hfsc: reduce hfsc_sched to 14 cachelines

hfsc_sched is huge (size: 920, cachelines: 15), but we can get it to 14
cachelines by placing level after filter_cnt (covering 4 byte hole) and
reducing period/nactive/flags to u32 (period is just a counter,
incremented when class becomes active -- 2**32 is plenty for this
purpose, also, long is only 32bit wide on 32bit platforms anyway).

cl_vtperiod is exported to userspace via tc_hfsc_stats, but its period
member is already u32, so no precision is lost there either.

Cc: Michal Soltys <soltys@ziu.info>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index dff92ea..3ddc7bd 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -115,9 +115,9 @@
 	struct gnet_stats_basic_packed bstats;
 	struct gnet_stats_queue qstats;
 	struct gnet_stats_rate_est64 rate_est;
-	unsigned int	level;		/* class level in hierarchy */
 	struct tcf_proto __rcu *filter_list; /* filter list */
 	unsigned int	filter_cnt;	/* filter count */
+	unsigned int	level;		/* class level in hierarchy */
 
 	struct hfsc_sched *sched;	/* scheduler data */
 	struct hfsc_class *cl_parent;	/* parent class */
@@ -165,10 +165,10 @@
 	struct runtime_sc cl_virtual;	/* virtual curve */
 	struct runtime_sc cl_ulimit;	/* upperlimit curve */
 
-	unsigned long	cl_flags;	/* which curves are valid */
-	unsigned long	cl_vtperiod;	/* vt period sequence number */
-	unsigned long	cl_parentperiod;/* parent's vt period sequence number*/
-	unsigned long	cl_nactive;	/* number of active children */
+	u8		cl_flags;	/* which curves are valid */
+	u32		cl_vtperiod;	/* vt period sequence number */
+	u32		cl_parentperiod;/* parent's vt period sequence number*/
+	u32		cl_nactive;	/* number of active children */
 };
 
 struct hfsc_sched {