Merge branch 'net-smc-introduce-ringbufs-usage-statistics'

Wen Gu says:

====================
net/smc: introduce ringbufs usage statistics

Currently, we have histograms that show the sizes of ringbufs that ever
used by SMC connections. However, they are always incremental and since
SMC allows the reuse of ringbufs, we cannot know the actual amount of
ringbufs being allocated or actively used.

So this patch set introduces statistics for the amount of ringbufs that
actually allocated by link group and actively used by connections of a
certain net namespace, so that we can react based on these memory usage
information, e.g. active fallback to TCP.

With appropriate adaptations of smc-tools, we can obtain these ringbufs
usage information:

$ smcr -d linkgroup
LG-ID    : 00000500
LG-Role  : SERV
LG-Type  : ASYML
VLAN     : 0
PNET-ID  :
Version  : 1
Conns    : 0
Sndbuf   : 12910592 B    <-
RMB      : 12910592 B    <-

or

$ smcr -d stats
[...]
RX Stats
  Data transmitted (Bytes)      869225943 (869.2M)
  Total requests                 18494479
  Buffer usage  (Bytes)          12910592 (12.31M)  <-
  [...]

TX Stats
  Data transmitted (Bytes)    12760884405 (12.76G)
  Total requests                 36988338
  Buffer usage  (Bytes)          12910592 (12.31M)  <-
  [...]
[...]

Change log:
v3->v2
- use new helper nla_put_uint() instead of nla_put_u64_64bit().

v2->v1
https://lore.kernel.org/r/20240807075939.57882-1-guwen@linux.alibaba.com/
- remove inline keyword in .c files.
- use local variable in macros to avoid potential side effects.

v1
https://lore.kernel.org/r/20240805090551.80786-1-guwen@linux.alibaba.com/
====================

Link: https://patch.msgid.link/20240814130827.73321-1-guwen@linux.alibaba.comSigned-off-by: Paolo Abeni <pabeni@redhat.com>

include/uapi/linux/smc.h

@@ -127,6 +127,8 @@ enum {
 	SMC_NLA_LGR_R_NET_COOKIE,	/* u64 */
 	SMC_NLA_LGR_R_PAD,		/* flag */
 	SMC_NLA_LGR_R_BUF_TYPE,		/* u8 */
+	SMC_NLA_LGR_R_SNDBUF_ALLOC,	/* uint */
+	SMC_NLA_LGR_R_RMB_ALLOC,	/* uint */
 	__SMC_NLA_LGR_R_MAX,
 	SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1
 };
@@ -162,6 +164,8 @@ enum {
 	SMC_NLA_LGR_D_V2_COMMON,	/* nest */
 	SMC_NLA_LGR_D_EXT_GID,		/* u64 */
 	SMC_NLA_LGR_D_PEER_EXT_GID,	/* u64 */
+	SMC_NLA_LGR_D_SNDBUF_ALLOC,	/* uint */
+	SMC_NLA_LGR_D_DMB_ALLOC,	/* uint */
 	__SMC_NLA_LGR_D_MAX,
 	SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1
 };
@@ -249,6 +253,8 @@ enum {
 	SMC_NLA_STATS_T_TX_BYTES,	/* u64 */
 	SMC_NLA_STATS_T_RX_CNT,		/* u64 */
 	SMC_NLA_STATS_T_TX_CNT,		/* u64 */
+	SMC_NLA_STATS_T_RX_RMB_USAGE,	/* uint */
+	SMC_NLA_STATS_T_TX_RMB_USAGE,	/* uint */
 	__SMC_NLA_STATS_T_MAX,
 	SMC_NLA_STATS_T_MAX = __SMC_NLA_STATS_T_MAX - 1
 };

net/smc/smc_core.c

@@ -221,6 +221,35 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 	write_unlock_bh(&lgr->conns_lock);
 }
 
+static void smc_lgr_buf_list_add(struct smc_link_group *lgr,
+				 bool is_rmb,
+				 struct list_head *buf_list,
+				 struct smc_buf_desc *buf_desc)
+{
+	list_add(&buf_desc->list, buf_list);
+	if (is_rmb) {
+		lgr->alloc_rmbs += buf_desc->len;
+		lgr->alloc_rmbs +=
+			lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0;
+	} else {
+		lgr->alloc_sndbufs += buf_desc->len;
+	}
+}
+
+static void smc_lgr_buf_list_del(struct smc_link_group *lgr,
+				 bool is_rmb,
+				 struct smc_buf_desc *buf_desc)
+{
+	list_del(&buf_desc->list);
+	if (is_rmb) {
+		lgr->alloc_rmbs -= buf_desc->len;
+		lgr->alloc_rmbs -=
+			lgr->is_smcd ? sizeof(struct smcd_cdc_msg) : 0;
+	} else {
+		lgr->alloc_sndbufs -= buf_desc->len;
+	}
+}
+
 int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb);
@@ -363,6 +392,10 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr,
 	smc_target[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_R_SNDBUF_ALLOC, lgr->alloc_sndbufs))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_R_RMB_ALLOC, lgr->alloc_rmbs))
+		goto errattr;
 	if (lgr->smc_version > SMC_V1) {
 		v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON);
 		if (!v2_attrs)
@@ -541,6 +574,10 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr,
 		goto errattr;
 	if (nla_put_u32(skb, SMC_NLA_LGR_D_CHID, smc_ism_get_chid(lgr->smcd)))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_D_SNDBUF_ALLOC, lgr->alloc_sndbufs))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_LGR_D_DMB_ALLOC, lgr->alloc_rmbs))
+		goto errattr;
 	memcpy(smc_pnet, lgr->smcd->pnetid, SMC_MAX_PNETID_LEN);
 	smc_pnet[SMC_MAX_PNETID_LEN] = 0;
 	if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet))
@@ -1138,7 +1175,7 @@ static void smcr_buf_unuse(struct smc_buf_desc *buf_desc, bool is_rmb,
 		lock = is_rmb ? &lgr->rmbs_lock :
 				&lgr->sndbufs_lock;
 		down_write(lock);
-		list_del(&buf_desc->list);
+		smc_lgr_buf_list_del(lgr, is_rmb, buf_desc);
 		up_write(lock);
 
 		smc_buf_free(lgr, is_rmb, buf_desc);
@@ -1166,22 +1203,30 @@ static void smcd_buf_detach(struct smc_connection *conn)
 static void smc_buf_unuse(struct smc_connection *conn,
 			  struct smc_link_group *lgr)
 {
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	bool is_smcd = lgr->is_smcd;
+	int bufsize;
+
 	if (conn->sndbuf_desc) {
-		if (!lgr->is_smcd && conn->sndbuf_desc->is_vm) {
+		bufsize = conn->sndbuf_desc->len;
+		if (!is_smcd && conn->sndbuf_desc->is_vm) {
 			smcr_buf_unuse(conn->sndbuf_desc, false, lgr);
 		} else {
-			memzero_explicit(conn->sndbuf_desc->cpu_addr, conn->sndbuf_desc->len);
+			memzero_explicit(conn->sndbuf_desc->cpu_addr, bufsize);
 			WRITE_ONCE(conn->sndbuf_desc->used, 0);
 		}
+		SMC_STAT_RMB_SIZE(smc, is_smcd, false, false, bufsize);
 	}
 	if (conn->rmb_desc) {
-		if (!lgr->is_smcd) {
+		bufsize = conn->rmb_desc->len;
+		if (!is_smcd) {
 			smcr_buf_unuse(conn->rmb_desc, true, lgr);
 		} else {
-			memzero_explicit(conn->rmb_desc->cpu_addr,
-					 conn->rmb_desc->len + sizeof(struct smcd_cdc_msg));
+			bufsize += sizeof(struct smcd_cdc_msg);
+			memzero_explicit(conn->rmb_desc->cpu_addr, bufsize);
 			WRITE_ONCE(conn->rmb_desc->used, 0);
 		}
+		SMC_STAT_RMB_SIZE(smc, is_smcd, true, false, bufsize);
 	}
 }
 
@@ -1377,7 +1422,7 @@ static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
 			buf_list = &lgr->sndbufs[i];
 		list_for_each_entry_safe(buf_desc, bf_desc, buf_list,
 					 list) {
-			list_del(&buf_desc->list);
+			smc_lgr_buf_list_del(lgr, is_rmb, buf_desc);
 			smc_buf_free(lgr, is_rmb, buf_desc);
 		}
 	}
@@ -2390,7 +2435,7 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		buf_desc = smc_buf_get_slot(bufsize_comp, lock, buf_list);
 		if (buf_desc) {
 			buf_desc->is_dma_need_sync = 0;
-			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
+			SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize);
 			SMC_STAT_BUF_REUSE(smc, is_smcd, is_rmb);
 			break; /* found reusable slot */
 		}
@@ -2411,10 +2456,10 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		}
 
 		SMC_STAT_RMB_ALLOC(smc, is_smcd, is_rmb);
-		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, bufsize);
+		SMC_STAT_RMB_SIZE(smc, is_smcd, is_rmb, true, bufsize);
 		buf_desc->used = 1;
 		down_write(lock);
-		list_add(&buf_desc->list, buf_list);
+		smc_lgr_buf_list_add(lgr, is_rmb, buf_list, buf_desc);
 		up_write(lock);
 		break; /* found */
 	}
@@ -2496,7 +2541,8 @@ int smc_buf_create(struct smc_sock *smc, bool is_smcd)
 	rc = __smc_buf_create(smc, is_smcd, true);
 	if (rc && smc->conn.sndbuf_desc) {
 		down_write(&smc->conn.lgr->sndbufs_lock);
-		list_del(&smc->conn.sndbuf_desc->list);
+		smc_lgr_buf_list_del(smc->conn.lgr, false,
+				     smc->conn.sndbuf_desc);
 		up_write(&smc->conn.lgr->sndbufs_lock);
 		smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
 		smc->conn.sndbuf_desc = NULL;

net/smc/smc_core.h

@@ -281,6 +281,8 @@ struct smc_link_group {
 	struct rw_semaphore	sndbufs_lock;	/* protects tx buffers */
 	struct list_head	rmbs[SMC_RMBE_SIZES];	/* rx buffers */
 	struct rw_semaphore	rmbs_lock;	/* protects rx buffers */
+	u64			alloc_sndbufs;	/* stats of tx buffers */
+	u64			alloc_rmbs;	/* stats of rx buffers */
 
 	u8			id[SMC_LGR_ID_SIZE];	/* unique lgr id */
 	struct delayed_work	free_work;	/* delayed freeing of an lgr */

net/smc/smc_stats.c

@@ -218,6 +218,12 @@ static int smc_nl_fill_stats_tech_data(struct sk_buff *skb,
 			      smc_tech->tx_bytes,
 			      SMC_NLA_STATS_PAD))
 		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_STATS_T_RX_RMB_USAGE,
+			 smc_tech->rx_rmbuse))
+		goto errattr;
+	if (nla_put_uint(skb, SMC_NLA_STATS_T_TX_RMB_USAGE,
+			 smc_tech->tx_rmbuse))
+		goto errattr;
 	if (nla_put_u64_64bit(skb, SMC_NLA_STATS_T_RX_CNT,
 			      smc_tech->rx_cnt,
 			      SMC_NLA_STATS_PAD))

net/smc/smc_stats.h

@@ -79,6 +79,8 @@ struct smc_stats_tech {
 	u64			tx_bytes;
 	u64			rx_cnt;
 	u64			tx_cnt;
+	u64			rx_rmbuse;
+	u64			tx_rmbuse;
 };
 
 struct smc_stats {
@@ -135,38 +137,46 @@ do { \
 } \
 while (0)
 
-#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _len) \
+#define SMC_STAT_RMB_SIZE_SUB(_smc_stats, _tech, k, _is_add, _len) \
 do { \
+	typeof(_smc_stats) stats = (_smc_stats); \
+	typeof(_is_add) is_a = (_is_add); \
 	typeof(_len) _l = (_len); \
 	typeof(_tech) t = (_tech); \
 	int _pos; \
 	int m = SMC_BUF_MAX - 1; \
 	if (_l <= 0) \
 		break; \
-	_pos = fls((_l - 1) >> 13); \
-	_pos = (_pos <= m) ? _pos : m; \
-	this_cpu_inc((*(_smc_stats)).smc[t].k ## _rmbsize.buf[_pos]); \
+	if (is_a) { \
+		_pos = fls((_l - 1) >> 13); \
+		_pos = (_pos <= m) ? _pos : m; \
+		this_cpu_inc((*stats).smc[t].k ## _rmbsize.buf[_pos]); \
+		this_cpu_add((*stats).smc[t].k ## _rmbuse, _l); \
+	} else { \
+		this_cpu_sub((*stats).smc[t].k ## _rmbuse, _l); \
+	} \
 } \
 while (0)
 
 #define SMC_STAT_RMB_SUB(_smc_stats, type, t, key) \
 	this_cpu_inc((*(_smc_stats)).smc[t].rmb ## _ ## key.type ## _cnt)
 
-#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _len) \
+#define SMC_STAT_RMB_SIZE(_smc, _is_smcd, _is_rx, _is_add, _len) \
 do { \
 	struct net *_net = sock_net(&(_smc)->sk); \
 	struct smc_stats __percpu *_smc_stats = _net->smc.smc_stats; \
+	typeof(_is_add) is_add = (_is_add); \
 	typeof(_is_smcd) is_d = (_is_smcd); \
 	typeof(_is_rx) is_r = (_is_rx); \
 	typeof(_len) l = (_len); \
 	if ((is_d) && (is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, rx, is_add, l); \
 	if ((is_d) && !(is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_D, tx, is_add, l); \
 	if (!(is_d) && (is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, rx, is_add, l); \
 	if (!(is_d) && !(is_r)) \
-		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, l); \
+		SMC_STAT_RMB_SIZE_SUB(_smc_stats, SMC_TYPE_R, tx, is_add, l); \
 } \
 while (0)