linux-stable/arch/x86/mm/pgtable_32.c
Hugh Dickins aeed5fce37 x86: fix PAE pmd_bad bootup warning
Fix warning from pmd_bad() at bootup on a HIGHMEM64G HIGHPTE x86_32.

That came from 9fc34113f6 x86: debug pmd_bad();
but we understand now that the typecasting was wrong for PAE in the previous
version: pagetable pages above 4GB looked bad and stopped Arjan from booting.

And revert that cded932b75 x86: fix pmd_bad
and pud_bad to support huge pages.  It was the wrong way round: we shouldn't
weaken every pmd_bad and pud_bad check to let huge pages slip through - in
part they check that we _don't_ have a huge page where it's not expected.

Put the x86 pmd_bad() and pud_bad() definitions back to what they have long
been: they can be improved (x86_32 should use PTE_MASK, to stop PAE thinking
junk in the upper word is good; and x86_64 should follow x86_32's stricter
comparison, to stop thinking any subset of required bits is good); but that
should be a later patch.

Fix Hans' good observation that follow_page() will never find pmd_huge()
because that would have already failed the pmd_bad test: test pmd_huge in
between the pmd_none and pmd_bad tests.  Tighten x86's pmd_huge() check?
No, once it's a hugepage entry, it can get quite far from a good pmd: for
example, PROT_NONE leaves it with only ACCESSED of the KERN_PGTABLE bits.

However... though follow_page() contains this and another test for huge
pages, so it's nice to keep it working on them, where does it actually get
called on a huge page?  get_user_pages() checks is_vm_hugetlb_page(vma) to
to call alternative hugetlb processing, as does unmap_vmas() and others.

Signed-off-by: Hugh Dickins <hugh@veritas.com>
Earlier-version-tested-by: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jeff Chua <jeff.chua.linux@gmail.com>
Cc: Hans Rosenfeld <hans.rosenfeld@amd.com>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-05-06 13:08:58 -07:00

174 lines
4.5 KiB
C

#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/nmi.h>
#include <linux/swap.h>
#include <linux/smp.h>
#include <linux/highmem.h>
#include <linux/slab.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/fixmap.h>
#include <asm/e820.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
void show_mem(void)
{
int total = 0, reserved = 0;
int shared = 0, cached = 0;
int highmem = 0;
struct page *page;
pg_data_t *pgdat;
unsigned long i;
unsigned long flags;
printk(KERN_INFO "Mem-info:\n");
show_free_areas();
for_each_online_pgdat(pgdat) {
pgdat_resize_lock(pgdat, &flags);
for (i = 0; i < pgdat->node_spanned_pages; ++i) {
if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
touch_nmi_watchdog();
page = pgdat_page_nr(pgdat, i);
total++;
if (PageHighMem(page))
highmem++;
if (PageReserved(page))
reserved++;
else if (PageSwapCache(page))
cached++;
else if (page_count(page))
shared += page_count(page) - 1;
}
pgdat_resize_unlock(pgdat, &flags);
}
printk(KERN_INFO "%d pages of RAM\n", total);
printk(KERN_INFO "%d pages of HIGHMEM\n", highmem);
printk(KERN_INFO "%d reserved pages\n", reserved);
printk(KERN_INFO "%d pages shared\n", shared);
printk(KERN_INFO "%d pages swap cached\n", cached);
printk(KERN_INFO "%lu pages dirty\n", global_page_state(NR_FILE_DIRTY));
printk(KERN_INFO "%lu pages writeback\n",
global_page_state(NR_WRITEBACK));
printk(KERN_INFO "%lu pages mapped\n", global_page_state(NR_FILE_MAPPED));
printk(KERN_INFO "%lu pages slab\n",
global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE));
printk(KERN_INFO "%lu pages pagetables\n",
global_page_state(NR_PAGETABLE));
}
/*
* Associate a virtual page frame with a given physical page frame
* and protection flags for that frame.
*/
static void set_pte_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
pgd = swapper_pg_dir + pgd_index(vaddr);
if (pgd_none(*pgd)) {
BUG();
return;
}
pud = pud_offset(pgd, vaddr);
if (pud_none(*pud)) {
BUG();
return;
}
pmd = pmd_offset(pud, vaddr);
if (pmd_none(*pmd)) {
BUG();
return;
}
pte = pte_offset_kernel(pmd, vaddr);
if (pgprot_val(flags))
set_pte_present(&init_mm, vaddr, pte, pfn_pte(pfn, flags));
else
pte_clear(&init_mm, vaddr, pte);
/*
* It's enough to flush this one mapping.
* (PGE mappings get flushed as well)
*/
__flush_tlb_one(vaddr);
}
/*
* 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_WARNING "set_pmd_pfn: vaddr misaligned\n");
return; /* BUG(); */
}
if (pfn & (PTRS_PER_PTE-1)) { /* pfn is misaligned */
printk(KERN_WARNING "set_pmd_pfn: pfn misaligned\n");
return; /* BUG(); */
}
pgd = swapper_pg_dir + pgd_index(vaddr);
if (pgd_none(*pgd)) {
printk(KERN_WARNING "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)
*/
__flush_tlb_one(vaddr);
}
static int fixmaps;
unsigned long __FIXADDR_TOP = 0xfffff000;
EXPORT_SYMBOL(__FIXADDR_TOP);
void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
{
unsigned long address = __fix_to_virt(idx);
if (idx >= __end_of_fixed_addresses) {
BUG();
return;
}
set_pte_pfn(address, phys >> PAGE_SHIFT, flags);
fixmaps++;
}
/**
* 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 reserve_top_address(unsigned long reserve)
{
BUG_ON(fixmaps > 0);
printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
(int)-reserve);
__FIXADDR_TOP = -reserve - PAGE_SIZE;
__VMALLOC_RESERVE += reserve;
}