![Tejun Heo](/assets/img/avatar_default.png)
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>
338 lines
8.4 KiB
C
338 lines
8.4 KiB
C
/*
|
|
* Copyright IBM Corp. 2007,2009
|
|
* Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/errno.h>
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/smp.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/pagemap.h>
|
|
#include <linux/spinlock.h>
|
|
#include <linux/module.h>
|
|
#include <linux/quicklist.h>
|
|
|
|
#include <asm/system.h>
|
|
#include <asm/pgtable.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/mmu_context.h>
|
|
|
|
#ifndef CONFIG_64BIT
|
|
#define ALLOC_ORDER 1
|
|
#define TABLES_PER_PAGE 4
|
|
#define FRAG_MASK 15UL
|
|
#define SECOND_HALVES 10UL
|
|
|
|
void clear_table_pgstes(unsigned long *table)
|
|
{
|
|
clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
|
|
memset(table + 256, 0, PAGE_SIZE/4);
|
|
clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
|
|
memset(table + 768, 0, PAGE_SIZE/4);
|
|
}
|
|
|
|
#else
|
|
#define ALLOC_ORDER 2
|
|
#define TABLES_PER_PAGE 2
|
|
#define FRAG_MASK 3UL
|
|
#define SECOND_HALVES 2UL
|
|
|
|
void clear_table_pgstes(unsigned long *table)
|
|
{
|
|
clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
|
|
memset(table + 256, 0, PAGE_SIZE/2);
|
|
}
|
|
|
|
#endif
|
|
|
|
unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE;
|
|
EXPORT_SYMBOL(VMALLOC_START);
|
|
|
|
static int __init parse_vmalloc(char *arg)
|
|
{
|
|
if (!arg)
|
|
return -EINVAL;
|
|
VMALLOC_START = (VMALLOC_END - memparse(arg, &arg)) & PAGE_MASK;
|
|
return 0;
|
|
}
|
|
early_param("vmalloc", parse_vmalloc);
|
|
|
|
unsigned long *crst_table_alloc(struct mm_struct *mm, int noexec)
|
|
{
|
|
struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
|
|
|
|
if (!page)
|
|
return NULL;
|
|
page->index = 0;
|
|
if (noexec) {
|
|
struct page *shadow = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
|
|
if (!shadow) {
|
|
__free_pages(page, ALLOC_ORDER);
|
|
return NULL;
|
|
}
|
|
page->index = page_to_phys(shadow);
|
|
}
|
|
spin_lock(&mm->context.list_lock);
|
|
list_add(&page->lru, &mm->context.crst_list);
|
|
spin_unlock(&mm->context.list_lock);
|
|
return (unsigned long *) page_to_phys(page);
|
|
}
|
|
|
|
void crst_table_free(struct mm_struct *mm, unsigned long *table)
|
|
{
|
|
unsigned long *shadow = get_shadow_table(table);
|
|
struct page *page = virt_to_page(table);
|
|
|
|
spin_lock(&mm->context.list_lock);
|
|
list_del(&page->lru);
|
|
spin_unlock(&mm->context.list_lock);
|
|
if (shadow)
|
|
free_pages((unsigned long) shadow, ALLOC_ORDER);
|
|
free_pages((unsigned long) table, ALLOC_ORDER);
|
|
}
|
|
|
|
#ifdef CONFIG_64BIT
|
|
int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
|
|
{
|
|
unsigned long *table, *pgd;
|
|
unsigned long entry;
|
|
|
|
BUG_ON(limit > (1UL << 53));
|
|
repeat:
|
|
table = crst_table_alloc(mm, mm->context.noexec);
|
|
if (!table)
|
|
return -ENOMEM;
|
|
spin_lock(&mm->page_table_lock);
|
|
if (mm->context.asce_limit < limit) {
|
|
pgd = (unsigned long *) mm->pgd;
|
|
if (mm->context.asce_limit <= (1UL << 31)) {
|
|
entry = _REGION3_ENTRY_EMPTY;
|
|
mm->context.asce_limit = 1UL << 42;
|
|
mm->context.asce_bits = _ASCE_TABLE_LENGTH |
|
|
_ASCE_USER_BITS |
|
|
_ASCE_TYPE_REGION3;
|
|
} else {
|
|
entry = _REGION2_ENTRY_EMPTY;
|
|
mm->context.asce_limit = 1UL << 53;
|
|
mm->context.asce_bits = _ASCE_TABLE_LENGTH |
|
|
_ASCE_USER_BITS |
|
|
_ASCE_TYPE_REGION2;
|
|
}
|
|
crst_table_init(table, entry);
|
|
pgd_populate(mm, (pgd_t *) table, (pud_t *) pgd);
|
|
mm->pgd = (pgd_t *) table;
|
|
mm->task_size = mm->context.asce_limit;
|
|
table = NULL;
|
|
}
|
|
spin_unlock(&mm->page_table_lock);
|
|
if (table)
|
|
crst_table_free(mm, table);
|
|
if (mm->context.asce_limit < limit)
|
|
goto repeat;
|
|
update_mm(mm, current);
|
|
return 0;
|
|
}
|
|
|
|
void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
|
|
{
|
|
pgd_t *pgd;
|
|
|
|
if (mm->context.asce_limit <= limit)
|
|
return;
|
|
__tlb_flush_mm(mm);
|
|
while (mm->context.asce_limit > limit) {
|
|
pgd = mm->pgd;
|
|
switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
|
|
case _REGION_ENTRY_TYPE_R2:
|
|
mm->context.asce_limit = 1UL << 42;
|
|
mm->context.asce_bits = _ASCE_TABLE_LENGTH |
|
|
_ASCE_USER_BITS |
|
|
_ASCE_TYPE_REGION3;
|
|
break;
|
|
case _REGION_ENTRY_TYPE_R3:
|
|
mm->context.asce_limit = 1UL << 31;
|
|
mm->context.asce_bits = _ASCE_TABLE_LENGTH |
|
|
_ASCE_USER_BITS |
|
|
_ASCE_TYPE_SEGMENT;
|
|
break;
|
|
default:
|
|
BUG();
|
|
}
|
|
mm->pgd = (pgd_t *) (pgd_val(*pgd) & _REGION_ENTRY_ORIGIN);
|
|
mm->task_size = mm->context.asce_limit;
|
|
crst_table_free(mm, (unsigned long *) pgd);
|
|
}
|
|
update_mm(mm, current);
|
|
}
|
|
#endif
|
|
|
|
/*
|
|
* page table entry allocation/free routines.
|
|
*/
|
|
unsigned long *page_table_alloc(struct mm_struct *mm)
|
|
{
|
|
struct page *page;
|
|
unsigned long *table;
|
|
unsigned long bits;
|
|
|
|
bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
|
|
spin_lock(&mm->context.list_lock);
|
|
page = NULL;
|
|
if (!list_empty(&mm->context.pgtable_list)) {
|
|
page = list_first_entry(&mm->context.pgtable_list,
|
|
struct page, lru);
|
|
if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
|
|
page = NULL;
|
|
}
|
|
if (!page) {
|
|
spin_unlock(&mm->context.list_lock);
|
|
page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
|
|
if (!page)
|
|
return NULL;
|
|
pgtable_page_ctor(page);
|
|
page->flags &= ~FRAG_MASK;
|
|
table = (unsigned long *) page_to_phys(page);
|
|
if (mm->context.has_pgste)
|
|
clear_table_pgstes(table);
|
|
else
|
|
clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
|
|
spin_lock(&mm->context.list_lock);
|
|
list_add(&page->lru, &mm->context.pgtable_list);
|
|
}
|
|
table = (unsigned long *) page_to_phys(page);
|
|
while (page->flags & bits) {
|
|
table += 256;
|
|
bits <<= 1;
|
|
}
|
|
page->flags |= bits;
|
|
if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
|
|
list_move_tail(&page->lru, &mm->context.pgtable_list);
|
|
spin_unlock(&mm->context.list_lock);
|
|
return table;
|
|
}
|
|
|
|
void page_table_free(struct mm_struct *mm, unsigned long *table)
|
|
{
|
|
struct page *page;
|
|
unsigned long bits;
|
|
|
|
bits = (mm->context.noexec || mm->context.has_pgste) ? 3UL : 1UL;
|
|
bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
|
|
page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
|
|
spin_lock(&mm->context.list_lock);
|
|
page->flags ^= bits;
|
|
if (page->flags & FRAG_MASK) {
|
|
/* Page now has some free pgtable fragments. */
|
|
list_move(&page->lru, &mm->context.pgtable_list);
|
|
page = NULL;
|
|
} else
|
|
/* All fragments of the 4K page have been freed. */
|
|
list_del(&page->lru);
|
|
spin_unlock(&mm->context.list_lock);
|
|
if (page) {
|
|
pgtable_page_dtor(page);
|
|
__free_page(page);
|
|
}
|
|
}
|
|
|
|
void disable_noexec(struct mm_struct *mm, struct task_struct *tsk)
|
|
{
|
|
struct page *page;
|
|
|
|
spin_lock(&mm->context.list_lock);
|
|
/* Free shadow region and segment tables. */
|
|
list_for_each_entry(page, &mm->context.crst_list, lru)
|
|
if (page->index) {
|
|
free_pages((unsigned long) page->index, ALLOC_ORDER);
|
|
page->index = 0;
|
|
}
|
|
/* "Free" second halves of page tables. */
|
|
list_for_each_entry(page, &mm->context.pgtable_list, lru)
|
|
page->flags &= ~SECOND_HALVES;
|
|
spin_unlock(&mm->context.list_lock);
|
|
mm->context.noexec = 0;
|
|
update_mm(mm, tsk);
|
|
}
|
|
|
|
/*
|
|
* switch on pgstes for its userspace process (for kvm)
|
|
*/
|
|
int s390_enable_sie(void)
|
|
{
|
|
struct task_struct *tsk = current;
|
|
struct mm_struct *mm, *old_mm;
|
|
|
|
/* Do we have switched amode? If no, we cannot do sie */
|
|
if (user_mode == HOME_SPACE_MODE)
|
|
return -EINVAL;
|
|
|
|
/* Do we have pgstes? if yes, we are done */
|
|
if (tsk->mm->context.has_pgste)
|
|
return 0;
|
|
|
|
/* lets check if we are allowed to replace the mm */
|
|
task_lock(tsk);
|
|
if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
|
|
#ifdef CONFIG_AIO
|
|
!hlist_empty(&tsk->mm->ioctx_list) ||
|
|
#endif
|
|
tsk->mm != tsk->active_mm) {
|
|
task_unlock(tsk);
|
|
return -EINVAL;
|
|
}
|
|
task_unlock(tsk);
|
|
|
|
/* we copy the mm and let dup_mm create the page tables with_pgstes */
|
|
tsk->mm->context.alloc_pgste = 1;
|
|
mm = dup_mm(tsk);
|
|
tsk->mm->context.alloc_pgste = 0;
|
|
if (!mm)
|
|
return -ENOMEM;
|
|
|
|
/* Now lets check again if something happened */
|
|
task_lock(tsk);
|
|
if (!tsk->mm || atomic_read(&tsk->mm->mm_users) > 1 ||
|
|
#ifdef CONFIG_AIO
|
|
!hlist_empty(&tsk->mm->ioctx_list) ||
|
|
#endif
|
|
tsk->mm != tsk->active_mm) {
|
|
mmput(mm);
|
|
task_unlock(tsk);
|
|
return -EINVAL;
|
|
}
|
|
|
|
/* ok, we are alone. No ptrace, no threads, etc. */
|
|
old_mm = tsk->mm;
|
|
tsk->mm = tsk->active_mm = mm;
|
|
preempt_disable();
|
|
update_mm(mm, tsk);
|
|
cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
|
|
preempt_enable();
|
|
task_unlock(tsk);
|
|
mmput(old_mm);
|
|
return 0;
|
|
}
|
|
EXPORT_SYMBOL_GPL(s390_enable_sie);
|
|
|
|
#if defined(CONFIG_DEBUG_PAGEALLOC) && defined(CONFIG_HIBERNATION)
|
|
bool kernel_page_present(struct page *page)
|
|
{
|
|
unsigned long addr;
|
|
int cc;
|
|
|
|
addr = page_to_phys(page);
|
|
asm volatile(
|
|
" lra %1,0(%1)\n"
|
|
" ipm %0\n"
|
|
" srl %0,28"
|
|
: "=d" (cc), "+a" (addr) : : "cc");
|
|
return cc == 0;
|
|
}
|
|
#endif /* CONFIG_HIBERNATION && CONFIG_DEBUG_PAGEALLOC */
|