powerpc: Switch 16GB and 16MB explicit hugepages to a different page table format

We will be switching PMD_SHIFT to 24 bits to facilitate THP impmenetation.
With PMD_SHIFT set to 24, we now have 16MB huge pages allocated at PGD level.
That means with 32 bit process we cannot allocate normal pages at
all, because we cover the entire address space with one pgd entry. Fix this
by switching to a new page table format for hugepages. With the new page table
format for 16GB and 16MB hugepages we won't allocate hugepage directory. Instead
we encode the PTE information directly at the directory level. This forces 16MB
hugepage at PMD level. This will also make the page take walk much simpler later
when we add the THP support.

With the new table format we have 4 cases for pgds and pmds:
(1) invalid (all zeroes)
(2) pointer to next table, as normal; bottom 6 bits == 0
(3) leaf pte for huge page, bottom two bits != 00
(4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 15 insertions, 3 deletions

diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
index d7efdbf640c7..4b921affa495 100644
--- a/arch/powerpc/mm/gup.c
+++ b/arch/powerpc/mm/gup.c
@@ -68,7 +68,11 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 		next = pmd_addr_end(addr, end);
 		if (pmd_none(pmd))
 			return 0;
-		if (is_hugepd(pmdp)) {
+		if (pmd_huge(pmd)) {
+			if (!gup_hugepte((pte_t *)pmdp, PMD_SIZE, addr, next,
+					 write, pages, nr))
+				return 0;
+		} else if (is_hugepd(pmdp)) {
 			if (!gup_hugepd((hugepd_t *)pmdp, PMD_SHIFT,
 					addr, next, write, pages, nr))
 				return 0;
@@ -92,7 +96,11 @@ static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
 		next = pud_addr_end(addr, end);
 		if (pud_none(pud))
 			return 0;
-		if (is_hugepd(pudp)) {
+		if (pud_huge(pud)) {
+			if (!gup_hugepte((pte_t *)pudp, PUD_SIZE, addr, next,
+					 write, pages, nr))
+				return 0;
+		} else if (is_hugepd(pudp)) {
 			if (!gup_hugepd((hugepd_t *)pudp, PUD_SHIFT,
 					addr, next, write, pages, nr))
 				return 0;
@@ -153,7 +161,11 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(pgd))
 			goto slow;
-		if (is_hugepd(pgdp)) {
+		if (pgd_huge(pgd)) {
+			if (!gup_hugepte((pte_t *)pgdp, PGDIR_SIZE, addr, next,
+					 write, pages, &nr))
+				goto slow;
+		} else if (is_hugepd(pgdp)) {
 			if (!gup_hugepd((hugepd_t *)pgdp, PGDIR_SHIFT,
 					addr, next, write, pages, &nr))
 				goto slow;