@@ -163,24 +163,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
unsigned long pgsize,
unsigned long ncontig)
{
- 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);
-
- /*
- * If HW_AFDBM is enabled, then the HW could turn on
- * the dirty or accessed bit for any page in the set,
- * so check them all.
- */
- if (pte_dirty(pte))
- orig_pte = pte_mkdirty(orig_pte);
-
- if (pte_young(pte))
- orig_pte = pte_mkyoung(orig_pte);
+ pte_t pte, tmp_pte;
+ bool present;
+
+ pte = __ptep_get_and_clear(mm, addr, ptep);
+ present = pte_present(pte);
+ while (--ncontig) {
+ ptep++;
+ addr += pgsize;
+ tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+ if (present) {
+ if (pte_dirty(tmp_pte))
+ pte = pte_mkdirty(pte);
+ if (pte_young(tmp_pte))
+ pte = pte_mkyoung(pte);
+ }
}
- return orig_pte;
+ return pte;
}
static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -401,13 +400,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
{
int ncontig;
size_t pgsize;
- pte_t orig_pte = __ptep_get(ptep);
-
- if (!pte_cont(orig_pte))
- return __ptep_get_and_clear(mm, addr, ptep);
-
- ncontig = find_num_contig(mm, addr, ptep, &pgsize);
+ ncontig = num_contig_ptes(sz, &pgsize);
return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
}
@@ -451,6 +445,8 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
pgprot_t hugeprot;
pte_t orig_pte;
+ VM_WARN_ON(!pte_present(pte));
+
if (!pte_cont(pte))
return __ptep_set_access_flags(vma, addr, ptep, pte, dirty);
@@ -461,6 +457,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
return 0;
orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig);
+ VM_WARN_ON(!pte_present(orig_pte));
/* Make sure we don't lose the dirty or young state */
if (pte_dirty(orig_pte))
@@ -485,7 +482,10 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
size_t pgsize;
pte_t pte;
- if (!pte_cont(__ptep_get(ptep))) {
+ pte = __ptep_get(ptep);
+ VM_WARN_ON(!pte_present(pte));
+
+ if (!pte_cont(pte)) {
__ptep_set_wrprotect(mm, addr, ptep);
return;
}
@@ -509,8 +509,12 @@ pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
struct mm_struct *mm = vma->vm_mm;
size_t pgsize;
int ncontig;
+ pte_t pte;
- if (!pte_cont(__ptep_get(ptep)))
+ pte = __ptep_get(ptep);
+ VM_WARN_ON(!pte_present(pte));
+
+ if (!pte_cont(pte))
return ptep_clear_flush(vma, addr, ptep);
ncontig = find_num_contig(mm, addr, ptep, &pgsize);
arm64 supports multiple huge_pte sizes. Some of the sizes are covered by a single pte entry at a particular level (PMD_SIZE, PUD_SIZE), and some are covered by multiple ptes at a particular level (CONT_PTE_SIZE, CONT_PMD_SIZE). So the function has to figure out the size from the huge_pte pointer. This was previously done by walking the pgtable to determine the level, then using the PTE_CONT bit to determine the number of ptes. But the PTE_CONT bit is only valid when the pte is present. For non-present pte values (e.g. markers, migration entries), the previous implementation was therefore erroniously determining the size. There is at least one known caller in core-mm, move_huge_pte(), which may call huge_ptep_get_and_clear() for a non-present pte. So we must be robust to this case. Additionally the "regular" ptep_get_and_clear() is robust to being called for non-present ptes so it makes sense to follow the behaviour. Fix this by using the new sz parameter which is now provided to the function. Additionally when clearing each pte in a contig range, don't gather the access and dirty bits if the pte is not present. An alternative approach that would not require API changes would be to store the PTE_CONT bit in a spare bit in the swap entry pte. But it felt cleaner to follow other APIs' lead and just pass in the size. While we are at it, add some debug warnings in functions that require the pte is present. As an aside, PTE_CONT is bit 52, which corresponds to bit 40 in the swap entry offset field (layout of non-present pte). Since hugetlb is never swapped to disk, this field will only be populated for markers, which always set this bit to 0 and hwpoison swap entries, which set the offset field to a PFN; So it would only ever be 1 for a 52-bit PVA system where memory in that high half was poisoned (I think!). So in practice, this bit would almost always be zero for non-present ptes and we would only clear the first entry if it was actually a contiguous block. That's probably a less severe symptom than if it was always interpretted as 1 and cleared out potentially-present neighboring PTEs. Cc: <stable@vger.kernel.org> Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit") Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> --- arch/arm64/mm/hugetlbpage.c | 54 ++++++++++++++++++++----------------- 1 file changed, 29 insertions(+), 25 deletions(-)