ struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+ struct nvdimm_bus *nvdimm_bus;
+ struct blk_alloc_info info = {
+ .nd_mapping = nd_mapping,
+ .available = nd_mapping->size,
+ .res = valid,
+ };
+
+ WARN_ON(!is_nd_blk(&nd_region->dev));
+ nvdimm_bus = walk_to_nvdimm_bus(&nd_region->dev);
+ device_for_each_child(&nvdimm_bus->dev, &info, alias_dpa_busy);
+ return;
+ }
+
+ /* allocation needs to be contiguous, so this is all or nothing */
+ if (resource_size(valid) < n)
+ goto invalid;
+
+ /* we've got all the space we need and no existing allocation */
+ if (!exist)
+ return;
+
+ /* allocation needs to be contiguous with the existing namespace */
+ if (valid->start == exist->end + 1
+ || valid->end == exist->start - 1)
+ return;
+
+ invalid:
+ /* truncate @valid size to 0 */
+ valid->end = valid->start - 1;
}
enum alloc_loc {
@@ -534,18 +602,24 @@ static resource_size_t scan_allocate(struct nd_region *nd_region,
resource_size_t n)
{
resource_size_t mapping_end = nd_mapping->start + nd_mapping->size - 1;
- bool is_reserve = strcmp(label_id->id, "pmem-reserve") == 0;
bool is_pmem = strncmp(label_id->id, "pmem", 4) == 0;
struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+ struct resource *res, *exist = NULL, valid;
const resource_size_t to_allocate = n;
- struct resource *res;
int first;
+ for_each_dpa_resource(ndd, res)
+ if (strcmp(label_id->id, res->name) == 0)
+ exist = res;
+
+ valid.start = nd_mapping->start;
+ valid.end = mapping_end;
+ valid.name = "free space";
retry:
first = 0;
for_each_dpa_resource(ndd, res) {
- resource_size_t allocate, available = 0, free_start, free_end;
struct resource *next = res->sibling, *new_res = NULL;
+ resource_size_t allocate, available = 0;
enum alloc_loc loc = ALLOC_ERR;
const char *action;
int rc = 0;
@@ -558,32 +632,35 @@ static resource_size_t scan_allocate(struct nd_region *nd_region,
/* space at the beginning of the mapping */
if (!first++ && res->start > nd_mapping->start) {
- free_start = nd_mapping->start;
- available = res->start - free_start;
- if (space_v