Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "So here's my next branch for powerpc.  A bit late as I was on vacation
  last week.  It's mostly the same stuff that was in next already, I
  just added two patches today which are the wiring up of lockref for
  powerpc, which for some reason fell through the cracks last time and
  is trivial.

  The highlights are, in addition to a bunch of bug fixes:

   - Reworked Machine Check handling on kernels running without a
     hypervisor (or acting as a hypervisor).  Provides hooks to handle
     some errors in real mode such as TLB errors, handle SLB errors,
     etc...

   - Support for retrieving memory error information from the service
     processor on IBM servers running without a hypervisor and routing
     them to the memory poison infrastructure.

   - _PAGE_NUMA support on server processors

   - 32-bit BookE relocatable kernel support

   - FSL e6500 hardware tablewalk support

   - A bunch of new/revived board support

   - FSL e6500 deeper idle states and altivec powerdown support

  You'll notice a generic mm change here, it has been acked by the
  relevant authorities and is a pre-req for our _PAGE_NUMA support"

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (121 commits)
  powerpc: Implement arch_spin_is_locked() using arch_spin_value_unlocked()
  powerpc: Add support for the optimised lockref implementation
  powerpc/powernv: Call OPAL sync before kexec'ing
  powerpc/eeh: Escalate error on non-existing PE
  powerpc/eeh: Handle multiple EEH errors
  powerpc: Fix transactional FP/VMX/VSX unavailable handlers
  powerpc: Don't corrupt transactional state when using FP/VMX in kernel
  powerpc: Reclaim two unused thread_info flag bits
  powerpc: Fix races with irq_work
  Move precessing of MCE queued event out from syscall exit path.
  pseries/cpuidle: Remove redundant call to ppc64_runlatch_off() in cpu idle routines
  powerpc: Make add_system_ram_resources() __init
  powerpc: add SATA_MV to ppc64_defconfig
  powerpc/powernv: Increase candidate fw image size
  powerpc: Add debug checks to catch invalid cpu-to-node mappings
  powerpc: Fix the setup of CPU-to-Node mappings during CPU online
  powerpc/iommu: Don't detach device without IOMMU group
  powerpc/eeh: Hotplug improvement
  powerpc/eeh: Call opal_pci_reinit() on powernv for restoring config space
  powerpc/eeh: Add restore_config operation
  ...

1 files changed, 91 insertions, 5 deletions

diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 5a944f25e94ff..86a63de072c61 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -31,6 +31,8 @@
 #include <asm/sparsemem.h>
 #include <asm/prom.h>
 #include <asm/smp.h>
+#include <asm/cputhreads.h>
+#include <asm/topology.h>
 #include <asm/firmware.h>
 #include <asm/paca.h>
 #include <asm/hvcall.h>
@@ -152,9 +154,22 @@ static void __init get_node_active_region(unsigned long pfn,
 	}
 }
 
-static void map_cpu_to_node(int cpu, int node)
+static void reset_numa_cpu_lookup_table(void)
+{
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		numa_cpu_lookup_table[cpu] = -1;
+}
+
+static void update_numa_cpu_lookup_table(unsigned int cpu, int node)
 {
 	numa_cpu_lookup_table[cpu] = node;
+}
+
+static void map_cpu_to_node(int cpu, int node)
+{
+	update_numa_cpu_lookup_table(cpu, node);
 
 	dbg("adding cpu %d to node %d\n", cpu, node);
 
@@ -522,11 +537,24 @@ static int of_drconf_to_nid_single(struct of_drconf_cell *drmem,
  */
 static int numa_setup_cpu(unsigned long lcpu)
 {
-	int nid = 0;
-	struct device_node *cpu = of_get_cpu_node(lcpu, NULL);
+	int nid;
+	struct device_node *cpu;
+
+	/*
+	 * If a valid cpu-to-node mapping is already available, use it
+	 * directly instead of querying the firmware, since it represents
+	 * the most recent mapping notified to us by the platform (eg: VPHN).
+	 */
+	if ((nid = numa_cpu_lookup_table[lcpu]) >= 0) {
+		map_cpu_to_node(lcpu, nid);
+		return nid;
+	}
+
+	cpu = of_get_cpu_node(lcpu, NULL);
 
 	if (!cpu) {
 		WARN_ON(1);
+		nid = 0;
 		goto out;
 	}
 
@@ -542,16 +570,38 @@ out:
 	return nid;
 }
 
+static void verify_cpu_node_mapping(int cpu, int node)
+{
+	int base, sibling, i;
+
+	/* Verify that all the threads in the core belong to the same node */
+	base = cpu_first_thread_sibling(cpu);
+
+	for (i = 0; i < threads_per_core; i++) {
+		sibling = base + i;
+
+		if (sibling == cpu || cpu_is_offline(sibling))
+			continue;
+
+		if (cpu_to_node(sibling) != node) {
+			WARN(1, "CPU thread siblings %d and %d don't belong"
+				" to the same node!\n", cpu, sibling);
+			break;
+		}
+	}
+}
+
 static int cpu_numa_callback(struct notifier_block *nfb, unsigned long action,
 			     void *hcpu)
 {
 	unsigned long lcpu = (unsigned long)hcpu;
-	int ret = NOTIFY_DONE;
+	int ret = NOTIFY_DONE, nid;
 
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		numa_setup_cpu(lcpu);
+		nid = numa_setup_cpu(lcpu);
+		verify_cpu_node_mapping((int)lcpu, nid);
 		ret = NOTIFY_OK;
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1069,6 +1119,7 @@ void __init do_init_bootmem(void)
 	 */
 	setup_node_to_cpumask_map();
 
+	reset_numa_cpu_lookup_table();
 	register_cpu_notifier(&ppc64_numa_nb);
 	cpu_numa_callback(&ppc64_numa_nb, CPU_UP_PREPARE,
 			  (void *)(unsigned long)boot_cpuid);
@@ -1447,6 +1498,33 @@ static int update_cpu_topology(void *data)
 	return 0;
 }
 
+static int update_lookup_table(void *data)
+{
+	struct topology_update_data *update;
+
+	if (!data)
+		return -EINVAL;
+
+	/*
+	 * Upon topology update, the numa-cpu lookup table needs to be updated
+	 * for all threads in the core, including offline CPUs, to ensure that
+	 * future hotplug operations respect the cpu-to-node associativity
+	 * properly.
+	 */
+	for (update = data; update; update = update->next) {
+		int nid, base, j;
+
+		nid = update->new_nid;
+		base = cpu_first_thread_sibling(update->cpu);
+
+		for (j = 0; j < threads_per_core; j++) {
+			update_numa_cpu_lookup_table(base + j, nid);
+		}
+	}
+
+	return 0;
+}
+
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
@@ -1515,6 +1593,14 @@ int arch_update_cpu_topology(void)
 
 	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
+	/*
+	 * Update the numa-cpu lookup table with the new mappings, even for
+	 * offline CPUs. It is best to perform this update from the stop-
+	 * machine context.
+	 */
+	stop_machine(update_lookup_table, &updates[0],
+					cpumask_of(raw_smp_processor_id()));
+
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		unregister_cpu_under_node(ud->cpu, ud->old_nid);
 		register_cpu_under_node(ud->cpu, ud->new_nid);