summary refs log tree commit diff
path: root/net/ipv4
diff options
context:
space:
mode:
authorIdo Schimmel <idosch@OSS.NVIDIA.COM>2021-05-17 21:15:18 +0300
committerDavid S. Miller <davem@davemloft.net>2021-05-18 13:27:32 -0700
commitce5c9c20d364f156c885efed8c71fca2945db00f (patch)
treebb4858afb789ab04d7330dc3bff07f999814bbff /net/ipv4
parent2e68ea92684181412b73979baf1af7d04619c52c (diff)
downloadlinux-ce5c9c20d364f156c885efed8c71fca2945db00f.tar.gz
ipv4: Add a sysctl to control multipath hash fields
A subsequent patch will add a new multipath hash policy where the packet
fields used for multipath hash calculation are determined by user space.
This patch adds a sysctl that allows user space to set these fields.

The packet fields are represented using a bitmask and are common between
IPv4 and IPv6 to allow user space to use the same numbering across both
protocols. For example, to hash based on standard 5-tuple:

 # sysctl -w net.ipv4.fib_multipath_hash_fields=0x0037
 net.ipv4.fib_multipath_hash_fields = 0x0037

The kernel rejects unknown fields, for example:

 # sysctl -w net.ipv4.fib_multipath_hash_fields=0x1000
 sysctl: setting key "net.ipv4.fib_multipath_hash_fields": Invalid argument

More fields can be added in the future, if needed.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/fib_frontend.c6
-rw-r--r--net/ipv4/sysctl_net_ipv4.c12
2 files changed, 18 insertions, 0 deletions
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index bfb345c88271..af8814a11378 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1514,6 +1514,12 @@ static int __net_init ip_fib_net_init(struct net *net)
 	if (err)
 		return err;
 
+#ifdef CONFIG_IP_ROUTE_MULTIPATH
+	/* Default to 3-tuple */
+	net->ipv4.sysctl_fib_multipath_hash_fields =
+		FIB_MULTIPATH_HASH_FIELD_DEFAULT_MASK;
+#endif
+
 	/* Avoid false sharing : Use at least a full cache line */
 	size = max_t(size_t, size, L1_CACHE_BYTES);
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index a62934b9f15a..45bab3733621 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -19,6 +19,7 @@
 #include <net/snmp.h>
 #include <net/icmp.h>
 #include <net/ip.h>
+#include <net/ip_fib.h>
 #include <net/route.h>
 #include <net/tcp.h>
 #include <net/udp.h>
@@ -48,6 +49,8 @@ static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
 static int one_day_secs = 24 * 3600;
+static u32 fib_multipath_hash_fields_all_mask __maybe_unused =
+	FIB_MULTIPATH_HASH_FIELD_ALL_MASK;
 
 /* obsolete */
 static int sysctl_tcp_low_latency __read_mostly;
@@ -1052,6 +1055,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
+	{
+		.procname	= "fib_multipath_hash_fields",
+		.data		= &init_net.ipv4.sysctl_fib_multipath_hash_fields,
+		.maxlen		= sizeof(u32),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= &fib_multipath_hash_fields_all_mask,
+	},
 #endif
 	{
 		.procname	= "ip_unprivileged_port_start",