6 files changed, 294 insertions, 6 deletions

diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 1c00e0196f6c..e7392b45a5ef 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -12,7 +12,8 @@ obj-y				:= fault.o mem.o \
 				   mmu_context_$(CONFIG_WORD_SIZE).o
 hash-$(CONFIG_PPC_NATIVE)	:= hash_native_64.o
 obj-$(CONFIG_PPC64)		+= hash_utils_64.o \
-				   slb_low.o slb.o stab.o mmap.o $(hash-y)
+				   slb_low.o slb.o stab.o \
+				   gup.o mmap.o $(hash-y)
 obj-$(CONFIG_PPC_STD_MMU_32)	+= ppc_mmu_32.o
 obj-$(CONFIG_PPC_STD_MMU)	+= hash_low_$(CONFIG_WORD_SIZE).o \
 				   tlb_$(CONFIG_WORD_SIZE).o
diff --git a/arch/powerpc/mm/gup.c b/arch/powerpc/mm/gup.c
new file mode 100644
index 000000000000..9fdf4d6335e4
--- /dev/null
+++ b/arch/powerpc/mm/gup.c
@@ -0,0 +1,280 @@
+/*
+ * Lockless get_user_pages_fast for powerpc
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ */
+#undef DEBUG
+
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/hugetlb.h>
+#include <linux/vmstat.h>
+#include <linux/pagemap.h>
+#include <linux/rwsem.h>
+#include <asm/pgtable.h>
+
+/*
+ * The performance critical leaf functions are made noinline otherwise gcc
+ * inlines everything into a single function which results in too much
+ * register pressure.
+ */
+static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
+		unsigned long end, int write, struct page **pages, int *nr)
+{
+	unsigned long mask, result;
+	pte_t *ptep;
+
+	result = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		result |= _PAGE_RW;
+	mask = result | _PAGE_SPECIAL;
+
+	ptep = pte_offset_kernel(&pmd, addr);
+	do {
+		pte_t pte = *ptep;
+		struct page *page;
+
+		if ((pte_val(pte) & mask) != result)
+			return 0;
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		page = pte_page(pte);
+		if (!page_cache_get_speculative(page))
+			return 0;
+		if (unlikely(pte != *ptep)) {
+			put_page(page);
+			return 0;
+		}
+		pages[*nr] = page;
+		(*nr)++;
+
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+
+	return 1;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static noinline int gup_huge_pte(pte_t *ptep, struct hstate *hstate,
+				 unsigned long *addr, unsigned long end,
+				 int write, struct page **pages, int *nr)
+{
+	unsigned long mask;
+	unsigned long pte_end;
+	struct page *head, *page;
+	pte_t pte;
+	int refs;
+
+	pte_end = (*addr + huge_page_size(hstate)) & huge_page_mask(hstate);
+	if (pte_end < end)
+		end = pte_end;
+
+	pte = *ptep;
+	mask = _PAGE_PRESENT|_PAGE_USER;
+	if (write)
+		mask |= _PAGE_RW;
+	if ((pte_val(pte) & mask) != mask)
+		return 0;
+	/* hugepages are never "special" */
+	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+	refs = 0;
+	head = pte_page(pte);
+	page = head + ((*addr & ~huge_page_mask(hstate)) >> PAGE_SHIFT);
+	do {
+		VM_BUG_ON(compound_head(page) != head);
+		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(pte != *ptep)) {
+		/* Could be optimized better */
+		while (*nr) {
+			put_page(page);
+			(*nr)--;
+		}
+	}
+
+	return 1;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
+		int write, struct page **pages, int *nr)
+{
+	unsigned long next;
+	pmd_t *pmdp;
+
+	pmdp = pmd_offset(&pud, addr);
+	do {
+		pmd_t pmd = *pmdp;
+
+		next = pmd_addr_end(addr, end);
+		if (pmd_none(pmd))
+			return 0;
+		if (!gup_pte_range(pmd, addr, next, write, pages, nr))
+			return 0;
+	} while (pmdp++, addr = next, addr != end);
+
+	return 1;
+}
+
+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(&pgd, addr);
+	do {
+		pud_t pud = *pudp;
+
+		next = pud_addr_end(addr, end);
+		if (pud_none(pud))
+			return 0;
+		if (!gup_pmd_range(pud, addr, next, write, pages, nr))
+			return 0;
+	} while (pudp++, addr = next, addr != end);
+
+	return 1;
+}
+
+int get_user_pages_fast(unsigned long start, int nr_pages, int write,
+			struct page **pages)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long addr, len, end;
+	unsigned long next;
+	pgd_t *pgdp;
+	int psize, nr = 0;
+	unsigned int shift;
+
+	pr_debug("%s(%lx,%x,%s)\n", __func__, start, nr_pages, write ? "write" : "read");
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+					start, len)))
+		goto slow_irqon;
+
+	pr_debug("  aligned: %lx .. %lx\n", start, end);
+
+#ifdef CONFIG_HUGETLB_PAGE
+	/* We bail out on slice boundary crossing when hugetlb is
+	 * enabled in order to not have to deal with two different
+	 * page table formats
+	 */
+	if (addr < SLICE_LOW_TOP) {
+		if (end > SLICE_LOW_TOP)
+			goto slow_irqon;
+
+		if (unlikely(GET_LOW_SLICE_INDEX(addr) !=
+			     GET_LOW_SLICE_INDEX(end - 1)))
+			goto slow_irqon;
+	} else {
+		if (unlikely(GET_HIGH_SLICE_INDEX(addr) !=
+			     GET_HIGH_SLICE_INDEX(end - 1)))
+			goto slow_irqon;
+	}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+	/*
+	 * XXX: batch / limit 'nr', to avoid large irq off latency
+	 * needs some instrumenting to determine the common sizes used by
+	 * important workloads (eg. DB2), and whether limiting the batch size
+	 * will decrease performance.
+	 *
+	 * It seems like we're in the clear for the moment. Direct-IO is
+	 * the main guy that batches up lots of get_user_pages, and even
+	 * they are limited to 64-at-a-time which is not so many.
+	 */
+	/*
+	 * This doesn't prevent pagetable teardown, but does prevent
+	 * the pagetables from being freed on powerpc.
+	 *
+	 * So long as we atomically load page table pointers versus teardown,
+	 * we can follow the address down to the the page and take a ref on it.
+	 */
+	local_irq_disable();
+
+	psize = get_slice_psize(mm, addr);
+	shift = mmu_psize_defs[psize].shift;
+
+#ifdef CONFIG_HUGETLB_PAGE
+	if (unlikely(mmu_huge_psizes[psize])) {
+		pte_t *ptep;
+		unsigned long a = addr;
+		unsigned long sz = ((1UL) << shift);
+		struct hstate *hstate = size_to_hstate(sz);
+
+		BUG_ON(!hstate);
+		/*
+		 * XXX: could be optimized to avoid hstate
+		 * lookup entirely (just use shift)
+		 */
+
+		do {
+			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, a)].shift);
+			ptep = huge_pte_offset(mm, a);
+			pr_debug(" %016lx: huge ptep %p\n", a, ptep);
+			if (!ptep || !gup_huge_pte(ptep, hstate, &a, end, write, pages,
+						   &nr))
+				goto slow;
+		} while (a != end);
+	} else
+#endif /* CONFIG_HUGETLB_PAGE */
+	{
+		pgdp = pgd_offset(mm, addr);
+		do {
+			pgd_t pgd = *pgdp;
+
+			VM_BUG_ON(shift != mmu_psize_defs[get_slice_psize(mm, addr)].shift);
+			pr_debug("  %016lx: normal pgd %p\n", addr, (void *)pgd);
+			next = pgd_addr_end(addr, end);
+			if (pgd_none(pgd))
+				goto slow;
+			if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+				goto slow;
+		} while (pgdp++, addr = next, addr != end);
+	}
+	local_irq_enable();
+
+	VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
+	return nr;
+
+	{
+		int ret;
+
+slow:
+		local_irq_enable();
+slow_irqon:
+		pr_debug("  slow path ! nr = %d\n", nr);
+
+		/* Try to get the remaining pages with get_user_pages */
+		start += nr << PAGE_SHIFT;
+		pages += nr;
+
+		down_read(&mm->mmap_sem);
+		ret = get_user_pages(current, mm, start,
+			(end - start) >> PAGE_SHIFT, write, 0, pages, NULL);
+		up_read(&mm->mmap_sem);
+
+		/* Have to be a bit careful with return values */
+		if (nr > 0) {
+			if (ret < 0)
+				ret = nr;
+			else
+				ret += nr;
+		}
+
+		return ret;
+	}
+}
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index ed0aab0208a6..f1c2d55b4377 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -736,14 +736,21 @@ static int __init hugetlbpage_init(void)
 
 	if (!cpu_has_feature(CPU_FTR_16M_PAGE))
 		return -ENODEV;
+
 	/* Add supported huge page sizes.  Need to change HUGE_MAX_HSTATE
 	 * and adjust PTE_NONCACHE_NUM if the number of supported huge page
 	 * sizes changes.
 	 */
 	set_huge_psize(MMU_PAGE_16M);
-	set_huge_psize(MMU_PAGE_64K);
 	set_huge_psize(MMU_PAGE_16G);
 
+	/* Temporarily disable support for 64K huge pages when 64K SPU local
+	 * store support is enabled as the current implementation conflicts.
+	 */
+#ifndef CONFIG_SPU_FS_64K_LS
+	set_huge_psize(MMU_PAGE_64K);
+#endif
+
 	for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
 		if (mmu_huge_psizes[psize]) {
 			huge_pgtable_cache(psize) = kmem_cache_create(
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 702691cb9e82..1c93c255873b 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -311,7 +311,7 @@ void __init paging_init(void)
 #endif /* CONFIG_HIGHMEM */
 
 	printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%lx\n",
-	       (u64)top_of_ram, total_ram);
+	       (unsigned long long)top_of_ram, total_ram);
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c
index c53145f61942..6aa120813775 100644
--- a/arch/powerpc/mm/ppc_mmu_32.c
+++ b/arch/powerpc/mm/ppc_mmu_32.c
@@ -236,8 +236,8 @@ void __init MMU_init_hw(void)
 
 	Hash_end = (struct hash_pte *) ((unsigned long)Hash + Hash_size);
 
-	printk("Total memory = %ldMB; using %ldkB for hash table (at %p)\n",
-	       total_memory >> 20, Hash_size >> 10, Hash);
+	printk("Total memory = %lldMB; using %ldkB for hash table (at %p)\n",
+	       (unsigned long long)(total_memory >> 20), Hash_size >> 10, Hash);
 
 
 	/*
diff --git a/arch/powerpc/mm/tlb_64.c b/arch/powerpc/mm/tlb_64.c
index 409fcc7b63ce..be7dd422c0fa 100644
--- a/arch/powerpc/mm/tlb_64.c
+++ b/arch/powerpc/mm/tlb_64.c
@@ -34,7 +34,7 @@
 DEFINE_PER_CPU(struct ppc64_tlb_batch, ppc64_tlb_batch);
 
 /* This is declared as we are using the more or less generic
- * include/asm-powerpc/tlb.h file -- tgall
+ * arch/powerpc/include/asm/tlb.h file -- tgall
  */
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 static DEFINE_PER_CPU(struct pte_freelist_batch *, pte_freelist_cur);