linux/arch/s390/mm/init.c

237 lines
5.9 KiB
C
Raw Normal View History

/*
* arch/s390/mm/init.c
*
* S390 version
* Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
* Author(s): Hartmut Penner (hp@de.ibm.com)
*
* Derived from "arch/i386/mm/init.c"
* Copyright (C) 1995 Linus Torvalds
*/
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/pagemap.h>
#include <linux/bootmem.h>
#include <linux/pfn.h>
#include <linux/poison.h>
#include <linux/initrd.h>
#include <linux/export.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include <asm/processor.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/dma.h>
#include <asm/lowcore.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/sections.h>
pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((__aligned__(PAGE_SIZE)));
unsigned long empty_zero_page, zero_page_mask;
EXPORT_SYMBOL(empty_zero_page);
static unsigned long setup_zero_pages(void)
{
struct cpuid cpu_id;
unsigned int order;
unsigned long size;
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 */
default:
order = 2;
break;
}
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--) {
SetPageReserved(page);
page++;
}
size = PAGE_SIZE << order;
zero_page_mask = (size - 1) & PAGE_MASK;
return 1UL << order;
}
/*
* paging_init() sets up the page tables
*/
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
unsigned long pgd_type;
init_mm.pgd = swapper_pg_dir;
S390_lowcore.kernel_asce = __pa(init_mm.pgd) & PAGE_MASK;
#ifdef CONFIG_64BIT
/* A three level page table (4TB) is enough for the kernel space. */
S390_lowcore.kernel_asce |= _ASCE_TYPE_REGION3 | _ASCE_TABLE_LENGTH;
pgd_type = _REGION3_ENTRY_EMPTY;
#else
S390_lowcore.kernel_asce |= _ASCE_TABLE_LENGTH;
pgd_type = _SEGMENT_ENTRY_EMPTY;
#endif
clear_table((unsigned long *) init_mm.pgd, pgd_type,
sizeof(unsigned long)*2048);
vmem_map_init();
/* enable virtual mapping in kernel mode */
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
__ctl_load(S390_lowcore.kernel_asce, 13, 13);
Fix IRQ flag handling naming Fix the IRQ flag handling naming. In linux/irqflags.h under one configuration, it maps: local_irq_enable() -> raw_local_irq_enable() local_irq_disable() -> raw_local_irq_disable() local_irq_save() -> raw_local_irq_save() ... and under the other configuration, it maps: raw_local_irq_enable() -> local_irq_enable() raw_local_irq_disable() -> local_irq_disable() raw_local_irq_save() -> local_irq_save() ... This is quite confusing. There should be one set of names expected of the arch, and this should be wrapped to give another set of names that are expected by users of this facility. Change this to have the arch provide: flags = arch_local_save_flags() flags = arch_local_irq_save() arch_local_irq_restore(flags) arch_local_irq_disable() arch_local_irq_enable() arch_irqs_disabled_flags(flags) arch_irqs_disabled() arch_safe_halt() Then linux/irqflags.h wraps these to provide: raw_local_save_flags(flags) raw_local_irq_save(flags) raw_local_irq_restore(flags) raw_local_irq_disable() raw_local_irq_enable() raw_irqs_disabled_flags(flags) raw_irqs_disabled() raw_safe_halt() with type checking on the flags 'arguments', and then wraps those to provide: local_save_flags(flags) local_irq_save(flags) local_irq_restore(flags) local_irq_disable() local_irq_enable() irqs_disabled_flags(flags) irqs_disabled() safe_halt() with tracing included if enabled. The arch functions can now all be inline functions rather than some of them having to be macros. Signed-off-by: David Howells <dhowells@redhat.com> [X86, FRV, MN10300] Signed-off-by: Chris Metcalf <cmetcalf@tilera.com> [Tile] Signed-off-by: Michal Simek <monstr@monstr.eu> [Microblaze] Tested-by: Catalin Marinas <catalin.marinas@arm.com> [ARM] Acked-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> [AVR] Acked-by: Tony Luck <tony.luck@intel.com> [IA-64] Acked-by: Hirokazu Takata <takata@linux-m32r.org> [M32R] Acked-by: Greg Ungerer <gerg@uclinux.org> [M68K/M68KNOMMU] Acked-by: Ralf Baechle <ralf@linux-mips.org> [MIPS] Acked-by: Kyle McMartin <kyle@mcmartin.ca> [PA-RISC] Acked-by: Paul Mackerras <paulus@samba.org> [PowerPC] Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com> [S390] Acked-by: Chen Liqin <liqin.chen@sunplusct.com> [Score] Acked-by: Matt Fleming <matt@console-pimps.org> [SH] Acked-by: David S. Miller <davem@davemloft.net> [Sparc] Acked-by: Chris Zankel <chris@zankel.net> [Xtensa] Reviewed-by: Richard Henderson <rth@twiddle.net> [Alpha] Reviewed-by: Yoshinori Sato <ysato@users.sourceforge.jp> [H8300] Cc: starvik@axis.com [CRIS] Cc: jesper.nilsson@axis.com [CRIS] Cc: linux-cris-kernel@axis.com
2010-10-07 13:08:55 +00:00
arch_local_irq_restore(4UL << (BITS_PER_LONG - 8));
atomic_set(&init_mm.context.attach_count, 1);
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);
fault_init();
}
void __init mem_init(void)
{
unsigned long codesize, reservedpages, datasize, initsize;
max_mapnr = num_physpages = max_low_pfn;
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
/* Setup guest page hinting */
cmma_init();
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();
totalram_pages -= 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",
nr_free_pages() << (PAGE_SHIFT-10),
max_mapnr << (PAGE_SHIFT-10),
codesize >> 10,
reservedpages << (PAGE_SHIFT-10),
datasize >>10,
initsize >> 10);
printk("Write protected kernel read-only data: %#lx - %#lx\n",
(unsigned long)&_stext,
PFN_ALIGN((unsigned long)&_eshared) - 1);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
void kernel_map_pages(struct page *page, int numpages, int enable)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long address;
int i;
for (i = 0; i < numpages; i++) {
address = page_to_phys(page + i);
pgd = pgd_offset_k(address);
pud = pud_offset(pgd, address);
pmd = pmd_offset(pud, address);
pte = pte_offset_kernel(pmd, address);
if (!enable) {
__ptep_ipte(address, pte);
pte_val(*pte) = _PAGE_TYPE_EMPTY;
continue;
}
*pte = mk_pte_phys(address, __pgprot(_PAGE_TYPE_RW));
/* Flush cpu write queue. */
mb();
}
}
#endif
void free_init_pages(char *what, unsigned long begin, unsigned long end)
{
unsigned long addr = begin;
if (begin >= end)
return;
for (; addr < end; addr += PAGE_SIZE) {
ClearPageReserved(virt_to_page(addr));
init_page_count(virt_to_page(addr));
memset((void *)(addr & PAGE_MASK), POISON_FREE_INITMEM,
PAGE_SIZE);
free_page(addr);
totalram_pages++;
}
printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
}
void free_initmem(void)
{
free_init_pages("unused kernel memory",
(unsigned long)&__init_begin,
(unsigned long)&__init_end);
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
free_init_pages("initrd memory", start, end);
}
#endif
#ifdef CONFIG_MEMORY_HOTPLUG
int arch_add_memory(int nid, u64 start, u64 size)
{
struct pglist_data *pgdat;
struct zone *zone;
int rc;
pgdat = NODE_DATA(nid);
zone = pgdat->node_zones + ZONE_MOVABLE;
rc = vmem_add_mapping(start, size);
if (rc)
return rc;
mm: show node to memory section relationship with symlinks in sysfs Show node to memory section relationship with symlinks in sysfs Add /sys/devices/system/node/nodeX/memoryY symlinks for all the memory sections located on nodeX. For example: /sys/devices/system/node/node1/memory135 -> ../../memory/memory135 indicates that memory section 135 resides on node1. Also revises documentation to cover this change as well as updating Documentation/ABI/testing/sysfs-devices-memory to include descriptions of memory hotremove files 'phys_device', 'phys_index', and 'state' that were previously not described there. In addition to it always being a good policy to provide users with the maximum possible amount of physical location information for resources that can be hot-added and/or hot-removed, the following are some (but likely not all) of the user benefits provided by this change. Immediate: - Provides information needed to determine the specific node on which a defective DIMM is located. This will reduce system downtime when the node or defective DIMM is swapped out. - Prevents unintended onlining of a memory section that was previously offlined due to a defective DIMM. This could happen during node hot-add when the user or node hot-add assist script onlines _all_ offlined sections due to user or script inability to identify the specific memory sections located on the hot-added node. The consequences of reintroducing the defective memory could be ugly. - Provides information needed to vary the amount and distribution of memory on specific nodes for testing or debugging purposes. Future: - Will provide information needed to identify the memory sections that need to be offlined prior to physical removal of a specific node. Symlink creation during boot was tested on 2-node x86_64, 2-node ppc64, and 2-node ia64 systems. Symlink creation during physical memory hot-add tested on a 2-node x86_64 system. Signed-off-by: Gary Hade <garyhade@us.ibm.com> Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com> Acked-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-01-06 22:39:14 +00:00
rc = __add_pages(nid, zone, PFN_DOWN(start), PFN_DOWN(size));
if (rc)
vmem_remove_mapping(start, size);
return rc;
}
#endif /* CONFIG_MEMORY_HOTPLUG */