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>

1 files changed, 21 insertions, 1 deletions

diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index d13eccbb67e9..1b937c235913 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -20,6 +20,12 @@
 #include "label.h"
 
 enum {
+	/*
+	 * Limits the maximum number of block apertures a dimm can
+	 * support and is an input to the geometry/on-disk-format of a
+	 * BTT instance
+	 */
+	ND_MAX_LANES = 256,
 	SECTOR_SHIFT = 9,
 };
 
@@ -75,6 +81,11 @@ static inline struct nd_namespace_index *to_next_namespace_index(
 	for (res = (ndd)->dpa.child, next = res ? res->sibling : NULL; \
 			res; res = next, next = next ? next->sibling : NULL)
 
+struct nd_percpu_lane {
+	int count;
+	spinlock_t lock;
+};
+
 struct nd_region {
 	struct device dev;
 	struct ida ns_ida;
@@ -84,9 +95,10 @@ struct nd_region {
 	u16 ndr_mappings;
 	u64 ndr_size;
 	u64 ndr_start;
-	int id;
+	int id, num_lanes;
 	void *provider_data;
 	struct nd_interleave_set *nd_set;
+	struct nd_percpu_lane __percpu *lane;
 	struct nd_mapping mapping[0];
 };
 
@@ -100,9 +112,11 @@ static inline unsigned nd_inc_seq(unsigned seq)
 	return next[seq & 3];
 }
 
+struct btt;
 struct nd_btt {
 	struct device dev;
 	struct nd_namespace_common *ndns;
+	struct btt *btt;
 	unsigned long lbasize;
 	u8 *uuid;
 	int id;
@@ -157,6 +171,8 @@ static inline struct device *nd_btt_create(struct nd_region *nd_region)
 
 #endif
 struct nd_region *to_nd_region(struct device *dev);
+unsigned int nd_region_acquire_lane(struct nd_region *nd_region);
+void nd_region_release_lane(struct nd_region *nd_region, unsigned int lane);
 int nd_region_to_nstype(struct nd_region *nd_region);
 int nd_region_register_namespaces(struct nd_region *nd_region, int *err);
 u64 nd_region_interleave_set_cookie(struct nd_region *nd_region);
@@ -172,4 +188,8 @@ struct resource *nvdimm_allocate_dpa(struct nvdimm_drvdata *ndd,
 		resource_size_t n);
 resource_size_t nvdimm_namespace_capacity(struct nd_namespace_common *ndns);
 struct nd_namespace_common *nvdimm_namespace_common_probe(struct device *dev);
+int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns);
+int nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns);
+const char *nvdimm_namespace_disk_name(struct nd_namespace_common *ndns,
+		char *name);
 #endif /* __ND_H__ */