1 files changed, 160 insertions, 230 deletions

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index e1881c31b1c..0c1073ed1e8 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -1,8 +1,6 @@
 /*
- *  arch/s390/mm/init.c
- *
  *  S390 version
- *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
+ *    Copyright IBM Corp. 1999
  *    Author(s): Hartmut Penner (hp@de.ibm.com)
  *
  *  Derived from "arch/i386/mm/init.c"
@@ -23,10 +21,13 @@
 #include <linux/init.h>
 #include <linux/pagemap.h>
 #include <linux/bootmem.h>
+#include <linux/memory.h>
 #include <linux/pfn.h>
-
+#include <linux/poison.h>
+#include <linux/initrd.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -35,267 +36,196 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+#include <asm/ctl_reg.h>
+#include <asm/sclp.h>
 
 pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
-char  empty_zero_page[PAGE_SIZE] __attribute__((__aligned__(PAGE_SIZE)));
 
-void diag10(unsigned long addr)
-{
-        if (addr >= 0x7ff00000)
-                return;
-	asm volatile(
-#ifdef CONFIG_64BIT
-		"	sam31\n"
-		"	diag	%0,%0,0x10\n"
-		"0:	sam64\n"
-#else
-		"	diag	%0,%0,0x10\n"
-		"0:\n"
-#endif
-		EX_TABLE(0b,0b)
-		: : "a" (addr));
-}
+unsigned long empty_zero_page, zero_page_mask;
+EXPORT_SYMBOL(empty_zero_page);
 
-void show_mem(void)
+static void __init setup_zero_pages(void)
 {
-        int i, total = 0, reserved = 0;
-        int shared = 0, cached = 0;
+	struct cpuid cpu_id;
+	unsigned int order;
 	struct page *page;
+	int i;
+
+	get_cpu_id(&cpu_id);
+	switch (cpu_id.machine) {
+	case 0x9672:	/* g5 */
+	case 0x2064:	/* z900 */
+	case 0x2066:	/* z900 */
+	case 0x2084:	/* z990 */
+	case 0x2086:	/* z990 */
+	case 0x2094:	/* z9-109 */
+	case 0x2096:	/* z9-109 */
+		order = 0;
+		break;
+	case 0x2097:	/* z10 */
+	case 0x2098:	/* z10 */
+	case 0x2817:	/* z196 */
+	case 0x2818:	/* z196 */
+		order = 2;
+		break;
+	case 0x2827:	/* zEC12 */
+	case 0x2828:	/* zEC12 */
+	default:
+		order = 5;
+		break;
+	}
+	/* Limit number of empty zero pages for small memory sizes */
+	if (order > 2 && totalram_pages <= 16384)
+		order = 2;
+
+	empty_zero_page = __get_free_pages(GFP_KERNEL | __GFP_ZERO, order);
+	if (!empty_zero_page)
+		panic("Out of memory in setup_zero_pages");
+
+	page = virt_to_page((void *) empty_zero_page);
+	split_page(page, order);
+	for (i = 1 << order; i > 0; i--) {
+		mark_page_reserved(page);
+		page++;
+	}
 
-        printk("Mem-info:\n");
-        show_free_areas();
-        printk("Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
-        i = max_mapnr;
-        while (i-- > 0) {
-		page = pfn_to_page(i);
-                total++;
-		if (PageReserved(page))
-                        reserved++;
-		else if (PageSwapCache(page))
-                        cached++;
-		else if (page_count(page))
-			shared += page_count(page) - 1;
-        }
-        printk("%d pages of RAM\n",total);
-        printk("%d reserved pages\n",reserved);
-        printk("%d pages shared\n",shared);
-        printk("%d pages swap cached\n",cached);
+	zero_page_mask = ((PAGE_SIZE << order) - 1) & PAGE_MASK;
 }
 
-extern unsigned long __initdata zholes_size[];
 /*
  * paging_init() sets up the page tables
  */
-
-#ifndef CONFIG_64BIT
-void __init paging_init(void)
-{
-        pgd_t * pg_dir;
-        pte_t * pg_table;
-        pte_t   pte;
-	int     i;
-        unsigned long tmp;
-        unsigned long pfn = 0;
-        unsigned long pgdir_k = (__pa(swapper_pg_dir) & PAGE_MASK) | _KERNSEG_TABLE;
-        static const int ssm_mask = 0x04000000L;
-	unsigned long ro_start_pfn, ro_end_pfn;
-	unsigned long zones_size[MAX_NR_ZONES];
-
-	ro_start_pfn = PFN_DOWN((unsigned long)&__start_rodata);
-	ro_end_pfn = PFN_UP((unsigned long)&__end_rodata);
-
-	memset(zones_size, 0, sizeof(zones_size));
-	zones_size[ZONE_DMA] = max_low_pfn;
-	free_area_init_node(0, &contig_page_data, zones_size,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT,
-			    zholes_size);
-
-	/* unmap whole virtual address space */
-	
-        pg_dir = swapper_pg_dir;
-
-	for (i = 0; i < PTRS_PER_PGD; i++)
-		pmd_clear((pmd_t *) pg_dir++);
-		
-	/*
-	 * map whole physical memory to virtual memory (identity mapping) 
-	 */
-
-        pg_dir = swapper_pg_dir;
-
-        while (pfn < max_low_pfn) {
-                /*
-                 * pg_table is physical at this point
-                 */
-		pg_table = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
-
-		pmd_populate_kernel(&init_mm, (pmd_t *) pg_dir, pg_table);
-                pg_dir++;
-
-                for (tmp = 0 ; tmp < PTRS_PER_PTE ; tmp++,pg_table++) {
-			if (pfn >= ro_start_pfn && pfn < ro_end_pfn)
-				pte = pfn_pte(pfn, __pgprot(_PAGE_RO));
-			else
-				pte = pfn_pte(pfn, PAGE_KERNEL);
-                        if (pfn >= max_low_pfn)
-				pte_val(pte) = _PAGE_TYPE_EMPTY;
-			set_pte(pg_table, pte);
-                        pfn++;
-                }
-        }
-
-	S390_lowcore.kernel_asce = pgdir_k;
-
-        /* enable virtual mapping in kernel mode */
-	__ctl_load(pgdir_k, 1, 1);
-	__ctl_load(pgdir_k, 7, 7);
-	__ctl_load(pgdir_k, 13, 13);
-	__raw_local_irq_ssm(ssm_mask);
-
-        local_flush_tlb();
-}
-
-#else /* CONFIG_64BIT */
-
 void __init paging_init(void)
 {
-        pgd_t * pg_dir;
-	pmd_t * pm_dir;
-        pte_t * pt_dir;
-        pte_t   pte;
-	int     i,j,k;
-        unsigned long pfn = 0;
-        unsigned long pgdir_k = (__pa(swapper_pg_dir) & PAGE_MASK) |
-          _KERN_REGION_TABLE;
-	static const int ssm_mask = 0x04000000L;
-	unsigned long zones_size[MAX_NR_ZONES];
-	unsigned long dma_pfn, high_pfn;
-	unsigned long ro_start_pfn, ro_end_pfn;
+	unsigned long max_zone_pfns[MAX_NR_ZONES];
+	unsigned long pgd_type, asce_bits;
 
-	memset(zones_size, 0, sizeof(zones_size));
-	dma_pfn = MAX_DMA_ADDRESS >> PAGE_SHIFT;
-	high_pfn = max_low_pfn;
-	ro_start_pfn = PFN_DOWN((unsigned long)&__start_rodata);
-	ro_end_pfn = PFN_UP((unsigned long)&__end_rodata);
-
-	if (dma_pfn > high_pfn)
-		zones_size[ZONE_DMA] = high_pfn;
-	else {
-		zones_size[ZONE_DMA] = dma_pfn;
-		zones_size[ZONE_NORMAL] = high_pfn - dma_pfn;
+	init_mm.pgd = swapper_pg_dir;
+#ifdef CONFIG_64BIT
+	if (VMALLOC_END > (1UL << 42)) {
+		asce_bits = _ASCE_TYPE_REGION2 | _ASCE_TABLE_LENGTH;
+		pgd_type = _REGION2_ENTRY_EMPTY;
+	} else {
+		asce_bits = _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
+		pgd_type = _REGION3_ENTRY_EMPTY;
 	}
-
-	/* Initialize mem_map[].  */
-	free_area_init_node(0, &contig_page_data, zones_size,
-			    __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
-
-	/*
-	 * map whole physical memory to virtual memory (identity mapping) 
-	 */
-
-        pg_dir = swapper_pg_dir;
-	
-        for (i = 0 ; i < PTRS_PER_PGD ; i++,pg_dir++) {
-	
-                if (pfn >= max_low_pfn) {
-                        pgd_clear(pg_dir);
-                        continue;
-                }          
-        
-		pm_dir = (pmd_t *) alloc_bootmem_pages(PAGE_SIZE * 4);
-                pgd_populate(&init_mm, pg_dir, pm_dir);
-
-                for (j = 0 ; j < PTRS_PER_PMD ; j++,pm_dir++) {
-                        if (pfn >= max_low_pfn) {
-                                pmd_clear(pm_dir);
-                                continue; 
-                        }          
-                        
-			pt_dir = (pte_t *) alloc_bootmem_pages(PAGE_SIZE);
-                        pmd_populate_kernel(&init_mm, pm_dir, pt_dir);
-	
-                        for (k = 0 ; k < PTRS_PER_PTE ; k++,pt_dir++) {
-				if (pfn >= ro_start_pfn && pfn < ro_end_pfn)
-					pte = pfn_pte(pfn, __pgprot(_PAGE_RO));
-				else
-					pte = pfn_pte(pfn, PAGE_KERNEL);
-				if (pfn >= max_low_pfn)
-					pte_val(pte) = _PAGE_TYPE_EMPTY;
-                                set_pte(pt_dir, pte);
-                                pfn++;
-                        }
-                }
-        }
-
-	S390_lowcore.kernel_asce = pgdir_k;
+#else
+	asce_bits = _ASCE_TABLE_LENGTH;
+	pgd_type = _SEGMENT_ENTRY_EMPTY;
+#endif
+	S390_lowcore.kernel_asce = (__pa(init_mm.pgd) & PAGE_MASK) | asce_bits;
+	clear_table((unsigned long *) init_mm.pgd, pgd_type,
+		    sizeof(unsigned long)*2048);
+	vmem_map_init();
 
         /* enable virtual mapping in kernel mode */
-	__ctl_load(pgdir_k, 1, 1);
-	__ctl_load(pgdir_k, 7, 7);
-	__ctl_load(pgdir_k, 13, 13);
-	__raw_local_irq_ssm(ssm_mask);
-
-        local_flush_tlb();
+	__ctl_load(S390_lowcore.kernel_asce, 1, 1);
+	__ctl_load(S390_lowcore.kernel_asce, 7, 7);
+	__ctl_load(S390_lowcore.kernel_asce, 13, 13);
+	arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
+
+	sparse_memory_present_with_active_regions(MAX_NUMNODES);
+	sparse_init();
+	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
+	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+	free_area_init_nodes(max_zone_pfns);
 }
-#endif /* CONFIG_64BIT */
 
 void __init mem_init(void)
 {
-	unsigned long codesize, reservedpages, datasize, initsize;
+	if (MACHINE_HAS_TLB_LC)
+		cpumask_set_cpu(0, &init_mm.context.cpu_attach_mask);
+	cpumask_set_cpu(0, mm_cpumask(&init_mm));
+	atomic_set(&init_mm.context.attach_count, 1);
 
-        max_mapnr = num_physpages = max_low_pfn;
+        max_mapnr = max_low_pfn;
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
-        /* clear the zero-page */
-        memset(empty_zero_page, 0, PAGE_SIZE);
+	/* Setup guest page hinting */
+	cmma_init();
 
 	/* this will put all low memory onto the freelists */
-	totalram_pages += free_all_bootmem();
+	free_all_bootmem();
+	setup_zero_pages();	/* Setup zeroed pages. */
 
-	reservedpages = 0;
-
-	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
-	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
-	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
-        printk("Memory: %luk/%luk available (%ldk kernel code, %ldk reserved, %ldk data, %ldk init)\n",
-                (unsigned long) nr_free_pages() << (PAGE_SHIFT-10),
-                max_mapnr << (PAGE_SHIFT-10),
-                codesize >> 10,
-                reservedpages << (PAGE_SHIFT-10),
-                datasize >>10,
-                initsize >> 10);
+	mem_init_print_info(NULL);
 	printk("Write protected kernel read-only data: %#lx - %#lx\n",
-	       (unsigned long)&__start_rodata,
-	       PFN_ALIGN((unsigned long)&__end_rodata) - 1);
+	       (unsigned long)&_stext,
+	       PFN_ALIGN((unsigned long)&_eshared) - 1);
 }
 
 void free_initmem(void)
 {
-        unsigned long addr;
-
-        addr = (unsigned long)(&__init_begin);
-        for (; addr < (unsigned long)(&__init_end); addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		free_page(addr);
-		totalram_pages++;
-        }
-        printk ("Freeing unused kernel memory: %ldk freed\n",
-		((unsigned long)&__init_end - (unsigned long)&__init_begin) >> 10);
+	free_initmem_default(POISON_FREE_INITMEM);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
+void __init free_initrd_mem(unsigned long start, unsigned long end)
 {
-        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++;
-        }
+	free_reserved_area((void *)start, (void *)end, POISON_FREE_INITMEM,
+			   "initrd");
+}
+#endif
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+int arch_add_memory(int nid, u64 start, u64 size)
+{
+	unsigned long zone_start_pfn, zone_end_pfn, nr_pages;
+	unsigned long start_pfn = PFN_DOWN(start);
+	unsigned long size_pages = PFN_DOWN(size);
+	struct zone *zone;
+	int rc;
+
+	rc = vmem_add_mapping(start, size);
+	if (rc)
+		return rc;
+	for_each_zone(zone) {
+		if (zone_idx(zone) != ZONE_MOVABLE) {
+			/* Add range within existing zone limits */
+			zone_start_pfn = zone->zone_start_pfn;
+			zone_end_pfn = zone->zone_start_pfn +
+				       zone->spanned_pages;
+		} else {
+			/* Add remaining range to ZONE_MOVABLE */
+			zone_start_pfn = start_pfn;
+			zone_end_pfn = start_pfn + size_pages;
+		}
+		if (start_pfn < zone_start_pfn || start_pfn >= zone_end_pfn)
+			continue;
+		nr_pages = (start_pfn + size_pages > zone_end_pfn) ?
+			   zone_end_pfn - start_pfn : size_pages;
+		rc = __add_pages(nid, zone, start_pfn, nr_pages);
+		if (rc)
+			break;
+		start_pfn += nr_pages;
+		size_pages -= nr_pages;
+		if (!size_pages)
+			break;
+	}
+	if (rc)
+		vmem_remove_mapping(start, size);
+	return rc;
+}
+
+unsigned long memory_block_size_bytes(void)
+{
+	/*
+	 * Make sure the memory block size is always greater
+	 * or equal than the memory increment size.
+	 */
+	return max_t(unsigned long, MIN_MEMORY_BLOCK_SIZE, sclp_get_rzm());
+}
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/*
+	 * There is no hardware or firmware interface which could trigger a
+	 * hot memory remove on s390. So there is nothing that needs to be
+	 * implemented.
+	 */
+	return -EBUSY;
 }
 #endif
+#endif /* CONFIG_MEMORY_HOTPLUG */