From mboxrd@z Thu Jan 1 00:00:00 1970 From: Valentin Schneider Date: Wed, 17 Mar 2021 20:56:12 +0000 Subject: Re: [PATCH 0/1] sched/topology: NUMA distance deduplication Message-Id: <87wnu5pkib.mognet@arm.com> List-Id: References: <255d6b5d-194e-eb0e-ecdd-97477a534441@physik.fu-berlin.de> <8735wtr2ro.mognet@arm.com> <87zgz1pmx4.mognet@arm.com> In-Reply-To: <87zgz1pmx4.mognet@arm.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: John Paul Adrian Glaubitz Cc: "Peter Zijlstra (Intel)" , Linux Kernel Mailing List , "linux-ia64@vger.kernel.org" , Sergei Trofimovich , debian-ia64 On 17/03/21 20:04, Valentin Schneider wrote: > Technically it *is* coping with it, it's just dumping the entire NUMA > distance matrix in the process... Let me see if I can't figure out why your > system doesn't end up with nr_node_ids=1. > Does the below a) compile b) do anything? >From what I could gather, nothing actually tickles the possible map for ia64. The standard pattern seems to be node_possible_map = numa_nodes_parsed; but here at a quick glance it seems it's online or nothing, so that's what I went for. HTH. --- diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c index a5636524af76..e2af6b172200 100644 --- a/arch/ia64/kernel/acpi.c +++ b/arch/ia64/kernel/acpi.c @@ -446,7 +446,8 @@ void __init acpi_numa_fixup(void) if (srat_num_cpus = 0) { node_set_online(0); node_cpuid[0].phys_id = hard_smp_processor_id(); - return; + slit_distance(0, 0) = LOCAL_DISTANCE; + goto out; } /* @@ -489,7 +490,7 @@ void __init acpi_numa_fixup(void) for (j = 0; j < MAX_NUMNODES; j++) slit_distance(i, j) = i = j ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return; + goto out; } memset(numa_slit, -1, sizeof(numa_slit)); @@ -514,6 +515,8 @@ void __init acpi_numa_fixup(void) printk("\n"); } #endif +out: + node_possible_map = node_online_map; } #endif /* CONFIG_ACPI_NUMA */