nd_btt: atomic sector updates
BTT stands for Block Translation Table, and is a way to provide power
fail sector atomicity semantics for block devices that have the ability
to perform byte granularity IO. It relies on the capability of libnvdimm
namespace devices to do byte aligned IO.
The BTT works as a stacked blocked device, and reserves a chunk of space
from the backing device for its accounting metadata. It is a bio-based
driver because all IO is done synchronously, and there is no queuing or
asynchronous completions at either the device or the driver level.
The BTT uses 'lanes' to index into various 'on-disk' data structures,
and lanes also act as a synchronization mechanism in case there are more
CPUs than available lanes. We did a comparison between two lane lock
strategies - first where we kept an atomic counter around that tracked
which was the last lane that was used, and 'our' lane was determined by
atomically incrementing that. That way, for the nr_cpus > nr_lanes case,
theoretically, no CPU would be blocked waiting for a lane. The other
strategy was to use the cpu number we're scheduled on to and hash it to
a lane number. Theoretically, this could block an IO that could've
otherwise run using a different, free lane. But some fio workloads
showed that the direct cpu -> lane hash performed faster than tracking
'last lane' - my reasoning is the cache thrash caused by moving the
atomic variable made that approach slower than simply waiting out the
in-progress IO. This supports the conclusion that the driver can be a
very simple bio-based one that does synchronous IOs instead of queuing.
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jens Axboe <axboe@fb.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Neil Brown <neilb@suse.de>
Cc: Jeff Moyer <jmoyer@redhat.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
[jmoyer: fix nmi watchdog timeout in btt_map_init]
[jmoyer: move btt initialization to module load path]
[jmoyer: fix memory leak in the btt initialization path]
[jmoyer: Don't overwrite corrupted arenas]
Signed-off-by: Vishal Verma <vishal.l.verma@linux.intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index 4fd9238..fe8ec21 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -32,6 +32,7 @@
put_device(&nvdimm->dev);
}
+ free_percpu(nd_region->lane);
ida_simple_remove(®ion_ida, nd_region->id);
kfree(nd_region);
}
@@ -531,13 +532,66 @@
}
EXPORT_SYMBOL_GPL(nd_region_provider_data);
+/**
+ * nd_region_acquire_lane - allocate and lock a lane
+ * @nd_region: region id and number of lanes possible
+ *
+ * A lane correlates to a BLK-data-window and/or a log slot in the BTT.
+ * We optimize for the common case where there are 256 lanes, one
+ * per-cpu. For larger systems we need to lock to share lanes. For now
+ * this implementation assumes the cost of maintaining an allocator for
+ * free lanes is on the order of the lock hold time, so it implements a
+ * static lane = cpu % num_lanes mapping.
+ *
+ * In the case of a BTT instance on top of a BLK namespace a lane may be
+ * acquired recursively. We lock on the first instance.
+ *
+ * In the case of a BTT instance on top of PMEM, we only acquire a lane
+ * for the BTT metadata updates.
+ */
+unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
+{
+ unsigned int cpu, lane;
+
+ cpu = get_cpu();
+ if (nd_region->num_lanes < nr_cpu_ids) {
+ struct nd_percpu_lane *ndl_lock, *ndl_count;
+
+ lane = cpu % nd_region->num_lanes;
+ ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+ ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+ if (ndl_count->count++ == 0)
+ spin_lock(&ndl_lock->lock);
+ } else
+ lane = cpu;
+
+ return lane;
+}
+EXPORT_SYMBOL(nd_region_acquire_lane);
+
+void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane)
+{
+ if (nd_region->num_lanes < nr_cpu_ids) {
+ unsigned int cpu = get_cpu();
+ struct nd_percpu_lane *ndl_lock, *ndl_count;
+
+ ndl_count = per_cpu_ptr(nd_region->lane, cpu);
+ ndl_lock = per_cpu_ptr(nd_region->lane, lane);
+ if (--ndl_count->count == 0)
+ spin_unlock(&ndl_lock->lock);
+ put_cpu();
+ }
+ put_cpu();
+}
+EXPORT_SYMBOL(nd_region_release_lane);
+
static struct nd_region *nd_region_create(struct nvdimm_bus *nvdimm_bus,
struct nd_region_desc *ndr_desc, struct device_type *dev_type,
const char *caller)
{
struct nd_region *nd_region;
struct device *dev;
- u16 i;
+ unsigned int i;
for (i = 0; i < ndr_desc->num_mappings; i++) {
struct nd_mapping *nd_mapping = &ndr_desc->nd_mapping[i];
@@ -557,9 +611,19 @@
if (!nd_region)
return NULL;
nd_region->id = ida_simple_get(®ion_ida, 0, 0, GFP_KERNEL);
- if (nd_region->id < 0) {
- kfree(nd_region);
- return NULL;
+ if (nd_region->id < 0)
+ goto err_id;
+
+ nd_region->lane = alloc_percpu(struct nd_percpu_lane);
+ if (!nd_region->lane)
+ goto err_percpu;
+
+ for (i = 0; i < nr_cpu_ids; i++) {
+ struct nd_percpu_lane *ndl;
+
+ ndl = per_cpu_ptr(nd_region->lane, i);
+ spin_lock_init(&ndl->lock);
+ ndl->count = 0;
}
memcpy(nd_region->mapping, ndr_desc->nd_mapping,
@@ -573,6 +637,7 @@
nd_region->ndr_mappings = ndr_desc->num_mappings;
nd_region->provider_data = ndr_desc->provider_data;
nd_region->nd_set = ndr_desc->nd_set;
+ nd_region->num_lanes = ndr_desc->num_lanes;
ida_init(&nd_region->ns_ida);
ida_init(&nd_region->btt_ida);
dev = &nd_region->dev;
@@ -585,11 +650,18 @@
nd_device_register(dev);
return nd_region;
+
+ err_percpu:
+ ida_simple_remove(®ion_ida, nd_region->id);
+ err_id:
+ kfree(nd_region);
+ return NULL;
}
struct nd_region *nvdimm_pmem_region_create(struct nvdimm_bus *nvdimm_bus,
struct nd_region_desc *ndr_desc)
{
+ ndr_desc->num_lanes = ND_MAX_LANES;
return nd_region_create(nvdimm_bus, ndr_desc, &nd_pmem_device_type,
__func__);
}
@@ -600,6 +672,7 @@
{
if (ndr_desc->num_mappings > 1)
return NULL;
+ ndr_desc->num_lanes = min(ndr_desc->num_lanes, ND_MAX_LANES);
return nd_region_create(nvdimm_bus, ndr_desc, &nd_blk_device_type,
__func__);
}
@@ -608,6 +681,7 @@
struct nd_region *nvdimm_volatile_region_create(struct nvdimm_bus *nvdimm_bus,
struct nd_region_desc *ndr_desc)
{
+ ndr_desc->num_lanes = ND_MAX_LANES;
return nd_region_create(nvdimm_bus, ndr_desc, &nd_volatile_device_type,
__func__);
}