RDS: bind hash table size increase, add per-bucket rw lock

The single global rw lock in bind hash table is replaced with
a per-bucket lock. The size of the hash table is increased
from 1024 to 8192.

Orabug: 18071861

Tested-by: Michael Nowak <michael.nowak@oracle.com>
Signed-off-by: Bang Nguyen <bang.nguyen@oracle.com>
Signed-off-by: Mukesh Kacker <mukesh.kacker@oracle.com>
Acked-by: Venkat Venkatsubra <venkat.x.venkatsubra@oracle.com>
(cherry picked from commit 4fc6d8f3870b5ac39415f475b2a5817a5a89d48e)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index ac41334f57c8becb8e15a3a78693fba31aa53486..7f7b2baa8d3ef455aa510823f5a9e62d7be537ca 100644 (file)
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -754,6 +754,7 @@ static void rds_exit(void)
        rds_page_exit();
        rds_info_deregister_func(RDS_INFO_SOCKETS, rds_sock_info);
        rds_info_deregister_func(RDS_INFO_RECV_MESSAGES, rds_sock_inc_info);
+
 }
 module_exit(rds_exit);
 
@@ -761,6 +762,8 @@ static int rds_init(void)
 {
        int ret;
 
+       rds_bind_lock_init();
+
        ret = rds_conn_init();
        if (ret)
                goto out;

diff --git a/net/rds/bind.c b/net/rds/bind.c
index 02975163bd0652816fe46bb1050e4218e6b3280b..cbbabb3a82577516434be0135f70d091a3e28ba6 100644 (file)
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -37,11 +37,15 @@
 #include <linux/jhash.h>
 #include "rds.h"
 
-#define BIND_HASH_SIZE 1024
-static struct hlist_head bind_hash_table[BIND_HASH_SIZE];
-static DEFINE_RWLOCK(rds_bind_lock);
+struct bind_bucket {
+       rwlock_t                lock;
+       struct hlist_head       head;
+};
 
-static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
+#define BIND_HASH_SIZE 8192
+static struct bind_bucket bind_hash_table[BIND_HASH_SIZE];
+
+static struct bind_bucket *hash_to_bucket(__be32 addr, __be16 port)
 {
        return bind_hash_table + (jhash_2words((u32)addr, (u32)port, 0) &
                                  (BIND_HASH_SIZE - 1));
@@ -50,11 +54,12 @@ static struct hlist_head *hash_to_bucket(__be32 addr, __be16 port)
 /*
  * must hold either read or write lock (write lock for insert != NULL)
  */
-static struct rds_sock *rds_bind_lookup(__be32 addr, __be16 port,
+static struct rds_sock *rds_bind_lookup(struct bind_bucket *bucket,
+                                        __be32 addr, __be16 port,
                                        struct rds_sock *insert)
 {
        struct rds_sock *rs;
-       struct hlist_head *head = hash_to_bucket(addr, port);
+       struct hlist_head *head = &bucket->head;
        u64 cmp;
        u64 needle = ((u64)be32_to_cpu(addr) << 32) | be16_to_cpu(port);
 
@@ -92,10 +97,11 @@ struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
 {
        struct rds_sock *rs;
        unsigned long flags;
+       struct bind_bucket *bucket = hash_to_bucket(addr, port);
 
-       read_lock_irqsave(&rds_bind_lock, flags);
-       rs = rds_bind_lookup(addr, port, NULL);
-       read_unlock_irqrestore(&rds_bind_lock, flags);
+       read_lock_irqsave(&bucket->lock, flags);
+       rs = rds_bind_lookup(bucket, addr, port, NULL);
+       read_unlock_irqrestore(&bucket->lock, flags);
 
        if (rs && sock_flag(rds_rs_to_sk(rs), SOCK_DEAD)) {
                rds_sock_put(rs);
@@ -114,6 +120,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
        unsigned long flags;
        int ret = -EADDRINUSE;
        u16 rover, last;
+       struct bind_bucket *bucket;
 
        if (*port != 0) {
                rover = be16_to_cpu(*port);
@@ -123,13 +130,16 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
                last = rover - 1;
        }
 
-       write_lock_irqsave(&rds_bind_lock, flags);
-
        do {
                struct rds_sock *rrs;
                if (rover == 0)
                        rover++;
-               rrs = rds_bind_lookup(addr, cpu_to_be16(rover), rs);
+
+               bucket = hash_to_bucket(addr, cpu_to_be16(rover));
+
+               write_lock_irqsave(&bucket->lock, flags);
+               rrs = rds_bind_lookup(bucket, addr, cpu_to_be16(rover), rs);
+               write_unlock_irqrestore(&bucket->lock, flags);
 
                if (!rrs) {
                        *port = rs->rs_bound_port;
@@ -141,16 +151,16 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
                        rds_sock_put(rrs);
        } while (rover++ != last);
 
-       write_unlock_irqrestore(&rds_bind_lock, flags);
-
        return ret;
 }
 
 void rds_remove_bound(struct rds_sock *rs)
 {
        unsigned long flags;
+       struct bind_bucket *bucket =
+               hash_to_bucket(rs->rs_bound_addr, rs->rs_bound_port);
 
-       write_lock_irqsave(&rds_bind_lock, flags);
+       write_lock_irqsave(&bucket->lock, flags);
 
        if (rs->rs_bound_addr) {
                rdsdebug("rs %p unbinding from %pI4:%d\n",
@@ -162,7 +172,7 @@ void rds_remove_bound(struct rds_sock *rs)
                rs->rs_bound_addr = 0;
        }
 
-       write_unlock_irqrestore(&rds_bind_lock, flags);
+       write_unlock_irqrestore(&bucket->lock, flags);
 }
 
 int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
@@ -204,3 +214,10 @@ out:
        release_sock(sk);
        return ret;
 }
+
+void rds_bind_lock_init(void)
+{
+       int i;
+       for (i = 0; i < BIND_HASH_SIZE; i++)
+               rwlock_init(&bind_hash_table[i].lock);
+}

diff --git a/net/rds/rds.h b/net/rds/rds.h
index 4e747773f449538b6e1f1635858f07d5cefbc099..4c764a75a742aabb6e32561f04f2842ba137ac52 100644 (file)
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -645,6 +645,7 @@ void debug_sock_put(struct sock *sock);
 int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
 void rds_remove_bound(struct rds_sock *rs);
 struct rds_sock *rds_find_bound(__be32 addr, __be16 port);
+void rds_bind_lock_init(void);
 
 /* cong.c */
 int rds_cong_get_maps(struct rds_connection *conn);