For systems that use CPU isolation (via nohz_full), creating or destroying
a socket with SO_TIMESTAMP, SO_TIMESTAMPNS or SO_TIMESTAMPING with flag
SOF_TIMESTAMPING_RX_SOFTWARE will cause a static key to be enabled/disabled.
This in turn causes undesired IPIs to isolated CPUs.

So enable the static key unconditionally, if CPU isolation is enabled,
thus avoiding the IPIs.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

---
v2: mention SOF_TIMESTAMPING_OPT_TX_SWHW in the commit log (Willem de Bruijn / Paolo Abeni)
v3: SOF_TIMESTAMPING_OPT_TX_SWHW is irrelevant (Willem de Bruijn)
v4: additional changelog improvements (Willem de Bruijn)
v5: late initcall not necessary, can use subsys initcall (Willem de Bruijn)

diff --git a/net/core/dev.c b/net/core/dev.c
index 0d548431f3fa..7832793b2980 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -153,6 +153,7 @@
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
 #include <net/netdev_rx_queue.h>
+#include <linux/sched/isolation.h>
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -11596,6 +11597,10 @@ static int __init net_dev_init(void)
 				       NULL, dev_cpu_dead);
 	WARN_ON(rc < 0);
 	rc = 0;
+
+	/* avoid static key IPIs to isolated CPUs */
+	if (housekeeping_enabled(HK_TYPE_MISC))
+		net_enable_timestamp();
 out:
 	return rc;
 }

On Thu, 7 Mar 2024 14:14:03 -0300 Marcelo Tosatti wrote:
> net/core/dev.c: enable timestamp static key if CPU isolation is configured

Doesn't apply to net-next, please respin.

When you do, one more nit: please use net: as the prefix,
instead of net/code/dev.c. No need to state the entire file path.
-- 
pw-bot: cr

Marcelo Tosatti wrote:
> 
> For systems that use CPU isolation (via nohz_full), creating or destroying
> a socket with SO_TIMESTAMP, SO_TIMESTAMPNS or SO_TIMESTAMPING with flag
> SOF_TIMESTAMPING_RX_SOFTWARE will cause a static key to be enabled/disabled.
> This in turn causes undesired IPIs to isolated CPUs.
> 
> So enable the static key unconditionally, if CPU isolation is enabled,
> thus avoiding the IPIs.
> 
> Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Reviewed-by: Willem de Bruijn <willemb@google.com>