Patch "rfs: annotate lockless accesses to RFS sock flow table" has been added to the 5.15-stable tree

[Sasha Levin <sashal@xxxxxxxxxx>]

This is a note to let you know that I've just added the patch titled

    rfs: annotate lockless accesses to RFS sock flow table

to the 5.15-stable tree which can be found at:
    http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
     rfs-annotate-lockless-accesses-to-rfs-sock-flow-tabl.patch
and it can be found in the queue-5.15 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.



commit 412ac7f82e21790affb8bc2bf15b9fa500c09ae3
Author: Eric Dumazet <edumazet@xxxxxxxxxx>
Date:   Tue Jun 6 07:41:15 2023 +0000

    rfs: annotate lockless accesses to RFS sock flow table
    
    [ Upstream commit 5c3b74a92aa285a3df722bf6329ba7ccf70346d6 ]
    
    Add READ_ONCE()/WRITE_ONCE() on accesses to the sock flow table.
    
    This also prevents a (smart ?) compiler to remove the condition in:
    
    if (table->ents[index] != newval)
            table->ents[index] = newval;
    
    We need the condition to avoid dirtying a shared cache line.
    
    Fixes: fec5e652e58f ("rfs: Receive Flow Steering")
    Signed-off-by: Eric Dumazet <edumazet@xxxxxxxxxx>
    Reviewed-by: Simon Horman <simon.horman@xxxxxxxxxxxx>
    Reviewed-by: Kuniyuki Iwashima <kuniyu@xxxxxxxxxx>
    Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
    Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5b6c38f748076..823f5ed4ec0cc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -737,8 +737,11 @@ static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
 		/* We only give a hint, preemption can change CPU under us */
 		val |= raw_smp_processor_id();
 
-		if (table->ents[index] != val)
-			table->ents[index] = val;
+		/* The following WRITE_ONCE() is paired with the READ_ONCE()
+		 * here, and another one in get_rps_cpu().
+		 */
+		if (READ_ONCE(table->ents[index]) != val)
+			WRITE_ONCE(table->ents[index], val);
 	}
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 56a3bff7249d4..24d711fe376a3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4458,8 +4458,10 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb,
 		u32 next_cpu;
 		u32 ident;
 
-		/* First check into global flow table if there is a match */
-		ident = sock_flow_table->ents[hash & sock_flow_table->mask];
+		/* First check into global flow table if there is a match.
+		 * This READ_ONCE() pairs with WRITE_ONCE() from rps_record_sock_flow().
+		 */
+		ident = READ_ONCE(sock_flow_table->ents[hash & sock_flow_table->mask]);
 		if ((ident ^ hash) & ~rps_cpu_mask)
 			goto try_rps;