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

Pull powerpc updates from Michael Ellerman:
 "Notable changes:

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

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

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

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

  And the usual small fixes, cleanups and improvements.

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

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

11 files changed, 87 insertions, 764 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 9ade4489f415..620a986209f5 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1,8 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- * The file intends to implement the platform dependent EEH operations on
- * powernv platform. Actually, the powernv was created in order to fully
- * hypervisor support.
+ * PowerNV Platform dependent EEH operations
  *
  * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2013.
  */
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 2f4479b94ac3..09f49eed7fb8 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -716,7 +716,7 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 		 * to reload MMCR0 (see mmcr0 comment above).
 		 */
 		if (!cpu_has_feature(CPU_FTR_POWER9_DD2_1)) {
-			asm volatile(PPC_INVALIDATE_ERAT);
+			asm volatile(PPC_ISA_3_0_INVALIDATE_ERAT);
 			mtspr(SPRN_MMCR0, mmcr0);
 		}
 
@@ -758,7 +758,6 @@ static unsigned long power9_idle_stop(unsigned long psscr, bool mmu_on)
 	mtspr(SPRN_PTCR,	sprs.ptcr);
 	mtspr(SPRN_RPR,		sprs.rpr);
 	mtspr(SPRN_TSCR,	sprs.tscr);
-	mtspr(SPRN_LDBAR,	sprs.ldbar);
 
 	if (pls >= pnv_first_tb_loss_level) {
 		/* TB loss */
@@ -790,6 +789,7 @@ core_woken:
 	mtspr(SPRN_MMCR0,	sprs.mmcr0);
 	mtspr(SPRN_MMCR1,	sprs.mmcr1);
 	mtspr(SPRN_MMCR2,	sprs.mmcr2);
+	mtspr(SPRN_LDBAR,	sprs.ldbar);
 
 	mtspr(SPRN_SPRG3,	local_paca->sprg_vdso);
 
@@ -1155,10 +1155,10 @@ static void __init pnv_power9_idle_init(void)
 			pnv_deepest_stop_psscr_mask);
 	}
 
-	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%lld\n",
+	pr_info("cpuidle-powernv: First stop level that may lose SPRs = 0x%llx\n",
 		pnv_first_spr_loss_level);
 
-	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%lld\n",
+	pr_info("cpuidle-powernv: First stop level that may lose timebase = 0x%llx\n",
 		pnv_first_tb_loss_level);
 }
 
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index c321fdbc2200..c16249d251f1 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -19,18 +19,25 @@
 
 #include "pci.h"
 
-/*
- * spinlock to protect initialisation of an npu_context for a particular
- * mm_struct.
- */
-static DEFINE_SPINLOCK(npu_context_lock);
-
 static struct pci_dev *get_pci_dev(struct device_node *dn)
 {
 	struct pci_dn *pdn = PCI_DN(dn);
+	struct pci_dev *pdev;
 
-	return pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
+	pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pdn->phb->bus),
 					   pdn->busno, pdn->devfn);
+
+	/*
+	 * pci_get_domain_bus_and_slot() increased the reference count of
+	 * the PCI device, but callers don't need that actually as the PE
+	 * already holds a reference to the device. Since callers aren't
+	 * aware of the reference count change, call pci_dev_put() now to
+	 * avoid leaks.
+	 */
+	if (pdev)
+		pci_dev_put(pdev);
+
+	return pdev;
 }
 
 /* Given a NPU device get the associated PCI device. */
@@ -359,15 +366,6 @@ struct npu_comp {
 /* An NPU descriptor, valid for POWER9 only */
 struct npu {
 	int index;
-	__be64 *mmio_atsd_regs[NV_NMMU_ATSD_REGS];
-	unsigned int mmio_atsd_count;
-
-	/* Bitmask for MMIO register usage */
-	unsigned long mmio_atsd_usage;
-
-	/* Do we need to explicitly flush the nest mmu? */
-	bool nmmu_flush;
-
 	struct npu_comp npucomp;
 };
 
@@ -624,534 +622,8 @@ struct iommu_table_group *pnv_npu_compound_attach(struct pnv_ioda_pe *pe)
 }
 #endif /* CONFIG_IOMMU_API */
 
-/* Maximum number of nvlinks per npu */
-#define NV_MAX_LINKS 6
-
-/* Maximum index of npu2 hosts in the system. Always < NV_MAX_NPUS */
-static int max_npu2_index;
-
-struct npu_context {
-	struct mm_struct *mm;
-	struct pci_dev *npdev[NV_MAX_NPUS][NV_MAX_LINKS];
-	struct mmu_notifier mn;
-	struct kref kref;
-	bool nmmu_flush;
-
-	/* Callback to stop translation requests on a given GPU */
-	void (*release_cb)(struct npu_context *context, void *priv);
-
-	/*
-	 * Private pointer passed to the above callback for usage by
-	 * device drivers.
-	 */
-	void *priv;
-};
-
-struct mmio_atsd_reg {
-	struct npu *npu;
-	int reg;
-};
-
-/*
- * Find a free MMIO ATSD register and mark it in use. Return -ENOSPC
- * if none are available.
- */
-static int get_mmio_atsd_reg(struct npu *npu)
-{
-	int i;
-
-	for (i = 0; i < npu->mmio_atsd_count; i++) {
-		if (!test_bit(i, &npu->mmio_atsd_usage))
-			if (!test_and_set_bit_lock(i, &npu->mmio_atsd_usage))
-				return i;
-	}
-
-	return -ENOSPC;
-}
-
-static void put_mmio_atsd_reg(struct npu *npu, int reg)
-{
-	clear_bit_unlock(reg, &npu->mmio_atsd_usage);
-}
-
-/* MMIO ATSD register offsets */
-#define XTS_ATSD_LAUNCH 0
-#define XTS_ATSD_AVA    1
-#define XTS_ATSD_STAT   2
-
-static unsigned long get_atsd_launch_val(unsigned long pid, unsigned long psize)
-{
-	unsigned long launch = 0;
-
-	if (psize == MMU_PAGE_COUNT) {
-		/* IS set to invalidate entire matching PID */
-		launch |= PPC_BIT(12);
-	} else {
-		/* AP set to invalidate region of psize */
-		launch |= (u64)mmu_get_ap(psize) << PPC_BITLSHIFT(17);
-	}
-
-	/* PRS set to process-scoped */
-	launch |= PPC_BIT(13);
-
-	/* PID */
-	launch |= pid << PPC_BITLSHIFT(38);
-
-	/* Leave "No flush" (bit 39) 0 so every ATSD performs a flush */
-
-	return launch;
-}
-
-static void mmio_atsd_regs_write(struct mmio_atsd_reg
-			mmio_atsd_reg[NV_MAX_NPUS], unsigned long offset,
-			unsigned long val)
-{
-	struct npu *npu;
-	int i, reg;
-
-	for (i = 0; i <= max_npu2_index; i++) {
-		reg = mmio_atsd_reg[i].reg;
-		if (reg < 0)
-			continue;
-
-		npu = mmio_atsd_reg[i].npu;
-		__raw_writeq_be(val, npu->mmio_atsd_regs[reg] + offset);
-	}
-}
-
-static void mmio_invalidate_pid(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS],
-				unsigned long pid)
-{
-	unsigned long launch = get_atsd_launch_val(pid, MMU_PAGE_COUNT);
-
-	/* Invalidating the entire process doesn't use a va */
-	mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch);
-}
-
-static void mmio_invalidate_range(struct mmio_atsd_reg
-			mmio_atsd_reg[NV_MAX_NPUS], unsigned long pid,
-			unsigned long start, unsigned long psize)
-{
-	unsigned long launch = get_atsd_launch_val(pid, psize);
-
-	/* Write all VAs first */
-	mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_AVA, start);
-
-	/* Issue one barrier for all address writes */
-	eieio();
-
-	/* Launch */
-	mmio_atsd_regs_write(mmio_atsd_reg, XTS_ATSD_LAUNCH, launch);
-}
-
-#define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
-
-static void mmio_invalidate_wait(
-	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
-{
-	struct npu *npu;
-	int i, reg;
-
-	/* Wait for all invalidations to complete */
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* Wait for completion */
-		npu = mmio_atsd_reg[i].npu;
-		reg = mmio_atsd_reg[i].reg;
-		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
-			cpu_relax();
-	}
-}
-
-/*
- * Acquires all the address translation shootdown (ATSD) registers required to
- * launch an ATSD on all links this npu_context is active on.
- */
-static void acquire_atsd_reg(struct npu_context *npu_context,
-			struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
-{
-	int i, j;
-	struct npu *npu;
-	struct pci_dev *npdev;
-
-	for (i = 0; i <= max_npu2_index; i++) {
-		mmio_atsd_reg[i].reg = -1;
-		for (j = 0; j < NV_MAX_LINKS; j++) {
-			/*
-			 * There are no ordering requirements with respect to
-			 * the setup of struct npu_context, but to ensure
-			 * consistent behaviour we need to ensure npdev[][] is
-			 * only read once.
-			 */
-			npdev = READ_ONCE(npu_context->npdev[i][j]);
-			if (!npdev)
-				continue;
-
-			npu = pci_bus_to_host(npdev->bus)->npu;
-			if (!npu)
-				continue;
-
-			mmio_atsd_reg[i].npu = npu;
-			mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
-			while (mmio_atsd_reg[i].reg < 0) {
-				mmio_atsd_reg[i].reg = get_mmio_atsd_reg(npu);
-				cpu_relax();
-			}
-			break;
-		}
-	}
-}
-
-/*
- * Release previously acquired ATSD registers. To avoid deadlocks the registers
- * must be released in the same order they were acquired above in
- * acquire_atsd_reg.
- */
-static void release_atsd_reg(struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS])
-{
-	int i;
-
-	for (i = 0; i <= max_npu2_index; i++) {
-		/*
-		 * We can't rely on npu_context->npdev[][] being the same here
-		 * as when acquire_atsd_reg() was called, hence we use the
-		 * values stored in mmio_atsd_reg during the acquire phase
-		 * rather than re-reading npdev[][].
-		 */
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		put_mmio_atsd_reg(mmio_atsd_reg[i].npu, mmio_atsd_reg[i].reg);
-	}
-}
-
-/*
- * Invalidate a virtual address range
- */
-static void mmio_invalidate(struct npu_context *npu_context,
-			unsigned long start, unsigned long size)
-{
-	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
-	unsigned long pid = npu_context->mm->context.id;
-	unsigned long atsd_start = 0;
-	unsigned long end = start + size - 1;
-	int atsd_psize = MMU_PAGE_COUNT;
-
-	/*
-	 * Convert the input range into one of the supported sizes. If the range
-	 * doesn't fit, use the next larger supported size. Invalidation latency
-	 * is high, so over-invalidation is preferred to issuing multiple
-	 * invalidates.
-	 *
-	 * A 4K page size isn't supported by NPU/GPU ATS, so that case is
-	 * ignored.
-	 */
-	if (size == SZ_64K) {
-		atsd_start = start;
-		atsd_psize = MMU_PAGE_64K;
-	} else if (ALIGN_DOWN(start, SZ_2M) == ALIGN_DOWN(end, SZ_2M)) {
-		atsd_start = ALIGN_DOWN(start, SZ_2M);
-		atsd_psize = MMU_PAGE_2M;
-	} else if (ALIGN_DOWN(start, SZ_1G) == ALIGN_DOWN(end, SZ_1G)) {
-		atsd_start = ALIGN_DOWN(start, SZ_1G);
-		atsd_psize = MMU_PAGE_1G;
-	}
-
-	if (npu_context->nmmu_flush)
-		/*
-		 * Unfortunately the nest mmu does not support flushing specific
-		 * addresses so we have to flush the whole mm once before
-		 * shooting down the GPU translation.
-		 */
-		flush_all_mm(npu_context->mm);
-
-	/*
-	 * Loop over all the NPUs this process is active on and launch
-	 * an invalidate.
-	 */
-	acquire_atsd_reg(npu_context, mmio_atsd_reg);
-
-	if (atsd_psize == MMU_PAGE_COUNT)
-		mmio_invalidate_pid(mmio_atsd_reg, pid);
-	else
-		mmio_invalidate_range(mmio_atsd_reg, pid, atsd_start,
-					atsd_psize);
-
-	mmio_invalidate_wait(mmio_atsd_reg);
-
-	/*
-	 * The GPU requires two flush ATSDs to ensure all entries have been
-	 * flushed. We use PID 0 as it will never be used for a process on the
-	 * GPU.
-	 */
-	mmio_invalidate_pid(mmio_atsd_reg, 0);
-	mmio_invalidate_wait(mmio_atsd_reg);
-	mmio_invalidate_pid(mmio_atsd_reg, 0);
-	mmio_invalidate_wait(mmio_atsd_reg);
-
-	release_atsd_reg(mmio_atsd_reg);
-}
-
-static void pnv_npu2_mn_release(struct mmu_notifier *mn,
-				struct mm_struct *mm)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-
-	/* Call into device driver to stop requests to the NMMU */
-	if (npu_context->release_cb)
-		npu_context->release_cb(npu_context, npu_context->priv);
-
-	/*
-	 * There should be no more translation requests for this PID, but we
-	 * need to ensure any entries for it are removed from the TLB.
-	 */
-	mmio_invalidate(npu_context, 0, ~0UL);
-}
-
-static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
-					struct mm_struct *mm,
-					unsigned long start, unsigned long end)
-{
-	struct npu_context *npu_context = mn_to_npu_context(mn);
-	mmio_invalidate(npu_context, start, end - start);
-}
-
-static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
-	.release = pnv_npu2_mn_release,
-	.invalidate_range = pnv_npu2_mn_invalidate_range,
-};
-
-/*
- * Call into OPAL to setup the nmmu context for the current task in
- * the NPU. This must be called to setup the context tables before the
- * GPU issues ATRs. pdev should be a pointed to PCIe GPU device.
- *
- * A release callback should be registered to allow a device driver to
- * be notified that it should not launch any new translation requests
- * as the final TLB invalidate is about to occur.
- *
- * Returns an error if there no contexts are currently available or a
- * npu_context which should be passed to pnv_npu2_handle_fault().
- *
- * mmap_sem must be held in write mode and must not be called from interrupt
- * context.
- */
-struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
-			unsigned long flags,
-			void (*cb)(struct npu_context *, void *),
-			void *priv)
-{
-	int rc;
-	u32 nvlink_index;
-	struct device_node *nvlink_dn;
-	struct mm_struct *mm = current->mm;
-	struct npu *npu;
-	struct npu_context *npu_context;
-	struct pci_controller *hose;
-
-	/*
-	 * At present we don't support GPUs connected to multiple NPUs and I'm
-	 * not sure the hardware does either.
-	 */
-	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
-
-	if (!npdev)
-		/* No nvlink associated with this GPU device */
-		return ERR_PTR(-ENODEV);
-
-	/* We only support DR/PR/HV in pnv_npu2_map_lpar_dev() */
-	if (flags & ~(MSR_DR | MSR_PR | MSR_HV))
-		return ERR_PTR(-EINVAL);
-
-	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
-	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
-							&nvlink_index)))
-		return ERR_PTR(-ENODEV);
-
-	if (!mm || mm->context.id == 0) {
-		/*
-		 * Kernel thread contexts are not supported and context id 0 is
-		 * reserved on the GPU.
-		 */
-		return ERR_PTR(-EINVAL);
-	}
-
-	hose = pci_bus_to_host(npdev->bus);
-	npu = hose->npu;
-	if (!npu)
-		return ERR_PTR(-ENODEV);
-
-	/*
-	 * We store the npu pci device so we can more easily get at the
-	 * associated npus.
-	 */
-	spin_lock(&npu_context_lock);
-	npu_context = mm->context.npu_context;
-	if (npu_context) {
-		if (npu_context->release_cb != cb ||
-			npu_context->priv != priv) {
-			spin_unlock(&npu_context_lock);
-			return ERR_PTR(-EINVAL);
-		}
-
-		WARN_ON(!kref_get_unless_zero(&npu_context->kref));
-	}
-	spin_unlock(&npu_context_lock);
-
-	if (!npu_context) {
-		/*
-		 * We can set up these fields without holding the
-		 * npu_context_lock as the npu_context hasn't been returned to
-		 * the caller meaning it can't be destroyed. Parallel allocation
-		 * is protected against by mmap_sem.
-		 */
-		rc = -ENOMEM;
-		npu_context = kzalloc(sizeof(struct npu_context), GFP_KERNEL);
-		if (npu_context) {
-			kref_init(&npu_context->kref);
-			npu_context->mm = mm;
-			npu_context->mn.ops = &nv_nmmu_notifier_ops;
-			rc = __mmu_notifier_register(&npu_context->mn, mm);
-		}
-
-		if (rc) {
-			kfree(npu_context);
-			return ERR_PTR(rc);
-		}
-
-		mm->context.npu_context = npu_context;
-	}
-
-	npu_context->release_cb = cb;
-	npu_context->priv = priv;
-
-	/*
-	 * npdev is a pci_dev pointer setup by the PCI code. We assign it to
-	 * npdev[][] to indicate to the mmu notifiers that an invalidation
-	 * should also be sent over this nvlink. The notifiers don't use any
-	 * other fields in npu_context, so we just need to ensure that when they
-	 * deference npu_context->npdev[][] it is either a valid pointer or
-	 * NULL.
-	 */
-	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], npdev);
-
-	if (!npu->nmmu_flush) {
-		/*
-		 * If we're not explicitly flushing ourselves we need to mark
-		 * the thread for global flushes
-		 */
-		npu_context->nmmu_flush = false;
-		mm_context_add_copro(mm);
-	} else
-		npu_context->nmmu_flush = true;
-
-	return npu_context;
-}
-EXPORT_SYMBOL(pnv_npu2_init_context);
-
-static void pnv_npu2_release_context(struct kref *kref)
-{
-	struct npu_context *npu_context =
-		container_of(kref, struct npu_context, kref);
-
-	if (!npu_context->nmmu_flush)
-		mm_context_remove_copro(npu_context->mm);
-
-	npu_context->mm->context.npu_context = NULL;
-}
-
-/*
- * Destroy a context on the given GPU. May free the npu_context if it is no
- * longer active on any GPUs. Must not be called from interrupt context.
- */
-void pnv_npu2_destroy_context(struct npu_context *npu_context,
-			struct pci_dev *gpdev)
-{
-	int removed;
-	struct npu *npu;
-	struct pci_dev *npdev = pnv_pci_get_npu_dev(gpdev, 0);
-	struct device_node *nvlink_dn;
-	u32 nvlink_index;
-	struct pci_controller *hose;
-
-	if (WARN_ON(!npdev))
-		return;
-
-	hose = pci_bus_to_host(npdev->bus);
-	npu = hose->npu;
-	if (!npu)
-		return;
-	nvlink_dn = of_parse_phandle(npdev->dev.of_node, "ibm,nvlink", 0);
-	if (WARN_ON(of_property_read_u32(nvlink_dn, "ibm,npu-link-index",
-							&nvlink_index)))
-		return;
-	WRITE_ONCE(npu_context->npdev[npu->index][nvlink_index], NULL);
-	spin_lock(&npu_context_lock);
-	removed = kref_put(&npu_context->kref, pnv_npu2_release_context);
-	spin_unlock(&npu_context_lock);
-
-	/*
-	 * We need to do this outside of pnv_npu2_release_context so that it is
-	 * outside the spinlock as mmu_notifier_destroy uses SRCU.
-	 */
-	if (removed) {
-		mmu_notifier_unregister(&npu_context->mn,
-					npu_context->mm);
-
-		kfree(npu_context);
-	}
-
-}
-EXPORT_SYMBOL(pnv_npu2_destroy_context);
-
-/*
- * Assumes mmap_sem is held for the contexts associated mm.
- */
-int pnv_npu2_handle_fault(struct npu_context *context, uintptr_t *ea,
-			unsigned long *flags, unsigned long *status, int count)
-{
-	u64 rc = 0, result = 0;
-	int i, is_write;
-	struct page *page[1];
-	const char __user *u;
-	char c;
-
-	/* mmap_sem should be held so the struct_mm must be present */
-	struct mm_struct *mm = context->mm;
-
-	WARN_ON(!rwsem_is_locked(&mm->mmap_sem));
-
-	for (i = 0; i < count; i++) {
-		is_write = flags[i] & NPU2_WRITE;
-		rc = get_user_pages_remote(NULL, mm, ea[i], 1,
-					is_write ? FOLL_WRITE : 0,
-					page, NULL, NULL);
-
-		if (rc != 1) {
-			status[i] = rc;
-			result = -EFAULT;
-			continue;
-		}
-
-		/* Make sure partition scoped tree gets a pte */
-		u = page_address(page[0]);
-		if (__get_user(c, u))
-			result = -EFAULT;
-
-		status[i] = 0;
-		put_page(page[0]);
-	}
-
-	return result;
-}
-EXPORT_SYMBOL(pnv_npu2_handle_fault);
-
 int pnv_npu2_init(struct pci_controller *hose)
 {
-	unsigned int i;
-	u64 mmio_atsd;
 	static int npu_index;
 	struct npu *npu;
 	int ret;
@@ -1160,33 +632,18 @@ int pnv_npu2_init(struct pci_controller *hose)
 	if (!npu)
 		return -ENOMEM;
 
-	npu->nmmu_flush = of_property_read_bool(hose->dn, "ibm,nmmu-flush");
-
-	for (i = 0; i < ARRAY_SIZE(npu->mmio_atsd_regs) &&
-			!of_property_read_u64_index(hose->dn, "ibm,mmio-atsd",
-				i, &mmio_atsd); i++)
-		npu->mmio_atsd_regs[i] = ioremap(mmio_atsd, 32);
-
-	pr_info("NPU%d: Found %d MMIO ATSD registers", hose->global_number, i);
-	npu->mmio_atsd_count = i;
-	npu->mmio_atsd_usage = 0;
 	npu_index++;
 	if (WARN_ON(npu_index >= NV_MAX_NPUS)) {
 		ret = -ENOSPC;
 		goto fail_exit;
 	}
-	max_npu2_index = npu_index;
 	npu->index = npu_index;
 	hose->npu = npu;
 
 	return 0;
 
 fail_exit:
-	for (i = 0; i < npu->mmio_atsd_count; ++i)
-		iounmap(npu->mmio_atsd_regs[i]);
-
 	kfree(npu);
-
 	return ret;
 }
 
diff --git a/arch/powerpc/platforms/powernv/opal-call.c b/arch/powerpc/platforms/powernv/opal-call.c
index 36c8fa3647a2..29ca523c1c79 100644
--- a/arch/powerpc/platforms/powernv/opal-call.c
+++ b/arch/powerpc/platforms/powernv/opal-call.c
@@ -273,7 +273,6 @@ 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);
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index 5cae375525d0..3e1f064a18db 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -137,6 +137,43 @@ static void print_nx_checkstop_reason(const char *level,
 					xstop_reason[i].description);
 }
 
+static void print_npu_checkstop_reason(const char *level,
+					struct OpalHMIEvent *hmi_evt)
+{
+	uint8_t reason, reason_count, i;
+
+	/*
+	 * We may not have a checkstop reason on some combination of
+	 * hardware and/or skiboot version
+	 */
+	if (!hmi_evt->u.xstop_error.xstop_reason) {
+		printk("%s	NPU checkstop on chip %x\n", level,
+			be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id));
+		return;
+	}
+
+	/*
+	 * NPU2 has 3 FIRs. Reason encoded on a byte as:
+	 *   2 bits for the FIR number
+	 *   6 bits for the bit number
+	 * It may be possible to find several reasons.
+	 *
+	 * We don't display a specific message per FIR bit as there
+	 * are too many and most are meaningless without the workbook
+	 * and/or hw team help anyway.
+	 */
+	reason_count = sizeof(hmi_evt->u.xstop_error.xstop_reason) /
+		sizeof(reason);
+	for (i = 0; i < reason_count; i++) {
+		reason = (hmi_evt->u.xstop_error.xstop_reason >> (8 * i)) & 0xFF;
+		if (reason)
+			printk("%s	NPU checkstop on chip %x: FIR%d bit %d is set\n",
+				level,
+				be32_to_cpu(hmi_evt->u.xstop_error.u.chip_id),
+				reason >> 6, reason & 0x3F);
+	}
+}
+
 static void print_checkstop_reason(const char *level,
 					struct OpalHMIEvent *hmi_evt)
 {
@@ -148,6 +185,9 @@ static void print_checkstop_reason(const char *level,
 	case CHECKSTOP_TYPE_NX:
 		print_nx_checkstop_reason(level, hmi_evt);
 		break;
+	case CHECKSTOP_TYPE_NPU:
+		print_npu_checkstop_reason(level, hmi_evt);
+		break;
 	default:
 		printk("%s	Unknown Malfunction Alert of type %d\n",
 		       level, type);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 98c5d94b17fb..aba443be7daa 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -202,16 +202,18 @@ static int __init opal_register_exception_handlers(void)
 	glue = 0x7000;
 
 	/*
-	 * Check if we are running on newer firmware that exports
-	 * OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to patch
-	 * the HMI interrupt and we catch it directly in Linux.
+	 * Only ancient OPAL firmware requires this.
+	 * Specifically, firmware from FW810.00 (released June 2014)
+	 * through FW810.20 (Released October 2014).
 	 *
-	 * For older firmware (i.e currently released POWER8 System Firmware
-	 * as of today <= SV810_087), we fallback to old behavior and let OPAL
-	 * patch the HMI vector and handle it inside OPAL firmware.
+	 * Check if we are running on newer (post Oct 2014) firmware that
+	 * exports the OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to
+	 * patch the HMI interrupt and we catch it directly in Linux.
 	 *
-	 * For newer firmware (in development/yet to be released) we will
-	 * start catching/handling HMI directly in Linux.
+	 * For older firmware (i.e < FW810.20), we fallback to old behavior and
+	 * let OPAL patch the HMI vector and handle it inside OPAL firmware.
+	 *
+	 * For newer firmware we catch/handle the HMI directly in Linux.
 	 */
 	if (!opal_check_token(OPAL_HANDLE_HMI)) {
 		pr_info("Old firmware detected, OPAL handles HMIs.\n");
@@ -221,6 +223,11 @@ static int __init opal_register_exception_handlers(void)
 		glue += 128;
 	}
 
+	/*
+	 * Only applicable to ancient firmware, all modern
+	 * (post March 2015/skiboot 5.0) firmware will just return
+	 * OPAL_UNSUPPORTED.
+	 */
 	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
 #endif
 
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 10cc42b9e541..d8080558d020 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -50,6 +50,8 @@
 static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
 					      "NPU_OCAPI" };
 
+static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
+
 void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 			    const char *fmt, ...)
 {
@@ -2356,7 +2358,7 @@ static long pnv_pci_ioda2_set_window(struct iommu_table_group *table_group,
 	return 0;
 }
 
-void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable)
+static 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;
@@ -2456,6 +2458,14 @@ static long pnv_pci_ioda2_setup_default_config(struct pnv_ioda_pe *pe)
 	if (!pnv_iommu_bypass_disabled)
 		pnv_pci_ioda2_set_bypass(pe, true);
 
+	/*
+	 * Set table base for the case of IOMMU DMA use. Usually this is done
+	 * from dma_dev_setup() which is not called when a device is returned
+	 * from VFIO so do it here.
+	 */
+	if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, tbl);
+
 	return 0;
 }
 
@@ -2543,6 +2553,8 @@ static void pnv_ioda2_take_ownership(struct iommu_table_group *table_group)
 	pnv_pci_ioda2_unset_window(&pe->table_group, 0);
 	if (pe->pbus)
 		pnv_ioda_setup_bus_dma(pe, pe->pbus);
+	else if (pe->pdev)
+		set_iommu_table_base(&pe->pdev->dev, NULL);
 	iommu_tce_table_put(tbl);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index ff1a33fee8e6..6104418c9ad5 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -34,7 +34,6 @@
 #include "powernv.h"
 #include "pci.h"
 
-static DEFINE_MUTEX(p2p_mutex);
 static DEFINE_MUTEX(tunnel_mutex);
 
 int pnv_pci_get_slot_id(struct device_node *np, uint64_t *id)
@@ -857,79 +856,6 @@ 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);
-
 struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 {
 	struct pci_controller *hose = pci_bus_to_host(dev->bus);
@@ -938,54 +864,6 @@ struct device_node *pnv_pci_get_phb_node(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(pnv_pci_get_phb_node);
 
-int pnv_pci_enable_tunnel(struct pci_dev *dev, u64 *asnind)
-{
-	struct device_node *np;
-	const __be32 *prop;
-	struct pnv_ioda_pe *pe;
-	uint16_t window_id;
-	int rc;
-
-	if (!radix_enabled())
-		return -ENXIO;
-
-	if (!(np = pnv_pci_get_phb_node(dev)))
-		return -ENXIO;
-
-	prop = of_get_property(np, "ibm,phb-indications", NULL);
-	of_node_put(np);
-
-	if (!prop || !prop[1])
-		return -ENXIO;
-
-	*asnind = (u64)be32_to_cpu(prop[1]);
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	/* Increase real window size to accept as_notify messages. */
-	window_id = (pe->pe_number << 1 ) + 1;
-	rc = opal_pci_map_pe_dma_window_real(pe->phb->opal_id, pe->pe_number,
-					     window_id, pe->tce_bypass_base,
-					     (uint64_t)1 << 48);
-	return opal_error_code(rc);
-}
-EXPORT_SYMBOL_GPL(pnv_pci_enable_tunnel);
-
-int pnv_pci_disable_tunnel(struct pci_dev *dev)
-{
-	struct pnv_ioda_pe *pe;
-
-	pe = pnv_ioda_get_pe(dev);
-	if (!pe)
-		return -ENODEV;
-
-	/* Restore default real window size. */
-	pnv_pci_ioda2_set_bypass(pe, true);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_disable_tunnel);
-
 int pnv_pci_set_tunnel_bar(struct pci_dev *dev, u64 addr, int enable)
 {
 	__be64 val;
@@ -1040,29 +918,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(pnv_pci_set_tunnel_bar);
 
-#ifdef CONFIG_PPC64	/* for thread.tidr */
-int pnv_pci_get_as_notify_info(struct task_struct *task, u32 *lpid, u32 *pid,
-			       u32 *tid)
-{
-	struct mm_struct *mm = NULL;
-
-	if (task == NULL)
-		return -EINVAL;
-
-	mm = get_task_mm(task);
-	if (mm == NULL)
-		return -EINVAL;
-
-	*pid = mm->context.id;
-	mmput(mm);
-
-	*tid = task->thread.tidr;
-	*lpid = mfspr(SPRN_LPID);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(pnv_pci_get_as_notify_info);
-#endif
-
 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 be26ab3d99e0..469c24463247 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -79,9 +79,6 @@ 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;
 };
@@ -172,8 +169,6 @@ struct pnv_phb {
 	/* PHB and hub diagnostics */
 	unsigned int		diag_data_size;
 	u8			*diag_data;
-
-	int p2p_target_count;
 };
 
 extern struct pci_ops pnv_pci_ops;
@@ -200,7 +195,6 @@ extern int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type);
 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 void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 extern unsigned long pnv_pci_ioda2_get_table_size(__u32 page_shift,
 		__u64 window_size, __u32 levels);
 extern int pnv_eeh_post_init(void);
diff --git a/arch/powerpc/platforms/powernv/vas-window.c b/arch/powerpc/platforms/powernv/vas-window.c
index ea5ca0201da8..0c0d27d17976 100644
--- a/arch/powerpc/platforms/powernv/vas-window.c
+++ b/arch/powerpc/platforms/powernv/vas-window.c
@@ -40,16 +40,6 @@ static void compute_paste_address(struct vas_window *window, u64 *addr, int *len
 	pr_debug("Txwin #%d: Paste addr 0x%llx\n", winid, *addr);
 }
 
-u64 vas_win_paste_addr(struct vas_window *win)
-{
-	u64 addr;
-
-	compute_paste_address(win, &addr, NULL);
-
-	return addr;
-}
-EXPORT_SYMBOL(vas_win_paste_addr);
-
 static inline void get_hvwc_mmio_bar(struct vas_window *window,
 			u64 *start, int *len)
 {
@@ -1264,12 +1254,3 @@ int vas_win_close(struct vas_window *window)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(vas_win_close);
-
-/*
- * Return a system-wide unique window id for the window @win.
- */
-u32 vas_win_id(struct vas_window *win)
-{
-	return encode_pswid(win->vinst->vas_id, win->winid);
-}
-EXPORT_SYMBOL_GPL(vas_win_id);
diff --git a/arch/powerpc/platforms/powernv/vas.h b/arch/powerpc/platforms/powernv/vas.h
index 9cc5251816db..5574aec9ee88 100644
--- a/arch/powerpc/platforms/powernv/vas.h
+++ b/arch/powerpc/platforms/powernv/vas.h
@@ -444,26 +444,6 @@ static inline u64 read_hvwc_reg(struct vas_window *win,
 	return in_be64(win->hvwc_map+reg);
 }
 
-/*
- * Encode/decode the Partition Send Window ID (PSWID) for a window in
- * a way that we can uniquely identify any window in the system. i.e.
- * we should be able to locate the 'struct vas_window' given the PSWID.
- *
- *	Bits	Usage
- *	0:7	VAS id (8 bits)
- *	8:15	Unused, 0 (3 bits)
- *	16:31	Window id (16 bits)
- */
-static inline u32 encode_pswid(int vasid, int winid)
-{
-	u32 pswid = 0;
-
-	pswid |= vasid << (31 - 7);
-	pswid |= winid;
-
-	return pswid;
-}
-
 static inline void decode_pswid(u32 pswid, int *vasid, int *winid)
 {
 	if (vasid)