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

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.
 

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

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);

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,

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

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 */

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
+}

arch/powerpc/kexec/file_load_64.c

@@ -950,6 +950,93 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image)
 	return (unsigned int)(usm_entries * sizeof(u64));
 }
 
+/**
+ * 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.
@@ -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)

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)

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 */

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)
 

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

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);
 }
 

arch/powerpc/platforms/powernv/opal-call.c

@@ -267,8 +267,6 @@ OPAL_CALL(opal_xive_get_queue_state,		OPAL_XIVE_GET_QUEUE_STATE);
 OPAL_CALL(opal_xive_set_queue_state,		OPAL_XIVE_SET_QUEUE_STATE);
 OPAL_CALL(opal_xive_get_vp_state,		OPAL_XIVE_GET_VP_STATE);
 OPAL_CALL(opal_signal_system_reset,		OPAL_SIGNAL_SYSTEM_RESET);
-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);

arch/powerpc/platforms/powernv/pci-ioda.c

@@ -47,8 +47,7 @@
 #define PNV_IODA1_M64_SEGS	8	/* Segments per M64 BAR	*/
 #define PNV_IODA1_DMA32_SEGSIZE	0x10000000
 
-static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_NVLINK",
-					      "NPU_OCAPI" };
+static const char * const pnv_phb_names[] = { "IODA1", "IODA2", "NPU_OCAPI" };
 
 static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable);
 static void pnv_pci_configure_bus(struct pci_bus *bus);
@@ -192,8 +191,6 @@ void pnv_ioda_free_pe(struct pnv_ioda_pe *pe)
 	unsigned int pe_num = pe->pe_number;
 
 	WARN_ON(pe->pdev);
-	WARN_ON(pe->npucomp); /* NPUs for nvlink are not supposed to be freed */
-	kfree(pe->npucomp);
 	memset(pe, 0, sizeof(struct pnv_ioda_pe));
 
 	mutex_lock(&phb->ioda.pe_alloc_mutex);
@@ -875,7 +872,7 @@ int pnv_ioda_deconfigure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Release from all parents PELT-V. NPUs don't have a PELTV
 	 * table
 	 */
-	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+	if (phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_unset_peltv(phb, pe, parent);
 
 	rc = opal_pci_set_pe(phb->opal_id, pe->pe_number, pe->rid,
@@ -946,7 +943,7 @@ int pnv_ioda_configure_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe)
 	 * Configure PELTV. NPUs don't have a PELTV table so skip
 	 * configuration on them.
 	 */
-	if (phb->type != PNV_PHB_NPU_NVLINK && phb->type != PNV_PHB_NPU_OCAPI)
+	if (phb->type != PNV_PHB_NPU_OCAPI)
 		pnv_ioda_set_peltv(phb, pe, true);
 
 	/* Setup reverse map */
@@ -1002,8 +999,7 @@ static struct pnv_ioda_pe *pnv_ioda_setup_dev_PE(struct pci_dev *dev)
 
 	/* NOTE: We don't get a reference for the pointer in the PE
 	 * data structure, both the device and PE structures should be
-	 * destroyed at the same time. However, removing nvlink
-	 * devices will need some work.
+	 * destroyed at the same time.
 	 *
 	 * At some point we want to remove the PDN completely anyways
 	 */
@@ -1099,113 +1095,6 @@ static struct pnv_ioda_pe *pnv_ioda_setup_bus_PE(struct pci_bus *bus, bool all)
 	return pe;
 }
 
-static struct pnv_ioda_pe *pnv_ioda_setup_npu_PE(struct pci_dev *npu_pdev)
-{
-	int pe_num, found_pe = false, rc;
-	long rid;
-	struct pnv_ioda_pe *pe;
-	struct pci_dev *gpu_pdev;
-	struct pci_dn *npu_pdn;
-	struct pnv_phb *phb = pci_bus_to_pnvhb(npu_pdev->bus);
-
-	/*
-	 * Intentionally leak a reference on the npu device (for
-	 * nvlink only; this is not an opencapi path) to make sure it
-	 * never goes away, as it's been the case all along and some
-	 * work is needed otherwise.
-	 */
-	pci_dev_get(npu_pdev);
-
-	/*
-	 * Due to a hardware errata PE#0 on the NPU is reserved for
-	 * error handling. This means we only have three PEs remaining
-	 * which need to be assigned to four links, implying some
-	 * links must share PEs.
-	 *
-	 * To achieve this we assign PEs such that NPUs linking the
-	 * same GPU get assigned the same PE.
-	 */
-	gpu_pdev = pnv_pci_get_gpu_dev(npu_pdev);
-	for (pe_num = 0; pe_num < phb->ioda.total_pe_num; pe_num++) {
-		pe = &phb->ioda.pe_array[pe_num];
-		if (!pe->pdev)
-			continue;
-
-		if (pnv_pci_get_gpu_dev(pe->pdev) == gpu_pdev) {
-			/*
-			 * This device has the same peer GPU so should
-			 * be assigned the same PE as the existing
-			 * peer NPU.
-			 */
-			dev_info(&npu_pdev->dev,
-				"Associating to existing PE %x\n", pe_num);
-			npu_pdn = pci_get_pdn(npu_pdev);
-			rid = npu_pdev->bus->number << 8 | npu_pdn->devfn;
-			npu_pdn->pe_number = pe_num;
-			phb->ioda.pe_rmap[rid] = pe->pe_number;
-			pe->device_count++;
-
-			/* Map the PE to this link */
-			rc = opal_pci_set_pe(phb->opal_id, pe_num, rid,
-					OpalPciBusAll,
-					OPAL_COMPARE_RID_DEVICE_NUMBER,
-					OPAL_COMPARE_RID_FUNCTION_NUMBER,
-					OPAL_MAP_PE);
-			WARN_ON(rc != OPAL_SUCCESS);
-			found_pe = true;
-			break;
-		}
-	}
-
-	if (!found_pe)
-		/*
-		 * Could not find an existing PE so allocate a new
-		 * one.
-		 */
-		return pnv_ioda_setup_dev_PE(npu_pdev);
-	else
-		return pe;
-}
-
-static void pnv_ioda_setup_npu_PEs(struct pci_bus *bus)
-{
-	struct pci_dev *pdev;
-
-	list_for_each_entry(pdev, &bus->devices, bus_list)
-		pnv_ioda_setup_npu_PE(pdev);
-}
-
-static void pnv_pci_ioda_setup_nvlink(void)
-{
-	struct pci_controller *hose;
-	struct pnv_phb *phb;
-	struct pnv_ioda_pe *pe;
-
-	list_for_each_entry(hose, &hose_list, list_node) {
-		phb = hose->private_data;
-		if (phb->type == PNV_PHB_NPU_NVLINK) {
-			/* PE#0 is needed for error reporting */
-			pnv_ioda_reserve_pe(phb, 0);
-			pnv_ioda_setup_npu_PEs(hose->bus);
-			if (phb->model == PNV_PHB_MODEL_NPU2)
-				WARN_ON_ONCE(pnv_npu2_init(hose));
-		}
-	}
-	list_for_each_entry(hose, &hose_list, list_node) {
-		phb = hose->private_data;
-		if (phb->type != PNV_PHB_IODA2)
-			continue;
-
-		list_for_each_entry(pe, &phb->ioda.pe_list, list)
-			pnv_npu2_map_lpar(pe, MSR_DR | MSR_PR | MSR_HV);
-	}
-
-#ifdef CONFIG_IOMMU_API
-	/* setup iommu groups so we can do nvlink pass-thru */
-	pnv_pci_npu_setup_iommu_groups();
-#endif
-}
-
 static void pnv_pci_ioda1_setup_dma_pe(struct pnv_phb *phb,
 				       struct pnv_ioda_pe *pe);
 
@@ -1468,18 +1357,6 @@ static struct iommu_table_ops pnv_ioda1_iommu_ops = {
 #define PHB3_TCE_KILL_INVAL_PE		PPC_BIT(1)
 #define PHB3_TCE_KILL_INVAL_ONE		PPC_BIT(2)
 
-static void pnv_pci_phb3_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
-	__be64 __iomem *invalidate = pnv_ioda_get_inval_reg(phb, rm);
-	const unsigned long val = PHB3_TCE_KILL_INVAL_ALL;
-
-	mb(); /* Ensure previous TCE table stores are visible */
-	if (rm)
-		__raw_rm_writeq_be(val, invalidate);
-	else
-		__raw_writeq_be(val, invalidate);
-}
-
 static inline void pnv_pci_phb3_tce_invalidate_pe(struct pnv_ioda_pe *pe)
 {
 	/* 01xb - invalidate TCEs that match the specified PE# */
@@ -1539,20 +1416,6 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 		struct pnv_phb *phb = pe->phb;
 		unsigned int shift = tbl->it_page_shift;
 
-		/*
-		 * NVLink1 can use the TCE kill register directly as
-		 * it's the same as PHB3. NVLink2 is different and
-		 * should go via the OPAL call.
-		 */
-		if (phb->model == PNV_PHB_MODEL_NPU) {
-			/*
-			 * The NVLink hardware does not support TCE kill
-			 * per TCE entry so we have to invalidate
-			 * the entire cache for it.
-			 */
-			pnv_pci_phb3_tce_invalidate_entire(phb, rm);
-			continue;
-		}
 		if (phb->model == PNV_PHB_MODEL_PHB3 && phb->regs)
 			pnv_pci_phb3_tce_invalidate(pe, rm, shift,
 						    index, npages);
@@ -1564,14 +1427,6 @@ static void pnv_pci_ioda2_tce_invalidate(struct iommu_table *tbl,
 	}
 }
 
-void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm)
-{
-	if (phb->model == PNV_PHB_MODEL_NPU || phb->model == PNV_PHB_MODEL_PHB3)
-		pnv_pci_phb3_tce_invalidate_entire(phb, rm);
-	else
-		opal_pci_tce_kill(phb->opal_id, OPAL_PCI_TCE_KILL, 0, 0, 0, 0);
-}
-
 static int pnv_ioda2_tce_build(struct iommu_table *tbl, long index,
 		long npages, unsigned long uaddr,
 		enum dma_data_direction direction,
@@ -2451,7 +2306,6 @@ static void pnv_pci_enable_bridges(void)
 
 static void pnv_pci_ioda_fixup(void)
 {
-	pnv_pci_ioda_setup_nvlink();
 	pnv_pci_ioda_create_dbgfs();
 
 	pnv_pci_enable_bridges();
@@ -2824,15 +2678,6 @@ static void pnv_pci_release_device(struct pci_dev *pdev)
 		pnv_ioda_release_pe(pe);
 }
 
-static void pnv_npu_disable_device(struct pci_dev *pdev)
-{
-	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
-	struct eeh_pe *eehpe = edev ? edev->pe : NULL;
-
-	if (eehpe && eeh_ops && eeh_ops->reset)
-		eeh_ops->reset(eehpe, EEH_RESET_HOT);
-}
-
 static void pnv_pci_ioda_shutdown(struct pci_controller *hose)
 {
 	struct pnv_phb *phb = hose->private_data;
@@ -2874,16 +2719,6 @@ static const struct pci_controller_ops pnv_pci_ioda_controller_ops = {
 	.shutdown		= pnv_pci_ioda_shutdown,
 };
 
-static const struct pci_controller_ops pnv_npu_ioda_controller_ops = {
-	.setup_msi_irqs		= pnv_setup_msi_irqs,
-	.teardown_msi_irqs	= pnv_teardown_msi_irqs,
-	.enable_device_hook	= pnv_pci_enable_device_hook,
-	.window_alignment	= pnv_pci_window_alignment,
-	.reset_secondary_bus	= pnv_pci_reset_secondary_bus,
-	.shutdown		= pnv_pci_ioda_shutdown,
-	.disable_device		= pnv_npu_disable_device,
-};
-
 static const struct pci_controller_ops pnv_npu_ocapi_ioda_controller_ops = {
 	.enable_device_hook	= pnv_ocapi_enable_device_hook,
 	.release_device		= pnv_pci_release_device,
@@ -2957,10 +2792,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 		phb->model = PNV_PHB_MODEL_P7IOC;
 	else if (of_device_is_compatible(np, "ibm,power8-pciex"))
 		phb->model = PNV_PHB_MODEL_PHB3;
-	else if (of_device_is_compatible(np, "ibm,power8-npu-pciex"))
-		phb->model = PNV_PHB_MODEL_NPU;
-	else if (of_device_is_compatible(np, "ibm,power9-npu-pciex"))
-		phb->model = PNV_PHB_MODEL_NPU2;
 	else
 		phb->model = PNV_PHB_MODEL_UNKNOWN;
 
@@ -3118,9 +2949,6 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	ppc_md.pcibios_fixup = pnv_pci_ioda_fixup;
 
 	switch (phb->type) {
-	case PNV_PHB_NPU_NVLINK:
-		hose->controller_ops = pnv_npu_ioda_controller_ops;
-		break;
 	case PNV_PHB_NPU_OCAPI:
 		hose->controller_ops = pnv_npu_ocapi_ioda_controller_ops;
 		break;
@@ -3173,11 +3001,6 @@ void __init pnv_pci_init_ioda2_phb(struct device_node *np)
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_IODA2);
 }
 
-void __init pnv_pci_init_npu_phb(struct device_node *np)
-{
-	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_NVLINK);
-}
-
 void __init pnv_pci_init_npu2_opencapi_phb(struct device_node *np)
 {
 	pnv_pci_init_ioda_phb(np, 0, PNV_PHB_NPU_OCAPI);

arch/powerpc/platforms/powernv/pci.c

@@ -926,17 +926,6 @@ void __init pnv_pci_init(void)
 	for_each_compatible_node(np, NULL, "ibm,ioda3-phb")
 		pnv_pci_init_ioda2_phb(np);
 
-	/* Look for NPU PHBs */
-	for_each_compatible_node(np, NULL, "ibm,ioda2-npu-phb")
-		pnv_pci_init_npu_phb(np);
-
-	/*
-	 * Look for NPU2 PHBs which we treat mostly as NPU PHBs with
-	 * the exception of TCE kill which requires an OPAL call.
-	 */
-	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-phb")
-		pnv_pci_init_npu_phb(np);
-
 	/* Look for NPU2 OpenCAPI PHBs */
 	for_each_compatible_node(np, NULL, "ibm,ioda2-npu2-opencapi-phb")
 		pnv_pci_init_npu2_opencapi_phb(np);

arch/powerpc/platforms/powernv/pci.h

@@ -10,10 +10,9 @@
 struct pci_dn;
 
 enum pnv_phb_type {
-	PNV_PHB_IODA1		= 0,
-	PNV_PHB_IODA2		= 1,
-	PNV_PHB_NPU_NVLINK	= 2,
-	PNV_PHB_NPU_OCAPI	= 3,
+	PNV_PHB_IODA1,
+	PNV_PHB_IODA2,
+	PNV_PHB_NPU_OCAPI,
 };
 
 /* Precise PHB model for error management */
@@ -21,8 +20,6 @@ enum pnv_phb_model {
 	PNV_PHB_MODEL_UNKNOWN,
 	PNV_PHB_MODEL_P7IOC,
 	PNV_PHB_MODEL_PHB3,
-	PNV_PHB_MODEL_NPU,
-	PNV_PHB_MODEL_NPU2,
 };
 
 #define PNV_PCI_DIAG_BUF_SIZE	8192
@@ -81,7 +78,6 @@ struct pnv_ioda_pe {
 
 	/* "Base" iommu table, ie, 4K TCEs, 32-bit DMA */
 	struct iommu_table_group table_group;
-	struct npu_comp		*npucomp;
 
 	/* 64-bit TCE bypass region */
 	bool			tce_bypass_enabled;
@@ -289,9 +285,7 @@ extern struct iommu_table *pnv_pci_table_alloc(int nid);
 
 extern void pnv_pci_init_ioda_hub(struct device_node *np);
 extern void pnv_pci_init_ioda2_phb(struct device_node *np);
-extern void pnv_pci_init_npu_phb(struct device_node *np);
 extern void pnv_pci_init_npu2_opencapi_phb(struct device_node *np);
-extern void pnv_npu2_map_lpar(struct pnv_ioda_pe *gpe, unsigned long msr);
 extern void pnv_pci_reset_secondary_bus(struct pci_dev *dev);
 extern int pnv_eeh_phb_reset(struct pci_controller *hose, int option);
 
@@ -314,11 +308,6 @@ extern void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
 #define pe_info(pe, fmt, ...)					\
 	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
-/* Nvlink functions */
-extern void pnv_npu_try_dma_set_bypass(struct pci_dev *gpdev, bool bypass);
-extern void pnv_pci_ioda2_tce_invalidate_entire(struct pnv_phb *phb, bool rm);
-extern void pnv_pci_npu_setup_iommu_groups(void);
-
 /* pci-ioda-tce.c */
 #define POWERNV_IOMMU_DEFAULT_LEVELS	2
 #define POWERNV_IOMMU_MAX_LEVELS	5

arch/powerpc/platforms/pseries/pci.c

@@ -224,8 +224,6 @@ static void __init pSeries_request_regions(void)
 
 void __init pSeries_final_fixup(void)
 {
-	struct pci_controller *hose;
-
 	pSeries_request_regions();
 
 	eeh_show_enabled();
@@ -234,27 +232,6 @@ void __init pSeries_final_fixup(void)
 	ppc_md.pcibios_sriov_enable = pseries_pcibios_sriov_enable;
 	ppc_md.pcibios_sriov_disable = pseries_pcibios_sriov_disable;
 #endif
-	list_for_each_entry(hose, &hose_list, list_node) {
-		struct device_node *dn = hose->dn, *nvdn;
-
-		while (1) {
-			dn = of_find_all_nodes(dn);
-			if (!dn)
-				break;
-			nvdn = of_parse_phandle(dn, "ibm,nvlink", 0);
-			if (!nvdn)
-				continue;
-			if (!of_device_is_compatible(nvdn, "ibm,npu-link"))
-				continue;
-			if (!of_device_is_compatible(nvdn->parent,
-						"ibm,power9-npu"))
-				continue;
-#ifdef CONFIG_PPC_POWERNV
-			WARN_ON_ONCE(pnv_npu2_init(hose));
-#endif
-			break;
-		}
-	}
 }
 
 /*