hugetlb: simplify hugetlb handling in follow_page_mask

During discussions of this series [1], it was suggested that hugetlb
handling code in follow_page_mask could be simplified.  At the beginning
of follow_page_mask, there currently is a call to follow_huge_addr which
'may' handle hugetlb pages.  ia64 is the only architecture which provides
a follow_huge_addr routine that does not return error.  Instead, at each
level of the page table a check is made for a hugetlb entry.  If a hugetlb
entry is found, a call to a routine associated with that entry is made.

Currently, there are two checks for hugetlb entries at each page table
level.  The first check is of the form:

        if (p?d_huge())
                page = follow_huge_p?d();

the second check is of the form:

        if (is_hugepd())
                page = follow_huge_pd().

We can replace these checks, as well as the special handling routines such
as follow_huge_p?d() and follow_huge_pd() with a single routine to handle
hugetlb vmas.

A new routine hugetlb_follow_page_mask is called for hugetlb vmas at the
beginning of follow_page_mask.  hugetlb_follow_page_mask will use the
existing routine huge_pte_offset to walk page tables looking for hugetlb
entries.  huge_pte_offset can be overwritten by architectures, and already
handles special cases such as hugepd entries.

[1] https://lore.kernel.org/linux-mm/cover.1661240170.git.baolin.wang@linux.alibaba.com/

[mike.kravetz@oracle.com: remove vma (pmd sharing) per Peter]
  Link: https://lkml.kernel.org/r/20221028181108.119432-1-mike.kravetz@oracle.com
[mike.kravetz@oracle.com: remove left over hugetlb_vma_unlock_read()]
  Link: https://lkml.kernel.org/r/20221030225825.40872-1-mike.kravetz@oracle.com
Link: https://lkml.kernel.org/r/20220919021348.22151-1-mike.kravetz@oracle.com
Signed-off-by: Mike Kravetz <mike.kravetz@oracle.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Tested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Naoya Horiguchi <naoya.horiguchi@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 56 insertions, 116 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 546df97c31e4..0af18c1e4b31 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -6209,6 +6209,62 @@ static inline bool __follow_hugetlb_must_fault(unsigned int flags, pte_t *pte,
 	return false;
 }
 
+struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags)
+{
+	struct hstate *h = hstate_vma(vma);
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long haddr = address & huge_page_mask(h);
+	struct page *page = NULL;
+	spinlock_t *ptl;
+	pte_t *pte, entry;
+
+	/*
+	 * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via
+	 * follow_hugetlb_page().
+	 */
+	if (WARN_ON_ONCE(flags & FOLL_PIN))
+		return NULL;
+
+retry:
+	pte = huge_pte_offset(mm, haddr, huge_page_size(h));
+	if (!pte)
+		return NULL;
+
+	ptl = huge_pte_lock(h, mm, pte);
+	entry = huge_ptep_get(pte);
+	if (pte_present(entry)) {
+		page = pte_page(entry) +
+				((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
+		/*
+		 * Note that page may be a sub-page, and with vmemmap
+		 * optimizations the page struct may be read only.
+		 * try_grab_page() will increase the ref count on the
+		 * head page, so this will be OK.
+		 *
+		 * try_grab_page() should always succeed here, because we hold
+		 * the ptl lock and have verified pte_present().
+		 */
+		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
+			page = NULL;
+			goto out;
+		}
+	} else {
+		if (is_hugetlb_entry_migration(entry)) {
+			spin_unlock(ptl);
+			__migration_entry_wait_huge(pte, ptl);
+			goto retry;
+		}
+		/*
+		 * hwpoisoned entry is treated as no_page_table in
+		 * follow_page_mask().
+		 */
+	}
+out:
+	spin_unlock(ptl);
+	return page;
+}
+
 long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			 struct page **pages, struct vm_area_struct **vmas,
 			 unsigned long *position, unsigned long *nr_pages,
@@ -7201,122 +7257,6 @@ __weak unsigned long hugetlb_mask_last_page(struct hstate *h)
  * These functions are overwritable if your architecture needs its own
  * behavior.
  */
-struct page * __weak
-follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-struct page * __weak
-follow_huge_pd(struct vm_area_struct *vma,
-	       unsigned long address, hugepd_t hpd, int flags, int pdshift)
-{
-	WARN(1, "hugepd follow called with no support for hugepage directory format\n");
-	return NULL;
-}
-
-struct page * __weak
-follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address, int flags)
-{
-	struct hstate *h = hstate_vma(vma);
-	struct mm_struct *mm = vma->vm_mm;
-	struct page *page = NULL;
-	spinlock_t *ptl;
-	pte_t *ptep, pte;
-
-	/*
-	 * FOLL_PIN is not supported for follow_page(). Ordinary GUP goes via
-	 * follow_hugetlb_page().
-	 */
-	if (WARN_ON_ONCE(flags & FOLL_PIN))
-		return NULL;
-
-retry:
-	ptep = huge_pte_offset(mm, address, huge_page_size(h));
-	if (!ptep)
-		return NULL;
-
-	ptl = huge_pte_lock(h, mm, ptep);
-	pte = huge_ptep_get(ptep);
-	if (pte_present(pte)) {
-		page = pte_page(pte) +
-			((address & ~huge_page_mask(h)) >> PAGE_SHIFT);
-		/*
-		 * try_grab_page() should always succeed here, because: a) we
-		 * hold the pmd (ptl) lock, and b) we've just checked that the
-		 * huge pmd (head) page is present in the page tables. The ptl
-		 * prevents the head page and tail pages from being rearranged
-		 * in any way. So this page must be available at this point,
-		 * unless the page refcount overflowed:
-		 */
-		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
-			page = NULL;
-			goto out;
-		}
-	} else {
-		if (is_hugetlb_entry_migration(pte)) {
-			spin_unlock(ptl);
-			__migration_entry_wait_huge(ptep, ptl);
-			goto retry;
-		}
-		/*
-		 * hwpoisoned entry is treated as no_page_table in
-		 * follow_page_mask().
-		 */
-	}
-out:
-	spin_unlock(ptl);
-	return page;
-}
-
-struct page * __weak
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int flags)
-{
-	struct page *page = NULL;
-	spinlock_t *ptl;
-	pte_t pte;
-
-	if (WARN_ON_ONCE(flags & FOLL_PIN))
-		return NULL;
-
-retry:
-	ptl = huge_pte_lock(hstate_sizelog(PUD_SHIFT), mm, (pte_t *)pud);
-	if (!pud_huge(*pud))
-		goto out;
-	pte = huge_ptep_get((pte_t *)pud);
-	if (pte_present(pte)) {
-		page = pud_page(*pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT);
-		if (WARN_ON_ONCE(!try_grab_page(page, flags))) {
-			page = NULL;
-			goto out;
-		}
-	} else {
-		if (is_hugetlb_entry_migration(pte)) {
-			spin_unlock(ptl);
-			__migration_entry_wait(mm, (pte_t *)pud, ptl);
-			goto retry;
-		}
-		/*
-		 * hwpoisoned entry is treated as no_page_table in
-		 * follow_page_mask().
-		 */
-	}
-out:
-	spin_unlock(ptl);
-	return page;
-}
-
-struct page * __weak
-follow_huge_pgd(struct mm_struct *mm, unsigned long address, pgd_t *pgd, int flags)
-{
-	if (flags & (FOLL_GET | FOLL_PIN))
-		return NULL;
-
-	return pte_page(*(pte_t *)pgd) + ((address & ~PGDIR_MASK) >> PAGE_SHIFT);
-}
-
 int isolate_hugetlb(struct page *page, struct list_head *list)
 {
 	int ret = 0;