#ifndef _PPC64_PGTABLE_H
#define _PPC64_PGTABLE_H
-#include <asm-generic/4level-fixup.h>
-
/*
* This file contains the functions and defines necessary to modify and use
* the ppc64 hashed page table.
#include <asm/tlbflush.h>
#endif /* __ASSEMBLY__ */
-/* PMD_SHIFT determines what a second-level page table entry can map */
-#define PMD_SHIFT (PAGE_SHIFT + PAGE_SHIFT - 3)
-#define PMD_SIZE (1UL << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
-
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-#define PGDIR_SHIFT (PAGE_SHIFT + (PAGE_SHIFT - 3) + (PAGE_SHIFT - 2))
-#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
-
/*
* Entries per page directory level. The PTE level must use a 64b record
* for each page table entry. The PMD and PGD level use a 32b record for
* each entry by assuming that each entry is page aligned.
*/
#define PTE_INDEX_SIZE 9
-#define PMD_INDEX_SIZE 10
-#define PGD_INDEX_SIZE 10
+#define PMD_INDEX_SIZE 7
+#define PUD_INDEX_SIZE 7
+#define PGD_INDEX_SIZE 9
+
+#define PTE_TABLE_SIZE (sizeof(pte_t) << PTE_INDEX_SIZE)
+#define PMD_TABLE_SIZE (sizeof(pmd_t) << PMD_INDEX_SIZE)
+#define PUD_TABLE_SIZE (sizeof(pud_t) << PUD_INDEX_SIZE)
+#define PGD_TABLE_SIZE (sizeof(pgd_t) << PGD_INDEX_SIZE)
#define PTRS_PER_PTE (1 << PTE_INDEX_SIZE)
#define PTRS_PER_PMD (1 << PMD_INDEX_SIZE)
+#define PTRS_PER_PUD (1 << PMD_INDEX_SIZE)
#define PTRS_PER_PGD (1 << PGD_INDEX_SIZE)
-#define USER_PTRS_PER_PGD (1024)
-#define FIRST_USER_ADDRESS 0
+/* PMD_SHIFT determines what a second-level page table entry can map */
+#define PMD_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PMD_SIZE (1UL << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+
+/* PUD_SHIFT determines what a third-level page table entry can map */
+#define PUD_SHIFT (PMD_SHIFT + PMD_INDEX_SIZE)
+#define PUD_SIZE (1UL << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
-#define EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
- PGD_INDEX_SIZE + PAGE_SHIFT)
+/* PGDIR_SHIFT determines what a fourth-level page table entry can map */
+#define PGDIR_SHIFT (PUD_SHIFT + PUD_INDEX_SIZE)
+#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define FIRST_USER_ADDRESS 0
/*
* Size of EA range mapped by our pagetables.
*/
-#define PGTABLE_EA_BITS 41
-#define PGTABLE_EA_MASK ((1UL<<PGTABLE_EA_BITS)-1)
+#define PGTABLE_EADDR_SIZE (PTE_INDEX_SIZE + PMD_INDEX_SIZE + \
+ PUD_INDEX_SIZE + PGD_INDEX_SIZE + PAGE_SHIFT)
+#define PGTABLE_RANGE (1UL << PGTABLE_EADDR_SIZE)
-/*
- * Define the address range of the vmalloc VM area.
- */
-#define VMALLOC_START (0xD000000000000000ul)
-#define VMALLOC_END (VMALLOC_START + PGTABLE_EA_MASK)
+#if TASK_SIZE_USER64 > PGTABLE_RANGE
+#error TASK_SIZE_USER64 exceeds pagetable range
+#endif
-/*
- * Define the address range of the imalloc VM area.
- * (used for ioremap)
- */
-#define IMALLOC_START (ioremap_bot)
-#define IMALLOC_VMADDR(x) ((unsigned long)(x))
-#define PHBS_IO_BASE (0xE000000000000000ul) /* Reserve 2 gigs for PHBs */
-#define IMALLOC_BASE (0xE000000080000000ul)
-#define IMALLOC_END (IMALLOC_BASE + PGTABLE_EA_MASK)
+#if TASK_SIZE_USER64 > (1UL << (USER_ESID_BITS + SID_SHIFT))
+#error TASK_SIZE_USER64 exceeds user VSID range
+#endif
/*
- * Define the user address range
+ * Define the address range of the vmalloc VM area.
*/
-#define USER_START (0UL)
-#define USER_END (USER_START + PGTABLE_EA_MASK)
-
+#define VMALLOC_START (0xD000000000000000ul)
+#define VMALLOC_SIZE (0x80000000000UL)
+#define VMALLOC_END (VMALLOC_START + VMALLOC_SIZE)
/*
* Bits in a linux-style PTE. These match the bits in the
/* shift to put page number into pte */
#define PTE_SHIFT (17)
-/* We allow 2^41 bytes of real memory, so we need 29 bits in the PMD
- * to give the PTE page number. The bottom two bits are for flags. */
-#define PMD_TO_PTEPAGE_SHIFT (2)
-
#ifdef CONFIG_HUGETLB_PAGE
#ifndef __ASSEMBLY__
int hash_huge_page(struct mm_struct *mm, unsigned long access,
unsigned long ea, unsigned long vsid, int local);
-
-void hugetlb_mm_free_pgd(struct mm_struct *mm);
#endif /* __ASSEMBLY__ */
#define HAVE_ARCH_UNMAPPED_AREA
#else
#define hash_huge_page(mm,a,ea,vsid,local) -1
-#define hugetlb_mm_free_pgd(mm) do {} while (0)
#endif
*/
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-#define pfn_pte(pfn,pgprot) \
-({ \
- pte_t pte; \
- pte_val(pte) = ((unsigned long)(pfn) << PTE_SHIFT) | \
- pgprot_val(pgprot); \
- pte; \
-})
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+ pte_t pte;
+
+
+ pte_val(pte) = (pfn << PTE_SHIFT) | pgprot_val(pgprot);
+ return pte;
+}
#define pte_modify(_pte, newprot) \
(__pte((pte_val(_pte) & _PAGE_CHG_MASK) | pgprot_val(newprot)))
#define pte_pfn(x) ((unsigned long)((pte_val(x) >> PTE_SHIFT)))
#define pte_page(x) pfn_to_page(pte_pfn(x))
-#define pmd_set(pmdp, ptep) \
- (pmd_val(*(pmdp)) = (__ba_to_bpn(ptep) << PMD_TO_PTEPAGE_SHIFT))
+#define pmd_set(pmdp, ptep) ({BUG_ON((u64)ptep < KERNELBASE); pmd_val(*(pmdp)) = (unsigned long)(ptep);})
#define pmd_none(pmd) (!pmd_val(pmd))
#define pmd_bad(pmd) (pmd_val(pmd) == 0)
#define pmd_present(pmd) (pmd_val(pmd) != 0)
#define pmd_clear(pmdp) (pmd_val(*(pmdp)) = 0)
-#define pmd_page_kernel(pmd) \
- (__bpn_to_ba(pmd_val(pmd) >> PMD_TO_PTEPAGE_SHIFT))
+#define pmd_page_kernel(pmd) (pmd_val(pmd))
#define pmd_page(pmd) virt_to_page(pmd_page_kernel(pmd))
-#define pgd_set(pgdp, pmdp) (pgd_val(*(pgdp)) = (__ba_to_bpn(pmdp)))
+
+#define pud_set(pudp, pmdp) (pud_val(*(pudp)) = (unsigned long)(pmdp))
+#define pud_none(pud) (!pud_val(pud))
+#define pud_bad(pud) ((pud_val(pud)) == 0)
+#define pud_present(pud) (pud_val(pud) != 0)
+#define pud_clear(pudp) (pud_val(*(pudp)) = 0)
+#define pud_page(pud) (pud_val(pud))
+
+#define pgd_set(pgdp, pudp) ({pgd_val(*(pgdp)) = (unsigned long)(pudp);})
#define pgd_none(pgd) (!pgd_val(pgd))
-#define pgd_bad(pgd) ((pgd_val(pgd)) == 0)
-#define pgd_present(pgd) (pgd_val(pgd) != 0UL)
-#define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0UL)
-#define pgd_page(pgd) (__bpn_to_ba(pgd_val(pgd)))
+#define pgd_bad(pgd) (pgd_val(pgd) == 0)
+#define pgd_present(pgd) (pgd_val(pgd) != 0)
+#define pgd_clear(pgdp) (pgd_val(*(pgdp)) = 0)
+#define pgd_page(pgd) (pgd_val(pgd))
/*
* Find an entry in a page-table-directory. We combine the address region
* (the high order N bits) and the pgd portion of the address.
*/
/* to avoid overflow in free_pgtables we don't use PTRS_PER_PGD here */
-#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x7ff)
+#define pgd_index(address) (((address) >> (PGDIR_SHIFT)) & 0x1ff)
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index(address))
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(dir,addr) \
- ((pmd_t *) pgd_page(*(dir)) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
+#define pud_offset(pgdp, addr) \
+ (((pud_t *) pgd_page(*(pgdp))) + (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)))
+
+#define pmd_offset(pudp,addr) \
+ (((pmd_t *) pud_page(*(pudp))) + (((addr) >> PMD_SHIFT) & (PTRS_PER_PMD - 1)))
-/* Find an entry in the third-level page table.. */
#define pte_offset_kernel(dir,addr) \
- ((pte_t *) pmd_page_kernel(*(dir)) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
+ (((pte_t *) pmd_page_kernel(*(dir))) + (((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1)))
#define pte_offset_map(dir,addr) pte_offset_kernel((dir), (addr))
#define pte_offset_map_nested(dir,addr) pte_offset_kernel((dir), (addr))
/* This now only contains the vmalloc pages */
#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-/* to find an entry in the ioremap page-table-directory */
-#define pgd_offset_i(address) (ioremap_pgd + pgd_index(address))
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
pte_clear(mm, addr, ptep);
flush_tlb_pending();
}
- *ptep = __pte(pte_val(pte)) & ~_PAGE_HPTEFLAGS;
+ *ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
}
/* Set the dirty and/or accessed bits atomically in a linux PTE, this
#define __HAVE_ARCH_PTE_SAME
#define pte_same(A,B) (((pte_val(A) ^ pte_val(B)) & ~_PAGE_HPTEFLAGS) == 0)
-extern unsigned long ioremap_bot, ioremap_base;
-
-#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
-#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
-
-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %08x.\n", __FILE__, __LINE__, pmd_val(e))
+ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pmd_val(e))
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, pud_val(e))
#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %08x.\n", __FILE__, __LINE__, pgd_val(e))
+ printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-extern pgd_t swapper_pg_dir[1024];
-extern pgd_t ioremap_dir[1024];
+extern pgd_t swapper_pg_dir[];
extern void paging_init(void);
-/*
- * Because the huge pgtables are only 2 level, they can take
- * at most around 4M, much less than one hugepage which the
- * process is presumably entitled to use. So we don't bother
- * freeing up the pagetables on unmap, and wait until
- * destroy_context() to clean up the lot.
- */
#define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) \
- do { } while (0)
+ free_pgd_range(tlb, addr, end, floor, ceiling)
/*
* This gets called at the end of handling a page fault, when
*/
#define kern_addr_valid(addr) (1)
-#define io_remap_page_range(vma, vaddr, paddr, size, prot) \
- remap_pfn_range(vma, vaddr, (paddr) >> PAGE_SHIFT, size, prot)
-
#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
remap_pfn_range(vma, vaddr, pfn, size, prot)
-#define MK_IOSPACE_PFN(space, pfn) (pfn)
-#define GET_IOSPACE(pfn) 0
-#define GET_PFN(pfn) (pfn)
-
void pgtable_cache_init(void);
-extern void hpte_init_native(void);
-extern void hpte_init_lpar(void);
-extern void hpte_init_iSeries(void);
-
-/* imalloc region types */
-#define IM_REGION_UNUSED 0x1
-#define IM_REGION_SUBSET 0x2
-#define IM_REGION_EXISTS 0x4
-#define IM_REGION_OVERLAP 0x8
-#define IM_REGION_SUPERSET 0x10
-
-extern struct vm_struct * im_get_free_area(unsigned long size);
-extern struct vm_struct * im_get_area(unsigned long v_addr, unsigned long size,
- int region_type);
-unsigned long im_free(void *addr);
-
-extern long pSeries_lpar_hpte_insert(unsigned long hpte_group,
- unsigned long va, unsigned long prpn,
- int secondary, unsigned long hpteflags,
- int bolted, int large);
-
-extern long native_hpte_insert(unsigned long hpte_group, unsigned long va,
- unsigned long prpn, int secondary,
- unsigned long hpteflags, int bolted, int large);
-
/*
* find_linux_pte returns the address of a linux pte for a given
* effective address and directory. If not found, it returns zero.
static inline pte_t *find_linux_pte(pgd_t *pgdir, unsigned long ea)
{
pgd_t *pg;
+ pud_t *pu;
pmd_t *pm;
pte_t *pt = NULL;
pte_t pte;
pg = pgdir + pgd_index(ea);
if (!pgd_none(*pg)) {
-
- pm = pmd_offset(pg, ea);
- if (pmd_present(*pm)) {
- pt = pte_offset_kernel(pm, ea);
- pte = *pt;
- if (!pte_present(pte))
- pt = NULL;
+ pu = pud_offset(pg, ea);
+ if (!pud_none(*pu)) {
+ pm = pmd_offset(pu, ea);
+ if (pmd_present(*pm)) {
+ pt = pte_offset_kernel(pm, ea);
+ pte = *pt;
+ if (!pte_present(pte))
+ pt = NULL;
+ }
}
}