nd_btt: Make BTT lanes preemptible

nd_region_acquire_lane uses get_cpu, which disables preemption. This is
an issue on PREEMPT_RT kernels, since btt_write_pg and also
nd_region_acquire_lane itself take a spin lock, resulting in BUG:
sleeping function called from invalid context.

Fix the issue by replacing get_cpu with smp_process_id and
migrate_disable when needed. This makes BTT operations preemptible, thus
permitting the use of spin_lock.

BUG example occurring when running ndctl tests on PREEMPT_RT kernel:

BUG: sleeping function called from invalid context at
kernel/locking/spinlock_rt.c:48
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 4903, name:
libndctl
preempt_count: 1, expected: 0
RCU nest depth: 0, expected: 0
Preemption disabled at:
[<ffffffffc1313db5>] nd_region_acquire_lane+0x15/0x90 [libnvdimm]
Call Trace:
 <TASK>
 dump_stack_lvl+0x8e/0xb0
 __might_resched+0x19b/0x250
 rt_spin_lock+0x4c/0x100
 ? btt_write_pg+0x2d7/0x500 [nd_btt]
 btt_write_pg+0x2d7/0x500 [nd_btt]
 ? local_clock_noinstr+0x9/0xc0
 btt_submit_bio+0x16d/0x270 [nd_btt]
 __submit_bio+0x48/0x80
 __submit_bio_noacct+0x7e/0x1e0
 submit_bio_wait+0x58/0xb0
 __blkdev_direct_IO_simple+0x107/0x240
 ? inode_set_ctime_current+0x51/0x110
 ? __pfx_submit_bio_wait_endio+0x10/0x10
 blkdev_write_iter+0x1d8/0x290
 vfs_write+0x237/0x330
 ...
 </TASK>

Fixes: 5212e11f ("nd_btt: atomic sector updates")
Signed-off-by: Tomas Glozar <tglozar@redhat.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Ira Weiny <ira.weiny@intel.com>

drivers/nvdimm/region_devs.c

@@ -939,7 +939,8 @@ unsigned int nd_region_acquire_lane(struct nd_region *nd_region)
 {
 	unsigned int cpu, lane;
 
-	cpu = get_cpu();
+	migrate_disable();
+	cpu = smp_processor_id();
 	if (nd_region->num_lanes < nr_cpu_ids) {
 		struct nd_percpu_lane *ndl_lock, *ndl_count;
 
@@ -958,16 +959,15 @@ 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();
+		unsigned int cpu = smp_processor_id();
 		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();
+	migrate_enable();
 }
 EXPORT_SYMBOL(nd_region_release_lane);