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, 8 insertions, 42 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 8b4f93e84868..4a76c0fc6bbf 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -149,6 +149,8 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     unsigned long len);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
 			    struct vm_area_struct *, struct vm_area_struct *);
+struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags);
 long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
 			 struct page **, struct vm_area_struct **,
 			 unsigned long *, unsigned long *, long, unsigned int,
@@ -209,17 +211,6 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pte_t *ptep);
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
-struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
-			      int write);
-struct page *follow_huge_pd(struct vm_area_struct *vma,
-			    unsigned long address, hugepd_t hpd,
-			    int flags, int pdshift);
-struct page *follow_huge_pmd_pte(struct vm_area_struct *vma, unsigned long address,
-				 int flags);
-struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
-				pud_t *pud, int flags);
-struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
-			     pgd_t *pgd, int flags);
 
 void hugetlb_vma_lock_read(struct vm_area_struct *vma);
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
@@ -272,6 +263,12 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
+static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
+				unsigned long address, unsigned int flags)
+{
+	BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/
+}
+
 static inline long follow_hugetlb_page(struct mm_struct *mm,
 			struct vm_area_struct *vma, struct page **pages,
 			struct vm_area_struct **vmas, unsigned long *position,
@@ -282,12 +279,6 @@ static inline long follow_hugetlb_page(struct mm_struct *mm,
 	return 0;
 }
 
-static inline struct page *follow_huge_addr(struct mm_struct *mm,
-					unsigned long address, int write)
-{
-	return ERR_PTR(-EINVAL);
-}
-
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
 					  struct mm_struct *src,
 					  struct vm_area_struct *dst_vma,
@@ -320,31 +311,6 @@ static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
-static inline struct page *follow_huge_pd(struct vm_area_struct *vma,
-				unsigned long address, hugepd_t hpd, int flags,
-				int pdshift)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pmd_pte(struct vm_area_struct *vma,
-				unsigned long address, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pud(struct mm_struct *mm,
-				unsigned long address, pud_t *pud, int flags)
-{
-	return NULL;
-}
-
-static inline struct page *follow_huge_pgd(struct mm_struct *mm,
-				unsigned long address, pgd_t *pgd, int flags)
-{
-	return NULL;
-}
-
 static inline int prepare_hugepage_range(struct file *file,
 				unsigned long addr, unsigned long len)
 {