@@ -226,9 +226,9 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
int advice);
-int madvise_collapse(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end);
+int madvise_collapse_thp(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end);
void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start,
unsigned long end, long adjust_next);
spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma);
@@ -373,9 +373,9 @@ static inline int hugepage_madvise(struct vm_area_struct *vma,
return -EINVAL;
}
-static inline int madvise_collapse(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end)
+static inline int madvise_collapse_thp(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
{
return -EINVAL;
}
@@ -1276,6 +1276,8 @@ int enable_hugetlb_hgm(struct vm_area_struct *vma);
int hugetlb_alloc_largest_pte(struct hugetlb_pte *hpte, struct mm_struct *mm,
struct vm_area_struct *vma, unsigned long start,
unsigned long end);
+int hugetlb_collapse(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end);
#else
static inline bool hugetlb_hgm_enabled(struct vm_area_struct *vma)
{
@@ -1297,6 +1299,12 @@ int hugetlb_alloc_largest_pte(struct hugetlb_pte *hpte, struct mm_struct *mm,
{
return -EINVAL;
}
+static inline
+int hugetlb_collapse(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ return -EINVAL;
+}
#endif
static inline spinlock_t *huge_pte_lock(struct hstate *h,
@@ -7921,6 +7921,148 @@ int hugetlb_alloc_largest_pte(struct hugetlb_pte *hpte, struct mm_struct *mm,
return 0;
}
+/*
+ * Collapse the address range from @start to @end to be mapped optimally.
+ *
+ * This is only valid for shared mappings. The main use case for this function
+ * is following UFFDIO_CONTINUE. If a user UFFDIO_CONTINUEs an entire hugepage
+ * by calling UFFDIO_CONTINUE once for each 4K region, the kernel doesn't know
+ * to collapse the mapping after the final UFFDIO_CONTINUE. Instead, we leave
+ * it up to userspace to tell us to do so, via MADV_COLLAPSE.
+ *
+ * Any holes in the mapping will be filled. If there is no page in the
+ * pagecache for a region we're collapsing, the PTEs will be cleared.
+ *
+ * If high-granularity PTEs are uffd-wp markers, those markers will be dropped.
+ */
+int hugetlb_collapse(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ struct hstate *h = hstate_vma(vma);
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ struct mmu_notifier_range range;
+ struct mmu_gather tlb;
+ unsigned long curr = start;
+ int ret = 0;
+ struct page *hpage, *subpage;
+ pgoff_t idx;
+ bool writable = vma->vm_flags & VM_WRITE;
+ bool shared = vma->vm_flags & VM_SHARED;
+ struct hugetlb_pte hpte;
+ pte_t entry;
+
+ /*
+ * This is only supported for shared VMAs, because we need to look up
+ * the page to use for any PTEs we end up creating.
+ */
+ if (!shared)
+ return -EINVAL;
+
+ if (!hugetlb_hgm_enabled(vma))
+ return 0;
+
+ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm,
+ start, end);
+ mmu_notifier_invalidate_range_start(&range);
+ tlb_gather_mmu(&tlb, mm);
+
+ /*
+ * Grab the lock VMA lock for writing. This will prevent concurrent
+ * high-granularity page table walks, so that we can safely collapse
+ * and free page tables.
+ */
+ hugetlb_vma_lock_write(vma);
+
+ while (curr < end) {
+ ret = hugetlb_alloc_largest_pte(&hpte, mm, vma, curr, end);
+ if (ret)
+ goto out;
+
+ entry = huge_ptep_get(hpte.ptep);
+
+ /*
+ * There is no work to do if the PTE doesn't point to page
+ * tables.
+ */
+ if (!pte_present(entry))
+ goto next_hpte;
+ if (hugetlb_pte_present_leaf(&hpte, entry))
+ goto next_hpte;
+
+ idx = vma_hugecache_offset(h, vma, curr);
+ hpage = find_get_page(mapping, idx);
+
+ if (hpage && !HPageMigratable(hpage)) {
+ /*
+ * Don't collapse a mapping to a page that is pending
+ * a migration. Migration swap entries may have placed
+ * in the page table.
+ */
+ ret = -EBUSY;
+ put_page(hpage);
+ goto out;
+ }
+
+ if (hpage && PageHWPoison(hpage)) {
+ /*
+ * Don't collapse a mapping to a page that is
+ * hwpoisoned.
+ */
+ ret = -EHWPOISON;
+ put_page(hpage);
+ /*
+ * By setting ret to -EHWPOISON, if nothing else
+ * happens, we will tell userspace that we couldn't
+ * fully collapse everything due to poison.
+ *
+ * Skip this page, and continue to collapse the rest
+ * of the mapping.
+ */
+ curr = (curr & huge_page_mask(h)) + huge_page_size(h);
+ continue;
+ }
+
+ /*
+ * Clear all the PTEs, and drop ref/mapcounts
+ * (on tlb_finish_mmu).
+ */
+ __unmap_hugepage_range(&tlb, vma, curr,
+ curr + hugetlb_pte_size(&hpte),
+ NULL,
+ ZAP_FLAG_DROP_MARKER);
+ /* Free the PTEs. */
+ hugetlb_free_pgd_range(&tlb,
+ curr, curr + hugetlb_pte_size(&hpte),
+ curr, curr + hugetlb_pte_size(&hpte));
+ if (!hpage) {
+ huge_pte_clear(mm, curr, hpte.ptep,
+ hugetlb_pte_size(&hpte));
+ goto next_hpte;
+ }
+
+ page_dup_file_rmap(hpage, true);
+
+ subpage = hugetlb_find_subpage(h, hpage, curr);
+ entry = make_huge_pte_with_shift(vma, subpage,
+ writable, hpte.shift);
+ set_huge_pte_at(mm, curr, hpte.ptep, entry);
+next_hpte:
+ curr += hugetlb_pte_size(&hpte);
+
+ if (curr < end) {
+ /* Don't hold the VMA lock for too long. */
+ hugetlb_vma_unlock_write(vma);
+ cond_resched();
+ hugetlb_vma_lock_write(vma);
+ }
+ }
+out:
+ hugetlb_vma_unlock_write(vma);
+ tlb_finish_mmu(&tlb);
+ mmu_notifier_invalidate_range_end(&range);
+ return ret;
+}
+
#endif /* CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING */
/*
@@ -2555,8 +2555,8 @@ static int madvise_collapse_errno(enum scan_result r)
}
}
-int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
- unsigned long start, unsigned long end)
+int madvise_collapse_thp(struct vm_area_struct *vma, struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
{
struct collapse_control *cc;
struct mm_struct *mm = vma->vm_mm;
@@ -986,6 +986,24 @@ static long madvise_remove(struct vm_area_struct *vma,
return error;
}
+static int madvise_collapse(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
+{
+ /* Only allow collapsing for HGM-enabled, shared mappings. */
+ if (is_vm_hugetlb_page(vma)) {
+ *prev = vma;
+ if (!hugetlb_hgm_eligible(vma))
+ return -EINVAL;
+ if (!hugetlb_hgm_enabled(vma))
+ return 0;
+ return hugetlb_collapse(vma->vm_mm, vma, start, end);
+ }
+
+ return madvise_collapse_thp(vma, prev, start, end);
+
+}
+
/*
* Apply an madvise behavior to a region of a vma. madvise_update_vma
* will handle splitting a vm area into separate areas, each area with its own
@@ -1157,6 +1175,9 @@ madvise_behavior_valid(int behavior)
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
case MADV_HUGEPAGE:
case MADV_NOHUGEPAGE:
+#endif
+#if defined(CONFIG_HUGETLB_HIGH_GRANULARITY_MAPPING) || \
+ defined(CONFIG_TRANSPARENT_HUGEPAGE)
case MADV_COLLAPSE:
#endif
case MADV_DONTDUMP:
@@ -1347,7 +1368,8 @@ int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
* MADV_NOHUGEPAGE - mark the given range as not worth being backed by
* transparent huge pages so the existing pages will not be
* coalesced into THP and new pages will not be allocated as THP.
- * MADV_COLLAPSE - synchronously coalesce pages into new THP.
+ * MADV_COLLAPSE - synchronously coalesce pages into new THP, or, for HugeTLB
+ * pages, collapse the mapping.
* MADV_DONTDUMP - the application wants to prevent pages in the given range
* from being included in its core dump.
* MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
This is a necessary extension to the UFFDIO_CONTINUE changes. When userspace finishes mapping an entire hugepage with UFFDIO_CONTINUE, the kernel has no mechanism to automatically collapse the page table to map the whole hugepage normally. We require userspace to inform us that they would like the mapping to be collapsed; they do this with MADV_COLLAPSE. If userspace has not mapped all of a hugepage with UFFDIO_CONTINUE, but only some, hugetlb_collapse will cause the requested range to be mapped as if it were UFFDIO_CONTINUE'd already. The effects of any UFFDIO_WRITEPROTECT calls may be undone by a call to MADV_COLLAPSE for intersecting address ranges. This commit is co-opting the same madvise mode that has been introduced to synchronously collapse THPs. The function that does THP collapsing has been renamed to madvise_collapse_thp. As with the rest of the high-granularity mapping support, MADV_COLLAPSE is only supported for shared VMAs right now. Signed-off-by: James Houghton <jthoughton@google.com> --- include/linux/huge_mm.h | 12 ++-- include/linux/hugetlb.h | 8 +++ mm/hugetlb.c | 142 ++++++++++++++++++++++++++++++++++++++++ mm/khugepaged.c | 4 +- mm/madvise.c | 24 ++++++- 5 files changed, 181 insertions(+), 9 deletions(-)