arm64/mm: new ptep layer to manage contig bit

Create a new layer for the in-table PTE manipulation APIs.  For now, The
existing API is prefixed with double underscore to become the arch-private
API and the public API is just a simple wrapper that calls the private
API.

The public API implementation will subsequently be used to transparently
manipulate the contiguous bit where appropriate.  But since there are
already some contig-aware users (e.g.  hugetlb, kernel mapper), we must
first ensure those users use the private API directly so that the future
contig-bit manipulations in the public API do not interfere with those
existing uses.

The following APIs are treated this way:

 - ptep_get
 - set_pte
 - set_ptes
 - pte_clear
 - ptep_get_and_clear
 - ptep_test_and_clear_young
 - ptep_clear_flush_young
 - ptep_set_wrprotect
 - ptep_set_access_flags

Link: https://lkml.kernel.org/r/20240215103205.2607016-11-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: John Hubbard <jhubbard@nvidia.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Borislav Petkov (AMD) <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morse <james.morse@arm.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

7 files changed, 44 insertions, 44 deletions

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 3235e23309ec..9a1c66183d16 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -191,7 +191,7 @@ static void show_pte(unsigned long addr)
 		if (!ptep)
 			break;
 
-		pte = ptep_get(ptep);
+		pte = __ptep_get(ptep);
 		pr_cont(", pte=%016llx", pte_val(pte));
 		pte_unmap(ptep);
 	} while(0);
@@ -205,16 +205,16 @@ static void show_pte(unsigned long addr)
  *
  * It needs to cope with hardware update of the accessed/dirty state by other
  * agents in the system and can safely skip the __sync_icache_dcache() call as,
- * like set_ptes(), the PTE is never changed from no-exec to exec here.
+ * like __set_ptes(), the PTE is never changed from no-exec to exec here.
  *
  * Returns whether or not the PTE actually changed.
  */
-int ptep_set_access_flags(struct vm_area_struct *vma,
-			  unsigned long address, pte_t *ptep,
-			  pte_t entry, int dirty)
+int __ptep_set_access_flags(struct vm_area_struct *vma,
+			    unsigned long address, pte_t *ptep,
+			    pte_t entry, int dirty)
 {
 	pteval_t old_pteval, pteval;
-	pte_t pte = ptep_get(ptep);
+	pte_t pte = __ptep_get(ptep);
 
 	if (pte_same(pte, entry))
 		return 0;
diff --git a/arch/arm64/mm/fixmap.c b/arch/arm64/mm/fixmap.c
index c0a3301203bd..bfc02568805a 100644
--- a/arch/arm64/mm/fixmap.c
+++ b/arch/arm64/mm/fixmap.c
@@ -121,9 +121,9 @@ void __set_fixmap(enum fixed_addresses idx,
 	ptep = fixmap_pte(addr);
 
 	if (pgprot_val(flags)) {
-		set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
+		__set_pte(ptep, pfn_pte(phys >> PAGE_SHIFT, flags));
 	} else {
-		pte_clear(&init_mm, addr, ptep);
+		__pte_clear(&init_mm, addr, ptep);
 		flush_tlb_kernel_range(addr, addr+PAGE_SIZE);
 	}
 }
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 48e8b429879d..0f0e10bb0a95 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -145,14 +145,14 @@ pte_t huge_ptep_get(pte_t *ptep)
 {
 	int ncontig, i;
 	size_t pgsize;
-	pte_t orig_pte = ptep_get(ptep);
+	pte_t orig_pte = __ptep_get(ptep);
 
 	if (!pte_present(orig_pte) || !pte_cont(orig_pte))
 		return orig_pte;
 
 	ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize);
 	for (i = 0; i < ncontig; i++, ptep++) {
-		pte_t pte = ptep_get(ptep);
+		pte_t pte = __ptep_get(ptep);
 
 		if (pte_dirty(pte))
 			orig_pte = pte_mkdirty(orig_pte);
@@ -177,11 +177,11 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = ptep_get(ptep);
+	pte_t orig_pte = __ptep_get(ptep);
 	unsigned long i;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
 
 		/*
 		 * If HW_AFDBM is enabled, then the HW could turn on
@@ -229,7 +229,7 @@ static void clear_flush(struct mm_struct *mm,
 	unsigned long i, saddr = addr;
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
-		ptep_get_and_clear(mm, addr, ptep);
+		__ptep_get_and_clear(mm, addr, ptep);
 
 	flush_tlb_range(&vma, saddr, addr);
 }
@@ -247,12 +247,12 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 	if (!pte_present(pte)) {
 		for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-			set_ptes(mm, addr, ptep, pte, 1);
+			__set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
 	if (!pte_cont(pte)) {
-		set_ptes(mm, addr, ptep, pte, 1);
+		__set_ptes(mm, addr, ptep, pte, 1);
 		return;
 	}
 
@@ -263,7 +263,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	clear_flush(mm, addr, ptep, pgsize, ncontig);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -393,7 +393,7 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 	ncontig = num_contig_ptes(sz, &pgsize);
 
 	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
-		pte_clear(mm, addr, ptep);
+		__pte_clear(mm, addr, ptep);
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
@@ -401,10 +401,10 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = ptep_get(ptep);
+	pte_t orig_pte = __ptep_get(ptep);
 
 	if (!pte_cont(orig_pte))
-		return ptep_get_and_clear(mm, addr, ptep);
+		return __ptep_get_and_clear(mm, addr, ptep);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
@@ -424,11 +424,11 @@ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
 {
 	int i;
 
-	if (pte_write(pte) != pte_write(ptep_get(ptep)))
+	if (pte_write(pte) != pte_write(__ptep_get(ptep)))
 		return 1;
 
 	for (i = 0; i < ncontig; i++) {
-		pte_t orig_pte = ptep_get(ptep + i);
+		pte_t orig_pte = __ptep_get(ptep + i);
 
 		if (pte_dirty(pte) != pte_dirty(orig_pte))
 			return 1;
@@ -452,7 +452,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	pte_t orig_pte;
 
 	if (!pte_cont(pte))
-		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+		return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
@@ -471,7 +471,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 
 	return 1;
 }
@@ -485,8 +485,8 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	size_t pgsize;
 	pte_t pte;
 
-	if (!pte_cont(ptep_get(ptep))) {
-		ptep_set_wrprotect(mm, addr, ptep);
+	if (!pte_cont(__ptep_get(ptep))) {
+		__ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
 
@@ -500,7 +500,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	pfn = pte_pfn(pte);
 
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
-		set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
+		__set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1);
 }
 
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
@@ -510,7 +510,7 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 	size_t pgsize;
 	int ncontig;
 
-	if (!pte_cont(ptep_get(ptep)))
+	if (!pte_cont(__ptep_get(ptep)))
 		return ptep_clear_flush(vma, addr, ptep);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
@@ -543,7 +543,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		 * when the permission changes from executable to non-executable
 		 * in cases where cpu is affected with errata #2645198.
 		 */
-		if (pte_user_exec(ptep_get(ptep)))
+		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
 	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c
index c2a9f4f6c7dd..9ee16cfce587 100644
--- a/arch/arm64/mm/kasan_init.c
+++ b/arch/arm64/mm/kasan_init.c
@@ -112,8 +112,8 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
 		if (!early)
 			memset(__va(page_phys), KASAN_SHADOW_INIT, PAGE_SIZE);
 		next = addr + PAGE_SIZE;
-		set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
-	} while (ptep++, addr = next, addr != end && pte_none(ptep_get(ptep)));
+		__set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+	} while (ptep++, addr = next, addr != end && pte_none(__ptep_get(ptep)));
 }
 
 static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
@@ -271,7 +271,7 @@ static void __init kasan_init_shadow(void)
 	 * so we should make sure that it maps the zero page read-only.
 	 */
 	for (i = 0; i < PTRS_PER_PTE; i++)
-		set_pte(&kasan_early_shadow_pte[i],
+		__set_pte(&kasan_early_shadow_pte[i],
 			pfn_pte(sym_to_pfn(kasan_early_shadow_page),
 				PAGE_KERNEL_RO));
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 343629a17042..6208c7541f87 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -173,16 +173,16 @@ static void init_pte(pmd_t *pmdp, unsigned long addr, unsigned long end,
 
 	ptep = pte_set_fixmap_offset(pmdp, addr);
 	do {
-		pte_t old_pte = ptep_get(ptep);
+		pte_t old_pte = __ptep_get(ptep);
 
-		set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
+		__set_pte(ptep, pfn_pte(__phys_to_pfn(phys), prot));
 
 		/*
 		 * After the PTE entry has been populated once, we
 		 * only allow updates to the permission attributes.
 		 */
 		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte),
-					      pte_val(ptep_get(ptep))));
+					      pte_val(__ptep_get(ptep))));
 
 		phys += PAGE_SIZE;
 	} while (ptep++, addr += PAGE_SIZE, addr != end);
@@ -852,12 +852,12 @@ static void unmap_hotplug_pte_range(pmd_t *pmdp, unsigned long addr,
 
 	do {
 		ptep = pte_offset_kernel(pmdp, addr);
-		pte = ptep_get(ptep);
+		pte = __ptep_get(ptep);
 		if (pte_none(pte))
 			continue;
 
 		WARN_ON(!pte_present(pte));
-		pte_clear(&init_mm, addr, ptep);
+		__pte_clear(&init_mm, addr, ptep);
 		flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 		if (free_mapped)
 			free_hotplug_page_range(pte_page(pte),
@@ -985,7 +985,7 @@ static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
 
 	do {
 		ptep = pte_offset_kernel(pmdp, addr);
-		pte = ptep_get(ptep);
+		pte = __ptep_get(ptep);
 
 		/*
 		 * This is just a sanity check here which verifies that
@@ -1004,7 +1004,7 @@ static void free_empty_pte_table(pmd_t *pmdp, unsigned long addr,
 	 */
 	ptep = pte_offset_kernel(pmdp, 0UL);
 	for (i = 0; i < PTRS_PER_PTE; i++) {
-		if (!pte_none(ptep_get(&ptep[i])))
+		if (!pte_none(__ptep_get(&ptep[i])))
 			return;
 	}
 
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 73a5e8f82586..0c4e3ecf989d 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -36,12 +36,12 @@ bool can_set_direct_map(void)
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
 {
 	struct page_change_data *cdata = data;
-	pte_t pte = ptep_get(ptep);
+	pte_t pte = __ptep_get(ptep);
 
 	pte = clear_pte_bit(pte, cdata->clear_mask);
 	pte = set_pte_bit(pte, cdata->set_mask);
 
-	set_pte(ptep, pte);
+	__set_pte(ptep, pte);
 	return 0;
 }
 
@@ -245,5 +245,5 @@ bool kernel_page_present(struct page *page)
 		return true;
 
 	ptep = pte_offset_kernel(pmdp, addr);
-	return pte_valid(ptep_get(ptep));
+	return pte_valid(__ptep_get(ptep));
 }
diff --git a/arch/arm64/mm/trans_pgd.c b/arch/arm64/mm/trans_pgd.c
index f71ab4704cce..5139a28130c0 100644
--- a/arch/arm64/mm/trans_pgd.c
+++ b/arch/arm64/mm/trans_pgd.c
@@ -33,7 +33,7 @@ static void *trans_alloc(struct trans_pgd_info *info)
 
 static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 {
-	pte_t pte = ptep_get(src_ptep);
+	pte_t pte = __ptep_get(src_ptep);
 
 	if (pte_valid(pte)) {
 		/*
@@ -41,7 +41,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 		 * read only (code, rodata). Clear the RDONLY bit from
 		 * the temporary mappings we use during restore.
 		 */
-		set_pte(dst_ptep, pte_mkwrite_novma(pte));
+		__set_pte(dst_ptep, pte_mkwrite_novma(pte));
 	} else if ((debug_pagealloc_enabled() ||
 		   is_kfence_address((void *)addr)) && !pte_none(pte)) {
 		/*
@@ -55,7 +55,7 @@ static void _copy_pte(pte_t *dst_ptep, pte_t *src_ptep, unsigned long addr)
 		 */
 		BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-		set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte)));
+		__set_pte(dst_ptep, pte_mkpresent(pte_mkwrite_novma(pte)));
 	}
 }