/*
* Dissolve a given free hugepage into free buddy pages. This function does
* nothing for in-use (including surplus) hugepages. Returns -EBUSY if the
- * number of free hugepages would be reduced below the number of reserved
- * hugepages.
+ * dissolution fails because a give page is not a free hugepage, or because
+ * free hugepages are fully reserved.
*/
int dissolve_free_huge_page(struct page *page)
{
- int rc = 0;
+ int rc = -EBUSY;
spin_lock(&hugetlb_lock);
if (PageHuge(page) && !page_count(page)) {
struct page *head = compound_head(page);
struct hstate *h = page_hstate(head);
int nid = page_to_nid(head);
- if (h->free_huge_pages - h->resv_huge_pages == 0) {
- rc = -EBUSY;
+ if (h->free_huge_pages - h->resv_huge_pages == 0)
goto out;
- }
/*
* Move PageHWPoison flag from head page to the raw error page,
* which makes any subpages rather than the error page reusable.
h->free_huge_pages_node[nid]--;
h->max_huge_pages--;
update_and_free_page(h, head);
+ rc = 0;
}
out:
spin_unlock(&hugetlb_lock);
struct page *page;
struct hstate *h = hstate_vma(vma);
unsigned long sz = huge_page_size(h);
- const unsigned long mmun_start = start; /* For mmu_notifiers */
- const unsigned long mmun_end = end; /* For mmu_notifiers */
+ unsigned long mmun_start = start; /* For mmu_notifiers */
+ unsigned long mmun_end = end; /* For mmu_notifiers */
WARN_ON(!is_vm_hugetlb_page(vma));
BUG_ON(start & ~huge_page_mask(h));
*/
tlb_remove_check_page_size_change(tlb, sz);
tlb_start_vma(tlb, vma);
+
+ /*
+ * If sharing possible, alert mmu notifiers of worst case.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end);
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
address = start;
for (; address < end; address += sz) {
ptl = huge_pte_lock(h, mm, ptep);
if (huge_pmd_unshare(mm, &address, ptep)) {
spin_unlock(ptl);
+ /*
+ * We just unmapped a page of PMDs by clearing a PUD.
+ * The caller's TLB flush range should cover this area.
+ */
continue;
}
{
struct mm_struct *mm;
struct mmu_gather tlb;
+ unsigned long tlb_start = start;
+ unsigned long tlb_end = end;
+
+ /*
+ * If shared PMDs were possibly used within this vma range, adjust
+ * start/end for worst case tlb flushing.
+ * Note that we can not be sure if PMDs are shared until we try to
+ * unmap pages. However, we want to make sure TLB flushing covers
+ * the largest possible range.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end);
mm = vma->vm_mm;
- tlb_gather_mmu(&tlb, mm, start, end);
+ tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end);
__unmap_hugepage_range(&tlb, vma, start, end, ref_page);
- tlb_finish_mmu(&tlb, start, end);
+ tlb_finish_mmu(&tlb, tlb_start, tlb_end);
}
/*
* cannot race with other handlers or page migration.
* Keep the pte_same checks anyway to make transition from the mutex easier.
*/
-static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
+static vm_fault_t hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
struct page *pagecache_page, spinlock_t *ptl)
{
pte_t pte;
struct hstate *h = hstate_vma(vma);
struct page *old_page, *new_page;
- int ret = 0, outside_reserve = 0;
+ int outside_reserve = 0;
+ vm_fault_t ret = 0;
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
unsigned long haddr = address & huge_page_mask(h);
return 0;
}
- ret = (PTR_ERR(new_page) == -ENOMEM) ?
- VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ ret = vmf_error(PTR_ERR(new_page));
goto out_release_old;
}
return 0;
}
-static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
- struct address_space *mapping, pgoff_t idx,
- unsigned long address, pte_t *ptep, unsigned int flags)
+static vm_fault_t hugetlb_no_page(struct mm_struct *mm,
+ struct vm_area_struct *vma,
+ struct address_space *mapping, pgoff_t idx,
+ unsigned long address, pte_t *ptep, unsigned int flags)
{
struct hstate *h = hstate_vma(vma);
- int ret = VM_FAULT_SIGBUS;
+ vm_fault_t ret = VM_FAULT_SIGBUS;
int anon_rmap = 0;
unsigned long size;
struct page *page;
page = alloc_huge_page(vma, haddr, 0);
if (IS_ERR(page)) {
- ret = PTR_ERR(page);
- if (ret == -ENOMEM)
- ret = VM_FAULT_OOM;
- else
- ret = VM_FAULT_SIGBUS;
+ ret = vmf_error(PTR_ERR(page));
goto out;
}
clear_huge_page(page, address, pages_per_huge_page(h));
}
#endif
-int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags)
{
pte_t *ptep, entry;
spinlock_t *ptl;
- int ret;
+ vm_fault_t ret;
u32 hash;
pgoff_t idx;
struct page *page = NULL;
if (absent || is_swap_pte(huge_ptep_get(pte)) ||
((flags & FOLL_WRITE) &&
!huge_pte_write(huge_ptep_get(pte)))) {
- int ret;
+ vm_fault_t ret;
unsigned int fault_flags = 0;
if (pte)
pte_t pte;
struct hstate *h = hstate_vma(vma);
unsigned long pages = 0;
+ unsigned long f_start = start;
+ unsigned long f_end = end;
+ bool shared_pmd = false;
+
+ /*
+ * In the case of shared PMDs, the area to flush could be beyond
+ * start/end. Set f_start/f_end to cover the maximum possible
+ * range if PMD sharing is possible.
+ */
+ adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end);
BUG_ON(address >= end);
- flush_cache_range(vma, address, end);
+ flush_cache_range(vma, f_start, f_end);
- mmu_notifier_invalidate_range_start(mm, start, end);
+ mmu_notifier_invalidate_range_start(mm, f_start, f_end);
i_mmap_lock_write(vma->vm_file->f_mapping);
for (; address < end; address += huge_page_size(h)) {
spinlock_t *ptl;
if (huge_pmd_unshare(mm, &address, ptep)) {
pages++;
spin_unlock(ptl);
+ shared_pmd = true;
continue;
}
pte = huge_ptep_get(ptep);
* Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare
* may have cleared our pud entry and done put_page on the page table:
* once we release i_mmap_rwsem, another task can do the final put_page
- * and that page table be reused and filled with junk.
+ * and that page table be reused and filled with junk. If we actually
+ * did unshare a page of pmds, flush the range corresponding to the pud.
*/
- flush_hugetlb_tlb_range(vma, start, end);
+ if (shared_pmd)
+ flush_hugetlb_tlb_range(vma, f_start, f_end);
+ else
+ flush_hugetlb_tlb_range(vma, start, end);
/*
* No need to call mmu_notifier_invalidate_range() we are downgrading
* page table protection not changing it to point to a new page.
* See Documentation/vm/mmu_notifier.rst
*/
i_mmap_unlock_write(vma->vm_file->f_mapping);
- mmu_notifier_invalidate_range_end(mm, start, end);
+ mmu_notifier_invalidate_range_end(mm, f_start, f_end);
return pages << h->order;
}
/*
* check on proper vm_flags and page table alignment
*/
- if (vma->vm_flags & VM_MAYSHARE &&
- vma->vm_start <= base && end <= vma->vm_end)
+ if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end))
return true;
return false;
}
+/*
+ * Determine if start,end range within vma could be mapped by shared pmd.
+ * If yes, adjust start and end to cover range associated with possible
+ * shared pmd mappings.
+ */
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
+{
+ unsigned long check_addr = *start;
+
+ if (!(vma->vm_flags & VM_MAYSHARE))
+ return;
+
+ for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) {
+ unsigned long a_start = check_addr & PUD_MASK;
+ unsigned long a_end = a_start + PUD_SIZE;
+
+ /*
+ * If sharing is possible, adjust start/end if necessary.
+ */
+ if (range_in_vma(vma, a_start, a_end)) {
+ if (a_start < *start)
+ *start = a_start;
+ if (a_end > *end)
+ *end = a_end;
+ }
+ }
+}
+
/*
* Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc()
* and returns the corresponding pte. While this is not necessary for the
{
return 0;
}
+
+void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
+ unsigned long *start, unsigned long *end)
+{
+}
#define want_pmd_share() (0)
#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */