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>

arch/powerpc/include/asm/page.h

@@ -380,6 +380,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 #endif
 
 #define is_hugepd(pdep)               (hugepd_ok(*((hugepd_t *)(pdep))))
+#define pgd_huge pgd_huge
 int pgd_huge(pgd_t pgd);
 #else /* CONFIG_HUGETLB_PAGE */
 #define is_hugepd(pdep)			0

include/linux/hugetlb.h

@@ -175,6 +175,52 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 }
 
 #endif /* !CONFIG_HUGETLB_PAGE */
+/*
+ * hugepages at page global directory. If arch support
+ * hugepages at pgd level, they need to define this.
+ */
+#ifndef pgd_huge
+#define pgd_huge(x)	0
+#endif
+
+#ifndef pgd_write
+static inline int pgd_write(pgd_t pgd)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef pud_write
+static inline int pud_write(pud_t pud)
+{
+	BUG();
+	return 0;
+}
+#endif
+
+#ifndef is_hugepd
+/*
+ * Some architectures requires a hugepage directory format that is
+ * required to support multiple hugepage sizes. For example
+ * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+ * introduced the same on powerpc. This allows for a more flexible hugepage
+ * pagetable layout.
+ */
+typedef struct { unsigned long pd; } hugepd_t;
+#define is_hugepd(hugepd) (0)
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+			      unsigned pdshift, unsigned long end,
+			      int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#else
+extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		       unsigned pdshift, unsigned long end,
+		       int write, struct page **pages, int *nr);
+#endif
 
 #define HUGETLB_ANON_FILE "anon_hugepage"
 

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 @@ static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 	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 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 				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);
@@ -909,23 +960,27 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
 	return 1;
 }
 
-static int gup_pud_range(pgd_t *pgdp, unsigned long addr, unsigned long end,
+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))
 				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;
 	} while (pudp++, addr = next, addr != end);
@@ -970,10 +1025,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 	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);