Merge commit 'v2.6.27-rc6' into timers/hpet

7 files changed, 331 insertions, 34 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/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 5ce5a4dcd008..8920eea34528 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -151,39 +151,58 @@ static struct mmu_psize_def mmu_psize_defaults_gp[] = {
 	},
 };
 
+static unsigned long htab_convert_pte_flags(unsigned long pteflags)
+{
+	unsigned long rflags = pteflags & 0x1fa;
+
+	/* _PAGE_EXEC -> NOEXEC */
+	if ((pteflags & _PAGE_EXEC) == 0)
+		rflags |= HPTE_R_N;
+
+	/* PP bits. PAGE_USER is already PP bit 0x2, so we only
+	 * need to add in 0x1 if it's a read-only user page
+	 */
+	if ((pteflags & _PAGE_USER) && !((pteflags & _PAGE_RW) &&
+					 (pteflags & _PAGE_DIRTY)))
+		rflags |= 1;
+
+	/* Always add C */
+	return rflags | HPTE_R_C;
+}
 
 int htab_bolt_mapping(unsigned long vstart, unsigned long vend,
-		      unsigned long pstart, unsigned long mode,
+		      unsigned long pstart, unsigned long prot,
 		      int psize, int ssize)
 {
 	unsigned long vaddr, paddr;
 	unsigned int step, shift;
-	unsigned long tmp_mode;
 	int ret = 0;
 
 	shift = mmu_psize_defs[psize].shift;
 	step = 1 << shift;
 
+	prot = htab_convert_pte_flags(prot);
+
+	DBG("htab_bolt_mapping(%lx..%lx -> %lx (%lx,%d,%d)\n",
+	    vstart, vend, pstart, prot, psize, ssize);
+
 	for (vaddr = vstart, paddr = pstart; vaddr < vend;
 	     vaddr += step, paddr += step) {
 		unsigned long hash, hpteg;
 		unsigned long vsid = get_kernel_vsid(vaddr, ssize);
 		unsigned long va = hpt_va(vaddr, vsid, ssize);
+		unsigned long tprot = prot;
 
-		tmp_mode = mode;
-		
-		/* Make non-kernel text non-executable */
-		if (!in_kernel_text(vaddr))
-			tmp_mode = mode | HPTE_R_N;
+		/* Make kernel text executable */
+		if (in_kernel_text(vaddr))
+			tprot &= ~HPTE_R_N;
 
 		hash = hpt_hash(va, shift, ssize);
 		hpteg = ((hash & htab_hash_mask) * HPTES_PER_GROUP);
 
-		DBG("htab_bolt_mapping: calling %p\n", ppc_md.hpte_insert);
-
 		BUG_ON(!ppc_md.hpte_insert);
-		ret = ppc_md.hpte_insert(hpteg, va, paddr,
-				tmp_mode, HPTE_V_BOLTED, psize, ssize);
+		ret = ppc_md.hpte_insert(hpteg, va, paddr, tprot,
+					 HPTE_V_BOLTED, psize, ssize);
 
 		if (ret < 0)
 			break;
@@ -519,9 +538,9 @@ static unsigned long __init htab_get_table_size(void)
 #ifdef CONFIG_MEMORY_HOTPLUG
 void create_section_mapping(unsigned long start, unsigned long end)
 {
-		BUG_ON(htab_bolt_mapping(start, end, __pa(start),
-			_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX,
-			mmu_linear_psize, mmu_kernel_ssize));
+	BUG_ON(htab_bolt_mapping(start, end, __pa(start),
+				 PAGE_KERNEL, mmu_linear_psize,
+				 mmu_kernel_ssize));
 }
 
 int remove_section_mapping(unsigned long start, unsigned long end)
@@ -570,7 +589,7 @@ void __init htab_initialize(void)
 {
 	unsigned long table;
 	unsigned long pteg_count;
-	unsigned long mode_rw;
+	unsigned long prot;
 	unsigned long base = 0, size = 0, limit;
 	int i;
 
@@ -628,7 +647,7 @@ void __init htab_initialize(void)
 		mtspr(SPRN_SDR1, _SDR1);
 	}
 
-	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
+	prot = PAGE_KERNEL;
 
 #ifdef CONFIG_DEBUG_PAGEALLOC
 	linear_map_hash_count = lmb_end_of_DRAM() >> PAGE_SHIFT;
@@ -647,7 +666,8 @@ void __init htab_initialize(void)
 		base = (unsigned long)__va(lmb.memory.region[i].base);
 		size = lmb.memory.region[i].size;
 
-		DBG("creating mapping for region: %lx : %lx\n", base, size);
+		DBG("creating mapping for region: %lx..%lx (prot: %x)\n",
+		    base, size, prot);
 
 #ifdef CONFIG_U3_DART
 		/* Do not map the DART space. Fortunately, it will be aligned
@@ -664,21 +684,21 @@ void __init htab_initialize(void)
 			unsigned long dart_table_end = dart_tablebase + 16 * MB;
 			if (base != dart_tablebase)
 				BUG_ON(htab_bolt_mapping(base, dart_tablebase,
-							__pa(base), mode_rw,
+							__pa(base), prot,
 							mmu_linear_psize,
 							mmu_kernel_ssize));
 			if ((base + size) > dart_table_end)
 				BUG_ON(htab_bolt_mapping(dart_tablebase+16*MB,
 							base + size,
 							__pa(dart_table_end),
-							 mode_rw,
+							 prot,
 							 mmu_linear_psize,
 							 mmu_kernel_ssize));
 			continue;
 		}
 #endif /* CONFIG_U3_DART */
 		BUG_ON(htab_bolt_mapping(base, base + size, __pa(base),
-				mode_rw, mmu_linear_psize, mmu_kernel_ssize));
+				prot, mmu_linear_psize, mmu_kernel_ssize));
        }
 
 	/*
@@ -696,7 +716,7 @@ void __init htab_initialize(void)
 			tce_alloc_start = base + size + 1;
 
 		BUG_ON(htab_bolt_mapping(tce_alloc_start, tce_alloc_end,
-					 __pa(tce_alloc_start), mode_rw,
+					 __pa(tce_alloc_start), prot,
 					 mmu_linear_psize, mmu_kernel_ssize));
 	}
 
@@ -1117,8 +1137,7 @@ static void kernel_map_linear_page(unsigned long vaddr, unsigned long lmi)
 	unsigned long hash, hpteg;
 	unsigned long vsid = get_kernel_vsid(vaddr, mmu_kernel_ssize);
 	unsigned long va = hpt_va(vaddr, vsid, mmu_kernel_ssize);
-	unsigned long mode = _PAGE_ACCESSED | _PAGE_DIRTY |
-		_PAGE_COHERENT | PP_RWXX | HPTE_R_N;
+	unsigned long mode = htab_convert_pte_flags(PAGE_KERNEL);
 	int ret;
 
 	hash = hpt_hash(va, PAGE_SHIFT, mmu_kernel_ssize);
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 4f7df85129d8..036fe2f10c77 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -206,13 +206,10 @@ static int __meminit vmemmap_populated(unsigned long start, int page_size)
 int __meminit vmemmap_populate(struct page *start_page,
 			       unsigned long nr_pages, int node)
 {
-	unsigned long mode_rw;
 	unsigned long start = (unsigned long)start_page;
 	unsigned long end = (unsigned long)(start_page + nr_pages);
 	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 
-	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
-
 	/* Align to the page size of the linear mapping. */
 	start = _ALIGN_DOWN(start, page_size);
 
@@ -230,9 +227,9 @@ int __meminit vmemmap_populate(struct page *start_page,
 		pr_debug("vmemmap %08lx allocated at %p, physical %08lx.\n",
 			start, p, __pa(p));
 
-		mapped = htab_bolt_mapping(start, start + page_size,
-					__pa(p), mode_rw, mmu_vmemmap_psize,
-					mmu_kernel_ssize);
+		mapped = htab_bolt_mapping(start, start + page_size, __pa(p),
+					   PAGE_KERNEL, mmu_vmemmap_psize,
+					   mmu_kernel_ssize);
 		BUG_ON(mapped < 0);
 	}
 
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);