proc: Reduce cache miss in snmp6_seq_show

This is to use the generic interfaces snmp_get_cpu_field{,64}_batch to
aggregate the data by going through all the items of each cpu sequentially.

Signed-off-by: Jia He <hejianet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 22 insertions, 8 deletions

diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 679253d0af84..cc8e3ae9ca73 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -30,6 +30,11 @@
 #include <net/transp_v6.h>
 #include <net/ipv6.h>
 
+#define MAX4(a, b, c, d) \
+        max_t(u32, max_t(u32, a, b), max_t(u32, c, d))
+#define SNMP_MIB_MAX MAX4(UDP_MIB_MAX, TCP_MIB_MAX, \
+                        IPSTATS_MIB_MAX, ICMP_MIB_MAX)
+
 static int sockstat6_seq_show(struct seq_file *seq, void *v)
 {
         struct net *net = seq->private;
@@ -191,25 +196,34 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu *pcpumib,
                                 atomic_long_t *smib,
                                 const struct snmp_mib *itemlist)
 {
+        unsigned long buff[SNMP_MIB_MAX];
         int i;
-        unsigned long val;
 
-        for (i = 0; itemlist[i].name; i++) {
-                val = pcpumib ?
-                        snmp_fold_field(pcpumib, itemlist[i].entry) :
-                        atomic_long_read(smib + itemlist[i].entry);
-                seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name, val);
+        if (pcpumib) {
+                memset(buff, 0, sizeof(unsigned long) * SNMP_MIB_MAX);
+
+                snmp_get_cpu_field_batch(buff, itemlist, pcpumib);
+                for (i = 0; itemlist[i].name; i++)
+                        seq_printf(seq, "%-32s\t%lu\n",
+                                   itemlist[i].name, buff[i]);
+        } else {
+                for (i = 0; itemlist[i].name; i++)
+                        seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name,
+                                   atomic_long_read(smib + itemlist[i].entry));
         }
 }
 
 static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu *mib,
                                   const struct snmp_mib *itemlist, size_t syncpoff)
 {
+        u64 buff64[SNMP_MIB_MAX];
         int i;
 
+        memset(buff64, 0, sizeof(unsigned long) * SNMP_MIB_MAX);
+
+        snmp_get_cpu_field64_batch(buff64, itemlist, mib, syncpoff);
         for (i = 0; itemlist[i].name; i++)
-                seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name,
-                           snmp_fold_field64(mib, itemlist[i].entry, syncpoff));
+                seq_printf(seq, "%-32s\t%llu\n", itemlist[i].name, buff64[i]);
 }
 
 static int snmp6_seq_show(struct seq_file *seq, void *v)