4 files changed, 234 insertions, 2 deletions

diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index 79836a7dd00c..e3cda21b5ee9 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -4,7 +4,7 @@
 asflags-y := -ansi
 ccflags-y := -Werror
 
-obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o
+obj-$(CONFIG_SPARC64)   += ultra.o tlb.o tsb.o gup.o
 obj-y                   += fault_$(BITS).o
 obj-y                   += init_$(BITS).o
 obj-$(CONFIG_SPARC32)   += loadmmu.o
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
new file mode 100644
index 000000000000..a986b5d05712
--- /dev/null
+++ b/arch/sparc/mm/gup.c
@@ -0,0 +1,181 @@
+/*
+ * Lockless get_user_pages_fast for sparc, cribbed from powerpc
+ *
+ * Copyright (C) 2008 Nick Piggin
+ * Copyright (C) 2008 Novell Inc.
+ */
+
+#include <linux/sched.h>
+#include <linux/mm.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;
+
+	if (tlb_type == hypervisor) {
+		result = _PAGE_PRESENT_4V|_PAGE_P_4V;
+		if (write)
+			result |= _PAGE_WRITE_4V;
+	} else {
+		result = _PAGE_PRESENT_4U|_PAGE_P_4U;
+		if (write)
+			result |= _PAGE_WRITE_4U;
+	}
+	mask = result | _PAGE_SPECIAL;
+
+	ptep = pte_offset_kernel(&pmd, addr);
+	do {
+		struct page *page, *head;
+		pte_t pte = *ptep;
+
+		if ((pte_val(pte) & mask) != result)
+			return 0;
+		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+		/* The hugepage case is simplified on sparc64 because
+		 * we encode the sub-page pfn offsets into the
+		 * hugepage PTEs.  We could optimize this in the future
+		 * use page_cache_add_speculative() for the hugepage case.
+		 */
+		page = pte_page(pte);
+		head = compound_head(page);
+		if (!page_cache_get_speculative(head))
+			return 0;
+		if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+			put_page(head);
+			return 0;
+		}
+
+		pages[*nr] = page;
+		(*nr)++;
+	} while (ptep++, addr += PAGE_SIZE, addr != end);
+
+	return 1;
+}
+
+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 nr = 0;
+
+	start &= PAGE_MASK;
+	addr = start;
+	len = (unsigned long) nr_pages << PAGE_SHIFT;
+	end = start + len;
+
+	/*
+	 * 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 sparc.
+	 *
+	 * 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();
+
+	pgdp = pgd_offset(mm, addr);
+	do {
+		pgd_t pgd = *pgdp;
+
+		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();
+
+		/* 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/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 3fd8e18bed80..581531dbc8b5 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1597,6 +1597,44 @@ static void __init tsb_phys_patch(void)
 static struct hv_tsb_descr ktsb_descr[NUM_KTSB_DESCR];
 extern struct tsb swapper_tsb[KERNEL_TSB_NENTRIES];
 
+static void patch_one_ktsb_phys(unsigned int *start, unsigned int *end, unsigned long pa)
+{
+	pa >>= KTSB_PHYS_SHIFT;
+
+	while (start < end) {
+		unsigned int *ia = (unsigned int *)(unsigned long)*start;
+
+		ia[0] = (ia[0] & ~0x3fffff) | (pa >> 10);
+		__asm__ __volatile__("flush	%0" : : "r" (ia));
+
+		ia[1] = (ia[1] & ~0x3ff) | (pa & 0x3ff);
+		__asm__ __volatile__("flush	%0" : : "r" (ia + 1));
+
+		start++;
+	}
+}
+
+static void ktsb_phys_patch(void)
+{
+	extern unsigned int __swapper_tsb_phys_patch;
+	extern unsigned int __swapper_tsb_phys_patch_end;
+	unsigned long ktsb_pa;
+
+	ktsb_pa = kern_base + ((unsigned long)&swapper_tsb[0] - KERNBASE);
+	patch_one_ktsb_phys(&__swapper_tsb_phys_patch,
+			    &__swapper_tsb_phys_patch_end, ktsb_pa);
+#ifndef CONFIG_DEBUG_PAGEALLOC
+	{
+	extern unsigned int __swapper_4m_tsb_phys_patch;
+	extern unsigned int __swapper_4m_tsb_phys_patch_end;
+	ktsb_pa = (kern_base +
+		   ((unsigned long)&swapper_4m_tsb[0] - KERNBASE));
+	patch_one_ktsb_phys(&__swapper_4m_tsb_phys_patch,
+			    &__swapper_4m_tsb_phys_patch_end, ktsb_pa);
+	}
+#endif
+}
+
 static void __init sun4v_ktsb_init(void)
 {
 	unsigned long ktsb_pa;
@@ -1716,8 +1754,10 @@ void __init paging_init(void)
 		sun4u_pgprot_init();
 
 	if (tlb_type == cheetah_plus ||
-	    tlb_type == hypervisor)
+	    tlb_type == hypervisor) {
 		tsb_phys_patch();
+		ktsb_phys_patch();
+	}
 
 	if (tlb_type == hypervisor) {
 		sun4v_patch_tlb_handlers();
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index a5f51b22fcbe..536412d8f416 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -236,6 +236,8 @@ static void setup_tsb_params(struct mm_struct *mm, unsigned long tsb_idx, unsign
 	}
 }
 
+struct kmem_cache *pgtable_cache __read_mostly;
+
 static struct kmem_cache *tsb_caches[8] __read_mostly;
 
 static const char *tsb_cache_names[8] = {
@@ -253,6 +255,15 @@ void __init pgtable_cache_init(void)
 {
 	unsigned long i;
 
+	pgtable_cache = kmem_cache_create("pgtable_cache",
+					  PAGE_SIZE, PAGE_SIZE,
+					  0,
+					  _clear_page);
+	if (!pgtable_cache) {
+		prom_printf("pgtable_cache_init(): Could not create!\n");
+		prom_halt();
+	}
+
 	for (i = 0; i < 8; i++) {
 		unsigned long size = 8192 << i;
 		const char *name = tsb_cache_names[i];