net: Busy polling should ignore sender CPUs

This patch is a cleanup/fix for NAPI IDs following the changes that made it
so that sender_cpu and napi_id were doing a better job of sharing the same
location in the sk_buff.

One issue I found is that we weren't validating the napi_id as being valid
before we started trying to setup the busy polling.  This change corrects
that by using the MIN_NAPI_ID value that is now used in both allocating the
NAPI IDs, as well as validating them.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c0452de..3fcda9e 100644 (file)
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -35,6 +35,12 @@ struct napi_struct;
 extern unsigned int sysctl_net_busy_read __read_mostly;
 extern unsigned int sysctl_net_busy_poll __read_mostly;
 
+/*             0 - Reserved to indicate value not set
+ *     1..NR_CPUS - Reserved for sender_cpu
+ *  NR_CPUS+1..~0 - Region available for NAPI IDs
+ */
+#define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
+
 static inline bool net_busy_loop_on(void)
 {
        return sysctl_net_busy_poll;
@@ -58,10 +64,9 @@ static inline unsigned long busy_loop_end_time(void)
 
 static inline bool sk_can_busy_loop(const struct sock *sk)
 {
-       return sk->sk_ll_usec && sk->sk_napi_id && !signal_pending(current);
+       return sk->sk_ll_usec && !signal_pending(current);
 }
 
-
 static inline bool busy_loop_timeout(unsigned long end_time)
 {
        unsigned long now = busy_loop_us_clock();

diff --git a/net/core/dev.c b/net/core/dev.c
index 7869ae3..ab337bf 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5066,15 +5066,20 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
        int (*napi_poll)(struct napi_struct *napi, int budget);
        void *have_poll_lock = NULL;
        struct napi_struct *napi;
+       unsigned int napi_id;
        int rc;
 
 restart:
+       napi_id = READ_ONCE(sk->sk_napi_id);
+       if (napi_id < MIN_NAPI_ID)
+               return 0;
+
        rc = false;
        napi_poll = NULL;
 
        rcu_read_lock();
 
-       napi = napi_by_id(sk->sk_napi_id);
+       napi = napi_by_id(napi_id);
        if (!napi)
                goto out;
 
@@ -5143,10 +5148,10 @@ static void napi_hash_add(struct napi_struct *napi)
 
        spin_lock(&napi_hash_lock);
 
-       /* 0..NR_CPUS+1 range is reserved for sender_cpu use */
+       /* 0..NR_CPUS range is reserved for sender_cpu use */
        do {
-               if (unlikely(++napi_gen_id < NR_CPUS + 1))
-                       napi_gen_id = NR_CPUS + 1;
+               if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+                       napi_gen_id = MIN_NAPI_ID;
        } while (napi_by_id(napi_gen_id));
        napi->napi_id = napi_gen_id;