arm64: hugetlb: Add break-before-make logic for contiguous entries

It has become apparent that one has to take special care when modifying
attributes of memory mappings that employ the contiguous bit.

Both the requirement and the architecturally correct "Break-Before-Make"
technique of updating contiguous entries can be found described in:
ARM DDI 0487A.k_iss10775, "Misprogramming of the Contiguous bit",
page D4-1762.

The huge pte accessors currently replace the attributes of contiguous
pte entries in place thus can, on certain platforms, lead to TLB
conflict aborts or even erroneous results returned from TLB lookups.

This patch adds two helper functions -

* get_clear_flush(.) - clears a contiguous entry and returns the head
  pte (whilst taking care to retain dirty bit information that could
  have been modified by DBM).

* clear_flush(.) that clears a contiguous entry

A tlb invalidate is performed to then ensure that there is no
possibility of multiple tlb entries being present for the same region.

Cc: David Woods <dwoods@mellanox.com>
Signed-off-by: Steve Capper <steve.capper@arm.com>
(Added helper clear_flush(), updated commit log, and some cleanup)
Signed-off-by: Punit Agrawal <punit.agrawal@arm.com>
[catalin.marinas@arm.com: remove CONFIG_ARM64_HW_AFDBM check]
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/mm/hugetlbpage.c

@@ -68,6 +68,66 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	return CONT_PTES;
 }
 
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step.
+ */
+static pte_t get_clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	pte_t orig_pte = huge_ptep_get(ptep);
+	bool valid = pte_valid(orig_pte);
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
+		pte_t pte = ptep_get_and_clear(mm, addr, ptep);
+
+		/*
+		 * If HW_AFDBM is enabled, then the HW could turn on
+		 * the dirty bit for any page in the set, so check
+		 * them all.  All hugetlb entries are already young.
+		 */
+		if (pte_dirty(pte))
+			orig_pte = pte_mkdirty(orig_pte);
+	}
+
+	if (valid)
+		flush_tlb_range(&vma, saddr, addr);
+	return orig_pte;
+}
+
+/*
+ * Changing some bits of contiguous entries requires us to follow a
+ * Break-Before-Make approach, breaking the whole contiguous set
+ * before we can change any entries. See ARM DDI 0487A.k_iss10775,
+ * "Misprogramming of the Contiguous bit", page D4-1762.
+ *
+ * This helper performs the break step for use cases where the
+ * original pte is not needed.
+ */
+static void clear_flush(struct mm_struct *mm,
+			     unsigned long addr,
+			     pte_t *ptep,
+			     unsigned long pgsize,
+			     unsigned long ncontig)
+{
+	struct vm_area_struct vma = { .vm_mm = mm };
+	unsigned long i, saddr = addr;
+
+	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++)
+		pte_clear(mm, addr, ptep);
+
+	flush_tlb_range(&vma, saddr, addr);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte)
 {
@@ -93,6 +153,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 	dpfn = pgsize >> PAGE_SHIFT;
 	hugeprot = pte_pgprot(pte);
 
+	clear_flush(mm, addr, ptep, pgsize, ncontig);
+
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
 		pr_debug("%s: set pte %p to 0x%llx\n", __func__, ptep,
 			 pte_val(pfn_pte(pfn, hugeprot)));
@@ -194,25 +256,16 @@ pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep)
 {
-	int ncontig, i;
+	int ncontig;
 	size_t pgsize;
 	pte_t orig_pte = huge_ptep_get(ptep);
 
 	if (!pte_cont(orig_pte))
 		return ptep_get_and_clear(mm, addr, ptep);
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		/*
-		 * If HW_AFDBM is enabled, then the HW could
-		 * turn on the dirty bit for any of the page
-		 * in the set, so check them all.
-		 */
-		if (pte_dirty(ptep_get_and_clear(mm, addr, ptep)))
-			orig_pte = pte_mkdirty(orig_pte);
-	}
 
-	return orig_pte;
+	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
@@ -223,52 +276,69 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	size_t pgsize = 0;
 	unsigned long pfn = pte_pfn(pte), dpfn;
 	pgprot_t hugeprot;
+	pte_t orig_pte;
 
 	if (!pte_cont(pte))
 		return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
 
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
-	hugeprot = pte_pgprot(pte);
 
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) {
-		changed |= ptep_set_access_flags(vma, addr, ptep,
-				pfn_pte(pfn, hugeprot), dirty);
-	}
+	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	if (!pte_same(orig_pte, pte))
+		changed = 1;
+
+	/* Make sure we don't lose the dirty state */
+	if (pte_dirty(orig_pte))
+		pte = pte_mkdirty(pte);
+
+	hugeprot = pte_pgprot(pte);
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
 
 	return changed;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 			     unsigned long addr, pte_t *ptep)
 {
+	unsigned long pfn, dpfn;
+	pgprot_t hugeprot;
 	int ncontig, i;
 	size_t pgsize;
+	pte_t pte;
 
 	if (!pte_cont(*ptep)) {
 		ptep_set_wrprotect(mm, addr, ptep);
 		return;
 	}
 
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-		ptep_set_wrprotect(mm, addr, ptep);
+	dpfn = pgsize >> PAGE_SHIFT;
+
+	pte = get_clear_flush(mm, addr, ptep, pgsize, ncontig);
+	pte = pte_wrprotect(pte);
+
+	hugeprot = pte_pgprot(pte);
+	pfn = pte_pfn(pte);
+
+	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
+		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 }
 
 void huge_ptep_clear_flush(struct vm_area_struct *vma,
 			   unsigned long addr, pte_t *ptep)
 {
-	int ncontig, i;
 	size_t pgsize;
+	int ncontig;
 
 	if (!pte_cont(*ptep)) {
 		ptep_clear_flush(vma, addr, ptep);
 		return;
 	}
 
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
-	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize)
-		ptep_clear_flush(vma, addr, ptep);
+	clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
 }
 
 static __init int setup_hugepagesz(char *opt)