| Message ID | 1471776902-3151-1-git-send-email-ppaidipe@linux.vnet.ibm.com |
|---|---|
| State | Accepted |
| Headers | show |
ppaidipe@linux.vnet.ibm.com writes: > From: Pridhiviraj Paidipeddi <ppaidipe@linux.vnet.ibm.com> > > Currently we are getting request to queue occ load opal message when host services > got load occ request from FSP. This request we got before initializing opal messaging > due to which we are failed to get list node from msg_free_list list. > > [3204300512,3] opalmsg: No available node in the free list, allocating > > This patch fixes this issue by initializing opal messaging(opal_init_msg) before > platform.init, as in platform.init we are loading host services lid and getting > occ load request command from FSP. So when opal_init_msg initializes we will > be initialized msg_free_list with an empty list. Thanks! Works and looks safe. Merged to master as of 564ed2a8caadc6b4e858bc7933131ed27ba9f13a I think this clears us up to eliminate the allocation of new messages and instead throw an error - as continually allocating them has led us down a bad path in the past.
diff --git a/core/init.c b/core/init.c index 86bcdea..decad2b 100644 --- a/core/init.c +++ b/core/init.c @@ -746,6 +746,13 @@ void __noreturn main_cpu_entry(const void *fdt, u32 master_cpu) /* Register routine to dispatch and read sensors */ sensor_init(); + /* + * Initialize the opal messaging before platform.init as we are + * getting request to queue occ load opal message when host services + * got load occ request from FSP + */ + opal_init_msg(); + /* * We have initialized the basic HW, we can now call into the * platform to perform subsequent inits, such as establishing @@ -773,9 +780,6 @@ void __noreturn main_cpu_entry(const void *fdt, u32 master_cpu) /* NX init */ nx_init(); - /* Initialize the opal messaging */ - opal_init_msg(); - /* Probe IO hubs */ probe_p7ioc();