mm: Update generic gup implementation to handle hugepage directory
Update generic gup implementation with powerpc specific details.
On powerpc at pmd level we can have hugepte, normal pmd pointer
or a pointer to the hugepage directory.
Tested-by: Steve Capper <steve.capper@linaro.org>
Acked-by: Steve Capper <steve.capper@linaro.org>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
diff --git a/mm/gup.c b/mm/gup.c
index cd62c8c..0ca1df9 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -3,7 +3,6 @@
#include <linux/err.h>
#include <linux/spinlock.h>
-#include <linux/hugetlb.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
@@ -12,6 +11,7 @@
#include <linux/sched.h>
#include <linux/rwsem.h>
+#include <linux/hugetlb.h>
#include <asm/pgtable.h>
#include "internal.h"
@@ -875,6 +875,49 @@
return 1;
}
+static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
+ unsigned long end, int write,
+ struct page **pages, int *nr)
+{
+ int refs;
+ struct page *head, *page, *tail;
+
+ if (write && !pgd_write(orig))
+ return 0;
+
+ refs = 0;
+ head = pgd_page(orig);
+ page = head + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
+ tail = page;
+ do {
+ VM_BUG_ON_PAGE(compound_head(page) != head, page);
+ pages[*nr] = page;
+ (*nr)++;
+ page++;
+ refs++;
+ } while (addr += PAGE_SIZE, addr != end);
+
+ if (!page_cache_add_speculative(head, refs)) {
+ *nr -= refs;
+ return 0;
+ }
+
+ if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ while (refs--) {
+ if (PageTail(tail))
+ get_huge_page_tail(tail);
+ tail++;
+ }
+
+ return 1;
+}
+
static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
@@ -902,6 +945,14 @@
pages, nr))
return 0;
+ } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) {
+ /*
+ * architecture have different format for hugetlbfs
+ * pmd format and THP pmd format
+ */
+ if (!gup_huge_pd(__hugepd(pmd_val(pmd)), addr,
+ PMD_SHIFT, next, write, pages, nr))
+ return 0;
} else if (!gup_pte_range(pmd, addr, next, write, pages, nr))
return 0;
} while (pmdp++, addr = next, addr != end);
@@ -909,22 +960,26 @@
return 1;
}
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
+static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
{
unsigned long next;
pud_t *pudp;
- pudp = pud_offset(pgdp, addr);
+ pudp = pud_offset(&pgd, addr);
do {
pud_t pud = ACCESS_ONCE(*pudp);
next = pud_addr_end(addr, end);
if (pud_none(pud))
return 0;
- if (pud_huge(pud)) {
+ if (unlikely(pud_huge(pud))) {
if (!gup_huge_pud(pud, pudp, addr, next, write,
- pages, nr))
+ pages, nr))
+ return 0;
+ } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) {
+ if (!gup_huge_pd(__hugepd(pud_val(pud)), addr,
+ PUD_SHIFT, next, write, pages, nr))
return 0;
} else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
return 0;
@@ -970,10 +1025,20 @@
local_irq_save(flags);
pgdp = pgd_offset(mm, addr);
do {
+ pgd_t pgd = ACCESS_ONCE(*pgdp);
+
next = pgd_addr_end(addr, end);
- if (pgd_none(*pgdp))
+ if (pgd_none(pgd))
break;
- else if (!gup_pud_range(pgdp, addr, next, write, pages, &nr))
+ if (unlikely(pgd_huge(pgd))) {
+ if (!gup_huge_pgd(pgd, pgdp, addr, next, write,
+ pages, &nr))
+ break;
+ } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) {
+ if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr,
+ PGDIR_SHIFT, next, write, pages, &nr))
+ break;
+ } else if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
break;
} while (pgdp++, addr = next, addr != end);
local_irq_restore(flags);