udp: Introduce optional per-netns hash table.

The maximum hash table size is 64K due to the nature of the protocol. [0]
It's smaller than TCP, and fewer sockets can cause a performance drop.

On an EC2 c5.24xlarge instance (192 GiB memory), after running iperf3 in
different netns, creating 32Mi sockets without data transfer in the root
netns causes regression for the iperf3's connection.

  uhash_entries		sockets		length		Gbps
	    64K		      1		     1		5.69
			    1Mi		    16		5.27
			    2Mi		    32		4.90
			    4Mi		    64		4.09
			    8Mi		   128		2.96
			   16Mi		   256		2.06
			   32Mi		   512		1.12

The per-netns hash table breaks the lengthy lists into shorter ones.  It is
useful on a multi-tenant system with thousands of netns.  With smaller hash
tables, we can look up sockets faster, isolate noisy neighbours, and reduce
lock contention.

The max size of the per-netns table is 64K as well.  This is because the
possible hash range by udp_hashfn() always fits in 64K within the same
netns and we cannot make full use of the whole buckets larger than 64K.

  /* 0 < num < 64K  ->  X < hash < X + 64K */
  (num + net_hash_mix(net)) & mask;

Also, the min size is 128.  We use a bitmap to search for an available
port in udp_lib_get_port().  To keep the bitmap on the stack and not
fire the CONFIG_FRAME_WARN error at build time, we round up the table
size to 128.

The sysctl usage is the same with TCP:

  $ dmesg | cut -d ' ' -f 6- | grep "UDP hash"
  UDP hash table entries: 65536 (order: 9, 2097152 bytes, vmalloc)

  # sysctl net.ipv4.udp_hash_entries
  net.ipv4.udp_hash_entries = 65536  # can be changed by uhash_entries

  # sysctl net.ipv4.udp_child_hash_entries
  net.ipv4.udp_child_hash_entries = 0  # disabled by default

  # ip netns add test1
  # ip netns exec test1 sysctl net.ipv4.udp_hash_entries
  net.ipv4.udp_hash_entries = -65536  # share the global table

  # sysctl -w net.ipv4.udp_child_hash_entries=100
  net.ipv4.udp_child_hash_entries = 100

  # ip netns add test2
  # ip netns exec test2 sysctl net.ipv4.udp_hash_entries
  net.ipv4.udp_hash_entries = 128  # own a per-netns table with 2^n buckets

We could optimise the hash table lookup/iteration further by removing
the netns comparison for the per-netns one in the future.  Also, we
could optimise the sparse udp_hslot layout by putting it in udp_table.

[0]: https://lore.kernel.org/netdev/4ACC2815.7010101@gmail.com/

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 40 insertions, 0 deletions

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0af28cedd071..0d0cc4ef2b85 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -40,6 +40,7 @@ static int one_day_secs = 24 * 3600;
 static u32 fib_multipath_hash_fields_all_mask __maybe_unused =
 	FIB_MULTIPATH_HASH_FIELD_ALL_MASK;
 static unsigned int tcp_child_ehash_entries_max = 16 * 1024 * 1024;
+static unsigned int udp_child_hash_entries_max = UDP_HTABLE_SIZE_MAX;
 static int tcp_plb_max_rounds = 31;
 static int tcp_plb_max_cong_thresh = 256;
 
@@ -402,12 +403,36 @@ static int proc_tcp_ehash_entries(struct ctl_table *table, int write,
 	if (!net_eq(net, &init_net) && !hinfo->pernet)
 		tcp_ehash_entries *= -1;
 
+	memset(&tbl, 0, sizeof(tbl));
 	tbl.data = &tcp_ehash_entries;
 	tbl.maxlen = sizeof(int);
 
 	return proc_dointvec(&tbl, write, buffer, lenp, ppos);
 }
 
+static int proc_udp_hash_entries(struct ctl_table *table, int write,
+				 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct net *net = container_of(table->data, struct net,
+				       ipv4.sysctl_udp_child_hash_entries);
+	int udp_hash_entries;
+	struct ctl_table tbl;
+
+	udp_hash_entries = net->ipv4.udp_table->mask + 1;
+
+	/* A negative number indicates that the child netns
+	 * shares the global udp_table.
+	 */
+	if (!net_eq(net, &init_net) && net->ipv4.udp_table == &udp_table)
+		udp_hash_entries *= -1;
+
+	memset(&tbl, 0, sizeof(tbl));
+	tbl.data = &udp_hash_entries;
+	tbl.maxlen = sizeof(int);
+
+	return proc_dointvec(&tbl, write, buffer, lenp, ppos);
+}
+
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 static int proc_fib_multipath_hash_policy(struct ctl_table *table, int write,
 					  void *buffer, size_t *lenp,
@@ -1362,6 +1387,21 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra2		= &tcp_child_ehash_entries_max,
 	},
 	{
+		.procname	= "udp_hash_entries",
+		.data		= &init_net.ipv4.sysctl_udp_child_hash_entries,
+		.mode		= 0444,
+		.proc_handler	= proc_udp_hash_entries,
+	},
+	{
+		.procname	= "udp_child_hash_entries",
+		.data		= &init_net.ipv4.sysctl_udp_child_hash_entries,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= &udp_child_hash_entries_max,
+	},
+	{
 		.procname	= "udp_rmem_min",
 		.data		= &init_net.ipv4.sysctl_udp_rmem_min,
 		.maxlen		= sizeof(init_net.ipv4.sysctl_udp_rmem_min),