1 files changed, 39 insertions, 56 deletions

diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index a4f33de4008e..e1bf5ca397fe 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -17,6 +17,8 @@
 #include <linux/memblock.h>
 #include <linux/bootmem.h>
 #include <linux/moduleparam.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
@@ -32,6 +34,7 @@
 #define PAGE_SHIFT_16G	34
 
 unsigned int HPAGE_SHIFT;
+EXPORT_SYMBOL(HPAGE_SHIFT);
 
 /*
  * Tracks gpages after the device tree is scanned and before the
@@ -55,7 +58,7 @@ static unsigned nr_gpages;
 
 #define hugepd_none(hpd)	(hpd_val(hpd) == 0)
 
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz)
 {
 	/* Only called for hugetlbfs pages, hence can ignore THP */
 	return __find_linux_pte_or_hugepte(mm->pgd, addr, NULL, NULL);
@@ -77,7 +80,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
 		num_hugepd = 1;
 	}
 
-	new = kmem_cache_zalloc(cachep, GFP_KERNEL);
+	new = kmem_cache_zalloc(cachep, pgtable_gfp_flags(mm, GFP_KERNEL));
 
 	BUG_ON(pshift > HUGEPD_SHIFT_MASK);
 	BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
@@ -617,62 +620,39 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 	} while (addr = next, addr != end);
 }
 
-/*
- * We are holding mmap_sem, so a parallel huge page collapse cannot run.
- * To prevent hugepage split, disable irq.
- */
-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)
 {
-	bool is_thp;
-	pte_t *ptep, pte;
-	unsigned shift;
-	unsigned long mask, flags;
-	struct page *page = ERR_PTR(-EINVAL);
-
-	local_irq_save(flags);
-	ptep = find_linux_pte_or_hugepte(mm->pgd, address, &is_thp, &shift);
-	if (!ptep)
-		goto no_page;
-	pte = READ_ONCE(*ptep);
-	/*
-	 * Verify it is a huge page else bail.
-	 * Transparent hugepages are handled by generic code. We can skip them
-	 * here.
-	 */
-	if (!shift || is_thp)
-		goto no_page;
-
-	if (!pte_present(pte)) {
-		page = NULL;
-		goto no_page;
+	pte_t *ptep;
+	spinlock_t *ptl;
+	struct page *page = NULL;
+	unsigned long mask;
+	int shift = hugepd_shift(hpd);
+	struct mm_struct *mm = vma->vm_mm;
+
+retry:
+	ptl = &mm->page_table_lock;
+	spin_lock(ptl);
+
+	ptep = hugepte_offset(hpd, address, pdshift);
+	if (pte_present(*ptep)) {
+		mask = (1UL << shift) - 1;
+		page = pte_page(*ptep);
+		page += ((address & mask) >> PAGE_SHIFT);
+		if (flags & FOLL_GET)
+			get_page(page);
+	} else {
+		if (is_hugetlb_entry_migration(*ptep)) {
+			spin_unlock(ptl);
+			__migration_entry_wait(mm, ptep, ptl);
+			goto retry;
+		}
 	}
-	mask = (1UL << shift) - 1;
-	page = pte_page(pte);
-	if (page)
-		page += (address & mask) / PAGE_SIZE;
-
-no_page:
-	local_irq_restore(flags);
+	spin_unlock(ptl);
 	return page;
 }
 
-struct page *
-follow_huge_pmd(struct mm_struct *mm, unsigned long address,
-		pmd_t *pmd, int write)
-{
-	BUG();
-	return NULL;
-}
-
-struct page *
-follow_huge_pud(struct mm_struct *mm, unsigned long address,
-		pud_t *pud, int write)
-{
-	BUG();
-	return NULL;
-}
-
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
 {
@@ -763,8 +743,11 @@ static int __init add_huge_page_size(unsigned long long size)
 	 * Hash: 16M and 16G
 	 */
 	if (radix_enabled()) {
-		if (mmu_psize != MMU_PAGE_2M)
-			return -EINVAL;
+		if (mmu_psize != MMU_PAGE_2M) {
+			if (cpu_has_feature(CPU_FTR_POWER9_DD1) ||
+			    (mmu_psize != MMU_PAGE_1G))
+				return -EINVAL;
+		}
 	} else {
 		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
 			return -EINVAL;
@@ -963,7 +946,7 @@ pte_t *__find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 			if (pmd_none(pmd))
 				return NULL;
 
-			if (pmd_trans_huge(pmd)) {
+			if (pmd_trans_huge(pmd) || pmd_devmap(pmd)) {
 				if (is_thp)
 					*is_thp = true;
 				ret_pte = (pte_t *) pmdp;