/*
 * Reserve Xen mfn_list.
 */
static void __init xen_reserve_xen_mfnlist(void)
{
	phys_addr_t start, size;

	if (xen_start_info->mfn_list >= __START_KERNEL_map) {
		start = __pa(xen_start_info->mfn_list);
		size = PFN_ALIGN(xen_start_info->nr_pages *
				 sizeof(unsigned long));
	} else {
		start = PFN_PHYS(xen_start_info->first_p2m_pfn);
		size = PFN_PHYS(xen_start_info->nr_p2m_frames);
	}

	if (!xen_is_e820_reserved(start, size)) {
		memblock_reserve(start, size);
		return;
	}

#ifdef CONFIG_X86_32
	/*
	 * Relocating the p2m on 32 bit system to an arbitrary virtual address
	 * is not supported, so just give up.
	 */
	xen_raw_console_write("Xen hypervisor allocated p2m list conflicts with E820 map\n");
	BUG();
#else
	xen_relocate_p2m();
#endif
}

void __init bootmem_init(void)
{
	/* Reserve all memory below PHYS_OFFSET, as memory
	 * accounting doesn't work for pages below that address.
	 *
	 * If PHYS_OFFSET is zero reserve page at address 0:
	 * successfull allocations should never return NULL.
	 */
	if (PHYS_OFFSET)
		memblock_reserve(0, PHYS_OFFSET);
	else
		memblock_reserve(0, 1);

	early_init_fdt_scan_reserved_mem();

	if (!memblock_phys_mem_size())
		panic("No memory found!\n");

	min_low_pfn = PFN_UP(memblock_start_of_DRAM());
	min_low_pfn = max(min_low_pfn, PFN_UP(PHYS_OFFSET));
	max_pfn = PFN_DOWN(memblock_end_of_DRAM());
	max_low_pfn = min(max_pfn, MAX_LOW_PFN);

	memblock_set_current_limit(PFN_PHYS(max_low_pfn));
	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));

	memblock_dump_all();
}

static void __init xen_add_extra_mem(unsigned long start_pfn,
				     unsigned long n_pfns)
{
	int i;

	/*
	 * No need to check for zero size, should happen rarely and will only
	 * write a new entry regarded to be unused due to zero size.
	 */
	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		/* Add new region. */
		if (xen_extra_mem[i].n_pfns == 0) {
			xen_extra_mem[i].start_pfn = start_pfn;
			xen_extra_mem[i].n_pfns = n_pfns;
			break;
		}
		/* Append to existing region. */
		if (xen_extra_mem[i].start_pfn + xen_extra_mem[i].n_pfns ==
		    start_pfn) {
			xen_extra_mem[i].n_pfns += n_pfns;
			break;
		}
	}
	if (i == XEN_EXTRA_MEM_MAX_REGIONS)
		printk(KERN_WARNING "Warning: not enough extra memory regions\n");

	memblock_reserve(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}

static void __init xen_del_extra_mem(unsigned long start_pfn,
				     unsigned long n_pfns)
{
	int i;
	unsigned long start_r, size_r;

	for (i = 0; i < XEN_EXTRA_MEM_MAX_REGIONS; i++) {
		start_r = xen_extra_mem[i].start_pfn;
		size_r = xen_extra_mem[i].n_pfns;

		/* Start of region. */
		if (start_r == start_pfn) {
			BUG_ON(n_pfns > size_r);
			xen_extra_mem[i].start_pfn += n_pfns;
			xen_extra_mem[i].n_pfns -= n_pfns;
			break;
		}
		/* End of region. */
		if (start_r + size_r == start_pfn + n_pfns) {
			BUG_ON(n_pfns > size_r);
			xen_extra_mem[i].n_pfns -= n_pfns;
			break;
		}
		/* Mid of region. */
		if (start_pfn > start_r && start_pfn < start_r + size_r) {
			BUG_ON(start_pfn + n_pfns > start_r + size_r);
			xen_extra_mem[i].n_pfns = start_pfn - start_r;
			/* Calling memblock_reserve() again is okay. */
			xen_add_extra_mem(start_pfn + n_pfns, start_r + size_r -
					  (start_pfn + n_pfns));
			break;
		}
	}
	memblock_free(PFN_PHYS(start_pfn), PFN_PHYS(n_pfns));
}

	for_each_memblock(memory, reg) {
		unsigned long start_pfn = memblock_region_memory_base_pfn(reg);
		unsigned long end_pfn = memblock_region_memory_end_pfn(reg);

		memblock_set_node(PFN_PHYS(start_pfn),
				  PFN_PHYS(end_pfn - start_pfn),
				  &memblock.memory, 0);
	}

void __init crashlog_init_mem(bootmem_data_t *bdata)
{
	unsigned long addr;

	if (crashlog_addr)
		return;

	addr = PFN_PHYS(bdata->node_low_pfn) - CRASHLOG_OFFSET;
	if (reserve_bootmem(addr, CRASHLOG_SIZE, BOOTMEM_EXCLUSIVE) < 0) {
		printk("Crashlog failed to allocate RAM at address 0x%lx\n", addr);
		bdata->node_low_pfn -= CRASHLOG_PAGES;
		addr = PFN_PHYS(bdata->node_low_pfn);
	}
	crashlog_addr = addr;
}

/*
 * On Meta machines the conventional approach is to stash system RAM
 * in node 0, and other memory blocks in to node 1 and up, ordered by
 * latency. Each node's pgdat is node-local at the beginning of the node,
 * immediately followed by the node mem map.
 */
void __init setup_bootmem_node(int nid, unsigned long start, unsigned long end)
{
	unsigned long bootmap_pages, bootmem_paddr;
	unsigned long start_pfn, end_pfn;
	unsigned long pgdat_paddr;

	/* Don't allow bogus node assignment */
	BUG_ON(nid > MAX_NUMNODES || nid <= 0);

	start_pfn = start >> PAGE_SHIFT;
	end_pfn = end >> PAGE_SHIFT;

	memblock_add(start, end - start);

	memblock_set_node(PFN_PHYS(start_pfn),
			  PFN_PHYS(end_pfn - start_pfn), nid);

	/* Node-local pgdat */
	pgdat_paddr = memblock_alloc_base(sizeof(struct pglist_data),
					  SMP_CACHE_BYTES, end);
	NODE_DATA(nid) = __va(pgdat_paddr);
	memset(NODE_DATA(nid), 0, sizeof(struct pglist_data));

	NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
	NODE_DATA(nid)->node_start_pfn = start_pfn;
	NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;

	/* Node-local bootmap */
	bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
	bootmem_paddr = memblock_alloc_base(bootmap_pages << PAGE_SHIFT,
					    PAGE_SIZE, end);
	init_bootmem_node(NODE_DATA(nid), bootmem_paddr >> PAGE_SHIFT,
			  start_pfn, end_pfn);

	free_bootmem_with_active_regions(nid, end_pfn);

	/* Reserve the pgdat and bootmap space with the bootmem allocator */
	reserve_bootmem_node(NODE_DATA(nid), pgdat_paddr & PAGE_MASK,
			     sizeof(struct pglist_data), BOOTMEM_DEFAULT);
	reserve_bootmem_node(NODE_DATA(nid), bootmem_paddr,
			     bootmap_pages << PAGE_SHIFT, BOOTMEM_DEFAULT);

	/* It's up */
	node_set_online(nid);

	/* Kick sparsemem */
	sparse_memory_present_with_active_regions(nid);
}

void *dma_generic_alloc_coherent(struct device *dev, size_t size,
				 dma_addr_t *dma_handle, gfp_t gfp,
				 unsigned long attrs)
{
	void *ret, *ret_nocache;
	int order = get_order(size);

	gfp |= __GFP_ZERO;

	ret = (void *)__get_free_pages(gfp, order);
	if (!ret)
		return NULL;

	/*
	 * Pages from the page allocator may have data present in
	 * cache. So flush the cache before using uncached memory.
	 */
	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);

	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
	if (!ret_nocache) {
		free_pages((unsigned long)ret, order);
		return NULL;
	}

	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);

	*dma_handle = virt_to_phys(ret);
	if (!WARN_ON(!dev))
		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);

	return ret_nocache;
}

/*
 * Set the page permissions for a particular virtual address.  If the
 * address is a vmalloc mapping (or other non-linear mapping), then
 * find the linear mapping of the page and also set its protections to
 * match.
 */
static void set_aliased_prot(void *v, pgprot_t prot)
{
	int level;
	pte_t *ptep;
	pte_t pte;
	unsigned long pfn;
	struct page *page;

	ptep = lookup_address((unsigned long)v, &level);
	BUG_ON(ptep == NULL);

	pfn = pte_pfn(*ptep);
	page = pfn_to_page(pfn);

	pte = pfn_pte(pfn, prot);

	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
		BUG();

	if (!PageHighMem(page)) {
		void *av = __va(PFN_PHYS(pfn));

		if (av != v)
			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
				BUG();
	} else
		kmap_flush_unused();
}

static void xen_load_gdt(const struct desc_ptr *dtr)
{
	unsigned long va = dtr->address;
	unsigned int size = dtr->size + 1;
	unsigned pages = (size + PAGE_SIZE - 1) / PAGE_SIZE;
	unsigned long frames[pages];
	int f;

	/* A GDT can be up to 64k in size, which corresponds to 8192
	   8-byte entries, or 16 4k pages.. */

	BUG_ON(size > 65536);
	BUG_ON(va & ~PAGE_MASK);

	for (f = 0; va < dtr->address + size; va += PAGE_SIZE, f++) {
		int level;
		pte_t *ptep = lookup_address(va, &level);
		unsigned long pfn, mfn;
		void *virt;

		BUG_ON(ptep == NULL);

		pfn = pte_pfn(*ptep);
		mfn = pfn_to_mfn(pfn);
		virt = __va(PFN_PHYS(pfn));

		frames[f] = mfn;

		make_lowmem_page_readonly((void *)va);
		make_lowmem_page_readonly(virt);
	}

	if (HYPERVISOR_set_gdt(frames, size / sizeof(struct desc_struct)))
		BUG();
}

/**
 *
 * Create a new NUMA distance table.
 *
 */
static int __init numa_alloc_distance(void)
{
	size_t size;
	u64 phys;
	int i, j;

	size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn),
				      size, PAGE_SIZE);
	if (WARN_ON(!phys))
		return -ENOMEM;

	memblock_reserve(phys, size);

	numa_distance = __va(phys);
	numa_distance_cnt = nr_node_ids;

	/* fill with the default distances */
	for (i = 0; i < numa_distance_cnt; i++)
		for (j = 0; j < numa_distance_cnt; j++)
			numa_distance[i * numa_distance_cnt + j] = i == j ?
				LOCAL_DISTANCE : REMOTE_DISTANCE;

	pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);

	return 0;
}

static void __init setup_initrd(void)
{
	unsigned long size;

	if (initrd_start >= initrd_end) {
		pr_info("initrd not found or empty");
		goto disable;
	}
	if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
		pr_err("initrd extends beyond end of memory");
		goto disable;
	}

	size = initrd_end - initrd_start;
	memblock_reserve(__pa(initrd_start), size);
	initrd_below_start_ok = 1;

	pr_info("Initial ramdisk at: 0x%p (%lu bytes)\n",
		(void *)(initrd_start), size);
	return;
disable:
	pr_cont(" - disabling initrd\n");
	initrd_start = 0;
	initrd_end = 0;
}

/* Create kernel-VA-space MMIO mapping for an on-chip IO device. */
void __iomem *iorpc_ioremap(int hv_fd, resource_size_t offset,
			    unsigned long size)
{
	pgprot_t mmio_base, prot = { 0 };
	unsigned long pfn;
	int err;

	/* Look up the shim's lotar and base PA. */
	err = __iorpc_get_mmio_base(hv_fd, &mmio_base);
	if (err) {
		TRACE("get_mmio_base() failure: %d\n", err);
		return NULL;
	}

	/* Make sure the HV driver approves of our offset and size. */
	err = __iorpc_check_mmio_offset(hv_fd, offset, size);
	if (err) {
		TRACE("check_mmio_offset() failure: %d\n", err);
		return NULL;
	}

	/*
	 * mmio_base contains a base pfn and homing coordinates.  Turn
	 * it into an MMIO pgprot and offset pfn.
	 */
	prot = hv_pte_set_lotar(prot, hv_pte_get_lotar(mmio_base));
	pfn = pte_pfn(mmio_base) + PFN_DOWN(offset);

	return ioremap_prot(PFN_PHYS(pfn), size, prot);
}

void init_mm(void)
{
    unsigned long start_pfn, max_pfn;

    printk("go_mm: initializing\n");

    arch_init_mm(&start_pfn, &max_pfn);

    printk("go_mm: initializing best fit page allocator for %lx-%lx\n",
        (unsigned long)pfn_to_virt(start_pfn),
        (unsigned long)pfn_to_virt(max_pfn));
    init_page_allocator(PFN_PHYS(start_pfn), PFN_PHYS(max_pfn));
    printk("go_mm: done\n");

    arch_init_p2m(max_pfn);
    arch_init_demand_mapping_area(max_pfn);
}

char * __init xen_memory_setup(void)
{
	unsigned long max_pfn = xen_start_info->nr_pages;

	e820.nr_map = 0;
	add_memory_region(0, PFN_PHYS(max_pfn), E820_RAM);

	return "Xen";
}

/*
 * Set the page permissions for a particular virtual address.  If the
 * address is a vmalloc mapping (or other non-linear mapping), then
 * find the linear mapping of the page and also set its protections to
 * match.
 */
static void set_aliased_prot(void *v, pgprot_t prot)
{
	int level;
	pte_t *ptep;
	pte_t pte;
	unsigned long pfn;
	struct page *page;
	unsigned char dummy;

	ptep = lookup_address((unsigned long)v, &level);
	BUG_ON(ptep == NULL);

	pfn = pte_pfn(*ptep);
	page = pfn_to_page(pfn);

	pte = pfn_pte(pfn, prot);

	/*
	 * Careful: update_va_mapping() will fail if the virtual address
	 * we're poking isn't populated in the page tables.  We don't
	 * need to worry about the direct map (that's always in the page
	 * tables), but we need to be careful about vmap space.  In
	 * particular, the top level page table can lazily propagate
	 * entries between processes, so if we've switched mms since we
	 * vmapped the target in the first place, we might not have the
	 * top-level page table entry populated.
	 *
	 * We disable preemption because we want the same mm active when
	 * we probe the target and when we issue the hypercall.  We'll
	 * have the same nominal mm, but if we're a kernel thread, lazy
	 * mm dropping could change our pgd.
	 *
	 * Out of an abundance of caution, this uses __get_user() to fault
	 * in the target address just in case there's some obscure case
	 * in which the target address isn't readable.
	 */

	preempt_disable();

	pagefault_disable();	/* Avoid warnings due to being atomic. */
	__get_user(dummy, (unsigned char __user __force *)v);
	pagefault_enable();

	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
		BUG();

	if (!PageHighMem(page)) {
		void *av = __va(PFN_PHYS(pfn));

		if (av != v)
			if (HYPERVISOR_update_va_mapping((unsigned long)av, pte, 0))
				BUG();
	} else
		kmap_flush_unused();

	preempt_enable();
}

static u64 __init mem_hole_size(u64 start, u64 end)
{
	unsigned long start_pfn = PFN_UP(start);
	unsigned long end_pfn = PFN_DOWN(end);

	if (start_pfn < end_pfn)
		return PFN_PHYS(absent_pages_in_range(start_pfn, end_pfn));
	return 0;
}

static void __init bootmem_init(void)
{
	unsigned long start_pfn, bootmap_size;
	unsigned long size = initrd_end - initrd_start;

	start_pfn = PFN_UP(__pa(&_end));

	min_low_pfn = PFN_UP(MEMORY_START);
	max_low_pfn = PFN_UP(MEMORY_START + MEMORY_SIZE);

	/* Initialize the boot-time allocator with low memory only. */
	bootmap_size = init_bootmem_node(NODE_DATA(0), start_pfn,
					 min_low_pfn, max_low_pfn);
	add_active_range(0, min_low_pfn, max_low_pfn);

	free_bootmem(PFN_PHYS(start_pfn),
		     (max_low_pfn - start_pfn) << PAGE_SHIFT);
	memory_present(0, start_pfn, max_low_pfn);

	/* Reserve space for the bootmem bitmap. */
	reserve_bootmem(PFN_PHYS(start_pfn), bootmap_size, BOOTMEM_DEFAULT);

	if (size == 0) {
		printk(KERN_INFO "Initrd not found or empty");
		goto disable;
	}

	if (__pa(initrd_end) > PFN_PHYS(max_low_pfn)) {
		printk(KERN_ERR "Initrd extends beyond end of memory");
		goto disable;
	}

	/* Reserve space for the initrd bitmap. */
	reserve_bootmem(__pa(initrd_start), size, BOOTMEM_DEFAULT);
	initrd_below_start_ok = 1;

	pr_info("Initial ramdisk at: 0x%lx (%lu bytes)\n",
		 initrd_start, size);
	return;
disable:
	printk(KERN_CONT " - disabling initrd\n");
	initrd_start = 0;
	initrd_end = 0;
}

/*
 * Register fully available low RAM pages with the bootmem allocator.
 */
static void __init register_bootmem_low_pages(void)
{
	unsigned long curr_pfn, last_pfn, pages;

	/*
	 * We are rounding up the start address of usable memory:
	 */
	curr_pfn = PFN_UP(__MEMORY_START);

	/*
	 * ... and at the end of the usable range downwards:
	 */
	last_pfn = PFN_DOWN(__pa(memory_end));

	if (last_pfn > max_low_pfn)
		last_pfn = max_low_pfn;

	pages = last_pfn - curr_pfn;
	free_bootmem(PFN_PHYS(curr_pfn), PFN_PHYS(pages));
}

/* Flush a page out of whatever cache(s) it is in. */
void homecache_flush_cache(struct page *page, int order)
{
	int pages = 1 << order;
	int length = cache_flush_length(pages * PAGE_SIZE);
	unsigned long pfn = page_to_pfn(page);
	struct cpumask home_mask;

	homecache_mask(page, pages, &home_mask);
	flush_remote(pfn, length, &home_mask, 0, 0, 0, NULL, NULL, 0);
	sim_validate_lines_evicted(PFN_PHYS(pfn), pages * PAGE_SIZE);
}