arm64: hugetlb: Restore TLB invalidation for BBM on contiguous ptes

Commit fb396bb4 ("arm64/hugetlb: Drop TLB flush from get_clear_flush()")
removed TLB invalidation from get_clear_flush() [now get_clear_contig()]
on the basis that the core TLB invalidation code is aware of hugetlb
mappings backed by contiguous page-table entries and will cover the
correct virtual address range.

However, this change also resulted in the TLB invalidation being removed
from the "break" step in the break-before-make (BBM) sequence used
internally by huge_ptep_set_{access_flags,wrprotect}(), therefore
making the BBM sequence unsafe irrespective of later invalidation.

Although the architecture is desperately unclear about how exactly
contiguous ptes should be updated in a live page-table, restore TLB
invalidation to our BBM sequence under the assumption that BBM is the
right thing to be doing in the first place.

Fixes: fb396bb4 ("arm64/hugetlb: Drop TLB flush from get_clear_flush()")
Cc: Ard Biesheuvel <ardb@kernel.org>
Cc: Steve Capper <steve.capper@arm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Marc Zyngier <maz@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Link: https://lore.kernel.org/r/20220629095349.25748-1-will@kernel.orgSigned-off-by: Catalin Marinas <catalin.marinas@arm.com>

arch/arm64/mm/hugetlbpage.c

@@ -214,6 +214,19 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 	return orig_pte;
 }
 
+static pte_t get_clear_contig_flush(struct mm_struct *mm,
+				    unsigned long addr,
+				    pte_t *ptep,
+				    unsigned long pgsize,
+				    unsigned long ncontig)
+{
+	pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig);
+	struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0);
+
+	flush_tlb_range(&vma, addr, addr + (pgsize * ncontig));
+	return orig_pte;
+}
+
 /*
  * Changing some bits of contiguous entries requires us to follow a
  * Break-Before-Make approach, breaking the whole contiguous set
@@ -447,19 +460,20 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int ncontig, i;
 	size_t pgsize = 0;
 	unsigned long pfn = pte_pfn(pte), dpfn;
+	struct mm_struct *mm = vma->vm_mm;
 	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);
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
 
 	if (!__cont_access_flags_changed(ptep, pte, ncontig))
 		return 0;
 
-	orig_pte = get_clear_contig(vma->vm_mm, addr, ptep, pgsize, ncontig);
+	orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
 
 	/* Make sure we don't lose the dirty or young state */
 	if (pte_dirty(orig_pte))
@@ -470,7 +484,7 @@ 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_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
+		set_pte_at(mm, addr, ptep, pfn_pte(pfn, hugeprot));
 
 	return 1;
 }
@@ -492,7 +506,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
 
-	pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig);
+	pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
 	pte = pte_wrprotect(pte);
 
 	hugeprot = pte_pgprot(pte);
@@ -505,17 +519,15 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 			    unsigned long addr, pte_t *ptep)
 {
+	struct mm_struct *mm = vma->vm_mm;
 	size_t pgsize;
 	int ncontig;
-	pte_t orig_pte;
 
 	if (!pte_cont(READ_ONCE(*ptep)))
 		return ptep_clear_flush(vma, addr, ptep);
 
-	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
-	orig_pte = get_clear_contig(vma->vm_mm, addr, ptep, pgsize, ncontig);
-	flush_tlb_range(vma, addr, addr + pgsize * ncontig);
-	return orig_pte;
+	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+	return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
 static int __init hugetlbpage_init(void)