@@ -665,7 +665,8 @@ void print_tm(const struct tcf_t *tm)
tm->expires / hz);
}
-static void print_tcstats_basic_hw(struct rtattr **tbs, const char *prefix)
+static void print_tcstats_basic_hw(struct rtattr **tbs, const char *prefix,
+ __u64 packets64, __u64 packets64_hw)
{
struct gnet_stats_basic bs_hw;
@@ -674,8 +675,9 @@ static void print_tcstats_basic_hw(struct rtattr **tbs, const char *prefix)
memcpy(&bs_hw, RTA_DATA(tbs[TCA_STATS_BASIC_HW]),
MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC_HW]), sizeof(bs_hw)));
+ packets64_hw = packets64_hw ? : bs_hw.packets;
- if (bs_hw.bytes == 0 && bs_hw.packets == 0)
+ if (bs_hw.bytes == 0 && packets64_hw == 0)
return;
if (tbs[TCA_STATS_BASIC]) {
@@ -684,15 +686,16 @@ static void print_tcstats_basic_hw(struct rtattr **tbs, const char *prefix)
memcpy(&bs, RTA_DATA(tbs[TCA_STATS_BASIC]),
MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC]),
sizeof(bs)));
+ packets64 = packets64 ? : bs.packets;
- if (bs.bytes >= bs_hw.bytes && bs.packets >= bs_hw.packets) {
+ if (bs.bytes >= bs_hw.bytes && packets64 >= packets64_hw) {
print_nl();
print_string(PRINT_FP, NULL, "%s", prefix);
print_lluint(PRINT_ANY, "sw_bytes",
"Sent software %llu bytes",
bs.bytes - bs_hw.bytes);
- print_uint(PRINT_ANY, "sw_packets", " %u pkt",
- bs.packets - bs_hw.packets);
+ print_lluint(PRINT_ANY, "sw_packets", " %llu pkt",
+ packets64 - packets64_hw);
}
}
@@ -700,21 +703,40 @@ static void print_tcstats_basic_hw(struct rtattr **tbs, const char *prefix)
print_string(PRINT_FP, NULL, "%s", prefix);
print_lluint(PRINT_ANY, "hw_bytes", "Sent hardware %llu bytes",
bs_hw.bytes);
- print_uint(PRINT_ANY, "hw_packets", " %u pkt", bs_hw.packets);
+ print_lluint(PRINT_ANY, "hw_packets", " %llu pkt", packets64_hw);
+}
+
+static void parse_packets64(const struct rtattr *nest, __u64 *p_packets64,
+ __u64 *p_packets64_hw)
+{
+ unsigned short prev_type = __TCA_STATS_MAX;
+ const struct rtattr *pos;
+
+ /* 'TCA_STATS_PKT64' can appear twice in the 'TCA_ACT_STATS' nest.
+ * Whether the attribute carries the combined or hardware only
+ * statistics depends on the attribute that precedes it in the nest.
+ */
+ rtattr_for_each_nested(pos, nest) {
+ if (pos->rta_type == TCA_STATS_PKT64 &&
+ prev_type == TCA_STATS_BASIC)
+ *p_packets64 = rta_getattr_u64(pos);
+ else if (pos->rta_type == TCA_STATS_PKT64 &&
+ prev_type == TCA_STATS_BASIC_HW)
+ *p_packets64_hw = rta_getattr_u64(pos);
+ prev_type = pos->rta_type;
+ }
}
void print_tcstats2_attr(struct rtattr *rta, const char *prefix, struct rtattr **xstats)
{
struct rtattr *tbs[TCA_STATS_MAX + 1];
+ __u64 packets64 = 0, packets64_hw = 0;
parse_rtattr_nested(tbs, TCA_STATS_MAX, rta);
+ parse_packets64(rta, &packets64, &packets64_hw);
if (tbs[TCA_STATS_BASIC]) {
struct gnet_stats_basic bs = {0};
- __u64 packets64 = 0;
-
- if (tbs[TCA_STATS_PKT64])
- packets64 = rta_getattr_u64(tbs[TCA_STATS_PKT64]);
memcpy(&bs, RTA_DATA(tbs[TCA_STATS_BASIC]),
MIN(RTA_PAYLOAD(tbs[TCA_STATS_BASIC]), sizeof(bs)));
@@ -740,7 +762,7 @@ void print_tcstats2_attr(struct rtattr *rta, const char *prefix, struct rtattr *
}
if (tbs[TCA_STATS_BASIC_HW])
- print_tcstats_basic_hw(tbs, prefix);
+ print_tcstats_basic_hw(tbs, prefix, packets64, packets64_hw);
if (tbs[TCA_STATS_RATE_EST64]) {
struct gnet_stats_rate_est64 re = {0};
The netlink nest that carriers tc action statistics looks as follows: [TCA_ACT_STATS] [TCA_STATS_BASIC] [TCA_STATS_BASIC_HW] Where 'TCA_STATS_BASIC' carries the combined software and hardware packets (32-bits) and bytes (64-bit) counters and 'TCA_STATS_BASIC_HW' carries the hardware statistics. When the number of packets exceeds 0xffffffff, the kernel emits the 'TCA_STATS_PKT64' attribute: [TCA_ACT_STATS] [TCA_STATS_BASIC] [TCA_STATS_PKT64] [TCA_STATS_BASIC_HW] [TCA_STATS_PKT64] This layout is not ideal as the only way for user space to know what each 'TCA_STATS_PKT64' attribute carries is to check which attribute precedes it, which is exactly what some applications are doing [1]. Do the same in iproute2 so that users with existing kernels could read the 64-bit hardware packets counter of tc actions instead of reading the truncated 32-bit counter. Before: $ tc -s filter show dev swp2 ingress filter protocol all pref 1 flower chain 0 filter protocol all pref 1 flower chain 0 handle 0x1 skip_sw in_hw in_hw_count 1 action order 1: mirred (Egress Redirect to device swp1) stolen index 1 ref 1 bind 1 installed 47 sec used 23 sec Action statistics: Sent 368689092544 bytes 5760767071 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 368689092544 bytes 1465799775 pkt backlog 0b 0p requeues 0 used_hw_stats immediate Where 5760767071 - 1465799775 = 0x100000000 After: $ tc -s filter show dev swp2 ingress filter protocol all pref 1 flower chain 0 filter protocol all pref 1 flower chain 0 handle 0x1 skip_sw in_hw in_hw_count 1 action order 1: mirred (Egress Redirect to device swp1) stolen index 1 ref 1 bind 1 installed 71 sec used 47 sec Action statistics: Sent 368689092544 bytes 5760767071 pkt (dropped 0, overlimits 0 requeues 0) Sent software 0 bytes 0 pkt Sent hardware 368689092544 bytes 5760767071 pkt backlog 0b 0p requeues 0 used_hw_stats immediate [1] https://github.com/openvswitch/ovs/commit/006e1c6dbfbadf474c17c8fa1ea358918d371588 Reported-by: Joe Botha <joe@atomic.ac> Reviewed-by: Petr Machata <petrm@nvidia.com> Signed-off-by: Ido Schimmel <idosch@nvidia.com> --- tc/tc_util.c | 44 +++++++++++++++++++++++++++++++++----------- 1 file changed, 33 insertions(+), 11 deletions(-)