snmp: 64bit ipstats_mib for all arches

/proc/net/snmp and /proc/net/netstat expose SNMP counters.

Width of these counters is either 32 or 64 bits, depending on the size
of "unsigned long" in kernel.

This means user program parsing these files must already be prepared to
deal with 64bit values, regardless of user program being 32 or 64 bit.

This patch introduces 64bit snmp values for IPSTAT mib, where some
counters can wrap pretty fast if they are 32bit wide.

# netstat -s|egrep "InOctets|OutOctets"
    InOctets: 244068329096
    OutOctets: 244069348848

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 76 insertions, 10 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 640db9b9033..3ceb025b16f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1427,6 +1427,42 @@ unsigned long snmp_fold_field(void __percpu *mib[], int offt)
 }
 EXPORT_SYMBOL_GPL(snmp_fold_field);
 
+#if BITS_PER_LONG==32
+
+u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset)
+{
+	u64 res = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		void *bhptr, *userptr;
+		struct u64_stats_sync *syncp;
+		u64 v_bh, v_user;
+		unsigned int start;
+
+		/* first mib used by softirq context, we must use _bh() accessors */
+		bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu);
+		syncp = (struct u64_stats_sync *)(bhptr + syncp_offset);
+		do {
+			start = u64_stats_fetch_begin_bh(syncp);
+			v_bh = *(((u64 *) bhptr) + offt);
+		} while (u64_stats_fetch_retry_bh(syncp, start));
+
+		/* second mib used in USER context */
+		userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu);
+		syncp = (struct u64_stats_sync *)(userptr + syncp_offset);
+		do {
+			start = u64_stats_fetch_begin(syncp);
+			v_user = *(((u64 *) userptr) + offt);
+		} while (u64_stats_fetch_retry(syncp, start));
+
+		res += v_bh + v_user;
+	}
+	return res;
+}
+EXPORT_SYMBOL_GPL(snmp_fold_field64);
+#endif
+
 int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align)
 {
 	BUG_ON(ptr == NULL);
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index e320ca6b3ef..4ae1f203f7c 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -343,10 +343,12 @@ static int snmp_seq_show(struct seq_file *seq, void *v)
 		   IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2,
 		   sysctl_ip_default_ttl);
 
+	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
 	for (i = 0; snmp4_ipstats_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.ip_statistics,
-					   snmp4_ipstats_list[i].entry));
+		seq_printf(seq, " %llu",
+			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+					     snmp4_ipstats_list[i].entry,
+					     offsetof(struct ipstats_mib, syncp)));
 
 	icmp_put(seq);	/* RFC 2011 compatibility */
 	icmpmsg_put(seq);
@@ -432,9 +434,10 @@ static int netstat_seq_show(struct seq_file *seq, void *v)
 
 	seq_puts(seq, "\nIpExt:");
 	for (i = 0; snmp4_ipextstats_list[i].name != NULL; i++)
-		seq_printf(seq, " %lu",
-			   snmp_fold_field((void __percpu **)net->mib.ip_statistics,
-					   snmp4_ipextstats_list[i].entry));
+		seq_printf(seq, " %llu",
+			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
+					     snmp4_ipextstats_list[i].entry,
+					     offsetof(struct ipstats_mib, syncp)));
 
 	seq_putc(seq, '\n');
 	return 0;
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 2514adf5251..e81155d2f25 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3862,12 +3862,28 @@ static inline void __snmp6_fill_stats(u64 *stats, void __percpu **mib,
 	memset(&stats[items], 0, pad);
 }
 
+static inline void __snmp6_fill_stats64(u64 *stats, void __percpu **mib,
+				      int items, int bytes, size_t syncpoff)
+{
+	int i;
+	int pad = bytes - sizeof(u64) * items;
+	BUG_ON(pad < 0);
+
+	/* Use put_unaligned() because stats may not be aligned for u64. */
+	put_unaligned(items, &stats[0]);
+	for (i = 1; i < items; i++)
+		put_unaligned(snmp_fold_field64(mib, i, syncpoff), &stats[i]);
+
+	memset(&stats[items], 0, pad);
+}
+
 static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype,
 			     int bytes)
 {
 	switch (attrtype) {
 	case IFLA_INET6_STATS:
-		__snmp6_fill_stats(stats, (void __percpu **)idev->stats.ipv6, IPSTATS_MIB_MAX, bytes);
+		__snmp6_fill_stats64(stats, (void __percpu **)idev->stats.ipv6,
+				     IPSTATS_MIB_MAX, bytes, offsetof(struct ipstats_mib, syncp));
 		break;
 	case IFLA_INET6_ICMP6STATS:
 		__snmp6_fill_stats(stats, (void __percpu **)idev->stats.icmpv6, ICMP6_MIB_MAX, bytes);
diff --git a/net/ipv6/proc.c b/net/ipv6/proc.c
index 566798d69f3..d082eaeefa2 100644
--- a/net/ipv6/proc.c
+++ b/net/ipv6/proc.c
@@ -174,17 +174,28 @@ static void snmp6_seq_show_item(struct seq_file *seq, void __percpu **mib,
 				const struct snmp_mib *itemlist)
 {
 	int i;
-	for (i=0; itemlist[i].name; i++)
+
+	for (i = 0; itemlist[i].name; i++)
 		seq_printf(seq, "%-32s\t%lu\n", itemlist[i].name,
 			   snmp_fold_field(mib, itemlist[i].entry));
 }
 
+static void snmp6_seq_show_item64(struct seq_file *seq, void __percpu **mib,
+				  const struct snmp_mib *itemlist, size_t syncpoff)
+{
+	int i;
+
+	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));
+}
+
 static int snmp6_seq_show(struct seq_file *seq, void *v)
 {
 	struct net *net = (struct net *)seq->private;
 
-	snmp6_seq_show_item(seq, (void __percpu **)net->mib.ipv6_statistics,
-			    snmp6_ipstats_list);
+	snmp6_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics,
+			    snmp6_ipstats_list, offsetof(struct ipstats_mib, syncp));
 	snmp6_seq_show_item(seq, (void __percpu **)net->mib.icmpv6_statistics,
 			    snmp6_icmp6_list);
 	snmp6_seq_show_icmpv6msg(seq,