diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 71f4727da373..5a98aa272184 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -185,10 +185,22 @@ void __init setup_per_cpu_areas(void)
 #endif
 	rc = -EINVAL;
 	if (pcpu_chosen_fc != PCPU_FC_PAGE) {
-		const size_t atom_size = cpu_has_pse ? PMD_SIZE : PAGE_SIZE;
 		const size_t dyn_size = PERCPU_MODULE_RESERVE +
 			PERCPU_DYNAMIC_RESERVE - PERCPU_FIRST_CHUNK_RESERVE;
+		size_t atom_size;
 
+		/*
+		 * On 64bit, use PMD_SIZE for atom_size so that embedded
+		 * percpu areas are aligned to PMD.  This, in the future,
+		 * can also allow using PMD mappings in vmalloc area.  Use
+		 * PAGE_SIZE on 32bit as vmalloc space is highly contended
+		 * and large vmalloc area allocs can easily fail.
+		 */
+#ifdef CONFIG_X86_64
+		atom_size = PMD_SIZE;
+#else
+		atom_size = PAGE_SIZE;
+#endif
 		rc = pcpu_embed_first_chunk(PERCPU_FIRST_CHUNK_RESERVE,
 					    dyn_size, atom_size,
 					    pcpu_cpu_distance,
diff --git a/mm/percpu.c b/mm/percpu.c
index f47af9123af7..f921fdfb5430 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1132,20 +1132,20 @@ static void pcpu_dump_alloc_info(const char *lvl,
 		for (alloc_end += gi->nr_units / upa;
 		     alloc < alloc_end; alloc++) {
 			if (!(alloc % apl)) {
-				printk("\n");
+				printk(KERN_CONT "\n");
 				printk("%spcpu-alloc: ", lvl);
 			}
-			printk("[%0*d] ", group_width, group);
+			printk(KERN_CONT "[%0*d] ", group_width, group);
 
 			for (unit_end += upa; unit < unit_end; unit++)
 				if (gi->cpu_map[unit] != NR_CPUS)
-					printk("%0*d ", cpu_width,
+					printk(KERN_CONT "%0*d ", cpu_width,
 					       gi->cpu_map[unit]);
 				else
-					printk("%s ", empty_str);
+					printk(KERN_CONT "%s ", empty_str);
 		}
 	}
-	printk("\n");
+	printk(KERN_CONT "\n");
 }
 
 /**