Merge tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman: "This is a bit late, partly due to me travelling, and partly due to a power outage knocking out some of my test systems *while* I was travelling. - Initial support for running on a system with an Ultravisor, which is software that runs below the hypervisor and protects guests against some attacks by the hypervisor. - Support for building the kernel to run as a "Secure Virtual Machine", ie. as a guest capable of running on a system with an Ultravisor. - Some changes to our DMA code on bare metal, to allow devices with medium sized DMA masks (> 32 && < 59 bits) to use more than 2GB of DMA space. - Support for firmware assisted crash dumps on bare metal (powernv). - Two series fixing bugs in and refactoring our PCI EEH code. - A large series refactoring our exception entry code to use gas macros, both to make it more readable and also enable some future optimisations. As well as many cleanups and other minor features & fixups. Thanks to: Adam Zerella, Alexey Kardashevskiy, Alistair Popple, Andrew Donnellan, Aneesh Kumar K.V, Anju T Sudhakar, Anshuman Khandual, Balbir Singh, Benjamin Herrenschmidt, Cédric Le Goater, Christophe JAILLET, Christophe Leroy, Christopher M. Riedl, Christoph Hellwig, Claudio Carvalho, Daniel Axtens, David Gibson, David Hildenbrand, Desnes A. Nunes do Rosario, Ganesh Goudar, Gautham R. Shenoy, Greg Kurz, Guerney Hunt, Gustavo Romero, Halil Pasic, Hari Bathini, Joakim Tjernlund, Jonathan Neuschafer, Jordan Niethe, Leonardo Bras, Lianbo Jiang, Madhavan Srinivasan, Mahesh Salgaonkar, Mahesh Salgaonkar, Masahiro Yamada, Maxiwell S. Garcia, Michael Anderson, Nathan Chancellor, Nathan Lynch, Naveen N. Rao, Nicholas Piggin, Oliver O'Halloran, Qian Cai, Ram Pai, Ravi Bangoria, Reza Arbab, Ryan Grimm, Sam Bobroff, Santosh Sivaraj, Segher Boessenkool, Sukadev Bhattiprolu, Thiago Bauermann, Thiago Jung Bauermann, Thomas Gleixner, Tom Lendacky, Vasant Hegde" * tag 'powerpc-5.4-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (264 commits) powerpc/mm/mce: Keep irqs disabled during lockless page table walk powerpc: Use ftrace_graph_ret_addr() when unwinding powerpc/ftrace: Enable HAVE_FUNCTION_GRAPH_RET_ADDR_PTR ftrace: Look up the address of return_to_handler() using helpers powerpc: dump kernel log before carrying out fadump or kdump docs: powerpc: Add missing documentation reference powerpc/xmon: Fix output of XIVE IPI powerpc/xmon: Improve output of XIVE interrupts powerpc/mm/radix: remove useless kernel messages powerpc/fadump: support holes in kernel boot memory area powerpc/fadump: remove RMA_START and RMA_END macros powerpc/fadump: update documentation about option to release opalcore powerpc/fadump: consider f/w load area powerpc/opalcore: provide an option to invalidate /sys/firmware/opal/core file powerpc/opalcore: export /sys/firmware/opal/core for analysing opal crashes powerpc/fadump: update documentation about CONFIG_PRESERVE_FA_DUMP powerpc/fadump: add support to preserve crash data on FADUMP disabled kernel powerpc/fadump: improve how crashed kernel's memory is reserved powerpc/fadump: consider reserved ranges while releasing memory powerpc/fadump: make crash memory ranges array allocation generic ...
author: Linus Torvalds 2019-09-20 11:48:06 -0700
committer: Linus Torvalds 2019-09-20 11:48:06 -0700
commit: 45824fc0da6e46cc5d563105e1eaaf3098a686f9 (patch)
tree: 8e57c1f18104ed5f0d74d9eed9dc0365b3c137b8 /arch/powerpc/mm
parent: 8c2b418c3f95a488f5226870eee68574d323f0f8 (diff)
parent: d9101bfa6adc831bda8836c4d774820553c14942 (diff)
20 files changed, 786 insertions, 1019 deletions
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 0f499db315d6..5e147986400d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -7,7 +7,7 @@ ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 obj-y				:= fault.o mem.o pgtable.o mmap.o \
 				   init_$(BITS).o pgtable_$(BITS).o \
-				   pgtable-frag.o \
+				   pgtable-frag.o ioremap.o ioremap_$(BITS).o \
 				   init-common.o mmu_context.o drmem.o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= nohash/
 obj-$(CONFIG_PPC_BOOK3S_32)	+= book3s32/
diff --git a/arch/powerpc/mm/book3s32/mmu.c b/arch/powerpc/mm/book3s32/mmu.c
index e249fbf6b9c3..84d5fab94f8f 100644
--- a/arch/powerpc/mm/book3s32/mmu.c
+++ b/arch/powerpc/mm/book3s32/mmu.c
@@ -74,7 +74,7 @@ static int find_free_bat(void)
 {
 	int b;
 
-	if (cpu_has_feature(CPU_FTR_601)) {
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
 		for (b = 0; b < 4; b++) {
 			struct ppc_bat *bat = BATS[b];
 
@@ -106,7 +106,7 @@ static int find_free_bat(void)
  */
 static unsigned int block_size(unsigned long base, unsigned long top)
 {
-	unsigned int max_size = (cpu_has_feature(CPU_FTR_601) ? 8 : 256) << 20;
+	unsigned int max_size = IS_ENABLED(CONFIG_PPC_BOOK3S_601) ? SZ_8M : SZ_256M;
 	unsigned int base_shift = (ffs(base) - 1) & 31;
 	unsigned int block_shift = (fls(top - base) - 1) & 31;
 
@@ -189,7 +189,7 @@ void mmu_mark_initmem_nx(void)
 	unsigned long top = (unsigned long)_etext - PAGE_OFFSET;
 	unsigned long size;
 
-	if (cpu_has_feature(CPU_FTR_601))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
 		return;
 
 	for (i = 0; i < nb - 1 && base < top && top - base > (128 << 10);) {
@@ -227,7 +227,7 @@ void mmu_mark_rodata_ro(void)
 	int nb = mmu_has_feature(MMU_FTR_USE_HIGH_BATS) ? 8 : 4;
 	int i;
 
-	if (cpu_has_feature(CPU_FTR_601))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
 		return;
 
 	for (i = 0; i < nb; i++) {
@@ -259,7 +259,7 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
 		flags &= ~_PAGE_COHERENT;
 
 	bl = (size >> 17) - 1;
-	if (PVR_VER(mfspr(SPRN_PVR)) != 1) {
+	if (!IS_ENABLED(CONFIG_PPC_BOOK3S_601)) {
 		/* 603, 604, etc. */
 		/* Do DBAT first */
 		wimgxpp = flags & (_PAGE_WRITETHRU | _PAGE_NO_CACHE
@@ -297,8 +297,7 @@ void __init setbat(int index, unsigned long virt, phys_addr_t phys,
 /*
  * Preload a translation in the hash table
  */
-void hash_preload(struct mm_struct *mm, unsigned long ea,
-		  bool is_exec, unsigned long trap)
+void hash_preload(struct mm_struct *mm, unsigned long ea)
 {
 	pmd_t *pmd;
 
@@ -310,6 +309,39 @@ void hash_preload(struct mm_struct *mm, unsigned long ea,
 }
 
 /*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux PTE.
+ *
+ * This must always be called with the pte lock held.
+ */
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+		      pte_t *ptep)
+{
+	if (!mmu_has_feature(MMU_FTR_HPTE_TABLE))
+		return;
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
+
+	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
+	if (!pte_young(*ptep) || address >= TASK_SIZE)
+		return;
+
+	/* We have to test for regs NULL since init will get here first thing at boot */
+	if (!current->thread.regs)
+		return;
+
+	/* We also avoid filling the hash if not coming from a fault */
+	if (TRAP(current->thread.regs) != 0x300 && TRAP(current->thread.regs) != 0x400)
+		return;
+
+	hash_preload(vma->vm_mm, address);
+}
+
+/*
  * Initialize the hash table and patch the instructions in hashtable.S.
  */
 void __init MMU_init_hw(void)
@@ -358,6 +390,15 @@ void __init MMU_init_hw(void)
 	hash_mb2 = hash_mb = 32 - LG_HPTEG_SIZE - lg_n_hpteg;
 	if (lg_n_hpteg > 16)
 		hash_mb2 = 16 - LG_HPTEG_SIZE;
+
+	/*
+	 * When KASAN is selected, there is already an early temporary hash
+	 * table and the switch to the final hash table is done later.
+	 */
+	if (IS_ENABLED(CONFIG_KASAN))
+		return;
+
+	MMU_init_hw_patch();
 }
 
 void __init MMU_init_hw_patch(void)
@@ -400,7 +441,7 @@ void setup_initial_memory_limit(phys_addr_t first_memblock_base,
 	BUG_ON(first_memblock_base != 0);
 
 	/* 601 can only access 16MB at the moment */
-	if (PVR_VER(mfspr(SPRN_PVR)) == 1)
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
 		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x01000000));
 	else /* Anything else has 256M mapped */
 		memblock_set_current_limit(min_t(u64, first_memblock_size, 0x10000000));
@@ -418,9 +459,6 @@ void __init setup_kuep(bool disabled)
 {
 	pr_info("Activating Kernel Userspace Execution Prevention\n");
 
-	if (cpu_has_feature(CPU_FTR_601))
-		pr_warn("KUEP is not working on powerpc 601 (No NX bit in Seg Regs)\n");
-
 	if (disabled)
 		pr_warn("KUEP cannot be disabled yet on 6xx when compiled in\n");
 }
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index b8ad14bb1170..3410ea9f4de1 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -34,6 +34,7 @@
 #include <linux/libfdt.h>
 #include <linux/pkeys.h>
 #include <linux/hugetlb.h>
+#include <linux/cpu.h>
 
 #include <asm/debugfs.h>
 #include <asm/processor.h>
@@ -61,6 +62,7 @@
 #include <asm/ps3.h>
 #include <asm/pte-walk.h>
 #include <asm/asm-prototypes.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 
@@ -271,10 +273,6 @@ int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
 		if (overlaps_kernel_text(vaddr, vaddr + step))
 			tprot &= ~HPTE_R_N;
 
-		/* Make kvm guest trampolines executable */
-		if (overlaps_kvm_tmp(vaddr, vaddr + step))
-			tprot &= ~HPTE_R_N;
-
 		/*
 		 * If relocatable, check if it overlaps interrupt vectors that
 		 * are copied down to real 0. For relocatable kernel
@@ -823,7 +821,7 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	 * For now, UPRT is 0 and we have no segment table.
 	 */
 	htab_size =  __ilog2(htab_size) - 18;
-	mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
+	mmu_partition_table_set_entry(0, hash_table | htab_size, 0, false);
 	pr_info("Partition table %p\n", partition_tb);
 }
 
@@ -857,12 +855,6 @@ static void __init htab_initialize(void)
 		/* Using a hypervisor which owns the htab */
 		htab_address = NULL;
 		_SDR1 = 0; 
-		/*
-		 * On POWER9, we need to do a H_REGISTER_PROC_TBL hcall
-		 * to inform the hypervisor that we wish to use the HPT.
-		 */
-		if (cpu_has_feature(CPU_FTR_ARCH_300))
-			register_process_table(0, 0, 0);
 #ifdef CONFIG_FA_DUMP
 		/*
 		 * If firmware assisted dump is active firmware preserves
@@ -1075,8 +1067,8 @@ void hash__early_init_mmu_secondary(void)
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else
-			mtspr(SPRN_PTCR,
-			      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+			set_ptcr_when_no_uv(__pa(partition_tb) |
+					    (PATB_SIZE_SHIFT - 12));
 	}
 	/* Initialize SLB */
 	slb_initialize();
@@ -1460,8 +1452,8 @@ int hash_page(unsigned long ea, unsigned long access, unsigned long trap,
 }
 EXPORT_SYMBOL_GPL(hash_page);
 
-int __hash_page(unsigned long ea, unsigned long msr, unsigned long trap,
-		unsigned long dsisr)
+int __hash_page(unsigned long trap, unsigned long ea, unsigned long dsisr,
+		unsigned long msr)
 {
 	unsigned long access = _PAGE_PRESENT | _PAGE_READ;
 	unsigned long flags = 0;
@@ -1518,8 +1510,8 @@ static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
 }
 #endif
 
-void hash_preload(struct mm_struct *mm, unsigned long ea,
-		  bool is_exec, unsigned long trap)
+static void hash_preload(struct mm_struct *mm, unsigned long ea,
+			 bool is_exec, unsigned long trap)
 {
 	int hugepage_shift;
 	unsigned long vsid;
@@ -1599,6 +1591,57 @@ out_exit:
 	local_irq_restore(flags);
 }
 
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ * We use it to preload an HPTE into the hash table corresponding to
+ * the updated linux PTE.
+ *
+ * This must always be called with the pte lock held.
+ */
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+		      pte_t *ptep)
+{
+	/*
+	 * We don't need to worry about _PAGE_PRESENT here because we are
+	 * called with either mm->page_table_lock held or ptl lock held
+	 */
+	unsigned long trap;
+	bool is_exec;
+
+	if (radix_enabled()) {
+		prefetch((void *)address);
+		return;
+	}
+
+	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
+	if (!pte_young(*ptep) || address >= TASK_SIZE)
+		return;
+
+	/*
+	 * We try to figure out if we are coming from an instruction
+	 * access fault and pass that down to __hash_page so we avoid
+	 * double-faulting on execution of fresh text. We have to test
+	 * for regs NULL since init will get here first thing at boot.
+	 *
+	 * We also avoid filling the hash if not coming from a fault.
+	 */
+
+	trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
+	switch (trap) {
+	case 0x300:
+		is_exec = false;
+		break;
+	case 0x400:
+		is_exec = true;
+		break;
+	default:
+		return;
+	}
+
+	hash_preload(vma->vm_mm, address, is_exec, trap);
+}
+
 #ifdef CONFIG_PPC_MEM_KEYS
 /*
  * Return the protection key associated with the given address and the
@@ -1931,10 +1974,16 @@ static int hpt_order_get(void *data, u64 *val)
 
 static int hpt_order_set(void *data, u64 val)
 {
+	int ret;
+
 	if (!mmu_hash_ops.resize_hpt)
 		return -ENODEV;
 
-	return mmu_hash_ops.resize_hpt(val);
+	cpus_read_lock();
+	ret = mmu_hash_ops.resize_hpt(val);
+	cpus_read_unlock();
+
+	return ret;
 }
 
 DEFINE_DEBUGFS_ATTRIBUTE(fops_hpt_order, hpt_order_get, hpt_order_set, "%llu\n");
@@ -1957,7 +2006,4 @@ void __init print_system_hash_info(void)
 
 	if (htab_hash_mask)
 		pr_info("htab_hash_mask    = 0x%lx\n", htab_hash_mask);
-	pr_info("kernel vmalloc start   = 0x%lx\n", KERN_VIRT_START);
-	pr_info("kernel IO start        = 0x%lx\n", KERN_IO_START);
-	pr_info("kernel vmemmap start   = 0x%lx\n", (unsigned long)vmemmap);
 }
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 7d0e0d0d22c4..75483b40fcb1 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -8,10 +8,13 @@
 #include <linux/memblock.h>
 #include <misc/cxl-base.h>
 
+#include <asm/debugfs.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/trace.h>
 #include <asm/powernv.h>
+#include <asm/firmware.h>
+#include <asm/ultravisor.h>
 
 #include <mm/mmu_decl.h>
 #include <trace/events/thp.h>
@@ -21,9 +24,6 @@ EXPORT_SYMBOL(__pmd_frag_nr);
 unsigned long __pmd_frag_size_shift;
 EXPORT_SYMBOL(__pmd_frag_size_shift);
 
-int (*register_process_table)(unsigned long base, unsigned long page_size,
-			      unsigned long tbl_size);
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * This is called when relaxing access to a hugepage. It's also called in the page
@@ -205,37 +205,61 @@ void __init mmu_partition_table_init(void)
 	 * 64 K size.
 	 */
 	ptcr = __pa(partition_tb) | (PATB_SIZE_SHIFT - 12);
-	mtspr(SPRN_PTCR, ptcr);
+	set_ptcr_when_no_uv(ptcr);
 	powernv_set_nmmu_ptcr(ptcr);
 }
 
+static void flush_partition(unsigned int lpid, bool radix)
+{
+	if (radix) {
+		radix__flush_all_lpid(lpid);
+		radix__flush_all_lpid_guest(lpid);
+	} else {
+		asm volatile("ptesync" : : : "memory");
+		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
+			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
+		/* do we need fixup here ?*/
+		asm volatile("eieio; tlbsync; ptesync" : : : "memory");
+		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
+	}
+}
+
 void mmu_partition_table_set_entry(unsigned int lpid, unsigned long dw0,
-				   unsigned long dw1)
+				  unsigned long dw1, bool flush)
 {
 	unsigned long old = be64_to_cpu(partition_tb[lpid].patb0);
 
+	/*
+	 * When ultravisor is enabled, the partition table is stored in secure
+	 * memory and can only be accessed doing an ultravisor call. However, we
+	 * maintain a copy of the partition table in normal memory to allow Nest
+	 * MMU translations to occur (for normal VMs).
+	 *
+	 * Therefore, here we always update partition_tb, regardless of whether
+	 * we are running under an ultravisor or not.
+	 */
 	partition_tb[lpid].patb0 = cpu_to_be64(dw0);
 	partition_tb[lpid].patb1 = cpu_to_be64(dw1);
 
 	/*
-	 * Global flush of TLBs and partition table caches for this lpid.
-	 * The type of flush (hash or radix) depends on what the previous
-	 * use of this partition ID was, not the new use.
+	 * If ultravisor is enabled, we do an ultravisor call to register the
+	 * partition table entry (PATE), which also do a global flush of TLBs
+	 * and partition table caches for the lpid. Otherwise, just do the
+	 * flush. The type of flush (hash or radix) depends on what the previous
+	 * use of the partition ID was, not the new use.
 	 */
-	asm volatile("ptesync" : : : "memory");
-	if (old & PATB_HR) {
-		asm volatile(PPC_TLBIE_5(%0,%1,2,0,1) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 1);
-	} else {
-		asm volatile(PPC_TLBIE_5(%0,%1,2,0,0) : :
-			     "r" (TLBIEL_INVAL_SET_LPID), "r" (lpid));
-		trace_tlbie(lpid, 0, TLBIEL_INVAL_SET_LPID, lpid, 2, 0, 0);
+	if (firmware_has_feature(FW_FEATURE_ULTRAVISOR)) {
+		uv_register_pate(lpid, dw0, dw1);
+		pr_info("PATE registered by ultravisor: dw0 = 0x%lx, dw1 = 0x%lx\n",
+			dw0, dw1);
+	} else if (flush) {
+		/*
+		 * Boot does not need to flush, because MMU is off and each
+		 * CPU does a tlbiel_all() before switching them on, which
+		 * flushes everything.
+		 */
+		flush_partition(lpid, (old & PATB_HR));
 	}
-	/* do we need fixup here ?*/
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 EXPORT_SYMBOL_GPL(mmu_partition_table_set_entry);
 
@@ -447,23 +471,48 @@ int pmd_move_must_withdraw(struct spinlock *new_pmd_ptl,
 	return true;
 }
 
-int ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid)
-{
-	unsigned long i;
+/*
+ * Does the CPU support tlbie?
+ */
+bool tlbie_capable __read_mostly = true;
+EXPORT_SYMBOL(tlbie_capable);
 
-	if (radix_enabled())
-		return radix__ioremap_range(ea, pa, size, prot, nid);
-
-	for (i = 0; i < size; i += PAGE_SIZE) {
-		int err = map_kernel_page(ea + i, pa + i, prot);
-		if (err) {
-			if (slab_is_available())
-				unmap_kernel_range(ea, size);
-			else
-				WARN_ON_ONCE(1); /* Should clean up */
-			return err;
-		}
+/*
+ * Should tlbie be used for management of CPU TLBs, for kernel and process
+ * address spaces? tlbie may still be used for nMMU accelerators, and for KVM
+ * guest address spaces.
+ */
+bool tlbie_enabled __read_mostly = true;
+
+static int __init setup_disable_tlbie(char *str)
+{
+	if (!radix_enabled()) {
+		pr_err("disable_tlbie: Unable to disable TLBIE with Hash MMU.\n");
+		return 1;
 	}
 
+	tlbie_capable = false;
+	tlbie_enabled = false;
+
+        return 1;
+}
+__setup("disable_tlbie", setup_disable_tlbie);
+
+static int __init pgtable_debugfs_setup(void)
+{
+	if (!tlbie_capable)
+		return 0;
+
+	/*
+	 * There is no locking vs tlb flushing when changing this value.
+	 * The tlb flushers will see one value or another, and use either
+	 * tlbie or tlbiel with IPIs. In both cases the TLBs will be
+	 * invalidated as expected.
+	 */
+	debugfs_create_bool("tlbie_enabled", 0600,
+			powerpc_debugfs_root,
+			&tlbie_enabled);
+
 	return 0;
 }
+arch_initcall(pgtable_debugfs_setup);
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index b4ca9e95e678..3a1fbf9cb8f8 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -27,25 +27,13 @@
 #include <asm/sections.h>
 #include <asm/trace.h>
 #include <asm/uaccess.h>
+#include <asm/ultravisor.h>
 
 #include <trace/events/thp.h>
 
 unsigned int mmu_pid_bits;
 unsigned int mmu_base_pid;
 
-static int native_register_process_table(unsigned long base, unsigned long pg_sz,
-					 unsigned long table_size)
-{
-	unsigned long patb0, patb1;
-
-	patb0 = be64_to_cpu(partition_tb[0].patb0);
-	patb1 = base | table_size | PATB_GR;
-
-	mmu_partition_table_set_entry(0, patb0, patb1);
-
-	return 0;
-}
-
 static __ref void *early_alloc_pgtable(unsigned long size, int nid,
 			unsigned long region_start, unsigned long region_end)
 {
@@ -380,18 +368,6 @@ static void __init radix_init_pgtable(void)
 	 */
 	rts_field = radix__get_tree_size();
 	process_tb->prtb0 = cpu_to_be64(rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE);
-	/*
-	 * Fill in the partition table. We are suppose to use effective address
-	 * of process table here. But our linear mapping also enable us to use
-	 * physical address here.
-	 */
-	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
-	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
-	asm volatile("ptesync" : : : "memory");
-	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
-		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
-	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
-	trace_tlbie(0, 0, TLBIEL_INVAL_SET_LPID, 0, 2, 1, 1);
 
 	/*
 	 * The init_mm context is given the first available (non-zero) PID,
@@ -412,20 +388,15 @@ static void __init radix_init_pgtable(void)
 
 static void __init radix_init_partition_table(void)
 {
-	unsigned long rts_field, dw0;
+	unsigned long rts_field, dw0, dw1;
 
 	mmu_partition_table_init();
 	rts_field = radix__get_tree_size();
 	dw0 = rts_field | __pa(init_mm.pgd) | RADIX_PGD_INDEX_SIZE | PATB_HR;
-	mmu_partition_table_set_entry(0, dw0, 0);
+	dw1 = __pa(process_tb) | (PRTB_SIZE_SHIFT - 12) | PATB_GR;
+	mmu_partition_table_set_entry(0, dw0, dw1, false);
 
 	pr_info("Initializing Radix MMU\n");
-	pr_info("Partition table %p\n", partition_tb);
-}
-
-void __init radix_init_native(void)
-{
-	register_process_table = native_register_process_table;
 }
 
 static int __init get_idx_from_shift(unsigned int shift)
@@ -621,8 +592,9 @@ void __init radix__early_init_mmu(void)
 	__pmd_frag_nr = RADIX_PMD_FRAG_NR;
 	__pmd_frag_size_shift = RADIX_PMD_FRAG_SIZE_SHIFT;
 
+	radix_init_pgtable();
+
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		radix_init_native();
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
@@ -633,11 +605,9 @@ void __init radix__early_init_mmu(void)
 
 	memblock_set_current_limit(MEMBLOCK_ALLOC_ANYWHERE);
 
-	radix_init_pgtable();
 	/* Switch to the guard PID before turning on MMU */
 	radix__switch_mmu_context(NULL, &init_mm);
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		tlbiel_all();
+	tlbiel_all();
 }
 
 void radix__early_init_mmu_secondary(void)
@@ -650,14 +620,14 @@ void radix__early_init_mmu_secondary(void)
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
-		mtspr(SPRN_PTCR,
-		      __pa(partition_tb) | (PATB_SIZE_SHIFT - 12));
+		set_ptcr_when_no_uv(__pa(partition_tb) |
+				    (PATB_SIZE_SHIFT - 12));
+
 		radix_init_amor();
 	}
 
 	radix__switch_mmu_context(NULL, &init_mm);
-	if (cpu_has_feature(CPU_FTR_HVMODE))
-		tlbiel_all();
+	tlbiel_all();
 }
 
 void radix__mmu_cleanup_all(void)
@@ -667,7 +637,7 @@ void radix__mmu_cleanup_all(void)
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr & ~LPCR_UPRT);
-		mtspr(SPRN_PTCR, 0);
+		set_ptcr_when_no_uv(0);
 		powernv_set_nmmu_ptcr(0);
 		radix__flush_tlb_all();
 	}
@@ -737,8 +707,8 @@ static int __meminit stop_machine_change_mapping(void *data)
 
 	spin_unlock(&init_mm.page_table_lock);
 	pte_clear(&init_mm, params->aligned_start, params->pte);
-	create_physical_mapping(params->aligned_start, params->start, -1);
-	create_physical_mapping(params->end, params->aligned_end, -1);
+	create_physical_mapping(__pa(params->aligned_start), __pa(params->start), -1);
+	create_physical_mapping(__pa(params->end), __pa(params->aligned_end), -1);
 	spin_lock(&init_mm.page_table_lock);
 	return 0;
 }
@@ -902,7 +872,7 @@ int __meminit radix__create_section_mapping(unsigned long start, unsigned long e
 		return -1;
 	}
 
-	return create_physical_mapping(start, end, nid);
+	return create_physical_mapping(__pa(start), __pa(end), nid);
 }
 
 int __meminit radix__remove_section_mapping(unsigned long start, unsigned long end)
@@ -1218,26 +1188,6 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 	return 1;
 }
 
-int radix__ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size,
-			pgprot_t prot, int nid)
-{
-	if (likely(slab_is_available())) {
-		int err = ioremap_page_range(ea, ea + size, pa, prot);
-		if (err)
-			unmap_kernel_range(ea, size);
-		return err;
-	} else {
-		unsigned long i;
-
-		for (i = 0; i < size; i += PAGE_SIZE) {
-			int err = map_kernel_page(ea + i, pa + i, prot);
-			if (WARN_ON_ONCE(err)) /* Should clean up */
-				return err;
-		}
-		return 0;
-	}
-}
-
 int __init arch_ioremap_p4d_supported(void)
 {
 	return 0;
diff --git a/arch/powerpc/mm/book3s64/radix_tlb.c b/arch/powerpc/mm/book3s64/radix_tlb.c
index 71f7fede2fa4..631be42abd33 100644
--- a/arch/powerpc/mm/book3s64/radix_tlb.c
+++ b/arch/powerpc/mm/book3s64/radix_tlb.c
@@ -51,11 +51,15 @@ static void tlbiel_all_isa300(unsigned int num_sets, unsigned int is)
 	 * and partition table entries. Then flush the remaining sets of the
 	 * TLB.
 	 */
-	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
-	for (set = 1; set < num_sets; set++)
-		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
 
-	/* Do the same for process scoped entries. */
+	if (early_cpu_has_feature(CPU_FTR_HVMODE)) {
+		/* MSR[HV] should flush partition scope translations first. */
+		tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 0);
+		for (set = 1; set < num_sets; set++)
+			tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 0);
+	}
+
+	/* Flush process scoped entries. */
 	tlbiel_radix_set_isa300(0, is, 0, RIC_FLUSH_ALL, 1);
 	for (set = 1; set < num_sets; set++)
 		tlbiel_radix_set_isa300(set, is, 0, RIC_FLUSH_TLB, 1);
@@ -116,22 +120,6 @@ static __always_inline void __tlbie_pid(unsigned long pid, unsigned long ric)
 	trace_tlbie(0, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbiel_lpid(unsigned long lpid, int set,
-				unsigned long ric)
-{
-	unsigned long rb,rs,prs,r;
-
-	rb = PPC_BIT(52); /* IS = 2 */
-	rb |= set << PPC_BITLSHIFT(51);
-	rs = 0;  /* LPID comes from LPIDR */
-	prs = 0; /* partition scoped */
-	r = 1;   /* radix format */
-
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
-}
-
 static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
@@ -146,23 +134,20 @@ static __always_inline void __tlbie_lpid(unsigned long lpid, unsigned long ric)
 	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
 }
 
-static __always_inline void __tlbiel_lpid_guest(unsigned long lpid, int set,
-						unsigned long ric)
+static __always_inline void __tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
 {
 	unsigned long rb,rs,prs,r;
 
 	rb = PPC_BIT(52); /* IS = 2 */
-	rb |= set << PPC_BITLSHIFT(51);
-	rs = 0;  /* LPID comes from LPIDR */
+	rs = lpid;
 	prs = 1; /* process scoped */
 	r = 1;   /* radix format */
 
-	asm volatile(PPC_TLBIEL(%0, %4, %3, %2, %1)
+	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
 		     : : "r"(rb), "i"(r), "i"(prs), "i"(ric), "r"(rs) : "memory");
-	trace_tlbie(lpid, 1, rb, rs, ric, prs, r);
+	trace_tlbie(lpid, 0, rb, rs, ric, prs, r);
 }
 
-
 static __always_inline void __tlbiel_va(unsigned long va, unsigned long pid,
 					unsigned long ap, unsigned long ric)
 {
@@ -285,32 +270,37 @@ static inline void _tlbie_pid(unsigned long pid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static inline void _tlbiel_lpid(unsigned long lpid, unsigned long ric)
+struct tlbiel_pid {
+	unsigned long pid;
+	unsigned long ric;
+};
+
+static void do_tlbiel_pid(void *info)
 {
-	int set;
+	struct tlbiel_pid *t = info;
 
-	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
+	if (t->ric == RIC_FLUSH_TLB)
+		_tlbiel_pid(t->pid, RIC_FLUSH_TLB);
+	else if (t->ric == RIC_FLUSH_PWC)
+		_tlbiel_pid(t->pid, RIC_FLUSH_PWC);
+	else
+		_tlbiel_pid(t->pid, RIC_FLUSH_ALL);
+}
 
-	asm volatile("ptesync": : :"memory");
+static inline void _tlbiel_pid_multicast(struct mm_struct *mm,
+				unsigned long pid, unsigned long ric)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_pid t = { .pid = pid, .ric = ric };
 
+	on_each_cpu_mask(cpus, do_tlbiel_pid, &t, 1);
 	/*
-	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
-	 * also flush the entire Page Walk Cache.
+	 * Always want the CPU translations to be invalidated with tlbiel in
+	 * these paths, so while coprocessors must use tlbie, we can not
+	 * optimise away the tlbiel component.
 	 */
-	__tlbiel_lpid(lpid, 0, ric);
-
-	/* For PWC, only one flush is needed */
-	if (ric == RIC_FLUSH_PWC) {
-		asm volatile("ptesync": : :"memory");
-		return;
-	}
-
-	/* For the remaining sets, just flush the TLB */
-	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
-		__tlbiel_lpid(lpid, set, RIC_FLUSH_TLB);
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST "; isync" : : :"memory");
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_pid(pid, RIC_FLUSH_ALL);
 }
 
 static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric)
@@ -337,35 +327,28 @@ static inline void _tlbie_lpid(unsigned long lpid, unsigned long ric)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-static __always_inline void _tlbiel_lpid_guest(unsigned long lpid, unsigned long ric)
+static __always_inline void _tlbie_lpid_guest(unsigned long lpid, unsigned long ric)
 {
-	int set;
-
-	VM_BUG_ON(mfspr(SPRN_LPID) != lpid);
-
-	asm volatile("ptesync": : :"memory");
-
 	/*
-	 * Flush the first set of the TLB, and if we're doing a RIC_FLUSH_ALL,
-	 * also flush the entire Page Walk Cache.
+	 * Workaround the fact that the "ric" argument to __tlbie_pid
+	 * must be a compile-time contraint to match the "i" constraint
+	 * in the asm statement.
 	 */
-	__tlbiel_lpid_guest(lpid, 0, ric);
-
-	/* For PWC, only one flush is needed */
-	if (ric == RIC_FLUSH_PWC) {
-		asm volatile("ptesync": : :"memory");
-		return;
+	switch (ric) {
+	case RIC_FLUSH_TLB:
+		__tlbie_lpid_guest(lpid, RIC_FLUSH_TLB);
+		break;
+	case RIC_FLUSH_PWC:
+		__tlbie_lpid_guest(lpid, RIC_FLUSH_PWC);
+		break;
+	case RIC_FLUSH_ALL:
+	default:
+		__tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
 	}
-
-	/* For the remaining sets, just flush the TLB */
-	for (set = 1; set < POWER9_TLB_SETS_RADIX ; set++)
-		__tlbiel_lpid_guest(lpid, set, RIC_FLUSH_TLB);
-
-	asm volatile("ptesync": : :"memory");
-	asm volatile(PPC_RADIX_INVALIDATE_ERAT_GUEST : : :"memory");
+	fixup_tlbie_lpid(lpid);
+	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-
 static inline void __tlbiel_va_range(unsigned long start, unsigned long end,
 				    unsigned long pid, unsigned long page_size,
 				    unsigned long psize)
@@ -420,6 +403,53 @@ static __always_inline void _tlbie_va(unsigned long va, unsigned long pid,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+struct tlbiel_va {
+	unsigned long pid;
+	unsigned long va;
+	unsigned long psize;
+	unsigned long ric;
+};
+
+static void do_tlbiel_va(void *info)
+{
+	struct tlbiel_va *t = info;
+
+	if (t->ric == RIC_FLUSH_TLB)
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_TLB);
+	else if (t->ric == RIC_FLUSH_PWC)
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_PWC);
+	else
+		_tlbiel_va(t->va, t->pid, t->psize, RIC_FLUSH_ALL);
+}
+
+static inline void _tlbiel_va_multicast(struct mm_struct *mm,
+				unsigned long va, unsigned long pid,
+				unsigned long psize, unsigned long ric)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_va t = { .va = va, .pid = pid, .psize = psize, .ric = ric };
+	on_each_cpu_mask(cpus, do_tlbiel_va, &t, 1);
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_va(va, pid, psize, RIC_FLUSH_TLB);
+}
+
+struct tlbiel_va_range {
+	unsigned long pid;
+	unsigned long start;
+	unsigned long end;
+	unsigned long page_size;
+	unsigned long psize;
+	bool also_pwc;
+};
+
+static void do_tlbiel_va_range(void *info)
+{
+	struct tlbiel_va_range *t = info;
+
+	_tlbiel_va_range(t->start, t->end, t->pid, t->page_size,
+				    t->psize, t->also_pwc);
+}
+
 static __always_inline void _tlbie_lpid_va(unsigned long va, unsigned long lpid,
 			      unsigned long psize, unsigned long ric)
 {
@@ -443,6 +473,21 @@ static inline void _tlbie_va_range(unsigned long start, unsigned long end,
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
+static inline void _tlbiel_va_range_multicast(struct mm_struct *mm,
+				unsigned long start, unsigned long end,
+				unsigned long pid, unsigned long page_size,
+				unsigned long psize, bool also_pwc)
+{
+	struct cpumask *cpus = mm_cpumask(mm);
+	struct tlbiel_va_range t = { .start = start, .end = end,
+				.pid = pid, .page_size = page_size,
+				.psize = psize, .also_pwc = also_pwc };
+
+	on_each_cpu_mask(cpus, do_tlbiel_va_range, &t, 1);
+	if (atomic_read(&mm->context.copros) > 0)
+		_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
+}
+
 /*
  * Base TLB flushing operations:
  *
@@ -580,10 +625,14 @@ void radix__flush_tlb_mm(struct mm_struct *mm)
 			goto local;
 		}
 
-		if (mm_needs_flush_escalation(mm))
-			_tlbie_pid(pid, RIC_FLUSH_ALL);
-		else
-			_tlbie_pid(pid, RIC_FLUSH_TLB);
+		if (cputlb_use_tlbie()) {
+			if (mm_needs_flush_escalation(mm))
+				_tlbie_pid(pid, RIC_FLUSH_ALL);
+			else
+				_tlbie_pid(pid, RIC_FLUSH_TLB);
+		} else {
+			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
+		}
 	} else {
 local:
 		_tlbiel_pid(pid, RIC_FLUSH_TLB);
@@ -609,7 +658,10 @@ static void __flush_all_mm(struct mm_struct *mm, bool fullmm)
 				goto local;
 			}
 		}
-		_tlbie_pid(pid, RIC_FLUSH_ALL);
+		if (cputlb_use_tlbie())
+			_tlbie_pid(pid, RIC_FLUSH_ALL);
+		else
+			_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_ALL);
 	} else {
 local:
 		_tlbiel_pid(pid, RIC_FLUSH_ALL);
@@ -644,7 +696,10 @@ void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmaddr,
 			exit_flush_lazy_tlbs(mm);
 			goto local;
 		}
-		_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
+		if (cputlb_use_tlbie())
+			_tlbie_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
+		else
+			_tlbiel_va_multicast(mm, vmaddr, pid, psize, RIC_FLUSH_TLB);
 	} else {
 local:
 		_tlbiel_va(vmaddr, pid, psize, RIC_FLUSH_TLB);
@@ -666,6 +721,24 @@ EXPORT_SYMBOL(radix__flush_tlb_page);
 #define radix__flush_all_mm radix__local_flush_all_mm
 #endif /* CONFIG_SMP */
 
+static void do_tlbiel_kernel(void *info)
+{
+	_tlbiel_pid(0, RIC_FLUSH_ALL);
+}
+
+static inline void _tlbiel_kernel_broadcast(void)
+{
+	on_each_cpu(do_tlbiel_kernel, NULL, 1);
+	if (tlbie_capable) {
+		/*
+		 * Coherent accelerators don't refcount kernel memory mappings,
+		 * so have to always issue a tlbie for them. This is quite a
+		 * slow path anyway.
+		 */
+		_tlbie_pid(0, RIC_FLUSH_ALL);
+	}
+}
+
 /*
  * If kernel TLBIs ever become local rather than global, then
  * drivers/misc/ocxl/link.c:ocxl_link_add_pe will need some work, as it
@@ -673,7 +746,10 @@ EXPORT_SYMBOL(radix__flush_tlb_page);
  */
 void radix__flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	_tlbie_pid(0, RIC_FLUSH_ALL);
+	if (cputlb_use_tlbie())
+		_tlbie_pid(0, RIC_FLUSH_ALL);
+	else
+		_tlbiel_kernel_broadcast();
 }
 EXPORT_SYMBOL(radix__flush_tlb_kernel_range);
 
@@ -729,10 +805,14 @@ is_local:
 		if (local) {
 			_tlbiel_pid(pid, RIC_FLUSH_TLB);
 		} else {
-			if (mm_needs_flush_escalation(mm))
-				_tlbie_pid(pid, RIC_FLUSH_ALL);
-			else
-				_tlbie_pid(pid, RIC_FLUSH_TLB);
+			if (cputlb_use_tlbie()) {
+				if (mm_needs_flush_escalation(mm))
+					_tlbie_pid(pid, RIC_FLUSH_ALL);
+				else
+					_tlbie_pid(pid, RIC_FLUSH_TLB);
+			} else {
+				_tlbiel_pid_multicast(mm, pid, RIC_FLUSH_TLB);
+			}
 		}
 	} else {
 		bool hflush = flush_all_sizes;
@@ -757,8 +837,8 @@ is_local:
 				gflush = false;
 		}
 
-		asm volatile("ptesync": : :"memory");
 		if (local) {
+			asm volatile("ptesync": : :"memory");
 			__tlbiel_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbiel_va_range(hstart, hend, pid,
@@ -767,7 +847,8 @@ is_local:
 				__tlbiel_va_range(gstart, gend, pid,
 						PUD_SIZE, MMU_PAGE_1G);
 			asm volatile("ptesync": : :"memory");
-		} else {
+		} else if (cputlb_use_tlbie()) {
+			asm volatile("ptesync": : :"memory");
 			__tlbie_va_range(start, end, pid, page_size, mmu_virtual_psize);
 			if (hflush)
 				__tlbie_va_range(hstart, hend, pid,
@@ -777,6 +858,15 @@ is_local:
 						PUD_SIZE, MMU_PAGE_1G);
 			fixup_tlbie();
 			asm volatile("eieio; tlbsync; ptesync": : :"memory");
+		} else {
+			_tlbiel_va_range_multicast(mm,
+					start, end, pid, page_size, mmu_virtual_psize, false);
+			if (hflush)
+				_tlbiel_va_range_multicast(mm,
+					hstart, hend, pid, PMD_SIZE, MMU_PAGE_2M, false);
+			if (gflush)
+				_tlbiel_va_range_multicast(mm,
+					gstart, gend, pid, PUD_SIZE, MMU_PAGE_1G, false);
 		}
 	}
 	preempt_enable();
@@ -835,32 +925,19 @@ EXPORT_SYMBOL_GPL(radix__flush_pwc_lpid);
 /*
  * Flush partition scoped translations from LPID (=LPIDR)
  */
-void radix__flush_tlb_lpid(unsigned int lpid)
+void radix__flush_all_lpid(unsigned int lpid)
 {
 	_tlbie_lpid(lpid, RIC_FLUSH_ALL);
 }
-EXPORT_SYMBOL_GPL(radix__flush_tlb_lpid);
+EXPORT_SYMBOL_GPL(radix__flush_all_lpid);
 
 /*
- * Flush partition scoped translations from LPID (=LPIDR)
+ * Flush process scoped translations from LPID (=LPIDR)
  */
-void radix__local_flush_tlb_lpid(unsigned int lpid)
+void radix__flush_all_lpid_guest(unsigned int lpid)
 {
-	_tlbiel_lpid(lpid, RIC_FLUSH_ALL);
+	_tlbie_lpid_guest(lpid, RIC_FLUSH_ALL);
 }
-EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid);
-
-/*
- * Flush process scoped translations from LPID (=LPIDR).
- * Important difference, the guest normally manages its own translations,
- * but some cases e.g., vCPU CPU migration require KVM to flush.
- */
-void radix__local_flush_tlb_lpid_guest(unsigned int lpid)
-{
-	_tlbiel_lpid_guest(lpid, RIC_FLUSH_ALL);
-}
-EXPORT_SYMBOL_GPL(radix__local_flush_tlb_lpid_guest);
-
 
 static void radix__flush_tlb_pwc_range_psize(struct mm_struct *mm, unsigned long start,
 				  unsigned long end, int psize);
@@ -966,16 +1043,26 @@ is_local:
 		if (local) {
 			_tlbiel_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		} else {
-			if (mm_needs_flush_escalation(mm))
-				also_pwc = true;
+			if (cputlb_use_tlbie()) {
+				if (mm_needs_flush_escalation(mm))
+					also_pwc = true;
+
+				_tlbie_pid(pid,
+					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
+			} else {
+				_tlbiel_pid_multicast(mm, pid,
+					also_pwc ?  RIC_FLUSH_ALL : RIC_FLUSH_TLB);
+			}
 
-			_tlbie_pid(pid, also_pwc ? RIC_FLUSH_ALL : RIC_FLUSH_TLB);
 		}
 	} else {
 		if (local)
 			_tlbiel_va_range(start, end, pid, page_size, psize, also_pwc);
-		else
+		else if (cputlb_use_tlbie())
 			_tlbie_va_range(start, end, pid, page_size, psize, also_pwc);
+		else
+			_tlbiel_va_range_multicast(mm,
+					start, end, pid, page_size, psize, also_pwc);
 	}
 	preempt_enable();
 }
@@ -1017,7 +1104,11 @@ void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr)
 			exit_flush_lazy_tlbs(mm);
 			goto local;
 		}
-		_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
+		if (cputlb_use_tlbie())
+			_tlbie_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
+		else
+			_tlbiel_va_range_multicast(mm,
+					addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
 	} else {
 local:
 		_tlbiel_va_range(addr, end, pid, PAGE_SIZE, mmu_virtual_psize, true);
diff --git a/arch/powerpc/mm/dma-noncoherent.c b/arch/powerpc/mm/dma-noncoherent.c
index c617282d5b2a..2a82984356f8 100644
--- a/arch/powerpc/mm/dma-noncoherent.c
+++ b/arch/powerpc/mm/dma-noncoherent.c
@@ -4,310 +4,18 @@
  *    Copyright (C) 2001 Dan Malek (dmalek@jlc.net)
  *
  *  Copyright (C) 2000 Russell King
- *
- * Consistent memory allocators.  Used for DMA devices that want to
- * share uncached memory with the processor core.  The function return
- * is the virtual address and 'dma_handle' is the physical address.
- * Mostly stolen from the ARM port, with some changes for PowerPC.
- *						-- Dan
- *
- * Reorganized to get rid of the arch-specific consistent_* functions
- * and provide non-coherent implementations for the DMA API. -Matt
- *
- * Added in_interrupt() safe dma_alloc_coherent()/dma_free_coherent()
- * implementation. This is pulled straight from ARM and barely
- * modified. -Matt
  */
 
-#include <linux/sched.h>
-#include <linux/slab.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
-#include <linux/string.h>
 #include <linux/types.h>
 #include <linux/highmem.h>
 #include <linux/dma-direct.h>
 #include <linux/dma-noncoherent.h>
-#include <linux/export.h>
 
 #include <asm/tlbflush.h>
 #include <asm/dma.h>
 
-#include <mm/mmu_decl.h>
-
-/*
- * This address range defaults to a value that is safe for all
- * platforms which currently set CONFIG_NOT_COHERENT_CACHE. It
- * can be further configured for specific applications under
- * the "Advanced Setup" menu. -Matt
- */
-#define CONSISTENT_BASE		(IOREMAP_TOP)
-#define CONSISTENT_END 		(CONSISTENT_BASE + CONFIG_CONSISTENT_SIZE)
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-
-/*
- * This is the page table (2MB) covering uncached, DMA consistent allocations
- */
-static DEFINE_SPINLOCK(consistent_lock);
-
-/*
- * VM region handling support.
- *
- * This should become something generic, handling VM region allocations for
- * vmalloc and similar (ioremap, module space, etc).
- *
- * I envisage vmalloc()'s supporting vm_struct becoming:
- *
- *  struct vm_struct {
- *    struct vm_region	region;
- *    unsigned long	flags;
- *    struct page	**pages;
- *    unsigned int	nr_pages;
- *    unsigned long	phys_addr;
- *  };
- *
- * get_vm_area() would then call vm_region_alloc with an appropriate
- * struct vm_region head (eg):
- *
- *  struct vm_region vmalloc_head = {
- *	.vm_list	= LIST_HEAD_INIT(vmalloc_head.vm_list),
- *	.vm_start	= VMALLOC_START,
- *	.vm_end		= VMALLOC_END,
- *  };
- *
- * However, vmalloc_head.vm_start is variable (typically, it is dependent on
- * the amount of RAM found at boot time.)  I would imagine that get_vm_area()
- * would have to initialise this each time prior to calling vm_region_alloc().
- */
-struct ppc_vm_region {
-	struct list_head	vm_list;
-	unsigned long		vm_start;
-	unsigned long		vm_end;
-};
-
-static struct ppc_vm_region consistent_head = {
-	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_start	= CONSISTENT_BASE,
-	.vm_end		= CONSISTENT_END,
-};
-
-static struct ppc_vm_region *
-ppc_vm_region_alloc(struct ppc_vm_region *head, size_t size, gfp_t gfp)
-{
-	unsigned long addr = head->vm_start, end = head->vm_end - size;
-	unsigned long flags;
-	struct ppc_vm_region *c, *new;
-
-	new = kmalloc(sizeof(struct ppc_vm_region), gfp);
-	if (!new)
-		goto out;
-
-	spin_lock_irqsave(&consistent_lock, flags);
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if ((addr + size) < addr)
-			goto nospc;
-		if ((addr + size) <= c->vm_start)
-			goto found;
-		addr = c->vm_end;
-		if (addr > end)
-			goto nospc;
-	}
-
- found:
-	/*
-	 * Insert this entry _before_ the one we found.
-	 */
-	list_add_tail(&new->vm_list, &c->vm_list);
-	new->vm_start = addr;
-	new->vm_end = addr + size;
-
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	return new;
-
- nospc:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	kfree(new);
- out:
-	return NULL;
-}
-
-static struct ppc_vm_region *ppc_vm_region_find(struct ppc_vm_region *head, unsigned long addr)
-{
-	struct ppc_vm_region *c;
-
-	list_for_each_entry(c, &head->vm_list, vm_list) {
-		if (c->vm_start == addr)
-			goto out;
-	}
-	c = NULL;
- out:
-	return c;
-}
-
-/*
- * Allocate DMA-coherent memory space and return both the kernel remapped
- * virtual and bus address for that space.
- */
-void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp, unsigned long attrs)
-{
-	struct page *page;
-	struct ppc_vm_region *c;
-	unsigned long order;
-	u64 mask = ISA_DMA_THRESHOLD, limit;
-
-	if (dev) {
-		mask = dev->coherent_dma_mask;
-
-		/*
-		 * Sanity check the DMA mask - it must be non-zero, and
-		 * must be able to be satisfied by a DMA allocation.
-		 */
-		if (mask == 0) {
-			dev_warn(dev, "coherent DMA mask is unset\n");
-			goto no_page;
-		}
-
-		if ((~mask) & ISA_DMA_THRESHOLD) {
-			dev_warn(dev, "coherent DMA mask %#llx is smaller "
-				 "than system GFP_DMA mask %#llx\n",
-				 mask, (unsigned long long)ISA_DMA_THRESHOLD);
-			goto no_page;
-		}
-	}
-
-
-	size = PAGE_ALIGN(size);
-	limit = (mask + 1) & ~mask;
-	if ((limit && size >= limit) ||
-	    size >= (CONSISTENT_END - CONSISTENT_BASE)) {
-		printk(KERN_WARNING "coherent allocation too big (requested %#x mask %#Lx)\n",
-		       size, mask);
-		return NULL;
-	}
-
-	order = get_order(size);
-
-	/* Might be useful if we ever have a real legacy DMA zone... */
-	if (mask != 0xffffffff)
-		gfp |= GFP_DMA;
-
-	page = alloc_pages(gfp, order);
-	if (!page)
-		goto no_page;
-
-	/*
-	 * Invalidate any data that might be lurking in the
-	 * kernel direct-mapped region for device DMA.
-	 */
-	{
-		unsigned long kaddr = (unsigned long)page_address(page);
-		memset(page_address(page), 0, size);
-		flush_dcache_range(kaddr, kaddr + size);
-	}
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = ppc_vm_region_alloc(&consistent_head, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM));
-	if (c) {
-		unsigned long vaddr = c->vm_start;
-		struct page *end = page + (1 << order);
-
-		split_page(page, order);
-
-		/*
-		 * Set the "dma handle"
-		 */
-		*dma_handle = phys_to_dma(dev, page_to_phys(page));
-
-		do {
-			SetPageReserved(page);
-			map_kernel_page(vaddr, page_to_phys(page),
-					pgprot_noncached(PAGE_KERNEL));
-			page++;
-			vaddr += PAGE_SIZE;
-		} while (size -= PAGE_SIZE);
-
-		/*
-		 * Free the otherwise unused pages.
-		 */
-		while (page < end) {
-			__free_page(page);
-			page++;
-		}
-
-		return (void *)c->vm_start;
-	}
-
-	if (page)
-		__free_pages(page, order);
- no_page:
-	return NULL;
-}
-
-/*
- * free a page as defined by the above mapping.
- */
-void arch_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t dma_handle, unsigned long attrs)
-{
-	struct ppc_vm_region *c;
-	unsigned long flags, addr;
-	
-	size = PAGE_ALIGN(size);
-
-	spin_lock_irqsave(&consistent_lock, flags);
-
-	c = ppc_vm_region_find(&consistent_head, (unsigned long)vaddr);
-	if (!c)
-		goto no_area;
-
-	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
-	}
-
-	addr = c->vm_start;
-	do {
-		pte_t *ptep;
-		unsigned long pfn;
-
-		ptep = pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(addr),
-							       addr),
-						    addr),
-					 addr);
-		if (!pte_none(*ptep) && pte_present(*ptep)) {
-			pfn = pte_pfn(*ptep);
-			pte_clear(&init_mm, addr, ptep);
-			if (pfn_valid(pfn)) {
-				struct page *page = pfn_to_page(pfn);
-				__free_reserved_page(page);
-			}
-		}
-		addr += PAGE_SIZE;
-	} while (size -= PAGE_SIZE);
-
-	flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
-	list_del(&c->vm_list);
-
-	spin_unlock_irqrestore(&consistent_lock, flags);
-
-	kfree(c);
-	return;
-
- no_area:
-	spin_unlock_irqrestore(&consistent_lock, flags);
-	printk(KERN_ERR "%s: trying to free invalid coherent area: %p\n",
-	       __func__, vaddr);
-	dump_stack();
-}
-
 /*
  * make an area consistent.
  */
@@ -408,23 +116,9 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 	__dma_sync_page(paddr, size, dir);
 }
 
-/*
- * Return the PFN for a given cpu virtual address returned by arch_dma_alloc.
- */
-long arch_dma_coherent_to_pfn(struct device *dev, void *vaddr,
-		dma_addr_t dma_addr)
+void arch_dma_prep_coherent(struct page *page, size_t size)
 {
-	/* This should always be populated, so we don't test every
-	 * level. If that fails, we'll have a nice crash which
-	 * will be as good as a BUG_ON()
-	 */
-	unsigned long cpu_addr = (unsigned long)vaddr;
-	pgd_t *pgd = pgd_offset_k(cpu_addr);
-	pud_t *pud = pud_offset(pgd, cpu_addr);
-	pmd_t *pmd = pmd_offset(pud, cpu_addr);
-	pte_t *ptep = pte_offset_kernel(pmd, cpu_addr);
+	unsigned long kaddr = (unsigned long)page_address(page);
 
-	if (pte_none(*ptep) || !pte_present(*ptep))
-		return 0;
-	return pte_pfn(*ptep);
+	flush_dcache_range(kaddr, kaddr + size);
 }
diff --git a/arch/powerpc/mm/ioremap.c b/arch/powerpc/mm/ioremap.c
new file mode 100644
index 000000000000..fc669643ce6a
--- /dev/null
+++ b/arch/powerpc/mm/ioremap.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <asm/io-workarounds.h>
+
+unsigned long ioremap_bot;
+EXPORT_SYMBOL(ioremap_bot);
+
+void __iomem *ioremap(phys_addr_t addr, unsigned long size)
+{
+	pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
+	void *caller = __builtin_return_address(0);
+
+	if (iowa_is_active())
+		return iowa_ioremap(addr, size, prot, caller);
+	return __ioremap_caller(addr, size, prot, caller);
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_wc(phys_addr_t addr, unsigned long size)
+{
+	pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
+	void *caller = __builtin_return_address(0);
+
+	if (iowa_is_active())
+		return iowa_ioremap(addr, size, prot, caller);
+	return __ioremap_caller(addr, size, prot, caller);
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
+{
+	pgprot_t prot = pgprot_cached(PAGE_KERNEL);
+	void *caller = __builtin_return_address(0);
+
+	if (iowa_is_active())
+		return iowa_ioremap(addr, size, prot, caller);
+	return __ioremap_caller(addr, size, prot, caller);
+}
+
+void __iomem *ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
+{
+	pte_t pte = __pte(flags);
+	void *caller = __builtin_return_address(0);
+
+	/* writeable implies dirty for kernel addresses */
+	if (pte_write(pte))
+		pte = pte_mkdirty(pte);
+
+	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
+	pte = pte_exprotect(pte);
+	pte = pte_mkprivileged(pte);
+
+	if (iowa_is_active())
+		return iowa_ioremap(addr, size, pte_pgprot(pte), caller);
+	return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
+}
+EXPORT_SYMBOL(ioremap_prot);
+
+int early_ioremap_range(unsigned long ea, phys_addr_t pa,
+			unsigned long size, pgprot_t prot)
+{
+	unsigned long i;
+
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		int err = map_kernel_page(ea + i, pa + i, prot);
+
+		if (WARN_ON_ONCE(err))  /* Should clean up */
+			return err;
+	}
+
+	return 0;
+}
+
+void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
+			 pgprot_t prot, void *caller)
+{
+	struct vm_struct *area;
+	int ret;
+	unsigned long va;
+
+	area = __get_vm_area_caller(size, VM_IOREMAP, IOREMAP_START, IOREMAP_END, caller);
+	if (area == NULL)
+		return NULL;
+
+	area->phys_addr = pa;
+	va = (unsigned long)area->addr;
+
+	ret = ioremap_page_range(va, va + size, pa, prot);
+	if (!ret)
+		return (void __iomem *)area->addr + offset;
+
+	unmap_kernel_range(va, size);
+	free_vm_area(area);
+
+	return NULL;
+}
diff --git a/arch/powerpc/mm/ioremap_32.c b/arch/powerpc/mm/ioremap_32.c
new file mode 100644
index 000000000000..f36121f25243
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_32.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include <mm/mmu_decl.h>
+
+void __iomem *ioremap_wt(phys_addr_t addr, unsigned long size)
+{
+	pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
+
+	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wt);
+
+void __iomem *
+__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
+{
+	unsigned long v;
+	phys_addr_t p, offset;
+	int err;
+
+	/*
+	 * Choose an address to map it to.
+	 * Once the vmalloc system is running, we use it.
+	 * Before then, we use space going down from IOREMAP_TOP
+	 * (ioremap_bot records where we're up to).
+	 */
+	p = addr & PAGE_MASK;
+	offset = addr & ~PAGE_MASK;
+	size = PAGE_ALIGN(addr + size) - p;
+
+	/*
+	 * If the address lies within the first 16 MB, assume it's in ISA
+	 * memory space
+	 */
+	if (p < 16 * 1024 * 1024)
+		p += _ISA_MEM_BASE;
+
+#ifndef CONFIG_CRASH_DUMP
+	/*
+	 * Don't allow anybody to remap normal RAM that we're using.
+	 * mem_init() sets high_memory so only do the check after that.
+	 */
+	if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
+	    page_is_ram(__phys_to_pfn(p))) {
+		pr_warn("%s(): phys addr 0x%llx is RAM lr %ps\n", __func__,
+			(unsigned long long)p, __builtin_return_address(0));
+		return NULL;
+	}
+#endif
+
+	if (size == 0)
+		return NULL;
+
+	/*
+	 * Is it already mapped?  Perhaps overlapped by a previous
+	 * mapping.
+	 */
+	v = p_block_mapped(p);
+	if (v)
+		return (void __iomem *)v + offset;
+
+	if (slab_is_available())
+		return do_ioremap(p, offset, size, prot, caller);
+
+	/*
+	 * Should check if it is a candidate for a BAT mapping
+	 */
+
+	err = early_ioremap_range(ioremap_bot - size, p, size, prot);
+	if (err)
+		return NULL;
+	ioremap_bot -= size;
+
+	return (void __iomem *)ioremap_bot + offset;
+}
+
+void iounmap(volatile void __iomem *addr)
+{
+	/*
+	 * If mapped by BATs then there is nothing to do.
+	 * Calling vfree() generates a benign warning.
+	 */
+	if (v_block_mapped((unsigned long)addr))
+		return;
+
+	if (addr > high_memory && (unsigned long)addr < ioremap_bot)
+		vunmap((void *)(PAGE_MASK & (unsigned long)addr));
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
new file mode 100644
index 000000000000..fd29e51700cd
--- /dev/null
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/**
+ * Low level function to establish the page tables for an IO mapping
+ */
+void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
+{
+	int ret;
+	unsigned long va = (unsigned long)ea;
+
+	/* We don't support the 4K PFN hack with ioremap */
+	if (pgprot_val(prot) & H_PAGE_4K_PFN)
+		return NULL;
+
+	if ((ea + size) >= (void *)IOREMAP_END) {
+		pr_warn("Outside the supported range\n");
+		return NULL;
+	}
+
+	WARN_ON(pa & ~PAGE_MASK);
+	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+	WARN_ON(size & ~PAGE_MASK);
+
+	if (slab_is_available()) {
+		ret = ioremap_page_range(va, va + size, pa, prot);
+		if (ret)
+			unmap_kernel_range(va, size);
+	} else {
+		ret = early_ioremap_range(va, pa, size, prot);
+	}
+
+	if (ret)
+		return NULL;
+
+	return (void __iomem *)ea;
+}
+EXPORT_SYMBOL(__ioremap_at);
+
+/**
+ * Low level function to tear down the page tables for an IO mapping. This is
+ * used for mappings that are manipulated manually, like partial unmapping of
+ * PCI IOs or ISA space.
+ */
+void __iounmap_at(void *ea, unsigned long size)
+{
+	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
+	WARN_ON(size & ~PAGE_MASK);
+
+	unmap_kernel_range((unsigned long)ea, size);
+}
+EXPORT_SYMBOL(__iounmap_at);
+
+void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
+			       pgprot_t prot, void *caller)
+{
+	phys_addr_t paligned, offset;
+	void __iomem *ret;
+	int err;
+
+	/* We don't support the 4K PFN hack with ioremap */
+	if (pgprot_val(prot) & H_PAGE_4K_PFN)
+		return NULL;
+
+	/*
+	 * Choose an address to map it to. Once the vmalloc system is running,
+	 * we use it. Before that, we map using addresses going up from
+	 * ioremap_bot.  vmalloc will use the addresses from IOREMAP_BASE
+	 * through ioremap_bot.
+	 */
+	paligned = addr & PAGE_MASK;
+	offset = addr & ~PAGE_MASK;
+	size = PAGE_ALIGN(addr + size) - paligned;
+
+	if (size == 0 || paligned == 0)
+		return NULL;
+
+	if (slab_is_available())
+		return do_ioremap(paligned, offset, size, prot, caller);
+
+	err = early_ioremap_range(ioremap_bot, paligned, size, prot);
+	if (err)
+		return NULL;
+
+	ret = (void __iomem *)ioremap_bot + offset;
+	ioremap_bot += size;
+
+	return ret;
+}
+
+/*
+ * Unmap an IO region and remove it from vmalloc'd list.
+ * Access to IO memory should be serialized by driver.
+ */
+void iounmap(volatile void __iomem *token)
+{
+	void *addr;
+
+	if (!slab_is_available())
+		return;
+
+	addr = (void *)((unsigned long __force)PCI_FIX_ADDR(token) & PAGE_MASK);
+
+	if ((unsigned long)addr < ioremap_bot) {
+		pr_warn("Attempt to iounmap early bolted mapping at 0x%p\n", addr);
+		return;
+	}
+	vunmap(addr);
+}
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/powerpc/mm/kasan/kasan_init_32.c b/arch/powerpc/mm/kasan/kasan_init_32.c
index 74f4555a62ba..802387b231ad 100644
--- a/arch/powerpc/mm/kasan/kasan_init_32.c
+++ b/arch/powerpc/mm/kasan/kasan_init_32.c
@@ -5,6 +5,7 @@
 #include <linux/kasan.h>
 #include <linux/printk.h>
 #include <linux/memblock.h>
+#include <linux/moduleloader.h>
 #include <linux/sched/task.h>
 #include <linux/vmalloc.h>
 #include <asm/pgalloc.h>
@@ -46,7 +47,19 @@ static int __ref kasan_init_shadow_page_tables(unsigned long k_start, unsigned l
 			kasan_populate_pte(new, PAGE_READONLY);
 		else
 			kasan_populate_pte(new, PAGE_KERNEL_RO);
-		pmd_populate_kernel(&init_mm, pmd, new);
+
+		smp_wmb(); /* See comment in __pte_alloc */
+
+		spin_lock(&init_mm.page_table_lock);
+			/* Has another populated it ? */
+		if (likely((void *)pmd_page_vaddr(*pmd) == kasan_early_shadow_pte)) {
+			pmd_populate_kernel(&init_mm, pmd, new);
+			new = NULL;
+		}
+		spin_unlock(&init_mm.page_table_lock);
+
+		if (new && slab_is_available())
+			pte_free_kernel(&init_mm, new);
 	}
 	return 0;
 }
@@ -74,7 +87,7 @@ static int __ref kasan_init_region(void *start, size_t size)
 	if (!slab_is_available())
 		block = memblock_alloc(k_end - k_start, PAGE_SIZE);
 
-	for (k_cur = k_start; k_cur < k_end; k_cur += PAGE_SIZE) {
+	for (k_cur = k_start & PAGE_MASK; k_cur < k_end; k_cur += PAGE_SIZE) {
 		pmd_t *pmd = pmd_offset(pud_offset(pgd_offset_k(k_cur), k_cur), k_cur);
 		void *va = block ? block + k_cur - k_start : kasan_get_one_page();
 		pte_t pte = pfn_pte(PHYS_PFN(__pa(va)), PAGE_KERNEL);
@@ -137,7 +150,11 @@ void __init kasan_init(void)
 #ifdef CONFIG_MODULES
 void *module_alloc(unsigned long size)
 {
-	void *base = vmalloc_exec(size);
+	void *base;
+
+	base = __vmalloc_node_range(size, MODULE_ALIGN, VMALLOC_START, VMALLOC_END,
+				    GFP_KERNEL, PAGE_KERNEL_EXEC, VM_FLUSH_RESET_PERMS,
+				    NUMA_NO_NODE, __builtin_return_address(0));
 
 	if (!base)
 		return NULL;
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9191a66b3bc5..be941d382c8d 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -302,12 +302,9 @@ void __init mem_init(void)
 	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
 		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
 #endif /* CONFIG_HIGHMEM */
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	pr_info("  * 0x%08lx..0x%08lx  : consistent mem\n",
-		IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
-#endif /* CONFIG_NOT_COHERENT_CACHE */
-	pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
-		ioremap_bot, IOREMAP_TOP);
+	if (ioremap_bot != IOREMAP_TOP)
+		pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
+			ioremap_bot, IOREMAP_TOP);
 	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
 		VMALLOC_START, VMALLOC_END);
 #endif /* CONFIG_PPC32 */
@@ -407,63 +404,6 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 EXPORT_SYMBOL(flush_icache_user_range);
 
 /*
- * This is called at the end of handling a user page fault, when the
- * fault has been handled by updating a PTE in the linux page tables.
- * We use it to preload an HPTE into the hash table corresponding to
- * the updated linux PTE.
- * 
- * This must always be called with the pte lock held.
- */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
-		      pte_t *ptep)
-{
-#ifdef CONFIG_PPC_BOOK3S
-	/*
-	 * We don't need to worry about _PAGE_PRESENT here because we are
-	 * called with either mm->page_table_lock held or ptl lock held
-	 */
-	unsigned long trap;
-	bool is_exec;
-
-	if (radix_enabled()) {
-		prefetch((void *)address);
-		return;
-	}
-
-	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
-	if (!pte_young(*ptep) || address >= TASK_SIZE)
-		return;
-
-	/* We try to figure out if we are coming from an instruction
-	 * access fault and pass that down to __hash_page so we avoid
-	 * double-faulting on execution of fresh text. We have to test
-	 * for regs NULL since init will get here first thing at boot
-	 *
-	 * We also avoid filling the hash if not coming from a fault
-	 */
-
-	trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
-	switch (trap) {
-	case 0x300:
-		is_exec = false;
-		break;
-	case 0x400:
-		is_exec = true;
-		break;
-	default:
-		return;
-	}
-
-	hash_preload(vma->vm_mm, address, is_exec, trap);
-#endif /* CONFIG_PPC_BOOK3S */
-#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
-	&& defined(CONFIG_HUGETLB_PAGE)
-	if (is_vm_hugetlb_page(vma))
-		book3e_hugetlb_preload(vma, address, *ptep);
-#endif
-}
-
-/*
  * System memory should not be in /proc/iomem but various tools expect it
  * (eg kdump).
  */
diff --git a/arch/powerpc/mm/mmu_decl.h b/arch/powerpc/mm/mmu_decl.h
index 32c1a191c28a..c750ac9ec713 100644
--- a/arch/powerpc/mm/mmu_decl.h
+++ b/arch/powerpc/mm/mmu_decl.h
@@ -82,10 +82,6 @@ static inline void print_system_hash_info(void) {}
 
 #else /* CONFIG_PPC_MMU_NOHASH */
 
-extern void hash_preload(struct mm_struct *mm, unsigned long ea,
-			 bool is_exec, unsigned long trap);
-
-
 extern void _tlbie(unsigned long address);
 extern void _tlbia(void);
 
@@ -95,6 +91,8 @@ void print_system_hash_info(void);
 
 #ifdef CONFIG_PPC32
 
+void hash_preload(struct mm_struct *mm, unsigned long ea);
+
 extern void mapin_ram(void);
 extern void setbat(int index, unsigned long virt, phys_addr_t phys,
 		   unsigned int size, pgprot_t prot);
@@ -108,7 +106,6 @@ extern u8 early_hash[];
 
 #endif /* CONFIG_PPC32 */
 
-extern unsigned long ioremap_bot;
 extern unsigned long __max_low_memory;
 extern phys_addr_t __initial_memory_limit_addr;
 extern phys_addr_t total_memory;
diff --git a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c
index 61915f4d3c7f..8b88be91b622 100644
--- a/arch/powerpc/mm/nohash/book3e_hugetlbpage.c
+++ b/arch/powerpc/mm/nohash/book3e_hugetlbpage.c
@@ -122,8 +122,8 @@ static inline int book3e_tlb_exists(unsigned long ea, unsigned long pid)
 	return found;
 }
 
-void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
-			    pte_t pte)
+static void
+book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea, pte_t pte)
 {
 	unsigned long mas1, mas2;
 	u64 mas7_3;
@@ -183,6 +183,18 @@ void book3e_hugetlb_preload(struct vm_area_struct *vma, unsigned long ea,
 	local_irq_restore(flags);
 }
 
+/*
+ * This is called at the end of handling a user page fault, when the
+ * fault has been handled by updating a PTE in the linux page tables.
+ *
+ * This must always be called with the pte lock held.
+ */
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+{
+	if (is_vm_hugetlb_page(vma))
+		book3e_hugetlb_preload(vma, address, *ptep);
+}
+
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr)
 {
 	struct hstate *hstate = hstate_file(vma->vm_file);
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index bf60983a58c7..696f568253a0 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -703,6 +703,8 @@ static void __init early_init_mmu_global(void)
 	 * for use by the TLB miss code
 	 */
 	linear_map_top = memblock_end_of_DRAM();
+
+	ioremap_bot = IOREMAP_BASE;
 }
 
 static void __init early_mmu_set_memory_limit(void)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 35cb96cfc258..8ec5dfb65b2e 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -27,166 +27,13 @@
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/fixmap.h>
-#include <asm/io.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 
 #include <mm/mmu_decl.h>
 
-unsigned long ioremap_bot;
-EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
-
 extern char etext[], _stext[], _sinittext[], _einittext[];
 
-void __iomem *
-ioremap(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
-
-	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap);
-
-void __iomem *
-ioremap_wc(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
-
-	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_wc);
-
-void __iomem *
-ioremap_wt(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_cached_wthru(PAGE_KERNEL);
-
-	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_wt);
-
-void __iomem *
-ioremap_coherent(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_cached(PAGE_KERNEL);
-
-	return __ioremap_caller(addr, size, prot, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_coherent);
-
-void __iomem *
-ioremap_prot(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
-	pte_t pte = __pte(flags);
-
-	/* writeable implies dirty for kernel addresses */
-	if (pte_write(pte))
-		pte = pte_mkdirty(pte);
-
-	/* we don't want to let _PAGE_USER and _PAGE_EXEC leak out */
-	pte = pte_exprotect(pte);
-	pte = pte_mkprivileged(pte);
-
-	return __ioremap_caller(addr, size, pte_pgprot(pte), __builtin_return_address(0));
-}
-EXPORT_SYMBOL(ioremap_prot);
-
-void __iomem *
-__ioremap(phys_addr_t addr, unsigned long size, unsigned long flags)
-{
-	return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0));
-}
-
-void __iomem *
-__ioremap_caller(phys_addr_t addr, unsigned long size, pgprot_t prot, void *caller)
-{
-	unsigned long v, i;
-	phys_addr_t p;
-	int err;
-
-	/*
-	 * Choose an address to map it to.
-	 * Once the vmalloc system is running, we use it.
-	 * Before then, we use space going down from IOREMAP_TOP
-	 * (ioremap_bot records where we're up to).
-	 */
-	p = addr & PAGE_MASK;
-	size = PAGE_ALIGN(addr + size) - p;
-
-	/*
-	 * If the address lies within the first 16 MB, assume it's in ISA
-	 * memory space
-	 */
-	if (p < 16*1024*1024)
-		p += _ISA_MEM_BASE;
-
-#ifndef CONFIG_CRASH_DUMP
-	/*
-	 * Don't allow anybody to remap normal RAM that we're using.
-	 * mem_init() sets high_memory so only do the check after that.
-	 */
-	if (slab_is_available() && p <= virt_to_phys(high_memory - 1) &&
-	    page_is_ram(__phys_to_pfn(p))) {
-		printk("__ioremap(): phys addr 0x%llx is RAM lr %ps\n",
-		       (unsigned long long)p, __builtin_return_address(0));
-		return NULL;
-	}
-#endif
-
-	if (size == 0)
-		return NULL;
-
-	/*
-	 * Is it already mapped?  Perhaps overlapped by a previous
-	 * mapping.
-	 */
-	v = p_block_mapped(p);
-	if (v)
-		goto out;
-
-	if (slab_is_available()) {
-		struct vm_struct *area;
-		area = get_vm_area_caller(size, VM_IOREMAP, caller);
-		if (area == 0)
-			return NULL;
-		area->phys_addr = p;
-		v = (unsigned long) area->addr;
-	} else {
-		v = (ioremap_bot -= size);
-	}
-
-	/*
-	 * Should check if it is a candidate for a BAT mapping
-	 */
-
-	err = 0;
-	for (i = 0; i < size && err == 0; i += PAGE_SIZE)
-		err = map_kernel_page(v + i, p + i, prot);
-	if (err) {
-		if (slab_is_available())
-			vunmap((void *)v);
-		return NULL;
-	}
-
-out:
-	return (void __iomem *) (v + ((unsigned long)addr & ~PAGE_MASK));
-}
-EXPORT_SYMBOL(__ioremap);
-
-void iounmap(volatile void __iomem *addr)
-{
-	/*
-	 * If mapped by BATs then there is nothing to do.
-	 * Calling vfree() generates a benign warning.
-	 */
-	if (v_block_mapped((unsigned long)addr))
-		return;
-
-	if (addr > high_memory && (unsigned long) addr < ioremap_bot)
-		vunmap((void *) (PAGE_MASK & (unsigned long)addr));
-}
-EXPORT_SYMBOL(iounmap);
-
 static void __init *early_alloc_pgtable(unsigned long size)
 {
 	void *ptr = memblock_alloc(size, size);
@@ -252,7 +99,7 @@ static void __init __mapin_ram_chunk(unsigned long offset, unsigned long top)
 		map_kernel_page(v, p, ktext ? PAGE_KERNEL_TEXT : PAGE_KERNEL);
 #ifdef CONFIG_PPC_BOOK3S_32
 		if (ktext)
-			hash_preload(&init_mm, v, false, 0x300);
+			hash_preload(&init_mm, v);
 #endif
 		v += PAGE_SIZE;
 		p += PAGE_SIZE;
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 9ad59b733984..e78832dce7bb 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
- *  This file contains ioremap and related functions for 64-bit machines.
+ *  This file contains pgtable related functions for 64-bit machines.
  *
  *  Derived from arch/ppc64/mm/init.c
  *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
@@ -34,7 +34,6 @@
 #include <asm/pgalloc.h>
 #include <asm/page.h>
 #include <asm/prom.h>
-#include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/pgtable.h>
 #include <asm/mmu.h>
@@ -98,208 +97,8 @@ unsigned long __pte_frag_nr;
 EXPORT_SYMBOL(__pte_frag_nr);
 unsigned long __pte_frag_size_shift;
 EXPORT_SYMBOL(__pte_frag_size_shift);
-unsigned long ioremap_bot;
-#else /* !CONFIG_PPC_BOOK3S_64 */
-unsigned long ioremap_bot = IOREMAP_BASE;
 #endif
 
-int __weak ioremap_range(unsigned long ea, phys_addr_t pa, unsigned long size, pgprot_t prot, int nid)
-{
-	unsigned long i;
-
-	for (i = 0; i < size; i += PAGE_SIZE) {
-		int err = map_kernel_page(ea + i, pa + i, prot);
-		if (err) {
-			if (slab_is_available())
-				unmap_kernel_range(ea, size);
-			else
-				WARN_ON_ONCE(1); /* Should clean up */
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-/**
- * __ioremap_at - Low level function to establish the page tables
- *                for an IO mapping
- */
-void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
-{
-	/* We don't support the 4K PFN hack with ioremap */
-	if (pgprot_val(prot) & H_PAGE_4K_PFN)
-		return NULL;
-
-	if ((ea + size) >= (void *)IOREMAP_END) {
-		pr_warn("Outside the supported range\n");
-		return NULL;
-	}
-
-	WARN_ON(pa & ~PAGE_MASK);
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	if (ioremap_range((unsigned long)ea, pa, size, prot, NUMA_NO_NODE))
-		return NULL;
-
-	return (void __iomem *)ea;
-}
-
-/**
- * __iounmap_from - Low level function to tear down the page tables
- *                  for an IO mapping. This is used for mappings that
- *                  are manipulated manually, like partial unmapping of
- *                  PCI IOs or ISA space.
- */
-void __iounmap_at(void *ea, unsigned long size)
-{
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	unmap_kernel_range((unsigned long)ea, size);
-}
-
-void __iomem * __ioremap_caller(phys_addr_t addr, unsigned long size,
-				pgprot_t prot, void *caller)
-{
-	phys_addr_t paligned;
-	void __iomem *ret;
-
-	/*
-	 * Choose an address to map it to.
-	 * Once the imalloc system is running, we use it.
-	 * Before that, we map using addresses going
-	 * up from ioremap_bot.  imalloc will use
-	 * the addresses from ioremap_bot through
-	 * IMALLOC_END
-	 * 
-	 */
-	paligned = addr & PAGE_MASK;
-	size = PAGE_ALIGN(addr + size) - paligned;
-
-	if ((size == 0) || (paligned == 0))
-		return NULL;
-
-	if (slab_is_available()) {
-		struct vm_struct *area;
-
-		area = __get_vm_area_caller(size, VM_IOREMAP,
-					    ioremap_bot, IOREMAP_END,
-					    caller);
-		if (area == NULL)
-			return NULL;
-
-		area->phys_addr = paligned;
-		ret = __ioremap_at(paligned, area->addr, size, prot);
-	} else {
-		ret = __ioremap_at(paligned, (void *)ioremap_bot, size, prot);
-		if (ret)
-			ioremap_bot += size;
-	}
-
-	if (ret)
-		ret += addr & ~PAGE_MASK;
-	return ret;
-}
-
-void __iomem * __ioremap(phys_addr_t addr, unsigned long size,
-			 unsigned long flags)
-{
-	return __ioremap_caller(addr, size, __pgprot(flags), __builtin_return_address(0));
-}
-
-void __iomem * ioremap(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_noncached(PAGE_KERNEL);
-	void *caller = __builtin_return_address(0);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, prot, caller);
-	return __ioremap_caller(addr, size, prot, caller);
-}
-
-void __iomem * ioremap_wc(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_noncached_wc(PAGE_KERNEL);
-	void *caller = __builtin_return_address(0);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, prot, caller);
-	return __ioremap_caller(addr, size, prot, caller);
-}
-
-void __iomem *ioremap_coherent(phys_addr_t addr, unsigned long size)
-{
-	pgprot_t prot = pgprot_cached(PAGE_KERNEL);
-	void *caller = __builtin_return_address(0);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, prot, caller);
-	return __ioremap_caller(addr, size, prot, caller);
-}
-
-void __iomem * ioremap_prot(phys_addr_t addr, unsigned long size,
-			     unsigned long flags)
-{
-	pte_t pte = __pte(flags);
-	void *caller = __builtin_return_address(0);
-
-	/* writeable implies dirty for kernel addresses */
-	if (pte_write(pte))
-		pte = pte_mkdirty(pte);
-
-	/* we don't want to let _PAGE_EXEC leak out */
-	pte = pte_exprotect(pte);
-	/*
-	 * Force kernel mapping.
-	 */
-	pte = pte_mkprivileged(pte);
-
-	if (ppc_md.ioremap)
-		return ppc_md.ioremap(addr, size, pte_pgprot(pte), caller);
-	return __ioremap_caller(addr, size, pte_pgprot(pte), caller);
-}
-
-
-/*  
- * Unmap an IO region and remove it from imalloc'd list.
- * Access to IO memory should be serialized by driver.
- */
-void __iounmap(volatile void __iomem *token)
-{
-	void *addr;
-
-	if (!slab_is_available())
-		return;
-	
-	addr = (void *) ((unsigned long __force)
-			 PCI_FIX_ADDR(token) & PAGE_MASK);
-	if ((unsigned long)addr < ioremap_bot) {
-		printk(KERN_WARNING "Attempt to iounmap early bolted mapping"
-		       " at 0x%p\n", addr);
-		return;
-	}
-	vunmap(addr);
-}
-
-void iounmap(volatile void __iomem *token)
-{
-	if (ppc_md.iounmap)
-		ppc_md.iounmap(token);
-	else
-		__iounmap(token);
-}
-
-EXPORT_SYMBOL(ioremap);
-EXPORT_SYMBOL(ioremap_wc);
-EXPORT_SYMBOL(ioremap_prot);
-EXPORT_SYMBOL(__ioremap);
-EXPORT_SYMBOL(__ioremap_at);
-EXPORT_SYMBOL(iounmap);
-EXPORT_SYMBOL(__iounmap);
-EXPORT_SYMBOL(__iounmap_at);
-
 #ifndef __PAGETABLE_PUD_FOLDED
 /* 4 level page table */
 struct page *pgd_page(pgd_t pgd)
diff --git a/arch/powerpc/mm/ptdump/bats.c b/arch/powerpc/mm/ptdump/bats.c
index a0d23e96e841..4154feac1da3 100644
--- a/arch/powerpc/mm/ptdump/bats.c
+++ b/arch/powerpc/mm/ptdump/bats.c
@@ -149,7 +149,7 @@ static int bats_show_603(struct seq_file *m, void *v)
 
 static int bats_open(struct inode *inode, struct file *file)
 {
-	if (cpu_has_feature(CPU_FTR_601))
+	if (IS_ENABLED(CONFIG_PPC_BOOK3S_601))
 		return single_open(file, bats_show_601, NULL);
 
 	return single_open(file, bats_show_603, NULL);
diff --git a/arch/powerpc/mm/ptdump/hashpagetable.c b/arch/powerpc/mm/ptdump/hashpagetable.c
index 72f0e4a3d839..a07278027c6f 100644
--- a/arch/powerpc/mm/ptdump/hashpagetable.c
+++ b/arch/powerpc/mm/ptdump/hashpagetable.c
@@ -237,7 +237,6 @@ static int native_find(unsigned long ea, int psize, bool primary, u64 *v, u64
 	return -1;
 }
 
-#ifdef CONFIG_PPC_PSERIES
 static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *r)
 {
 	struct hash_pte ptes[4];
@@ -274,7 +273,6 @@ static int pseries_find(unsigned long ea, int psize, bool primary, u64 *v, u64 *
 	}
 	return -1;
 }
-#endif
 
 static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps,
 		unsigned long *lp_bits)
@@ -316,10 +314,9 @@ static void decode_r(int bps, unsigned long r, unsigned long *rpn, int *aps,
 static int base_hpte_find(unsigned long ea, int psize, bool primary, u64 *v,
 			  u64 *r)
 {
-#ifdef CONFIG_PPC_PSERIES
-	if (firmware_has_feature(FW_FEATURE_LPAR))
+	if (IS_ENABLED(CONFIG_PPC_PSERIES) && firmware_has_feature(FW_FEATURE_LPAR))
 		return pseries_find(ea, psize, primary, v, r);
-#endif
+
 	return native_find(ea, psize, primary, v, r);
 }
 
@@ -386,12 +383,13 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
 			psize = mmu_vmalloc_psize;
 		else
 			psize = mmu_io_psize;
-#ifdef CONFIG_PPC_64K_PAGES
+
 		/* check for secret 4K mappings */
-		if (((pteval & H_PAGE_COMBO) == H_PAGE_COMBO) ||
-			((pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN))
+		if (IS_ENABLED(CONFIG_PPC_64K_PAGES) &&
+		    ((pteval & H_PAGE_COMBO) == H_PAGE_COMBO ||
+		     (pteval & H_PAGE_4K_PFN) == H_PAGE_4K_PFN))
 			psize = mmu_io_psize;
-#endif
+
 		/* check for hashpte */
 		status = hpte_find(st, addr, psize);
 
@@ -469,9 +467,10 @@ static void walk_linearmapping(struct pg_state *st)
 
 static void walk_vmemmap(struct pg_state *st)
 {
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
 	struct vmemmap_backing *ptr = vmemmap_list;
 
+	if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP))
+		return;
 	/*
 	 * Traverse the vmemmaped memory and dump pages that are in the hash
 	 * pagetable.
@@ -481,7 +480,6 @@ static void walk_vmemmap(struct pg_state *st)
 		ptr = ptr->list;
 	}
 	seq_puts(st->seq, "---[ vmemmap end ]---\n");
-#endif
 }
 
 static void populate_markers(void)
@@ -495,11 +493,7 @@ static void populate_markers(void)
 	address_markers[6].start_address = PHB_IO_END;
 	address_markers[7].start_address = IOREMAP_BASE;
 	address_markers[8].start_address = IOREMAP_END;
-#ifdef CONFIG_PPC_BOOK3S_64
 	address_markers[9].start_address =  H_VMEMMAP_START;
-#else
-	address_markers[9].start_address =  VMEMMAP_BASE;
-#endif
 }
 
 static int ptdump_show(struct seq_file *m, void *v)
diff --git a/arch/powerpc/mm/ptdump/ptdump.c b/arch/powerpc/mm/ptdump/ptdump.c
index 6a88a9f585d4..2f9ddc29c535 100644
--- a/arch/powerpc/mm/ptdump/ptdump.c
+++ b/arch/powerpc/mm/ptdump/ptdump.c
@@ -26,10 +26,6 @@
 
 #include "ptdump.h"
 
-#ifdef CONFIG_PPC32
-#define KERN_VIRT_START	PAGE_OFFSET
-#endif
-
 /*
  * To visualise what is happening,
  *
@@ -88,10 +84,6 @@ static struct addr_marker address_markers[] = {
 #else
 	{ 0,	"Early I/O remap start" },
 	{ 0,	"Early I/O remap end" },
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	{ 0,	"Consistent mem start" },
-	{ 0,	"Consistent mem end" },
-#endif
 #ifdef CONFIG_HIGHMEM
 	{ 0,	"Highmem PTEs start" },
 	{ 0,	"Highmem PTEs end" },
@@ -181,7 +173,7 @@ static void dump_addr(struct pg_state *st, unsigned long addr)
 
 static void note_prot_wx(struct pg_state *st, unsigned long addr)
 {
-	if (!st->check_wx)
+	if (!IS_ENABLED(CONFIG_PPC_DEBUG_WX) || !st->check_wx)
 		return;
 
 	if (!((st->current_flags & pgprot_val(PAGE_KERNEL_X)) == pgprot_val(PAGE_KERNEL_X)))
@@ -299,17 +291,15 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 
 static void walk_pagetables(struct pg_state *st)
 {
-	pgd_t *pgd = pgd_offset_k(0UL);
 	unsigned int i;
-	unsigned long addr;
-
-	addr = st->start_address;
+	unsigned long addr = st->start_address & PGDIR_MASK;
+	pgd_t *pgd = pgd_offset_k(addr);
 
 	/*
 	 * Traverse the linux pagetable structure and dump pages that are in
 	 * the hash pagetable.
 	 */
-	for (i = 0; i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
+	for (i = pgd_index(addr); i < PTRS_PER_PGD; i++, pgd++, addr += PGDIR_SIZE) {
 		if (!pgd_none(*pgd) && !pgd_is_leaf(*pgd))
 			/* pgd exists */
 			walk_pud(st, pgd, addr);
@@ -341,11 +331,6 @@ static void populate_markers(void)
 #else /* !CONFIG_PPC64 */
 	address_markers[i++].start_address = ioremap_bot;
 	address_markers[i++].start_address = IOREMAP_TOP;
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	address_markers[i++].start_address = IOREMAP_TOP;
-	address_markers[i++].start_address = IOREMAP_TOP +
-					     CONFIG_CONSISTENT_SIZE;
-#endif
 #ifdef CONFIG_HIGHMEM
 	address_markers[i++].start_address = PKMAP_BASE;
 	address_markers[i++].start_address = PKMAP_ADDR(LAST_PKMAP);
@@ -364,12 +349,13 @@ static int ptdump_show(struct seq_file *m, void *v)
 	struct pg_state st = {
 		.seq = m,
 		.marker = address_markers,
+		.start_address = PAGE_OFFSET,
 	};
 
-	if (radix_enabled())
-		st.start_address = PAGE_OFFSET;
-	else
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
 		st.start_address = KERN_VIRT_START;
+#endif
 
 	/* Traverse kernel page tables */
 	walk_pagetables(&st);
@@ -407,12 +393,13 @@ void ptdump_check_wx(void)
 		.seq = NULL,
 		.marker = address_markers,
 		.check_wx = true,
+		.start_address = PAGE_OFFSET,
 	};
 
-	if (radix_enabled())
-		st.start_address = PAGE_OFFSET;
-	else
+#ifdef CONFIG_PPC64
+	if (!radix_enabled())
 		st.start_address = KERN_VIRT_START;
+#endif
 
 	walk_pagetables(&st);
author	Linus Torvalds	2019-09-20 11:48:06 -0700
committer	Linus Torvalds	2019-09-20 11:48:06 -0700
commit	45824fc0da6e46cc5d563105e1eaaf3098a686f9 (patch)
tree	8e57c1f18104ed5f0d74d9eed9dc0365b3c137b8 /arch/powerpc/mm
parent	8c2b418c3f95a488f5226870eee68574d323f0f8 (diff)
parent	d9101bfa6adc831bda8836c4d774820553c14942 (diff)