mm/vmalloc: use raw_cpu_ptr() for vmap_block_queue access

The per-CPU resource vmap_block_queue is accessed via get_cpu_var().  That
macro disables preemption and then loads the pointer from the current CPU.

This doesn't work on PREEMPT_RT because a spinlock_t is later accessed
within the preempt-disable section.

There is no need to disable preemption while accessing the per-CPU struct
vmap_block_queue because the list is protected with a spinlock_t.  The
per-CPU struct is also accessed cross-CPU in purge_fragmented_blocks().

It is possible that by using raw_cpu_ptr() the code migrates to another
CPU and uses struct from another CPU.  This is fine because the list is
locked and the locked section is very short.

Use raw_cpu_ptr() to access vmap_block_queue.

Link: https://lkml.kernel.org/r/YnKx3duAB53P7ojN@linutronix.de
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/vmalloc.c

@@ -1938,11 +1938,10 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
 		return ERR_PTR(err);
 	}
 
-	vbq = &get_cpu_var(vmap_block_queue);
+	vbq = raw_cpu_ptr(&vmap_block_queue);
 	spin_lock(&vbq->lock);
 	list_add_tail_rcu(&vb->free_list, &vbq->free);
 	spin_unlock(&vbq->lock);
-	put_cpu_var(vmap_block_queue);
 
 	return vaddr;
 }
@@ -2021,7 +2020,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 	order = get_order(size);
 
 	rcu_read_lock();
-	vbq = &get_cpu_var(vmap_block_queue);
+	vbq = raw_cpu_ptr(&vmap_block_queue);
 	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
 		unsigned long pages_off;
 
@@ -2044,7 +2043,6 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 		break;
 	}
 
-	put_cpu_var(vmap_block_queue);
 	rcu_read_unlock();
 
 	/* Allocate new block if nothing was found */