2008-02-08 20:19:31 +08:00
|
|
|
/* MN10300 Page table management
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Matsushita Electric Industrial Co., Ltd.
|
|
|
|
* Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
|
|
|
|
* Modified by David Howells (dhowells@redhat.com)
|
|
|
|
*
|
|
|
|
* This program is free software; you can redistribute it and/or
|
|
|
|
* modify it under the terms of the GNU General Public Licence
|
|
|
|
* as published by the Free Software Foundation; either version
|
|
|
|
* 2 of the Licence, or (at your option) any later version.
|
|
|
|
*/
|
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/errno.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/gfp.h>
|
2008-02-08 20:19:31 +08:00
|
|
|
#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/quicklist.h>
|
|
|
|
|
|
|
|
#include <asm/pgtable.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
|
|
#include <asm/tlb.h>
|
|
|
|
#include <asm/tlbflush.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Associate a large virtual page frame with a given physical page frame
|
|
|
|
* and protection flags for that frame. pfn is for the base of the page,
|
|
|
|
* vaddr is what the page gets mapped to - both must be properly aligned.
|
|
|
|
* The pmd must already be instantiated. Assumes PAE mode.
|
|
|
|
*/
|
|
|
|
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
|
|
|
|
{
|
|
|
|
pgd_t *pgd;
|
|
|
|
pud_t *pud;
|
|
|
|
pmd_t *pmd;
|
|
|
|
|
|
|
|
if (vaddr & (PMD_SIZE-1)) { /* vaddr is misaligned */
|
|
|
|
printk(KERN_ERR "set_pmd_pfn: vaddr misaligned\n");
|
|
|
|
return; /* BUG(); */
|
|
|
|
}
|
|
|
|
if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */
|
|
|
|
printk(KERN_ERR "set_pmd_pfn: pfn misaligned\n");
|
|
|
|
return; /* BUG(); */
|
|
|
|
}
|
|
|
|
pgd = swapper_pg_dir + pgd_index(vaddr);
|
|
|
|
if (pgd_none(*pgd)) {
|
|
|
|
printk(KERN_ERR "set_pmd_pfn: pgd_none\n");
|
|
|
|
return; /* BUG(); */
|
|
|
|
}
|
|
|
|
pud = pud_offset(pgd, vaddr);
|
|
|
|
pmd = pmd_offset(pud, vaddr);
|
|
|
|
set_pmd(pmd, pfn_pmd(pfn, flags));
|
|
|
|
/*
|
|
|
|
* It's enough to flush this one mapping.
|
|
|
|
* (PGE mappings get flushed as well)
|
|
|
|
*/
|
2010-10-28 00:28:49 +08:00
|
|
|
local_flush_tlb_one(vaddr);
|
2008-02-08 20:19:31 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
|
|
|
|
{
|
|
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
|
|
|
|
if (pte)
|
|
|
|
clear_page(pte);
|
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
|
|
{
|
|
|
|
struct page *pte;
|
|
|
|
|
|
|
|
#ifdef CONFIG_HIGHPTE
|
|
|
|
pte = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
|
|
|
|
#else
|
|
|
|
pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
|
|
|
|
#endif
|
|
|
|
if (pte)
|
|
|
|
clear_highpage(pte);
|
|
|
|
return pte;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* List of all pgd's needed for non-PAE so it can invalidate entries
|
|
|
|
* in both cached and uncached pgd's; not needed for PAE since the
|
|
|
|
* kernel pmd is shared. If PAE were not to share the pmd a similar
|
|
|
|
* tactic would be needed. This is essentially codepath-based locking
|
|
|
|
* against pageattr.c; it is the unique case in which a valid change
|
|
|
|
* of kernel pagetables can't be lazily synchronized by vmalloc faults.
|
|
|
|
* vmalloc faults work because attached pagetables are never freed.
|
|
|
|
* If the locking proves to be non-performant, a ticketing scheme with
|
|
|
|
* checks at dup_mmap(), exec(), and other mmlist addition points
|
|
|
|
* could be used. The locking scheme was chosen on the basis of
|
|
|
|
* manfred's recommendations and having no core impact whatsoever.
|
|
|
|
* -- wli
|
|
|
|
*/
|
|
|
|
DEFINE_SPINLOCK(pgd_lock);
|
|
|
|
struct page *pgd_list;
|
|
|
|
|
|
|
|
static inline void pgd_list_add(pgd_t *pgd)
|
|
|
|
{
|
|
|
|
struct page *page = virt_to_page(pgd);
|
|
|
|
page->index = (unsigned long) pgd_list;
|
|
|
|
if (pgd_list)
|
|
|
|
set_page_private(pgd_list, (unsigned long) &page->index);
|
|
|
|
pgd_list = page;
|
|
|
|
set_page_private(page, (unsigned long) &pgd_list);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void pgd_list_del(pgd_t *pgd)
|
|
|
|
{
|
|
|
|
struct page *next, **pprev, *page = virt_to_page(pgd);
|
|
|
|
next = (struct page *) page->index;
|
|
|
|
pprev = (struct page **) page_private(page);
|
|
|
|
*pprev = next;
|
|
|
|
if (next)
|
|
|
|
set_page_private(next, (unsigned long) pprev);
|
|
|
|
}
|
|
|
|
|
|
|
|
void pgd_ctor(void *pgd)
|
|
|
|
{
|
|
|
|
unsigned long flags;
|
|
|
|
|
|
|
|
if (PTRS_PER_PMD == 1)
|
|
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
|
|
|
|
|
|
memcpy((pgd_t *)pgd + USER_PTRS_PER_PGD,
|
|
|
|
swapper_pg_dir + USER_PTRS_PER_PGD,
|
|
|
|
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
|
|
|
|
|
|
|
|
if (PTRS_PER_PMD > 1)
|
|
|
|
return;
|
|
|
|
|
|
|
|
pgd_list_add(pgd);
|
|
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
|
|
memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
|
|
|
|
}
|
|
|
|
|
|
|
|
/* never called when PTRS_PER_PMD > 1 */
|
|
|
|
void pgd_dtor(void *pgd)
|
|
|
|
{
|
|
|
|
unsigned long flags; /* can be called from interrupt context */
|
|
|
|
|
|
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
|
|
pgd_list_del(pgd);
|
|
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
|
|
{
|
|
|
|
return quicklist_alloc(0, GFP_KERNEL, pgd_ctor);
|
|
|
|
}
|
|
|
|
|
|
|
|
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
|
|
{
|
|
|
|
quicklist_free(0, pgd_dtor, pgd);
|
|
|
|
}
|
|
|
|
|
|
|
|
void __init pgtable_cache_init(void)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
void check_pgt_cache(void)
|
|
|
|
{
|
|
|
|
quicklist_trim(0, pgd_dtor, 25, 16);
|
|
|
|
}
|