Merge branch 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/…

…git/tj/percpu

Pull percpu updates from Tejun Heo:

 - Major reorganization of percpu header files which I think makes
   things a lot more readable and logical than before.

 - percpu-refcount is updated so that it requires explicit destruction
   and can be reinitialized if necessary.  This was pulled into the
   block tree to replace the custom percpu refcnting implemented in
   blk-mq.

 - In the process, percpu and percpu-refcount got cleaned up a bit

* 'for-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (21 commits)
  percpu-refcount: implement percpu_ref_reinit() and percpu_ref_is_zero()
  percpu-refcount: require percpu_ref to be exited explicitly
  percpu-refcount: use unsigned long for pcpu_count pointer
  percpu-refcount: add helpers for ->percpu_count accesses
  percpu-refcount: one bit is enough for REF_STATUS
  percpu-refcount, aio: use percpu_ref_cancel_init() in ioctx_alloc()
  workqueue: stronger test in process_one_work()
  workqueue: clear POOL_DISASSOCIATED in rebind_workers()
  percpu: Use ALIGN macro instead of hand coding alignment calculation
  percpu: invoke __verify_pcpu_ptr() from the generic part of accessors and operations
  percpu: preffity percpu header files
  percpu: use raw_cpu_*() to define __this_cpu_*()
  percpu: reorder macros in percpu header files
  percpu: move {raw|this}_cpu_*() definitions to include/linux/percpu-defs.h
  percpu: move generic {raw|this}_cpu_*_N() definitions to include/asm-generic/percpu.h
  percpu: only allow sized arch overrides for {raw|this}_cpu_*() ops
  percpu: reorganize include/linux/percpu-defs.h
  percpu: move accessors from include/linux/percpu.h to percpu-defs.h
  percpu: include/asm-generic/percpu.h should contain only arch-overridable parts
  percpu: introduce arch_raw_cpu_ptr()
  ...

arch/x86/include/asm/percpu.h

@@ -52,10 +52,9 @@
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
  */
-#define raw_cpu_ptr(ptr)				\
+#define arch_raw_cpu_ptr(ptr)				\
 ({							\
 	unsigned long tcp_ptr__;			\
-	__verify_pcpu_ptr(ptr);				\
 	asm volatile("add " __percpu_arg(1) ", %0"	\
 		     : "=r" (tcp_ptr__)			\
 		     : "m" (this_cpu_off), "0" (ptr));	\

drivers/target/target_core_tpg.c

@@ -825,7 +825,7 @@ int core_tpg_add_lun(
 
 	ret = core_dev_export(dev, tpg, lun);
 	if (ret < 0) {
-		percpu_ref_cancel_init(&lun->lun_ref);
+		percpu_ref_exit(&lun->lun_ref);
 		return ret;
 	}
 
@@ -880,5 +880,7 @@ int core_tpg_post_dellun(
 	lun->lun_status = TRANSPORT_LUN_STATUS_FREE;
 	spin_unlock(&tpg->tpg_lun_lock);
 
+	percpu_ref_exit(&lun->lun_ref);
+
 	return 0;
 }

fs/aio.c

@@ -506,6 +506,8 @@ static void free_ioctx(struct work_struct *work)
 
 	aio_free_ring(ctx);
 	free_percpu(ctx->cpu);
+	percpu_ref_exit(&ctx->reqs);
+	percpu_ref_exit(&ctx->users);
 	kmem_cache_free(kioctx_cachep, ctx);
 }
 
@@ -715,8 +717,8 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 err:
 	mutex_unlock(&ctx->ring_lock);
 	free_percpu(ctx->cpu);
-	free_percpu(ctx->reqs.pcpu_count);
-	free_percpu(ctx->users.pcpu_count);
+	percpu_ref_exit(&ctx->reqs);
+	percpu_ref_exit(&ctx->users);
 	kmem_cache_free(kioctx_cachep, ctx);
 	pr_debug("error allocating ioctx %d\n", err);
 	return ERR_PTR(err);