On 04/20/2016 01:31 AM, Ganapatrao Kulkarni wrote:

On Wed, Apr 20, 2016 at 1:11 PM, Dennis Chen [off-list ref] wrote:

quoted

On 20 April 2016 at 09:40, David Daney [off-list ref] wrote:

[...]

quoted

quoted

@@ -388,7 +389,9 @@ static int __init dummy_numa_init(void)
  void __init arm64_numa_init(void)
  {
         if (!numa_off) {
-               if (!numa_init(of_numa_init))
+               if (!acpi_disabled && !numa_init(arm64_acpi_numa_init))
+                       return;
+               if (acpi_disabled && !numa_init(of_numa_init))
                         return;
         }

On top of the latest version of the dt-based numa patch, if 'numa=off'
specified in the command line,
this function will fallback to invoke dummy_numa_init(), which give
rise the question here is, do we need to
touch any ACPI related stuff in the case? If not, then the output

no, ACPI is not fallback configuration for DT and vice versa.

quoted

message "No NUMA configuration found" followed
seems is not necessary since it's a little bit confusing in case of
numa has already been turned off explicitly.

thanks, this print can be moved out.
from function dummy_numa_init and it can be added in function arm64_numa_init
as a last line of if (!numa_off) to indicate, ACPI/DT based NUMA
configuration failed.

more appropriate would be,
pr_info("%s\n", "NUMA configuration failed or not found");

Although purely cosmetic, I agree that we need to improve the messages 
as to not confuse people.

I will rework the messages with your suggestions in mind to see if we 
can get something that is both concise and unambiguously reflects what 
the user asked for.

David.