2005-09-26 08:04:21 +02:00
|
|
|
/*
|
|
|
|
* PowerPC version
|
|
|
|
* Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
|
|
|
|
*
|
|
|
|
* Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
|
|
|
|
* and Cort Dougan (PReP) (cort@cs.nmt.edu)
|
|
|
|
* Copyright (C) 1996 Paul Mackerras
|
|
|
|
* PPC44x/36-bit changes by Matt Porter (mporter@mvista.com)
|
|
|
|
*
|
|
|
|
* Derived from "arch/i386/mm/init.c"
|
|
|
|
* Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public License
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the License, or (at your option) any later version.
|
|
|
|
*
|
|
|
|
*/
|
|
|
|
|
2011-07-23 00:24:23 +02:00
|
|
|
#include <linux/export.h>
|
2005-09-26 08:04:21 +02:00
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/errno.h>
|
|
|
|
#include <linux/string.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 09:04:11 +01:00
|
|
|
#include <linux/gfp.h>
|
2005-09-26 08:04:21 +02:00
|
|
|
#include <linux/types.h>
|
|
|
|
#include <linux/mm.h>
|
|
|
|
#include <linux/stddef.h>
|
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/bootmem.h>
|
|
|
|
#include <linux/highmem.h>
|
|
|
|
#include <linux/initrd.h>
|
|
|
|
#include <linux/pagemap.h>
|
2007-05-08 11:25:00 +02:00
|
|
|
#include <linux/suspend.h>
|
2010-07-12 06:36:09 +02:00
|
|
|
#include <linux/memblock.h>
|
2009-10-26 20:24:31 +01:00
|
|
|
#include <linux/hugetlb.h>
|
2011-11-02 15:56:12 +01:00
|
|
|
#include <linux/slab.h>
|
2014-10-14 13:17:47 +02:00
|
|
|
#include <linux/vmalloc.h>
|
2005-09-26 08:04:21 +02:00
|
|
|
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/prom.h>
|
|
|
|
#include <asm/io.h>
|
|
|
|
#include <asm/mmu_context.h>
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/mmu.h>
|
|
|
|
#include <asm/smp.h>
|
|
|
|
#include <asm/machdep.h>
|
|
|
|
#include <asm/btext.h>
|
|
|
|
#include <asm/tlb.h>
|
2005-10-06 04:23:33 +02:00
|
|
|
#include <asm/sections.h>
|
2008-07-01 03:30:06 +02:00
|
|
|
#include <asm/sparsemem.h>
|
2005-10-10 13:58:35 +02:00
|
|
|
#include <asm/vdso.h>
|
2008-04-23 15:05:20 +02:00
|
|
|
#include <asm/fixmap.h>
|
2010-03-16 14:16:25 +01:00
|
|
|
#include <asm/swiotlb.h>
|
2011-12-02 13:26:23 +01:00
|
|
|
#include <asm/rtas.h>
|
2005-09-26 08:04:21 +02:00
|
|
|
|
|
|
|
#include "mmu_decl.h"
|
|
|
|
|
|
|
|
#ifndef CPU_FTR_COHERENT_ICACHE
|
|
|
|
#define CPU_FTR_COHERENT_ICACHE 0 /* XXX for now */
|
|
|
|
#define CPU_FTR_NOEXECUTE 0
|
|
|
|
#endif
|
|
|
|
|
2012-08-21 03:42:33 +02:00
|
|
|
unsigned long long memory_limit;
|
2005-10-06 04:23:33 +02:00
|
|
|
|
2008-04-23 15:05:20 +02:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
pte_t *kmap_pte;
|
2013-03-10 04:22:39 +01:00
|
|
|
EXPORT_SYMBOL(kmap_pte);
|
2008-04-23 15:05:20 +02:00
|
|
|
pgprot_t kmap_prot;
|
|
|
|
EXPORT_SYMBOL(kmap_prot);
|
2016-05-05 09:54:08 +02:00
|
|
|
#define TOP_ZONE ZONE_HIGHMEM
|
2008-04-23 15:05:20 +02:00
|
|
|
|
|
|
|
static inline pte_t *virt_to_kpte(unsigned long vaddr)
|
|
|
|
{
|
|
|
|
return pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr),
|
|
|
|
vaddr), vaddr), vaddr);
|
|
|
|
}
|
2016-05-05 09:54:08 +02:00
|
|
|
#else
|
|
|
|
#define TOP_ZONE ZONE_NORMAL
|
2008-04-23 15:05:20 +02:00
|
|
|
#endif
|
|
|
|
|
2005-09-26 08:04:21 +02:00
|
|
|
int page_is_ram(unsigned long pfn)
|
|
|
|
{
|
|
|
|
#ifndef CONFIG_PPC64 /* XXX for now */
|
2008-09-15 12:43:35 +02:00
|
|
|
return pfn < max_pfn;
|
2005-09-26 08:04:21 +02:00
|
|
|
#else
|
2008-09-15 12:43:35 +02:00
|
|
|
unsigned long paddr = (pfn << PAGE_SHIFT);
|
2010-08-04 05:43:53 +02:00
|
|
|
struct memblock_region *reg;
|
2005-09-26 08:04:21 +02:00
|
|
|
|
2010-08-04 05:43:53 +02:00
|
|
|
for_each_memblock(memory, reg)
|
|
|
|
if (paddr >= reg->base && paddr < (reg->base + reg->size))
|
2005-09-26 08:04:21 +02:00
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
#endif
|
|
|
|
}
|
|
|
|
|
2005-10-29 02:46:18 +02:00
|
|
|
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
|
2005-09-26 08:04:21 +02:00
|
|
|
unsigned long size, pgprot_t vma_prot)
|
|
|
|
{
|
|
|
|
if (ppc_md.phys_mem_access_prot)
|
2005-10-29 02:46:18 +02:00
|
|
|
return ppc_md.phys_mem_access_prot(file, pfn, size, vma_prot);
|
2005-09-26 08:04:21 +02:00
|
|
|
|
2005-10-29 02:46:18 +02:00
|
|
|
if (!page_is_ram(pfn))
|
2008-12-18 20:13:51 +01:00
|
|
|
vma_prot = pgprot_noncached(vma_prot);
|
|
|
|
|
2005-09-26 08:04:21 +02:00
|
|
|
return vma_prot;
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(phys_mem_access_prot);
|
|
|
|
|
2005-10-31 03:37:12 +01:00
|
|
|
#ifdef CONFIG_MEMORY_HOTPLUG
|
|
|
|
|
2006-06-27 11:53:30 +02:00
|
|
|
#ifdef CONFIG_NUMA
|
|
|
|
int memory_add_physaddr_to_nid(u64 start)
|
|
|
|
{
|
|
|
|
return hot_add_scn_to_nid(start);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2016-07-05 07:07:54 +02:00
|
|
|
int __weak create_section_mapping(unsigned long start, unsigned long end)
|
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
|
|
|
int __weak remove_section_mapping(unsigned long start, unsigned long end)
|
|
|
|
{
|
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
2015-08-09 21:29:06 +02:00
|
|
|
int arch_add_memory(int nid, u64 start, u64 size, bool for_device)
|
2005-10-31 03:37:12 +01:00
|
|
|
{
|
2005-12-05 21:06:42 +01:00
|
|
|
struct pglist_data *pgdata;
|
2005-10-31 03:37:12 +01:00
|
|
|
struct zone *zone;
|
|
|
|
unsigned long start_pfn = start >> PAGE_SHIFT;
|
|
|
|
unsigned long nr_pages = size >> PAGE_SHIFT;
|
2016-02-09 04:32:42 +01:00
|
|
|
int rc;
|
2005-10-31 03:37:12 +01:00
|
|
|
|
2016-12-09 01:07:38 +01:00
|
|
|
resize_hpt_for_hotplug(memblock_phys_mem_size());
|
|
|
|
|
2005-12-05 21:06:42 +01:00
|
|
|
pgdata = NODE_DATA(nid);
|
|
|
|
|
2006-03-22 08:00:05 +01:00
|
|
|
start = (unsigned long)__va(start);
|
2016-02-09 04:32:42 +01:00
|
|
|
rc = create_section_mapping(start, start + size);
|
|
|
|
if (rc) {
|
|
|
|
pr_warning(
|
|
|
|
"Unable to create mapping for hot added memory 0x%llx..0x%llx: %d\n",
|
|
|
|
start, start + size, rc);
|
|
|
|
return -EFAULT;
|
|
|
|
}
|
2005-11-08 01:25:48 +01:00
|
|
|
|
2005-10-31 03:37:12 +01:00
|
|
|
/* this should work for most non-highmem platforms */
|
2014-08-07 01:07:45 +02:00
|
|
|
zone = pgdata->node_zones +
|
2015-08-09 21:29:06 +02:00
|
|
|
zone_for_memory(nid, start, size, 0, for_device);
|
2005-10-31 03:37:12 +01:00
|
|
|
|
2009-01-06 23:39:14 +01:00
|
|
|
return __add_pages(nid, zone, start_pfn, nr_pages);
|
2005-10-31 03:37:12 +01:00
|
|
|
}
|
2013-02-23 01:32:58 +01:00
|
|
|
|
|
|
|
#ifdef CONFIG_MEMORY_HOTREMOVE
|
|
|
|
int arch_remove_memory(u64 start, u64 size)
|
|
|
|
{
|
|
|
|
unsigned long start_pfn = start >> PAGE_SHIFT;
|
|
|
|
unsigned long nr_pages = size >> PAGE_SHIFT;
|
|
|
|
struct zone *zone;
|
2014-01-27 17:54:06 +01:00
|
|
|
int ret;
|
2013-02-23 01:32:58 +01:00
|
|
|
|
|
|
|
zone = page_zone(pfn_to_page(start_pfn));
|
2014-01-27 17:54:06 +01:00
|
|
|
ret = __remove_pages(zone, start_pfn, nr_pages);
|
2014-10-14 13:17:47 +02:00
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
/* Remove htab bolted mappings for this section of memory */
|
|
|
|
start = (unsigned long)__va(start);
|
|
|
|
ret = remove_section_mapping(start, start + size);
|
|
|
|
|
|
|
|
/* Ensure all vmalloc mappings are flushed in case they also
|
|
|
|
* hit that section of memory
|
|
|
|
*/
|
|
|
|
vm_unmap_aliases();
|
2014-01-27 17:54:06 +01:00
|
|
|
|
2016-12-09 01:07:38 +01:00
|
|
|
resize_hpt_for_hotplug(memblock_phys_mem_size());
|
|
|
|
|
2014-01-27 17:54:06 +01:00
|
|
|
return ret;
|
2013-02-23 01:32:58 +01:00
|
|
|
}
|
|
|
|
#endif
|
2008-06-04 00:30:54 +02:00
|
|
|
#endif /* CONFIG_MEMORY_HOTPLUG */
|
2008-02-05 09:10:18 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* walk_memory_resource() needs to make sure there is no holes in a given
|
2008-04-18 22:33:53 +02:00
|
|
|
* memory range. PPC64 does not maintain the memory layout in /proc/iomem.
|
2010-07-12 06:36:09 +02:00
|
|
|
* Instead it maintains it in memblock.memory structures. Walk through the
|
2008-04-18 22:33:53 +02:00
|
|
|
* memory regions, find holes and callback for contiguous regions.
|
2008-02-05 09:10:18 +01:00
|
|
|
*/
|
|
|
|
int
|
2009-09-23 01:45:46 +02:00
|
|
|
walk_system_ram_range(unsigned long start_pfn, unsigned long nr_pages,
|
|
|
|
void *arg, int (*func)(unsigned long, unsigned long, void *))
|
2008-02-05 09:10:18 +01:00
|
|
|
{
|
2010-08-04 05:43:53 +02:00
|
|
|
struct memblock_region *reg;
|
|
|
|
unsigned long end_pfn = start_pfn + nr_pages;
|
|
|
|
unsigned long tstart, tend;
|
2008-04-18 22:33:53 +02:00
|
|
|
int ret = -1;
|
|
|
|
|
2010-08-04 05:43:53 +02:00
|
|
|
for_each_memblock(memory, reg) {
|
2010-10-12 23:07:09 +02:00
|
|
|
tstart = max(start_pfn, memblock_region_memory_base_pfn(reg));
|
|
|
|
tend = min(end_pfn, memblock_region_memory_end_pfn(reg));
|
2010-08-04 05:43:53 +02:00
|
|
|
if (tstart >= tend)
|
|
|
|
continue;
|
|
|
|
ret = (*func)(tstart, tend - tstart, arg);
|
2008-04-18 22:33:53 +02:00
|
|
|
if (ret)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
return ret;
|
2008-02-05 09:10:18 +01:00
|
|
|
}
|
2009-09-23 01:45:46 +02:00
|
|
|
EXPORT_SYMBOL_GPL(walk_system_ram_range);
|
2008-02-05 09:10:18 +01:00
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
#ifndef CONFIG_NEED_MULTIPLE_NODES
|
2014-09-17 14:15:33 +02:00
|
|
|
void __init initmem_init(void)
|
2005-10-06 04:23:33 +02:00
|
|
|
{
|
2010-07-12 06:36:09 +02:00
|
|
|
max_low_pfn = max_pfn = memblock_end_of_DRAM() >> PAGE_SHIFT;
|
2014-09-17 14:15:33 +02:00
|
|
|
min_low_pfn = MEMORY_START >> PAGE_SHIFT;
|
2005-10-06 04:23:33 +02:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
2008-04-15 21:52:22 +02:00
|
|
|
max_low_pfn = lowmem_end_addr >> PAGE_SHIFT;
|
2005-10-06 04:23:33 +02:00
|
|
|
#endif
|
|
|
|
|
2013-01-09 13:40:18 +01:00
|
|
|
/* Place all memblock_regions in the same node and merge contiguous
|
|
|
|
* memblock_regions
|
|
|
|
*/
|
2014-01-22 00:49:26 +01:00
|
|
|
memblock_set_node(0, (phys_addr_t)ULLONG_MAX, &memblock.memory, 0);
|
2006-09-27 10:49:49 +02:00
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
/* XXX need to clip this if using highmem? */
|
2006-09-27 10:49:49 +02:00
|
|
|
sparse_memory_present_with_active_regions(0);
|
2014-09-17 14:15:36 +02:00
|
|
|
sparse_init();
|
2005-10-06 04:23:33 +02:00
|
|
|
}
|
|
|
|
|
2007-05-08 11:25:00 +02:00
|
|
|
/* mark pages that don't exist as nosave */
|
|
|
|
static int __init mark_nonram_nosave(void)
|
|
|
|
{
|
2010-08-04 05:43:53 +02:00
|
|
|
struct memblock_region *reg, *prev = NULL;
|
|
|
|
|
|
|
|
for_each_memblock(memory, reg) {
|
|
|
|
if (prev &&
|
2010-10-12 23:07:09 +02:00
|
|
|
memblock_region_memory_end_pfn(prev) < memblock_region_memory_base_pfn(reg))
|
|
|
|
register_nosave_region(memblock_region_memory_end_pfn(prev),
|
|
|
|
memblock_region_memory_base_pfn(reg));
|
2010-08-04 05:43:53 +02:00
|
|
|
prev = reg;
|
2007-05-08 11:25:00 +02:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
2014-09-18 21:05:02 +02:00
|
|
|
#else /* CONFIG_NEED_MULTIPLE_NODES */
|
|
|
|
static int __init mark_nonram_nosave(void)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif
|
2007-05-08 11:25:00 +02:00
|
|
|
|
2014-08-09 01:40:42 +02:00
|
|
|
static bool zone_limits_final;
|
|
|
|
|
2016-05-11 11:22:18 +02:00
|
|
|
/*
|
|
|
|
* The memory zones past TOP_ZONE are managed by generic mm code.
|
|
|
|
* These should be set to zero since that's what every other
|
|
|
|
* architecture does.
|
|
|
|
*/
|
2014-08-09 01:40:42 +02:00
|
|
|
static unsigned long max_zone_pfns[MAX_NR_ZONES] = {
|
2016-05-11 11:22:18 +02:00
|
|
|
[0 ... TOP_ZONE ] = ~0UL,
|
|
|
|
[TOP_ZONE + 1 ... MAX_NR_ZONES - 1] = 0
|
2014-08-09 01:40:42 +02:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Restrict the specified zone and all more restrictive zones
|
|
|
|
* to be below the specified pfn. May not be called after
|
|
|
|
* paging_init().
|
|
|
|
*/
|
|
|
|
void __init limit_zone_pfn(enum zone_type zone, unsigned long pfn_limit)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (WARN_ON(zone_limits_final))
|
|
|
|
return;
|
|
|
|
|
|
|
|
for (i = zone; i >= 0; i--) {
|
|
|
|
if (max_zone_pfns[i] > pfn_limit)
|
|
|
|
max_zone_pfns[i] = pfn_limit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find the least restrictive zone that is entirely below the
|
|
|
|
* specified pfn limit. Returns < 0 if no suitable zone is found.
|
|
|
|
*
|
|
|
|
* pfn_limit must be u64 because it can exceed 32 bits even on 32-bit
|
|
|
|
* systems -- the DMA limit can be higher than any possible real pfn.
|
|
|
|
*/
|
|
|
|
int dma_pfn_limit_to_zone(u64 pfn_limit)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2016-05-05 09:54:08 +02:00
|
|
|
for (i = TOP_ZONE; i >= 0; i--) {
|
2014-08-09 01:40:42 +02:00
|
|
|
if (max_zone_pfns[i] <= pfn_limit)
|
|
|
|
return i;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -EPERM;
|
|
|
|
}
|
2007-05-08 11:25:00 +02:00
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
/*
|
|
|
|
* paging_init() sets up the page tables - in fact we've already done this.
|
|
|
|
*/
|
|
|
|
void __init paging_init(void)
|
|
|
|
{
|
2011-07-04 20:44:19 +02:00
|
|
|
unsigned long long total_ram = memblock_phys_mem_size();
|
2010-07-12 06:36:09 +02:00
|
|
|
phys_addr_t top_of_ram = memblock_end_of_DRAM();
|
2005-10-06 04:23:33 +02:00
|
|
|
|
2008-04-23 15:05:20 +02:00
|
|
|
#ifdef CONFIG_PPC32
|
|
|
|
unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
|
|
|
|
unsigned long end = __fix_to_virt(FIX_HOLE);
|
|
|
|
|
|
|
|
for (; v < end; v += PAGE_SIZE)
|
|
|
|
map_page(v, 0, 0); /* XXX gross */
|
|
|
|
#endif
|
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
map_page(PKMAP_BASE, 0, 0); /* XXX gross */
|
2008-04-23 15:05:20 +02:00
|
|
|
pkmap_page_table = virt_to_kpte(PKMAP_BASE);
|
|
|
|
|
|
|
|
kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
|
2005-10-06 04:23:33 +02:00
|
|
|
kmap_prot = PAGE_KERNEL;
|
|
|
|
#endif /* CONFIG_HIGHMEM */
|
|
|
|
|
2011-07-04 20:44:19 +02:00
|
|
|
printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%llx\n",
|
2008-07-31 05:51:42 +02:00
|
|
|
(unsigned long long)top_of_ram, total_ram);
|
2006-04-12 22:25:01 +02:00
|
|
|
printk(KERN_DEBUG "Memory hole size: %ldMB\n",
|
2008-07-09 17:09:23 +02:00
|
|
|
(long int)((top_of_ram - total_ram) >> 20));
|
2014-08-09 01:40:42 +02:00
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
#ifdef CONFIG_HIGHMEM
|
2014-08-09 01:40:42 +02:00
|
|
|
limit_zone_pfn(ZONE_NORMAL, lowmem_end_addr >> PAGE_SHIFT);
|
2006-09-27 10:49:49 +02:00
|
|
|
#endif
|
2016-05-05 09:54:08 +02:00
|
|
|
limit_zone_pfn(TOP_ZONE, top_of_ram >> PAGE_SHIFT);
|
2014-08-09 01:40:42 +02:00
|
|
|
zone_limits_final = true;
|
2006-09-27 10:49:49 +02:00
|
|
|
free_area_init_nodes(max_zone_pfns);
|
2007-05-08 11:25:00 +02:00
|
|
|
|
|
|
|
mark_nonram_nosave();
|
2005-10-06 04:23:33 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
void __init mem_init(void)
|
|
|
|
{
|
2013-10-12 02:22:38 +02:00
|
|
|
/*
|
|
|
|
* book3s is limited to 16 page sizes due to encoding this in
|
|
|
|
* a 4-bit field for slices.
|
|
|
|
*/
|
|
|
|
BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
|
|
|
|
|
2010-03-16 14:16:25 +01:00
|
|
|
#ifdef CONFIG_SWIOTLB
|
2012-08-03 12:14:10 +02:00
|
|
|
swiotlb_init(0);
|
2010-03-16 14:16:25 +01:00
|
|
|
#endif
|
|
|
|
|
2005-10-06 04:23:33 +02:00
|
|
|
high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
|
2013-07-04 00:04:32 +02:00
|
|
|
set_max_mapnr(max_pfn);
|
2013-07-04 00:03:24 +02:00
|
|
|
free_all_bootmem();
|
2005-10-06 04:23:33 +02:00
|
|
|
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
{
|
|
|
|
unsigned long pfn, highmem_mapnr;
|
|
|
|
|
2008-04-15 21:52:22 +02:00
|
|
|
highmem_mapnr = lowmem_end_addr >> PAGE_SHIFT;
|
2005-10-06 04:23:33 +02:00
|
|
|
for (pfn = highmem_mapnr; pfn < max_mapnr; ++pfn) {
|
2011-06-28 11:54:46 +02:00
|
|
|
phys_addr_t paddr = (phys_addr_t)pfn << PAGE_SHIFT;
|
2005-10-06 04:23:33 +02:00
|
|
|
struct page *page = pfn_to_page(pfn);
|
2013-07-04 00:04:09 +02:00
|
|
|
if (!memblock_is_reserved(paddr))
|
|
|
|
free_highmem_page(page);
|
2005-10-06 04:23:33 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HIGHMEM */
|
|
|
|
|
2011-06-28 21:54:47 +02:00
|
|
|
#if defined(CONFIG_PPC_FSL_BOOK3E) && !defined(CONFIG_SMP)
|
|
|
|
/*
|
|
|
|
* If smp is enabled, next_tlbcam_idx is initialized in the cpu up
|
|
|
|
* functions.... do it here for the non-smp case.
|
|
|
|
*/
|
|
|
|
per_cpu(next_tlbcam_idx, smp_processor_id()) =
|
|
|
|
(mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) - 1;
|
|
|
|
#endif
|
|
|
|
|
2013-07-04 00:04:09 +02:00
|
|
|
mem_init_print_info(NULL);
|
2009-05-27 05:44:50 +02:00
|
|
|
#ifdef CONFIG_PPC32
|
|
|
|
pr_info("Kernel virtual memory layout:\n");
|
|
|
|
pr_info(" * 0x%08lx..0x%08lx : fixmap\n", FIXADDR_START, FIXADDR_TOP);
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
|
|
pr_info(" * 0x%08lx..0x%08lx : highmem PTEs\n",
|
|
|
|
PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
|
|
|
|
#endif /* CONFIG_HIGHMEM */
|
2009-05-27 05:50:33 +02:00
|
|
|
#ifdef CONFIG_NOT_COHERENT_CACHE
|
|
|
|
pr_info(" * 0x%08lx..0x%08lx : consistent mem\n",
|
|
|
|
IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
|
|
|
|
#endif /* CONFIG_NOT_COHERENT_CACHE */
|
2009-05-27 05:44:50 +02:00
|
|
|
pr_info(" * 0x%08lx..0x%08lx : early ioremap\n",
|
|
|
|
ioremap_bot, IOREMAP_TOP);
|
|
|
|
pr_info(" * 0x%08lx..0x%08lx : vmalloc & ioremap\n",
|
|
|
|
VMALLOC_START, VMALLOC_END);
|
|
|
|
#endif /* CONFIG_PPC32 */
|
2005-10-06 04:23:33 +02:00
|
|
|
}
|
|
|
|
|
2011-06-18 09:36:39 +02:00
|
|
|
void free_initmem(void)
|
|
|
|
{
|
2011-06-18 09:36:40 +02:00
|
|
|
ppc_md.progress = ppc_printk_progress;
|
2013-04-30 00:06:47 +02:00
|
|
|
free_initmem_default(POISON_FREE_INITMEM);
|
2011-06-18 09:36:39 +02:00
|
|
|
}
|
|
|
|
|
powerpc: Force page alignment for initrd reserved memory
When using 64K pages with a separate cpio rootfs, U-Boot will align
the rootfs on a 4K page boundary. When the memory is reserved, and
subsequent early memblock_alloc is called, it will allocate memory
between the 64K page alignment and reserved memory. When the reserved
memory is subsequently freed, it is done so by pages, causing the
early memblock_alloc requests to be re-used, which in my case, caused
the device-tree to be clobbered.
This patch forces the reserved memory for initrd to be kernel page
aligned, and will move the device tree if it overlaps with the range
extension of initrd. This patch will also consolidate the identical
function free_initrd_mem() from mm/init_32.c, init_64.c to mm/mem.c,
and adds the same range extension when freeing initrd. free_initrd_mem()
is also moved to the __init section.
Many thanks to Milton Miller for his input on this patch.
[BenH: Fixed build without CONFIG_BLK_DEV_INITRD]
Signed-off-by: Dave Carroll <dcarroll@astekcorp.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-06-09 08:52:38 +02:00
|
|
|
#ifdef CONFIG_BLK_DEV_INITRD
|
|
|
|
void __init free_initrd_mem(unsigned long start, unsigned long end)
|
|
|
|
{
|
2013-07-04 00:02:51 +02:00
|
|
|
free_reserved_area((void *)start, (void *)end, -1, "initrd");
|
powerpc: Force page alignment for initrd reserved memory
When using 64K pages with a separate cpio rootfs, U-Boot will align
the rootfs on a 4K page boundary. When the memory is reserved, and
subsequent early memblock_alloc is called, it will allocate memory
between the 64K page alignment and reserved memory. When the reserved
memory is subsequently freed, it is done so by pages, causing the
early memblock_alloc requests to be re-used, which in my case, caused
the device-tree to be clobbered.
This patch forces the reserved memory for initrd to be kernel page
aligned, and will move the device tree if it overlaps with the range
extension of initrd. This patch will also consolidate the identical
function free_initrd_mem() from mm/init_32.c, init_64.c to mm/mem.c,
and adds the same range extension when freeing initrd. free_initrd_mem()
is also moved to the __init section.
Many thanks to Milton Miller for his input on this patch.
[BenH: Fixed build without CONFIG_BLK_DEV_INITRD]
Signed-off-by: Dave Carroll <dcarroll@astekcorp.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2011-06-09 08:52:38 +02:00
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
2005-09-26 08:04:21 +02:00
|
|
|
/*
|
|
|
|
* This is called when a page has been modified by the kernel.
|
|
|
|
* It just marks the page as not i-cache clean. We do the i-cache
|
|
|
|
* flush later when the page is given to a user process, if necessary.
|
|
|
|
*/
|
|
|
|
void flush_dcache_page(struct page *page)
|
|
|
|
{
|
|
|
|
if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
|
|
|
|
return;
|
|
|
|
/* avoid an atomic op if possible */
|
|
|
|
if (test_bit(PG_arch_1, &page->flags))
|
|
|
|
clear_bit(PG_arch_1, &page->flags);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(flush_dcache_page);
|
|
|
|
|
|
|
|
void flush_dcache_icache_page(struct page *page)
|
|
|
|
{
|
2009-10-26 20:24:31 +01:00
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
if (PageCompound(page)) {
|
|
|
|
flush_dcache_icache_hugepage(page);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
#endif
|
2015-04-16 02:40:23 +02:00
|
|
|
#if defined(CONFIG_8xx) || defined(CONFIG_PPC64)
|
|
|
|
/* On 8xx there is no need to kmap since highmem is not supported */
|
|
|
|
__flush_dcache_icache(page_address(page));
|
|
|
|
#else
|
|
|
|
if (IS_ENABLED(CONFIG_BOOKE) || sizeof(phys_addr_t) > sizeof(void *)) {
|
2011-11-25 16:14:16 +01:00
|
|
|
void *start = kmap_atomic(page);
|
2009-10-26 20:24:31 +01:00
|
|
|
__flush_dcache_icache(start);
|
2011-11-25 16:14:16 +01:00
|
|
|
kunmap_atomic(start);
|
2015-04-16 02:40:23 +02:00
|
|
|
} else {
|
|
|
|
__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
|
2009-10-26 20:24:31 +01:00
|
|
|
}
|
2005-09-26 08:04:21 +02:00
|
|
|
#endif
|
|
|
|
}
|
2012-08-03 13:56:33 +02:00
|
|
|
EXPORT_SYMBOL(flush_dcache_icache_page);
|
2009-10-26 20:24:31 +01:00
|
|
|
|
2005-09-26 08:04:21 +02:00
|
|
|
void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
|
|
|
|
{
|
|
|
|
clear_page(page);
|
|
|
|
|
|
|
|
/*
|
2011-03-31 03:57:33 +02:00
|
|
|
* We shouldn't have to do this, but some versions of glibc
|
2005-09-26 08:04:21 +02:00
|
|
|
* require it (ld.so assumes zero filled pages are icache clean)
|
|
|
|
* - Anton
|
|
|
|
*/
|
2006-02-06 03:24:53 +01:00
|
|
|
flush_dcache_page(pg);
|
2005-09-26 08:04:21 +02:00
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(clear_user_page);
|
|
|
|
|
|
|
|
void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
|
|
|
|
struct page *pg)
|
|
|
|
{
|
|
|
|
copy_page(vto, vfrom);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We should be able to use the following optimisation, however
|
|
|
|
* there are two problems.
|
|
|
|
* Firstly a bug in some versions of binutils meant PLT sections
|
|
|
|
* were not marked executable.
|
|
|
|
* Secondly the first word in the GOT section is blrl, used
|
|
|
|
* to establish the GOT address. Until recently the GOT was
|
|
|
|
* not marked executable.
|
|
|
|
* - Anton
|
|
|
|
*/
|
|
|
|
#if 0
|
|
|
|
if (!vma->vm_file && ((vma->vm_flags & VM_EXEC) == 0))
|
|
|
|
return;
|
|
|
|
#endif
|
|
|
|
|
2006-02-06 03:24:53 +01:00
|
|
|
flush_dcache_page(pg);
|
2005-09-26 08:04:21 +02:00
|
|
|
}
|
|
|
|
|
|
|
|
void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
|
|
|
|
unsigned long addr, int len)
|
|
|
|
{
|
|
|
|
unsigned long maddr;
|
|
|
|
|
|
|
|
maddr = (unsigned long) kmap(page) + (addr & ~PAGE_MASK);
|
|
|
|
flush_icache_range(maddr, maddr + len);
|
|
|
|
kunmap(page);
|
|
|
|
}
|
|
|
|
EXPORT_SYMBOL(flush_icache_user_range);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This is called at the end of handling a user page fault, when the
|
|
|
|
* fault has been handled by updating a PTE in the linux page tables.
|
|
|
|
* We use it to preload an HPTE into the hash table corresponding to
|
|
|
|
* the updated linux PTE.
|
|
|
|
*
|
2005-11-23 22:37:39 +01:00
|
|
|
* This must always be called with the pte lock held.
|
2005-09-26 08:04:21 +02:00
|
|
|
*/
|
|
|
|
void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
|
MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself
On VIVT ARM, when we have multiple shared mappings of the same file
in the same MM, we need to ensure that we have coherency across all
copies. We do this via make_coherent() by making the pages
uncacheable.
This used to work fine, until we allowed highmem with highpte - we
now have a page table which is mapped as required, and is not available
for modification via update_mmu_cache().
Ralf Beache suggested getting rid of the PTE value passed to
update_mmu_cache():
On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables
to construct a pointer to the pte again. Passing a pte_t * is much
more elegant. Maybe we might even replace the pte argument with the
pte_t?
Ben Herrenschmidt would also like the pte pointer for PowerPC:
Passing the ptep in there is exactly what I want. I want that
-instead- of the PTE value, because I have issue on some ppc cases,
for I$/D$ coherency, where set_pte_at() may decide to mask out the
_PAGE_EXEC.
So, pass in the mapped page table pointer into update_mmu_cache(), and
remove the PTE value, updating all implementations and call sites to
suit.
Includes a fix from Stephen Rothwell:
sparc: fix fallout from update_mmu_cache API change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-12-18 17:40:18 +01:00
|
|
|
pte_t *ptep)
|
2005-09-26 08:04:21 +02:00
|
|
|
{
|
2005-11-07 01:06:55 +01:00
|
|
|
#ifdef CONFIG_PPC_STD_MMU
|
2013-06-20 11:00:22 +02:00
|
|
|
/*
|
|
|
|
* We don't need to worry about _PAGE_PRESENT here because we are
|
|
|
|
* called with either mm->page_table_lock held or ptl lock held
|
|
|
|
*/
|
2016-02-26 01:26:26 +01:00
|
|
|
unsigned long access, trap;
|
|
|
|
|
2016-04-29 15:26:22 +02:00
|
|
|
if (radix_enabled())
|
|
|
|
return;
|
2005-09-26 08:04:21 +02:00
|
|
|
|
|
|
|
/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
|
MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself
On VIVT ARM, when we have multiple shared mappings of the same file
in the same MM, we need to ensure that we have coherency across all
copies. We do this via make_coherent() by making the pages
uncacheable.
This used to work fine, until we allowed highmem with highpte - we
now have a page table which is mapped as required, and is not available
for modification via update_mmu_cache().
Ralf Beache suggested getting rid of the PTE value passed to
update_mmu_cache():
On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables
to construct a pointer to the pte again. Passing a pte_t * is much
more elegant. Maybe we might even replace the pte argument with the
pte_t?
Ben Herrenschmidt would also like the pte pointer for PowerPC:
Passing the ptep in there is exactly what I want. I want that
-instead- of the PTE value, because I have issue on some ppc cases,
for I$/D$ coherency, where set_pte_at() may decide to mask out the
_PAGE_EXEC.
So, pass in the mapped page table pointer into update_mmu_cache(), and
remove the PTE value, updating all implementations and call sites to
suit.
Includes a fix from Stephen Rothwell:
sparc: fix fallout from update_mmu_cache API change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-12-18 17:40:18 +01:00
|
|
|
if (!pte_young(*ptep) || address >= TASK_SIZE)
|
2005-09-26 08:04:21 +02:00
|
|
|
return;
|
|
|
|
|
2005-11-07 01:06:55 +01:00
|
|
|
/* We try to figure out if we are coming from an instruction
|
|
|
|
* access fault and pass that down to __hash_page so we avoid
|
|
|
|
* double-faulting on execution of fresh text. We have to test
|
|
|
|
* for regs NULL since init will get here first thing at boot
|
|
|
|
*
|
|
|
|
* We also avoid filling the hash if not coming from a fault
|
|
|
|
*/
|
2016-02-26 01:26:26 +01:00
|
|
|
|
|
|
|
trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
|
|
|
|
switch (trap) {
|
|
|
|
case 0x300:
|
|
|
|
access = 0UL;
|
|
|
|
break;
|
|
|
|
case 0x400:
|
|
|
|
access = _PAGE_EXEC;
|
|
|
|
break;
|
|
|
|
default:
|
2005-11-07 01:06:55 +01:00
|
|
|
return;
|
2016-02-26 01:26:26 +01:00
|
|
|
}
|
|
|
|
|
2005-11-07 01:06:55 +01:00
|
|
|
hash_preload(vma->vm_mm, address, access, trap);
|
|
|
|
#endif /* CONFIG_PPC_STD_MMU */
|
2011-06-28 11:54:48 +02:00
|
|
|
#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
|
|
|
|
&& defined(CONFIG_HUGETLB_PAGE)
|
|
|
|
if (is_vm_hugetlb_page(vma))
|
2011-11-28 15:43:33 +01:00
|
|
|
book3e_hugetlb_preload(vma, address, *ptep);
|
2011-06-28 11:54:48 +02:00
|
|
|
#endif
|
2005-09-26 08:04:21 +02:00
|
|
|
}
|
2011-11-02 15:56:12 +01:00
|
|
|
|
|
|
|
/*
|
|
|
|
* System memory should not be in /proc/iomem but various tools expect it
|
|
|
|
* (eg kdump).
|
|
|
|
*/
|
2013-09-15 11:39:36 +02:00
|
|
|
static int __init add_system_ram_resources(void)
|
2011-11-02 15:56:12 +01:00
|
|
|
{
|
|
|
|
struct memblock_region *reg;
|
|
|
|
|
|
|
|
for_each_memblock(memory, reg) {
|
|
|
|
struct resource *res;
|
|
|
|
unsigned long base = reg->base;
|
|
|
|
unsigned long size = reg->size;
|
|
|
|
|
|
|
|
res = kzalloc(sizeof(struct resource), GFP_KERNEL);
|
|
|
|
WARN_ON(!res);
|
|
|
|
|
|
|
|
if (res) {
|
|
|
|
res->name = "System RAM";
|
|
|
|
res->start = base;
|
|
|
|
res->end = base + size - 1;
|
2016-01-26 21:57:22 +01:00
|
|
|
res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
|
2011-11-02 15:56:12 +01:00
|
|
|
WARN_ON(request_resource(&iomem_resource, res) < 0);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
subsys_initcall(add_system_ram_resources);
|
2011-08-30 11:19:17 +02:00
|
|
|
|
|
|
|
#ifdef CONFIG_STRICT_DEVMEM
|
|
|
|
/*
|
|
|
|
* devmem_is_allowed(): check to see if /dev/mem access to a certain address
|
|
|
|
* is valid. The argument is a physical page number.
|
|
|
|
*
|
|
|
|
* Access has to be given to non-kernel-ram areas as well, these contain the
|
|
|
|
* PCI mmio resources as well as potential bios/acpi data regions.
|
|
|
|
*/
|
|
|
|
int devmem_is_allowed(unsigned long pfn)
|
|
|
|
{
|
2016-01-21 17:15:31 +01:00
|
|
|
if (page_is_rtas_user_buf(pfn))
|
|
|
|
return 1;
|
2015-04-17 23:17:14 +02:00
|
|
|
if (iomem_is_exclusive(PFN_PHYS(pfn)))
|
2011-08-30 11:19:17 +02:00
|
|
|
return 0;
|
|
|
|
if (!page_is_ram(pfn))
|
|
|
|
return 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_STRICT_DEVMEM */
|