13 files changed, 346 insertions, 530 deletions

diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 871354aa3c00..e9d232561c82 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -2,9 +2,6 @@
 # Makefile for the linux Sparc-specific parts of the memory manager.
 #
 
-asflags-y := -ansi
-ccflags-y := -Werror
-
 obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
@@ -15,3 +12,5 @@ obj-$(CONFIG_SPARC32)   += leon_mm.o
 
 # Only used by sparc64
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+
+obj-$(CONFIG_EXECMEM)	+= execmem.o
diff --git a/arch/sparc/mm/execmem.c b/arch/sparc/mm/execmem.c
new file mode 100644
index 000000000000..0fac97dd5728
--- /dev/null
+++ b/arch/sparc/mm/execmem.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/mm.h>
+#include <linux/execmem.h>
+
+static struct execmem_info execmem_info __ro_after_init;
+
+struct execmem_info __init *execmem_arch_setup(void)
+{
+	execmem_info = (struct execmem_info){
+		.ranges = {
+			[EXECMEM_DEFAULT] = {
+				.start	= MODULES_VADDR,
+				.end	= MODULES_END,
+				.pgprot	= PAGE_KERNEL,
+				.alignment = 1,
+			},
+		},
+	};
+
+	return &execmem_info;
+}
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index de2031c2b2d7..86a831ebd8c8 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -83,7 +83,7 @@ static void __do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 		show_signal_msg(regs, sig, code,
 				addr, current);
 
-	force_sig_fault(sig, code, (void __user *) addr, 0);
+	force_sig_fault(sig, code, (void __user *) addr);
 }
 
 static unsigned long compute_si_addr(struct pt_regs *regs, int text_fault)
@@ -143,28 +143,19 @@ asmlinkage void do_sparc_fault(struct pt_regs *regs, int text_fault, int write,
 	if (pagefault_disabled() || !mm)
 		goto no_context;
 
+	if (!from_user && address >= PAGE_OFFSET)
+		goto no_context;
+
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
 retry:
-	mmap_read_lock(mm);
-
-	if (!from_user && address >= PAGE_OFFSET)
-		goto bad_area;
-
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, regs);
 	if (!vma)
-		goto bad_area;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-	if (expand_stack(vma, address))
-		goto bad_area;
+		goto bad_area_nosemaphore;
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
 	 */
-good_area:
 	code = SEGV_ACCERR;
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -187,7 +178,14 @@ good_area:
 	 */
 	fault = handle_mm_fault(vma, address, flags, regs);
 
-	if (fault_signal_pending(fault, regs))
+	if (fault_signal_pending(fault, regs)) {
+		if (!from_user)
+			goto no_context;
+		return;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
 		return;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
@@ -200,17 +198,15 @@ good_area:
 		BUG();
 	}
 
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_RETRY) {
-			flags |= FAULT_FLAG_TRIED;
+	if (fault & VM_FAULT_RETRY) {
+		flags |= FAULT_FLAG_TRIED;
 
-			/* No need to mmap_read_unlock(mm) as we would
-			 * have already released it in __lock_page_or_retry
-			 * in mm/filemap.c.
-			 */
+		/* No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
 
-			goto retry;
-		}
+		goto retry;
 	}
 
 	mmap_read_unlock(mm);
@@ -248,7 +244,6 @@ no_context:
 	}
 
 	unhandled_fault(address, tsk, regs);
-	do_exit(SIGKILL);
 
 /*
  * We ran out of memory, or some other thing happened to us that made
@@ -317,17 +312,9 @@ static void force_user_fault(unsigned long address, int write)
 
 	code = SEGV_MAPERR;
 
-	mmap_read_lock(mm);
-	vma = find_vma(mm, address);
+	vma = lock_mm_and_find_vma(mm, address, NULL);
 	if (!vma)
-		goto bad_area;
-	if (vma->vm_start <= address)
-		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
-	if (expand_stack(vma, address))
-		goto bad_area;
-good_area:
+		goto bad_area_nosemaphore;
 	code = SEGV_ACCERR;
 	if (write) {
 		if (!(vma->vm_flags & VM_WRITE))
@@ -346,6 +333,7 @@ good_area:
 	return;
 bad_area:
 	mmap_read_unlock(mm);
+bad_area_nosemaphore:
 	__do_fault_siginfo(code, SIGSEGV, tsk->thread.kregs, address);
 	return;
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index 0a6bcc85fba7..e326caf708c6 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -99,6 +99,7 @@ static unsigned int get_user_insn(unsigned long tpc)
 	local_irq_disable();
 
 	pmdp = pmd_offset(pudp, tpc);
+again:
 	if (pmd_none(*pmdp) || unlikely(pmd_bad(*pmdp)))
 		goto out_irq_enable;
 
@@ -115,6 +116,8 @@ static unsigned int get_user_insn(unsigned long tpc)
 #endif
 	{
 		ptep = pte_offset_map(pmdp, tpc);
+		if (!ptep)
+			goto again;
 		pte = *ptep;
 		if (pte_present(pte)) {
 			pa  = (pte_pfn(pte) << PAGE_SHIFT);
@@ -176,7 +179,7 @@ static void do_fault_siginfo(int code, int sig, struct pt_regs *regs,
 	if (unlikely(show_unhandled_signals))
 		show_signal_msg(regs, sig, code, addr, current);
 
-	force_sig_fault(sig, code, (void __user *) addr, 0);
+	force_sig_fault(sig, code, (void __user *) addr);
 }
 
 static unsigned int get_fault_insn(struct pt_regs *regs, unsigned int insn)
@@ -383,8 +386,9 @@ continue_fault:
 				goto bad_area;
 		}
 	}
-	if (expand_stack(vma, address))
-		goto bad_area;
+	vma = expand_stack(mm, address);
+	if (!vma)
+		goto bad_area_nosemaphore;
 	/*
 	 * Ok, we have a good vm_area for this memory access, so
 	 * we can handle it..
@@ -424,8 +428,17 @@ good_area:
 
 	fault = handle_mm_fault(vma, address, flags, regs);
 
-	if (fault_signal_pending(fault, regs))
+	if (fault_signal_pending(fault, regs)) {
+		if (regs->tstate & TSTATE_PRIV) {
+			insn = get_fault_insn(regs, insn);
+			goto handle_kernel_fault;
+		}
 		goto exit_exception;
+	}
+
+	/* The fault is fully completed (including releasing mmap lock) */
+	if (fault & VM_FAULT_COMPLETED)
+		goto lock_released;
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
@@ -437,20 +450,19 @@ good_area:
 		BUG();
 	}
 
-	if (flags & FAULT_FLAG_ALLOW_RETRY) {
-		if (fault & VM_FAULT_RETRY) {
-			flags |= FAULT_FLAG_TRIED;
+	if (fault & VM_FAULT_RETRY) {
+		flags |= FAULT_FLAG_TRIED;
 
-			/* No need to mmap_read_unlock(mm) as we would
-			 * have already released it in __lock_page_or_retry
-			 * in mm/filemap.c.
-			 */
+		/* No need to mmap_read_unlock(mm) as we would
+		 * have already released it in __lock_page_or_retry
+		 * in mm/filemap.c.
+		 */
 
-			goto retry;
-		}
+		goto retry;
 	}
 	mmap_read_unlock(mm);
 
+lock_released:
 	mm_rss = get_mm_rss(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE)
 	mm_rss -= (mm->context.thp_pte_count * (HPAGE_SIZE / PAGE_SIZE));
@@ -479,8 +491,9 @@ exit_exception:
 	 * Fix it, but check if it's kernel or user first..
 	 */
 bad_area:
-	insn = get_fault_insn(regs, insn);
 	mmap_read_unlock(mm);
+bad_area_nosemaphore:
+	insn = get_fault_insn(regs, insn);
 
 handle_kernel_fault:
 	do_kernel_fault(regs, si_code, fault_code, insn, address);
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index 0f49fada2093..4652e868663b 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -19,120 +19,29 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.h>
 
-/* Slightly simplified from the non-hugepage variant because by
- * definition we don't have to worry about any page coloring stuff
- */
 
-static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
-							unsigned long addr,
-							unsigned long len,
-							unsigned long pgoff,
-							unsigned long flags)
-{
-	struct hstate *h = hstate_file(filp);
-	unsigned long task_size = TASK_SIZE;
-	struct vm_unmapped_area_info info;
-
-	if (test_thread_flag(TIF_32BIT))
-		task_size = STACK_TOP32;
-
-	info.flags = 0;
-	info.length = len;
-	info.low_limit = TASK_UNMAPPED_BASE;
-	info.high_limit = min(task_size, VA_EXCLUDE_START);
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	addr = vm_unmapped_area(&info);
-
-	if ((addr & ~PAGE_MASK) && task_size > VA_EXCLUDE_END) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.low_limit = VA_EXCLUDE_END;
-		info.high_limit = task_size;
-		addr = vm_unmapped_area(&info);
-	}
-
-	return addr;
-}
-
-static unsigned long
-hugetlb_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
-				  const unsigned long len,
-				  const unsigned long pgoff,
-				  const unsigned long flags)
+static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 {
-	struct hstate *h = hstate_file(filp);
-	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0;
-	struct vm_unmapped_area_info info;
-
-	/* This should only ever run for 32-bit processes.  */
-	BUG_ON(!test_thread_flag(TIF_32BIT));
-
-	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
-	info.length = len;
-	info.low_limit = PAGE_SIZE;
-	info.high_limit = mm->mmap_base;
-	info.align_mask = PAGE_MASK & ~huge_page_mask(h);
-	info.align_offset = 0;
-	addr = vm_unmapped_area(&info);
-
-	/*
-	 * A failed mmap() very likely causes application failure,
-	 * so fall back to the bottom-up function here. This scenario
-	 * can happen with large stack limits and large mmap()
-	 * allocations.
-	 */
-	if (addr & ~PAGE_MASK) {
-		VM_BUG_ON(addr != -ENOMEM);
-		info.flags = 0;
-		info.low_limit = TASK_UNMAPPED_BASE;
-		info.high_limit = STACK_TOP32;
-		addr = vm_unmapped_area(&info);
-	}
+	unsigned long hugepage_size = _PAGE_SZ4MB_4U;
 
-	return addr;
-}
+	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4U;
 
-unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
-{
-	struct hstate *h = hstate_file(file);
-	struct mm_struct *mm = current->mm;
-	struct vm_area_struct *vma;
-	unsigned long task_size = TASK_SIZE;
-
-	if (test_thread_flag(TIF_32BIT))
-		task_size = STACK_TOP32;
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (len > task_size)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
-	}
-
-	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
-		vma = find_vma(mm, addr);
-		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
-			return addr;
+	switch (shift) {
+	case HPAGE_256MB_SHIFT:
+		hugepage_size = _PAGE_SZ256MB_4U;
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
+	case HPAGE_SHIFT:
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
+	case HPAGE_64K_SHIFT:
+		hugepage_size = _PAGE_SZ64K_4U;
+		break;
+	default:
+		WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift);
 	}
-	if (mm->get_unmapped_area == arch_get_unmapped_area)
-		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
-				pgoff, flags);
-	else
-		return hugetlb_get_unmapped_area_topdown(file, addr, len,
-				pgoff, flags);
-}
 
-static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
-{
+	pte_val(entry) = pte_val(entry) | hugepage_size;
 	return entry;
 }
 
@@ -181,6 +90,7 @@ pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags)
 {
 	pte_t pte;
 
+	entry = pte_mkhuge(entry);
 	pte = hugepage_shift_to_tte(entry, shift);
 
 #ifdef CONFIG_SPARC64
@@ -297,7 +207,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 		return NULL;
 	if (sz >= PMD_SIZE)
 		return (pte_t *)pmd;
-	return pte_alloc_map(mm, pmd, addr);
+	return pte_alloc_huge(mm, pmd, addr);
 }
 
 pte_t *huge_pte_offset(struct mm_struct *mm,
@@ -324,10 +234,10 @@ pte_t *huge_pte_offset(struct mm_struct *mm,
 		return NULL;
 	if (is_hugetlb_pmd(*pmd))
 		return (pte_t *)pmd;
-	return pte_offset_map(pmd, addr);
+	return pte_offset_huge(pmd, addr);
 }
 
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t entry)
 {
 	unsigned int nptes, orig_shift, shift;
@@ -363,8 +273,14 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				    orig_shift);
 }
 
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry, unsigned long sz)
+{
+	__set_huge_pte_at(mm, addr, ptep, entry);
+}
+
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
@@ -399,134 +315,3 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 
 	return entry;
 }
-
-int pmd_huge(pmd_t pmd)
-{
-	return !pmd_none(pmd) &&
-		(pmd_val(pmd) & (_PAGE_VALID|_PAGE_PMD_HUGE)) != _PAGE_VALID;
-}
-
-int pud_huge(pud_t pud)
-{
-	return !pud_none(pud) &&
-		(pud_val(pud) & (_PAGE_VALID|_PAGE_PUD_HUGE)) != _PAGE_VALID;
-}
-
-static void hugetlb_free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
-			   unsigned long addr)
-{
-	pgtable_t token = pmd_pgtable(*pmd);
-
-	pmd_clear(pmd);
-	pte_free_tlb(tlb, token, addr);
-	mm_dec_nr_ptes(tlb->mm);
-}
-
-static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pmd_t *pmd;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	pmd = pmd_offset(pud, addr);
-	do {
-		next = pmd_addr_end(addr, end);
-		if (pmd_none(*pmd))
-			continue;
-		if (is_hugetlb_pmd(*pmd))
-			pmd_clear(pmd);
-		else
-			hugetlb_free_pte_range(tlb, pmd, addr);
-	} while (pmd++, addr = next, addr != end);
-
-	start &= PUD_MASK;
-	if (start < floor)
-		return;
-	if (ceiling) {
-		ceiling &= PUD_MASK;
-		if (!ceiling)
-			return;
-	}
-	if (end - 1 > ceiling - 1)
-		return;
-
-	pmd = pmd_offset(pud, start);
-	pud_clear(pud);
-	pmd_free_tlb(tlb, pmd, start);
-	mm_dec_nr_pmds(tlb->mm);
-}
-
-static void hugetlb_free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
-				   unsigned long addr, unsigned long end,
-				   unsigned long floor, unsigned long ceiling)
-{
-	pud_t *pud;
-	unsigned long next;
-	unsigned long start;
-
-	start = addr;
-	pud = pud_offset(p4d, addr);
-	do {
-		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		if (is_hugetlb_pud(*pud))
-			pud_clear(pud);
-		else
-			hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
-					       ceiling);
-	} while (pud++, addr = next, addr != end);
-
-	start &= PGDIR_MASK;
-	if (start < floor)
-		return;
-	if (ceiling) {
-		ceiling &= PGDIR_MASK;
-		if (!ceiling)
-			return;
-	}
-	if (end - 1 > ceiling - 1)
-		return;
-
-	pud = pud_offset(p4d, start);
-	p4d_clear(p4d);
-	pud_free_tlb(tlb, pud, start);
-	mm_dec_nr_puds(tlb->mm);
-}
-
-void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-			    unsigned long addr, unsigned long end,
-			    unsigned long floor, unsigned long ceiling)
-{
-	pgd_t *pgd;
-	p4d_t *p4d;
-	unsigned long next;
-
-	addr &= PMD_MASK;
-	if (addr < floor) {
-		addr += PMD_SIZE;
-		if (!addr)
-			return;
-	}
-	if (ceiling) {
-		ceiling &= PMD_MASK;
-		if (!ceiling)
-			return;
-	}
-	if (end - 1 > ceiling - 1)
-		end -= PMD_SIZE;
-	if (addr > end - 1)
-		return;
-
-	pgd = pgd_offset(tlb->mm, addr);
-	p4d = p4d_offset(pgd, addr);
-	do {
-		next = p4d_addr_end(addr, end);
-		if (p4d_none_or_clear_bad(p4d))
-			continue;
-		hugetlb_free_pud_range(tlb, p4d, addr, next, floor, ceiling);
-	} while (p4d++, addr = next, addr != end);
-}
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index 1e9f577f084d..fdc93dd12c3e 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -37,8 +37,7 @@
 
 #include "mm_32.h"
 
-unsigned long *sparc_valid_addr_bitmap;
-EXPORT_SYMBOL(sparc_valid_addr_bitmap);
+static unsigned long *sparc_valid_addr_bitmap;
 
 unsigned long phys_base;
 EXPORT_SYMBOL(phys_base);
@@ -233,19 +232,7 @@ static void __init taint_real_pages(void)
 	}
 }
 
-static void map_high_region(unsigned long start_pfn, unsigned long end_pfn)
-{
-	unsigned long tmp;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	printk("mapping high region %08lx - %08lx\n", start_pfn, end_pfn);
-#endif
-
-	for (tmp = start_pfn; tmp < end_pfn; tmp++)
-		free_highmem_page(pfn_to_page(tmp));
-}
-
-void __init mem_init(void)
+void __init arch_mm_preinit(void)
 {
 	int i;
 
@@ -275,30 +262,42 @@ void __init mem_init(void)
 	memset(sparc_valid_addr_bitmap, 0, i << 2);
 
 	taint_real_pages();
-
-	max_mapnr = last_valid_pfn - pfn_base;
-	high_memory = __va(max_low_pfn << PAGE_SHIFT);
-	memblock_free_all();
-
-	for (i = 0; sp_banks[i].num_bytes != 0; i++) {
-		unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT;
-		unsigned long end_pfn = (sp_banks[i].base_addr + sp_banks[i].num_bytes) >> PAGE_SHIFT;
-
-		if (end_pfn <= highstart_pfn)
-			continue;
-
-		if (start_pfn < highstart_pfn)
-			start_pfn = highstart_pfn;
-
-		map_high_region(start_pfn, end_pfn);
-	}
 }
 
 void sparc_flush_page_to_ram(struct page *page)
 {
 	unsigned long vaddr = (unsigned long)page_address(page);
 
-	if (vaddr)
-		__flush_page_to_ram(vaddr);
+	__flush_page_to_ram(vaddr);
 }
 EXPORT_SYMBOL(sparc_flush_page_to_ram);
+
+void sparc_flush_folio_to_ram(struct folio *folio)
+{
+	unsigned long vaddr = (unsigned long)folio_address(folio);
+	unsigned int i, nr = folio_nr_pages(folio);
+
+	for (i = 0; i < nr; i++)
+		__flush_page_to_ram(vaddr + i * PAGE_SIZE);
+}
+EXPORT_SYMBOL(sparc_flush_folio_to_ram);
+
+static const pgprot_t protection_map[16] = {
+	[VM_NONE]					= PAGE_NONE,
+	[VM_READ]					= PAGE_READONLY,
+	[VM_WRITE]					= PAGE_COPY,
+	[VM_WRITE | VM_READ]				= PAGE_COPY,
+	[VM_EXEC]					= PAGE_READONLY,
+	[VM_EXEC | VM_READ]				= PAGE_READONLY,
+	[VM_EXEC | VM_WRITE]				= PAGE_COPY,
+	[VM_EXEC | VM_WRITE | VM_READ]			= PAGE_COPY,
+	[VM_SHARED]					= PAGE_NONE,
+	[VM_SHARED | VM_READ]				= PAGE_READONLY,
+	[VM_SHARED | VM_WRITE]				= PAGE_SHARED,
+	[VM_SHARED | VM_WRITE | VM_READ]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC]				= PAGE_READONLY,
+	[VM_SHARED | VM_EXEC | VM_READ]			= PAGE_READONLY,
+	[VM_SHARED | VM_EXEC | VM_WRITE]		= PAGE_SHARED,
+	[VM_SHARED | VM_EXEC | VM_WRITE | VM_READ]	= PAGE_SHARED
+};
+DECLARE_VM_GET_PAGE_PROT
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 1b23639e2fcd..df9f7c444c39 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -195,21 +195,26 @@ atomic_t dcpage_flushes_xcall = ATOMIC_INIT(0);
 #endif
 #endif
 
-inline void flush_dcache_page_impl(struct page *page)
+inline void flush_dcache_folio_impl(struct folio *folio)
 {
+	unsigned int i, nr = folio_nr_pages(folio);
+
 	BUG_ON(tlb_type == hypervisor);
 #ifdef CONFIG_DEBUG_DCFLUSH
 	atomic_inc(&dcpage_flushes);
 #endif
 
 #ifdef DCACHE_ALIASING_POSSIBLE
-	__flush_dcache_page(page_address(page),
-			    ((tlb_type == spitfire) &&
-			     page_mapping_file(page) != NULL));
+	for (i = 0; i < nr; i++)
+		__flush_dcache_page(folio_address(folio) + i * PAGE_SIZE,
+				    ((tlb_type == spitfire) &&
+				     folio_flush_mapping(folio) != NULL));
 #else
-	if (page_mapping_file(page) != NULL &&
-	    tlb_type == spitfire)
-		__flush_icache_page(__pa(page_address(page)));
+	if (folio_flush_mapping(folio) != NULL &&
+	    tlb_type == spitfire) {
+		for (i = 0; i < nr; i++)
+			__flush_icache_page((pfn + i) * PAGE_SIZE);
+	}
 #endif
 }
 
@@ -218,10 +223,10 @@ inline void flush_dcache_page_impl(struct page *page)
 #define PG_dcache_cpu_mask	\
 	((1UL<<ilog2(roundup_pow_of_two(NR_CPUS)))-1UL)
 
-#define dcache_dirty_cpu(page) \
-	(((page)->flags >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask)
+#define dcache_dirty_cpu(folio) \
+	(((folio)->flags.f >> PG_dcache_cpu_shift) & PG_dcache_cpu_mask)
 
-static inline void set_dcache_dirty(struct page *page, int this_cpu)
+static inline void set_dcache_dirty(struct folio *folio, int this_cpu)
 {
 	unsigned long mask = this_cpu;
 	unsigned long non_cpu_bits;
@@ -238,11 +243,11 @@ static inline void set_dcache_dirty(struct page *page, int this_cpu)
 			     "bne,pn	%%xcc, 1b\n\t"
 			     " nop"
 			     : /* no outputs */
-			     : "r" (mask), "r" (non_cpu_bits), "r" (&page->flags)
+			     : "r" (mask), "r" (non_cpu_bits), "r" (&folio->flags.f)
 			     : "g1", "g7");
 }
 
-static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu)
+static inline void clear_dcache_dirty_cpu(struct folio *folio, unsigned long cpu)
 {
 	unsigned long mask = (1UL << PG_dcache_dirty);
 
@@ -260,7 +265,7 @@ static inline void clear_dcache_dirty_cpu(struct page *page, unsigned long cpu)
 			     " nop\n"
 			     "2:"
 			     : /* no outputs */
-			     : "r" (cpu), "r" (mask), "r" (&page->flags),
+			     : "r" (cpu), "r" (mask), "r" (&folio->flags.f),
 			       "i" (PG_dcache_cpu_mask),
 			       "i" (PG_dcache_cpu_shift)
 			     : "g1", "g7");
@@ -284,9 +289,10 @@ static void flush_dcache(unsigned long pfn)
 
 	page = pfn_to_page(pfn);
 	if (page) {
+		struct folio *folio = page_folio(page);
 		unsigned long pg_flags;
 
-		pg_flags = page->flags;
+		pg_flags = folio->flags.f;
 		if (pg_flags & (1UL << PG_dcache_dirty)) {
 			int cpu = ((pg_flags >> PG_dcache_cpu_shift) &
 				   PG_dcache_cpu_mask);
@@ -296,11 +302,11 @@ static void flush_dcache(unsigned long pfn)
 			 * in the SMP case.
 			 */
 			if (cpu == this_cpu)
-				flush_dcache_page_impl(page);
+				flush_dcache_folio_impl(folio);
 			else
-				smp_flush_dcache_page_impl(page, cpu);
+				smp_flush_dcache_folio_impl(folio, cpu);
 
-			clear_dcache_dirty_cpu(page, cpu);
+			clear_dcache_dirty_cpu(folio, cpu);
 
 			put_cpu();
 		}
@@ -388,12 +394,14 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 }
 #endif	/* CONFIG_HUGETLB_PAGE */
 
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *ptep)
+void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
+		unsigned long address, pte_t *ptep, unsigned int nr)
 {
 	struct mm_struct *mm;
 	unsigned long flags;
 	bool is_huge_tsb;
 	pte_t pte = *ptep;
+	unsigned int i;
 
 	if (tlb_type != hypervisor) {
 		unsigned long pfn = pte_pfn(pte);
@@ -440,15 +448,21 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long address, pte_t *
 		}
 	}
 #endif
-	if (!is_huge_tsb)
-		__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
-					address, pte_val(pte));
+	if (!is_huge_tsb) {
+		for (i = 0; i < nr; i++) {
+			__update_mmu_tsb_insert(mm, MM_TSB_BASE, PAGE_SHIFT,
+						address, pte_val(pte));
+			address += PAGE_SIZE;
+			pte_val(pte) += PAGE_SIZE;
+		}
+	}
 
 	spin_unlock_irqrestore(&mm->context.lock, flags);
 }
 
-void flush_dcache_page(struct page *page)
+void flush_dcache_folio(struct folio *folio)
 {
+	unsigned long pfn = folio_pfn(folio);
 	struct address_space *mapping;
 	int this_cpu;
 
@@ -459,35 +473,35 @@ void flush_dcache_page(struct page *page)
 	 * is merely the zero page.  The 'bigcore' testcase in GDB
 	 * causes this case to run millions of times.
 	 */
-	if (page == ZERO_PAGE(0))
+	if (is_zero_pfn(pfn))
 		return;
 
 	this_cpu = get_cpu();
 
-	mapping = page_mapping_file(page);
+	mapping = folio_flush_mapping(folio);
 	if (mapping && !mapping_mapped(mapping)) {
-		int dirty = test_bit(PG_dcache_dirty, &page->flags);
+		bool dirty = test_bit(PG_dcache_dirty, &folio->flags.f);
 		if (dirty) {
-			int dirty_cpu = dcache_dirty_cpu(page);
+			int dirty_cpu = dcache_dirty_cpu(folio);
 
 			if (dirty_cpu == this_cpu)
 				goto out;
-			smp_flush_dcache_page_impl(page, dirty_cpu);
+			smp_flush_dcache_folio_impl(folio, dirty_cpu);
 		}
-		set_dcache_dirty(page, this_cpu);
+		set_dcache_dirty(folio, this_cpu);
 	} else {
-		/* We could delay the flush for the !page_mapping
+		/* We could delay the flush for the !folio_mapping
 		 * case too.  But that case is for exec env/arg
 		 * pages and those are %99 certainly going to get
 		 * faulted into the tlb (and thus flushed) anyways.
 		 */
-		flush_dcache_page_impl(page);
+		flush_dcache_folio_impl(folio);
 	}
 
 out:
 	put_cpu();
 }
-EXPORT_SYMBOL(flush_dcache_page);
+EXPORT_SYMBOL(flush_dcache_folio);
 
 void __kprobes flush_icache_range(unsigned long start, unsigned long end)
 {
@@ -709,9 +723,10 @@ static void __init inherit_prom_mappings(void)
 
 void prom_world(int enter)
 {
-	if (!enter)
-		set_fs(get_fs());
-
+	/*
+	 * No need to change the address space any more, just flush
+	 * the register windows
+	 */
 	__asm__ __volatile__("flushw");
 }
 
@@ -1060,14 +1075,9 @@ static void __init allocate_node_data(int nid)
 {
 	struct pglist_data *p;
 	unsigned long start_pfn, end_pfn;
-#ifdef CONFIG_NUMA
 
-	NODE_DATA(nid) = memblock_alloc_node(sizeof(struct pglist_data),
-					     SMP_CACHE_BYTES, nid);
-	if (!NODE_DATA(nid)) {
-		prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid);
-		prom_halt();
-	}
+#ifdef CONFIG_NUMA
+	alloc_node_data(nid);
 
 	NODE_DATA(nid)->node_id = nid;
 #endif
@@ -1100,11 +1110,9 @@ static void init_node_masks_nonnuma(void)
 }
 
 #ifdef CONFIG_NUMA
-struct pglist_data *node_data[MAX_NUMNODES];
 
 EXPORT_SYMBOL(numa_cpu_lookup_table);
 EXPORT_SYMBOL(numa_cpumask_lookup_table);
-EXPORT_SYMBOL(node_data);
 
 static int scan_pio_for_cfg_handle(struct mdesc_handle *md, u64 pio,
 				   u32 cfg_handle)
@@ -1650,14 +1658,14 @@ bool kern_addr_valid(unsigned long addr)
 	if (pud_none(*pud))
 		return false;
 
-	if (pud_large(*pud))
+	if (pud_leaf(*pud))
 		return pfn_valid(pud_pfn(*pud));
 
 	pmd = pmd_offset(pud, addr);
 	if (pmd_none(*pmd))
 		return false;
 
-	if (pmd_large(*pmd))
+	if (pmd_leaf(*pmd))
 		return pfn_valid(pmd_pfn(*pmd));
 
 	pte = pte_offset_kernel(pmd, addr);
@@ -1666,7 +1674,6 @@ bool kern_addr_valid(unsigned long addr)
 
 	return pfn_valid(pte_pfn(*pte));
 }
-EXPORT_SYMBOL(kern_addr_valid);
 
 static unsigned long __ref kernel_map_hugepud(unsigned long vstart,
 					      unsigned long vend,
@@ -2280,10 +2287,10 @@ void __init paging_init(void)
 	setup_page_offset();
 
 	/* These build time checkes make sure that the dcache_dirty_cpu()
-	 * page->flags usage will work.
+	 * folio->flags usage will work.
 	 *
 	 * When a page gets marked as dcache-dirty, we store the
-	 * cpu number starting at bit 32 in the page->flags.  Also,
+	 * cpu number starting at bit 32 in the folio->flags.  Also,
 	 * functions like clear_dcache_dirty_cpu use the cpu mask
 	 * in 13-bit signed-immediate instruction fields.
 	 */
@@ -2498,10 +2505,6 @@ static void __init register_page_bootmem_info(void)
 }
 void __init mem_init(void)
 {
-	high_memory = __va(last_valid_pfn << PAGE_SHIFT);
-
-	memblock_free_all();
-
 	/*
 	 * Must be done after boot memory is put on freelist, because here we
 	 * might set fields in deferred struct pages that have not yet been
@@ -2626,13 +2629,11 @@ int __meminit vmemmap_populate(unsigned long vstart, unsigned long vend,
 
 	return 0;
 }
-
-void vmemmap_free(unsigned long start, unsigned long end,
-		struct vmem_altmap *altmap)
-{
-}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
+/* These are actually filled in at boot time by sun4{u,v}_pgprot_init() */
+static pgprot_t protection_map[16] __ro_after_init;
+
 static void prot_init_common(unsigned long page_none,
 			     unsigned long page_shared,
 			     unsigned long page_copy,
@@ -2877,40 +2878,40 @@ void __flush_tlb_all(void)
 			     : : "r" (pstate));
 }
 
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+static pte_t *__pte_alloc_one(struct mm_struct *mm)
 {
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	pte_t *pte = NULL;
-
-	if (page)
-		pte = (pte_t *) page_address(page);
+	struct ptdesc *ptdesc = pagetable_alloc(GFP_KERNEL | __GFP_ZERO, 0);
 
-	return pte;
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
-	struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-	if (!page)
+	if (!ptdesc)
 		return NULL;
-	if (!pgtable_pte_page_ctor(page)) {
-		__free_page(page);
+	if (!pagetable_pte_ctor(mm, ptdesc)) {
+		pagetable_free(ptdesc);
 		return NULL;
 	}
-	return (pte_t *) page_address(page);
+	return ptdesc_address(ptdesc);
 }
 
-void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
-	free_page((unsigned long)pte);
+	return __pte_alloc_one(mm);
+}
+
+pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+	return __pte_alloc_one(mm);
 }
 
 static void __pte_free(pgtable_t pte)
 {
-	struct page *page = virt_to_page(pte);
+	struct ptdesc *ptdesc = virt_to_ptdesc(pte);
 
-	pgtable_pte_page_dtor(page);
-	__free_page(page);
+	pagetable_dtor(ptdesc);
+	pagetable_free(ptdesc);
+}
+
+void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	__pte_free(pte);
 }
 
 void pte_free(struct mm_struct *mm, pgtable_t pte)
@@ -2927,6 +2928,22 @@ void pgtable_free(void *table, bool is_page)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void pte_free_now(struct rcu_head *head)
+{
+	struct page *page;
+
+	page = container_of(head, struct page, rcu_head);
+	__pte_free((pgtable_t)page_address(page));
+}
+
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+	struct page *page;
+
+	page = virt_to_page(pgtable);
+	call_rcu(&page->rcu_head, pte_free_now);
+}
+
 void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 			  pmd_t *pmd)
 {
@@ -2934,7 +2951,7 @@ void update_mmu_cache_pmd(struct vm_area_struct *vma, unsigned long addr,
 	struct mm_struct *mm;
 	pmd_t entry = *pmd;
 
-	if (!pmd_large(entry) || !pmd_young(entry))
+	if (!pmd_leaf(entry) || !pmd_young(entry))
 		return;
 
 	pte = pmd_val(entry);
@@ -3183,3 +3200,15 @@ void copy_highpage(struct page *to, struct page *from)
 	}
 }
 EXPORT_SYMBOL(copy_highpage);
+
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
+{
+	unsigned long prot = pgprot_val(protection_map[vm_flags &
+					(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
+
+	if (vm_flags & VM_SPARC_ADI)
+		prot |= _PAGE_MCD_4V;
+
+	return __pgprot(prot);
+}
+EXPORT_SYMBOL(vm_get_page_prot);
diff --git a/arch/sparc/mm/io-unit.c b/arch/sparc/mm/io-unit.c
index bf3e6d2fe5d9..d409cb450de4 100644
--- a/arch/sparc/mm/io-unit.c
+++ b/arch/sparc/mm/io-unit.c
@@ -13,7 +13,8 @@
 #include <linux/bitops.h>
 #include <linux/dma-map-ops.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <asm/io.h>
 #include <asm/io-unit.h>
@@ -93,13 +94,14 @@ static int __init iounit_init(void)
 subsys_initcall(iounit_init);
 
 /* One has to hold iounit->lock to call this */
-static unsigned long iounit_get_area(struct iounit_struct *iounit, unsigned long vaddr, int size)
+static dma_addr_t iounit_get_area(struct iounit_struct *iounit,
+				  phys_addr_t phys, int size)
 {
 	int i, j, k, npages;
 	unsigned long rotor, scan, limit;
 	iopte_t iopte;
 
-        npages = ((vaddr & ~PAGE_MASK) + size + (PAGE_SIZE-1)) >> PAGE_SHIFT;
+	npages = (offset_in_page(phys) + size + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 
 	/* A tiny bit of magic ingredience :) */
 	switch (npages) {
@@ -108,7 +110,7 @@ static unsigned long iounit_get_area(struct iounit_struct *iounit, unsigned long
 	default: i = 0x0213; break;
 	}
 	
-	IOD(("iounit_get_area(%08lx,%d[%d])=", vaddr, size, npages));
+	IOD(("%s(%pa,%d[%d])=", __func__, &phys, size, npages));
 	
 next:	j = (i & 15);
 	rotor = iounit->rotor[j - 1];
@@ -123,7 +125,8 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 		}
 		i >>= 4;
 		if (!(i & 15))
-			panic("iounit_get_area: Couldn't find free iopte slots for (%08lx,%d)\n", vaddr, size);
+			panic("iounit_get_area: Couldn't find free iopte slots for (%pa,%d)\n",
+			      &phys, size);
 		goto next;
 	}
 	for (k = 1, scan++; k < npages; k++)
@@ -131,30 +134,29 @@ nexti:	scan = find_next_zero_bit(iounit->bmap, limit, scan);
 			goto nexti;
 	iounit->rotor[j - 1] = (scan < limit) ? scan : iounit->limit[j - 1];
 	scan -= npages;
-	iopte = MKIOPTE(__pa(vaddr & PAGE_MASK));
-	vaddr = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + (vaddr & ~PAGE_MASK);
+	iopte = MKIOPTE(phys & PAGE_MASK);
+	phys = IOUNIT_DMA_BASE + (scan << PAGE_SHIFT) + offset_in_page(phys);
 	for (k = 0; k < npages; k++, iopte = __iopte(iopte_val(iopte) + 0x100), scan++) {
 		set_bit(scan, iounit->bmap);
 		sbus_writel(iopte_val(iopte), &iounit->page_table[scan]);
 	}
-	IOD(("%08lx\n", vaddr));
-	return vaddr;
+	IOD(("%pa\n", &phys));
+	return phys;
 }
 
-static dma_addr_t iounit_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t len, enum dma_data_direction dir,
-		unsigned long attrs)
+static dma_addr_t iounit_map_phys(struct device *dev, phys_addr_t phys,
+		size_t len, enum dma_data_direction dir, unsigned long attrs)
 {
-	void *vaddr = page_address(page) + offset;
 	struct iounit_struct *iounit = dev->archdata.iommu;
-	unsigned long ret, flags;
+	unsigned long flags;
+	dma_addr_t ret;
 	
 	/* XXX So what is maxphys for us and how do drivers know it? */
 	if (!len || len > 256 * 1024)
 		return DMA_MAPPING_ERROR;
 
 	spin_lock_irqsave(&iounit->lock, flags);
-	ret = iounit_get_area(iounit, (unsigned long)vaddr, len);
+	ret = iounit_get_area(iounit, phys, len);
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return ret;
 }
@@ -170,14 +172,15 @@ static int iounit_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
 	/* FIXME: Cache some resolved pages - often several sg entries are to the same page */
 	spin_lock_irqsave(&iounit->lock, flags);
 	for_each_sg(sgl, sg, nents, i) {
-		sg->dma_address = iounit_get_area(iounit, (unsigned long) sg_virt(sg), sg->length);
+		sg->dma_address =
+			iounit_get_area(iounit, sg_phys(sg), sg->length);
 		sg->dma_length = sg->length;
 	}
 	spin_unlock_irqrestore(&iounit->lock, flags);
 	return nents;
 }
 
-static void iounit_unmap_page(struct device *dev, dma_addr_t vaddr, size_t len,
+static void iounit_unmap_phys(struct device *dev, dma_addr_t vaddr, size_t len,
 		enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iounit_struct *iounit = dev->archdata.iommu;
@@ -244,7 +247,7 @@ static void *iounit_alloc(struct device *dev, size_t len,
 			long i;
 
 			pmdp = pmd_off_k(addr);
-			ptep = pte_offset_map(pmdp, addr);
+			ptep = pte_offset_kernel(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));
 
@@ -278,8 +281,8 @@ static const struct dma_map_ops iounit_dma_ops = {
 	.alloc			= iounit_alloc,
 	.free			= iounit_free,
 #endif
-	.map_page		= iounit_map_page,
-	.unmap_page		= iounit_unmap_page,
+	.map_phys		= iounit_map_phys,
+	.unmap_phys		= iounit_unmap_phys,
 	.map_sg			= iounit_map_sg,
 	.unmap_sg		= iounit_unmap_sg,
 };
diff --git a/arch/sparc/mm/iommu.c b/arch/sparc/mm/iommu.c
index 0c0342e5b10d..f48adf62724a 100644
--- a/arch/sparc/mm/iommu.c
+++ b/arch/sparc/mm/iommu.c
@@ -7,14 +7,15 @@
  * Copyright (C) 1996 Eddie C. Dost    (ecd@skynet.be)
  * Copyright (C) 1997,1998 Jakub Jelinek    (jj@sunsite.mff.cuni.cz)
  */
- 
+
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/dma-map-ops.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 
 #include <asm/io.h>
 #include <asm/mxcc.h>
@@ -180,18 +181,20 @@ static void iommu_flush_iotlb(iopte_t *iopte, unsigned int niopte)
 	}
 }
 
-static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t len, bool per_page_flush)
+static dma_addr_t __sbus_iommu_map_phys(struct device *dev, phys_addr_t paddr,
+		size_t len, bool per_page_flush, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
-	phys_addr_t paddr = page_to_phys(page) + offset;
-	unsigned long off = paddr & ~PAGE_MASK;
+	unsigned long off = offset_in_page(paddr);
 	unsigned long npages = (off + len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	unsigned long pfn = __phys_to_pfn(paddr);
 	unsigned int busa, busa0;
 	iopte_t *iopte, *iopte0;
 	int ioptex, i;
 
+	if (unlikely(attrs & DMA_ATTR_MMIO))
+		return DMA_MAPPING_ERROR;
+
 	/* XXX So what is maxphys for us and how do drivers know it? */
 	if (!len || len > 256 * 1024)
 		return DMA_MAPPING_ERROR;
@@ -201,10 +204,10 @@ static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
 	 * XXX Is this a good assumption?
 	 * XXX What if someone else unmaps it here and races us?
 	 */
-	if (per_page_flush && !PageHighMem(page)) {
+	if (per_page_flush && !PhysHighMem(paddr)) {
 		unsigned long vaddr, p;
 
-		vaddr = (unsigned long)page_address(page) + offset;
+		vaddr = (unsigned long)phys_to_virt(paddr);
 		for (p = vaddr & PAGE_MASK; p < vaddr + len; p += PAGE_SIZE)
 			flush_page_for_dma(p);
 	}
@@ -230,19 +233,19 @@ static dma_addr_t __sbus_iommu_map_page(struct device *dev, struct page *page,
 	return busa0 + off;
 }
 
-static dma_addr_t sbus_iommu_map_page_gflush(struct device *dev,
-		struct page *page, unsigned long offset, size_t len,
-		enum dma_data_direction dir, unsigned long attrs)
+static dma_addr_t sbus_iommu_map_phys_gflush(struct device *dev,
+		phys_addr_t phys, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
 	flush_page_for_dma(0);
-	return __sbus_iommu_map_page(dev, page, offset, len, false);
+	return __sbus_iommu_map_phys(dev, phys, len, false, attrs);
 }
 
-static dma_addr_t sbus_iommu_map_page_pflush(struct device *dev,
-		struct page *page, unsigned long offset, size_t len,
-		enum dma_data_direction dir, unsigned long attrs)
+static dma_addr_t sbus_iommu_map_phys_pflush(struct device *dev,
+		phys_addr_t phys, size_t len, enum dma_data_direction dir,
+		unsigned long attrs)
 {
-	return __sbus_iommu_map_page(dev, page, offset, len, true);
+	return __sbus_iommu_map_phys(dev, phys, len, true, attrs);
 }
 
 static int __sbus_iommu_map_sg(struct device *dev, struct scatterlist *sgl,
@@ -253,10 +256,10 @@ static int __sbus_iommu_map_sg(struct device *dev, struct scatterlist *sgl,
 	int j;
 
 	for_each_sg(sgl, sg, nents, j) {
-		sg->dma_address =__sbus_iommu_map_page(dev, sg_page(sg),
-				sg->offset, sg->length, per_page_flush);
+		sg->dma_address = __sbus_iommu_map_phys(dev, sg_phys(sg),
+				sg->length, per_page_flush, attrs);
 		if (sg->dma_address == DMA_MAPPING_ERROR)
-			return 0;
+			return -EIO;
 		sg->dma_length = sg->length;
 	}
 
@@ -276,7 +279,7 @@ static int sbus_iommu_map_sg_pflush(struct device *dev, struct scatterlist *sgl,
 	return __sbus_iommu_map_sg(dev, sgl, nents, dir, attrs, true);
 }
 
-static void sbus_iommu_unmap_page(struct device *dev, dma_addr_t dma_addr,
+static void sbus_iommu_unmap_phys(struct device *dev, dma_addr_t dma_addr,
 		size_t len, enum dma_data_direction dir, unsigned long attrs)
 {
 	struct iommu_struct *iommu = dev->archdata.iommu;
@@ -302,7 +305,7 @@ static void sbus_iommu_unmap_sg(struct device *dev, struct scatterlist *sgl,
 	int i;
 
 	for_each_sg(sgl, sg, nents, i) {
-		sbus_iommu_unmap_page(dev, sg->dma_address, sg->length, dir,
+		sbus_iommu_unmap_phys(dev, sg->dma_address, sg->length, dir,
 				attrs);
 		sg->dma_address = 0x21212121;
 	}
@@ -358,7 +361,7 @@ static void *sbus_iommu_alloc(struct device *dev, size_t len,
 				__flush_page_to_ram(page);
 
 			pmdp = pmd_off_k(addr);
-			ptep = pte_offset_map(pmdp, addr);
+			ptep = pte_offset_kernel(pmdp, addr);
 
 			set_pte(ptep, mk_pte(virt_to_page(page), dvma_prot));
 		}
@@ -425,8 +428,8 @@ static const struct dma_map_ops sbus_iommu_dma_gflush_ops = {
 	.alloc			= sbus_iommu_alloc,
 	.free			= sbus_iommu_free,
 #endif
-	.map_page		= sbus_iommu_map_page_gflush,
-	.unmap_page		= sbus_iommu_unmap_page,
+	.map_phys		= sbus_iommu_map_phys_gflush,
+	.unmap_phys		= sbus_iommu_unmap_phys,
 	.map_sg			= sbus_iommu_map_sg_gflush,
 	.unmap_sg		= sbus_iommu_unmap_sg,
 };
@@ -436,8 +439,8 @@ static const struct dma_map_ops sbus_iommu_dma_pflush_ops = {
 	.alloc			= sbus_iommu_alloc,
 	.free			= sbus_iommu_free,
 #endif
-	.map_page		= sbus_iommu_map_page_pflush,
-	.unmap_page		= sbus_iommu_unmap_page,
+	.map_phys		= sbus_iommu_map_phys_pflush,
+	.unmap_phys		= sbus_iommu_unmap_phys,
 	.map_sg			= sbus_iommu_map_sg_pflush,
 	.unmap_sg		= sbus_iommu_unmap_sg,
 };
diff --git a/arch/sparc/mm/leon_mm.c b/arch/sparc/mm/leon_mm.c
index ec61ff1f96b7..1dc9b3d70eda 100644
--- a/arch/sparc/mm/leon_mm.c
+++ b/arch/sparc/mm/leon_mm.c
@@ -39,12 +39,10 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr)
 	unsigned int ctxtbl;
 	unsigned int pgd, pmd, ped;
 	unsigned int ptr;
-	unsigned int lvl, pte, paddrbase;
+	unsigned int lvl, pte;
 	unsigned int ctx;
 	unsigned int paddr_calc;
 
-	paddrbase = 0;
-
 	if (srmmu_swprobe_trace)
 		printk(KERN_INFO "swprobe: trace on\n");
 
@@ -73,7 +71,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr)
 			printk(KERN_INFO "swprobe: pgd is entry level 3\n");
 		lvl = 3;
 		pte = pgd;
-		paddrbase = pgd & _SRMMU_PTE_PMASK_LEON;
 		goto ready;
 	}
 	if (((pgd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
@@ -96,7 +93,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr)
 			printk(KERN_INFO "swprobe: pmd is entry level 2\n");
 		lvl = 2;
 		pte = pmd;
-		paddrbase = pmd & _SRMMU_PTE_PMASK_LEON;
 		goto ready;
 	}
 	if (((pmd & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
@@ -124,7 +120,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr)
 			printk(KERN_INFO "swprobe: ped is entry level 1\n");
 		lvl = 1;
 		pte = ped;
-		paddrbase = ped & _SRMMU_PTE_PMASK_LEON;
 		goto ready;
 	}
 	if (((ped & SRMMU_ET_MASK) != SRMMU_ET_PTD)) {
@@ -147,7 +142,6 @@ unsigned long leon_swprobe(unsigned long vaddr, unsigned long *paddr)
 			printk(KERN_INFO "swprobe: ptr is entry level 0\n");
 		lvl = 0;
 		pte = ptr;
-		paddrbase = ptr & _SRMMU_PTE_PMASK_LEON;
 		goto ready;
 	}
 	if (srmmu_swprobe_trace)
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index a9aa6a92c7fe..f8fb4911d360 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -277,19 +277,13 @@ static void __init srmmu_nocache_init(void)
 
 	bitmap_bits = srmmu_nocache_size >> SRMMU_NOCACHE_BITMAP_SHIFT;
 
-	srmmu_nocache_pool = memblock_alloc(srmmu_nocache_size,
+	srmmu_nocache_pool = memblock_alloc_or_panic(srmmu_nocache_size,
 					    SRMMU_NOCACHE_ALIGN_MAX);
-	if (!srmmu_nocache_pool)
-		panic("%s: Failed to allocate %lu bytes align=0x%x\n",
-		      __func__, srmmu_nocache_size, SRMMU_NOCACHE_ALIGN_MAX);
 	memset(srmmu_nocache_pool, 0, srmmu_nocache_size);
 
 	srmmu_nocache_bitmap =
-		memblock_alloc(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
+		memblock_alloc_or_panic(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
 			       SMP_CACHE_BYTES);
-	if (!srmmu_nocache_bitmap)
-		panic("%s: Failed to allocate %zu bytes\n", __func__,
-		      BITS_TO_LONGS(bitmap_bits) * sizeof(long));
 	bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
 
 	srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
@@ -355,7 +349,8 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
 		return NULL;
 	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
 	spin_lock(&mm->page_table_lock);
-	if (page_ref_inc_return(page) == 2 && !pgtable_pte_page_ctor(page)) {
+	if (page_ref_inc_return(page) == 2 &&
+			!pagetable_pte_ctor(mm, page_ptdesc(page))) {
 		page_ref_dec(page);
 		ptep = NULL;
 	}
@@ -371,7 +366,7 @@ void pte_free(struct mm_struct *mm, pgtable_t ptep)
 	page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
 	spin_lock(&mm->page_table_lock);
 	if (page_ref_dec_return(page) == 1)
-		pgtable_pte_page_dtor(page);
+		pagetable_dtor(page_ptdesc(page));
 	spin_unlock(&mm->page_table_lock);
 
 	srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE);
@@ -451,9 +446,7 @@ static void __init sparc_context_init(int numctx)
 	unsigned long size;
 
 	size = numctx * sizeof(struct ctx_list);
-	ctx_list_pool = memblock_alloc(size, SMP_CACHE_BYTES);
-	if (!ctx_list_pool)
-		panic("%s: Failed to allocate %lu bytes\n", __func__, size);
+	ctx_list_pool = memblock_alloc_or_panic(size, SMP_CACHE_BYTES);
 
 	for (ctx = 0; ctx < numctx; ctx++) {
 		struct ctx_list *clist;
@@ -1512,7 +1505,7 @@ static void __init init_viking(void)
 
 		/*
 		 * We need this to make sure old viking takes no hits
-		 * on it's cache for dma snoops to workaround the
+		 * on its cache for dma snoops to workaround the
 		 * "load from non-cacheable memory" interrupt bug.
 		 * This is only necessary because of the new way in
 		 * which we use the IOMMU.
@@ -1636,30 +1629,32 @@ static void __init get_srmmu_type(void)
 /* Local cross-calls. */
 static void smp_flush_page_for_dma(unsigned long page)
 {
-	xc1((smpfunc_t) local_ops->page_for_dma, page);
+	xc1(local_ops->page_for_dma, page);
 	local_ops->page_for_dma(page);
 }
 
 static void smp_flush_cache_all(void)
 {
-	xc0((smpfunc_t) local_ops->cache_all);
+	xc0(local_ops->cache_all);
 	local_ops->cache_all();
 }
 
 static void smp_flush_tlb_all(void)
 {
-	xc0((smpfunc_t) local_ops->tlb_all);
+	xc0(local_ops->tlb_all);
 	local_ops->tlb_all();
 }
 
+static bool any_other_mm_cpus(struct mm_struct *mm)
+{
+	return cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids;
+}
+
 static void smp_flush_cache_mm(struct mm_struct *mm)
 {
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask))
-			xc1((smpfunc_t) local_ops->cache_mm, (unsigned long) mm);
+		if (any_other_mm_cpus(mm))
+			xc1(local_ops->cache_mm, (unsigned long)mm);
 		local_ops->cache_mm(mm);
 	}
 }
@@ -1667,11 +1662,8 @@ static void smp_flush_cache_mm(struct mm_struct *mm)
 static void smp_flush_tlb_mm(struct mm_struct *mm)
 {
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask)) {
-			xc1((smpfunc_t) local_ops->tlb_mm, (unsigned long) mm);
+		if (any_other_mm_cpus(mm)) {
+			xc1(local_ops->tlb_mm, (unsigned long)mm);
 			if (atomic_read(&mm->mm_users) == 1 && current->active_mm == mm)
 				cpumask_copy(mm_cpumask(mm),
 					     cpumask_of(smp_processor_id()));
@@ -1687,12 +1679,9 @@ static void smp_flush_cache_range(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask))
-			xc3((smpfunc_t) local_ops->cache_range,
-			    (unsigned long) vma, start, end);
+		if (any_other_mm_cpus(mm))
+			xc3(local_ops->cache_range, (unsigned long)vma, start,
+			    end);
 		local_ops->cache_range(vma, start, end);
 	}
 }
@@ -1704,12 +1693,9 @@ static void smp_flush_tlb_range(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask))
-			xc3((smpfunc_t) local_ops->tlb_range,
-			    (unsigned long) vma, start, end);
+		if (any_other_mm_cpus(mm))
+			xc3(local_ops->tlb_range, (unsigned long)vma, start,
+			    end);
 		local_ops->tlb_range(vma, start, end);
 	}
 }
@@ -1719,12 +1705,8 @@ static void smp_flush_cache_page(struct vm_area_struct *vma, unsigned long page)
 	struct mm_struct *mm = vma->vm_mm;
 
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask))
-			xc2((smpfunc_t) local_ops->cache_page,
-			    (unsigned long) vma, page);
+		if (any_other_mm_cpus(mm))
+			xc2(local_ops->cache_page, (unsigned long)vma, page);
 		local_ops->cache_page(vma, page);
 	}
 }
@@ -1734,12 +1716,8 @@ static void smp_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
 	struct mm_struct *mm = vma->vm_mm;
 
 	if (mm->context != NO_CONTEXT) {
-		cpumask_t cpu_mask;
-		cpumask_copy(&cpu_mask, mm_cpumask(mm));
-		cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-		if (!cpumask_empty(&cpu_mask))
-			xc2((smpfunc_t) local_ops->tlb_page,
-			    (unsigned long) vma, page);
+		if (any_other_mm_cpus(mm))
+			xc2(local_ops->tlb_page, (unsigned long)vma, page);
 		local_ops->tlb_page(vma, page);
 	}
 }
@@ -1753,19 +1731,15 @@ static void smp_flush_page_to_ram(unsigned long page)
 	 * XXX This experiment failed, research further... -DaveM
 	 */
 #if 1
-	xc1((smpfunc_t) local_ops->page_to_ram, page);
+	xc1(local_ops->page_to_ram, page);
 #endif
 	local_ops->page_to_ram(page);
 }
 
 static void smp_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr)
 {
-	cpumask_t cpu_mask;
-	cpumask_copy(&cpu_mask, mm_cpumask(mm));
-	cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
-	if (!cpumask_empty(&cpu_mask))
-		xc2((smpfunc_t) local_ops->sig_insns,
-		    (unsigned long) mm, insn_addr);
+	if (any_other_mm_cpus(mm))
+		xc2(local_ops->sig_insns, (unsigned long)mm, insn_addr);
 	local_ops->sig_insns(mm, insn_addr);
 }
 
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 9a725547578e..a35ddcca5e76 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -52,8 +52,10 @@ out:
 
 void arch_enter_lazy_mmu_mode(void)
 {
-	struct tlb_batch *tb = this_cpu_ptr(&tlb_batch);
+	struct tlb_batch *tb;
 
+	preempt_disable();
+	tb = this_cpu_ptr(&tlb_batch);
 	tb->active = 1;
 }
 
@@ -64,6 +66,7 @@ void arch_leave_lazy_mmu_mode(void)
 	if (tb->tlb_nr)
 		flush_tlb_pending();
 	tb->active = 0;
+	preempt_enable();
 }
 
 static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
@@ -118,6 +121,7 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 		unsigned long paddr, pfn = pte_pfn(orig);
 		struct address_space *mapping;
 		struct page *page;
+		struct folio *folio;
 
 		if (!pfn_valid(pfn))
 			goto no_cache_flush;
@@ -127,13 +131,14 @@ void tlb_batch_add(struct mm_struct *mm, unsigned long vaddr,
 			goto no_cache_flush;
 
 		/* A real file page? */
-		mapping = page_mapping_file(page);
+		folio = page_folio(page);
+		mapping = folio_flush_mapping(folio);
 		if (!mapping)
 			goto no_cache_flush;
 
 		paddr = (unsigned long) page_address(page);
 		if ((paddr ^ vaddr) & (1 << 13))
-			flush_dcache_page_all(mm, page);
+			flush_dcache_folio_all(mm, folio);
 	}
 
 no_cache_flush:
@@ -149,6 +154,8 @@ static void tlb_batch_pmd_scan(struct mm_struct *mm, unsigned long vaddr,
 	pte_t *pte;
 
 	pte = pte_offset_map(&pmd, vaddr);
+	if (!pte)
+		return;
 	end = vaddr + HPAGE_SIZE;
 	while (vaddr < end) {
 		if (pte_val(*pte) & _PAGE_VALID) {
@@ -179,12 +186,12 @@ static void __set_pmd_acct(struct mm_struct *mm, unsigned long addr,
 		 * hugetlb_pte_count.
 		 */
 		if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
-			if (is_huge_zero_page(pmd_page(pmd)))
+			if (is_huge_zero_pmd(pmd))
 				mm->context.hugetlb_pte_count++;
 			else
 				mm->context.thp_pte_count++;
 		} else {
-			if (is_huge_zero_page(pmd_page(orig)))
+			if (is_huge_zero_pmd(orig))
 				mm->context.hugetlb_pte_count--;
 			else
 				mm->context.thp_pte_count--;
@@ -245,6 +252,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 {
 	pmd_t old, entry;
 
+	VM_WARN_ON_ONCE(!pmd_present(*pmdp));
 	entry = __pmd(pmd_val(*pmdp) & ~_PAGE_VALID);
 	old = pmdp_establish(vma, address, pmdp, entry);
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
@@ -255,7 +263,7 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 	 * Sanity check pmd before doing the actual decrement.
 	 */
 	if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
-	    !is_huge_zero_page(pmd_page(entry)))
+	    !is_huge_zero_pmd(entry))
 		(vma->vm_mm)->context.thp_pte_count--;
 
 	return old;
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 0dce4b7ff73e..5fe52a64c7e7 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -266,7 +266,7 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	default:
 		printk(KERN_ERR "TSB[%s:%d]: Impossible TSB size %lu, killing process.\n",
 		       current->comm, current->pid, tsb_bytes);
-		do_exit(SIGSEGV);
+		BUG();
 	}
 	tte |= pte_sz_bits(page_sz);
 
@@ -385,7 +385,7 @@ static unsigned long tsb_size_to_rss_limit(unsigned long new_size)
  * will not trigger any longer.
  *
  * The TSB can be anywhere from 8K to 1MB in size, in increasing powers
- * of two.  The TSB must be aligned to it's size, so f.e. a 512K TSB
+ * of two.  The TSB must be aligned to its size, so f.e. a 512K TSB
  * must be 512K aligned.  It also must be physically contiguous, so we
  * cannot use vmalloc().
  *
@@ -402,8 +402,8 @@ void tsb_grow(struct mm_struct *mm, unsigned long tsb_index, unsigned long rss)
 	unsigned long new_rss_limit;
 	gfp_t gfp_flags;
 
-	if (max_tsb_size > (PAGE_SIZE << MAX_ORDER))
-		max_tsb_size = (PAGE_SIZE << MAX_ORDER);
+	if (max_tsb_size > PAGE_SIZE << MAX_PAGE_ORDER)
+		max_tsb_size = PAGE_SIZE << MAX_PAGE_ORDER;
 
 	new_cache_index = 0;
 	for (new_size = 8192; new_size < max_tsb_size; new_size <<= 1UL) {