net: Cache hash and flow_id to avoid recalculation

get_rps_cpu() can cache flow_id and hash as both are required by
set_rps_cpu() instead of recalculating them twice.

Signed-off-by: Krishna Kumar <krikku@gmail.com>
Link: https://patch.msgid.link/20250825031005.3674864-3-krikku@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/core/dev.c b/net/core/dev.c
index fbf0894c55d0ba36b69e31f8af50cb812cac56b5..1d1650d9ecff4a863b3449bf88d7201d72ec8e33 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4881,7 +4881,8 @@ static bool rps_flow_is_active(struct rps_dev_flow *rflow,
 
 static struct rps_dev_flow *
 set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
-           struct rps_dev_flow *rflow, u16 next_cpu)
+           struct rps_dev_flow *rflow, u16 next_cpu, u32 hash,
+           u32 flow_id)
 {
        if (next_cpu < nr_cpu_ids) {
                u32 head;
@@ -4892,8 +4893,6 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
                struct rps_dev_flow *tmp_rflow;
                unsigned int tmp_cpu;
                u16 rxq_index;
-               u32 flow_id;
-               u32 hash;
                int rc;
 
                /* Should we steer this flow to a different hardware queue? */
@@ -4909,9 +4908,6 @@ set_rps_cpu(struct net_device *dev, struct sk_buff *skb,
                if (!flow_table)
                        goto out;
 
-               hash = skb_get_hash(skb);
-               flow_id = rfs_slot(hash, flow_table);
-
                tmp_rflow = &flow_table->flows[flow_id];
                tmp_cpu = READ_ONCE(tmp_rflow->cpu);
 
@@ -4959,6 +4955,7 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
        struct rps_dev_flow_table *flow_table;
        struct rps_map *map;
        int cpu = -1;
+       u32 flow_id;
        u32 tcpu;
        u32 hash;
 
@@ -5005,7 +5002,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
                /* OK, now we know there is a match,
                 * we can look at the local (per receive queue) flow table
                 */
-               rflow = &flow_table->flows[rfs_slot(hash, flow_table)];
+               flow_id = rfs_slot(hash, flow_table);
+               rflow = &flow_table->flows[flow_id];
                tcpu = rflow->cpu;
 
                /*
@@ -5024,7 +5022,8 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
                     ((int)(READ_ONCE(per_cpu(softnet_data, tcpu).input_queue_head) -
                      rflow->last_qtail)) >= 0)) {
                        tcpu = next_cpu;
-                       rflow = set_rps_cpu(dev, skb, rflow, next_cpu);
+                       rflow = set_rps_cpu(dev, skb, rflow, next_cpu, hash,
+                                           flow_id);
                }
 
                if (tcpu < nr_cpu_ids && cpu_online(tcpu)) {