linux/arch/x86/mm/pgtable.c
Tejun Heo 5a0e3ad6af 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>
2010-03-30 22:02:32 +09:00

375 lines
8.5 KiB
C

#include <linux/mm.h>
#include <linux/gfp.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/tlb.h>
#include <asm/fixmap.h>
#define PGALLOC_GFP GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO
#ifdef CONFIG_HIGHPTE
#define PGALLOC_USER_GFP __GFP_HIGHMEM
#else
#define PGALLOC_USER_GFP 0
#endif
gfp_t __userpte_alloc_gfp = PGALLOC_GFP | PGALLOC_USER_GFP;
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
{
return (pte_t *)__get_free_page(PGALLOC_GFP);
}
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
{
struct page *pte;
pte = alloc_pages(__userpte_alloc_gfp, 0);
if (pte)
pgtable_page_ctor(pte);
return pte;
}
static int __init setup_userpte(char *arg)
{
if (!arg)
return -EINVAL;
/*
* "userpte=nohigh" disables allocation of user pagetables in
* high memory.
*/
if (strcmp(arg, "nohigh") == 0)
__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
else
return -EINVAL;
return 0;
}
early_param("userpte", setup_userpte);
void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
{
pgtable_page_dtor(pte);
paravirt_release_pte(page_to_pfn(pte));
tlb_remove_page(tlb, pte);
}
#if PAGETABLE_LEVELS > 2
void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
{
paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
tlb_remove_page(tlb, virt_to_page(pmd));
}
#if PAGETABLE_LEVELS > 3
void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
{
paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
tlb_remove_page(tlb, virt_to_page(pud));
}
#endif /* PAGETABLE_LEVELS > 3 */
#endif /* PAGETABLE_LEVELS > 2 */
static inline void pgd_list_add(pgd_t *pgd)
{
struct page *page = virt_to_page(pgd);
list_add(&page->lru, &pgd_list);
}
static inline void pgd_list_del(pgd_t *pgd)
{
struct page *page = virt_to_page(pgd);
list_del(&page->lru);
}
#define UNSHARED_PTRS_PER_PGD \
(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
static void pgd_ctor(pgd_t *pgd)
{
/* If the pgd points to a shared pagetable level (either the
ptes in non-PAE, or shared PMD in PAE), then just copy the
references from swapper_pg_dir. */
if (PAGETABLE_LEVELS == 2 ||
(PAGETABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
PAGETABLE_LEVELS == 4) {
clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
swapper_pg_dir + KERNEL_PGD_BOUNDARY,
KERNEL_PGD_PTRS);
paravirt_alloc_pmd_clone(__pa(pgd) >> PAGE_SHIFT,
__pa(swapper_pg_dir) >> PAGE_SHIFT,
KERNEL_PGD_BOUNDARY,
KERNEL_PGD_PTRS);
}
/* list required to sync kernel mapping updates */
if (!SHARED_KERNEL_PMD)
pgd_list_add(pgd);
}
static void pgd_dtor(pgd_t *pgd)
{
unsigned long flags; /* can be called from interrupt context */
if (SHARED_KERNEL_PMD)
return;
spin_lock_irqsave(&pgd_lock, flags);
pgd_list_del(pgd);
spin_unlock_irqrestore(&pgd_lock, flags);
}
/*
* 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.
* -- wli
*/
#ifdef CONFIG_X86_PAE
/*
* In PAE mode, we need to do a cr3 reload (=tlb flush) when
* updating the top-level pagetable entries to guarantee the
* processor notices the update. Since this is expensive, and
* all 4 top-level entries are used almost immediately in a
* new process's life, we just pre-populate them here.
*
* Also, if we're in a paravirt environment where the kernel pmd is
* not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
* and initialize the kernel pmds here.
*/
#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD
void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
{
paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
/* Note: almost everything apart from _PAGE_PRESENT is
reserved at the pmd (PDPT) level. */
set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
/*
* According to Intel App note "TLBs, Paging-Structure Caches,
* and Their Invalidation", April 2007, document 317080-001,
* section 8.1: in PAE mode we explicitly have to flush the
* TLB via cr3 if the top-level pgd is changed...
*/
if (mm == current->active_mm)
write_cr3(read_cr3());
}
#else /* !CONFIG_X86_PAE */
/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS 0
#endif /* CONFIG_X86_PAE */
static void free_pmds(pmd_t *pmds[])
{
int i;
for(i = 0; i < PREALLOCATED_PMDS; i++)
if (pmds[i])
free_page((unsigned long)pmds[i]);
}
static int preallocate_pmds(pmd_t *pmds[])
{
int i;
bool failed = false;
for(i = 0; i < PREALLOCATED_PMDS; i++) {
pmd_t *pmd = (pmd_t *)__get_free_page(PGALLOC_GFP);
if (pmd == NULL)
failed = true;
pmds[i] = pmd;
}
if (failed) {
free_pmds(pmds);
return -ENOMEM;
}
return 0;
}
/*
* Mop up any pmd pages which may still be attached to the pgd.
* Normally they will be freed by munmap/exit_mmap, but any pmd we
* preallocate which never got a corresponding vma will need to be
* freed manually.
*/
static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
{
int i;
for(i = 0; i < PREALLOCATED_PMDS; i++) {
pgd_t pgd = pgdp[i];
if (pgd_val(pgd) != 0) {
pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
pgdp[i] = native_make_pgd(0);
paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
pmd_free(mm, pmd);
}
}
}
static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
{
pud_t *pud;
unsigned long addr;
int i;
if (PREALLOCATED_PMDS == 0) /* Work around gcc-3.4.x bug */
return;
pud = pud_offset(pgd, 0);
for (addr = i = 0; i < PREALLOCATED_PMDS;
i++, pud++, addr += PUD_SIZE) {
pmd_t *pmd = pmds[i];
if (i >= KERNEL_PGD_BOUNDARY)
memcpy(pmd, (pmd_t *)pgd_page_vaddr(swapper_pg_dir[i]),
sizeof(pmd_t) * PTRS_PER_PMD);
pud_populate(mm, pud, pmd);
}
}
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
pmd_t *pmds[PREALLOCATED_PMDS];
unsigned long flags;
pgd = (pgd_t *)__get_free_page(PGALLOC_GFP);
if (pgd == NULL)
goto out;
mm->pgd = pgd;
if (preallocate_pmds(pmds) != 0)
goto out_free_pgd;
if (paravirt_pgd_alloc(mm) != 0)
goto out_free_pmds;
/*
* Make sure that pre-populating the pmds is atomic with
* respect to anything walking the pgd_list, so that they
* never see a partially populated pgd.
*/
spin_lock_irqsave(&pgd_lock, flags);
pgd_ctor(pgd);
pgd_prepopulate_pmd(mm, pgd, pmds);
spin_unlock_irqrestore(&pgd_lock, flags);
return pgd;
out_free_pmds:
free_pmds(pmds);
out_free_pgd:
free_page((unsigned long)pgd);
out:
return NULL;
}
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
pgd_mop_up_pmds(mm, pgd);
pgd_dtor(pgd);
paravirt_pgd_free(mm, pgd);
free_page((unsigned long)pgd);
}
int ptep_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep,
pte_t entry, int dirty)
{
int changed = !pte_same(*ptep, entry);
if (changed && dirty) {
*ptep = entry;
pte_update_defer(vma->vm_mm, address, ptep);
flush_tlb_page(vma, address);
}
return changed;
}
int ptep_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
int ret = 0;
if (pte_young(*ptep))
ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,
(unsigned long *) &ptep->pte);
if (ret)
pte_update(vma->vm_mm, addr, ptep);
return ret;
}
int ptep_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pte_t *ptep)
{
int young;
young = ptep_test_and_clear_young(vma, address, ptep);
if (young)
flush_tlb_page(vma, address);
return young;
}
/**
* reserve_top_address - reserves a hole in the top of kernel address space
* @reserve - size of hole to reserve
*
* Can be used to relocate the fixmap area and poke a hole in the top
* of kernel address space to make room for a hypervisor.
*/
void __init reserve_top_address(unsigned long reserve)
{
#ifdef CONFIG_X86_32
BUG_ON(fixmaps_set > 0);
printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
(int)-reserve);
__FIXADDR_TOP = -reserve - PAGE_SIZE;
#endif
}
int fixmaps_set;
void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
}
set_pte_vaddr(address, pte);
fixmaps_set++;
}
void native_set_fixmap(enum fixed_addresses idx, phys_addr_t phys,
pgprot_t flags)
{
__native_set_fixmap(idx, pfn_pte(phys >> PAGE_SHIFT, flags));
}