Merge tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

   - Removal of the NPU DMA code, used by the out-of-tree Nvidia driver,
     as well as some other functions only used by drivers that haven't
     (yet?) made it upstream.

   - A fix for a bug in our handling of hardware watchpoints (eg. perf
     record -e mem: ...) which could lead to register corruption and
     kernel crashes.

   - Enable HAVE_ARCH_HUGE_VMAP, which allows us to use large pages for
     vmalloc when using the Radix MMU.

   - A large but incremental rewrite of our exception handling code to
     use gas macros rather than multiple levels of nested CPP macros.

  And the usual small fixes, cleanups and improvements.

  Thanks to: Alastair D'Silva, Alexey Kardashevskiy, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Anton Blanchard, Arnd Bergmann,
  Athira Rajeev, Cédric Le Goater, Christian Lamparter, Christophe
  Leroy, Christophe Lombard, Christoph Hellwig, Daniel Axtens, Denis
  Efremov, Enrico Weigelt, Frederic Barrat, Gautham R. Shenoy, Geert
  Uytterhoeven, Geliang Tang, Gen Zhang, Greg Kroah-Hartman, Greg Kurz,
  Gustavo Romero, Krzysztof Kozlowski, Madhavan Srinivasan, Masahiro
  Yamada, Mathieu Malaterre, Michael Neuling, Nathan Lynch, Naveen N.
  Rao, Nicholas Piggin, Nishad Kamdar, Oliver O'Halloran, Qian Cai, Ravi
  Bangoria, Sachin Sant, Sam Bobroff, Satheesh Rajendran, Segher
  Boessenkool, Shaokun Zhang, Shawn Anastasio, Stewart Smith, Suraj
  Jitindar Singh, Thiago Jung Bauermann, YueHaibing"

* tag 'powerpc-5.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (163 commits)
  powerpc/powernv/idle: Fix restore of SPRN_LDBAR for POWER9 stop state.
  powerpc/eeh: Handle hugepages in ioremap space
  ocxl: Update for AFU descriptor template version 1.1
  powerpc/boot: pass CONFIG options in a simpler and more robust way
  powerpc/boot: add {get, put}_unaligned_be32 to xz_config.h
  powerpc/irq: Don't WARN continuously in arch_local_irq_restore()
  powerpc/module64: Use symbolic instructions names.
  powerpc/module32: Use symbolic instructions names.
  powerpc: Move PPC_HA() PPC_HI() and PPC_LO() to ppc-opcode.h
  powerpc/module64: Fix comment in R_PPC64_ENTRY handling
  powerpc/boot: Add lzo support for uImage
  powerpc/boot: Add lzma support for uImage
  powerpc/boot: don't force gzipped uImage
  powerpc/8xx: Add microcode patch to move SMC parameter RAM.
  powerpc/8xx: Use IO accessors in microcode programming.
  powerpc/8xx: replace #ifdefs by IS_ENABLED() in microcode.c
  powerpc/8xx: refactor programming of microcode CPM params.
  powerpc/8xx: refactor printing of microcode patch name.
  powerpc/8xx: Refactor microcode write
  powerpc/8xx: refactor writing of CPM microcode arrays
  ...

12 files changed, 835 insertions, 102 deletions

diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 9c6b3d860518..f7b484f55553 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -23,6 +23,7 @@ config PPC_PSERIES
 	select ARCH_RANDOM
 	select PPC_DOORBELL
 	select FORCE_SMP
+	select SWIOTLB
 	default y
 
 config PPC_SPLPAR
@@ -80,19 +81,19 @@ config LPARCFG
 	bool "LPAR Configuration Data"
 	depends on PPC_PSERIES
 	help
-	Provide system capacity information via human readable
-	<key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
+	  Provide system capacity information via human readable
+	  <key word>=<value> pairs through a /proc/ppc64/lparcfg interface.
 
 config PPC_PSERIES_DEBUG
 	depends on PPC_PSERIES && PPC_EARLY_DEBUG
 	bool "Enable extra debug logging in platforms/pseries"
-        help
+	default y
+	help
 	  Say Y here if you want the pseries core to produce a bunch of
 	  debug messages to the system log. Select this if you are having a
 	  problem with the pseries core and want to see more of what is
 	  going on. This does not enable debugging in lpar.c, which must
 	  be manually done due to its verbosity.
-	default y
 
 config PPC_SMLPAR
 	bool "Support for shared-memory logical partitions"
@@ -117,16 +118,16 @@ config CMM
 	  balance memory across many LPARs.
 
 config HV_PERF_CTRS
-       bool "Hypervisor supplied PMU events (24x7 & GPCI)"
-       default y
-       depends on PERF_EVENTS && PPC_PSERIES
-       help
+	bool "Hypervisor supplied PMU events (24x7 & GPCI)"
+	default y
+	depends on PERF_EVENTS && PPC_PSERIES
+	help
 	  Enable access to hypervisor supplied counters in perf. Currently,
 	  this enables code that uses the hcall GetPerfCounterInfo and 24x7
 	  interfaces to retrieve counters. GPCI exists on Power 6 and later
 	  systems. 24x7 is available on Power 8 and later systems.
 
-          If unsure, select Y.
+	  If unsure, select Y.
 
 config IBMVIO
 	depends on PPC_PSERIES
diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile
index a43ec843c8e2..ab3d59aeacca 100644
--- a/arch/powerpc/platforms/pseries/Makefile
+++ b/arch/powerpc/platforms/pseries/Makefile
@@ -25,6 +25,7 @@ obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)		+= ibmebus.o
 obj-$(CONFIG_PAPR_SCM)		+= papr_scm.o
+obj-$(CONFIG_PPC_SPLPAR)	+= vphn.o
 
 ifdef CONFIG_PPC_PSERIES
 obj-$(CONFIG_SUSPEND)		+= suspend.o
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 437a74173db2..16e86ba8aa20 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -58,6 +58,10 @@ static struct property *dlpar_parse_cc_property(struct cc_workarea *ccwa)
 
 	name = (char *)ccwa + be32_to_cpu(ccwa->name_offset);
 	prop->name = kstrdup(name, GFP_KERNEL);
+	if (!prop->name) {
+		dlpar_free_cc_property(prop);
+		return NULL;
+	}
 
 	prop->length = be32_to_cpu(ccwa->prop_length);
 	value = (char *)ccwa + be32_to_cpu(ccwa->prop_offset);
@@ -383,11 +387,11 @@ void queue_hotplug_event(struct pseries_hp_errorlog *hp_errlog)
 	struct pseries_hp_work *work;
 	struct pseries_hp_errorlog *hp_errlog_copy;
 
-	hp_errlog_copy = kmalloc(sizeof(struct pseries_hp_errorlog),
-				 GFP_KERNEL);
-	memcpy(hp_errlog_copy, hp_errlog, sizeof(struct pseries_hp_errorlog));
+	hp_errlog_copy = kmemdup(hp_errlog, sizeof(*hp_errlog), GFP_ATOMIC);
+	if (!hp_errlog_copy)
+		return;
 
-	work = kmalloc(sizeof(struct pseries_hp_work), GFP_KERNEL);
+	work = kmalloc(sizeof(struct pseries_hp_work), GFP_ATOMIC);
 	if (work) {
 		INIT_WORK((struct work_struct *)work, pseries_hp_work_fn);
 		work->errlog = hp_errlog_copy;
diff --git a/arch/powerpc/platforms/pseries/dtl.c b/arch/powerpc/platforms/pseries/dtl.c
index ab5de985a787..2b87480f2837 100644
--- a/arch/powerpc/platforms/pseries/dtl.c
+++ b/arch/powerpc/platforms/pseries/dtl.c
@@ -27,13 +27,7 @@ struct dtl {
 };
 static DEFINE_PER_CPU(struct dtl, cpu_dtl);
 
-/*
- * Dispatch trace log event mask:
- * 0x7: 0x1: voluntary virtual processor waits
- *      0x2: time-slice preempts
- *      0x4: virtual partition memory page faults
- */
-static u8 dtl_event_mask = 0x7;
+static u8 dtl_event_mask = DTL_LOG_ALL;
 
 
 /*
@@ -48,7 +42,6 @@ struct dtl_ring {
 	struct dtl_entry *write_ptr;
 	struct dtl_entry *buf;
 	struct dtl_entry *buf_end;
-	u8	saved_dtl_mask;
 };
 
 static DEFINE_PER_CPU(struct dtl_ring, dtl_rings);
@@ -98,7 +91,6 @@ static int dtl_start(struct dtl *dtl)
 	dtlr->write_ptr = dtl->buf;
 
 	/* enable event logging */
-	dtlr->saved_dtl_mask = lppaca_of(dtl->cpu).dtl_enable_mask;
 	lppaca_of(dtl->cpu).dtl_enable_mask |= dtl_event_mask;
 
 	dtl_consumer = consume_dtle;
@@ -116,7 +108,7 @@ static void dtl_stop(struct dtl *dtl)
 	dtlr->buf = NULL;
 
 	/* restore dtl_enable_mask */
-	lppaca_of(dtl->cpu).dtl_enable_mask = dtlr->saved_dtl_mask;
+	lppaca_of(dtl->cpu).dtl_enable_mask = DTL_LOG_PREEMPT;
 
 	if (atomic_dec_and_test(&dtl_count))
 		dtl_consumer = NULL;
@@ -188,11 +180,16 @@ static int dtl_enable(struct dtl *dtl)
 	if (dtl->buf)
 		return -EBUSY;
 
+	/* ensure there are no other conflicting dtl users */
+	if (!read_trylock(&dtl_access_lock))
+		return -EBUSY;
+
 	n_entries = dtl_buf_entries;
 	buf = kmem_cache_alloc_node(dtl_cache, GFP_KERNEL, cpu_to_node(dtl->cpu));
 	if (!buf) {
 		printk(KERN_WARNING "%s: buffer alloc failed for cpu %d\n",
 				__func__, dtl->cpu);
+		read_unlock(&dtl_access_lock);
 		return -ENOMEM;
 	}
 
@@ -209,8 +206,11 @@ static int dtl_enable(struct dtl *dtl)
 	}
 	spin_unlock(&dtl->lock);
 
-	if (rc)
+	if (rc) {
+		read_unlock(&dtl_access_lock);
 		kmem_cache_free(dtl_cache, buf);
+	}
+
 	return rc;
 }
 
@@ -222,6 +222,7 @@ static void dtl_disable(struct dtl *dtl)
 	dtl->buf = NULL;
 	dtl->buf_entries = 0;
 	spin_unlock(&dtl->lock);
+	read_unlock(&dtl_access_lock);
 }
 
 /* file interface */
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 2ec43b4639a0..46d0d35b9ca4 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -976,6 +976,9 @@ static int pseries_update_drconf_memory(struct of_reconfig_data *pr)
 	if (!memblock_size)
 		return -EINVAL;
 
+	if (!pr->old_prop)
+		return 0;
+
 	p = (__be32 *) pr->old_prop->value;
 	if (!p)
 		return -EINVAL;
diff --git a/arch/powerpc/platforms/pseries/hvconsole.c b/arch/powerpc/platforms/pseries/hvconsole.c
index 1498c6b989e6..1ac52963e08b 100644
--- a/arch/powerpc/platforms/pseries/hvconsole.c
+++ b/arch/powerpc/platforms/pseries/hvconsole.c
@@ -49,7 +49,7 @@ EXPORT_SYMBOL(hvc_get_chars);
  * @vtermno: The vtermno or unit_address of the adapter from which the data
  *	originated.
  * @buf: The character buffer that contains the character data to send to
- *	firmware.
+ *	firmware. Must be at least 16 bytes, even if count is less than 16.
  * @count: Send this number of characters.
  */
 int hvc_put_chars(uint32_t vtermno, const char *buf, int count)
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index 73620dfb63a1..09bb878c21e0 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -17,6 +17,10 @@
 #include <linux/jump_label.h>
 #include <linux/delay.h>
 #include <linux/stop_machine.h>
+#include <linux/spinlock.h>
+#include <linux/cpuhotplug.h>
+#include <linux/workqueue.h>
+#include <linux/proc_fs.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/page.h>
@@ -52,13 +56,591 @@ EXPORT_SYMBOL(plpar_hcall);
 EXPORT_SYMBOL(plpar_hcall9);
 EXPORT_SYMBOL(plpar_hcall_norets);
 
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+static u8 dtl_mask = DTL_LOG_PREEMPT;
+#else
+static u8 dtl_mask;
+#endif
+
+void alloc_dtl_buffers(unsigned long *time_limit)
+{
+	int cpu;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+
+	for_each_possible_cpu(cpu) {
+		pp = paca_ptrs[cpu];
+		if (pp->dispatch_log)
+			continue;
+		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
+		if (!dtl) {
+			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
+				cpu);
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+			pr_warn("Stolen time statistics will be unreliable\n");
+#endif
+			break;
+		}
+
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = dtl;
+		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
+		pp->dtl_curr = dtl;
+
+		if (time_limit && time_after(jiffies, *time_limit)) {
+			cond_resched();
+			*time_limit = jiffies + HZ;
+		}
+	}
+}
+
+void register_dtl_buffer(int cpu)
+{
+	long ret;
+	struct paca_struct *pp;
+	struct dtl_entry *dtl;
+	int hwcpu = get_hard_smp_processor_id(cpu);
+
+	pp = paca_ptrs[cpu];
+	dtl = pp->dispatch_log;
+	if (dtl && dtl_mask) {
+		pp->dtl_ridx = 0;
+		pp->dtl_curr = dtl;
+		lppaca_of(cpu).dtl_idx = 0;
+
+		/* hypervisor reads buffer length from this field */
+		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
+		ret = register_dtl(hwcpu, __pa(dtl));
+		if (ret)
+			pr_err("WARNING: DTL registration of cpu %d (hw %d) failed with %ld\n",
+			       cpu, hwcpu, ret);
+
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+	}
+}
+
+#ifdef CONFIG_PPC_SPLPAR
+struct dtl_worker {
+	struct delayed_work work;
+	int cpu;
+};
+
+struct vcpu_dispatch_data {
+	int last_disp_cpu;
+
+	int total_disp;
+
+	int same_cpu_disp;
+	int same_chip_disp;
+	int diff_chip_disp;
+	int far_chip_disp;
+
+	int numa_home_disp;
+	int numa_remote_disp;
+	int numa_far_disp;
+};
+
+/*
+ * This represents the number of cpus in the hypervisor. Since there is no
+ * architected way to discover the number of processors in the host, we
+ * provision for dealing with NR_CPUS. This is currently 2048 by default, and
+ * is sufficient for our purposes. This will need to be tweaked if
+ * CONFIG_NR_CPUS is changed.
+ */
+#define NR_CPUS_H	NR_CPUS
+
+DEFINE_RWLOCK(dtl_access_lock);
+static DEFINE_PER_CPU(struct vcpu_dispatch_data, vcpu_disp_data);
+static DEFINE_PER_CPU(u64, dtl_entry_ridx);
+static DEFINE_PER_CPU(struct dtl_worker, dtl_workers);
+static enum cpuhp_state dtl_worker_state;
+static DEFINE_MUTEX(dtl_enable_mutex);
+static int vcpudispatch_stats_on __read_mostly;
+static int vcpudispatch_stats_freq = 50;
+static __be32 *vcpu_associativity, *pcpu_associativity;
+
+
+static void free_dtl_buffers(unsigned long *time_limit)
+{
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	int cpu;
+	struct paca_struct *pp;
+
+	for_each_possible_cpu(cpu) {
+		pp = paca_ptrs[cpu];
+		if (!pp->dispatch_log)
+			continue;
+		kmem_cache_free(dtl_cache, pp->dispatch_log);
+		pp->dtl_ridx = 0;
+		pp->dispatch_log = 0;
+		pp->dispatch_log_end = 0;
+		pp->dtl_curr = 0;
+
+		if (time_limit && time_after(jiffies, *time_limit)) {
+			cond_resched();
+			*time_limit = jiffies + HZ;
+		}
+	}
+#endif
+}
+
+static int init_cpu_associativity(void)
+{
+	vcpu_associativity = kcalloc(num_possible_cpus() / threads_per_core,
+			VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL);
+	pcpu_associativity = kcalloc(NR_CPUS_H / threads_per_core,
+			VPHN_ASSOC_BUFSIZE * sizeof(__be32), GFP_KERNEL);
+
+	if (!vcpu_associativity || !pcpu_associativity) {
+		pr_err("error allocating memory for associativity information\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void destroy_cpu_associativity(void)
+{
+	kfree(vcpu_associativity);
+	kfree(pcpu_associativity);
+	vcpu_associativity = pcpu_associativity = 0;
+}
+
+static __be32 *__get_cpu_associativity(int cpu, __be32 *cpu_assoc, int flag)
+{
+	__be32 *assoc;
+	int rc = 0;
+
+	assoc = &cpu_assoc[(int)(cpu / threads_per_core) * VPHN_ASSOC_BUFSIZE];
+	if (!assoc[0]) {
+		rc = hcall_vphn(cpu, flag, &assoc[0]);
+		if (rc)
+			return NULL;
+	}
+
+	return assoc;
+}
+
+static __be32 *get_pcpu_associativity(int cpu)
+{
+	return __get_cpu_associativity(cpu, pcpu_associativity, VPHN_FLAG_PCPU);
+}
+
+static __be32 *get_vcpu_associativity(int cpu)
+{
+	return __get_cpu_associativity(cpu, vcpu_associativity, VPHN_FLAG_VCPU);
+}
+
+static int cpu_relative_dispatch_distance(int last_disp_cpu, int cur_disp_cpu)
+{
+	__be32 *last_disp_cpu_assoc, *cur_disp_cpu_assoc;
+
+	if (last_disp_cpu >= NR_CPUS_H || cur_disp_cpu >= NR_CPUS_H)
+		return -EINVAL;
+
+	last_disp_cpu_assoc = get_pcpu_associativity(last_disp_cpu);
+	cur_disp_cpu_assoc = get_pcpu_associativity(cur_disp_cpu);
+
+	if (!last_disp_cpu_assoc || !cur_disp_cpu_assoc)
+		return -EIO;
+
+	return cpu_distance(last_disp_cpu_assoc, cur_disp_cpu_assoc);
+}
+
+static int cpu_home_node_dispatch_distance(int disp_cpu)
+{
+	__be32 *disp_cpu_assoc, *vcpu_assoc;
+	int vcpu_id = smp_processor_id();
+
+	if (disp_cpu >= NR_CPUS_H) {
+		pr_debug_ratelimited("vcpu dispatch cpu %d > %d\n",
+						disp_cpu, NR_CPUS_H);
+		return -EINVAL;
+	}
+
+	disp_cpu_assoc = get_pcpu_associativity(disp_cpu);
+	vcpu_assoc = get_vcpu_associativity(vcpu_id);
+
+	if (!disp_cpu_assoc || !vcpu_assoc)
+		return -EIO;
+
+	return cpu_distance(disp_cpu_assoc, vcpu_assoc);
+}
+
+static void update_vcpu_disp_stat(int disp_cpu)
+{
+	struct vcpu_dispatch_data *disp;
+	int distance;
+
+	disp = this_cpu_ptr(&vcpu_disp_data);
+	if (disp->last_disp_cpu == -1) {
+		disp->last_disp_cpu = disp_cpu;
+		return;
+	}
+
+	disp->total_disp++;
+
+	if (disp->last_disp_cpu == disp_cpu ||
+		(cpu_first_thread_sibling(disp->last_disp_cpu) ==
+					cpu_first_thread_sibling(disp_cpu)))
+		disp->same_cpu_disp++;
+	else {
+		distance = cpu_relative_dispatch_distance(disp->last_disp_cpu,
+								disp_cpu);
+		if (distance < 0)
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n",
+					smp_processor_id());
+		else {
+			switch (distance) {
+			case 0:
+				disp->same_chip_disp++;
+				break;
+			case 1:
+				disp->diff_chip_disp++;
+				break;
+			case 2:
+				disp->far_chip_disp++;
+				break;
+			default:
+				pr_debug_ratelimited("vcpudispatch_stats: cpu %d (%d -> %d): unexpected relative dispatch distance %d\n",
+						 smp_processor_id(),
+						 disp->last_disp_cpu,
+						 disp_cpu,
+						 distance);
+			}
+		}
+	}
+
+	distance = cpu_home_node_dispatch_distance(disp_cpu);
+	if (distance < 0)
+		pr_debug_ratelimited("vcpudispatch_stats: cpu %d: error determining associativity\n",
+				smp_processor_id());
+	else {
+		switch (distance) {
+		case 0:
+			disp->numa_home_disp++;
+			break;
+		case 1:
+			disp->numa_remote_disp++;
+			break;
+		case 2:
+			disp->numa_far_disp++;
+			break;
+		default:
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d on %d: unexpected numa dispatch distance %d\n",
+						 smp_processor_id(),
+						 disp_cpu,
+						 distance);
+		}
+	}
+
+	disp->last_disp_cpu = disp_cpu;
+}
+
+static void process_dtl_buffer(struct work_struct *work)
+{
+	struct dtl_entry dtle;
+	u64 i = __this_cpu_read(dtl_entry_ridx);
+	struct dtl_entry *dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+	struct dtl_entry *dtl_end = local_paca->dispatch_log_end;
+	struct lppaca *vpa = local_paca->lppaca_ptr;
+	struct dtl_worker *d = container_of(work, struct dtl_worker, work.work);
+
+	if (!local_paca->dispatch_log)
+		return;
+
+	/* if we have been migrated away, we cancel ourself */
+	if (d->cpu != smp_processor_id()) {
+		pr_debug("vcpudispatch_stats: cpu %d worker migrated -- canceling worker\n",
+						smp_processor_id());
+		return;
+	}
+
+	if (i == be64_to_cpu(vpa->dtl_idx))
+		goto out;
+
+	while (i < be64_to_cpu(vpa->dtl_idx)) {
+		dtle = *dtl;
+		barrier();
+		if (i + N_DISPATCH_LOG < be64_to_cpu(vpa->dtl_idx)) {
+			/* buffer has overflowed */
+			pr_debug_ratelimited("vcpudispatch_stats: cpu %d lost %lld DTL samples\n",
+				d->cpu,
+				be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG - i);
+			i = be64_to_cpu(vpa->dtl_idx) - N_DISPATCH_LOG;
+			dtl = local_paca->dispatch_log + (i % N_DISPATCH_LOG);
+			continue;
+		}
+		update_vcpu_disp_stat(be16_to_cpu(dtle.processor_id));
+		++i;
+		++dtl;
+		if (dtl == dtl_end)
+			dtl = local_paca->dispatch_log;
+	}
+
+	__this_cpu_write(dtl_entry_ridx, i);
+
+out:
+	schedule_delayed_work_on(d->cpu, to_delayed_work(work),
+					HZ / vcpudispatch_stats_freq);
+}
+
+static int dtl_worker_online(unsigned int cpu)
+{
+	struct dtl_worker *d = &per_cpu(dtl_workers, cpu);
+
+	memset(d, 0, sizeof(*d));
+	INIT_DELAYED_WORK(&d->work, process_dtl_buffer);
+	d->cpu = cpu;
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	per_cpu(dtl_entry_ridx, cpu) = 0;
+	register_dtl_buffer(cpu);
+#else
+	per_cpu(dtl_entry_ridx, cpu) = be64_to_cpu(lppaca_of(cpu).dtl_idx);
+#endif
+
+	schedule_delayed_work_on(cpu, &d->work, HZ / vcpudispatch_stats_freq);
+	return 0;
+}
+
+static int dtl_worker_offline(unsigned int cpu)
+{
+	struct dtl_worker *d = &per_cpu(dtl_workers, cpu);
+
+	cancel_delayed_work_sync(&d->work);
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	unregister_dtl(get_hard_smp_processor_id(cpu));
+#endif
+
+	return 0;
+}
+
+static void set_global_dtl_mask(u8 mask)
+{
+	int cpu;
+
+	dtl_mask = mask;
+	for_each_present_cpu(cpu)
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+}
+
+static void reset_global_dtl_mask(void)
+{
+	int cpu;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+	dtl_mask = DTL_LOG_PREEMPT;
+#else
+	dtl_mask = 0;
+#endif
+	for_each_present_cpu(cpu)
+		lppaca_of(cpu).dtl_enable_mask = dtl_mask;
+}
+
+static int dtl_worker_enable(unsigned long *time_limit)
+{
+	int rc = 0, state;
+
+	if (!write_trylock(&dtl_access_lock)) {
+		rc = -EBUSY;
+		goto out;
+	}
+
+	set_global_dtl_mask(DTL_LOG_ALL);
+
+	/* Setup dtl buffers and register those */
+	alloc_dtl_buffers(time_limit);
+
+	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/dtl:online",
+					dtl_worker_online, dtl_worker_offline);
+	if (state < 0) {
+		pr_err("vcpudispatch_stats: unable to setup workqueue for DTL processing\n");
+		free_dtl_buffers(time_limit);
+		reset_global_dtl_mask();
+		write_unlock(&dtl_access_lock);
+		rc = -EINVAL;
+		goto out;
+	}
+	dtl_worker_state = state;
+
+out:
+	return rc;
+}
+
+static void dtl_worker_disable(unsigned long *time_limit)
+{
+	cpuhp_remove_state(dtl_worker_state);
+	free_dtl_buffers(time_limit);
+	reset_global_dtl_mask();
+	write_unlock(&dtl_access_lock);
+}
+
+static ssize_t vcpudispatch_stats_write(struct file *file, const char __user *p,
+		size_t count, loff_t *ppos)
+{
+	unsigned long time_limit = jiffies + HZ;
+	struct vcpu_dispatch_data *disp;
+	int rc, cmd, cpu;
+	char buf[16];
+
+	if (count > 15)
+		return -EINVAL;
+
+	if (copy_from_user(buf, p, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+	rc = kstrtoint(buf, 0, &cmd);
+	if (rc || cmd < 0 || cmd > 1) {
+		pr_err("vcpudispatch_stats: please use 0 to disable or 1 to enable dispatch statistics\n");
+		return rc ? rc : -EINVAL;
+	}
+
+	mutex_lock(&dtl_enable_mutex);
+
+	if ((cmd == 0 && !vcpudispatch_stats_on) ||
+			(cmd == 1 && vcpudispatch_stats_on))
+		goto out;
+
+	if (cmd) {
+		rc = init_cpu_associativity();
+		if (rc)
+			goto out;
+
+		for_each_possible_cpu(cpu) {
+			disp = per_cpu_ptr(&vcpu_disp_data, cpu);
+			memset(disp, 0, sizeof(*disp));
+			disp->last_disp_cpu = -1;
+		}
+
+		rc = dtl_worker_enable(&time_limit);
+		if (rc) {
+			destroy_cpu_associativity();
+			goto out;
+		}
+	} else {
+		dtl_worker_disable(&time_limit);
+		destroy_cpu_associativity();
+	}
+
+	vcpudispatch_stats_on = cmd;
+
+out:
+	mutex_unlock(&dtl_enable_mutex);
+	if (rc)
+		return rc;
+	return count;
+}
+
+static int vcpudispatch_stats_display(struct seq_file *p, void *v)
+{
+	int cpu;
+	struct vcpu_dispatch_data *disp;
+
+	if (!vcpudispatch_stats_on) {
+		seq_puts(p, "off\n");
+		return 0;
+	}
+
+	for_each_online_cpu(cpu) {
+		disp = per_cpu_ptr(&vcpu_disp_data, cpu);
+		seq_printf(p, "cpu%d", cpu);
+		seq_put_decimal_ull(p, " ", disp->total_disp);
+		seq_put_decimal_ull(p, " ", disp->same_cpu_disp);
+		seq_put_decimal_ull(p, " ", disp->same_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->diff_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->far_chip_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_home_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_remote_disp);
+		seq_put_decimal_ull(p, " ", disp->numa_far_disp);
+		seq_puts(p, "\n");
+	}
+
+	return 0;
+}
+
+static int vcpudispatch_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, vcpudispatch_stats_display, NULL);
+}
+
+static const struct file_operations vcpudispatch_stats_proc_ops = {
+	.open		= vcpudispatch_stats_open,
+	.read		= seq_read,
+	.write		= vcpudispatch_stats_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static ssize_t vcpudispatch_stats_freq_write(struct file *file,
+		const char __user *p, size_t count, loff_t *ppos)
+{
+	int rc, freq;
+	char buf[16];
+
+	if (count > 15)
+		return -EINVAL;
+
+	if (copy_from_user(buf, p, count))
+		return -EFAULT;
+
+	buf[count] = 0;
+	rc = kstrtoint(buf, 0, &freq);
+	if (rc || freq < 1 || freq > HZ) {
+		pr_err("vcpudispatch_stats_freq: please specify a frequency between 1 and %d\n",
+				HZ);
+		return rc ? rc : -EINVAL;
+	}
+
+	vcpudispatch_stats_freq = freq;
+
+	return count;
+}
+
+static int vcpudispatch_stats_freq_display(struct seq_file *p, void *v)
+{
+	seq_printf(p, "%d\n", vcpudispatch_stats_freq);
+	return 0;
+}
+
+static int vcpudispatch_stats_freq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, vcpudispatch_stats_freq_display, NULL);
+}
+
+static const struct file_operations vcpudispatch_stats_freq_proc_ops = {
+	.open		= vcpudispatch_stats_freq_open,
+	.read		= seq_read,
+	.write		= vcpudispatch_stats_freq_write,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init vcpudispatch_stats_procfs_init(void)
+{
+	if (!lppaca_shared_proc(get_lppaca()))
+		return 0;
+
+	if (!proc_create("powerpc/vcpudispatch_stats", 0600, NULL,
+					&vcpudispatch_stats_proc_ops))
+		pr_err("vcpudispatch_stats: error creating procfs file\n");
+	else if (!proc_create("powerpc/vcpudispatch_stats_freq", 0600, NULL,
+					&vcpudispatch_stats_freq_proc_ops))
+		pr_err("vcpudispatch_stats_freq: error creating procfs file\n");
+
+	return 0;
+}
+
+machine_device_initcall(pseries, vcpudispatch_stats_procfs_init);
+#endif /* CONFIG_PPC_SPLPAR */
+
 void vpa_init(int cpu)
 {
 	int hwcpu = get_hard_smp_processor_id(cpu);
 	unsigned long addr;
 	long ret;
-	struct paca_struct *pp;
-	struct dtl_entry *dtl;
 
 	/*
 	 * The spec says it "may be problematic" if CPU x registers the VPA of
@@ -99,22 +681,7 @@ void vpa_init(int cpu)
 	/*
 	 * Register dispatch trace log, if one has been allocated.
 	 */
-	pp = paca_ptrs[cpu];
-	dtl = pp->dispatch_log;
-	if (dtl) {
-		pp->dtl_ridx = 0;
-		pp->dtl_curr = dtl;
-		lppaca_of(cpu).dtl_idx = 0;
-
-		/* hypervisor reads buffer length from this field */
-		dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
-		ret = register_dtl(hwcpu, __pa(dtl));
-		if (ret)
-			pr_err("WARNING: DTL registration of cpu %d (hw %d) "
-			       "failed with %ld\n", smp_processor_id(),
-			       hwcpu, ret);
-		lppaca_of(cpu).dtl_enable_mask = 2;
-	}
+	register_dtl_buffer(cpu);
 }
 
 #ifdef CONFIG_PPC_BOOK3S_64
diff --git a/arch/powerpc/platforms/pseries/mobility.c b/arch/powerpc/platforms/pseries/mobility.c
index 0c48c8964783..fe812bebdf5e 100644
--- a/arch/powerpc/platforms/pseries/mobility.c
+++ b/arch/powerpc/platforms/pseries/mobility.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2010 IBM Corporation
  */
 
+#include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/kobject.h>
 #include <linux/smp.h>
@@ -19,6 +20,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include "pseries.h"
+#include "../../kernel/cacheinfo.h"
 
 static struct kobject *mobility_kobj;
 
@@ -335,11 +337,28 @@ void post_mobility_fixup(void)
 	if (rc)
 		printk(KERN_ERR "Post-mobility activate-fw failed: %d\n", rc);
 
+	/*
+	 * We don't want CPUs to go online/offline while the device
+	 * tree is being updated.
+	 */
+	cpus_read_lock();
+
+	/*
+	 * It's common for the destination firmware to replace cache
+	 * nodes.  Release all of the cacheinfo hierarchy's references
+	 * before updating the device tree.
+	 */
+	cacheinfo_teardown();
+
 	rc = pseries_devicetree_update(MIGRATION_SCOPE);
 	if (rc)
 		printk(KERN_ERR "Post-mobility device tree update "
 			"failed: %d\n", rc);
 
+	cacheinfo_rebuild();
+
+	cpus_read_unlock();
+
 	/* Possibly switch to a new RFI flush type */
 	pseries_setup_rfi_flush();
 
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 96c53b23e58f..c8ec670ee924 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -28,6 +28,7 @@ struct papr_scm_priv {
 	uint64_t blocks;
 	uint64_t block_size;
 	int metadata_size;
+	bool is_volatile;
 
 	uint64_t bound_addr;
 
@@ -96,42 +97,102 @@ static int drc_pmem_unbind(struct papr_scm_priv *p)
 }
 
 static int papr_scm_meta_get(struct papr_scm_priv *p,
-			struct nd_cmd_get_config_data_hdr *hdr)
+			     struct nd_cmd_get_config_data_hdr *hdr)
 {
 	unsigned long data[PLPAR_HCALL_BUFSIZE];
+	unsigned long offset, data_offset;
+	int len, read;
 	int64_t ret;
 
-	if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
 		return -EINVAL;
 
-	ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
-			hdr->in_offset, 1);
-
-	if (ret == H_PARAMETER) /* bad DRC index */
-		return -ENODEV;
-	if (ret)
-		return -EINVAL; /* other invalid parameter */
-
-	hdr->out_buf[0] = data[0] & 0xff;
-
+	for (len = hdr->in_length; len; len -= read) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8)
+			read = 8;
+		else if (len >= 4)
+			read = 4;
+		else if (len >= 2)
+			read = 2;
+		else
+			read = 1;
+
+		ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
+				  offset, read);
+
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+
+		switch (read) {
+		case 8:
+			*(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
+			break;
+		case 4:
+			*(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
+			break;
+
+		case 2:
+			*(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
+			break;
+
+		case 1:
+			*(uint8_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
+			break;
+		}
+	}
 	return 0;
 }
 
 static int papr_scm_meta_set(struct papr_scm_priv *p,
-			struct nd_cmd_set_config_hdr *hdr)
+			     struct nd_cmd_set_config_hdr *hdr)
 {
+	unsigned long offset, data_offset;
+	int len, wrote;
+	unsigned long data;
+	__be64 data_be;
 	int64_t ret;
 
-	if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+	if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
 		return -EINVAL;
 
-	ret = plpar_hcall_norets(H_SCM_WRITE_METADATA,
-			p->drc_index, hdr->in_offset, hdr->in_buf[0], 1);
-
-	if (ret == H_PARAMETER) /* bad DRC index */
-		return -ENODEV;
-	if (ret)
-		return -EINVAL; /* other invalid parameter */
+	for (len = hdr->in_length; len; len -= wrote) {
+
+		data_offset = hdr->in_length - len;
+		offset = hdr->in_offset + data_offset;
+
+		if (len >= 8) {
+			data = *(uint64_t *)(hdr->in_buf + data_offset);
+			data_be = cpu_to_be64(data);
+			wrote = 8;
+		} else if (len >= 4) {
+			data = *(uint32_t *)(hdr->in_buf + data_offset);
+			data &= 0xffffffff;
+			data_be = cpu_to_be32(data);
+			wrote = 4;
+		} else if (len >= 2) {
+			data = *(uint16_t *)(hdr->in_buf + data_offset);
+			data &= 0xffff;
+			data_be = cpu_to_be16(data);
+			wrote = 2;
+		} else {
+			data_be = *(uint8_t *)(hdr->in_buf + data_offset);
+			data_be &= 0xff;
+			wrote = 1;
+		}
+
+		ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
+					 offset, data_be, wrote);
+		if (ret == H_PARAMETER) /* bad DRC index */
+			return -ENODEV;
+		if (ret)
+			return -EINVAL; /* other invalid parameter */
+	}
 
 	return 0;
 }
@@ -153,7 +214,7 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
 		get_size_hdr = buf;
 
 		get_size_hdr->status = 0;
-		get_size_hdr->max_xfer = 1;
+		get_size_hdr->max_xfer = 8;
 		get_size_hdr->config_size = p->metadata_size;
 		*cmd_rc = 0;
 		break;
@@ -248,7 +309,10 @@ static int papr_scm_nvdimm_init(struct papr_scm_priv *p)
 	ndr_desc.nd_set = &p->nd_set;
 	set_bit(ND_REGION_PAGEMAP, &ndr_desc.flags);
 
-	p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
+	if (p->is_volatile)
+		p->region = nvdimm_volatile_region_create(p->bus, &ndr_desc);
+	else
+		p->region = nvdimm_pmem_region_create(p->bus, &ndr_desc);
 	if (!p->region) {
 		dev_err(dev, "Error registering region %pR from %pOF\n",
 				ndr_desc.res, p->dn);
@@ -293,6 +357,7 @@ static int papr_scm_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
+
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p)
 		return -ENOMEM;
@@ -304,11 +369,19 @@ static int papr_scm_probe(struct platform_device *pdev)
 	p->drc_index = drc_index;
 	p->block_size = block_size;
 	p->blocks = blocks;
+	p->is_volatile = !of_property_read_bool(dn, "ibm,cache-flush-required");
 
 	/* We just need to ensure that set cookies are unique across */
 	uuid_parse(uuid_str, (uuid_t *) uuid);
-	p->nd_set.cookie1 = uuid[0];
-	p->nd_set.cookie2 = uuid[1];
+	/*
+	 * cookie1 and cookie2 are not really little endian
+	 * we store a little endian representation of the
+	 * uuid str so that we can compare this with the label
+	 * area cookie irrespective of the endian config with which
+	 * the kernel is built.
+	 */
+	p->nd_set.cookie1 = cpu_to_le64(uuid[0]);
+	p->nd_set.cookie2 = cpu_to_le64(uuid[1]);
 
 	/* might be zero */
 	p->metadata_size = metadata_size;
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 8fa012a65a71..f5940cc71c37 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -38,6 +38,7 @@
 #include <linux/of.h>
 #include <linux/of_pci.h>
 #include <linux/memblock.h>
+#include <linux/swiotlb.h>
 
 #include <asm/mmu.h>
 #include <asm/processor.h>
@@ -67,6 +68,7 @@
 #include <asm/isa-bridge.h>
 #include <asm/security_features.h>
 #include <asm/asm-const.h>
+#include <asm/swiotlb.h>
 
 #include "pseries.h"
 #include "../../../../drivers/pci/pci.h"
@@ -273,46 +275,16 @@ struct kmem_cache *dtl_cache;
  */
 static int alloc_dispatch_logs(void)
 {
-	int cpu, ret;
-	struct paca_struct *pp;
-	struct dtl_entry *dtl;
-
 	if (!firmware_has_feature(FW_FEATURE_SPLPAR))
 		return 0;
 
 	if (!dtl_cache)
 		return 0;
 
-	for_each_possible_cpu(cpu) {
-		pp = paca_ptrs[cpu];
-		dtl = kmem_cache_alloc(dtl_cache, GFP_KERNEL);
-		if (!dtl) {
-			pr_warn("Failed to allocate dispatch trace log for cpu %d\n",
-				cpu);
-			pr_warn("Stolen time statistics will be unreliable\n");
-			break;
-		}
-
-		pp->dtl_ridx = 0;
-		pp->dispatch_log = dtl;
-		pp->dispatch_log_end = dtl + N_DISPATCH_LOG;
-		pp->dtl_curr = dtl;
-	}
+	alloc_dtl_buffers(0);
 
 	/* Register the DTL for the current (boot) cpu */
-	dtl = get_paca()->dispatch_log;
-	get_paca()->dtl_ridx = 0;
-	get_paca()->dtl_curr = dtl;
-	get_paca()->lppaca_ptr->dtl_idx = 0;
-
-	/* hypervisor reads buffer length from this field */
-	dtl->enqueue_to_dispatch_time = cpu_to_be32(DISPATCH_LOG_BYTES);
-	ret = register_dtl(hard_smp_processor_id(), __pa(dtl));
-	if (ret)
-		pr_err("WARNING: DTL registration of cpu %d (hw %d) failed "
-		       "with %d\n", smp_processor_id(),
-		       hard_smp_processor_id(), ret);
-	get_paca()->lppaca_ptr->dtl_enable_mask = 2;
+	register_dtl_buffer(smp_processor_id());
 
 	return 0;
 }
@@ -793,6 +765,9 @@ static void __init pSeries_setup_arch(void)
 	}
 
 	ppc_md.pcibios_root_bridge_prepare = pseries_root_bridge_prepare;
+
+	if (swiotlb_force == SWIOTLB_FORCE)
+		ppc_swiotlb_enable = 1;
 }
 
 static void pseries_panic(char *str)
diff --git a/arch/powerpc/platforms/pseries/vio.c b/arch/powerpc/platforms/pseries/vio.c
index ba758f4be328..6601b9d404dc 100644
--- a/arch/powerpc/platforms/pseries/vio.c
+++ b/arch/powerpc/platforms/pseries/vio.c
@@ -520,7 +520,7 @@ static dma_addr_t vio_dma_iommu_map_page(struct device *dev, struct page *page,
 
 	if (vio_cmo_alloc(viodev, roundup(size, IOMMU_PAGE_SIZE(tbl))))
 		goto out_fail;
-	ret = iommu_map_page(dev, tbl, page, offset, size, device_to_mask(dev),
+	ret = iommu_map_page(dev, tbl, page, offset, size, dma_get_mask(dev),
 			direction, attrs);
 	if (unlikely(ret == DMA_MAPPING_ERROR))
 		goto out_deallocate;
@@ -560,7 +560,7 @@ static int vio_dma_iommu_map_sg(struct device *dev, struct scatterlist *sglist,
 
 	if (vio_cmo_alloc(viodev, alloc_size))
 		goto out_fail;
-	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, device_to_mask(dev),
+	ret = ppc_iommu_map_sg(dev, tbl, sglist, nelems, dma_get_mask(dev),
 			direction, attrs);
 	if (unlikely(!ret))
 		goto out_deallocate;
diff --git a/arch/powerpc/platforms/pseries/vphn.c b/arch/powerpc/platforms/pseries/vphn.c
new file mode 100644
index 000000000000..3f07bf6c670e
--- /dev/null
+++ b/arch/powerpc/platforms/pseries/vphn.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <asm/byteorder.h>
+#include <asm/lppaca.h>
+
+/*
+ * The associativity domain numbers are returned from the hypervisor as a
+ * stream of mixed 16-bit and 32-bit fields. The stream is terminated by the
+ * special value of "all ones" (aka. 0xffff) and its size may not exceed 48
+ * bytes.
+ *
+ *    --- 16-bit fields -->
+ *  _________________________
+ *  |  0  |  1  |  2  |  3  |   be_packed[0]
+ *  ------+-----+-----+------
+ *  _________________________
+ *  |  4  |  5  |  6  |  7  |   be_packed[1]
+ *  -------------------------
+ *            ...
+ *  _________________________
+ *  | 20  | 21  | 22  | 23  |   be_packed[5]
+ *  -------------------------
+ *
+ * Convert to the sequence they would appear in the ibm,associativity property.
+ */
+static int vphn_unpack_associativity(const long *packed, __be32 *unpacked)
+{
+	__be64 be_packed[VPHN_REGISTER_COUNT];
+	int i, nr_assoc_doms = 0;
+	const __be16 *field = (const __be16 *) be_packed;
+	u16 last = 0;
+	bool is_32bit = false;
+
+#define VPHN_FIELD_UNUSED	(0xffff)
+#define VPHN_FIELD_MSB		(0x8000)
+#define VPHN_FIELD_MASK		(~VPHN_FIELD_MSB)
+
+	/* Let's fix the values returned by plpar_hcall9() */
+	for (i = 0; i < VPHN_REGISTER_COUNT; i++)
+		be_packed[i] = cpu_to_be64(packed[i]);
+
+	for (i = 1; i < VPHN_ASSOC_BUFSIZE; i++) {
+		u16 new = be16_to_cpup(field++);
+
+		if (is_32bit) {
+			/*
+			 * Let's concatenate the 16 bits of this field to the
+			 * 15 lower bits of the previous field
+			 */
+			unpacked[++nr_assoc_doms] =
+				cpu_to_be32(last << 16 | new);
+			is_32bit = false;
+		} else if (new == VPHN_FIELD_UNUSED)
+			/* This is the list terminator */
+			break;
+		else if (new & VPHN_FIELD_MSB) {
+			/* Data is in the lower 15 bits of this field */
+			unpacked[++nr_assoc_doms] =
+				cpu_to_be32(new & VPHN_FIELD_MASK);
+		} else {
+			/*
+			 * Data is in the lower 15 bits of this field
+			 * concatenated with the next 16 bit field
+			 */
+			last = new;
+			is_32bit = true;
+		}
+	}
+
+	/* The first cell contains the length of the property */
+	unpacked[0] = cpu_to_be32(nr_assoc_doms);
+
+	return nr_assoc_doms;
+}
+
+/* NOTE: This file is included by a selftest and built in userspace. */
+#ifdef __KERNEL__
+#include <asm/hvcall.h>
+
+long hcall_vphn(unsigned long cpu, u64 flags, __be32 *associativity)
+{
+	long rc;
+	long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+
+	rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, cpu);
+	vphn_unpack_associativity(retbuf, associativity);
+
+	return rc;
+}
+#endif