Index: head/sys/amd64/include/counter.h
===================================================================
--- head/sys/amd64/include/counter.h
+++ head/sys/amd64/include/counter.h
@@ -83,18 +83,11 @@
 static inline void
 counter_u64_add(counter_u64_t c, int64_t inc)
 {
-	int64_t *p;
-#ifdef notyet
+
 	__asm __volatile("addq\t%1,%%gs:(%0)"
 	    :
 	    : "r" ((char *)c - (char *)&__pcpu[0]), "ri" (inc)
 	    : "memory", "cc");
-#endif
-	/* temporary */
-	critical_enter();
-	p = zpcpu_get(c);
-	*p += inc;
-	critical_exit();
 }
 
 #endif	/* ! __MACHINE_COUNTER_H__ */
Index: head/sys/amd64/include/pcpu.h
===================================================================
--- head/sys/amd64/include/pcpu.h
+++ head/sys/amd64/include/pcpu.h
@@ -76,8 +76,7 @@
 	uint32_t pc_pcid_gen;						\
 	uint32_t pc_smp_tlb_done;	/* TLB op acknowledgement */	\
 	uint32_t pc_ibpb_set;						\
-	char	__pad[216]		/* be divisor of PAGE_SIZE	\
-					   after cache alignment */
+	char	__pad[3288]		/* pad to UMA_PCPU_ALLOC_SIZE */
 
 #define	PC_DBREG_CMD_NONE	0
 #define	PC_DBREG_CMD_LOAD	1
Index: head/sys/i386/include/pcpu.h
===================================================================
--- head/sys/i386/include/pcpu.h
+++ head/sys/i386/include/pcpu.h
@@ -80,7 +80,7 @@
 	caddr_t pc_pmap_eh_ptep;						\
 	uint32_t pc_smp_tlb_done;	/* TLB op acknowledgement */	\
 	uint32_t pc_ibpb_set;						\
-	char	__pad[538]
+	char	__pad[3610]
 
 #ifdef _KERNEL
 
Index: head/sys/sys/pcpu.h
===================================================================
--- head/sys/sys/pcpu.h
+++ head/sys/sys/pcpu.h
@@ -185,14 +185,6 @@
 	PCPU_MD_FIELDS;
 } __aligned(CACHE_LINE_SIZE);
 
-#ifdef CTASSERT
-/*
- * To minimize memory waste in per-cpu UMA zones, size of struct pcpu
- * should be denominator of PAGE_SIZE.
- */
-CTASSERT((PAGE_SIZE / sizeof(struct pcpu)) * sizeof(struct pcpu) == PAGE_SIZE);
-#endif
-
 #ifdef _KERNEL
 
 STAILQ_HEAD(cpuhead, pcpu);
@@ -208,6 +200,19 @@
 #define	curvidata	PCPU_GET(vidata)
 
 #define UMA_PCPU_ALLOC_SIZE		PAGE_SIZE
+
+#ifdef CTASSERT
+#if defined(__i386__) || defined(__amd64__)
+/* Required for counters(9) to work on x86. */
+CTASSERT(sizeof(struct pcpu) == UMA_PCPU_ALLOC_SIZE);
+#else
+/*
+ * To minimize memory waste in per-cpu UMA zones, size of struct pcpu
+ * should be denominator of PAGE_SIZE.
+ */
+CTASSERT((PAGE_SIZE / sizeof(struct pcpu)) * sizeof(struct pcpu) == PAGE_SIZE);
+#endif	/* UMA_PCPU_ALLOC_SIZE && x86 */
+#endif	/* CTASSERT */
 
 /* Accessor to elements allocated via UMA_ZONE_PCPU zone. */
 static inline void *