x86: define _PAGE_NUMA by reusing software bits on the PMD and PTE levels

_PAGE_NUMA is currently an alias of _PROT_PROTNONE to trap NUMA hinting
faults on x86.  Care is taken such that _PAGE_NUMA is used only in
situations where the VMA flags distinguish between NUMA hinting faults
and prot_none faults.  This decision was x86-specific and conceptually
it is difficult requiring special casing to distinguish between PROTNONE
and NUMA ptes based on context.

Fundamentally, we only need the _PAGE_NUMA bit to tell the difference
between an entry that is really unmapped and a page that is protected
for NUMA hinting faults as if the PTE is not present then a fault will
be trapped.

Swap PTEs on x86-64 use the bits after _PAGE_GLOBAL for the offset.
This patch shrinks the maximum possible swap size and uses the bit to
uniquely distinguish between NUMA hinting ptes and swap ptes.

Signed-off-by: Mel Gorman <mgorman@suse.de>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Steven Noonan <steven@uplinklabs.net>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 11 insertions, 4 deletions

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index b459ddf27d64..66276c1d23bb 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte)
 
 static inline int pte_special(pte_t pte)
 {
-	return pte_flags(pte) & _PAGE_SPECIAL;
+	return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) ==
+				 (_PAGE_PRESENT|_PAGE_SPECIAL);
 }
 
 static inline unsigned long pte_pfn(pte_t pte)
@@ -452,6 +453,12 @@ static inline int pte_present(pte_t a)
 			       _PAGE_NUMA);
 }
 
+#define pte_present_nonuma pte_present_nonuma
+static inline int pte_present_nonuma(pte_t a)
+{
+	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
+}
+
 #define pte_accessible pte_accessible
 static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
@@ -860,19 +867,19 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
 
 static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }
 
 static inline int pte_swp_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
 }
 
 static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
 {
-	VM_BUG_ON(pte_present(pte));
+	VM_BUG_ON(pte_present_nonuma(pte));
 	return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
 }