[PATCH v5 4/5] powerpc/numa: Early request for home node associativity

[Srikar Dronamraju]

Currently the kernel detects if its running on a shared lpar platform
and requests home node associativity before the scheduler sched_domains
are setup. However between the time NUMA setup is initialized and the
request for home node associativity, workqueue initializes its per node
cpumask. The per node workqueue possible cpumask may turn invalid
after home node associativity resulting in weird situations like
workqueue possible cpumask being a subset of workqueue online cpumask.

This can be fixed by requesting home node associativity earlier just
before NUMA setup. However at the NUMA setup time, kernel may not be in
a position to detect if its running on a shared lpar platform. So
request for home node associativity and if the request fails, fallback
on the device tree property.

Signed-off-by: Srikar Dronamraju <srikar at linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe at ellerman.id.au>
Cc: Nicholas Piggin <npiggin at gmail.com>
Cc: Nathan Lynch <nathanl at linux.ibm.com>
Cc: linuxppc-dev at lists.ozlabs.org
Cc: Abdul Haleem <abdhalee at linux.vnet.ibm.com>
Cc: Satheesh Rajendran <sathnaga at linux.vnet.ibm.com>
Reported-by: Abdul Haleem <abdhalee at linux.vnet.ibm.com>
Reviewed-by: Nathan Lynch <nathanl at linux.ibm.com>
---
Changelog (v2->v3):
- Handled comments from Nathan Lynch
  * Use first thread of the core for cpu-to-node map.
  * get hardware-id in numa_setup_cpu

Changelog (v1->v2):
- Handled comments from Nathan Lynch
  * Dont depend on pacas to be setup for the hwid


 arch/powerpc/mm/numa.c | 45 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 40 insertions(+), 5 deletions(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 63ec0c3c817f..f837a0e725bc 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -461,13 +461,27 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return nid;
 }
 
+static int vphn_get_nid(long hwid)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	long rc;
+
+	rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
+	if (rc == H_SUCCESS)
+		return associativity_to_nid(associativity);
+
+	return NUMA_NO_NODE;
+}
+
 /*
  * Figure out to which domain a cpu belongs and stick it there.
+ * cpu_to_phys_id is only valid between smp_setup_cpu_maps() and
+ * smp_setup_pacas(). If called outside this window, set get_hwid to true.
  * Return the id of the domain used.
  */
-static int numa_setup_cpu(unsigned long lcpu)
+static int numa_setup_cpu(unsigned long lcpu, bool get_hwid)
 {
-	struct device_node *cpu;
+	struct device_node *cpu = NULL;
 	int fcpu = cpu_first_thread_sibling(lcpu);
 	int nid = NUMA_NO_NODE;
 
@@ -485,6 +499,27 @@ static int numa_setup_cpu(unsigned long lcpu)
 		return nid;
 	}
 
+	/*
+	 * On a shared lpar, device tree will not have node associativity.
+	 * At this time lppaca, or its __old_status field may not be
+	 * updated. Hence kernel cannot detect if its on a shared lpar. So
+	 * request an explicit associativity irrespective of whether the
+	 * lpar is shared or dedicated. Use the device tree property as a
+	 * fallback.
+	 */
+	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+		long hwid;
+
+		if (get_hwid)
+			hwid = get_hard_smp_processor_id(lcpu);
+		else
+			hwid = cpu_to_phys_id[lcpu];
+		nid = vphn_get_nid(hwid);
+	}
+
+	if (nid != NUMA_NO_NODE)
+		goto out_present;
+
 	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
@@ -496,6 +531,7 @@ static int numa_setup_cpu(unsigned long lcpu)
 	}
 
 	nid = of_node_to_nid_single(cpu);
+	of_node_put(cpu);
 
 out_present:
 	if (nid < 0 || !node_possible(nid))
@@ -515,7 +551,6 @@ static int numa_setup_cpu(unsigned long lcpu)
 	}
 
 	map_cpu_to_node(lcpu, nid);
-	of_node_put(cpu);
 out:
 	return nid;
 }
@@ -546,7 +581,7 @@ static int ppc_numa_cpu_prepare(unsigned int cpu)
 {
 	int nid;
 
-	nid = numa_setup_cpu(cpu);
+	nid = numa_setup_cpu(cpu, true);
 	verify_cpu_node_mapping(cpu, nid);
 	return 0;
 }
@@ -893,7 +928,7 @@ void __init mem_topology_setup(void)
 	reset_numa_cpu_lookup_table();
 
 	for_each_present_cpu(cpu)
-		numa_setup_cpu(cpu);
+		numa_setup_cpu(cpu, false);
 }
 
 void __init initmem_init(void)
-- 
2.18.1