1 files changed, 220 insertions, 108 deletions

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index c0f5cff7703..e3734edffa6 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -19,6 +19,8 @@
  *
  */
 
+#undef DEBUG
+
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/kernel.h>
@@ -38,11 +40,13 @@
 #include <linux/nodemask.h>
 #include <linux/module.h>
 #include <linux/poison.h>
+#include <linux/memblock.h>
+#include <linux/hugetlb.h>
+#include <linux/slab.h>
 
 #include <asm/pgalloc.h>
 #include <asm/page.h>
 #include <asm/prom.h>
-#include <asm/lmb.h>
 #include <asm/rtas.h>
 #include <asm/io.h>
 #include <asm/mmu_context.h>
@@ -57,13 +61,12 @@
 #include <asm/mmzone.h>
 #include <asm/cputable.h>
 #include <asm/sections.h>
-#include <asm/system.h>
 #include <asm/iommu.h>
-#include <asm/abs_addr.h>
 #include <asm/vdso.h>
 
 #include "mmu_decl.h"
 
+#ifdef CONFIG_PPC_STD_MMU_64
 #if PGTABLE_RANGE > USER_VSID_RANGE
 #warning Limited user VSID range means pagetable space is wasted
 #endif
@@ -71,109 +74,82 @@
 #if (TASK_SIZE_USER64 < PGTABLE_RANGE) && (TASK_SIZE_USER64 < USER_VSID_RANGE)
 #warning TASK_SIZE is smaller than it needs to be.
 #endif
+#endif /* CONFIG_PPC_STD_MMU_64 */
 
-/* max amount of RAM to use */
-unsigned long __max_memory;
+phys_addr_t memstart_addr = ~0;
+EXPORT_SYMBOL_GPL(memstart_addr);
+phys_addr_t kernstart_addr;
+EXPORT_SYMBOL_GPL(kernstart_addr);
 
-void free_initmem(void)
+static void pgd_ctor(void *addr)
 {
-	unsigned long addr;
-
-	addr = (unsigned long)__init_begin;
-	for (; addr < (unsigned long)__init_end; addr += PAGE_SIZE) {
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		free_page(addr);
-		totalram_pages++;
-	}
-	printk ("Freeing unused kernel memory: %luk freed\n",
-		((unsigned long)__init_end - (unsigned long)__init_begin) >> 10);
+	memset(addr, 0, PGD_TABLE_SIZE);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
+static void pmd_ctor(void *addr)
 {
-	if (start < end)
-		printk ("Freeing initrd memory: %ldk freed\n", (end - start) >> 10);
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages++;
-	}
-}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	memset(addr, 0, PMD_TABLE_SIZE * 2);
+#else
+	memset(addr, 0, PMD_TABLE_SIZE);
 #endif
-
-#ifdef CONFIG_PROC_KCORE
-static struct kcore_list kcore_vmem;
-
-static int __init setup_kcore(void)
-{
-	int i;
-
-	for (i=0; i < lmb.memory.cnt; i++) {
-		unsigned long base, size;
-		struct kcore_list *kcore_mem;
-
-		base = lmb.memory.region[i].base;
-		size = lmb.memory.region[i].size;
-
-		/* GFP_ATOMIC to avoid might_sleep warnings during boot */
-		kcore_mem = kmalloc(sizeof(struct kcore_list), GFP_ATOMIC);
-		if (!kcore_mem)
-			panic("%s: kmalloc failed\n", __FUNCTION__);
-
-		kclist_add(kcore_mem, __va(base), size);
-	}
-
-	kclist_add(&kcore_vmem, (void *)VMALLOC_START, VMALLOC_END-VMALLOC_START);
-
-	return 0;
 }
-module_init(setup_kcore);
-#endif
 
-static void zero_ctor(struct kmem_cache *cache, void *addr)
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
 {
-	memset(addr, 0, kmem_cache_size(cache));
+	char *name;
+	unsigned long table_size = sizeof(void *) << shift;
+	unsigned long align = table_size;
+
+	/* When batching pgtable pointers for RCU freeing, we store
+	 * the index size in the low bits.  Table alignment must be
+	 * big enough to fit it.
+	 *
+	 * Likewise, hugeapge pagetable pointers contain a (different)
+	 * shift value in the low bits.  All tables must be aligned so
+	 * as to leave enough 0 bits in the address to contain it. */
+	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
+				     HUGEPD_SHIFT_MASK + 1);
+	struct kmem_cache *new;
+
+	/* It would be nice if this was a BUILD_BUG_ON(), but at the
+	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
+	 * constant expression, so so much for that. */
+	BUG_ON(!is_power_of_2(minalign));
+	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+
+	if (PGT_CACHE(shift))
+		return; /* Already have a cache of this size */
+
+	align = max_t(unsigned long, align, minalign);
+	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	pgtable_cache[shift - 1] = new;
+	pr_debug("Allocated pgtable cache for order %d\n", shift);
 }
 
-static const unsigned int pgtable_cache_size[2] = {
-	PGD_TABLE_SIZE, PMD_TABLE_SIZE
-};
-static const char *pgtable_cache_name[ARRAY_SIZE(pgtable_cache_size)] = {
-#ifdef CONFIG_PPC_64K_PAGES
-	"pgd_cache", "pmd_cache",
-#else
-	"pgd_cache", "pud_pmd_cache",
-#endif /* CONFIG_PPC_64K_PAGES */
-};
-
-#ifdef CONFIG_HUGETLB_PAGE
-/* Hugepages need one extra cache, initialized in hugetlbpage.c.  We
- * can't put into the tables above, because HPAGE_SHIFT is not compile
- * time constant. */
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)+1];
-#else
-struct kmem_cache *pgtable_cache[ARRAY_SIZE(pgtable_cache_size)];
-#endif
 
 void pgtable_cache_init(void)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(pgtable_cache_size); i++) {
-		int size = pgtable_cache_size[i];
-		const char *name = pgtable_cache_name[i];
-
-		pr_debug("Allocating page table cache %s (#%d) "
-			"for size: %08x...\n", name, i, size);
-		pgtable_cache[i] = kmem_cache_create(name,
-						     size, size,
-						     SLAB_PANIC,
-						     zero_ctor);
-	}
+	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
+		panic("Couldn't allocate pgtable caches");
+	/* In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index.  Verify that the
+	 * initialization above has also created a PUD cache.  This
+	 * will need re-examiniation if we add new possibilities for
+	 * the pagetable layout. */
+	BUG_ON(PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE));
 }
 
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
@@ -183,7 +159,7 @@ void pgtable_cache_init(void)
  * do this by hand as the proffered address may not be correctly aligned.
  * Subtraction of non-aligned pointers produces undefined results.
  */
-unsigned long __meminit vmemmap_section_start(unsigned long page)
+static unsigned long __meminit vmemmap_section_start(unsigned long page)
 {
 	unsigned long offset = page - ((unsigned long)(vmemmap));
 
@@ -196,7 +172,7 @@ unsigned long __meminit vmemmap_section_start(unsigned long page)
  * which overlaps this vmemmap page is initialised then this page is
  * initialised already.
  */
-int __meminit vmemmap_populated(unsigned long start, int page_size)
+static int __meminit vmemmap_populated(unsigned long start, int page_size)
 {
 	unsigned long end = start + page_size;
 
@@ -207,21 +183,99 @@ int __meminit vmemmap_populated(unsigned long start, int page_size)
 	return 0;
 }
 
-int __meminit vmemmap_populate(struct page *start_page,
-					unsigned long nr_pages, int node)
+/* On hash-based CPUs, the vmemmap is bolted in the hash table.
+ *
+ * On Book3E CPUs, the vmemmap is currently mapped in the top half of
+ * the vmalloc space using normal page tables, though the size of
+ * pages encoded in the PTEs can be different
+ */
+
+#ifdef CONFIG_PPC_BOOK3E
+static void __meminit vmemmap_create_mapping(unsigned long start,
+					     unsigned long page_size,
+					     unsigned long phys)
+{
+	/* Create a PTE encoding without page size */
+	unsigned long i, flags = _PAGE_PRESENT | _PAGE_ACCESSED |
+		_PAGE_KERNEL_RW;
+
+	/* PTEs only contain page size encodings up to 32M */
+	BUG_ON(mmu_psize_defs[mmu_vmemmap_psize].enc > 0xf);
+
+	/* Encode the size in the PTE */
+	flags |= mmu_psize_defs[mmu_vmemmap_psize].enc << 8;
+
+	/* For each PTE for that area, map things. Note that we don't
+	 * increment phys because all PTEs are of the large size and
+	 * thus must have the low bits clear
+	 */
+	for (i = 0; i < page_size; i += PAGE_SIZE)
+		BUG_ON(map_kernel_page(start + i, phys, flags));
+}
+#else /* CONFIG_PPC_BOOK3E */
+static void __meminit vmemmap_create_mapping(unsigned long start,
+					     unsigned long page_size,
+					     unsigned long phys)
+{
+	int  mapped = htab_bolt_mapping(start, start + page_size, phys,
+					pgprot_val(PAGE_KERNEL),
+					mmu_vmemmap_psize,
+					mmu_kernel_ssize);
+	BUG_ON(mapped < 0);
+}
+#endif /* CONFIG_PPC_BOOK3E */
+
+struct vmemmap_backing *vmemmap_list;
+
+static __meminit struct vmemmap_backing * vmemmap_list_alloc(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_linear_psize].shift;
+	static struct vmemmap_backing *next;
+	static int num_left;
+
+	/* allocate a page when required and hand out chunks */
+	if (!next || !num_left) {
+		next = vmemmap_alloc_block(PAGE_SIZE, node);
+		if (unlikely(!next)) {
+			WARN_ON(1);
+			return NULL;
+		}
+		num_left = PAGE_SIZE / sizeof(struct vmemmap_backing);
+	}
 
-	mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
+	num_left--;
+
+	return next++;
+}
+
+static __meminit void vmemmap_list_populate(unsigned long phys,
+					    unsigned long start,
+					    int node)
+{
+	struct vmemmap_backing *vmem_back;
+
+	vmem_back = vmemmap_list_alloc(node);
+	if (unlikely(!vmem_back)) {
+		WARN_ON(1);
+		return;
+	}
+
+	vmem_back->phys = phys;
+	vmem_back->virt_addr = start;
+	vmem_back->list = vmemmap_list;
+
+	vmemmap_list = vmem_back;
+}
+
+int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node)
+{
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
 
 	/* Align to the page size of the linear mapping. */
 	start = _ALIGN_DOWN(start, page_size);
 
+	pr_debug("vmemmap_populate %lx..%lx, node %d\n", start, end, node);
+
 	for (; start < end; start += page_size) {
-		int mapped;
 		void *p;
 
 		if (vmemmap_populated(start, page_size))
@@ -231,15 +285,73 @@ int __meminit vmemmap_populate(struct page *start_page,
 		if (!p)
 			return -ENOMEM;
 
-		pr_debug("vmemmap %08lx allocated at %p, physical %08lx.\n",
-			start, p, __pa(p));
+		vmemmap_list_populate(__pa(p), start, node);
 
-		mapped = htab_bolt_mapping(start, start + page_size,
-					__pa(p), mode_rw, mmu_linear_psize,
-					mmu_kernel_ssize);
-		BUG_ON(mapped < 0);
+		pr_debug("      * %016lx..%016lx allocated at %p\n",
+			 start, start + page_size, p);
+
+		vmemmap_create_mapping(start, page_size, __pa(p));
 	}
 
 	return 0;
 }
-#endif
+
+void vmemmap_free(unsigned long start, unsigned long end)
+{
+}
+
+void register_page_bootmem_memmap(unsigned long section_nr,
+				  struct page *start_page, unsigned long size)
+{
+}
+
+/*
+ * We do not have access to the sparsemem vmemmap, so we fallback to
+ * walking the list of sparsemem blocks which we already maintain for
+ * the sake of crashdump. In the long run, we might want to maintain
+ * a tree if performance of that linear walk becomes a problem.
+ *
+ * realmode_pfn_to_page functions can fail due to:
+ * 1) As real sparsemem blocks do not lay in RAM continously (they
+ * are in virtual address space which is not available in the real mode),
+ * the requested page struct can be split between blocks so get_page/put_page
+ * may fail.
+ * 2) When huge pages are used, the get_page/put_page API will fail
+ * in real mode as the linked addresses in the page struct are virtual
+ * too.
+ */
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct vmemmap_backing *vmem_back;
+	struct page *page;
+	unsigned long page_size = 1 << mmu_psize_defs[mmu_vmemmap_psize].shift;
+	unsigned long pg_va = (unsigned long) pfn_to_page(pfn);
+
+	for (vmem_back = vmemmap_list; vmem_back; vmem_back = vmem_back->list) {
+		if (pg_va < vmem_back->virt_addr)
+			continue;
+
+		/* Check that page struct is not split between real pages */
+		if ((pg_va + sizeof(struct page)) >
+				(vmem_back->virt_addr + page_size))
+			return NULL;
+
+		page = (struct page *) (vmem_back->phys + pg_va -
+				vmem_back->virt_addr);
+		return page;
+	}
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#elif defined(CONFIG_FLATMEM)
+
+struct page *realmode_pfn_to_page(unsigned long pfn)
+{
+	struct page *page = pfn_to_page(pfn);
+	return page;
+}
+EXPORT_SYMBOL_GPL(realmode_pfn_to_page);
+
+#endif /* CONFIG_SPARSEMEM_VMEMMAP/CONFIG_FLATMEM */