CONFIG_HIGHPTE vs. sub-page page tables.

Background: I've implemented 1K/2K page tables for s390.  These sub-page
page tables are required to properly support the s390 virtualization
instruction with KVM.  The SIE instruction requires that the page tables
have 256 page table entries (pte) followed by 256 page status table entries
(pgste).  The pgstes are only required if the process is using the SIE
instruction.  The pgstes are updated by the hardware and by the hypervisor
for a number of reasons, one of them is dirty and reference bit tracking.
To avoid wasting memory the standard pte table allocation should return
1K/2K (31/64 bit) and 2K/4K if the process is using SIE.

Problem: Page size on s390 is 4K, page table size is 1K or 2K.  That means
the s390 version for pte_alloc_one cannot return a pointer to a struct
page.  Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one
cannot return a pointer to a pte either, since that would require more than
32 bit for the return value of pte_alloc_one (and the pte * would not be
accessible since its not kmapped).

Solution: The only solution I found to this dilemma is a new typedef: a
pgtable_t.  For s390 pgtable_t will be a (pte *) - to be introduced with a
later patch.  For everybody else it will be a (struct page *).  The
additional problem with the initialization of the ptl lock and the
NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and
a destructor pgtable_page_dtor.  The page table allocation and free
functions need to call these two whenever a page table page is allocated or
freed.  pmd_populate will get a pgtable_t instead of a struct page pointer.
 To get the pgtable_t back from a pmd entry that has been installed with
pmd_populate a new function pmd_pgtable is added.  It replaces the pmd_page
call in free_pte_range and apply_to_pte_range.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 17 insertions, 7 deletions

diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index dc98e3844a0a..23d3291a3e81 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -489,14 +489,17 @@ srmmu_pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
         return (pte_t *)srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 }
 
-static struct page *
+static pgtable_t
 srmmu_pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
         unsigned long pte;
+        struct page *page;
 
         if ((pte = (unsigned long)srmmu_pte_alloc_one_kernel(mm, address)) == 0)
                 return NULL;
-        return pfn_to_page( __nocache_pa(pte) >> PAGE_SHIFT );
+        page = pfn_to_page( __nocache_pa(pte) >> PAGE_SHIFT );
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static void srmmu_free_pte_fast(pte_t *pte)
@@ -504,10 +507,11 @@ static void srmmu_free_pte_fast(pte_t *pte)
         srmmu_free_nocache((unsigned long)pte, PTE_SIZE);
 }
 
-static void srmmu_pte_free(struct page *pte)
+static void srmmu_pte_free(pgtable_t pte)
 {
         unsigned long p;
 
+        pgtable_page_dtor(pte);
         p = (unsigned long)page_address(pte);   /* Cached address (for test) */
         if (p == 0)
                 BUG();
diff --git a/arch/sparc/mm/sun4c.c b/arch/sparc/mm/sun4c.c
index 0729305f2f59..c0442e8c4b15 100644
--- a/arch/sparc/mm/sun4c.c
+++ b/arch/sparc/mm/sun4c.c
@@ -1947,12 +1947,17 @@ static pte_t *sun4c_pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
         return pte;
 }
 
-static struct page *sun4c_pte_alloc_one(struct mm_struct *mm, unsigned long address)
+static pgtable_t sun4c_pte_alloc_one(struct mm_struct *mm, unsigned long address)
 {
-        pte_t *pte = sun4c_pte_alloc_one_kernel(mm, address);
+        pte_t *pte;
+        struct page *page;
+
+        pte = sun4c_pte_alloc_one_kernel(mm, address);
         if (pte == NULL)
                 return NULL;
-        return virt_to_page(pte);
+        page = virt_to_page(pte);
+        pgtable_page_ctor(page);
+        return page;
 }
 
 static inline void sun4c_free_pte_fast(pte_t *pte)
@@ -1962,8 +1967,9 @@ static inline void sun4c_free_pte_fast(pte_t *pte)
         pgtable_cache_size++;
 }
 
-static void sun4c_pte_free(struct page *pte)
+static void sun4c_pte_free(pgtable_t pte)
 {
+        pgtable_page_dtor(pte);
         sun4c_free_pte_fast(page_address(pte));
 }