summaryrefslogtreecommitdiffstats
path: root/mm/hugetlb.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/hugetlb.c')
-rw-r--r--mm/hugetlb.c106
1 files changed, 67 insertions, 39 deletions
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index d26162e81fea..abc1c5fb7222 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -832,8 +832,27 @@ static bool vma_has_reserves(struct vm_area_struct *vma, long chg)
* Only the process that called mmap() has reserves for
* private mappings.
*/
- if (is_vma_resv_set(vma, HPAGE_RESV_OWNER))
- return true;
+ if (is_vma_resv_set(vma, HPAGE_RESV_OWNER)) {
+ /*
+ * Like the shared case above, a hole punch or truncate
+ * could have been performed on the private mapping.
+ * Examine the value of chg to determine if reserves
+ * actually exist or were previously consumed.
+ * Very Subtle - The value of chg comes from a previous
+ * call to vma_needs_reserves(). The reserve map for
+ * private mappings has different (opposite) semantics
+ * than that of shared mappings. vma_needs_reserves()
+ * has already taken this difference in semantics into
+ * account. Therefore, the meaning of chg is the same
+ * as in the shared case above. Code could easily be
+ * combined, but keeping it separate draws attention to
+ * subtle differences.
+ */
+ if (chg)
+ return false;
+ else
+ return true;
+ }
return false;
}
@@ -1003,7 +1022,9 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
((node = hstate_next_node_to_free(hs, mask)) || 1); \
nr_nodes--)
-#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA))
+#if (defined(CONFIG_X86_64) || defined(CONFIG_S390)) && \
+ ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || \
+ defined(CONFIG_CMA))
static void destroy_compound_gigantic_page(struct page *page,
unsigned int order)
{
@@ -1011,6 +1032,7 @@ static void destroy_compound_gigantic_page(struct page *page,
int nr_pages = 1 << order;
struct page *p = page + 1;
+ atomic_set(compound_mapcount_ptr(page), 0);
for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) {
clear_compound_head(p);
set_page_refcounted(p);
@@ -1816,6 +1838,25 @@ static long __vma_reservation_common(struct hstate *h,
if (vma->vm_flags & VM_MAYSHARE)
return ret;
+ else if (is_vma_resv_set(vma, HPAGE_RESV_OWNER) && ret >= 0) {
+ /*
+ * In most cases, reserves always exist for private mappings.
+ * However, a file associated with mapping could have been
+ * hole punched or truncated after reserves were consumed.
+ * As subsequent fault on such a range will not use reserves.
+ * Subtle - The reserve map for private mappings has the
+ * opposite meaning than that of shared mappings. If NO
+ * entry is in the reserve map, it means a reservation exists.
+ * If an entry exists in the reserve map, it means the
+ * reservation has already been consumed. As a result, the
+ * return value of this routine is the opposite of the
+ * value returned from reserve map manipulation routines above.
+ */
+ if (ret)
+ return 0;
+ else
+ return 1;
+ }
else
return ret < 0 ? ret : 0;
}
@@ -3138,7 +3179,6 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
unsigned long start, unsigned long end,
struct page *ref_page)
{
- int force_flush = 0;
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
pte_t *ptep;
@@ -3157,19 +3197,22 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
tlb_start_vma(tlb, vma);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
address = start;
-again:
for (; address < end; address += sz) {
ptep = huge_pte_offset(mm, address);
if (!ptep)
continue;
ptl = huge_pte_lock(h, mm, ptep);
- if (huge_pmd_unshare(mm, &address, ptep))
- goto unlock;
+ if (huge_pmd_unshare(mm, &address, ptep)) {
+ spin_unlock(ptl);
+ continue;
+ }
pte = huge_ptep_get(ptep);
- if (huge_pte_none(pte))
- goto unlock;
+ if (huge_pte_none(pte)) {
+ spin_unlock(ptl);
+ continue;
+ }
/*
* Migrating hugepage or HWPoisoned hugepage is already
@@ -3177,7 +3220,8 @@ again:
*/
if (unlikely(!pte_present(pte))) {
huge_pte_clear(mm, address, ptep);
- goto unlock;
+ spin_unlock(ptl);
+ continue;
}
page = pte_page(pte);
@@ -3187,9 +3231,10 @@ again:
* are about to unmap is the actual page of interest.
*/
if (ref_page) {
- if (page != ref_page)
- goto unlock;
-
+ if (page != ref_page) {
+ spin_unlock(ptl);
+ continue;
+ }
/*
* Mark the VMA as having unmapped its page so that
* future faults in this VMA will fail rather than
@@ -3205,30 +3250,14 @@ again:
hugetlb_count_sub(pages_per_huge_page(h), mm);
page_remove_rmap(page, true);
- force_flush = !__tlb_remove_page(tlb, page);
- if (force_flush) {
- address += sz;
- spin_unlock(ptl);
- break;
- }
- /* Bail out after unmapping reference page if supplied */
- if (ref_page) {
- spin_unlock(ptl);
- break;
- }
-unlock:
+
spin_unlock(ptl);
- }
- /*
- * mmu_gather ran out of room to batch pages, we break out of
- * the PTE lock to avoid doing the potential expensive TLB invalidate
- * and page-free while holding it.
- */
- if (force_flush) {
- force_flush = 0;
- tlb_flush_mmu(tlb);
- if (address < end && !ref_page)
- goto again;
+ tlb_remove_page_size(tlb, page, huge_page_size(h));
+ /*
+ * Bail out after unmapping reference page if supplied
+ */
+ if (ref_page)
+ break;
}
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
tlb_end_vma(tlb, vma);
@@ -3344,7 +3373,7 @@ retry_avoidcopy:
/* If no-one else is actually using this page, avoid the copy
* and just make the page writable */
if (page_mapcount(old_page) == 1 && PageAnon(old_page)) {
- page_move_anon_rmap(old_page, vma, address);
+ page_move_anon_rmap(old_page, vma);
set_huge_ptep_writable(vma, address, ptep);
return 0;
}
@@ -4190,7 +4219,6 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (saddr) {
spte = huge_pte_offset(svma->vm_mm, saddr);
if (spte) {
- mm_inc_nr_pmds(mm);
get_page(virt_to_page(spte));
break;
}
@@ -4205,9 +4233,9 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
if (pud_none(*pud)) {
pud_populate(mm, pud,
(pmd_t *)((unsigned long)spte & PAGE_MASK));
+ mm_inc_nr_pmds(mm);
} else {
put_page(virt_to_page(spte));
- mm_inc_nr_pmds(mm);
}
spin_unlock(ptl);
out: