Move vmmeter atomic counters into dedicated cache lines

Prior to the change they were subject to extreme false sharing.
In particular this change shaves about 3 seconds real time of -j 80 buildkernel.

Reviewed by:	alc, markj
Differential Revision:	https://reviews.freebsd.org/D12281

sys/sys/vmmeter.h

@@ -60,6 +60,12 @@ struct vmtotal {
 #if defined(_KERNEL) || defined(_WANT_VMMETER)
 #include <sys/counter.h>
 
+#ifdef _KERNEL
+#define VMMETER_ALIGNED	__aligned(CACHE_LINE_SIZE)
+#else
+#define VMMETER_ALIGNED
+#endif
+
 /*
  * System wide statistics counters.
  * Locking:
@@ -126,14 +132,15 @@ struct vmmeter {
 	u_int v_free_target;	/* (c) pages desired free */
 	u_int v_free_min;	/* (c) pages desired free */
 	u_int v_free_count;	/* (f) pages free */
-	u_int v_wire_count;	/* (a) pages wired down */
-	u_int v_active_count;	/* (q) pages active */
 	u_int v_inactive_target; /* (c) pages desired inactive */
-	u_int v_inactive_count;	/* (q) pages inactive */
-	u_int v_laundry_count;	/* (q) pages eligible for laundering */
 	u_int v_pageout_free_min;   /* (c) min pages reserved for kernel */
 	u_int v_interrupt_free_min; /* (c) reserved pages for int code */
 	u_int v_free_severe;	/* (c) severe page depletion point */
+	u_int v_wire_count VMMETER_ALIGNED; /* (a) pages wired down */
+	u_int v_active_count VMMETER_ALIGNED; /* (a) pages active */
+	u_int v_inactive_count VMMETER_ALIGNED;	/* (a) pages inactive */
+	u_int v_laundry_count VMMETER_ALIGNED; /* (a) pages eligible for
+						  laundering */
 };
 #endif /* _KERNEL || _WANT_VMMETER */
 

sys/vm/vm_meter.c

@@ -56,7 +56,7 @@ __FBSDID("$FreeBSD$");
 #include <vm/vm_object.h>
 #include <sys/sysctl.h>
 
-struct vmmeter vm_cnt = {
+struct vmmeter __exclusive_cache_line vm_cnt = {
 	.v_swtch = EARLY_COUNTER,
 	.v_trap = EARLY_COUNTER,
 	.v_syscall = EARLY_COUNTER,