Merge tag 'powerpc-5.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates and fixes from Michael Ellerman:
 "A bit of a mixture of things, tying up some loose ends.

  There's the removal of the nvlink code, which dependend on a commit in
  the vfio tree. Then the enablement of huge vmalloc which was in next
  for a few weeks but got dropped due to conflicts. And there's also a
  few fixes.

  Summary:

   - Remove the nvlink support now that it's only user has been removed.

   - Enable huge vmalloc mappings for Radix MMU (P9).

   - Fix KVM conversion to gfn-based MMU notifier callbacks.

   - Fix a kexec/kdump crash with hot plugged CPUs.

   - Fix boot failure on 32-bit with CONFIG_STACKPROTECTOR.

   - Restore alphabetic order of the selects under CONFIG_PPC.

  Thanks to: Christophe Leroy, Christoph Hellwig, Nicholas Piggin,
  Sandipan Das, and Sourabh Jain"

* tag 'powerpc-5.13-2' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux:
  KVM: PPC: Book3S HV: Fix conversion to gfn-based MMU notifier callbacks
  powerpc/kconfig: Restore alphabetic order of the selects under CONFIG_PPC
  powerpc/32: Fix boot failure with CONFIG_STACKPROTECTOR
  powerpc/powernv/memtrace: Fix dcache flushing
  powerpc/kexec_file: Use current CPU info while setting up FDT
  powerpc/64s/radix: Enable huge vmalloc mappings
  powerpc/powernv: remove the nvlink support

19 files changed, 175 insertions, 990 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index a816935d23d4..cb89dbdedc46 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3282,6 +3282,8 @@
 
 	nohugeiomap	[KNL,X86,PPC,ARM64] Disable kernel huge I/O mappings.
 
+	nohugevmalloc	[PPC] Disable kernel huge vmalloc mappings.
+
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index cb2d44ee4e38..088dd2afcfe4 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -120,28 +120,29 @@ config PPC
 	select ARCH_32BIT_OFF_T if PPC32
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
+	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_DEBUG_VIRTUAL
 	select ARCH_HAS_DEBUG_VM_PGTABLE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC_PSERIES
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
-	select ARCH_HAS_KCOV
 	select ARCH_HAS_HUGEPD			if HUGETLB_PAGE
+	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_CALLBACKS
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_MEMREMAP_COMPAT_ALIGN
 	select ARCH_HAS_MMIOWB			if PPC64
+	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PMEM_API
-	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
-	select ARCH_HAS_MEMBARRIER_CALLBACKS
-	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
 	select ARCH_HAS_STRICT_KERNEL_RWX	if ((PPC_BOOK3S_64 || PPC32) && !HIBERNATION)
 	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAS_UACCESS_FLUSHCACHE
-	select ARCH_HAS_COPY_MC			if PPC64
 	select ARCH_HAS_UBSAN_SANITIZE_ALL
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_KEEP_MEMBLOCK
@@ -164,9 +165,8 @@ config PPC
 	select BUILDTIME_TABLE_SORT
 	select CLONE_BACKWARDS
 	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
-	select DMA_OPS				if PPC64
 	select DMA_OPS_BYPASS			if PPC64
-	select ARCH_HAS_DMA_MAP_DIRECT 		if PPC64 && PPC_PSERIES
+	select DMA_OPS				if PPC64
 	select DYNAMIC_FTRACE			if FUNCTION_TRACER
 	select EDAC_ATOMIC_SCRUB
 	select EDAC_SUPPORT
@@ -186,23 +186,22 @@ config PPC
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_VDSO_TIME_NS
 	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HUGE_VMALLOC		if HAVE_ARCH_HUGE_VMAP
 	select HAVE_ARCH_HUGE_VMAP		if PPC_BOOK3S_64 && PPC_RADIX_MMU
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_ARCH_JUMP_LABEL_RELATIVE
 	select HAVE_ARCH_KASAN			if PPC32 && PPC_PAGE_SHIFT <= 14
 	select HAVE_ARCH_KASAN_VMALLOC		if PPC32 && PPC_PAGE_SHIFT <= 14
-	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_KFENCE			if PPC32
+	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if COMPAT
 	select HAVE_ARCH_NVRAM_OPS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ASM_MODVERSIONS
-	select HAVE_C_RECORDMCOUNT
-	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
-	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
 	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_C_RECORDMCOUNT
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DEBUG_STACKOVERFLOW
 	select HAVE_DYNAMIC_FTRACE
@@ -216,10 +215,13 @@ config PPC
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS			if GCC_VERSION >= 50200   # plugin support on gcc <= 5.1 is buggy on PPC
 	select HAVE_GENERIC_VDSO
+	select HAVE_HARDLOCKUP_DETECTOR_ARCH	if PPC_BOOK3S_64 && SMP
+	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
 	select HAVE_IDE
 	select HAVE_IOREMAP_PROT
 	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_IRQ_TIME_ACCOUNTING
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZMA			if DEFAULT_UIMAGE
 	select HAVE_KERNEL_LZO			if DEFAULT_UIMAGE
@@ -231,26 +233,25 @@ config PPC
 	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI				if PERF_EVENTS || (PPC64 && PPC_BOOK3S)
-	select HAVE_HARDLOCKUP_DETECTOR_ARCH	if PPC64 && PPC_BOOK3S && SMP
 	select HAVE_OPTPROBES
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_EVENTS_NMI		if PPC64
-	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select HUGETLB_PAGE_SIZE_VARIABLE	if PPC_BOOK3S_64 && HUGETLB_PAGE
-	select MMU_GATHER_RCU_TABLE_FREE
-	select MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE
+	select HAVE_RSEQ
 	select HAVE_SOFTIRQ_ON_OWN_STACK
+	select HAVE_STACKPROTECTOR		if PPC32 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r2)
+	select HAVE_STACKPROTECTOR		if PPC64 && $(cc-option,-mstack-protector-guard=tls -mstack-protector-guard-reg=r13)
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
-	select HAVE_IRQ_TIME_ACCOUNTING
-	select HAVE_RSEQ
+	select HUGETLB_PAGE_SIZE_VARIABLE	if PPC_BOOK3S_64 && HUGETLB_PAGE
 	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
 	select IRQ_FORCED_THREADING
+	select MMU_GATHER_PAGE_SIZE
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MODULES_USE_ELF_RELA
 	select NEED_DMA_MAP_STATE		if PPC64 || NOT_COHERENT_CACHE
 	select NEED_SG_DMA_LENGTH
diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
index a6e9a5585e61..e6b53c6e21e3 100644
--- a/arch/powerpc/include/asm/kvm_book3s.h
+++ b/arch/powerpc/include/asm/kvm_book3s.h
@@ -210,7 +210,7 @@ extern void kvmppc_free_pgtable_radix(struct kvm *kvm, pgd_t *pgd,
 				      unsigned int lpid);
 extern int kvmppc_radix_init(void);
 extern void kvmppc_radix_exit(void);
-extern bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
+extern void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			    unsigned long gfn);
 extern bool kvm_age_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			  unsigned long gfn);
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index c76157237e22..6ea9001de9a9 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -28,9 +28,6 @@ extern struct device_node *opal_node;
 
 /* API functions */
 int64_t opal_invalid_call(void);
-int64_t opal_npu_destroy_context(uint64_t phb_id, uint64_t pid, uint64_t bdf);
-int64_t opal_npu_init_context(uint64_t phb_id, int pasid, uint64_t msr,
-			uint64_t bdf);
 int64_t opal_npu_map_lpar(uint64_t phb_id, uint64_t bdf, uint64_t lparid,
 			uint64_t lpcr);
 int64_t opal_npu_spa_setup(uint64_t phb_id, uint32_t bdfn,
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index d2a2a14e56f9..74424c14515c 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -126,7 +126,6 @@ struct pci_controller {
 #endif	/* CONFIG_PPC64 */
 
 	void *private_data;
-	struct npu *npu;
 };
 
 /* These are used for config access before all the PCI probing
diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h
index 6436f0b41539..d1f53260725c 100644
--- a/arch/powerpc/include/asm/pci.h
+++ b/arch/powerpc/include/asm/pci.h
@@ -119,11 +119,4 @@ extern void pcibios_scan_phb(struct pci_controller *hose);
 
 #endif	/* __KERNEL__ */
 
-extern struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev);
-extern struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index);
-extern int pnv_npu2_init(struct pci_controller *hose);
-extern int pnv_npu2_map_lpar_dev(struct pci_dev *gpdev, unsigned int lparid,
-		unsigned long msr);
-extern int pnv_npu2_unmap_lpar_dev(struct pci_dev *gpdev);
-
 #endif /* __ASM_POWERPC_PCI_H */
diff --git a/arch/powerpc/kernel/module.c b/arch/powerpc/kernel/module.c
index fab84024650c..3f35c8d20be7 100644
--- a/arch/powerpc/kernel/module.c
+++ b/arch/powerpc/kernel/module.c
@@ -8,6 +8,7 @@
 #include <linux/moduleloader.h>
 #include <linux/err.h>
 #include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/bug.h>
 #include <asm/module.h>
 #include <linux/uaccess.h>
@@ -88,17 +89,22 @@ int module_finalize(const Elf_Ehdr *hdr,
 	return 0;
 }
 
-#ifdef MODULES_VADDR
 static __always_inline void *
 __module_alloc(unsigned long size, unsigned long start, unsigned long end)
 {
-	return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
-				    __builtin_return_address(0));
+	/*
+	 * Don't do huge page allocations for modules yet until more testing
+	 * is done. STRICT_MODULE_RWX may require extra work to support this
+	 * too.
+	 */
+	return __vmalloc_node_range(size, 1, start, end, GFP_KERNEL, PAGE_KERNEL_EXEC,
+				    VM_FLUSH_RESET_PERMS | VM_NO_HUGE_VMAP,
+				    NUMA_NO_NODE, __builtin_return_address(0));
 }
 
 void *module_alloc(unsigned long size)
 {
+#ifdef MODULES_VADDR
 	unsigned long limit = (unsigned long)_etext - SZ_32M;
 	void *ptr = NULL;
 
@@ -112,5 +118,7 @@ void *module_alloc(unsigned long size)
 		ptr = __module_alloc(size, MODULES_VADDR, MODULES_END);
 
 	return ptr;
-}
+#else
+	return __module_alloc(size, VMALLOC_START, VMALLOC_END);
 #endif
+}
diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
index f9eb49e23ec8..5056e175ca2c 100644
--- a/arch/powerpc/kexec/file_load_64.c
+++ b/arch/powerpc/kexec/file_load_64.c
@@ -951,6 +951,93 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 }
 
 /**
+ * add_node_props - Reads node properties from device node structure and add
+ *                  them to fdt.
+ * @fdt:            Flattened device tree of the kernel
+ * @node_offset:    offset of the node to add a property at
+ * @dn:             device node pointer
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int add_node_props(void *fdt, int node_offset, const struct device_node *dn)
+{
+	int ret = 0;
+	struct property *pp;
+
+	if (!dn)
+		return -EINVAL;
+
+	for_each_property_of_node(dn, pp) {
+		ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length);
+		if (ret < 0) {
+			pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret));
+			return ret;
+		}
+	}
+	return ret;
+}
+
+/**
+ * update_cpus_node - Update cpus node of flattened device tree using of_root
+ *                    device node.
+ * @fdt:              Flattened device tree of the kernel.
+ *
+ * Returns 0 on success, negative errno on error.
+ */
+static int update_cpus_node(void *fdt)
+{
+	struct device_node *cpus_node, *dn;
+	int cpus_offset, cpus_subnode_offset, ret = 0;
+
+	cpus_offset = fdt_path_offset(fdt, "/cpus");
+	if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) {
+		pr_err("Malformed device tree: error reading /cpus node: %s\n",
+		       fdt_strerror(cpus_offset));
+		return cpus_offset;
+	}
+
+	if (cpus_offset > 0) {
+		ret = fdt_del_node(fdt, cpus_offset);
+		if (ret < 0) {
+			pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
+			return -EINVAL;
+		}
+	}
+
+	/* Add cpus node to fdt */
+	cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
+	if (cpus_offset < 0) {
+		pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
+		return -EINVAL;
+	}
+
+	/* Add cpus node properties */
+	cpus_node = of_find_node_by_path("/cpus");
+	ret = add_node_props(fdt, cpus_offset, cpus_node);
+	of_node_put(cpus_node);
+	if (ret < 0)
+		return ret;
+
+	/* Loop through all subnodes of cpus and add them to fdt */
+	for_each_node_by_type(dn, "cpu") {
+		cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
+		if (cpus_subnode_offset < 0) {
+			pr_err("Unable to add %s subnode: %s\n", dn->full_name,
+			       fdt_strerror(cpus_subnode_offset));
+			ret = cpus_subnode_offset;
+			goto out;
+		}
+
+		ret = add_node_props(fdt, cpus_subnode_offset, dn);
+		if (ret < 0)
+			goto out;
+	}
+out:
+	of_node_put(dn);
+	return ret;
+}
+
+/**
  * setup_new_fdt_ppc64 - Update the flattend device-tree of the kernel
  *                       being loaded.
  * @image:               kexec image being loaded.
@@ -1006,6 +1093,11 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
 		}
 	}
 
+	/* Update cpus nodes information to account hotplug CPUs. */
+	ret =  update_cpus_node(fdt);
+	if (ret < 0)
+		goto out;
+
 	/* Update memory reserve map */
 	ret = get_reserved_memory_ranges(&rmem);
 	if (ret)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index b7bd9ca040b8..2d9193cd73be 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -795,7 +795,7 @@ static void kvmppc_unmap_hpte(struct kvm *kvm, unsigned long i,
 	}
 }
 
-static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
+static void kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 			    unsigned long gfn)
 {
 	unsigned long i;
@@ -829,15 +829,21 @@ static bool kvm_unmap_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		unlock_rmap(rmapp);
 		__unlock_hpte(hptep, be64_to_cpu(hptep[0]));
 	}
-	return false;
 }
 
 bool kvm_unmap_gfn_range_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	if (kvm_is_radix(kvm))
-		return kvm_unmap_radix(kvm, range->slot, range->start);
+	gfn_t gfn;
+
+	if (kvm_is_radix(kvm)) {
+		for (gfn = range->start; gfn < range->end; gfn++)
+			kvm_unmap_radix(kvm, range->slot, gfn);
+	} else {
+		for (gfn = range->start; gfn < range->end; gfn++)
+			kvm_unmap_rmapp(kvm, range->slot, range->start);
+	}
 
-	return kvm_unmap_rmapp(kvm, range->slot, range->start);
+	return false;
 }
 
 void kvmppc_core_flush_memslot_hv(struct kvm *kvm,
@@ -924,10 +930,18 @@ static bool kvm_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 bool kvm_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	if (kvm_is_radix(kvm))
-		kvm_age_radix(kvm, range->slot, range->start);
+	gfn_t gfn;
+	bool ret = false;
 
-	return kvm_age_rmapp(kvm, range->slot, range->start);
+	if (kvm_is_radix(kvm)) {
+		for (gfn = range->start; gfn < range->end; gfn++)
+			ret |= kvm_age_radix(kvm, range->slot, gfn);
+	} else {
+		for (gfn = range->start; gfn < range->end; gfn++)
+			ret |= kvm_age_rmapp(kvm, range->slot, gfn);
+	}
+
+	return ret;
 }
 
 static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
@@ -965,18 +979,24 @@ static bool kvm_test_age_rmapp(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 bool kvm_test_age_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 {
-	if (kvm_is_radix(kvm))
-		kvm_test_age_radix(kvm, range->slot, range->start);
+	WARN_ON(range->start + 1 != range->end);
 
-	return kvm_test_age_rmapp(kvm, range->slot, range->start);
+	if (kvm_is_radix(kvm))
+		return kvm_test_age_radix(kvm, range->slot, range->start);
+	else
+		return kvm_test_age_rmapp(kvm, range->slot, range->start);
 }
 
 bool kvm_set_spte_gfn_hv(struct kvm *kvm, struct kvm_gfn_range *range)
 {
+	WARN_ON(range->start + 1 != range->end);
+
 	if (kvm_is_radix(kvm))
-		return kvm_unmap_radix(kvm, range->slot, range->start);
+		kvm_unmap_radix(kvm, range->slot, range->start);
+	else
+		kvm_unmap_rmapp(kvm, range->slot, range->start);
 
-	return kvm_unmap_rmapp(kvm, range->slot, range->start);
+	return false;
 }
 
 static int vcpus_running(struct kvm *kvm)
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index ec4f58fa9f5a..d909c069363e 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -993,7 +993,7 @@ int kvmppc_book3s_radix_page_fault(struct kvm_vcpu *vcpu,
 }
 
 /* Called with kvm->mmu_lock held */
-bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
+void kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 		     unsigned long gfn)
 {
 	pte_t *ptep;
@@ -1002,14 +1002,13 @@ bool kvm_unmap_radix(struct kvm *kvm, struct kvm_memory_slot *memslot,
 
 	if (kvm->arch.secure_guest & KVMPPC_SECURE_INIT_DONE) {
 		uv_page_inval(kvm->arch.lpid, gpa, PAGE_SHIFT);
-		return false;
+		return;
 	}
 
 	ptep = find_kvm_secondary_pte(kvm, gpa, &shift);
 	if (ptep && pte_present(*ptep))
 		kvmppc_unmap_pte(kvm, ptep, gpa, shift, memslot,
 				 kvm->arch.lpid);
-	return false;
 }
 
 /* Called with kvm->mmu_lock held */
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index f2c690ee75d1..cc1a8a0f311e 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -5,6 +5,9 @@
 
 ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
+CFLAGS_code-patching.o += -fno-stack-protector
+CFLAGS_feature-fixups.o += -fno-stack-protector
+
 CFLAGS_REMOVE_code-patching.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index 2eb6ae150d1f..be2546b96816 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_SMP)	+= smp.o subcore.o subcore-asm.o
 obj-$(CONFIG_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_PRESERVE_FA_DUMP)	+= opal-fadump.o
 obj-$(CONFIG_OPAL_CORE)	+= opal-core.o
-obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
+obj-$(CONFIG_PCI)	+= pci.o pci-ioda.o pci-ioda-tce.o
 obj-$(CONFIG_PCI_IOV)   += pci-sriov.o
 obj-$(CONFIG_CXL_BASE)	+= pci-cxl.o
 obj-$(CONFIG_EEH)	+= eeh-powernv.o
diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c
index 71c1262589fe..537a4daed614 100644
--- a/arch/powerpc/platforms/powernv/memtrace.c
+++ b/arch/powerpc/platforms/powernv/memtrace.c
@@ -104,8 +104,8 @@ static void memtrace_clear_range(unsigned long start_pfn,
 	 * Before we go ahead and use this range as cache inhibited range
 	 * flush the cache.
 	 */
-	flush_dcache_range_chunked(PFN_PHYS(start_pfn),
-				   PFN_PHYS(start_pfn + nr_pages),
+	flush_dcache_range_chunked((unsigned long)pfn_to_kaddr(start_pfn),
+				   (unsigned long)pfn_to_kaddr(start_pfn + nr_pages),
 				   FLUSH_CHUNK_SIZE);
 }
 
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
deleted file mode 100644
index b711dc3262a3..000000000000
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ /dev/null
@@ -1,705 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * This file implements the DMA operations for NVLink devices. The NPU
- * devices all point to the same iommu table as the parent PCI device.
- *
- * Copyright Alistair Popple, IBM Corporation 2015.
- */
-
-#include <linux/mmu_notifier.h>
-#include <linux/mmu_context.h>
-#include <linux/of.h>
-#include <linux/pci.h>
-#include <linux/memblock.h>
-#include <linux/sizes.h>
-
-#include <asm/debugfs.h>
-#include <asm/powernv.h>
-#include <asm/ppc-pci.h>
-#include <asm/opal.h>
-
-#include "pci.h"
-
-static struct pci_dev *get_pci_dev(struct device_node *dn)
-{
-	struct pci_dn *pdn = PCI_DN(dn);
-	struct pci_dev *pdev;
-
-	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. */
-struct pci_dev *pnv_pci_get_gpu_dev(struct pci_dev *npdev)
-{
-	struct device_node *dn;
-	struct pci_dev *gpdev;
-
-	if (WARN_ON(!npdev))
-		return NULL;
-
-	if (WARN_ON(!npdev->dev.of_node))
-		return NULL;
-
-	/* Get assoicated PCI device */
-	dn = of_parse_phandle(npdev->dev.of_node, "ibm,gpu", 0);
-	if (!dn)
-		return NULL;
-
-	gpdev = get_pci_dev(dn);
-	of_node_put(dn);
-
-	return gpdev;
-}
-EXPORT_SYMBOL(pnv_pci_get_gpu_dev);
-
-/* Given the real PCI device get a linked NPU device. */
-struct pci_dev *pnv_pci_get_npu_dev(struct pci_dev *gpdev, int index)
-{
-	struct device_node *dn;
-	struct pci_dev *npdev;
-
-	if (WARN_ON(!gpdev))
-		return NULL;
-
-	/* Not all PCI devices have device-tree nodes */
-	if (!gpdev->dev.of_node)
-		return NULL;
-
-	/* Get assoicated PCI device */
-	dn = of_parse_phandle(gpdev->dev.of_node, "ibm,npu", index);
-	if (!dn)
-		return NULL;
-
-	npdev = get_pci_dev(dn);
-	of_node_put(dn);
-
-	return npdev;
-}
-EXPORT_SYMBOL(pnv_pci_get_npu_dev);
-
-#ifdef CONFIG_IOMMU_API
-/*
- * Returns the PE assoicated with the PCI device of the given
- * NPU. Returns the linked pci device if pci_dev != NULL.
- */
-static struct pnv_ioda_pe *get_gpu_pci_dev_and_pe(struct pnv_ioda_pe *npe,
-						  struct pci_dev **gpdev)
-{
-	struct pnv_phb *phb;
-	struct pci_controller *hose;
-	struct pci_dev *pdev;
-	struct pnv_ioda_pe *pe;
-	struct pci_dn *pdn;
-
-	pdev = pnv_pci_get_gpu_dev(npe->pdev);
-	if (!pdev)
-		return NULL;
-
-	pdn = pci_get_pdn(pdev);
-	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
-		return NULL;
-
-	hose = pci_bus_to_host(pdev->bus);
-	phb = hose->private_data;
-	pe = &phb->ioda.pe_array[pdn->pe_number];
-
-	if (gpdev)
-		*gpdev = pdev;
-
-	return pe;
-}
-
-static long pnv_npu_unset_window(struct iommu_table_group *table_group,
-		int num);
-
-static long pnv_npu_set_window(struct iommu_table_group *table_group, int num,
-		struct iommu_table *tbl)
-{
-	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
-			table_group);
-	struct pnv_phb *phb = npe->phb;
-	int64_t rc;
-	const unsigned long size = tbl->it_indirect_levels ?
-		tbl->it_level_size : tbl->it_size;
-	const __u64 start_addr = tbl->it_offset << tbl->it_page_shift;
-	const __u64 win_size = tbl->it_size << tbl->it_page_shift;
-	int num2 = (num == 0) ? 1 : 0;
-
-	/* NPU has just one TVE so if there is another table, remove it first */
-	if (npe->table_group.tables[num2])
-		pnv_npu_unset_window(&npe->table_group, num2);
-
-	pe_info(npe, "Setting up window %llx..%llx pg=%lx\n",
-			start_addr, start_addr + win_size - 1,
-			IOMMU_PAGE_SIZE(tbl));
-
-	rc = opal_pci_map_pe_dma_window(phb->opal_id,
-			npe->pe_number,
-			npe->pe_number,
-			tbl->it_indirect_levels + 1,
-			__pa(tbl->it_base),
-			size << 3,
-			IOMMU_PAGE_SIZE(tbl));
-	if (rc) {
-		pe_err(npe, "Failed to configure TCE table, err %lld\n", rc);
-		return rc;
-	}
-	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
-
-	/* Add the table to the list so its TCE cache will get invalidated */
-	pnv_pci_link_table_and_group(phb->hose->node, num,
-			tbl, &npe->table_group);
-
-	return 0;
-}
-
-static long pnv_npu_unset_window(struct iommu_table_group *table_group, int num)
-{
-	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
-			table_group);
-	struct pnv_phb *phb = npe->phb;
-	int64_t rc;
-
-	if (!npe->table_group.tables[num])
-		return 0;
-
-	pe_info(npe, "Removing DMA window\n");
-
-	rc = opal_pci_map_pe_dma_window(phb->opal_id, npe->pe_number,
-			npe->pe_number,
-			0/* levels */, 0/* table address */,
-			0/* table size */, 0/* page size */);
-	if (rc) {
-		pe_err(npe, "Unmapping failed, ret = %lld\n", rc);
-		return rc;
-	}
-	pnv_pci_ioda2_tce_invalidate_entire(phb, false);
-
-	pnv_pci_unlink_table_and_group(npe->table_group.tables[num],
-			&npe->table_group);
-
-	return 0;
-}
-
-/* Switch ownership from platform code to external user (e.g. VFIO) */
-static void pnv_npu_take_ownership(struct iommu_table_group *table_group)
-{
-	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
-			table_group);
-	struct pnv_phb *phb = npe->phb;
-	int64_t rc;
-	struct pci_dev *gpdev = NULL;
-
-	/*
-	 * Note: NPU has just a single TVE in the hardware which means that
-	 * while used by the kernel, it can have either 32bit window or
-	 * DMA bypass but never both. So we deconfigure 32bit window only
-	 * if it was enabled at the moment of ownership change.
-	 */
-	if (npe->table_group.tables[0]) {
-		pnv_npu_unset_window(&npe->table_group, 0);
-		return;
-	}
-
-	/* Disable bypass */
-	rc = opal_pci_map_pe_dma_window_real(phb->opal_id,
-			npe->pe_number, npe->pe_number,
-			0 /* bypass base */, 0);
-	if (rc) {
-		pe_err(npe, "Failed to disable bypass, err %lld\n", rc);
-		return;
-	}
-	pnv_pci_ioda2_tce_invalidate_entire(npe->phb, false);
-
-	get_gpu_pci_dev_and_pe(npe, &gpdev);
-	if (gpdev)
-		pnv_npu2_unmap_lpar_dev(gpdev);
-}
-
-static void pnv_npu_release_ownership(struct iommu_table_group *table_group)
-{
-	struct pnv_ioda_pe *npe = container_of(table_group, struct pnv_ioda_pe,
-			table_group);
-	struct pci_dev *gpdev = NULL;
-
-	get_gpu_pci_dev_and_pe(npe, &gpdev);
-	if (gpdev)
-		pnv_npu2_map_lpar_dev(gpdev, 0, MSR_DR | MSR_PR | MSR_HV);
-}
-
-static struct iommu_table_group_ops pnv_pci_npu_ops = {
-	.set_window = pnv_npu_set_window,
-	.unset_window = pnv_npu_unset_window,
-	.take_ownership = pnv_npu_take_ownership,
-	.release_ownership = pnv_npu_release_ownership,
-};
-#endif /* !CONFIG_IOMMU_API */
-
-/*
- * NPU2 ATS
- */
-/* Maximum possible number of ATSD MMIO registers per NPU */
-#define NV_NMMU_ATSD_REGS 8
-#define NV_NPU_MAX_PE_NUM	16
-
-/*
- * A compound NPU IOMMU group which might consist of 1 GPU + 2xNPUs (POWER8) or
- * up to 3 x (GPU + 2xNPUs) (POWER9).
- */
-struct npu_comp {
-	struct iommu_table_group table_group;
-	int pe_num;
-	struct pnv_ioda_pe *pe[NV_NPU_MAX_PE_NUM];
-};
-
-/* An NPU descriptor, valid for POWER9 only */
-struct npu {
-	int index;
-	struct npu_comp npucomp;
-};
-
-#ifdef CONFIG_IOMMU_API
-static long pnv_npu_peers_create_table_userspace(
-		struct iommu_table_group *table_group,
-		int num, __u32 page_shift, __u64 window_size, __u32 levels,
-		struct iommu_table **ptbl)
-{
-	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
-			table_group);
-
-	if (!npucomp->pe_num || !npucomp->pe[0] ||
-			!npucomp->pe[0]->table_group.ops ||
-			!npucomp->pe[0]->table_group.ops->create_table)
-		return -EFAULT;
-
-	return npucomp->pe[0]->table_group.ops->create_table(
-			&npucomp->pe[0]->table_group, num, page_shift,
-			window_size, levels, ptbl);
-}
-
-static long pnv_npu_peers_set_window(struct iommu_table_group *table_group,
-		int num, struct iommu_table *tbl)
-{
-	int i, j;
-	long ret = 0;
-	struct npu_comp *npucomp = container_of(table_group, struct npu_comp,
-			table_group);
-
-	for (i = 0; i < npucomp->pe_num; ++i) {
-		struct pnv_ioda_pe *pe = npucomp->pe[i];
-
-		if (!pe->table_group.ops->set_window)
-			continue;
-
-		ret = pe->table_group.ops->set_window(&pe->table_group,
-				num, tbl);
-		if (ret)
-			break;
-	}
-
-	if (ret) {
-		for (j = 0; j < i; ++j) {
-			struct pnv_ioda_pe *pe = npucomp->pe[j];
-
-			if (!pe->table_group.ops->unset_window)