net: Fix rcu_tasks stall in threaded busypoll

I was debugging a NIC driver when I noticed that when I enable
threaded busypoll, bpftrace hangs when starting up. dmesg showed:

  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 10658 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 40793 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 131273 jiffies old.
  rcu_tasks_wait_gp: rcu_tasks grace period number 85 (since boot) is 402058 jiffies old.
  INFO: rcu_tasks detected stalls on tasks:
  00000000769f52cd: .N nvcsw: 2/2 holdout: 1 idle_cpu: -1/64
  task:napi/eth2-8265  state:R  running task     stack:0     pid:48300 tgid:48300 ppid:2      task_flags:0x208040 flags:0x00004000
  Call Trace:
   <TASK>
   ? napi_threaded_poll_loop+0x27c/0x2c0
   ? __pfx_napi_threaded_poll+0x10/0x10
   ? napi_threaded_poll+0x26/0x80
   ? kthread+0xfa/0x240
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork+0x31/0x50
   ? __pfx_kthread+0x10/0x10
   ? ret_from_fork_asm+0x1a/0x30
   </TASK>

The cause is that in threaded busypoll, the main loop is in
napi_threaded_poll rather than napi_threaded_poll_loop, where the
latter rarely iterates more than once within its loop. For
rcu_softirq_qs_periodic inside napi_threaded_poll_loop to report its
qs state, the last_qs must be 100ms behind, and this can't happen
because napi_threaded_poll_loop rarely iterates in threaded busypoll,
and each time napi_threaded_poll_loop is called last_qs is reset to
latest jiffies.

This patch changes so that in threaded busypoll, last_qs is saved
in the outer napi_threaded_poll, and whether busy_poll_last_qs
is NULL indicates whether napi_threaded_poll_loop is called for
busypoll. This way last_qs would not reset to latest jiffies on
each invocation of napi_threaded_poll_loop.

Fixes: c18d4b190a46 ("net: Extend NAPI threaded polling to allow kthread based busy polling")
Cc: stable@vger.kernel.org
Signed-off-by: YiFei Zhu <zhuyifei@google.com>
Reviewed-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20260227221937.1060857-1-zhuyifei@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/net/core/dev.c b/net/core/dev.c
index c1a9f7fdcffa9b493d44e5b39f447f685dacd991..4af4cf2d63a47c2038ab082636f5f75f1e86e770 100644 (file)
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7794,11 +7794,12 @@ static int napi_thread_wait(struct napi_struct *napi)
        return -1;
 }
 
-static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
+static void napi_threaded_poll_loop(struct napi_struct *napi,
+                                   unsigned long *busy_poll_last_qs)
 {
+       unsigned long last_qs = busy_poll_last_qs ? *busy_poll_last_qs : jiffies;
        struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
        struct softnet_data *sd;
-       unsigned long last_qs = jiffies;
 
        for (;;) {
                bool repoll = false;
@@ -7827,12 +7828,12 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
                /* When busy poll is enabled, the old packets are not flushed in
                 * napi_complete_done. So flush them here.
                 */
-               if (busy_poll)
+               if (busy_poll_last_qs)
                        gro_flush_normal(&napi->gro, HZ >= 1000);
                local_bh_enable();
 
                /* Call cond_resched here to avoid watchdog warnings. */
-               if (repoll || busy_poll) {
+               if (repoll || busy_poll_last_qs) {
                        rcu_softirq_qs_periodic(last_qs);
                        cond_resched();
                }
@@ -7840,11 +7841,15 @@ static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
                if (!repoll)
                        break;
        }
+
+       if (busy_poll_last_qs)
+               *busy_poll_last_qs = last_qs;
 }
 
 static int napi_threaded_poll(void *data)
 {
        struct napi_struct *napi = data;
+       unsigned long last_qs = jiffies;
        bool want_busy_poll;
        bool in_busy_poll;
        unsigned long val;
@@ -7862,7 +7867,7 @@ static int napi_threaded_poll(void *data)
                        assign_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state,
                                   want_busy_poll);
 
-               napi_threaded_poll_loop(napi, want_busy_poll);
+               napi_threaded_poll_loop(napi, want_busy_poll ? &last_qs : NULL);
        }
 
        return 0;
@@ -13175,7 +13180,7 @@ static void run_backlog_napi(unsigned int cpu)
 {
        struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
 
-       napi_threaded_poll_loop(&sd->backlog, false);
+       napi_threaded_poll_loop(&sd->backlog, NULL);
 }
 
 static void backlog_napi_setup(unsigned int cpu)