summaryrefslogtreecommitdiff
path: root/drivers/nvdimm/pmem.c
diff options
context:
space:
mode:
authorVishal Verma <vishal.l.verma@intel.com>2015-06-25 04:20:32 -0400
committerDan Williams <dan.j.williams@intel.com>2015-06-26 11:23:38 -0400
commit5212e11fde4d40fa627668b4f2222d20db488f71 (patch)
tree153bae097b056dfc44f1781c69e24a8d1e71584a /drivers/nvdimm/pmem.c
parent8c2f7e8658df1d3b7cbfa62706941d14c715823a (diff)
downloadlwn-5212e11fde4d40fa627668b4f2222d20db488f71.tar.gz
lwn-5212e11fde4d40fa627668b4f2222d20db488f71.zip
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>
Diffstat (limited to 'drivers/nvdimm/pmem.c')
-rw-r--r--drivers/nvdimm/pmem.c14
1 files changed, 1 insertions, 13 deletions
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index d0c6b4bdba69..7346054bccbb 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -160,7 +160,6 @@ static void pmem_detach_disk(struct pmem_device *pmem)
static int pmem_attach_disk(struct nd_namespace_common *ndns,
struct pmem_device *pmem)
{
- struct nd_region *nd_region = to_nd_region(ndns->dev.parent);
struct gendisk *disk;
pmem->pmem_queue = blk_alloc_queue(GFP_KERNEL);
@@ -183,7 +182,7 @@ static int pmem_attach_disk(struct nd_namespace_common *ndns,
disk->private_data = pmem;
disk->queue = pmem->pmem_queue;
disk->flags = GENHD_FL_EXT_DEVT;
- sprintf(disk->disk_name, "pmem%d", nd_region->id);
+ nvdimm_namespace_disk_name(ndns, disk->disk_name);
disk->driverfs_dev = &ndns->dev;
set_capacity(disk, pmem->size >> 9);
pmem->pmem_disk = disk;
@@ -211,17 +210,6 @@ static int pmem_rw_bytes(struct nd_namespace_common *ndns,
return 0;
}
-static int nvdimm_namespace_attach_btt(struct nd_namespace_common *ndns)
-{
- /* TODO */
- return -ENXIO;
-}
-
-static void nvdimm_namespace_detach_btt(struct nd_namespace_common *ndns)
-{
- /* TODO */
-}
-
static void pmem_free(struct pmem_device *pmem)
{
iounmap(pmem->virt_addr);