1 files changed, 246 insertions, 170 deletions

diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index d2b59441ebdd..4652e868663b 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -1,12 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SPARC64 Huge TLB page support.
  *
  * Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
  */
 
-#include <linux/init.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/hugetlb.h>
 #include <linux/pagemap.h>
 #include <linux/sysctl.h>
@@ -18,224 +19,299 @@
 #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
- */
-#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL))
-#define VA_EXCLUDE_END   (0xfffff80000000000UL + (1UL << 32UL))
-
-static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
-							unsigned long addr,
-							unsigned long len,
-							unsigned long pgoff,
-							unsigned long flags)
+
+static pte_t sun4u_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 {
-	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 & ~HPAGE_MASK;
-	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);
+	unsigned long hugepage_size = _PAGE_SZ4MB_4U;
+
+	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4U;
+
+	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);
 	}
 
-	return addr;
+	pte_val(entry) = pte_val(entry) | hugepage_size;
+	return entry;
 }
 
-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 sun4v_hugepage_shift_to_tte(pte_t entry, unsigned int shift)
 {
-	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 & ~HPAGE_MASK;
-	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_4V;
+
+	pte_val(entry) = pte_val(entry) & ~_PAGE_SZALL_4V;
+
+	switch (shift) {
+	case HPAGE_16GB_SHIFT:
+		hugepage_size = _PAGE_SZ16GB_4V;
+		pte_val(entry) |= _PAGE_PUD_HUGE;
+		break;
+	case HPAGE_2GB_SHIFT:
+		hugepage_size = _PAGE_SZ2GB_4V;
+		pte_val(entry) |= _PAGE_PMD_HUGE;
+		break;
+	case HPAGE_256MB_SHIFT:
+		hugepage_size = _PAGE_SZ256MB_4V;
+		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_4V;
+		break;
+	default:
+		WARN_ONCE(1, "unsupported hugepage shift=%u\n", shift);
 	}
 
-	return addr;
+	pte_val(entry) = pte_val(entry) | hugepage_size;
+	return entry;
+}
+
+static pte_t hugepage_shift_to_tte(pte_t entry, unsigned int shift)
+{
+	if (tlb_type == hypervisor)
+		return sun4v_hugepage_shift_to_tte(entry, shift);
+	else
+		return sun4u_hugepage_shift_to_tte(entry, shift);
+}
+
+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
+	/* If this vma has ADI enabled on it, turn on TTE.mcd
+	 */
+	if (flags & VM_SPARC_ADI)
+		return pte_mkmcd(pte);
+	else
+		return pte_mknotmcd(pte);
+#else
+	return pte;
+#endif
 }
 
-unsigned long
-hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-		unsigned long len, unsigned long pgoff, unsigned long flags)
+static unsigned int sun4v_huge_tte_to_shift(pte_t entry)
 {
-	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 & ~HPAGE_MASK)
-		return -EINVAL;
-	if (len > task_size)
-		return -ENOMEM;
-
-	if (flags & MAP_FIXED) {
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-		return addr;
+	unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4V;
+	unsigned int shift;
+
+	switch (tte_szbits) {
+	case _PAGE_SZ16GB_4V:
+		shift = HPAGE_16GB_SHIFT;
+		break;
+	case _PAGE_SZ2GB_4V:
+		shift = HPAGE_2GB_SHIFT;
+		break;
+	case _PAGE_SZ256MB_4V:
+		shift = HPAGE_256MB_SHIFT;
+		break;
+	case _PAGE_SZ4MB_4V:
+		shift = REAL_HPAGE_SHIFT;
+		break;
+	case _PAGE_SZ64K_4V:
+		shift = HPAGE_64K_SHIFT;
+		break;
+	default:
+		shift = PAGE_SHIFT;
+		break;
 	}
+	return shift;
+}
 
-	if (addr) {
-		addr = ALIGN(addr, HPAGE_SIZE);
-		vma = find_vma(mm, addr);
-		if (task_size - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
-			return addr;
+static unsigned int sun4u_huge_tte_to_shift(pte_t entry)
+{
+	unsigned long tte_szbits = pte_val(entry) & _PAGE_SZALL_4U;
+	unsigned int shift;
+
+	switch (tte_szbits) {
+	case _PAGE_SZ256MB_4U:
+		shift = HPAGE_256MB_SHIFT;
+		break;
+	case _PAGE_SZ4MB_4U:
+		shift = REAL_HPAGE_SHIFT;
+		break;
+	case _PAGE_SZ64K_4U:
+		shift = HPAGE_64K_SHIFT;
+		break;
+	default:
+		shift = PAGE_SHIFT;
+		break;
 	}
-	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);
+	return shift;
 }
 
-pte_t *huge_pte_alloc(struct mm_struct *mm,
+static unsigned long tte_to_shift(pte_t entry)
+{
+	if (tlb_type == hypervisor)
+		return sun4v_huge_tte_to_shift(entry);
+
+	return sun4u_huge_tte_to_shift(entry);
+}
+
+static unsigned int huge_tte_to_shift(pte_t entry)
+{
+	unsigned long shift = tte_to_shift(entry);
+
+	if (shift == PAGE_SHIFT)
+		WARN_ONCE(1, "tto_to_shift: invalid hugepage tte=0x%lx\n",
+			  pte_val(entry));
+
+	return shift;
+}
+
+static unsigned long huge_tte_to_size(pte_t pte)
+{
+	unsigned long size = 1UL << huge_tte_to_shift(pte);
+
+	if (size == REAL_HPAGE_SIZE)
+		size = HPAGE_SIZE;
+	return size;
+}
+
+unsigned long pud_leaf_size(pud_t pud) { return 1UL << tte_to_shift(*(pte_t *)&pud); }
+unsigned long pmd_leaf_size(pmd_t pmd) { return 1UL << tte_to_shift(*(pte_t *)&pmd); }
+unsigned long pte_leaf_size(pte_t pte) { return 1UL << tte_to_shift(pte); }
+
+pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte = NULL;
-
-	/* We must align the address, because our caller will run
-	 * set_huge_pte_at() on whatever we return, which writes out
-	 * all of the sub-ptes for the hugepage range.  So we have
-	 * to give it the first such sub-pte.
-	 */
-	addr &= HPAGE_MASK;
 
 	pgd = pgd_offset(mm, addr);
-	pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd = pmd_alloc(mm, pud, addr);
-		if (pmd)
-			pte = pte_alloc_map(mm, NULL, pmd, addr);
-	}
-	return pte;
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	if (sz >= PUD_SIZE)
+		return (pte_t *)pud;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+	if (sz >= PMD_SIZE)
+		return (pte_t *)pmd;
+	return pte_alloc_huge(mm, pmd, addr);
 }
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
-	pte_t *pte = NULL;
-
-	addr &= HPAGE_MASK;
 
 	pgd = pgd_offset(mm, addr);
-	if (!pgd_none(*pgd)) {
-		pud = pud_offset(pgd, addr);
-		if (!pud_none(*pud)) {
-			pmd = pmd_offset(pud, addr);
-			if (!pmd_none(*pmd))
-				pte = pte_offset_map(pmd, addr);
-		}
-	}
-	return pte;
+	if (pgd_none(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, addr);
+	if (pud_none(*pud))
+		return NULL;
+	if (is_hugetlb_pud(*pud))
+		return (pte_t *)pud;
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return NULL;
+	if (is_hugetlb_pmd(*pmd))
+		return (pte_t *)pmd;
+	return pte_offset_huge(pmd, addr);
 }
 
-int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		     pte_t *ptep, pte_t entry)
 {
-	return 0;
+	unsigned int nptes, orig_shift, shift;
+	unsigned long i, size;
+	pte_t orig;
+
+	size = huge_tte_to_size(entry);
+
+	shift = PAGE_SHIFT;
+	if (size >= PUD_SIZE)
+		shift = PUD_SHIFT;
+	else if (size >= PMD_SIZE)
+		shift = PMD_SHIFT;
+	else
+		shift = PAGE_SHIFT;
+
+	nptes = size >> shift;
+
+	if (!pte_present(*ptep) && pte_present(entry))
+		mm->context.hugetlb_pte_count += nptes;
+
+	addr &= ~(size - 1);
+	orig = *ptep;
+	orig_shift = pte_none(orig) ? PAGE_SHIFT : huge_tte_to_shift(orig);
+
+	for (i = 0; i < nptes; i++)
+		ptep[i] = __pte(pte_val(entry) + (i << shift));
+
+	maybe_tlb_batch_add(mm, addr, ptep, orig, 0, orig_shift);
+	/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
+	if (size == HPAGE_SIZE)
+		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, orig, 0,
+				    orig_shift);
 }
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-		     pte_t *ptep, pte_t entry)
+		     pte_t *ptep, pte_t entry, unsigned long sz)
 {
-	int i;
-
-	if (!pte_present(*ptep) && pte_present(entry))
-		mm->context.huge_pte_count++;
-
-	addr &= HPAGE_MASK;
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, ptep, entry);
-		ptep++;
-		addr += PAGE_SIZE;
-		pte_val(entry) += PAGE_SIZE;
-	}
+	__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;
 	pte_t entry;
-	int i;
 
 	entry = *ptep;
-	if (pte_present(entry))
-		mm->context.huge_pte_count--;
+	size = huge_tte_to_size(entry);
 
-	addr &= HPAGE_MASK;
-
-	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		pte_clear(mm, addr, ptep);
-		addr += PAGE_SIZE;
-		ptep++;
-	}
+	shift = PAGE_SHIFT;
+	if (size >= PUD_SIZE)
+		shift = PUD_SHIFT;
+	else if (size >= PMD_SIZE)
+		shift = PMD_SHIFT;
+	else
+		shift = PAGE_SHIFT;
 
-	return entry;
-}
+	nptes = size >> shift;
+	orig_shift = pte_none(entry) ? PAGE_SHIFT : huge_tte_to_shift(entry);
 
-struct page *follow_huge_addr(struct mm_struct *mm,
-			      unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
+	if (pte_present(entry))
+		mm->context.hugetlb_pte_count -= nptes;
 
-int pmd_huge(pmd_t pmd)
-{
-	return 0;
-}
+	addr &= ~(size - 1);
+	for (i = 0; i < nptes; i++)
+		ptep[i] = __pte(0UL);
 
-int pud_huge(pud_t pud)
-{
-	return 0;
-}
+	maybe_tlb_batch_add(mm, addr, ptep, entry, 0, orig_shift);
+	/* An HPAGE_SIZE'ed page is composed of two REAL_HPAGE_SIZE'ed pages */
+	if (size == HPAGE_SIZE)
+		maybe_tlb_batch_add(mm, addr + REAL_HPAGE_SIZE, ptep, entry, 0,
+				    orig_shift);
 
-struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-			     pmd_t *pmd, int write)
-{
-	return NULL;
+	return entry;
 }