Merge branch 'nexthop-group-stats'

Petr Machata says:

====================
Support for nexthop group statistics

ECMP is a fundamental component in L3 designs. However, it's fragile. Many
factors influence whether an ECMP group will operate as intended: hash
policy (i.e. the set of fields that contribute to ECMP hash calculation),
neighbor validity, hash seed (which might lead to polarization) or the type
of ECMP group used (hash-threshold or resilient).

At the same time, collection of statistics that would help an operator
determine that the group performs as desired, is difficult.

A solution that we present in this patchset is to add counters to next hop
group entries. For SW-datapath deployments, this will on its own allow
collection and evaluation of relevant statistics. For HW-datapath
deployments, we further add a way to request that HW counters be installed
for a given group, in-kernel interfaces to collect the HW statistics, and
netlink interfaces to query them.

For example:

    # ip nexthop replace id 4000 group 4001/4002 hw_stats on

    # ip -s -d nexthop show id 4000
    id 4000 group 4001/4002 scope global proto unspec offload hw_stats on used on
      stats:
        id 4001 packets 5002 packets_hw 5000
        id 4002 packets 4999 packets_hw 4999

The point of the patchset is visibility of ECMP balance, and that is
influenced by packet headers, not their payload. Correspondingly, we only
include packet counters in the statistics, not byte counters.

We also decided to model HW statistics as a nexthop group attribute, not an
arbitrary nexthop one. The latter would count any traffic going through a
given nexthop, regardless of which ECMP group it is in, or any at all. The
reason is again hat the point of the patchset is ECMP balance visibility,
not arbitrary inspection of how busy a particular nexthop is.
Implementation of individual-nexthop statistics is certainly possible, and
could well follow the general approach we are taking in this patchset.
For resilient groups, per-bucket statistics could be done in a similar
manner as well.

This patchset contains the core code. mlxsw support will be sent in a
follow-up patch set.

This patchset progresses as follows:

- Patches #1 and #2 add support for a new next-hop object attribute,
  NHA_OP_FLAGS. That is meant to carry various op-specific signaling, in
  particular whether SW- and HW-collected nexthop stats should be part of
  the get or dump response. The idea is to avoid wasting message space, and
  time for collection of HW statistics, when the values are not needed.

- Patches #3 and #4 add SW-datapath stats and corresponding UAPI.

- Patches #5, torvalds#6 and torvalds#7 add support fro HW-datapath stats and UAPI.
  Individual drivers still need to contribute the appropriate HW-specific
  support code.

v4:
- Patch #2:
    - s/nla_get_bitfield32/nla_get_u32/ in __nh_valid_dump_req().

v3:
- Patch #3:
    - Convert to u64_stats_t
- Patch #4:
    - Give a symbolic name to the set of all valid dump flags
      for the NHA_OP_FLAGS attribute.
    - Convert to u64_stats_t
- Patch torvalds#6:
    - Use a named constant for the NHA_HW_STATS_ENABLE policy.

v2:
- Patch #2:
    - Change OP_FLAGS to u32, enforce through NLA_POLICY_MASK
- Patch #3:
    - Set err on nexthop_create_group() error path
- Patch #4:
    - Use uint to encode NHA_GROUP_STATS_ENTRY_PACKETS
    - Rename jump target in nla_put_nh_group_stats() to avoid
      having to rename further in the patchset.
- Patch torvalds#7:
    - Use uint to encode NHA_GROUP_STATS_ENTRY_PACKETS_HW
    - Do not cancel outside of nesting in nla_put_nh_group_stats()
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

include/net/nexthop.h

@@ -47,6 +47,8 @@ struct nh_config {
 	bool		nh_grp_res_has_idle_timer;
 	bool		nh_grp_res_has_unbalanced_timer;
 
+	bool		nh_hw_stats;
+
 	struct nlattr	*nh_encap;
 	u16		nh_encap_type;
 
@@ -95,8 +97,14 @@ struct nh_res_table {
 	struct nh_res_bucket	nh_buckets[] __counted_by(num_nh_buckets);
 };
 
+struct nh_grp_entry_stats {
+	u64_stats_t packets;
+	struct u64_stats_sync syncp;
+};
+
 struct nh_grp_entry {
 	struct nexthop	*nh;
+	struct nh_grp_entry_stats __percpu	*stats;
 	u8		weight;
 
 	union {
@@ -114,6 +122,7 @@ struct nh_grp_entry {
 
 	struct list_head nh_list;
 	struct nexthop	*nh_parent;  /* nexthop of group with this entry */
+	u64		packets_hw;
 };
 
 struct nh_group {
@@ -124,6 +133,7 @@ struct nh_group {
 	bool			resilient;
 	bool			fdb_nh;
 	bool			has_v4;
+	bool			hw_stats;
 
 	struct nh_res_table __rcu *res_table;
 	struct nh_grp_entry	nh_entries[] __counted_by(num_nh);
@@ -157,13 +167,15 @@ enum nexthop_event_type {
 	NEXTHOP_EVENT_REPLACE,
 	NEXTHOP_EVENT_RES_TABLE_PRE_REPLACE,
 	NEXTHOP_EVENT_BUCKET_REPLACE,
+	NEXTHOP_EVENT_HW_STATS_REPORT_DELTA,
 };
 
 enum nh_notifier_info_type {
 	NH_NOTIFIER_INFO_TYPE_SINGLE,
 	NH_NOTIFIER_INFO_TYPE_GRP,
 	NH_NOTIFIER_INFO_TYPE_RES_TABLE,
 	NH_NOTIFIER_INFO_TYPE_RES_BUCKET,
+	NH_NOTIFIER_INFO_TYPE_GRP_HW_STATS,
 };
 
 struct nh_notifier_single_info {
@@ -187,6 +199,7 @@ struct nh_notifier_grp_entry_info {
 struct nh_notifier_grp_info {
 	u16 num_nh;
 	bool is_fdb;
+	bool hw_stats;
 	struct nh_notifier_grp_entry_info nh_entries[] __counted_by(num_nh);
 };
 
@@ -200,9 +213,21 @@ struct nh_notifier_res_bucket_info {
 
 struct nh_notifier_res_table_info {
 	u16 num_nh_buckets;
+	bool hw_stats;
 	struct nh_notifier_single_info nhs[] __counted_by(num_nh_buckets);
 };
 
+struct nh_notifier_grp_hw_stats_entry_info {
+	u32 id;
+	u64 packets;
+};
+
+struct nh_notifier_grp_hw_stats_info {
+	u16 num_nh;
+	bool hw_stats_used;
+	struct nh_notifier_grp_hw_stats_entry_info stats[] __counted_by(num_nh);
+};
+
 struct nh_notifier_info {
 	struct net *net;
 	struct netlink_ext_ack *extack;
@@ -213,6 +238,7 @@ struct nh_notifier_info {
 		struct nh_notifier_grp_info *nh_grp;
 		struct nh_notifier_res_table_info *nh_res_table;
 		struct nh_notifier_res_bucket_info *nh_res_bucket;
+		struct nh_notifier_grp_hw_stats_info *nh_grp_hw_stats;
 	};
 };
 
@@ -225,6 +251,9 @@ void nexthop_bucket_set_hw_flags(struct net *net, u32 id, u16 bucket_index,
 				 bool offload, bool trap);
 void nexthop_res_grp_activity_update(struct net *net, u32 id, u16 num_buckets,
 				     unsigned long *activity);
+void nh_grp_hw_stats_report_delta(struct nh_notifier_grp_hw_stats_info *info,
+				  unsigned int nh_idx,
+				  u64 delta_packets);
 
 /* caller is holding rcu or rtnl; no reference taken to nexthop */
 struct nexthop *nexthop_find_by_id(struct net *net, u32 id);

include/uapi/linux/nexthop.h

@@ -30,6 +30,9 @@ enum {
 
 #define NEXTHOP_GRP_TYPE_MAX (__NEXTHOP_GRP_TYPE_MAX - 1)
 
+#define NHA_OP_FLAG_DUMP_STATS		BIT(0)
+#define NHA_OP_FLAG_DUMP_HW_STATS	BIT(1)
+
 enum {
 	NHA_UNSPEC,
 	NHA_ID,		/* u32; id for nexthop. id == 0 means auto-assign */
@@ -60,6 +63,18 @@ enum {
 	/* nested; nexthop bucket attributes */
 	NHA_RES_BUCKET,
 
+	/* u32; operation-specific flags */
+	NHA_OP_FLAGS,
+
+	/* nested; nexthop group stats */
+	NHA_GROUP_STATS,
+
+	/* u32; nexthop hardware stats enable */
+	NHA_HW_STATS_ENABLE,
+
+	/* u32; read-only; whether any driver collects HW stats */
+	NHA_HW_STATS_USED,
+
 	__NHA_MAX,
 };
 
@@ -101,4 +116,34 @@ enum {
 
 #define NHA_RES_BUCKET_MAX	(__NHA_RES_BUCKET_MAX - 1)
 
+enum {
+	NHA_GROUP_STATS_UNSPEC,
+
+	/* nested; nexthop group entry stats */
+	NHA_GROUP_STATS_ENTRY,
+
+	__NHA_GROUP_STATS_MAX,
+};
+
+#define NHA_GROUP_STATS_MAX	(__NHA_GROUP_STATS_MAX - 1)
+
+enum {
+	NHA_GROUP_STATS_ENTRY_UNSPEC,
+
+	/* u32; nexthop id of the nexthop group entry */
+	NHA_GROUP_STATS_ENTRY_ID,
+
+	/* uint; number of packets forwarded via the nexthop group entry */
+	NHA_GROUP_STATS_ENTRY_PACKETS,
+
+	/* uint; number of packets forwarded via the nexthop group entry in
+	 * hardware
+	 */
+	NHA_GROUP_STATS_ENTRY_PACKETS_HW,
+
+	__NHA_GROUP_STATS_ENTRY_MAX,
+};
+
+#define NHA_GROUP_STATS_ENTRY_MAX	(__NHA_GROUP_STATS_ENTRY_MAX - 1)
+
 #endif