Merge tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "Nothing really major this release, despite quite a lot of activity.
  Just lots of things all over the place.

  Some things of note include:

   - Access via perf to a new type of PMU (IMC) on Power9, which can
     count both core events as well as nest unit events (Memory
     controller etc).

   - Optimisations to the radix MMU TLB flushing, mostly to avoid
     unnecessary Page Walk Cache (PWC) flushes when the structure of the
     tree is not changing.

   - Reworks/cleanups of do_page_fault() to modernise it and bring it
     closer to other architectures where possible.

   - Rework of our page table walking so that THP updates only need to
     send IPIs to CPUs where the affected mm has run, rather than all
     CPUs.

   - The size of our vmalloc area is increased to 56T on 64-bit hash MMU
     systems. This avoids problems with the percpu allocator on systems
     with very sparse NUMA layouts.

   - STRICT_KERNEL_RWX support on PPC32.

   - A new sched domain topology for Power9, to capture the fact that
     pairs of cores may share an L2 cache.

   - Power9 support for VAS, which is a new mechanism for accessing
     coprocessors, and initial support for using it with the NX
     compression accelerator.

   - Major work on the instruction emulation support, adding support for
     many new instructions, and reworking it so it can be used to
     implement the emulation needed to fixup alignment faults.

   - Support for guests under PowerVM to use the Power9 XIVE interrupt
     controller.

  And probably that many things again that are almost as interesting,
  but I had to keep the list short. Plus the usual fixes and cleanups as
  always.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Andreas Schwab,
  Aneesh Kumar K.V, Anju T Sudhakar, Arvind Yadav, Balbir Singh,
  Benjamin Herrenschmidt, Bhumika Goyal, Breno Leitao, Bryant G. Ly,
  Christophe Leroy, Cédric Le Goater, Dan Carpenter, Dou Liyang,
  Frederic Barrat, Gautham R. Shenoy, Geliang Tang, Geoff Levand, Hannes
  Reinecke, Haren Myneni, Ivan Mikhaylov, John Allen, Julia Lawall,
  LABBE Corentin, Laurentiu Tudor, Madhavan Srinivasan, Markus Elfring,
  Masahiro Yamada, Matt Brown, Michael Neuling, Murilo Opsfelder Araujo,
  Nathan Fontenot, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran,
  Paul Mackerras, Rashmica Gupta, Rob Herring, Rui Teng, Sam Bobroff,
  Santosh Sivaraj, Scott Wood, Shilpasri G Bhat, Sukadev Bhattiprolu,
  Suraj Jitindar Singh, Tobin C. Harding, Victor Aoqui"

* tag 'powerpc-4.14-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (321 commits)
  powerpc/xive: Fix section __init warning
  powerpc: Fix kernel crash in emulation of vector loads and stores
  powerpc/xive: improve debugging macros
  powerpc/xive: add XIVE Exploitation Mode to CAS
  powerpc/xive: introduce H_INT_ESB hcall
  powerpc/xive: add the HW IRQ number under xive_irq_data
  powerpc/xive: introduce xive_esb_write()
  powerpc/xive: rename xive_poke_esb() in xive_esb_read()
  powerpc/xive: guest exploitation of the XIVE interrupt controller
  powerpc/xive: introduce a common routine xive_queue_page_alloc()
  powerpc/sstep: Avoid used uninitialized error
  axonram: Return directly after a failed kzalloc() in axon_ram_probe()
  axonram: Improve a size determination in axon_ram_probe()
  axonram: Delete an error message for a failed memory allocation in axon_ram_probe()
  powerpc/powernv/npu: Move tlb flush before launching ATSD
  powerpc/macintosh: constify wf_sensor_ops structures
  powerpc/iommu: Use permission-specific DEVICE_ATTR variants
  powerpc/eeh: Delete an error out of memory message at init time
  powerpc/mm: Use seq_putc() in two functions
  macintosh: Convert to using %pOF instead of full_name
  ...

27 files changed, 3271 insertions, 136 deletions

diff --git a/arch/powerpc/platforms/powernv/Kconfig b/arch/powerpc/platforms/powernv/Kconfig
index 6a6f4ef46b9e..340cbe263b33 100644
--- a/arch/powerpc/platforms/powernv/Kconfig
+++ b/arch/powerpc/platforms/powernv/Kconfig
@@ -30,3 +30,25 @@ config OPAL_PRD
 	help
 	  This enables the opal-prd driver, a facility to run processor
 	  recovery diagnostics on OpenPower machines
+
+config PPC_MEMTRACE
+	bool "Enable removal of RAM from kernel mappings for tracing"
+	depends on PPC_POWERNV && MEMORY_HOTREMOVE
+	default n
+	help
+	  Enabling this option allows for the removal of memory (RAM)
+	  from the kernel mappings to be used for hardware tracing.
+
+config PPC_VAS
+	bool "IBM Virtual Accelerator Switchboard (VAS)"
+	depends on PPC_POWERNV && PPC_64K_PAGES
+	default y
+	help
+	  This enables support for IBM Virtual Accelerator Switchboard (VAS).
+
+	  VAS allows accelerators in co-processors like NX-GZIP and NX-842
+	  to be accessible to kernel subsystems and user processes.
+
+	  VAS adapters are found in POWER9 based systems.
+
+	  If unsure, say N.
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index b5d98cb3f482..37d60f7dd86d 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -2,7 +2,7 @@ obj-y			+= setup.o opal-wrappers.o opal.o opal-async.o idle.o
 obj-y			+= opal-rtc.o opal-nvram.o opal-lpc.o opal-flash.o
 obj-y			+= rng.o opal-elog.o opal-dump.o opal-sysparam.o opal-sensor.o
 obj-y			+= opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
-obj-y			+= opal-kmsg.o
+obj-y			+= opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
 
 obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o
@@ -12,3 +12,6 @@ obj-$(CONFIG_PPC_SCOM)	+= opal-xscom.o
 obj-$(CONFIG_MEMORY_FAILURE)	+= opal-memory-errors.o
 obj-$(CONFIG_TRACEPOINTS)	+= opal-tracepoints.o
 obj-$(CONFIG_OPAL_PRD)	+= opal-prd.o
+obj-$(CONFIG_PERF_EVENTS) += opal-imc.o
+obj-$(CONFIG_PPC_MEMTRACE)	+= memtrace.o
+obj-$(CONFIG_PPC_VAS)	+= vas.o vas-window.o
diff --git a/arch/powerpc/platforms/powernv/copy-paste.h b/arch/powerpc/platforms/powernv/copy-paste.h
new file mode 100644
index 000000000000..c9a503623431
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/copy-paste.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright 2016-17 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <asm/ppc-opcode.h>
+
+#define CR0_SHIFT	28
+#define CR0_MASK	0xF
+/*
+ * Copy/paste instructions:
+ *
+ *	copy RA,RB
+ *		Copy contents of address (RA) + effective_address(RB)
+ *		to internal copy-buffer.
+ *
+ *	paste RA,RB
+ *		Paste contents of internal copy-buffer to the address
+ *		(RA) + effective_address(RB)
+ */
+static inline int vas_copy(void *crb, int offset)
+{
+	asm volatile(PPC_COPY(%0, %1)";"
+		:
+		: "b" (offset), "b" (crb)
+		: "memory");
+
+	return 0;
+}
+
+static inline int vas_paste(void *paste_address, int offset)
+{
+	u32 cr;
+
+	cr = 0;
+	asm volatile(PPC_PASTE(%1, %2)";"
+		"mfocrf %0, 0x80;"
+		: "=r" (cr)
+		: "b" (offset), "b" (paste_address)
+		: "memory", "cr0");
+
+	return (cr >> CR0_SHIFT) & CR0_MASK;
+}
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 3f48f6df1cf3..8864065eba22 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -113,7 +113,6 @@ static ssize_t pnv_eeh_ei_write(struct file *filp,
 				size_t count, loff_t *ppos)
 {
 	struct pci_controller *hose = filp->private_data;
-	struct eeh_dev *edev;
 	struct eeh_pe *pe;
 	int pe_no, type, func;
 	unsigned long addr, mask;
@@ -135,13 +134,7 @@ static ssize_t pnv_eeh_ei_write(struct file *filp,
 		return -EINVAL;
 
 	/* Retrieve PE */
-	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev)
-		return -ENOMEM;
-	edev->phb = hose;
-	edev->pe_config_addr = pe_no;
-	pe = eeh_pe_get(edev);
-	kfree(edev);
+	pe = eeh_pe_get(hose, pe_no, 0);
 	if (!pe)
 		return -ENODEV;
 
@@ -359,6 +352,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	uint32_t pcie_flags;
 	int ret;
+	int config_addr = (pdn->busno << 8) | (pdn->devfn);
 
 	/*
 	 * When probing the root bridge, which doesn't have any
@@ -393,8 +387,7 @@ static void *pnv_eeh_probe(struct pci_dn *pdn, void *data)
 		}
 	}
 
-	edev->config_addr    = (pdn->busno << 8) | (pdn->devfn);
-	edev->pe_config_addr = phb->ioda.pe_rmap[edev->config_addr];
+	edev->pe_config_addr = phb->ioda.pe_rmap[config_addr];
 
 	/* Create PE */
 	ret = eeh_add_to_parent_pe(edev);
@@ -933,7 +926,6 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
 static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type,
 				     int pos, u16 mask)
 {
-	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	int i, status = 0;
 
 	/* Wait for Transaction Pending bit to be cleared */
@@ -947,7 +939,7 @@ static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type,
 
 	pr_warn("%s: Pending transaction while issuing %sFLR to %04x:%02x:%02x.%01x\n",
 		__func__, type,
-		edev->phb->global_number, pdn->busno,
+		pdn->phb->global_number, pdn->busno,
 		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 }
 
@@ -1381,7 +1373,6 @@ static int pnv_eeh_get_pe(struct pci_controller *hose,
 	struct pnv_phb *phb = hose->private_data;
 	struct pnv_ioda_pe *pnv_pe;
 	struct eeh_pe *dev_pe;
-	struct eeh_dev edev;
 
 	/*
 	 * If PHB supports compound PE, to fetch
@@ -1397,10 +1388,7 @@ static int pnv_eeh_get_pe(struct pci_controller *hose,
 	}
 
 	/* Find the PE according to PE# */
-	memset(&edev, 0, sizeof(struct eeh_dev));
-	edev.phb = hose;
-	edev.pe_config_addr = pe_no;
-	dev_pe = eeh_pe_get(&edev);
+	dev_pe = eeh_pe_get(hose, pe_no, 0);
 	if (!dev_pe)
 		return -EEXIST;
 
@@ -1711,6 +1699,7 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 	struct pnv_phb *phb;
 	s64 ret;
+	int config_addr = (pdn->busno << 8) | (pdn->devfn);
 
 	if (!edev)
 		return -EEXIST;
@@ -1725,14 +1714,14 @@ static int pnv_eeh_restore_config(struct pci_dn *pdn)
 	if (edev->physfn) {
 		ret = pnv_eeh_restore_vf_config(pdn);
 	} else {
-		phb = edev->phb->private_data;
+		phb = pdn->phb->private_data;
 		ret = opal_pci_reinit(phb->opal_id,
-				      OPAL_REINIT_PCI_DEV, edev->config_addr);
+				      OPAL_REINIT_PCI_DEV, config_addr);
 	}
 
 	if (ret) {
 		pr_warn("%s: Can't reinit PCI dev 0x%x (%lld)\n",
-			__func__, edev->config_addr, ret);
+			__func__, config_addr, ret);
 		return -EIO;
 	}
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index a553aeea7af6..9f59041a172b 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -69,7 +69,7 @@ static int pnv_save_sprs_for_deep_states(void)
 	 * all cpus at boot. Get these reg values of current cpu and use the
 	 * same across all cpus.
 	 */
-	uint64_t lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+	uint64_t lpcr_val = mfspr(SPRN_LPCR);
 	uint64_t hid0_val = mfspr(SPRN_HID0);
 	uint64_t hid1_val = mfspr(SPRN_HID1);
 	uint64_t hid4_val = mfspr(SPRN_HID4);
@@ -388,6 +388,14 @@ void power9_idle(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
+static void pnv_program_cpu_hotplug_lpcr(unsigned int cpu, u64 lpcr_val)
+{
+	u64 pir = get_hard_smp_processor_id(cpu);
+
+	mtspr(SPRN_LPCR, lpcr_val);
+	opal_slw_set_reg(pir, SPRN_LPCR, lpcr_val);
+}
+
 /*
  * pnv_cpu_offline: A function that puts the CPU into the deepest
  * available platform idle state on a CPU-Offline.
@@ -397,6 +405,20 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 {
 	unsigned long srr1;
 	u32 idle_states = pnv_get_supported_cpuidle_states();
+	u64 lpcr_val;
+
+	/*
+	 * We don't want to take decrementer interrupts while we are
+	 * offline, so clear LPCR:PECE1. We keep PECE2 (and
+	 * LPCR_PECE_HVEE on P9) enabled as to let IPIs in.
+	 *
+	 * If the CPU gets woken up by a special wakeup, ensure that
+	 * the SLW engine sets LPCR with decrementer bit cleared, else
+	 * the CPU will come back to the kernel due to a spurious
+	 * wakeup.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
 
 	__ppc64_runlatch_off();
 
@@ -428,6 +450,16 @@ unsigned long pnv_cpu_offline(unsigned int cpu)
 
 	__ppc64_runlatch_on();
 
+	/*
+	 * Re-enable decrementer interrupts in LPCR.
+	 *
+	 * Further, we want stop states to be woken up by decrementer
+	 * for non-hotplug cases. So program the LPCR via stop api as
+	 * well.
+	 */
+	lpcr_val = mfspr(SPRN_LPCR) | (u64)LPCR_PECE1;
+	pnv_program_cpu_hotplug_lpcr(cpu, lpcr_val);
+
 	return srr1;
 }
 #endif
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
new file mode 100644
index 000000000000..de470caf0784
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -0,0 +1,282 @@
+/*
+ * Copyright (C) IBM Corporation, 2014, 2017
+ * Anton Blanchard, Rashmica Gupta.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "memtrace: " fmt
+
+#include <linux/bitops.h>
+#include <linux/string.h>
+#include <linux/memblock.h>
+#include <linux/init.h>
+#include <linux/moduleparam.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <linux/slab.h>
+#include <linux/memory.h>
+#include <linux/memory_hotplug.h>
+#include <asm/machdep.h>
+#include <asm/debugfs.h>
+
+/* This enables us to keep track of the memory removed from each node. */
+struct memtrace_entry {
+	void *mem;
+	u64 start;
+	u64 size;
+	u32 nid;
+	struct dentry *dir;
+	char name[16];
+};
+
+static u64 memtrace_size;
+
+static struct memtrace_entry *memtrace_array;
+static unsigned int memtrace_array_nr;
+
+
+static ssize_t memtrace_read(struct file *filp, char __user *ubuf,
+			     size_t count, loff_t *ppos)
+{
+	struct memtrace_entry *ent = filp->private_data;
+
+	return simple_read_from_buffer(ubuf, count, ppos, ent->mem, ent->size);
+}
+
+static bool valid_memtrace_range(struct memtrace_entry *dev,
+				 unsigned long start, unsigned long size)
+{
+	if ((start >= dev->start) &&
+	    ((start + size) <= (dev->start + dev->size)))
+		return true;
+
+	return false;
+}
+
+static int memtrace_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long size = vma->vm_end - vma->vm_start;
+	struct memtrace_entry *dev = filp->private_data;
+
+	if (!valid_memtrace_range(dev, vma->vm_pgoff << PAGE_SHIFT, size))
+		return -EINVAL;
+
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (remap_pfn_range(vma, vma->vm_start,
+			    vma->vm_pgoff + (dev->start >> PAGE_SHIFT),
+			    size, vma->vm_page_prot))
+		return -EAGAIN;
+
+	return 0;
+}
+
+static const struct file_operations memtrace_fops = {
+	.llseek = default_llseek,
+	.read	= memtrace_read,
+	.mmap	= memtrace_mmap,
+	.open	= simple_open,
+};
+
+static void flush_memory_region(u64 base, u64 size)
+{
+	unsigned long line_size = ppc64_caches.l1d.size;
+	u64 end = base + size;
+	u64 addr;
+
+	base = round_down(base, line_size);
+	end = round_up(end, line_size);
+
+	for (addr = base; addr < end; addr += line_size)
+		asm volatile("dcbf 0,%0" : "=r" (addr) :: "memory");
+}
+
+static int check_memblock_online(struct memory_block *mem, void *arg)
+{
+	if (mem->state != MEM_ONLINE)
+		return -1;
+
+	return 0;
+}
+
+static int change_memblock_state(struct memory_block *mem, void *arg)
+{
+	unsigned long state = (unsigned long)arg;
+
+	mem->state = state;
+
+	return 0;
+}
+
+static bool memtrace_offline_pages(u32 nid, u64 start_pfn, u64 nr_pages)
+{
+	u64 end_pfn = start_pfn + nr_pages - 1;
+
+	if (walk_memory_range(start_pfn, end_pfn, NULL,
+	    check_memblock_online))
+		return false;
+
+	walk_memory_range(start_pfn, end_pfn, (void *)MEM_GOING_OFFLINE,
+			  change_memblock_state);
+
+	if (offline_pages(start_pfn, nr_pages)) {
+		walk_memory_range(start_pfn, end_pfn, (void *)MEM_ONLINE,
+				  change_memblock_state);
+		return false;
+	}
+
+	walk_memory_range(start_pfn, end_pfn, (void *)MEM_OFFLINE,
+			  change_memblock_state);
+
+	/* RCU grace period? */
+	flush_memory_region((u64)__va(start_pfn << PAGE_SHIFT),
+			    nr_pages << PAGE_SHIFT);
+
+	lock_device_hotplug();
+	remove_memory(nid, start_pfn << PAGE_SHIFT, nr_pages << PAGE_SHIFT);
+	unlock_device_hotplug();
+
+	return true;
+}
+
+static u64 memtrace_alloc_node(u32 nid, u64 size)
+{
+	u64 start_pfn, end_pfn, nr_pages;
+	u64 base_pfn;
+
+	if (!NODE_DATA(nid) || !node_spanned_pages(nid))
+		return 0;
+
+	start_pfn = node_start_pfn(nid);
+	end_pfn = node_end_pfn(nid);
+	nr_pages = size >> PAGE_SHIFT;
+
+	/* Trace memory needs to be aligned to the size */
+	end_pfn = round_down(end_pfn - nr_pages, nr_pages);
+
+	for (base_pfn = end_pfn; base_pfn > start_pfn; base_pfn -= nr_pages) {
+		if (memtrace_offline_pages(nid, base_pfn, nr_pages) == true)
+			return base_pfn << PAGE_SHIFT;
+	}
+
+	return 0;
+}
+
+static int memtrace_init_regions_runtime(u64 size)
+{
+	u32 nid;
+	u64 m;
+
+	memtrace_array = kcalloc(num_online_nodes(),
+				sizeof(struct memtrace_entry), GFP_KERNEL);
+	if (!memtrace_array) {
+		pr_err("Failed to allocate memtrace_array\n");
+		return -EINVAL;
+	}
+
+	for_each_online_node(nid) {
+		m = memtrace_alloc_node(nid, size);
+
+		/*
+		 * A node might not have any local memory, so warn but
+		 * continue on.
+		 */
+		if (!m) {
+			pr_err("Failed to allocate trace memory on node %d\n", nid);
+			continue;
+		}
+
+		pr_info("Allocated trace memory on node %d at 0x%016llx\n", nid, m);
+
+		memtrace_array[memtrace_array_nr].start = m;
+		memtrace_array[memtrace_array_nr].size = size;
+		memtrace_array[memtrace_array_nr].nid = nid;
+		memtrace_array_nr++;
+	}
+
+	return 0;
+}
+
+static struct dentry *memtrace_debugfs_dir;
+
+static int memtrace_init_debugfs(void)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < memtrace_array_nr; i++) {
+		struct dentry *dir;
+		struct memtrace_entry *ent = &memtrace_array[i];
+
+		ent->mem = ioremap(ent->start, ent->size);
+		/* Warn but continue on */
+		if (!ent->mem) {
+			pr_err("Failed to map trace memory at 0x%llx\n",
+				 ent->start);
+			ret = -1;
+			continue;
+		}
+
+		snprintf(ent->name, 16, "%08x", ent->nid);
+		dir = debugfs_create_dir(ent->name, memtrace_debugfs_dir);
+		if (!dir)
+			return -1;
+
+		ent->dir = dir;
+		debugfs_create_file("trace", 0400, dir, ent, &memtrace_fops);
+		debugfs_create_x64("start", 0400, dir, &ent->start);
+		debugfs_create_x64("size", 0400, dir, &ent->size);
+	}
+
+	return ret;
+}
+
+static int memtrace_enable_set(void *data, u64 val)
+{
+	if (memtrace_size)
+		return -EINVAL;
+
+	if (!val)
+		return -EINVAL;
+
+	/* Make sure size is aligned to a memory block */
+	if (val & (memory_block_size_bytes() - 1))
+		return -EINVAL;
+
+	if (memtrace_init_regions_runtime(val))
+		return -EINVAL;
+
+	if (memtrace_init_debugfs())
+		return -EINVAL;
+
+	memtrace_size = val;
+
+	return 0;
+}
+
+static int memtrace_enable_get(void *data, u64 *val)
+{
+	*val = memtrace_size;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(memtrace_init_fops, memtrace_enable_get,
+					memtrace_enable_set, "0x%016llx\n");
+
+static int memtrace_init(void)
+{
+	memtrace_debugfs_dir = debugfs_create_dir("memtrace",
+						  powerpc_debugfs_root);
+	if (!memtrace_debugfs_dir)
+		return -1;
+
+	debugfs_create_file("enable", 0600, memtrace_debugfs_dir,
+			    NULL, &memtrace_init_fops);
+
+	return 0;
+}
+machine_device_initcall(powernv, memtrace_init);
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 4c7b8591f737..2cb6cbea4b3b 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -546,6 +546,12 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 	unsigned long pid = npu_context->mm->context.id;
 
 	/*
+	 * Unfortunately the nest mmu does not support flushing specific
+	 * addresses so we have to flush the whole mm.
+	 */
+	flush_tlb_mm(npu_context->mm);
+
+	/*
 	 * Loop over all the NPUs this process is active on and launch
 	 * an invalidate.
 	 */
@@ -576,12 +582,6 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 		}
 	}
 
-	/*
-	 * Unfortunately the nest mmu does not support flushing specific
-	 * addresses so we have to flush the whole mm.
-	 */
-	flush_tlb_mm(npu_context->mm);
-
 	mmio_invalidate_wait(mmio_atsd_reg, flush);
 	if (flush)
 		/* Wait for the flush to complete */
diff --git a/arch/powerpc/platforms/powernv/opal-async.c b/arch/powerpc/platforms/powernv/opal-async.c
index 83bebeec0fea..cf33769a7b72 100644
--- a/arch/powerpc/platforms/powernv/opal-async.c
+++ b/arch/powerpc/platforms/powernv/opal-async.c
@@ -171,8 +171,8 @@ int __init opal_async_comp_init(void)
 
 	async = of_get_property(opal_node, "opal-msg-async-num", NULL);
 	if (!async) {
-		pr_err("%s: %s has no opal-msg-async-num\n",
-				__func__, opal_node->full_name);
+		pr_err("%s: %pOF has no opal-msg-async-num\n",
+				__func__, opal_node);
 		err = -ENOENT;
 		goto out_opal_node;
 	}
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 4ec6219287fc..2fa3ac80cb4e 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -520,7 +520,7 @@ out:
  *   update_flash	: Flash new firmware image
  *
  */
-static struct bin_attribute image_data_attr = {
+static const struct bin_attribute image_data_attr = {
 	.attr = {.name = "image", .mode = 0200},
 	.size = MAX_IMAGE_SIZE,	/* Limit image size */
 	.write = image_data_write,
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index 88f3c61eec95..d78fed728cdf 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -30,6 +30,8 @@
 #include <asm/cputable.h>
 #include <asm/machdep.h>
 
+#include "powernv.h"
+
 static int opal_hmi_handler_nb_init;
 struct OpalHmiEvtNode {
 	struct list_head list;
@@ -267,8 +269,6 @@ static void hmi_event_handler(struct work_struct *work)
 	spin_unlock_irqrestore(&opal_hmi_evt_lock, flags);
 
 	if (unrecoverable) {
-		int ret;
-
 		/* Pull all HMI events from OPAL before we panic. */
 		while (opal_get_msg(__pa(&msg), sizeof(msg)) == OPAL_SUCCESS) {
 			u32 type;
@@ -284,23 +284,7 @@ static void hmi_event_handler(struct work_struct *work)
 			print_hmi_event_info(hmi_evt);
 		}
 
-		/*
-		 * Unrecoverable HMI exception. We need to inform BMC/OCC
-		 * about this error so that it can collect relevant data
-		 * for error analysis before rebooting.
-		 */
-		ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR,
-			"Unrecoverable HMI exception");
-		if (ret == OPAL_UNSUPPORTED) {
-			pr_emerg("Reboot type %d not supported\n",
-						OPAL_REBOOT_PLATFORM_ERROR);
-		}
-
-		/*
-		 * Fall through and panic if opal_cec_reboot2() returns
-		 * OPAL_UNSUPPORTED.
-		 */
-		panic("Unrecoverable HMI exception");
+		pnv_platform_error_reboot(NULL, "Unrecoverable HMI exception");
 	}
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-imc.c b/arch/powerpc/platforms/powernv/opal-imc.c
new file mode 100644
index 000000000000..21f6531fae20
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-imc.c
@@ -0,0 +1,226 @@
+/*
+ * OPAL IMC interface detection driver
+ * Supported on POWERNV platform
+ *
+ * Copyright	(C) 2017 Madhavan Srinivasan, IBM Corporation.
+ *		(C) 2017 Anju T Sudhakar, IBM Corporation.
+ *		(C) 2017 Hemant K Shaw, IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or later version.
+ */
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+#include <linux/crash_dump.h>
+#include <asm/opal.h>
+#include <asm/io.h>
+#include <asm/imc-pmu.h>
+#include <asm/cputhreads.h>
+
+/*
+ * imc_get_mem_addr_nest: Function to get nest counter memory region
+ * for each chip
+ */
+static int imc_get_mem_addr_nest(struct device_node *node,
+				 struct imc_pmu *pmu_ptr,
+				 u32 offset)
+{
+	int nr_chips = 0, i;
+	u64 *base_addr_arr, baddr;
+	u32 *chipid_arr;
+
+	nr_chips = of_property_count_u32_elems(node, "chip-id");
+	if (nr_chips <= 0)
+		return -ENODEV;
+
+	base_addr_arr = kcalloc(nr_chips, sizeof(u64), GFP_KERNEL);
+	if (!base_addr_arr)
+		return -ENOMEM;
+
+	chipid_arr = kcalloc(nr_chips, sizeof(u32), GFP_KERNEL);
+	if (!chipid_arr)
+		return -ENOMEM;
+
+	if (of_property_read_u32_array(node, "chip-id", chipid_arr, nr_chips))
+		goto error;
+
+	if (of_property_read_u64_array(node, "base-addr", base_addr_arr,
+								nr_chips))
+		goto error;
+
+	pmu_ptr->mem_info = kcalloc(nr_chips, sizeof(struct imc_mem_info),
+								GFP_KERNEL);
+	if (!pmu_ptr->mem_info)
+		goto error;
+
+	for (i = 0; i < nr_chips; i++) {
+		pmu_ptr->mem_info[i].id = chipid_arr[i];
+		baddr = base_addr_arr[i] + offset;
+		pmu_ptr->mem_info[i].vbase = phys_to_virt(baddr);
+	}
+
+	pmu_ptr->imc_counter_mmaped = true;
+	kfree(base_addr_arr);
+	kfree(chipid_arr);
+	return 0;
+
+error:
+	kfree(pmu_ptr->mem_info);
+	kfree(base_addr_arr);
+	kfree(chipid_arr);
+	return -1;
+}
+
+/*
+ * imc_pmu_create : Takes the parent device which is the pmu unit, pmu_index
+ *		    and domain as the inputs.
+ * Allocates memory for the struct imc_pmu, sets up its domain, size and offsets
+ */
+static int imc_pmu_create(struct device_node *parent, int pmu_index, int domain)
+{
+	int ret = 0;
+	struct imc_pmu *pmu_ptr;
+	u32 offset;
+
+	/* memory for pmu */
+	pmu_ptr = kzalloc(sizeof(struct imc_pmu), GFP_KERNEL);
+	if (!pmu_ptr)
+		return -ENOMEM;
+
+	/* Set the domain */
+	pmu_ptr->domain = domain;
+
+	ret = of_property_read_u32(parent, "size", &pmu_ptr->counter_mem_size);
+	if (ret) {
+		ret = -EINVAL;
+		goto free_pmu;
+	}
+
+	if (!of_property_read_u32(parent, "offset", &offset)) {
+		if (imc_get_mem_addr_nest(parent, pmu_ptr, offset)) {
+			ret = -EINVAL;
+			goto free_pmu;
+		}
+	}
+
+	/* Function to register IMC pmu */
+	ret = init_imc_pmu(parent, pmu_ptr, pmu_index);
+	if (ret)
+		pr_err("IMC PMU %s Register failed\n", pmu_ptr->pmu.name);
+
+	return 0;
+
+free_pmu:
+	kfree(pmu_ptr);
+	return ret;
+}
+
+static void disable_nest_pmu_counters(void)
+{
+	int nid, cpu;
+	const struct cpumask *l_cpumask;
+
+	get_online_cpus();
+	for_each_online_node(nid) {
+		l_cpumask = cpumask_of_node(nid);
+		cpu = cpumask_first(l_cpumask);
+		opal_imc_counters_stop(OPAL_IMC_COUNTERS_NEST,
+				       get_hard_smp_processor_id(cpu));
+	}
+	put_online_cpus();
+}
+
+static void disable_core_pmu_counters(void)
+{
+	cpumask_t cores_map;
+	int cpu, rc;
+
+	get_online_cpus();
+	/* Disable the IMC Core functions */
+	cores_map = cpu_online_cores_map();
+	for_each_cpu(cpu, &cores_map) {
+		rc = opal_imc_counters_stop(OPAL_IMC_COUNTERS_CORE,
+					    get_hard_smp_processor_id(cpu));
+		if (rc)
+			pr_err("%s: Failed to stop Core (cpu = %d)\n",
+				__FUNCTION__, cpu);
+	}
+	put_online_cpus();
+}
+
+static int opal_imc_counters_probe(struct platform_device *pdev)
+{
+	struct device_node *imc_dev = pdev->dev.of_node;
+	int pmu_count = 0, domain;
+	u32 type;
+
+	/*
+	 * Check whether this is kdump kernel. If yes, force the engines to
+	 * stop and return.
+	 */
+	if (is_kdump_kernel()) {
+		disable_nest_pmu_counters();
+		disable_core_pmu_counters();
+		return -ENODEV;
+	}
+
+	for_each_compatible_node(imc_dev, NULL, IMC_DTB_UNIT_COMPAT) {
+		if (of_property_read_u32(imc_dev, "type", &type)) {
+			pr_warn("IMC Device without type property\n");
+			continue;
+		}
+
+		switch (type) {
+		case IMC_TYPE_CHIP:
+			domain = IMC_DOMAIN_NEST;
+			break;
+		case IMC_TYPE_CORE:
+			domain =IMC_DOMAIN_CORE;
+			break;
+		case IMC_TYPE_THREAD:
+			domain = IMC_DOMAIN_THREAD;
+			break;
+		default:
+			pr_warn("IMC Unknown Device type \n");
+			domain = -1;
+			break;
+		}
+
+		if (!imc_pmu_create(imc_dev, pmu_count, domain))
+			pmu_count++;
+	}
+
+	return 0;
+}
+
+static void opal_imc_counters_shutdown(struct platform_device *pdev)
+{
+	/*
+	 * Function only stops the engines which is bare minimum.
+	 * TODO: Need to handle proper memory cleanup and pmu
+	 * unregister.
+	 */
+	disable_nest_pmu_counters();
+	disable_core_pmu_counters();
+}
+
+static const struct of_device_id opal_imc_match[] = {
+	{ .compatible = IMC_DTB_COMPAT },
+	{},
+};
+
+static struct platform_driver opal_imc_driver = {
+	.driver = {
+		.name = "opal-imc-counters",
+		.of_match_table = opal_imc_match,
+	},
+	.probe = opal_imc_counters_probe,
+	.shutdown = opal_imc_counters_shutdown,
+};
+
+builtin_platform_driver(opal_imc_driver);
diff --git a/arch/powerpc/platforms/powernv/opal-powercap.c b/arch/powerpc/platforms/powernv/opal-powercap.c
new file mode 100644
index 000000000000..badb29bde93f
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-powercap.c
@@ -0,0 +1,244 @@
+/*
+ * PowerNV OPAL Powercap interface
+ *
+ * Copyright 2017 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt)     "opal-powercap: " fmt
+
+#include <linux/of.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+
+#include <asm/opal.h>
+
+DEFINE_MUTEX(powercap_mutex);
+
+static struct kobject *powercap_kobj;
+
+struct powercap_attr {
+	u32 handle;
+	struct kobj_attribute attr;
+};
+
+static struct pcap {
+	struct attribute_group pg;
+	struct powercap_attr *pattrs;
+} *pcaps;
+
+static ssize_t powercap_show(struct kobject *kobj, struct kobj_attribute *attr,
+			     char *buf)
+{
+	struct powercap_attr *pcap_attr = container_of(attr,
+						struct powercap_attr, attr);
+	struct opal_msg msg;
+	u32 pcap;
+	int ret, token;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		pr_devel("Failed to get token\n");
+		return token;
+	}
+
+	ret = mutex_lock_interruptible(&powercap_mutex);
+	if (ret)
+		goto out_token;
+
+	ret = opal_get_powercap(pcap_attr->handle, token, (u32 *)__pa(&pcap));
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_devel("Failed to wait for the async response\n");
+			ret = -EIO;
+			goto out;
+		}
+		ret = opal_error_code(opal_get_async_rc(msg));
+		if (!ret) {
+			ret = sprintf(buf, "%u\n", be32_to_cpu(pcap));
+			if (ret < 0)
+				ret = -EIO;
+		}
+		break;
+	case OPAL_SUCCESS:
+		ret = sprintf(buf, "%u\n", be32_to_cpu(pcap));
+		if (ret < 0)
+			ret = -EIO;
+		break;
+	default:
+		ret = opal_error_code(ret);
+	}
+
+out:
+	mutex_unlock(&powercap_mutex);
+out_token:
+	opal_async_release_token(token);
+	return ret;
+}
+
+static ssize_t powercap_store(struct kobject *kobj,
+			      struct kobj_attribute *attr, const char *buf,
+			      size_t count)
+{
+	struct powercap_attr *pcap_attr = container_of(attr,
+						struct powercap_attr, attr);
+	struct opal_msg msg;
+	u32 pcap;
+	int ret, token;
+
+	ret = kstrtoint(buf, 0, &pcap);
+	if (ret)
+		return ret;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		pr_devel("Failed to get token\n");
+		return token;
+	}
+
+	ret = mutex_lock_interruptible(&powercap_mutex);
+	if (ret)
+		goto out_token;
+
+	ret = opal_set_powercap(pcap_attr->handle, token, pcap);
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_devel("Failed to wait for the async response\n");
+			ret = -EIO;
+			goto out;
+		}
+		ret = opal_error_code(opal_get_async_rc(msg));
+		if (!ret)
+			ret = count;
+		break;
+	case OPAL_SUCCESS:
+		ret = count;
+		break;
+	default:
+		ret = opal_error_code(ret);
+	}
+
+out:
+	mutex_unlock(&powercap_mutex);
+out_token:
+	opal_async_release_token(token);
+	return ret;
+}
+
+static void powercap_add_attr(int handle, const char *name,
+			      struct powercap_attr *attr)
+{
+	attr->handle = handle;
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = name;
+	attr->attr.attr.mode = 0444;
+	attr->attr.show = powercap_show;
+}
+
+void __init opal_powercap_init(void)
+{
+	struct device_node *powercap, *node;
+	int i = 0;
+
+	powercap = of_find_compatible_node(NULL, NULL, "ibm,opal-powercap");
+	if (!powercap) {
+		pr_devel("Powercap node not found\n");
+		return;
+	}
+
+	pcaps = kcalloc(of_get_child_count(powercap), sizeof(*pcaps),
+			GFP_KERNEL);
+	if (!pcaps)
+		return;
+
+	powercap_kobj = kobject_create_and_add("powercap", opal_kobj);
+	if (!powercap_kobj) {
+		pr_warn("Failed to create powercap kobject\n");
+		goto out_pcaps;
+	}
+
+	i = 0;
+	for_each_child_of_node(powercap, node) {
+		u32 cur, min, max;
+		int j = 0;
+		bool has_cur = false, has_min = false, has_max = false;
+
+		if (!of_property_read_u32(node, "powercap-min", &min)) {
+			j++;
+			has_min = true;
+		}
+
+		if (!of_property_read_u32(node, "powercap-max", &max)) {
+			j++;
+			has_max = true;
+		}
+
+		if (!of_property_read_u32(node, "powercap-current", &cur)) {
+			j++;
+			has_cur = true;
+		}
+
+		pcaps[i].pattrs = kcalloc(j, sizeof(struct powercap_attr),
+					  GFP_KERNEL);
+		if (!pcaps[i].pattrs)
+			goto out_pcaps_pattrs;
+
+		pcaps[i].pg.attrs = kcalloc(j + 1, sizeof(struct attribute *),
+					    GFP_KERNEL);
+		if (!pcaps[i].pg.attrs) {
+			kfree(pcaps[i].pattrs);
+			goto out_pcaps_pattrs;
+		}
+
+		j = 0;
+		pcaps[i].pg.name = node->name;
+		if (has_min) {
+			powercap_add_attr(min, "powercap-min",
+					  &pcaps[i].pattrs[j]);
+			pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr;
+			j++;
+		}
+
+		if (has_max) {
+			powercap_add_attr(max, "powercap-max",
+					  &pcaps[i].pattrs[j]);
+			pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr;
+			j++;
+		}
+
+		if (has_cur) {
+			powercap_add_attr(cur, "powercap-current",
+					  &pcaps[i].pattrs[j]);
+			pcaps[i].pattrs[j].attr.attr.mode |= 0220;
+			pcaps[i].pattrs[j].attr.store = powercap_store;
+			pcaps[i].pg.attrs[j] = &pcaps[i].pattrs[j].attr.attr;
+			j++;
+		}
+
+		if (sysfs_create_group(powercap_kobj, &pcaps[i].pg)) {
+			pr_warn("Failed to create powercap attribute group %s\n",
+				pcaps[i].pg.name);
+			goto out_pcaps_pattrs;
+		}
+		i++;
+	}
+
+	return;
+
+out_pcaps_pattrs:
+	while (--i >= 0) {
+		kfree(pcaps[i].pattrs);
+		kfree(pcaps[i].pg.attrs);
+	}
+	kobject_put(powercap_kobj);
+out_pcaps:
+	kfree(pcaps);
+}
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 2d6ee1c5ad85..de4dd09f4a15 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -241,15 +241,9 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf,
 
 	size = be16_to_cpu(hdr.size);
 
-	msg = kmalloc(size, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	rc = copy_from_user(msg, buf, size);
-	if (rc) {
-		size = -EFAULT;
-		goto out_free;
-	}
+	msg = memdup_user(buf, size);
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
 
 	rc = opal_prd_msg(msg);
 	if (rc) {
@@ -257,7 +251,6 @@ static ssize_t opal_prd_write(struct file *file, const char __user *buf,
 		size = -EIO;
 	}
 
-out_free:
 	kfree(msg);
 
 	return size;
diff --git a/arch/powerpc/platforms/powernv/opal-psr.c b/arch/powerpc/platforms/powernv/opal-psr.c
new file mode 100644
index 000000000000..7313b7fc9071
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-psr.c
@@ -0,0 +1,175 @@
+/*
+ * PowerNV OPAL Power-Shift-Ratio interface
+ *
+ * Copyright 2017 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt)     "opal-psr: " fmt
+
+#include <linux/of.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+
+#include <asm/opal.h>
+
+DEFINE_MUTEX(psr_mutex);
+
+static struct kobject *psr_kobj;
+
+struct psr_attr {
+	u32 handle;
+	struct kobj_attribute attr;
+} *psr_attrs;
+
+static ssize_t psr_show(struct kobject *kobj, struct kobj_attribute *attr,
+			char *buf)
+{
+	struct psr_attr *psr_attr = container_of(attr, struct psr_attr, attr);
+	struct opal_msg msg;
+	int psr, ret, token;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		pr_devel("Failed to get token\n");
+		return token;
+	}
+
+	ret = mutex_lock_interruptible(&psr_mutex);
+	if (ret)
+		goto out_token;
+
+	ret = opal_get_power_shift_ratio(psr_attr->handle, token,
+					    (u32 *)__pa(&psr));
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_devel("Failed to wait for the async response\n");
+			ret = -EIO;
+			goto out;
+		}
+		ret = opal_error_code(opal_get_async_rc(msg));
+		if (!ret) {
+			ret = sprintf(buf, "%u\n", be32_to_cpu(psr));
+			if (ret < 0)
+				ret = -EIO;
+		}
+		break;
+	case OPAL_SUCCESS:
+		ret = sprintf(buf, "%u\n", be32_to_cpu(psr));
+		if (ret < 0)
+			ret = -EIO;
+		break;
+	default:
+		ret = opal_error_code(ret);
+	}
+
+out:
+	mutex_unlock(&psr_mutex);
+out_token:
+	opal_async_release_token(token);
+	return ret;
+}
+
+static ssize_t psr_store(struct kobject *kobj, struct kobj_attribute *attr,
+			 const char *buf, size_t count)
+{
+	struct psr_attr *psr_attr = container_of(attr, struct psr_attr, attr);
+	struct opal_msg msg;
+	int psr, ret, token;
+
+	ret = kstrtoint(buf, 0, &psr);
+	if (ret)
+		return ret;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		pr_devel("Failed to get token\n");
+		return token;
+	}
+
+	ret = mutex_lock_interruptible(&psr_mutex);
+	if (ret)
+		goto out_token;
+
+	ret = opal_set_power_shift_ratio(psr_attr->handle, token, psr);
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_devel("Failed to wait for the async response\n");
+			ret = -EIO;
+			goto out;
+		}
+		ret = opal_error_code(opal_get_async_rc(msg));
+		if (!ret)
+			ret = count;
+		break;
+	case OPAL_SUCCESS:
+		ret = count;
+		break;
+	default:
+		ret = opal_error_code(ret);
+	}
+
+out:
+	mutex_unlock(&psr_mutex);
+out_token:
+	opal_async_release_token(token);
+	return ret;
+}
+
+void __init opal_psr_init(void)
+{
+	struct device_node *psr, *node;
+	int i = 0;
+
+	psr = of_find_compatible_node(NULL, NULL,
+				      "ibm,opal-power-shift-ratio");
+	if (!psr) {
+		pr_devel("Power-shift-ratio node not found\n");
+		return;
+	}
+
+	psr_attrs = kcalloc(of_get_child_count(psr), sizeof(struct psr_attr),
+			    GFP_KERNEL);
+	if (!psr_attrs)
+		return;
+
+	psr_kobj = kobject_create_and_add("psr", opal_kobj);
+	if (!psr_kobj) {
+		pr_warn("Failed to create psr kobject\n");
+		goto out;
+	}
+
+	for_each_child_of_node(psr, node) {
+		if (of_property_read_u32(node, "handle",
+					 &psr_attrs[i].handle))
+			goto out_kobj;
+
+		sysfs_attr_init(&psr_attrs[i].attr.attr);
+		if (of_property_read_string(node, "label",
+					    &psr_attrs[i].attr.attr.name))
+			goto out_kobj;
+		psr_attrs[i].attr.attr.mode = 0664;
+		psr_attrs[i].attr.show = psr_show;
+		psr_attrs[i].attr.store = psr_store;
+		if (sysfs_create_file(psr_kobj, &psr_attrs[i].attr.attr)) {
+			pr_devel("Failed to create psr sysfs file %s\n",
+				 psr_attrs[i].attr.attr.name);
+			goto out_kobj;
+		}
+		i++;
+	}
+
+	return;
+out_kobj:
+	kobject_put(psr_kobj);
+out:
+	kfree(psr_attrs);
+}
diff --git a/arch/powerpc/platforms/powernv/opal-sensor-groups.c b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
new file mode 100644
index 000000000000..7e5a235ebf76
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/opal-sensor-groups.c
@@ -0,0 +1,212 @@
+/*
+ * PowerNV OPAL Sensor-groups interface
+ *
+ * Copyright 2017 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt)     "opal-sensor-groups: " fmt
+
+#include <linux/of.h>
+#include <linux/kobject.h>
+#include <linux/slab.h>
+
+#include <asm/opal.h>
+
+DEFINE_MUTEX(sg_mutex);
+
+static struct kobject *sg_kobj;
+
+struct sg_attr {
+	u32 handle;
+	struct kobj_attribute attr;
+};
+
+static struct sensor_group {
+	char name[20];
+	struct attribute_group sg;
+	struct sg_attr *sgattrs;
+} *sgs;
+
+static ssize_t sg_store(struct kobject *kobj, struct kobj_attribute *attr,
+			const char *buf, size_t count)
+{
+	struct sg_attr *sattr = container_of(attr, struct sg_attr, attr);
+	struct opal_msg msg;
+	u32 data;
+	int ret, token;
+
+	ret = kstrtoint(buf, 0, &data);
+	if (ret)
+		return ret;
+
+	if (data != 1)
+		return -EINVAL;
+
+	token = opal_async_get_token_interruptible();
+	if (token < 0) {
+		pr_devel("Failed to get token\n");
+		return token;
+	}
+
+	ret = mutex_lock_interruptible(&sg_mutex);
+	if (ret)
+		goto out_token;
+
+	ret = opal_sensor_group_clear(sattr->handle, token);
+	switch (ret) {
+	case OPAL_ASYNC_COMPLETION:
+		ret = opal_async_wait_response(token, &msg);
+		if (ret) {
+			pr_devel("Failed to wait for the async response\n");
+			ret = -EIO;
+			goto out;
+		}
+		ret = opal_error_code(opal_get_async_rc(msg));
+		if (!ret)
+			ret = count;
+		break;
+	case OPAL_SUCCESS:
+		ret = count;
+		break;
+	default:
+		ret = opal_error_code(ret);
+	}
+
+out:
+	mutex_unlock(&sg_mutex);
+out_token:
+	opal_async_release_token(token);
+	return ret;
+}
+
+static struct sg_ops_info {
+	int opal_no;
+	const char *attr_name;
+	ssize_t (*store)(struct kobject *kobj, struct kobj_attribute *attr,
+			const char *buf, size_t count);
+} ops_info[] = {
+	{ OPAL_SENSOR_GROUP_CLEAR, "clear", sg_store },
+};
+
+static void add_attr(int handle, struct sg_attr *attr, int index)
+{
+	attr->handle = handle;
+	sysfs_attr_init(&attr->attr.attr);
+	attr->attr.attr.name = ops_info[index].attr_name;
+	attr->attr.attr.mode = 0220;
+	attr->attr.store = ops_info[index].store;
+}
+
+static int add_attr_group(const __be32 *ops, int len, struct sensor_group *sg,
+			   u32 handle)
+{
+	int i, j;
+	int count = 0;
+
+	for (i = 0; i < len; i++)
+		for (j = 0; j < ARRAY_SIZE(ops_info); j++)
+			if (be32_to_cpu(ops[i]) == ops_info[j].opal_no) {
+				add_attr(handle, &sg->sgattrs[count], j);
+				sg->sg.attrs[count] =
+					&sg->sgattrs[count].attr.attr;
+				count++;
+			}
+
+	return sysfs_create_group(sg_kobj, &sg->sg);
+}
+
+static int get_nr_attrs(const __be32 *ops, int len)
+{
+	int i, j;
+	int nr_attrs = 0;
+
+	for (i = 0; i < len; i++)
+		for (j = 0; j < ARRAY_SIZE(ops_info); j++)
+			if (be32_to_cpu(ops[i]) == ops_info[j].opal_no)
+				nr_attrs++;
+
+	return nr_attrs;
+}
+
+void __init opal_sensor_groups_init(void)
+{
+	struct device_node *sg, *node;
+	int i = 0;
+
+	sg = of_find_compatible_node(NULL, NULL, "ibm,opal-sensor-group");
+	if (!sg) {
+		pr_devel("Sensor groups node not found\n");
+		return;
+	}
+
+	sgs = kcalloc(of_get_child_count(sg), sizeof(*sgs), GFP_KERNEL);
+	if (!sgs)
+		return;
+
+	sg_kobj = kobject_create_and_add("sensor_groups", opal_kobj);
+	if (!sg_kobj) {
+		pr_warn("Failed to create sensor group kobject\n");
+		goto out_sgs;
+	}
+
+	for_each_child_of_node(sg, node) {
+		const __be32 *ops;
+		u32 sgid, len, nr_attrs, chipid;
+
+		ops = of_get_property(node, "ops", &len);
+		if (!ops)
+			continue;
+
+		nr_attrs = get_nr_attrs(ops, len);
+		if (!nr_attrs)
+			continue;
+
+		sgs[i].sgattrs = kcalloc(nr_attrs, sizeof(struct sg_attr),
+					 GFP_KERNEL);
+		if (!sgs[i].sgattrs)
+			goto out_sgs_sgattrs;
+
+		sgs[i].sg.attrs = kcalloc(nr_attrs + 1,
+					  sizeof(struct attribute *),
+					  GFP_KERNEL);
+
+		if (!sgs[i].sg.attrs) {
+			kfree(sgs[i].sgattrs);
+			goto out_sgs_sgattrs;
+		}
+
+		if (of_property_read_u32(node, "sensor-group-id", &sgid)) {
+			pr_warn("sensor-group-id property not found\n");
+			goto out_sgs_sgattrs;
+		}
+
+		if (!of_property_read_u32(node, "ibm,chip-id", &chipid))
+			sprintf(sgs[i].name, "%s%d", node->name, chipid);
+		else
+			sprintf(sgs[i].name, "%s", node->name);
+
+		sgs[i].sg.name = sgs[i].name;
+		if (add_attr_group(ops, len, &sgs[i], sgid)) {
+			pr_warn("Failed to create sensor attribute group %s\n",
+				sgs[i].sg.name);
+			goto out_sgs_sgattrs;
+		}
+		i++;
+	}
+
+	return;
+
+out_sgs_sgattrs:
+	while (--i >= 0) {
+		kfree(sgs[i].sgattrs);
+		kfree(sgs[i].sg.attrs);
+	}
+	kobject_put(sg_kobj);
+out_sgs:
+	kfree(sgs);
+}
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 4ca6c26a56d5..8c1ede2d3f7e 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -27,7 +27,7 @@
 
 	.globl opal_tracepoint_refcount
 opal_tracepoint_refcount:
-	.llong	0
+	.8byte	0
 
 	.section	".text"
 
@@ -310,3 +310,12 @@ OPAL_CALL(opal_xive_dump,			OPAL_XIVE_DUMP);
 OPAL_CALL(opal_npu_init_context,		OPAL_NPU_INIT_CONTEXT);
 OPAL_CALL(opal_npu_destroy_context,		OPAL_NPU_DESTROY_CONTEXT);
 OPAL_CALL(opal_npu_map_lpar,			OPAL_NPU_MAP_LPAR);
+OPAL_CALL(opal_imc_counters_init,		OPAL_IMC_COUNTERS_INIT);
+OPAL_CALL(opal_imc_counters_start,		OPAL_IMC_COUNTERS_START);
+OPAL_CALL(opal_imc_counters_stop,		OPAL_IMC_COUNTERS_STOP);
+OPAL_CALL(opal_pci_set_p2p,			OPAL_PCI_SET_P2P);
+OPAL_CALL(opal_get_powercap,			OPAL_GET_POWERCAP);
+OPAL_CALL(opal_set_powercap,			OPAL_SET_POWERCAP);
+OPAL_CALL(opal_get_power_shift_ratio,		OPAL_GET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_set_power_shift_ratio,		OPAL_SET_POWER_SHIFT_RATIO);
+OPAL_CALL(opal_sensor_group_clear,		OPAL_SENSOR_GROUP_CLEAR);
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 28651fb25417..81c0a943dea9 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -36,14 +36,14 @@ static scom_map_t opal_scom_map(struct device_node *dev, u64 reg, u64 count)
 	const __be32 *gcid;
 
 	if (!of_get_property(dev, "scom-controller", NULL)) {
-		pr_err("%s: device %s is not a SCOM controller\n",
-			__func__, dev->full_name);
+		pr_err("%s: device %pOF is not a SCOM controller\n",
+			__func__, dev);
 		return SCOM_MAP_INVALID;
 	}
 	gcid = of_get_property(dev, "ibm,chip-id", NULL);
 	if (!gcid) {
-		pr_err("%s: device %s has no ibm,chip-id\n",
-			__func__, dev->full_name);
+		pr_err("%s: device %pOF has no ibm,chip-id\n",
+			__func__, dev);
 		return SCOM_MAP_INVALID;
 	}
 	m = kmalloc(sizeof(struct opal_scom_map), GFP_KERNEL);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index cad6b57ce494..65c79ecf5a4d 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
+#include <linux/of_address.h>
 #include <linux/interrupt.h>
 #include <linux/notifier.h>
 #include <linux/slab.h>
@@ -25,11 +26,17 @@
 #include <linux/memblock.h>
 #include <linux/kthread.h>
 #include <linux/freezer.h>
+#include <linux/printk.h>
+#include <linux/kmsg_dump.h>
+#include <linux/console.h>
+#include <linux/sched/debug.h>
 
 #include <asm/machdep.h>
 #include <asm/opal.h>
 #include <asm/firmware.h>
 #include <asm/mce.h>
+#include <asm/imc-pmu.h>
+#include <asm/bug.h>
 
 #include "powernv.h"
 
@@ -162,12 +169,9 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node,
 			sizeof(struct mcheck_recoverable_range);
 
 	/*
-	 * Allocate a buffer to hold the MC recoverable ranges. We would be
-	 * accessing them in real mode, hence it needs to be within
-	 * RMO region.
+	 * Allocate a buffer to hold the MC recoverable ranges.
 	 */
-	mc_recoverable_range =__va(memblock_alloc_base(size, __alignof__(u64),
-							ppc64_rma_size));
+	mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64)));
 	memset(mc_recoverable_range, 0, size);
 
 	for (i = 0; i < mc_recoverable_range_len; i++) {
@@ -422,24 +426,88 @@ static int opal_recover_mce(struct pt_regs *regs,
 		/* Fatal machine check */
 		pr_err("Machine check interrupt is fatal\n");
 		recovered = 0;
-	} else if ((evt->severity == MCE_SEV_ERROR_SYNC) &&
-			(user_mode(regs) && !is_global_init(current))) {
+	}
+
+	if (!recovered && evt->severity == MCE_SEV_ERROR_SYNC) {
 		/*
-		 * For now, kill the task if we have received exception when
-		 * in userspace.
+		 * Try to kill processes if we get a synchronous machine check
+		 * (e.g., one caused by execution of this instruction). This
+		 * will devolve into a panic if we try to kill init or are in
+		 * an interrupt etc.
 		 *
 		 * TODO: Queue up this address for hwpoisioning later.
+		 * TODO: This is not quite right for d-side machine
+		 *       checks ->nip is not necessarily the important
+		 *       address.
 		 */
-		_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
-		recovered = 1;
+		if ((user_mode(regs))) {
+			_exception(SIGBUS, regs, BUS_MCEERR_AR, regs->nip);
+			recovered = 1;
+		} else if (die_will_crash()) {
+			/*
+			 * die() would kill the kernel, so better to go via
+			 * the platform reboot code that will log the
+			 * machine check.
+			 */
+			recovered = 0;
+		} else {
+			die("Machine check", regs, SIGBUS);
+			recovered = 1;
+		}
 	}
+
 	return recovered;
 }
 
+void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg)
+{
+	/*
+	 * This is mostly taken from kernel/panic.c, but tries to do
+	 * relatively minimal work. Don't use delay functions (TB may
+	 * be broken), don't crash dump (need to set a firmware log),
+	 * don't run notifiers. We do want to get some information to
+	 * Linux console.
+	 */
+	console_verbose();
+	bust_spinlocks(1);
+	pr_emerg("Hardware platform error: %s\n", msg);
+	if (regs)
+		show_regs(regs);
+	smp_send_stop();
+	printk_safe_flush_on_panic();
+	kmsg_dump(KMSG_DUMP_PANIC);
+	bust_spinlocks(0);
+	debug_locks_off();
+	console_flush_on_panic();
+
+	/*
+	 * Don't bother to shut things down because this will
+	 * xstop the system.
+	 */
+	if (opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR, msg)
+						== OPAL_UNSUPPORTED) {
+		pr_emerg("Reboot type %d not supported for %s\n",
+				OPAL_REBOOT_PLATFORM_ERROR, msg);
+	}
+
+	/*
+	 * We reached here. There can be three possibilities:
+	 * 1. We are running on a firmware level that do not support
+	 *    opal_cec_reboot2()
+	 * 2. We are running on a firmware level that do not support
+	 *    OPAL_REBOOT_PLATFORM_ERROR reboot type.
+	 * 3. We are running on FSP based system that does not need
+	 *    opal to trigger checkstop explicitly for error analysis.
+	 *    The FSP PRD component would have already got notified
+	 *    about this error through other channels.
+	 */
+
+	ppc_md.restart(NULL);
+}
+
 int opal_machine_check(struct pt_regs *regs)
 {
 	struct machine_check_event evt;
-	int ret;
 
 	if (!get_mce_event(&evt, MCE_EVENT_RELEASE))
 		return 0;
@@ -455,43 +523,7 @@ int opal_machine_check(struct pt_regs *regs)
 	if (opal_recover_mce(regs, &evt))
 		return 1;
 
-	/*
-	 * Unrecovered machine check, we are heading to panic path.
-	 *
-	 * We may have hit this MCE in very early stage of kernel
-	 * initialization even before opal-prd has started running. If
-	 * this is the case then this MCE error may go un-noticed or
-	 * un-analyzed if we go down panic path. We need to inform
-	 * BMC/OCC about this error so that they can collect relevant
-	 * data for error analysis before rebooting.
-	 * Use opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR) to do so.
-	 * This function may not return on BMC based system.
-	 */
-	ret = opal_cec_reboot2(OPAL_REBOOT_PLATFORM_ERROR,
-			"Unrecoverable Machine Check exception");
-	if (ret == OPAL_UNSUPPORTED) {
-		pr_emerg("Reboot type %d not supported\n",
-					OPAL_REBOOT_PLATFORM_ERROR);
-	}
-
-	/*
-	 * We reached here. There can be three possibilities:
-	 * 1. We are running on a firmware level that do not support
-	 *    opal_cec_reboot2()
-	 * 2. We are running on a firmware level that do not support
-	 *    OPAL_REBOOT_PLATFORM_ERROR reboot type.
-	 * 3. We are running on FSP based system that does not need opal
-	 *    to trigger checkstop explicitly for error analysis. The FSP
-	 *    PRD component would have already got notified about this
-	 *    error through other channels.
-	 *
-	 * If hardware marked this as an unrecoverable MCE, we are
-	 * going to panic anyway. Even if it didn't, it's not safe to
-	 * continue at this point, so we should explicitly panic.
-	 */
-
-	panic("PowerNV Unrecovered Machine Check");
-	return 0;
+	pnv_platform_error_reboot(regs, "Unrecoverable Machine Check exception");
 }
 
 /* Early hmi handler called in real mode. */
@@ -720,6 +752,15 @@ static void opal_pdev_init(const char *compatible)
 		of_platform_device_create(np, NULL, NULL);
 }
 
+static void __init opal_imc_init_dev(void)
+{
+	struct device_node *np;
+
+	np = of_find_compatible_node(NULL, NULL, IMC_DTB_COMPAT);
+	if (np)
+		of_platform_device_create(np, NULL, NULL);
+}
+
 static int kopald(void *unused)
 {
 	unsigned long timeout = msecs_to_jiffies(opal_heartbeat) + 1;
@@ -793,6 +834,9 @@ static int __init opal_init(void)
 	/* Setup a heatbeat thread if requested by OPAL */
 	opal_init_heartbeat();
 
+	/* Detect In-Memory Collection counters and create devices*/
+	opal_imc_init_dev();
+
 	/* Create leds platform devices */
 	leds = of_find_node_by_path("/ibm,opal/leds");
 	if (leds) {
@@ -836,6 +880,15 @@ static int __init opal_init(void)
 	/* Initialise OPAL kmsg dumper for flushing console on panic */
 	opal_kmsg_init();
 
+	/* Initialise OPAL powercap interface */
+	opal_powercap_init();
+
+	/* Initialise OPAL Power-Shifting-Ratio interface */
+	opal_psr_init();
+
+	/* Initialise OPAL sensor groups */
+	opal_sensor_groups_init();
+
 	return 0;
 }
 machine_subsys_initcall(powernv, opal_init);
@@ -952,6 +1005,7 @@ int opal_error_code(int rc)
 	case OPAL_UNSUPPORTED:		return -EIO;
 	case OPAL_HARDWARE:		return -EIO;
 	case OPAL_INTERNAL_ERROR:	return -EIO;
+	case OPAL_TIMEOUT:		return -ETIMEDOUT;
 	default:
 		pr_err("%s: unexpected OPAL error %d\n", __func__, rc);
 		return -EIO;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index b900eb1d5e17..57f9e55f4352 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -444,8 +444,8 @@ static void __init pnv_ioda_parse_m64_window(struct pnv_phb *phb)
 
 	r = of_get_property(dn, "ibm,opal-m64-window", NULL);
 	if (!r) {
-		pr_info("  No <ibm,opal-m64-window> on %s\n",
-			dn->full_name);
+		pr_info("  No <ibm,opal-m64-window> on %pOF\n",
+			dn);
 		return;
 	}
 
@@ -1408,7 +1408,6 @@ m64_failed:
 
 static long pnv_pci_ioda2_unset_window(struct iommu_table_group *table_group,
 		int num);
-static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 
 static void pnv_pci_ioda2_release_dma_pe(struct pci_dev *dev, struct pnv_ioda_pe *pe)
 {
@@ -2402,7 +2401,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
 	return 0;
 }
 
-static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
+void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
 {
 	uint16_t window_id = (pe->pe_number << 1 ) + 1;
 	int64_t rc;
@@ -3797,8 +3796,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	if (!of_device_is_available(np))
 		return;
 
-	pr_info("Initializing %s PHB (%s)\n",
-		pnv_phb_names[ioda_type], of_node_full_name(np));
+	pr_info("Initializing %s PHB (%pOF)\n",	pnv_phb_names[ioda_type], np);
 
 	prop64 = of_get_property(np, "ibm,opal-phbid", NULL);
 	if (!prop64) {
@@ -3813,8 +3811,8 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Allocate PCI controller */
 	phb->hose = hose = pcibios_alloc_controller(np);
 	if (!phb->hose) {
-		pr_err("  Can't allocate PCI controller for %s\n",
-		       np->full_name);
+		pr_err("  Can't allocate PCI controller for %pOF\n",
+		       np);
 		memblock_free(__pa(phb), sizeof(struct pnv_phb));
 		return;
 	}
@@ -3825,7 +3823,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		hose->first_busno = be32_to_cpu(prop32[0]);
 		hose->last_busno = be32_to_cpu(prop32[1]);
 	} else {
-		pr_warn("  Broken <bus-range> on %s\n", np->full_name);
+		pr_warn("  Broken <bus-range> on %pOF\n", np);
 		hose->first_busno = 0;
 		hose->last_busno = 0xff;
 	}
@@ -4046,7 +4044,7 @@ void __init pnv_pci_init_ioda_hub(struct device_node *np)
 	const __be64 *prop64;
 	u64 hub_id;
 
-	pr_info("Probing IODA IO-Hub %s\n", np->full_name);
+	pr_info("Probing IODA IO-Hub %pOF\n", np);
 
 	prop64 = of_get_property(np, "ibm,opal-hubid", NULL);
 	if (!prop64) {
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 7905d179d036..5422f4a6317c 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -37,6 +37,8 @@
 #include "powernv.h"
 #include "pci.h"
 
+static DEFINE_MUTEX(p2p_mutex);
+
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
 {
 	struct device_node *parent = np;
@@ -1017,6 +1019,79 @@ void pnv_pci_dma_bus_setup(struct pci_bus *bus)
 	}
 }
 
+int pnv_pci_set_p2p(struct pci_dev *initiator, struct pci_dev *target, u64 desc)
+{
+	struct pci_controller *hose;
+	struct pnv_phb *phb_init, *phb_target;
+	struct pnv_ioda_pe *pe_init;
+	int rc;
+
+	if (!opal_check_token(OPAL_PCI_SET_P2P))
+		return -ENXIO;
+
+	hose = pci_bus_to_host(initiator->bus);
+	phb_init = hose->private_data;
+
+	hose = pci_bus_to_host(target->bus);
+	phb_target = hose->private_data;
+
+	pe_init = pnv_ioda_get_pe(initiator);
+	if (!pe_init)
+		return -ENODEV;
+
+	/*
+	 * Configuring the initiator's PHB requires to adjust its
+	 * TVE#1 setting. Since the same device can be an initiator
+	 * several times for different target devices, we need to keep
+	 * a reference count to know when we can restore the default
+	 * bypass setting on its TVE#1 when disabling. Opal is not
+	 * tracking PE states, so we add a reference count on the PE
+	 * in linux.
+	 *
+	 * For the target, the configuration is per PHB, so we keep a
+	 * target reference count on the PHB.
+	 */
+	mutex_lock(&p2p_mutex);
+
+	if (desc & OPAL_PCI_P2P_ENABLE) {
+		/* always go to opal to validate the configuration */
+		rc = opal_pci_set_p2p(phb_init->opal_id, phb_target->opal_id,
+				      desc, pe_init->pe_number);
+
+		if (rc != OPAL_SUCCESS) {
+			rc = -EIO;
+			goto out;
+		}
+
+		pe_init->p2p_initiator_count++;
+		phb_target->p2p_target_count++;
+	} else {
+		if (!pe_init->p2p_initiator_count ||
+			!phb_target->p2p_target_count) {
+			rc = -EINVAL;
+			goto out;
+		}
+
+		if (--pe_init->p2p_initiator_count == 0)
+			pnv_pci_ioda2_set_bypass(pe_init, true);
+
+		if (--phb_target->p2p_target_count == 0) {
+			rc = opal_pci_set_p2p(phb_init->opal_id,
+					      phb_target->opal_id, desc,
+					      pe_init->pe_number);
+			if (rc != OPAL_SUCCESS) {
+				rc = -EIO;
+				goto out;
+			}
+		}
+	}
+	rc = 0;
+out:
+	mutex_unlock(&p2p_mutex);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(pnv_pci_set_p2p);
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index f16bc403ec03..a95273c524f6 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -78,6 +78,9 @@ struct pnv_ioda_pe {
 	struct pnv_ioda_pe	*master;
 	struct list_head	slaves;
 
+	/* PCI peer-to-peer*/
+	int			p2p_initiator_count;
+
 	/* Link in list of PE#s */
 	struct list_head	list;
 };
@@ -189,6 +192,7 @@ struct pnv_phb {
 #ifdef CONFIG_CXL_BASE
 	struct cxl_afu *cxl_afu;
 #endif
+	int p2p_target_count;
 };
 
 extern struct pci_ops pnv_pci_ops;
@@ -229,6 +233,7 @@ extern void pnv_teardown_msi_irqs(struct pci_dev *pdev);
 extern struct pnv_ioda_pe *pnv_ioda_get_pe(struct pci_dev *dev);
 extern void pnv_set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq);
 extern bool pnv_pci_enable_device_hook(struct pci_dev *dev);
+extern void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 
 extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 6dbc0a1da1f6..a159d48573d7 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -7,6 +7,8 @@ extern void pnv_smp_init(void);
 static inline void pnv_smp_init(void) { }
 #endif
 
+extern void pnv_platform_error_reboot(struct pt_regs *regs, const char *msg) __noreturn;
+
 struct pci_dev;
 
 #ifdef CONFIG_PCI
diff --git a/arch/powerpc/platforms/powernv/rng.c b/arch/powerpc/platforms/powernv/rng.c
index 1a9d84371a4d..718f50ed22f1 100644
--- a/arch/powerpc/platforms/powernv/rng.c
+++ b/arch/powerpc/platforms/powernv/rng.c
@@ -16,11 +16,13 @@
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <asm/archrandom.h>
+#include <asm/cputable.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/machdep.h>
 #include <asm/smp.h>
 
+#define DARN_ERR 0xFFFFFFFFFFFFFFFFul
 
 struct powernv_rng {
 	void __iomem *regs;
@@ -67,6 +69,41 @@ int powernv_get_random_real_mode(unsigned long *v)
 	return 1;
 }
 
+int powernv_get_random_darn(unsigned long *v)
+{
+	unsigned long val;
+
+	/* Using DARN with L=1 - 64-bit conditioned random number */
+	asm volatile(PPC_DARN(%0, 1) : "=r"(val));
+
+	if (val == DARN_ERR)
+		return 0;
+
+	*v = val;
+
+	return 1;
+}
+
+static int initialise_darn(void)
+{
+	unsigned long val;
+	int i;
+
+	if (!cpu_has_feature(CPU_FTR_ARCH_300))
+		return -ENODEV;
+
+	for (i = 0; i < 10; i++) {
+		if (powernv_get_random_darn(&val)) {
+			ppc_md.get_random_seed = powernv_get_random_darn;
+			return 0;
+		}
+	}
+
+	pr_warn("Unable to use DARN for get_random_seed()\n");
+
+	return -EIO;
+}
+
 int powernv_get_random_long(unsigned long *v)
 {
 	struct powernv_rng *rng;
@@ -88,7 +125,7 @@ static __init void rng_init_per_cpu(struct powernv_rng *rng,
 
 	chip_id = of_get_ibm_chip_id(dn);
 	if (chip_id == -1)
-		pr_warn("No ibm,chip-id found for %s.\n", dn->full_name);
+		pr_warn("No ibm,chip-id found for %pOF.\n", dn);
 
 	for_each_possible_cpu(cpu) {
 		if (per_cpu(powernv_rng, cpu) == NULL ||
@@ -141,8 +178,8 @@ static __init int rng_init(void)
 	for_each_compatible_node(dn, NULL, "ibm,power-rng") {
 		rc = rng_create(dn);
 		if (rc) {
-			pr_err("Failed creating rng for %s (%d).\n",
-				dn->full_name, rc);
+			pr_err("Failed creating rng for %pOF (%d).\n",
+				dn, rc);
 			continue;
 		}
 
@@ -150,6 +187,8 @@ static __init int rng_init(void)
 		of_platform_device_create(dn, NULL, NULL);
 	}
 
+	initialise_darn();
+
 	return 0;
 }
 machine_subsys_initcall(powernv, rng_init);
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 40dae96f7e20..c17f81e433f7 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -57,7 +57,7 @@ static void pnv_smp_setup_cpu(int cpu)
 
 static int pnv_smp_kick_cpu(int nr)
 {
-	unsigned int pcpu = get_hard_smp_processor_id(nr);
+	unsigned int pcpu;
 	unsigned long start_here =
 			__pa(ppc_function_entry(generic_secondary_smp_init));
 	long rc;
@@ -66,6 +66,7 @@ static int pnv_smp_kick_cpu(int nr)
 	if (nr < 0 || nr >= nr_cpu_ids)
 		return -EINVAL;
 
+	pcpu = get_hard_smp_processor_id(nr);
 	/*
 	 * If we already started or OPAL is not supported, we just
 	 * kick the CPU via the PACA
@@ -164,12 +165,6 @@ static void pnv_smp_cpu_kill_self(void)
 	if (cpu_has_feature(CPU_FTR_ARCH_207S))
 		wmask = SRR1_WAKEMASK_P8;
 
-	/* We don't want to take decrementer interrupts while we are offline,
-	 * so clear LPCR:PECE1. We keep PECE2 (and LPCR_PECE_HVEE on P9)
-	 * enabled as to let IPIs in.
-	 */
-	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
-
 	while (!generic_check_cpu_restart(cpu)) {
 		/*
 		 * Clear IPI flag, since we don't handle IPIs while
@@ -219,8 +214,6 @@ static void pnv_smp_cpu_kill_self(void)
 
 	}
 
-	/* Re-enable decrementer interrupts */
-	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) | LPCR_PECE1);
 	DBG("CPU%d coming online...\n", cpu);
 }
 
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
new file mode 100644
index 000000000000..5aae845b8cd9
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -0,0 +1,1134 @@
+/*
+ * Copyright 2016-17 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+#include <linux/io.h>
+#include <linux/log2.h>
+#include <linux/rcupdate.h>
+#include <linux/cred.h>
+
+#include "vas.h"
+#include "copy-paste.h"
+
+/*
+ * Compute the paste address region for the window @window using the
+ * ->paste_base_addr and ->paste_win_id_shift we got from device tree.
+ */
+static void compute_paste_address(struct vas_window *window, u64 *addr, int *len)
+{
+	int winid;
+	u64 base, shift;
+
+	base = window->vinst->paste_base_addr;
+	shift = window->vinst->paste_win_id_shift;
+	winid = window->winid;
+
+	*addr  = base + (winid << shift);
+	if (len)
+		*len = PAGE_SIZE;
+
+	pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
+}
+
+static inline void get_hvwc_mmio_bar(struct vas_window *window,
+			u64 *start, int *len)
+{
+	u64 pbaddr;
+
+	pbaddr = window->vinst->hvwc_bar_start;
+	*start = pbaddr + window->winid * VAS_HVWC_SIZE;
+	*len = VAS_HVWC_SIZE;
+}
+
+static inline void get_uwc_mmio_bar(struct vas_window *window,
+			u64 *start, int *len)
+{
+	u64 pbaddr;
+
+	pbaddr = window->vinst->uwc_bar_start;
+	*start = pbaddr + window->winid * VAS_UWC_SIZE;
+	*len = VAS_UWC_SIZE;
+}
+
+/*
+ * Map the paste bus address of the given send window into kernel address
+ * space. Unlike MMIO regions (map_mmio_region() below), paste region must
+ * be mapped cache-able and is only applicable to send windows.
+ */
+static void *map_paste_region(struct vas_window *txwin)
+{
+	int len;
+	void *map;
+	char *name;
+	u64 start;
+
+	name = kasprintf(GFP_KERNEL, "window-v%d-w%d", txwin->vinst->vas_id,
+				txwin->winid);
+	if (!name)
+		goto free_name;
+
+	txwin->paste_addr_name = name;
+	compute_paste_address(txwin, &start, &len);
+
+	if (!request_mem_region(start, len, name)) {
+		pr_devel("%s(): request_mem_region(0x%llx, %d) failed\n",
+				__func__, start, len);
+		goto free_name;
+	}
+
+	map = ioremap_cache(start, len);
+	if (!map) {
+		pr_devel("%s(): ioremap_cache(0x%llx, %d) failed\n", __func__,
+				start, len);
+		goto free_name;
+	}
+
+	pr_devel("Mapped paste addr 0x%llx to kaddr 0x%p\n", start, map);
+	return map;
+
+free_name:
+	kfree(name);
+	return ERR_PTR(-ENOMEM);
+}
+
+static void *map_mmio_region(char *name, u64 start, int len)
+{
+	void *map;
+
+	if (!request_mem_region(start, len, name)) {
+		pr_devel("%s(): request_mem_region(0x%llx, %d) failed\n",
+				__func__, start, len);
+		return NULL;
+	}
+
+	map = ioremap(start, len);
+	if (!map) {
+		pr_devel("%s(): ioremap(0x%llx, %d) failed\n", __func__, start,
+				len);
+		return NULL;
+	}
+
+	return map;
+}
+
+static void unmap_region(void *addr, u64 start, int len)
+{
+	iounmap(addr);
+	release_mem_region((phys_addr_t)start, len);
+}
+
+/*
+ * Unmap the paste address region for a window.
+ */
+static void unmap_paste_region(struct vas_window *window)
+{
+	int len;
+	u64 busaddr_start;
+
+	if (window->paste_kaddr) {
+		compute_paste_address(window, &busaddr_start, &len);
+		unmap_region(window->paste_kaddr, busaddr_start, len);
+		window->paste_kaddr = NULL;
+		kfree(window->paste_addr_name);
+		window->paste_addr_name = NULL;
+	}
+}
+
+/*
+ * Unmap the MMIO regions for a window.
+ */
+static void unmap_winctx_mmio_bars(struct vas_window *window)
+{
+	int len;
+	u64 busaddr_start;
+
+	if (window->hvwc_map) {
+		get_hvwc_mmio_bar(window, &busaddr_start, &len);
+		unmap_region(window->hvwc_map, busaddr_start, len);
+		window->hvwc_map = NULL;
+	}
+
+	if (window->uwc_map) {
+		get_uwc_mmio_bar(window, &busaddr_start, &len);
+		unmap_region(window->uwc_map, busaddr_start, len);
+		window->uwc_map = NULL;
+	}
+}
+
+/*
+ * Find the Hypervisor Window Context (HVWC) MMIO Base Address Region and the
+ * OS/User Window Context (UWC) MMIO Base Address Region for the given window.
+ * Map these bus addresses and save the mapped kernel addresses in @window.
+ */
+int map_winctx_mmio_bars(struct vas_window *window)
+{
+	int len;
+	u64 start;
+
+	get_hvwc_mmio_bar(window, &start, &len);
+	window->hvwc_map = map_mmio_region("HVWCM_Window", start, len);
+
+	get_uwc_mmio_bar(window, &start, &len);
+	window->uwc_map = map_mmio_region("UWCM_Window", start, len);
+
+	if (!window->hvwc_map || !window->uwc_map) {
+		unmap_winctx_mmio_bars(window);
+		return -1;
+	}
+
+	return 0;
+}
+
+/*
+ * Reset all valid registers in the HV and OS/User Window Contexts for
+ * the window identified by @window.
+ *
+ * NOTE: We cannot really use a for loop to reset window context. Not all
+ *	 offsets in a window context are valid registers and the valid
+ *	 registers are not sequential. And, we can only write to offsets
+ *	 with valid registers.
+ */
+void reset_window_regs(struct vas_window *window)
+{
+	write_hvwc_reg(window, VREG(LPID), 0ULL);
+	write_hvwc_reg(window, VREG(PID), 0ULL);
+	write_hvwc_reg(window, VREG(XLATE_MSR), 0ULL);
+	write_hvwc_reg(window, VREG(XLATE_LPCR), 0ULL);
+	write_hvwc_reg(window, VREG(XLATE_CTL), 0ULL);
+	write_hvwc_reg(window, VREG(AMR), 0ULL);
+	write_hvwc_reg(window, VREG(SEIDR), 0ULL);
+	write_hvwc_reg(window, VREG(FAULT_TX_WIN), 0ULL);
+	write_hvwc_reg(window, VREG(OSU_INTR_SRC_RA), 0ULL);
+	write_hvwc_reg(window, VREG(HV_INTR_SRC_RA), 0ULL);
+	write_hvwc_reg(window, VREG(PSWID), 0ULL);
+	write_hvwc_reg(window, VREG(LFIFO_BAR), 0ULL);
+	write_hvwc_reg(window, VREG(LDATA_STAMP_CTL), 0ULL);
+	write_hvwc_reg(window, VREG(LDMA_CACHE_CTL), 0ULL);
+	write_hvwc_reg(window, VREG(LRFIFO_PUSH), 0ULL);
+	write_hvwc_reg(window, VREG(CURR_MSG_COUNT), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_AFTER_COUNT), 0ULL);
+	write_hvwc_reg(window, VREG(LRX_WCRED), 0ULL);
+	write_hvwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL);
+	write_hvwc_reg(window, VREG(TX_WCRED), 0ULL);
+	write_hvwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL);
+	write_hvwc_reg(window, VREG(LFIFO_SIZE), 0ULL);
+	write_hvwc_reg(window, VREG(WINCTL), 0ULL);
+	write_hvwc_reg(window, VREG(WIN_STATUS), 0ULL);
+	write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), 0ULL);
+	write_hvwc_reg(window, VREG(TX_RSVD_BUF_COUNT), 0ULL);
+	write_hvwc_reg(window, VREG(LRFIFO_WIN_PTR), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_CTL), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_PID), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_LPID), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_TID), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_SCOPE), 0ULL);
+	write_hvwc_reg(window, VREG(NX_UTIL_ADDER), 0ULL);
+
+	/* Skip read-only registers: NX_UTIL and NX_UTIL_SE */
+
+	/*
+	 * The send and receive window credit adder registers are also
+	 * accessible from HVWC and have been initialized above. We don't
+	 * need to initialize from the OS/User Window Context, so skip
+	 * following calls:
+	 *
+	 *	write_uwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL);
+	 *	write_uwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL);
+	 */
+}
+
+/*
+ * Initialize window context registers related to Address Translation.
+ * These registers are common to send/receive windows although they
+ * differ for user/kernel windows. As we resolve the TODOs we may
+ * want to add fields to vas_winctx and move the initialization to
+ * init_vas_winctx_regs().
+ */
+static void init_xlate_regs(struct vas_window *window, bool user_win)
+{
+	u64 lpcr, val;
+
+	/*
+	 * MSR_TA, MSR_US are false for both kernel and user.
+	 * MSR_DR and MSR_PR are false for kernel.
+	 */
+	val = 0ULL;
+	val = SET_FIELD(VAS_XLATE_MSR_HV, val, 1);
+	val = SET_FIELD(VAS_XLATE_MSR_SF, val, 1);
+	if (user_win) {
+		val = SET_FIELD(VAS_XLATE_MSR_DR, val, 1);
+		val = SET_FIELD(VAS_XLATE_MSR_PR, val, 1);
+	}
+	write_hvwc_reg(window, VREG(XLATE_MSR), val);
+
+	lpcr = mfspr(SPRN_LPCR);
+	val = 0ULL;
+	/*
+	 * NOTE: From Section 5.7.8.1 Segment Lookaside Buffer of the
+	 *	 Power ISA, v3.0B, Page size encoding is 0 = 4KB, 5 = 64KB.
+	 *
+	 * NOTE: From Section 1.3.1, Address Translation Context of the
+	 *	 Nest MMU Workbook, LPCR_SC should be 0 for Power9.
+	 */
+	val = SET_FIELD(VAS_XLATE_LPCR_PAGE_SIZE, val, 5);
+	val = SET_FIELD(VAS_XLATE_LPCR_ISL, val, lpcr & LPCR_ISL);
+	val = SET_FIELD(VAS_XLATE_LPCR_TC, val, lpcr & LPCR_TC);
+	val = SET_FIELD(VAS_XLATE_LPCR_SC, val, 0);
+	write_hvwc_reg(window, VREG(XLATE_LPCR), val);
+
+	/*
+	 * Section 1.3.1 (Address translation Context) of NMMU workbook.
+	 *	0b00	Hashed Page Table mode
+	 *	0b01	Reserved
+	 *	0b10	Radix on HPT
+	 *	0b11	Radix on Radix
+	 */
+	val = 0ULL;
+	val = SET_FIELD(VAS_XLATE_MODE, val, radix_enabled() ? 3 : 2);
+	write_hvwc_reg(window, VREG(XLATE_CTL), val);
+
+	/*
+	 * TODO: Can we mfspr(AMR) even for user windows?
+	 */
+	val = 0ULL;
+	val = SET_FIELD(VAS_AMR, val, mfspr(SPRN_AMR));
+	write_hvwc_reg(window, VREG(AMR), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_SEIDR, val, 0);
+	write_hvwc_reg(window, VREG(SEIDR), val);
+}
+
+/*
+ * Initialize Reserved Send Buffer Count for the send window. It involves
+ * writing to the register, reading it back to confirm that the hardware
+ * has enough buffers to reserve. See section 1.3.1.2.1 of VAS workbook.
+ *
+ * Since we can only make a best-effort attempt to fulfill the request,
+ * we don't return any errors if we cannot.
+ *
+ * TODO: Reserved (aka dedicated) send buffers are not supported yet.
+ */
+static void init_rsvd_tx_buf_count(struct vas_window *txwin,
+				struct vas_winctx *winctx)
+{
+	write_hvwc_reg(txwin, VREG(TX_RSVD_BUF_COUNT), 0ULL);
+}
+
+/*
+ * init_winctx_regs()
+ *	Initialize window context registers for a receive window.
+ *	Except for caching control and marking window open, the registers
+ *	are initialized in the order listed in Section 3.1.4 (Window Context
+ *	Cache Register Details) of the VAS workbook although they don't need
+ *	to be.
+ *
+ * Design note: For NX receive windows, NX allocates the FIFO buffer in OPAL
+ *	(so that it can get a large contiguous area) and passes that buffer
+ *	to kernel via device tree. We now write that buffer address to the
+ *	FIFO BAR. Would it make sense to do this all in OPAL? i.e have OPAL
+ *	write the per-chip RX FIFO addresses to the windows during boot-up
+ *	as a one-time task? That could work for NX but what about other
+ *	receivers?  Let the receivers tell us the rx-fifo buffers for now.
+ */
+int init_winctx_regs(struct vas_window *window, struct vas_winctx *winctx)
+{
+	u64 val;
+	int fifo_size;
+
+	reset_window_regs(window);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LPID, val, winctx->lpid);
+	write_hvwc_reg(window, VREG(LPID), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_PID_ID, val, winctx->pidr);
+	write_hvwc_reg(window, VREG(PID), val);
+
+	init_xlate_regs(window, winctx->user_win);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_FAULT_TX_WIN, val, 0);
+	write_hvwc_reg(window, VREG(FAULT_TX_WIN), val);
+
+	/* In PowerNV, interrupts go to HV. */
+	write_hvwc_reg(window, VREG(OSU_INTR_SRC_RA), 0ULL);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_HV_INTR_SRC_RA, val, winctx->irq_port);
+	write_hvwc_reg(window, VREG(HV_INTR_SRC_RA), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_PSWID_EA_HANDLE, val, winctx->pswid);
+	write_hvwc_reg(window, VREG(PSWID), val);
+
+	write_hvwc_reg(window, VREG(SPARE1), 0ULL);
+	write_hvwc_reg(window, VREG(SPARE2), 0ULL);
+	write_hvwc_reg(window, VREG(SPARE3), 0ULL);
+
+	/*
+	 * NOTE: VAS expects the FIFO address to be copied into the LFIFO_BAR
+	 *	 register as is - do NOT shift the address into VAS_LFIFO_BAR
+	 *	 bit fields! Ok to set the page migration select fields -
+	 *	 VAS ignores the lower 10+ bits in the address anyway, because
+	 *	 the minimum FIFO size is 1K?
+	 *
+	 * See also: Design note in function header.
+	 */
+	val = __pa(winctx->rx_fifo);
+	val = SET_FIELD(VAS_PAGE_MIGRATION_SELECT, val, 0);
+	write_hvwc_reg(window, VREG(LFIFO_BAR), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LDATA_STAMP, val, winctx->data_stamp);
+	write_hvwc_reg(window, VREG(LDATA_STAMP_CTL), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LDMA_TYPE, val, winctx->dma_type);
+	val = SET_FIELD(VAS_LDMA_FIFO_DISABLE, val, winctx->fifo_disable);
+	write_hvwc_reg(window, VREG(LDMA_CACHE_CTL), val);
+
+	write_hvwc_reg(window, VREG(LRFIFO_PUSH), 0ULL);
+	write_hvwc_reg(window, VREG(CURR_MSG_COUNT), 0ULL);
+	write_hvwc_reg(window, VREG(LNOTIFY_AFTER_COUNT), 0ULL);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LRX_WCRED, val, winctx->wcreds_max);
+	write_hvwc_reg(window, VREG(LRX_WCRED), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_TX_WCRED, val, winctx->wcreds_max);
+	write_hvwc_reg(window, VREG(TX_WCRED), val);
+
+	write_hvwc_reg(window, VREG(LRX_WCRED_ADDER), 0ULL);
+	write_hvwc_reg(window, VREG(TX_WCRED_ADDER), 0ULL);
+
+	fifo_size = winctx->rx_fifo_size / 1024;
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LFIFO_SIZE, val, ilog2(fifo_size));
+	write_hvwc_reg(window, VREG(LFIFO_SIZE), val);
+
+	/* Update window control and caching control registers last so
+	 * we mark the window open only after fully initializing it and
+	 * pushing context to cache.
+	 */
+
+	write_hvwc_reg(window, VREG(WIN_STATUS), 0ULL);
+
+	init_rsvd_tx_buf_count(window, winctx);
+
+	/* for a send window, point to the matching receive window */
+	val = 0ULL;
+	val = SET_FIELD(VAS_LRX_WIN_ID, val, winctx->rx_win_id);
+	write_hvwc_reg(window, VREG(LRFIFO_WIN_PTR), val);
+
+	write_hvwc_reg(window, VREG(SPARE4), 0ULL);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_NOTIFY_DISABLE, val, winctx->notify_disable);
+	val = SET_FIELD(VAS_INTR_DISABLE, val, winctx->intr_disable);
+	val = SET_FIELD(VAS_NOTIFY_EARLY, val, winctx->notify_early);
+	val = SET_FIELD(VAS_NOTIFY_OSU_INTR, val, winctx->notify_os_intr_reg);
+	write_hvwc_reg(window, VREG(LNOTIFY_CTL), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LNOTIFY_PID, val, winctx->lnotify_pid);
+	write_hvwc_reg(window, VREG(LNOTIFY_PID), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LNOTIFY_LPID, val, winctx->lnotify_lpid);
+	write_hvwc_reg(window, VREG(LNOTIFY_LPID), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LNOTIFY_TID, val, winctx->lnotify_tid);
+	write_hvwc_reg(window, VREG(LNOTIFY_TID), val);
+
+	val = 0ULL;
+	val = SET_FIELD(VAS_LNOTIFY_MIN_SCOPE, val, winctx->min_scope);
+	val = SET_FIELD(VAS_LNOTIFY_MAX_SCOPE, val, winctx->max_scope);
+	write_hvwc_reg(window, VREG(LNOTIFY_SCOPE), val);
+
+	/* Skip read-only registers NX_UTIL and NX_UTIL_SE */
+
+	write_hvwc_reg(window, VREG(SPARE5), 0ULL);
+	write_hvwc_reg(window, VREG(NX_UTIL_ADDER), 0ULL);
+	write_hvwc_reg(window, VREG(SPARE6), 0ULL);
+
+	/* Finally, push window context to memory and... */
+	val = 0ULL;
+	val = SET_FIELD(VAS_PUSH_TO_MEM, val, 1);
+	write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), val);
+
+	/* ... mark the window open for business */
+	val = 0ULL;
+	val = SET_FIELD(VAS_WINCTL_REJ_NO_CREDIT, val, winctx->rej_no_credit);
+	val = SET_FIELD(VAS_WINCTL_PIN, val, winctx->pin_win);
+	val = SET_FIELD(VAS_WINCTL_TX_WCRED_MODE, val, winctx->tx_wcred_mode);
+	val = SET_FIELD(VAS_WINCTL_RX_WCRED_MODE, val, winctx->rx_wcred_mode);
+	val = SET_FIELD(VAS_WINCTL_TX_WORD_MODE, val, winctx->tx_word_mode);
+	val = SET_FIELD(VAS_WINCTL_RX_WORD_MODE, val, winctx->rx_word_mode);
+	val = SET_FIELD(VAS_WINCTL_FAULT_WIN, val, winctx->fault_win);
+	val = SET_FIELD(VAS_WINCTL_NX_WIN, val, winctx->nx_win);
+	val = SET_FIELD(VAS_WINCTL_OPEN, val, 1);
+	write_hvwc_reg(window, VREG(WINCTL), val);
+
+	return 0;
+}
+
+static DEFINE_SPINLOCK(vas_ida_lock);
+
+static void vas_release_window_id(struct ida *ida, int winid)
+{
+	spin_lock(&vas_ida_lock);
+	ida_remove(ida, winid);
+	spin_unlock(&vas_ida_lock);
+}
+
+static int vas_assign_window_id(struct ida *ida)
+{
+	int rc, winid;
+
+	do {
+		rc = ida_pre_get(ida, GFP_KERNEL);
+		if (!rc)
+			return -EAGAIN;
+
+		spin_lock(&vas_ida_lock);
+		rc = ida_get_new(ida, &winid);
+		spin_unlock(&vas_ida_lock);
+	} while (rc == -EAGAIN);
+
+	if (rc)
+		return rc;
+
+	if (winid > VAS_WINDOWS_PER_CHIP) {
+		pr_err("Too many (%d) open windows\n", winid);
+		vas_release_window_id(ida, winid);
+		return -EAGAIN;
+	}
+
+	return winid;
+}
+
+static void vas_window_free(struct vas_window *window)
+{
+	int winid = window->winid;
+	struct vas_instance *vinst = window->vinst;
+
+	unmap_winctx_mmio_bars(window);
+	kfree(window);
+
+	vas_release_window_id(&vinst->ida, winid);
+}
+
+static struct vas_window *vas_window_alloc(struct vas_instance *vinst)
+{
+	int winid;
+	struct vas_window *window;
+
+	winid = vas_assign_window_id(&vinst->ida);
+	if (winid < 0)
+		return ERR_PTR(winid);
+
+	window = kzalloc(sizeof(*window), GFP_KERNEL);
+	if (!window)
+		goto out_free;
+
+	window->vinst = vinst;
+	window->winid = winid;
+
+	if (map_winctx_mmio_bars(window))
+		goto out_free;
+
+	return window;
+
+out_free:
+	kfree(window);
+	vas_release_window_id(&vinst->ida, winid);
+	return ERR_PTR(-ENOMEM);
+}
+
+static void put_rx_win(struct vas_window *rxwin)
+{
+	/* Better not be a send window! */
+	WARN_ON_ONCE(rxwin->tx_win);
+
+	atomic_dec(&rxwin->num_txwins);
+}
+
+/*
+ * Get the VAS receive window associated with NX engine identified
+ * by @cop and if applicable, @pswid.
+ *
+ * See also function header of set_vinst_win().
+ */
+static struct vas_window *get_vinst_rxwin(struct vas_instance *vinst,
+			enum vas_cop_type cop, u32 pswid)
+{
+	struct vas_window *rxwin;
+
+	mutex_lock(&vinst->mutex);
+
+	if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI)
+		rxwin = vinst->rxwin[cop] ?: ERR_PTR(-EINVAL);
+	else
+		rxwin = ERR_PTR(-EINVAL);
+
+	if (!IS_ERR(rxwin))
+		atomic_inc(&rxwin->num_txwins);
+
+	mutex_unlock(&vinst->mutex);
+
+	return rxwin;
+}
+
+/*
+ * We have two tables of windows in a VAS instance. The first one,
+ * ->windows[], contains all the windows in the instance and allows
+ * looking up a window by its id. It is used to look up send windows
+ * during fault handling and receive windows when pairing user space
+ * send/receive windows.
+ *
+ * The second table, ->rxwin[], contains receive windows that are
+ * associated with NX engines. This table has VAS_COP_TYPE_MAX
+ * entries and is used to look up a receive window by its
+ * coprocessor type.
+ *
+ * Here, we save @window in the ->windows[] table. If it is a receive
+ * window, we also save the window in the ->rxwin[] table.
+ */
+static void set_vinst_win(struct vas_instance *vinst,
+			struct vas_window *window)
+{
+	int id = window->winid;
+
+	mutex_lock(&vinst->mutex);
+
+	/*
+	 * There should only be one receive window for a coprocessor type
+	 * unless its a user (FTW) window.
+	 */
+	if (!window->user_win && !window->tx_win) {
+		WARN_ON_ONCE(vinst->rxwin[window->cop]);
+		vinst->rxwin[window->cop] = window;
+	}
+
+	WARN_ON_ONCE(vinst->windows[id] != NULL);
+	vinst->windows[id] = window;
+
+	mutex_unlock(&vinst->mutex);
+}
+
+/*
+ * Clear this window from the table(s) of windows for this VAS instance.
+ * See also function header of set_vinst_win().
+ */
+static void clear_vinst_win(struct vas_window *window)
+{
+	int id = window->winid;
+	struct vas_instance *vinst = window->vinst;
+
+	mutex_lock(&vinst->mutex);
+
+	if (!window->user_win && !window->tx_win) {
+		WARN_ON_ONCE(!vinst->rxwin[window->cop]);
+		vinst->rxwin[window->cop] = NULL;
+	}
+
+	WARN_ON_ONCE(vinst->windows[id] != window);
+	vinst->windows[id] = NULL;
+
+	mutex_unlock(&vinst->mutex);
+}
+
+static void init_winctx_for_rxwin(struct vas_window *rxwin,
+			struct vas_rx_win_attr *rxattr,
+			struct vas_winctx *winctx)
+{
+	/*
+	 * We first zero (memset()) all fields and only set non-zero fields.
+	 * Following fields are 0/false but maybe deserve a comment:
+	 *
+	 *	->notify_os_intr_reg	In powerNV, send intrs to HV
+	 *	->notify_disable	False for NX windows
+	 *	->intr_disable		False for Fault Windows
+	 *	->xtra_write		False for NX windows
+	 *	->notify_early		NA for NX windows
+	 *	->rsvd_txbuf_count	NA for Rx windows
+	 *	->lpid, ->pid, ->tid	NA for Rx windows
+	 */
+
+	memset(winctx, 0, sizeof(struct vas_winctx));
+
+	winctx->rx_fifo = rxattr->rx_fifo;
+	winctx->rx_fifo_size = rxattr->rx_fifo_size;
+	winctx->wcreds_max = rxattr->wcreds_max ?: VAS_WCREDS_DEFAULT;
+	winctx->pin_win = rxattr->pin_win;
+
+	winctx->nx_win = rxattr->nx_win;
+	winctx->fault_win = rxattr->fault_win;
+	winctx->rx_word_mode = rxattr->rx_win_ord_mode;
+	winctx->tx_word_mode = rxattr->tx_win_ord_mode;
+	winctx->rx_wcred_mode = rxattr->rx_wcred_mode;
+	winctx->tx_wcred_mode = rxattr->tx_wcred_mode;
+
+	if (winctx->nx_win) {
+		winctx->data_stamp = true;
+		winctx->intr_disable = true;
+		winctx->pin_win = true;
+
+		WARN_ON_ONCE(winctx->fault_win);
+		WARN_ON_ONCE(!winctx->rx_word_mode);
+		WARN_ON_ONCE(!winctx->tx_word_mode);
+		WARN_ON_ONCE(winctx->notify_after_count);
+	} else if (winctx->fault_win) {
+		winctx->notify_disable = true;
+	} else if (winctx->user_win) {
+		/*
+		 * Section 1.8.1 Low Latency Core-Core Wake up of
+		 * the VAS workbook:
+		 *
+		 *      - disable credit checks ([tr]x_wcred_mode = false)
+		 *      - disable FIFO writes
+		 *      - enable ASB_Notify, disable interrupt
+		 */
+		winctx->fifo_disable = true;
+		winctx->intr_disable = true;
+		winctx->rx_fifo = NULL;
+	}
+
+	winctx->lnotify_lpid = rxattr->lnotify_lpid;
+	winctx->lnotify_pid = rxattr->lnotify_pid;
+	winctx->lnotify_tid = rxattr->lnotify_tid;
+	winctx->pswid = rxattr->pswid;
+	winctx->dma_type = VAS_DMA_TYPE_INJECT;
+	winctx->tc_mode = rxattr->tc_mode;
+
+	winctx->min_scope = VAS_SCOPE_LOCAL;
+	winctx->max_scope = VAS_SCOPE_VECTORED_GROUP;
+}
+
+static bool rx_win_args_valid(enum vas_cop_type cop,
+			struct vas_rx_win_attr *attr)
+{
+	dump_rx_win_attr(attr);
+
+	if (cop >= VAS_COP_TYPE_MAX)
+		return false;
+
+	if (cop != VAS_COP_TYPE_FTW &&
+				attr->rx_fifo_size < VAS_RX_FIFO_SIZE_MIN)
+		return false;
+
+	if (attr->rx_fifo_size > VAS_RX_FIFO_SIZE_MAX)
+		return false;
+
+	if (attr->nx_win) {
+		/* cannot be fault or user window if it is nx */
+		if (attr->fault_win || attr->user_win)
+			return false;
+		/*
+		 * Section 3.1.4.32: NX Windows must not disable notification,
+		 *	and must not enable interrupts or early notification.
+		 */
+		if (attr->notify_disable || !attr->intr_disable ||
+				attr->notify_early)
+			return false;
+	} else if (attr->fault_win) {
+		/* cannot be both fault and user window */
+		if (attr->user_win)
+			return false;
+
+		/*
+		 * Section 3.1.4.32: Fault windows must disable notification
+		 *	but not interrupts.
+		 */
+		if (!attr->notify_disable || attr->intr_disable)
+			return false;
+
+	} else if (attr->user_win) {
+		/*
+		 * User receive windows are only for fast-thread-wakeup
+		 * (FTW). They don't need a FIFO and must disable interrupts
+		 */
+		if (attr->rx_fifo || attr->rx_fifo_size || !attr->intr_disable)
+			return false;
+	} else {
+		/* Rx window must be one of NX or Fault or User window. */
+		return false;
+	}
+
+	return true;
+}
+
+void vas_init_rx_win_attr(struct vas_rx_win_attr *rxattr, enum vas_cop_type cop)
+{
+	memset(rxattr, 0, sizeof(*rxattr));
+
+	if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI) {
+		rxattr->pin_win = true;
+		rxattr->nx_win = true;
+		rxattr->fault_win = false;
+		rxattr->intr_disable = true;
+		rxattr->rx_wcred_mode = true;
+		rxattr->tx_wcred_mode = true;
+		rxattr->rx_win_ord_mode = true;
+		rxattr->tx_win_ord_mode = true;
+	} else if (cop == VAS_COP_TYPE_FAULT) {
+		rxattr->pin_win = true;
+		rxattr->fault_win = true;
+		rxattr->notify_disable = true;
+		rxattr->rx_wcred_mode = true;
+		rxattr->tx_wcred_mode = true;
+		rxattr->rx_win_ord_mode = true;
+		rxattr->tx_win_ord_mode = true;
+	} else if (cop == VAS_COP_TYPE_FTW) {
+		rxattr->user_win = true;
+		rxattr->intr_disable = true;
+
+		/*
+		 * As noted in the VAS Workbook we disable credit checks.
+		 * If we enable credit checks in the future, we must also
+		 * implement a mechanism to return the user credits or new
+		 * paste operations will fail.
+		 */
+	}
+}
+EXPORT_SYMBOL_GPL(vas_init_rx_win_attr);
+
+struct vas_window *vas_rx_win_open(int vasid, enum vas_cop_type cop,
+			struct vas_rx_win_attr *rxattr)
+{
+	struct vas_window *rxwin;
+	struct vas_winctx winctx;
+	struct vas_instance *vinst;
+
+	if (!rx_win_args_valid(cop, rxattr))
+		return ERR_PTR(-EINVAL);
+
+	vinst = find_vas_instance(vasid);
+	if (!vinst) {
+		pr_devel("vasid %d not found!\n", vasid);
+		return ERR_PTR(-EINVAL);
+	}
+	pr_devel("Found instance %d\n", vasid);
+
+	rxwin = vas_window_alloc(vinst);
+	if (IS_ERR(rxwin)) {
+		pr_devel("Unable to allocate memory for Rx window\n");
+		return rxwin;
+	}
+
+	rxwin->tx_win = false;
+	rxwin->nx_win = rxattr->nx_win;
+	rxwin->user_win = rxattr->user_win;
+	rxwin->cop = cop;
+	if (rxattr->user_win)
+		rxwin->pid = task_pid_vnr(current);
+
+	init_winctx_for_rxwin(rxwin, rxattr, &winctx);
+	init_winctx_regs(rxwin, &winctx);
+
+	set_vinst_win(vinst, rxwin);
+
+	return rxwin;
+}
+EXPORT_SYMBOL_GPL(vas_rx_win_open);
+
+void vas_init_tx_win_attr(struct vas_tx_win_attr *txattr, enum vas_cop_type cop)
+{
+	memset(txattr, 0, sizeof(*txattr));
+
+	if (cop == VAS_COP_TYPE_842 || cop == VAS_COP_TYPE_842_HIPRI) {
+		txattr->rej_no_credit = false;
+		txattr->rx_wcred_mode = true;
+		txattr->tx_wcred_mode = true;
+		txattr->rx_win_ord_mode = true;
+		txattr->tx_win_ord_mode = true;
+	} else if (cop == VAS_COP_TYPE_FTW) {
+		txattr->user_win = true;
+	}
+}
+EXPORT_SYMBOL_GPL(vas_init_tx_win_attr);
+
+static void init_winctx_for_txwin(struct vas_window *txwin,
+			struct vas_tx_win_attr *txattr,
+			struct vas_winctx *winctx)
+{
+	/*
+	 * We first zero all fields and only set non-zero ones. Following
+	 * are some fields set to 0/false for the stated reason:
+	 *
+	 *	->notify_os_intr_reg	In powernv, send intrs to HV
+	 *	->rsvd_txbuf_count	Not supported yet.
+	 *	->notify_disable	False for NX windows
+	 *	->xtra_write		False for NX windows
+	 *	->notify_early		NA for NX windows
+	 *	->lnotify_lpid		NA for Tx windows
+	 *	->lnotify_pid		NA for Tx windows
+	 *	->lnotify_tid		NA for Tx windows
+	 *	->tx_win_cred_mode	Ignore for now for NX windows
+	 *	->rx_win_cred_mode	Ignore for now for NX windows
+	 */
+	memset(winctx, 0, sizeof(struct vas_winctx));
+
+	winctx->wcreds_max = txattr->wcreds_max ?: VAS_WCREDS_DEFAULT;
+
+	winctx->user_win = txattr->user_win;
+	winctx->nx_win = txwin->rxwin->nx_win;
+	winctx->pin_win = txattr->pin_win;
+
+	winctx->rx_wcred_mode = txattr->rx_wcred_mode;
+	winctx->tx_wcred_mode = txattr->tx_wcred_mode;
+	winctx->rx_word_mode = txattr->rx_win_ord_mode;
+	winctx->tx_word_mode = txattr->tx_win_ord_mode;
+
+	if (winctx->nx_win) {
+		winctx->data_stamp = true;
+		winctx->intr_disable = true;
+	}
+
+	winctx->lpid = txattr->lpid;
+	winctx->pidr = txattr->pidr;
+	winctx->rx_win_id = txwin->rxwin->winid;
+
+	winctx->dma_type = VAS_DMA_TYPE_INJECT;
+	winctx->tc_mode = txattr->tc_mode;
+	winctx->min_scope = VAS_SCOPE_LOCAL;
+	winctx->max_scope = VAS_SCOPE_VECTORED_GROUP;
+
+	winctx->pswid = 0;
+}
+
+static bool tx_win_args_valid(enum vas_cop_type cop,
+			struct vas_tx_win_attr *attr)
+{
+	if (attr->tc_mode != VAS_THRESH_DISABLED)
+		return false;
+
+	if (cop > VAS_COP_TYPE_MAX)
+		return false;
+
+	if (attr->user_win &&
+			(cop != VAS_COP_TYPE_FTW || attr->rsvd_txbuf_count))
+		return false;
+
+	return true;
+}
+
+struct vas_window *vas_tx_win_open(int vasid, enum vas_cop_type cop,
+			struct vas_tx_win_attr *attr)
+{
+	int rc;
+	struct vas_window *txwin;
+	struct vas_window *rxwin;
+	struct vas_winctx winctx;
+	struct vas_instance *vinst;
+
+	if (!tx_win_args_valid(cop, attr))
+		return ERR_PTR(-EINVAL);
+
+	vinst = find_vas_instance(vasid);
+	if (!vinst) {
+		pr_devel("vasid %d not found!\n", vasid);
+		return ERR_PTR(-EINVAL);
+	}
+
+	rxwin = get_vinst_rxwin(vinst, cop, attr->pswid);
+	if (IS_ERR(rxwin)) {
+		pr_devel("No RxWin for vasid %d, cop %d\n", vasid, cop);
+		return rxwin;
+	}
+
+	txwin = vas_window_alloc(vinst);
+	if (IS_ERR(txwin)) {
+		rc = PTR_ERR(txwin);
+		goto put_rxwin;
+	}
+
+	txwin->tx_win = 1;
+	txwin->rxwin = rxwin;
+	txwin->nx_win = txwin->rxwin->nx_win;
+	txwin->pid = attr->pid;
+	txwin->user_win = attr->user_win;
+
+	init_winctx_for_txwin(txwin, attr, &winctx);
+
+	init_winctx_regs(txwin, &winctx);
+
+	/*
+	 * If its a kernel send window, map the window address into the
+	 * kernel's address space. For user windows, user must issue an
+	 * mmap() to map the window into their address space.
+	 *
+	 * NOTE: If kernel ever resubmits a user CRB after handling a page
+	 *	 fault, we will need to map this into kernel as well.
+	 */
+	if (!txwin->user_win) {
+		txwin->paste_kaddr = map_paste_region(txwin);
+		if (IS_ERR(txwin->paste_kaddr)) {
+			rc = PTR_ERR(txwin->paste_kaddr);
+			goto free_window;
+		}
+	}
+
+	set_vinst_win(vinst, txwin);
+
+	return txwin;
+
+free_window:
+	vas_window_free(txwin);
+
+put_rxwin:
+	put_rx_win(rxwin);
+	return ERR_PTR(rc);
+
+}
+EXPORT_SYMBOL_GPL(vas_tx_win_open);
+
+int vas_copy_crb(void *crb, int offset)
+{
+	return vas_copy(crb, offset);
+}
+EXPORT_SYMBOL_GPL(vas_copy_crb);
+
+#define RMA_LSMP_REPORT_ENABLE PPC_BIT(53)
+int vas_paste_crb(struct vas_window *txwin, int offset, bool re)
+{
+	int rc;
+	void *addr;
+	uint64_t val;
+
+	/*
+	 * Only NX windows are supported for now and hardware assumes
+	 * report-enable flag is set for NX windows. Ensure software
+	 * complies too.
+	 */
+	WARN_ON_ONCE(txwin->nx_win && !re);
+
+	addr = txwin->paste_kaddr;
+	if (re) {
+		/*
+		 * Set the REPORT_ENABLE bit (equivalent to writing
+		 * to 1K offset of the paste address)
+		 */
+		val = SET_FIELD(RMA_LSMP_REPORT_ENABLE, 0ULL, 1);
+		addr += val;
+	}
+
+	/*
+	 * Map the raw CR value from vas_paste() to an error code (there
+	 * is just pass or fail for now though).
+	 */
+	rc = vas_paste(addr, offset);
+	if (rc == 2)
+		rc = 0;
+	else
+		rc = -EINVAL;
+
+	print_fifo_msg_count(txwin);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(vas_paste_crb);
+
+static void poll_window_busy_state(struct vas_window *window)
+{
+	int busy;
+	u64 val;
+
+retry:
+	/*
+	 * Poll Window Busy flag
+	 */
+	val = read_hvwc_reg(window, VREG(WIN_STATUS));
+	busy = GET_FIELD(VAS_WIN_BUSY, val);
+	if (busy) {
+		val = 0;
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(HZ);
+		goto retry;
+	}
+}
+
+static void poll_window_castout(struct vas_window *window)
+{
+	int cached;
+	u64 val;
+
+	/* Cast window context out of the cache */
+retry:
+	val = read_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL));
+	cached = GET_FIELD(VAS_WIN_CACHE_STATUS, val);
+	if (cached) {
+		val = 0ULL;
+		val = SET_FIELD(VAS_CASTOUT_REQ, val, 1);
+		val = SET_FIELD(VAS_PUSH_TO_MEM, val, 0);
+		write_hvwc_reg(window, VREG(WIN_CTX_CACHING_CTL), val);
+
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule_timeout(HZ);
+		goto retry;
+	}
+}
+
+/*
+ * Close a window.
+ *
+ * See Section 1.12.1 of VAS workbook v1.05 for details on closing window:
+ *	- Disable new paste operations (unmap paste address)
+ *	- Poll for the "Window Busy" bit to be cleared
+ *	- Clear the Open/Enable bit for the Window.
+ *	- Poll for return of window Credits (implies FIFO empty for Rx win?)
+ *	- Unpin and cast window context out of cache
+ *
+ * Besides the hardware, kernel has some bookkeeping of course.
+ */
+int vas_win_close(struct vas_window *window)
+{
+	u64 val;
+
+	if (!window)
+		return 0;
+
+	if (!window->tx_win && atomic_read(&window->num_txwins) != 0) {
+		pr_devel("Attempting to close an active Rx window!\n");
+		WARN_ON_ONCE(1);
+		return -EBUSY;
+	}
+
+	unmap_paste_region(window);
+
+	clear_vinst_win(window);
+
+	poll_window_busy_state(window);
+
+	/* Unpin window from cache and close it */
+	val = read_hvwc_reg(window, VREG(WINCTL));
+	val = SET_FIELD(VAS_WINCTL_PIN, val, 0);
+	val = SET_FIELD(VAS_WINCTL_OPEN, val, 0);
+	write_hvwc_reg(window, VREG(WINCTL), val);
+
+	poll_window_castout(window);
+
+	/* if send window, drop reference to matching receive window */
+	if (window->tx_win)
+		put_rx_win(window->rxwin);
+
+	vas_window_free(window);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vas_win_close);
diff --git a/arch/powerpc/platforms/powernv/vas.c b/arch/powerpc/platforms/powernv/vas.c
new file mode 100644
index 000000000000..565a4878fefa
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/vas.c
@@ -0,0 +1,151 @@
+/*
+ * Copyright 2016-17 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "vas: " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/of.h>
+
+#include "vas.h"
+
+static DEFINE_MUTEX(vas_mutex);
+static LIST_HEAD(vas_instances);
+
+static int init_vas_instance(struct platform_device *pdev)
+{
+	int rc, vasid;
+	struct resource *res;
+	struct vas_instance *vinst;
+	struct device_node *dn = pdev->dev.of_node;
+
+	rc = of_property_read_u32(dn, "ibm,vas-id", &vasid);
+	if (rc) {
+		pr_err("No ibm,vas-id property for %s?\n", pdev->name);
+		return -ENODEV;
+	}
+
+	if (pdev->num_resources != 4) {
+		pr_err("Unexpected DT configuration for [%s, %d]\n",
+				pdev->name, vasid);
+		return -ENODEV;
+	}
+
+	vinst = kzalloc(sizeof(*vinst), GFP_KERNEL);
+	if (!vinst)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&vinst->node);
+	ida_init(&vinst->ida);
+	mutex_init(&vinst->mutex);
+	vinst->vas_id = vasid;
+	vinst->pdev = pdev;
+
+	res = &pdev->resource[0];
+	vinst->hvwc_bar_start = res->start;
+
+	res = &pdev->resource[1];
+	vinst->uwc_bar_start = res->start;
+
+	res = &pdev->resource[2];
+	vinst->paste_base_addr = res->start;
+
+	res = &pdev->resource[3];
+	if (res->end > 62) {
+		pr_err("Bad 'paste_win_id_shift' in DT, %llx\n", res->end);
+		goto free_vinst;
+	}
+
+	vinst->paste_win_id_shift = 63 - res->end;
+
+	pr_devel("Initialized instance [%s, %d], paste_base 0x%llx, "
+			"paste_win_id_shift 0x%llx\n", pdev->name, vasid,
+			vinst->paste_base_addr, vinst->paste_win_id_shift);
+
+	mutex_lock(&vas_mutex);
+	list_add(&vinst->node, &vas_instances);
+	mutex_unlock(&vas_mutex);
+
+	dev_set_drvdata(&pdev->dev, vinst);
+
+	return 0;
+
+free_vinst:
+	kfree(vinst);
+	return -ENODEV;
+
+}
+
+/*
+ * Although this is read/used multiple times, it is written to only
+ * during initialization.
+ */
+struct vas_instance *find_vas_instance(int vasid)
+{
+	struct list_head *ent;
+	struct vas_instance *vinst;
+
+	mutex_lock(&vas_mutex);
+	list_for_each(ent, &vas_instances) {
+		vinst = list_entry(ent, struct vas_instance, node);
+		if (vinst->vas_id == vasid) {
+			mutex_unlock(&vas_mutex);
+			return vinst;
+		}
+	}
+	mutex_unlock(&vas_mutex);
+
+	pr_devel("Instance %d not found\n", vasid);
+	return NULL;
+}
+
+static int vas_probe(struct platform_device *pdev)
+{
+	return init_vas_instance(pdev);
+}
+
+static const struct of_device_id powernv_vas_match[] = {
+	{ .compatible = "ibm,vas",},
+	{},
+};
+
+static struct platform_driver vas_driver = {
+	.driver = {
+		.name = "vas",
+		.of_match_table = powernv_vas_match,
+	},
+	.probe = vas_probe,
+};
+
+static int __init vas_init(void)
+{
+	int found = 0;
+	struct device_node *dn;
+
+	platform_driver_register(&vas_driver);
+
+	for_each_compatible_node(dn, NULL, "ibm,vas") {
+		of_platform_device_create(dn, NULL, NULL);
+		found++;
+	}
+
+	if (!found)
+		return -ENODEV;
+
+	pr_devel("Found %d instances\n", found);
+
+	return 0;
+}
+device_initcall(vas_init);
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
new file mode 100644
index 000000000000..38dee5d50f31
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -0,0 +1,467 @@
+/*
+ * Copyright 2016-17 IBM Corp.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _VAS_H
+#define _VAS_H
+#include <linux/atomic.h>
+#include <linux/idr.h>
+#include <asm/vas.h>
+#include <linux/io.h>
+
+/*
+ * Overview of Virtual Accelerator Switchboard (VAS).
+ *
+ * VAS is a hardware "switchboard" that allows senders and receivers to
+ * exchange messages with _minimal_ kernel involvment. The receivers are
+ * typically NX coprocessor engines that perform compression or encryption
+ * in hardware, but receivers can also be other software threads.
+ *
+ * Senders are user/kernel threads that submit compression/encryption or
+ * other requests to the receivers. Senders must format their messages as
+ * Coprocessor Request Blocks (CRB)s and submit them using the "copy" and
+ * "paste" instructions which were introduced in Power9.
+ *
+ * A Power node can have (upto?) 8 Power chips. There is one instance of
+ * VAS in each Power9 chip. Each instance of VAS has 64K windows or ports,
+ * Senders and receivers must each connect to a separate window before they
+ * can exchange messages through the switchboard.
+ *
+ * Each window is described by two types of window contexts:
+ *
+ *	Hypervisor Window Context (HVWC) of size VAS_HVWC_SIZE bytes
+ *
+ *	OS/User Window Context (UWC) of size VAS_UWC_SIZE bytes.
+ *
+ * A window context can be viewed as a set of 64-bit registers. The settings
+ * in these registers configure/control/determine the behavior of the VAS
+ * hardware when messages are sent/received through the window. The registers
+ * in the HVWC are configured by the kernel while the registers in the UWC can
+ * be configured by the kernel or by the user space application that is using
+ * the window.
+ *
+ * The HVWCs for all windows on a specific instance of VAS are in a contiguous
+ * range of hardware addresses or Base address region (BAR) referred to as the
+ * HVWC BAR for the instance. Similarly the UWCs for all windows on an instance
+ * are referred to as the UWC BAR for the instance.
+ *
+ * The two BARs for each instance are defined Power9 MMIO Ranges spreadsheet
+ * and available to the kernel in the VAS node's "reg" property in the device
+ * tree:
+ *
+ *	/proc/device-tree/vasm@.../reg
+ *
+ * (see vas_probe() for details on the reg property).
+ *
+ * The kernel maps the HVWC and UWC BAR regions into the kernel address
+ * space (hvwc_map and uwc_map). The kernel can then access the window
+ * contexts of a specific window using:
+ *
+ *	 hvwc = hvwc_map + winid * VAS_HVWC_SIZE.
+ *	 uwc = uwc_map + winid * VAS_UWC_SIZE.
+ *
+ * where winid is the window index (0..64K).
+ *
+ * As mentioned, a window context is used to "configure" a window. Besides
+ * this configuration address, each _send_ window also has a unique hardware
+ * "paste" address that is used to submit requests/CRBs (see vas_paste_crb()).
+ *
+ * The hardware paste address for a window is computed using the "paste
+ * base address" and "paste win id shift" reg properties in the VAS device
+ * tree node using:
+ *
+ *	paste_addr = paste_base + ((winid << paste_win_id_shift))
+ *
+ * (again, see vas_probe() for ->paste_base_addr and ->paste_win_id_shift).
+ *
+ * The kernel maps this hardware address into the sender's address space
+ * after which they can use the 'paste' instruction (new in Power9) to
+ * send a message (submit a request aka CRB) to the coprocessor.
+ *
+ * NOTE: In the initial version, senders can only in-kernel drivers/threads.
+ *	 Support for user space threads will be added in follow-on patches.
+ *
+ * TODO: Do we need to map the UWC into user address space so they can return
+ *	 credits? Its NA for NX but may be needed for other receive windows.
+ *
+ */
+
+#define VAS_WINDOWS_PER_CHIP		(64 << 10)
+
+/*
+ * Hypervisor and OS/USer Window Context sizes
+ */
+#define VAS_HVWC_SIZE			512
+#define VAS_UWC_SIZE			PAGE_SIZE
+
+/*
+ * Initial per-process credits.
+ * Max send window credits:    4K-1 (12-bits in VAS_TX_WCRED)
+ * Max receive window credits: 64K-1 (16 bits in VAS_LRX_WCRED)
+ *
+ * TODO: Needs tuning for per-process credits
+ */
+#define VAS_WCREDS_MIN			16
+#define VAS_WCREDS_MAX			((64 << 10) - 1)
+#define VAS_WCREDS_DEFAULT		(1 << 10)
+
+/*
+ * VAS Window Context Register Offsets and bitmasks.
+ * See Section 3.1.4 of VAS Work book
+ */
+#define VAS_LPID_OFFSET			0x010
+#define VAS_LPID			PPC_BITMASK(0, 11)
+
+#define VAS_PID_OFFSET			0x018
+#define VAS_PID_ID			PPC_BITMASK(0, 19)
+
+#define VAS_XLATE_MSR_OFFSET		0x020
+#define VAS_XLATE_MSR_DR		PPC_BIT(0)
+#define VAS_XLATE_MSR_TA		PPC_BIT(1)
+#define VAS_XLATE_MSR_PR		PPC_BIT(2)
+#define VAS_XLATE_MSR_US		PPC_BIT(3)
+#define VAS_XLATE_MSR_HV		PPC_BIT(4)
+#define VAS_XLATE_MSR_SF		PPC_BIT(5)
+
+#define VAS_XLATE_LPCR_OFFSET		0x028
+#define VAS_XLATE_LPCR_PAGE_SIZE	PPC_BITMASK(0, 2)
+#define VAS_XLATE_LPCR_ISL		PPC_BIT(3)
+#define VAS_XLATE_LPCR_TC		PPC_BIT(4)
+#define VAS_XLATE_LPCR_SC		PPC_BIT(5)
+
+#define VAS_XLATE_CTL_OFFSET		0x030
+#define VAS_XLATE_MODE			PPC_BITMASK(0, 1)
+
+#define VAS_AMR_OFFSET			0x040
+#define VAS_AMR				PPC_BITMASK(0, 63)
+
+#define VAS_SEIDR_OFFSET		0x048
+#define VAS_SEIDR			PPC_BITMASK(0, 63)
+
+#define VAS_FAULT_TX_WIN_OFFSET		0x050
+#define VAS_FAULT_TX_WIN		PPC_BITMASK(48, 63)
+
+#define VAS_OSU_INTR_SRC_RA_OFFSET	0x060
+#define VAS_OSU_INTR_SRC_RA		PPC_BITMASK(8, 63)
+
+#define VAS_HV_INTR_SRC_RA_OFFSET	0x070
+#define VAS_HV_INTR_SRC_RA		PPC_BITMASK(8, 63)
+
+#define VAS_PSWID_OFFSET		0x078
+#define VAS_PSWID_EA_HANDLE		PPC_BITMASK(0, 31)
+
+#define VAS_SPARE1_OFFSET		0x080
+#define VAS_SPARE2_OFFSET		0x088
+#define VAS_SPARE3_OFFSET		0x090
+#define VAS_SPARE4_OFFSET		0x130
+#define VAS_SPARE5_OFFSET		0x160
+#define VAS_SPARE6_OFFSET		0x188
+
+#define VAS_LFIFO_BAR_OFFSET		0x0A0
+#define VAS_LFIFO_BAR			PPC_BITMASK(8, 53)
+#define VAS_PAGE_MIGRATION_SELECT	PPC_BITMASK(54, 56)
+
+#define VAS_LDATA_STAMP_CTL_OFFSET	0x0A8
+#define VAS_LDATA_STAMP			PPC_BITMASK(0, 1)
+#define VAS_XTRA_WRITE			PPC_BIT(2)
+
+#define VAS_LDMA_CACHE_CTL_OFFSET	0x0B0
+#define VAS_LDMA_TYPE			PPC_BITMASK(0, 1)
+#define VAS_LDMA_FIFO_DISABLE		PPC_BIT(2)
+
+#define VAS_LRFIFO_PUSH_OFFSET		0x0B8
+#define VAS_LRFIFO_PUSH			PPC_BITMASK(0, 15)
+
+#define VAS_CURR_MSG_COUNT_OFFSET	0x0C0
+#define VAS_CURR_MSG_COUNT		PPC_BITMASK(0, 7)
+
+#define VAS_LNOTIFY_AFTER_COUNT_OFFSET	0x0C8
+#define VAS_LNOTIFY_AFTER_COUNT		PPC_BITMASK(0, 7)
+
+#define VAS_LRX_WCRED_OFFSET		0x0E0
+#define VAS_LRX_WCRED			PPC_BITMASK(0, 15)
+
+#define VAS_LRX_WCRED_ADDER_OFFSET	0x190
+#define VAS_LRX_WCRED_ADDER		PPC_BITMASK(0, 15)
+
+#define VAS_TX_WCRED_OFFSET		0x0F0
+#define VAS_TX_WCRED			PPC_BITMASK(4, 15)
+
+#define VAS_TX_WCRED_ADDER_OFFSET	0x1A0
+#define VAS_TX_WCRED_ADDER		PPC_BITMASK(4, 15)
+
+#define VAS_LFIFO_SIZE_OFFSET		0x100
+#define VAS_LFIFO_SIZE			PPC_BITMASK(0, 3)
+
+#define VAS_WINCTL_OFFSET		0x108
+#define VAS_WINCTL_OPEN			PPC_BIT(0)
+#define VAS_WINCTL_REJ_NO_CREDIT	PPC_BIT(1)
+#define VAS_WINCTL_PIN			PPC_BIT(2)
+#define VAS_WINCTL_TX_WCRED_MODE	PPC_BIT(3)
+#define VAS_WINCTL_RX_WCRED_MODE	PPC_BIT(4)
+#define VAS_WINCTL_TX_WORD_MODE		PPC_BIT(5)
+#define VAS_WINCTL_RX_WORD_MODE		PPC_BIT(6)
+#define VAS_WINCTL_RSVD_TXBUF		PPC_BIT(7)
+#define VAS_WINCTL_THRESH_CTL		PPC_BITMASK(8, 9)
+#define VAS_WINCTL_FAULT_WIN		PPC_BIT(10)
+#define VAS_WINCTL_NX_WIN		PPC_BIT(11)
+
+#define VAS_WIN_STATUS_OFFSET		0x110
+#define VAS_WIN_BUSY			PPC_BIT(1)
+
+#define VAS_WIN_CTX_CACHING_CTL_OFFSET	0x118
+#define VAS_CASTOUT_REQ			PPC_BIT(0)
+#define VAS_PUSH_TO_MEM			PPC_BIT(1)
+#define VAS_WIN_CACHE_STATUS		PPC_BIT(4)
+
+#define VAS_TX_RSVD_BUF_COUNT_OFFSET	0x120
+#define VAS_RXVD_BUF_COUNT		PPC_BITMASK(58, 63)
+
+#define VAS_LRFIFO_WIN_PTR_OFFSET	0x128
+#define VAS_LRX_WIN_ID			PPC_BITMASK(0, 15)
+
+/*
+ * Local Notification Control Register controls what happens in _response_
+ * to a paste command and hence applies only to receive windows.
+ */
+#define VAS_LNOTIFY_CTL_OFFSET		0x138
+#define VAS_NOTIFY_DISABLE		PPC_BIT(0)
+#define VAS_INTR_DISABLE		PPC_BIT(1)
+#define VAS_NOTIFY_EARLY		PPC_BIT(2)
+#define VAS_NOTIFY_OSU_INTR		PPC_BIT(3)
+
+#define VAS_LNOTIFY_PID_OFFSET		0x140
+#define VAS_LNOTIFY_PID			PPC_BITMASK(0, 19)
+
+#define VAS_LNOTIFY_LPID_OFFSET		0x148
+#define VAS_LNOTIFY_LPID		PPC_BITMASK(0, 11)
+
+#define VAS_LNOTIFY_TID_OFFSET		0x150
+#define VAS_LNOTIFY_TID			PPC_BITMASK(0, 15)
+
+#define VAS_LNOTIFY_SCOPE_OFFSET	0x158
+#define VAS_LNOTIFY_MIN_SCOPE		PPC_BITMASK(0, 1)
+#define VAS_LNOTIFY_MAX_SCOPE		PPC_BITMASK(2, 3)
+
+#define VAS_NX_UTIL_OFFSET		0x1B0
+#define VAS_NX_UTIL			PPC_BITMASK(0, 63)
+
+/* SE: Side effects */
+#define VAS_NX_UTIL_SE_OFFSET		0x1B8
+#define VAS_NX_UTIL_SE			PPC_BITMASK(0, 63)
+
+#define VAS_NX_UTIL_ADDER_OFFSET	0x180
+#define VAS_NX_UTIL_ADDER		PPC_BITMASK(32, 63)
+
+/*
+ * Local Notify Scope Control Register. (Receive windows only).
+ */
+enum vas_notify_scope {
+	VAS_SCOPE_LOCAL,
+	VAS_SCOPE_GROUP,
+	VAS_SCOPE_VECTORED_GROUP,
+	VAS_SCOPE_UNUSED,
+};
+
+/*
+ * Local DMA Cache Control Register (Receive windows only).
+ */
+enum vas_dma_type {
+	VAS_DMA_TYPE_INJECT,
+	VAS_DMA_TYPE_WRITE,
+};
+
+/*
+ * Local Notify Scope Control Register. (Receive windows only).
+ * Not applicable to NX receive windows.
+ */
+enum vas_notify_after_count {
+	VAS_NOTIFY_AFTER_256 = 0,
+	VAS_NOTIFY_NONE,
+	VAS_NOTIFY_AFTER_2
+};
+
+/*
+ * One per instance of VAS. Each instance will have a separate set of
+ * receive windows, one per coprocessor type.
+ *
+ * See also function header of set_vinst_win() for details on ->windows[]
+ * and ->rxwin[] tables.
+ */
+struct vas_instance {
+	int vas_id;
+	struct ida ida;
+	struct list_head node;
+	struct platform_device *pdev;
+
+	u64 hvwc_bar_start;
+	u64 uwc_bar_start;
+	u64 paste_base_addr;
+	u64 paste_win_id_shift;
+
+	struct mutex mutex;
+	struct vas_window *rxwin[VAS_COP_TYPE_MAX];
+	struct vas_window *windows[VAS_WINDOWS_PER_CHIP];
+};
+
+/*
+ * In-kernel state a VAS window. One per window.
+ */
+struct vas_window {
+	/* Fields common to send and receive windows */
+	struct vas_instance *vinst;
+	int winid;
+	bool tx_win;		/* True if send window */
+	bool nx_win;		/* True if NX window */
+	bool user_win;		/* True if user space window */
+	void *hvwc_map;		/* HV window context */
+	void *uwc_map;		/* OS/User window context */
+	pid_t pid;		/* Linux process id of owner */
+
+	/* Fields applicable only to send windows */
+	void *paste_kaddr;
+	char *paste_addr_name;
+	struct vas_window *rxwin;
+
+	/* Feilds applicable only to receive windows */
+	enum vas_cop_type cop;
+	atomic_t num_txwins;
+};
+
+/*
+ * Container for the hardware state of a window. One per-window.
+ *
+ * A VAS Window context is a 512-byte area in the hardware that contains
+ * a set of 64-bit registers. Individual bit-fields in these registers
+ * determine the configuration/operation of the hardware. struct vas_winctx
+ * is a container for the register fields in the window context.
+ */
+struct vas_winctx {
+	void *rx_fifo;
+	int rx_fifo_size;
+	int wcreds_max;
+	int rsvd_txbuf_count;
+
+	bool user_win;
+	bool nx_win;
+	bool fault_win;
+	bool rsvd_txbuf_enable;
+	bool pin_win;
+	bool rej_no_credit;
+	bool tx_wcred_mode;
+	bool rx_wcred_mode;
+	bool tx_word_mode;
+	bool rx_word_mode;
+	bool data_stamp;
+	bool xtra_write;
+	bool notify_disable;
+	bool intr_disable;
+	bool fifo_disable;
+	bool notify_early;
+	bool notify_os_intr_reg;
+
+	int lpid;
+	int pidr;		/* value from SPRN_PID, not linux pid */
+	int lnotify_lpid;
+	int lnotify_pid;
+	int lnotify_tid;
+	u32 pswid;
+	int rx_win_id;
+	int fault_win_id;
+	int tc_mode;
+
+	u64 irq_port;
+
+	enum vas_dma_type dma_type;
+	enum vas_notify_scope min_scope;
+	enum vas_notify_scope max_scope;
+	enum vas_notify_after_count notify_after_count;
+};
+
+extern struct vas_instance *find_vas_instance(int vasid);
+
+/*
+ * VREG(x):
+ * Expand a register's short name (eg: LPID) into two parameters:
+ *	- the register's short name in string form ("LPID"), and
+ *	- the name of the macro (eg: VAS_LPID_OFFSET), defining the
+ *	  register's offset in the window context
+ */
+#define VREG_SFX(n, s)	__stringify(n), VAS_##n##s
+#define VREG(r)		VREG_SFX(r, _OFFSET)
+
+#ifdef vas_debug
+static inline void dump_rx_win_attr(struct vas_rx_win_attr *attr)
+{
+	pr_err("fault %d, notify %d, intr %d early %d\n",
+			attr->fault_win, attr->notify_disable,
+			attr->intr_disable, attr->notify_early);
+
+	pr_err("rx_fifo_size %d, max value %d\n",
+				attr->rx_fifo_size, VAS_RX_FIFO_SIZE_MAX);
+}
+
+static inline void vas_log_write(struct vas_window *win, char *name,
+			void *regptr, u64 val)
+{
+	if (val)
+		pr_err("%swin #%d: %s reg %p, val 0x%016llx\n",
+				win->tx_win ? "Tx" : "Rx", win->winid, name,
+				regptr, val);
+}
+
+#else	/* vas_debug */
+
+#define vas_log_write(win, name, reg, val)
+#define dump_rx_win_attr(attr)
+
+#endif	/* vas_debug */
+
+static inline void write_uwc_reg(struct vas_window *win, char *name,
+			s32 reg, u64 val)
+{
+	void *regptr;
+
+	regptr = win->uwc_map + reg;
+	vas_log_write(win, name, regptr, val);
+
+	out_be64(regptr, val);
+}
+
+static inline void write_hvwc_reg(struct vas_window *win, char *name,
+			s32 reg, u64 val)
+{
+	void *regptr;
+
+	regptr = win->hvwc_map + reg;
+	vas_log_write(win, name, regptr, val);
+
+	out_be64(regptr, val);
+}
+
+static inline u64 read_hvwc_reg(struct vas_window *win,
+			char *name __maybe_unused, s32 reg)
+{
+	return in_be64(win->hvwc_map+reg);
+}
+
+#ifdef vas_debug
+
+static void print_fifo_msg_count(struct vas_window *txwin)
+{
+	uint64_t read_hvwc_reg(struct vas_window *w, char *n, uint64_t o);
+	pr_devel("Winid %d, Msg count %llu\n", txwin->winid,
+			(uint64_t)read_hvwc_reg(txwin, VREG(LRFIFO_PUSH)));
+}
+#else	/* vas_debug */
+
+#define print_fifo_msg_count(window)
+
+#endif	/* vas_debug */
+
+#endif /* _VAS_H */