[PATCH v6 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: Satheesh Rajendran <sathnaga at linux.vnet.ibm.com>
Reported-by: Abdul Haleem <abdhalee at linux.vnet.ibm.com>
---
Changelog (v5->v6):
- Handled comments from Michael Ellerman
  * hardware-id is now deciphered in vphn_get_nid
  * No need to pass extra bool

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 | 41 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 40 insertions(+), 1 deletion(-)

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 63ec0c3..ee7400f 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -461,6 +461,41 @@ static int of_drconf_to_nid_single(struct drmem_lmb *lmb)
 	return nid;
 }
 
+#ifdef CONFIG_PPC_SPLPAR
+static int vphn_get_nid(long lcpu)
+{
+	__be32 associativity[VPHN_ASSOC_BUFSIZE] = {0};
+	long rc, hwid;
+
+	/*
+	 * 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. cpu_to_phys_id is only valid between
+	 * smp_setup_cpu_maps() and smp_setup_pacas().
+	 */
+	if (firmware_has_feature(FW_FEATURE_VPHN)) {
+		if (cpu_to_phys_id)
+			hwid = cpu_to_phys_id[lcpu];
+		else
+			hwid = get_hard_smp_processor_id(lcpu);
+
+		rc = hcall_vphn(hwid, VPHN_FLAG_VCPU, associativity);
+		if (rc == H_SUCCESS)
+			return associativity_to_nid(associativity);
+	}
+
+	return NUMA_NO_NODE;
+}
+#else
+static int vphn_get_nid(long unused)
+{
+	return NUMA_NO_NODE;
+}
+#endif  /* CONFIG_PPC_SPLPAR */
+
 /*
  * Figure out to which domain a cpu belongs and stick it there.
  * Return the id of the domain used.
@@ -485,6 +520,10 @@ static int numa_setup_cpu(unsigned long lcpu)
 		return nid;
 	}
 
+	nid = vphn_get_nid(lcpu);
+	if (nid != NUMA_NO_NODE)
+		goto out_present;
+
 	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
@@ -496,6 +535,7 @@ 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 +555,6 @@ static int numa_setup_cpu(unsigned long lcpu)
 	}
 
 	map_cpu_to_node(lcpu, nid);
-	of_node_put(cpu);
 out:
 	return nid;
 }
-- 
1.8.3.1