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>

include/net/ip.h

@@ -165,12 +165,12 @@ struct ipv4_config {
 };
 
 extern struct ipv4_config ipv4_config;
-#define IP_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.ip_statistics, field)
+#define IP_INC_STATS(net, field)	SNMP_INC_STATS64((net)->mib.ip_statistics, field)
-#define IP_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.ip_statistics, field)
+#define IP_INC_STATS_BH(net, field)	SNMP_INC_STATS64_BH((net)->mib.ip_statistics, field)
-#define IP_ADD_STATS(net, field, val)	SNMP_ADD_STATS((net)->mib.ip_statistics, field, val)
+#define IP_ADD_STATS(net, field, val)	SNMP_ADD_STATS64((net)->mib.ip_statistics, field, val)
-#define IP_ADD_STATS_BH(net, field, val) SNMP_ADD_STATS_BH((net)->mib.ip_statistics, field, val)
+#define IP_ADD_STATS_BH(net, field, val) SNMP_ADD_STATS64_BH((net)->mib.ip_statistics, field, val)
-#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS((net)->mib.ip_statistics, field, val)
+#define IP_UPD_PO_STATS(net, field, val) SNMP_UPD_PO_STATS64((net)->mib.ip_statistics, field, val)
-#define IP_UPD_PO_STATS_BH(net, field, val) SNMP_UPD_PO_STATS_BH((net)->mib.ip_statistics, field, val)
+#define IP_UPD_PO_STATS_BH(net, field, val) SNMP_UPD_PO_STATS64_BH((net)->mib.ip_statistics, field, val)
 #define NET_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.net_statistics, field)
 #define NET_INC_STATS_BH(net, field)	SNMP_INC_STATS_BH((net)->mib.net_statistics, field)
 #define NET_INC_STATS_USER(net, field) 	SNMP_INC_STATS_USER((net)->mib.net_statistics, field)
@@ -178,6 +178,14 @@ extern struct ipv4_config ipv4_config;
 #define NET_ADD_STATS_USER(net, field, adnd) SNMP_ADD_STATS_USER((net)->mib.net_statistics, field, adnd)
 
 extern unsigned long snmp_fold_field(void __percpu *mib[], int offt);
+#if BITS_PER_LONG==32
+extern u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t sync_off);
+#else
+static inline u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_off)
+{
+	return snmp_fold_field(mib, offt);
+}
+#endif
 extern int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align);
 extern void snmp_mib_free(void __percpu *ptr[2]);
 

include/net/ipv6.h

@@ -136,17 +136,17 @@ extern struct ctl_path net_ipv6_ctl_path[];
 /* MIBs */
 
 #define IP6_INC_STATS(net, idev,field)		\
-		_DEVINC(net, ipv6, , idev, field)
+		_DEVINC(net, ipv6, 64, idev, field)
 #define IP6_INC_STATS_BH(net, idev,field)	\
-		_DEVINC(net, ipv6, _BH, idev, field)
+		_DEVINC(net, ipv6, 64_BH, idev, field)
 #define IP6_ADD_STATS(net, idev,field,val)	\
-		_DEVADD(net, ipv6, , idev, field, val)
+		_DEVADD(net, ipv6, 64, idev, field, val)
 #define IP6_ADD_STATS_BH(net, idev,field,val)	\
-		_DEVADD(net, ipv6, _BH, idev, field, val)
+		_DEVADD(net, ipv6, 64_BH, idev, field, val)
 #define IP6_UPD_PO_STATS(net, idev,field,val)   \
-		_DEVUPD(net, ipv6, , idev, field, val)
+		_DEVUPD(net, ipv6, 64, idev, field, val)
 #define IP6_UPD_PO_STATS_BH(net, idev,field,val)   \
-		_DEVUPD(net, ipv6, _BH, idev, field, val)
+		_DEVUPD(net, ipv6, 64_BH, idev, field, val)
 #define ICMP6_INC_STATS(net, idev, field)	\
 		_DEVINC(net, icmpv6, , idev, field)
 #define ICMP6_INC_STATS_BH(net, idev, field)	\

include/net/snmp.h

@@ -47,15 +47,16 @@ struct snmp_mib {
 }
 
 /*
- * We use all unsigned longs. Linux will soon be so reliable that even 
+ * We use unsigned longs for most mibs but u64 for ipstats.
- * these will rapidly get too small 8-). Seriously consider the IpInReceives 
- * count on the 20Gb/s + networks people expect in a few years time!
  */
+#include <linux/u64_stats_sync.h>
 
 /* IPstats */
 #define IPSTATS_MIB_MAX	__IPSTATS_MIB_MAX
 struct ipstats_mib {
-	unsigned long	mibs[IPSTATS_MIB_MAX];
+	/* mibs[] must be first field of struct ipstats_mib */
+	u64		mibs[IPSTATS_MIB_MAX];
+	struct u64_stats_sync syncp;
 };
 
 /* ICMP */
@@ -155,4 +156,70 @@ struct linux_xfrm_mib {
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
 	} while (0)
+
+
+#if BITS_PER_LONG==32
+
+#define SNMP_ADD_STATS64_BH(mib, field, addend) 			\
+	do {								\
+		__typeof__(*mib[0]) *ptr = __this_cpu_ptr((mib)[0]);	\
+		u64_stats_update_begin(&ptr->syncp);			\
+		ptr->mibs[field] += addend;				\
+		u64_stats_update_end(&ptr->syncp);			\
+	} while (0)
+#define SNMP_ADD_STATS64_USER(mib, field, addend) 			\
+	do {								\
+		__typeof__(*mib[0]) *ptr;				\
+		preempt_disable();					\
+		ptr = __this_cpu_ptr((mib)[1]);				\
+		u64_stats_update_begin(&ptr->syncp);			\
+		ptr->mibs[field] += addend;				\
+		u64_stats_update_end(&ptr->syncp);			\
+		preempt_enable();					\
+	} while (0)
+#define SNMP_ADD_STATS64(mib, field, addend)				\
+	do {								\
+		__typeof__(*mib[0]) *ptr;				\
+		preempt_disable();					\
+		ptr = __this_cpu_ptr((mib)[!in_softirq()]);		\
+		u64_stats_update_begin(&ptr->syncp);			\
+		ptr->mibs[field] += addend;				\
+		u64_stats_update_end(&ptr->syncp);			\
+		preempt_enable();					\
+	} while (0)
+#define SNMP_INC_STATS64_BH(mib, field) SNMP_ADD_STATS64_BH(mib, field, 1)
+#define SNMP_INC_STATS64_USER(mib, field) SNMP_ADD_STATS64_USER(mib, field, 1)
+#define SNMP_INC_STATS64(mib, field) SNMP_ADD_STATS64(mib, field, 1)
+#define SNMP_UPD_PO_STATS64(mib, basefield, addend)			\
+	do {								\
+		__typeof__(*mib[0]) *ptr;				\
+		preempt_disable();					\
+		ptr = __this_cpu_ptr((mib)[!in_softirq()]);		\
+		u64_stats_update_begin(&ptr->syncp);			\
+		ptr->mibs[basefield##PKTS]++;				\
+		ptr->mibs[basefield##OCTETS] += addend;			\
+		u64_stats_update_end(&ptr->syncp);			\
+		preempt_enable();					\
+	} while (0)
+#define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend)			\
+	do {								\
+		__typeof__(*mib[0]) *ptr;				\
+		ptr = __this_cpu_ptr((mib)[!in_softirq()]);		\
+		u64_stats_update_begin(&ptr->syncp);			\
+		ptr->mibs[basefield##PKTS]++;				\
+		ptr->mibs[basefield##OCTETS] += addend;			\
+		u64_stats_update_end(&ptr->syncp);			\
+	} while (0)
+#else
+#define SNMP_INC_STATS64_BH(mib, field)		SNMP_INC_STATS_BH(mib, field)
+#define SNMP_INC_STATS64_USER(mib, field)	SNMP_INC_STATS_USER(mib, field)
+#define SNMP_INC_STATS64(mib, field)		SNMP_INC_STATS(mib, field)
+#define SNMP_DEC_STATS64(mib, field)		SNMP_DEC_STATS(mib, field)
+#define SNMP_ADD_STATS64_BH(mib, field, addend) SNMP_ADD_STATS_BH(mib, field, addend)
+#define SNMP_ADD_STATS64_USER(mib, field, addend) SNMP_ADD_STATS_USER(mib, field, addend)
+#define SNMP_ADD_STATS64(mib, field, addend)	SNMP_ADD_STATS(mib, field, addend)
+#define SNMP_UPD_PO_STATS64(mib, basefield, addend) SNMP_UPD_PO_STATS(mib, basefield, addend)
+#define SNMP_UPD_PO_STATS64_BH(mib, basefield, addend) SNMP_UPD_PO_STATS_BH(mib, basefield, addend)
+#endif
+
 #endif

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);

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",
+		seq_printf(seq, " %llu",
-			   snmp_fold_field((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
-					   snmp4_ipstats_list[i].entry));
+					     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",
+		seq_printf(seq, " %llu",
-			   snmp_fold_field((void __percpu **)net->mib.ip_statistics,
+			   snmp_fold_field64((void __percpu **)net->mib.ip_statistics,
-					   snmp4_ipextstats_list[i].entry));
+					     snmp4_ipextstats_list[i].entry,
+					     offsetof(struct ipstats_mib, syncp)));
 
 	seq_putc(seq, '\n');
 	return 0;

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);

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_seq_show_item64(seq, (void __percpu **)net->mib.ipv6_statistics,
-			    snmp6_ipstats_list);
+			    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,