mm/follow_page_mask: add support for hugepage directory entry

Architectures like ppc64 supports hugepage size that is not mapped to
any of of the page table levels.  Instead they add an alternate page
table entry format called hugepage directory (hugepd).  hugepd indicates
that the page table entry maps to a set of hugetlb pages.  Add support
for this in generic follow_page_mask code.  We already support this
format in the generic gup code.

The default implementation prints warning and returns NULL.  We will add
ppc64 support in later patches

Link: http://lkml.kernel.org/r/1494926612-23928-7-git-send-email-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Anshuman Khandual <khandual@linux.vnet.ibm.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Mike Kravetz <kravetz@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 45 insertions, 0 deletions

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index f01427c79947..c92a1f0c7240 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -141,6 +141,9 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
 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(struct mm_struct *mm, unsigned long address,
                                 pmd_t *pmd, int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
@@ -175,6 +178,7 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 static inline void hugetlb_show_meminfo(void)
 {
 }
+#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL
 #define follow_huge_pmd(mm, addr, pmd, flags)   NULL
 #define follow_huge_pud(mm, addr, pud, flags)   NULL
 #define follow_huge_pgd(mm, addr, pgd, flags)   NULL
diff --git a/mm/gup.c b/mm/gup.c
index fe95a37a4172..9e472cb835b5 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -226,6 +226,14 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
                         return page;
                 return no_page_table(vma, flags);
         }
+        if (is_hugepd(__hugepd(pmd_val(*pmd)))) {
+                page = follow_huge_pd(vma, address,
+                                      __hugepd(pmd_val(*pmd)), flags,
+                                      PMD_SHIFT);
+                if (page)
+                        return page;
+                return no_page_table(vma, flags);
+        }
         if (pmd_devmap(*pmd)) {
                 ptl = pmd_lock(mm, pmd);
                 page = follow_devmap_pmd(vma, address, pmd, flags);
@@ -292,6 +300,14 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma,
                         return page;
                 return no_page_table(vma, flags);
         }
+        if (is_hugepd(__hugepd(pud_val(*pud)))) {
+                page = follow_huge_pd(vma, address,
+                                      __hugepd(pud_val(*pud)), flags,
+                                      PUD_SHIFT);
+                if (page)
+                        return page;
+                return no_page_table(vma, flags);
+        }
         if (pud_devmap(*pud)) {
                 ptl = pud_lock(mm, pud);
                 page = follow_devmap_pud(vma, address, pud, flags);
@@ -311,6 +327,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
                                     unsigned int flags, unsigned int *page_mask)
 {
         p4d_t *p4d;
+        struct page *page;
 
         p4d = p4d_offset(pgdp, address);
         if (p4d_none(*p4d))
@@ -319,6 +336,14 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma,
         if (unlikely(p4d_bad(*p4d)))
                 return no_page_table(vma, flags);
 
+        if (is_hugepd(__hugepd(p4d_val(*p4d)))) {
+                page = follow_huge_pd(vma, address,
+                                      __hugepd(p4d_val(*p4d)), flags,
+                                      P4D_SHIFT);
+                if (page)
+                        return page;
+                return no_page_table(vma, flags);
+        }
         return follow_pud_mask(vma, address, p4d, flags, page_mask);
 }
 
@@ -363,6 +388,14 @@ struct page *follow_page_mask(struct vm_area_struct *vma,
                         return page;
                 return no_page_table(vma, flags);
         }
+        if (is_hugepd(__hugepd(pgd_val(*pgd)))) {
+                page = follow_huge_pd(vma, address,
+                                      __hugepd(pgd_val(*pgd)), flags,
+                                      PGDIR_SHIFT);
+                if (page)
+                        return page;
+                return no_page_table(vma, flags);
+        }
 
         return follow_p4d_mask(vma, address, pgd, flags, page_mask);
 }
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a446869aa7f1..332637342555 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -4669,6 +4669,14 @@ follow_huge_addr(struct mm_struct *mm, unsigned long address,
 }
 
 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(struct mm_struct *mm, unsigned long address,
                 pmd_t *pmd, int flags)
 {