linux/arch/um/kernel/mem.c

303 lines
6.8 KiB
C
Raw Normal View History

/*
* Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
* Licensed under the GPL
*/
#include <linux/stddef.h>
#include <linux/module.h>
#include <linux/bootmem.h>
#include <linux/highmem.h>
#include <linux/mm.h>
#include <linux/swap.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 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/fixmap.h>
#include <asm/page.h>
#include <as-layout.h>
#include <init.h>
#include <kern.h>
#include <kern_util.h>
#include <mem_user.h>
#include <os.h>
/* allocated in paging_init, zeroed in mem_init, and unchanged thereafter */
unsigned long *empty_zero_page = NULL;
EXPORT_SYMBOL(empty_zero_page);
/* allocated in paging_init and unchanged thereafter */
static unsigned long *empty_bad_page = NULL;
/*
* Initialized during boot, and readonly for initializing page tables
* afterwards
*/
pgd_t swapper_pg_dir[PTRS_PER_PGD];
/* Initialized at boot time, and readonly after that */
unsigned long long highmem;
int kmalloc_ok = 0;
/* Used during early boot */
static unsigned long brk_end;
#ifdef CONFIG_HIGHMEM
static void setup_highmem(unsigned long highmem_start,
unsigned long highmem_len)
{
unsigned long highmem_pfn;
int i;
highmem_pfn = __pa(highmem_start) >> PAGE_SHIFT;
for (i = 0; i < highmem_len >> PAGE_SHIFT; i++)
free_highmem_page(&mem_map[highmem_pfn + i]);
}
#endif
void __init mem_init(void)
{
/* clear the zero-page */
memset(empty_zero_page, 0, PAGE_SIZE);
/* Map in the area just after the brk now that kmalloc is about
* to be turned on.
*/
brk_end = (unsigned long) UML_ROUND_UP(sbrk(0));
map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0);
free_bootmem(__pa(brk_end), uml_reserved - brk_end);
uml_reserved = brk_end;
/* this will put all low memory onto the freelists */
mm: concentrate modification of totalram_pages into the mm core Concentrate code to modify totalram_pages into the mm core, so the arch memory initialized code doesn't need to take care of it. With these changes applied, only following functions from mm core modify global variable totalram_pages: free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(), adjust_managed_page_count(). With this patch applied, it will be much more easier for us to keep totalram_pages and zone->managed_pages in consistence. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: David Howells <dhowells@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:24 +08:00
free_all_bootmem();
max_low_pfn = totalram_pages;
#ifdef CONFIG_HIGHMEM
setup_highmem(end_iomem, highmem);
#endif
max_pfn = totalram_pages;
mem_init_print_info(NULL);
kmalloc_ok = 1;
}
/*
* Create a page table and place a pointer to it in a middle page
* directory entry.
*/
static void __init one_page_table_init(pmd_t *pmd)
{
if (pmd_none(*pmd)) {
pte_t *pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
set_pmd(pmd, __pmd(_KERNPG_TABLE +
(unsigned long) __pa(pte)));
if (pte != pte_offset_kernel(pmd, 0))
BUG();
}
}
static void __init one_md_table_init(pud_t *pud)
{
#ifdef CONFIG_3_LEVEL_PGTABLES
pmd_t *pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
set_pud(pud, __pud(_KERNPG_TABLE + (unsigned long) __pa(pmd_table)));
if (pmd_table != pmd_offset(pud, 0))
BUG();
#endif
}
static void __init fixrange_init(unsigned long start, unsigned long end,
pgd_t *pgd_base)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
int i, j;
unsigned long vaddr;
vaddr = start;
i = pgd_index(vaddr);
j = pmd_index(vaddr);
pgd = pgd_base + i;
for ( ; (i < PTRS_PER_PGD) && (vaddr < end); pgd++, i++) {
pud = pud_offset(pgd, vaddr);
if (pud_none(*pud))
one_md_table_init(pud);
pmd = pmd_offset(pud, vaddr);
for (; (j < PTRS_PER_PMD) && (vaddr < end); pmd++, j++) {
one_page_table_init(pmd);
vaddr += PMD_SIZE;
}
j = 0;
}
}
#ifdef CONFIG_HIGHMEM
pte_t *kmap_pte;
pgprot_t kmap_prot;
#define kmap_get_fixmap_pte(vaddr) \
pte_offset_kernel(pmd_offset(pud_offset(pgd_offset_k(vaddr), (vaddr)),\
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
(vaddr)), (vaddr))
static void __init kmap_init(void)
{
unsigned long kmap_vstart;
/* cache the first kmap pte */
kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
kmap_pte = kmap_get_fixmap_pte(kmap_vstart);
kmap_prot = PAGE_KERNEL;
}
static void __init init_highmem(void)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long vaddr;
/*
* Permanent kmaps:
*/
vaddr = PKMAP_BASE;
fixrange_init(vaddr, vaddr + PAGE_SIZE*LAST_PKMAP, swapper_pg_dir);
pgd = swapper_pg_dir + pgd_index(vaddr);
pud = pud_offset(pgd, vaddr);
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pkmap_page_table = pte;
kmap_init();
}
#endif /* CONFIG_HIGHMEM */
static void __init fixaddr_user_init( void)
{
#ifdef CONFIG_ARCH_REUSE_HOST_VSYSCALL_AREA
long size = FIXADDR_USER_END - FIXADDR_USER_START;
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
phys_t p;
unsigned long v, vaddr = FIXADDR_USER_START;
if (!size)
return;
fixrange_init( FIXADDR_USER_START, FIXADDR_USER_END, swapper_pg_dir);
v = (unsigned long) alloc_bootmem_low_pages(size);
memcpy((void *) v , (void *) FIXADDR_USER_START, size);
p = __pa(v);
for ( ; size > 0; size -= PAGE_SIZE, vaddr += PAGE_SIZE,
p += PAGE_SIZE) {
pgd = swapper_pg_dir + pgd_index(vaddr);
pud = pud_offset(pgd, vaddr);
pmd = pmd_offset(pud, vaddr);
pte = pte_offset_kernel(pmd, vaddr);
pte_set_val(*pte, p, PAGE_READONLY);
}
#endif
}
void __init paging_init(void)
{
unsigned long zones_size[MAX_NR_ZONES], vaddr;
int i;
empty_zero_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
empty_bad_page = (unsigned long *) alloc_bootmem_low_pages(PAGE_SIZE);
for (i = 0; i < ARRAY_SIZE(zones_size); i++)
zones_size[i] = 0;
zones_size[ZONE_NORMAL] = (end_iomem >> PAGE_SHIFT) -
(uml_physmem >> PAGE_SHIFT);
#ifdef CONFIG_HIGHMEM
zones_size[ZONE_HIGHMEM] = highmem >> PAGE_SHIFT;
#endif
free_area_init(zones_size);
/*
* Fixed mappings, only the page table structure has to be
* created - mappings will be set by set_fixmap():
*/
vaddr = __fix_to_virt(__end_of_fixed_addresses - 1) & PMD_MASK;
fixrange_init(vaddr, FIXADDR_TOP, swapper_pg_dir);
fixaddr_user_init();
#ifdef CONFIG_HIGHMEM
init_highmem();
#endif
}
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
/*
* This can't do anything because nothing in the kernel image can be freed
* since it's not in kernel physical memory.
*/
void free_initmem(void)
{
}
#ifdef CONFIG_BLK_DEV_INITRD
void free_initrd_mem(unsigned long start, unsigned long end)
{
mm: enhance free_reserved_area() to support poisoning memory with zero Address more review comments from last round of code review. 1) Enhance free_reserved_area() to support poisoning freed memory with pattern '0'. This could be used to get rid of poison_init_mem() on ARM64. 2) A previous patch has disabled memory poison for initmem on s390 by mistake, so restore to the original behavior. 3) Remove redundant PAGE_ALIGN() when calling free_reserved_area(). Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:02:51 +08:00
free_reserved_area((void *)start, (void *)end, -1, "initrd");
}
#endif
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
/* Allocate and free page tables. */
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd = (pgd_t *)__get_free_page(GFP_KERNEL);
if (pgd) {
memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
memcpy(pgd + USER_PTRS_PER_PGD,
swapper_pg_dir + USER_PTRS_PER_PGD,
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
}
return pgd;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
free_page((unsigned long) pgd);
}
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
pte_t *pte;
pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
return pte;
}
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *pte;
pte = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
if (pte)
pgtable_page_ctor(pte);
return pte;
}
uml: header untangling Untangle UML headers somewhat and add some includes where they were needed explicitly, but gotten accidentally via some other header. arch/um/include/um_uaccess.h loses asm/fixmap.h because it uses no fixmap stuff and gains elf.h, because it needs FIXADDR_USER_*, and archsetjmp.h, because it needs jmp_buf. pmd_alloc_one is uninlined because it needs mm_struct, and that's inconvenient to provide in asm-um/pgtable-3level.h. elf_core_copy_fpregs is also uninlined from elf-i386.h and elf-x86_64.h, which duplicated the code anyway, to arch/um/kernel/process.c, so that the reference to current_thread doesn't pull sched.h or anything related into asm/elf.h. arch/um/sys-i386/ldt.c, arch/um/kernel/tlb.c and arch/um/kernel/skas/uaccess.c got sched.h because they dereference task_structs. Its includes of linux and asm headers got turned from "" to <>. arch/um/sys-i386/bug.c gets asm/errno.h because it needs errno constants. asm/elf-i386 gets asm/user.h because it needs user_regs_struct. asm/fixmap.h gets page.h because it needs PAGE_SIZE and PAGE_MASK and system.h for BUG_ON. asm/pgtable doesn't need sched.h. asm/processor-generic.h defined mm_segment_t, but didn't use it. So, that definition is moved to uaccess.h, which defines a bunch of mm_segment_t-related stuff. thread_info.h uses mm_segment_t, and includes uaccess.h, which causes a recursion. So, the definition is placed above the include of thread_info. in uaccess.h. thread_info.h also gets page.h because it needs PAGE_SIZE. ObCheckpatchViolationJustification - I'm not adding a typedef; I'm moving mm_segment_t from one place to another. Signed-off-by: Jeff Dike <jdike@linux.intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-05 14:30:53 +08:00
#ifdef CONFIG_3_LEVEL_PGTABLES
pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
{
pmd_t *pmd = (pmd_t *) __get_free_page(GFP_KERNEL);
if (pmd)
memset(pmd, 0, PAGE_SIZE);
return pmd;
}
#endif
void *uml_kmalloc(int size, int flags)
{
return kmalloc(size, flags);
}