aboutsummaryrefslogtreecommitdiffstats
path: root/arch/ppc
diff options
context:
space:
mode:
authorMartin Schwidefsky <schwidefsky@de.ibm.com>2008-02-08 07:22:04 -0500
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2008-02-08 12:22:42 -0500
commit2f569afd9ced9ebec9a6eb3dbf6f83429be0a7b4 (patch)
tree23a31763887d9505e62e9d7cc8ec2fa4b86bd380 /arch/ppc
parent13214adf738abc92b0a00c0763fd3be79eebaa7c (diff)
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>
Diffstat (limited to 'arch/ppc')
-rw-r--r--arch/ppc/mm/pgtable.c9
1 files changed, 6 insertions, 3 deletions
diff --git a/arch/ppc/mm/pgtable.c b/arch/ppc/mm/pgtable.c
index 409fcaa4994..03a79bff127 100644
--- a/arch/ppc/mm/pgtable.c
+++ b/arch/ppc/mm/pgtable.c
@@ -95,7 +95,7 @@ __init_refok pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long add
95 return pte; 95 return pte;
96} 96}
97 97
98struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address) 98pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
99{ 99{
100 struct page *ptepage; 100 struct page *ptepage;
101 101
@@ -106,8 +106,10 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
106#endif 106#endif
107 107
108 ptepage = alloc_pages(flags, 0); 108 ptepage = alloc_pages(flags, 0);
109 if (ptepage) 109 if (ptepage) {
110 clear_highpage(ptepage); 110 clear_highpage(ptepage);
111 pgtable_page_ctor(ptepage);
112 }
111 return ptepage; 113 return ptepage;
112} 114}
113 115
@@ -119,11 +121,12 @@ void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
119 free_page((unsigned long)pte); 121 free_page((unsigned long)pte);
120} 122}
121 123
122void pte_free(struct mm_struct *mm, struct page *ptepage) 124void pte_free(struct mm_struct *mm, pgtable_t ptepage)
123{ 125{
124#ifdef CONFIG_SMP 126#ifdef CONFIG_SMP
125 hash_page_sync(); 127 hash_page_sync();
126#endif 128#endif
129 pgtable_page_dtor(ptepage);
127 __free_page(ptepage); 130 __free_page(ptepage);
128} 131}
129 132