x86: fix PAE pmd_bad bootup warning

Fix warning from pmd_bad() at bootup on a HIGHMEM64G HIGHPTE x86_32.

That came from 9fc34113f6880b215cbea4e7017fc818700384c2 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 cded932b75ab0a5f9181ee3da34a0a488d1a14fd 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>

diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 9ee007b..369cf06 100644 (file)
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -172,10 +172,3 @@ void reserve_top_address(unsigned long reserve)
        __FIXADDR_TOP = -reserve - PAGE_SIZE;
        __VMALLOC_RESERVE += reserve;
 }
-
-int pmd_bad(pmd_t pmd)
-{
-       WARN_ON_ONCE(pmd_bad_v1(pmd) != pmd_bad_v2(pmd));
-
-       return pmd_bad_v1(pmd);
-}

diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
index 577ab79..d7f0403 100644 (file)
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -88,14 +88,7 @@ extern unsigned long pg0[];
 /* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
 #define pmd_none(x)    (!(unsigned long)pmd_val((x)))
 #define pmd_present(x) (pmd_val((x)) & _PAGE_PRESENT)
-
-extern int pmd_bad(pmd_t pmd);
-
-#define pmd_bad_v1(x)                                                  \
-       (_KERNPG_TABLE != (pmd_val((x)) & ~(PAGE_MASK | _PAGE_USER)))
-#define        pmd_bad_v2(x)                                                   \
-       (_KERNPG_TABLE != (pmd_val((x)) & ~(PAGE_MASK | _PAGE_USER |    \
-                                           _PAGE_PSE | _PAGE_NX)))
+#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
 
 #define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
 

diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
index a3bbf87..efe83dc 100644 (file)
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -158,14 +158,12 @@ static inline unsigned long pgd_bad(pgd_t pgd)
 
 static inline unsigned long pud_bad(pud_t pud)
 {
-       return pud_val(pud) &
-               ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER | _PAGE_PSE | _PAGE_NX);
+       return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
 }
 
 static inline unsigned long pmd_bad(pmd_t pmd)
 {
-       return pmd_val(pmd) &
-               ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER | _PAGE_PSE | _PAGE_NX);
+       return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
 }
 
 #define pte_none(x)    (!pte_val((x)))

diff --git a/mm/memory.c b/mm/memory.c
index bbab1e3..48c122d 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -969,7 +969,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                goto no_page_table;
        
        pmd = pmd_offset(pud, address);
-       if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+       if (pmd_none(*pmd))
                goto no_page_table;
 
        if (pmd_huge(*pmd)) {
@@ -978,6 +978,9 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                goto out;
        }
 
+       if (unlikely(pmd_bad(*pmd)))
+               goto no_page_table;
+
        ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
        if (!ptep)
                goto out;