[RFC PATCH 11/16] mm: thp: 1GB THP follow_p*d_page() support.

[Zi Yan <zi.yan@sent.com>]

From: Zi Yan <ziy@nvidia.com>

Add follow_page support for 1GB THPs.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 include/linux/huge_mm.h | 11 +++++++
 mm/gup.c                | 60 ++++++++++++++++++++++++++++++++-
 mm/huge_memory.c        | 73 ++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 142 insertions(+), 2 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 589e5af5a1c2..c7bc40c4a5e2 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -20,6 +20,10 @@ extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud);
 extern int do_huge_pud_anonymous_page(struct vm_fault *vmf);
 extern vm_fault_t do_huge_pud_wp_page(struct vm_fault *vmf, pud_t orig_pud);
+extern struct page *follow_trans_huge_pud(struct vm_area_struct *vma,
+					  unsigned long addr,
+					  pud_t *pud,
+					  unsigned int flags);
 #else
 static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
 {
@@ -32,6 +36,13 @@ extern vm_fault_t do_huge_pud_wp_page(struct vm_fault *vmf, pud_t orig_pud)
 {
 	return VM_FAULT_FALLBACK;
 }
+struct page *follow_trans_huge_pud(struct vm_area_struct *vma,
+					  unsigned long addr,
+					  pud_t *pud,
+					  unsigned int flags)
+{
+	return NULL;
+}
 #endif
 
 extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd);
diff --git a/mm/gup.c b/mm/gup.c
index bd883a112724..4b32ae3c5fa2 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -698,10 +698,68 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
 		if (page)
 			return page;
 	}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+	if (likely(!pud_trans_huge(*pud))) {
+		if (unlikely(pud_bad(*pud)))
+			return no_page_table(vma, flags);
+		return follow_pmd_mask(vma, address, pud, flags, ctx);
+	}
+
+	ptl = pud_lock(mm, pud);
+
+	if (unlikely(!pud_trans_huge(*pud))) {
+		spin_unlock(ptl);
+		if (unlikely(pud_bad(*pud)))
+			return no_page_table(vma, flags);
+		return follow_pmd_mask(vma, address, pud, flags, ctx);
+	}
+
+	if (flags & FOLL_SPLIT) {
+		int ret;
+		pmd_t *pmd = NULL;
+
+		page = pud_page(*pud);
+		if (is_huge_zero_page(page)) {
+
+			spin_unlock(ptl);
+			ret = 0;
+			split_huge_pud(vma, pud, address);
+			pmd = pmd_offset(pud, address);
+			split_huge_pmd(vma, pmd, address);
+			if (pmd_trans_unstable(pmd))
+				ret = -EBUSY;
+		} else {
+			get_page(page);
+			spin_unlock(ptl);
+			lock_page(page);
+			ret = split_huge_pud_page(page);
+			if (!ret)
+				ret = split_huge_page(page);
+			else {
+				unlock_page(page);
+				put_page(page);
+				goto out;
+			}
+			unlock_page(page);
+			put_page(page);
+			if (pud_none(*pud))
+				return no_page_table(vma, flags);
+			pmd = pmd_offset(pud, address);
+		}
+out:
+		return ret ? ERR_PTR(ret) :
+			follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
+	}
+	page = follow_trans_huge_pud(vma, address, pud, flags);
+	spin_unlock(ptl);
+	ctx->page_mask = HPAGE_PUD_NR - 1;
+	return page;
+#else
 	if (unlikely(pud_bad(*pud)))
 		return no_page_table(vma, flags);
-
 	return follow_pmd_mask(vma, address, pud, flags, ctx);
+#endif
 }
 
 static struct page *follow_p4d_mask(struct vm_area_struct *vma,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 398f1b52f789..e209c2dfc5b7 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1259,6 +1259,77 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 	return page;
 }
 
+/*
+ * FOLL_FORCE can write to even unwritable pmd's, but only
+ * after we've gone through a COW cycle and they are dirty.
+ */
+static inline bool can_follow_write_pud(pud_t pud, unsigned int flags)
+{
+	return pud_write(pud) ||
+	       ((flags & FOLL_FORCE) && (flags & FOLL_COW) && pud_dirty(pud));
+}
+
+struct page *follow_trans_huge_pud(struct vm_area_struct *vma,
+				   unsigned long addr,
+				   pud_t *pud,
+				   unsigned int flags)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct page *page = NULL;
+
+	assert_spin_locked(pud_lockptr(mm, pud));
+
+	if (flags & FOLL_WRITE && !can_follow_write_pud(*pud, flags))
+		goto out;
+
+	/* Avoid dumping huge zero page */
+	if ((flags & FOLL_DUMP) && is_huge_zero_pud(*pud))
+		return ERR_PTR(-EFAULT);
+
+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	/*&& pud_protnone(*pmd)*/
+	if ((flags & FOLL_NUMA))
+		goto out;
+
+	page = pud_page(*pud);
+	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+	if (flags & FOLL_TOUCH)
+		touch_pud(vma, addr, pud, flags);
+	if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) {
+		/*
+		 * We don't mlock() pte-mapped THPs. This way we can avoid
+		 * leaking mlocked pages into non-VM_LOCKED VMAs.
+		 *
+		 * For anon THP:
+		 *
+		 * We do the same thing as PMD-level THP.
+		 *
+		 * For file THP:
+		 *
+		 * No support yet.
+		 *
+		 */
+
+		if (PageAnon(page) && compound_mapcount(page) != 1)
+			goto skip_mlock;
+		if (PagePUDDoubleMap(page) || !page->mapping)
+			goto skip_mlock;
+		if (!trylock_page(page))
+			goto skip_mlock;
+		lru_add_drain();
+		if (page->mapping && !PagePUDDoubleMap(page))
+			mlock_vma_page(page);
+		unlock_page(page);
+	}
+skip_mlock:
+	page += (addr & ~HPAGE_PUD_MASK) >> PAGE_SHIFT;
+	VM_BUG_ON_PAGE(!PageCompound(page) && !is_zone_device_page(page), page);
+	if (flags & FOLL_GET)
+		get_page(page);
+
+out:
+	return page;
+}
 int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
 		  struct vm_area_struct *vma)
@@ -1501,7 +1572,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 		goto out;
 
 	page = pmd_page(*pmd);
-	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page), page);
+	VM_BUG_ON_PAGE(!PageHead(page) && !is_zone_device_page(page) && !PMDPageInPUD(page), page);
 
 	if (!try_grab_page(page, flags))
 		return ERR_PTR(-ENOMEM);
-- 
2.28.0