#ifndef _I386_PGTABLE_H
#define _I386_PGTABLE_H
-#include <linux/config.h>
/*
* The Linux memory management assumes a three-level page table setup. On
#include <asm/processor.h>
#include <asm/fixmap.h>
#include <linux/threads.h>
+#include <asm/paravirt.h>
#ifndef _I386_BITOPS_H
#include <asm/bitops.h>
#include <linux/list.h>
#include <linux/spinlock.h>
+struct mm_struct;
+struct vm_area_struct;
+
/*
* ZERO_PAGE is a global shared page that is always zero: used
* for zero-mapped memory areas etc..
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
extern unsigned long empty_zero_page[1024];
extern pgd_t swapper_pg_dir[1024];
-extern kmem_cache_t *pgd_cache;
-extern kmem_cache_t *pmd_cache;
+extern struct kmem_cache *pmd_cache;
extern spinlock_t pgd_lock;
extern struct page *pgd_list;
+void check_pgt_cache(void);
-void pmd_ctor(void *, kmem_cache_t *, unsigned long);
-void pgd_ctor(void *, kmem_cache_t *, unsigned long);
-void pgd_dtor(void *, kmem_cache_t *, unsigned long);
+void pmd_ctor(void *, struct kmem_cache *, unsigned long);
void pgtable_cache_init(void);
void paging_init(void);
+
/*
* The Linux x86 paging architecture is 'compile-time dual-mode', it
* implements both the traditional 2-level x86 page tables and the
* area for the same reason. ;)
*/
#define VMALLOC_OFFSET (8*1024*1024)
-#define VMALLOC_START (((unsigned long) high_memory + vmalloc_earlyreserve + \
+#define VMALLOC_START (((unsigned long) high_memory + \
2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1))
#ifdef CONFIG_HIGHMEM
# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
extern unsigned long pg0[];
#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
-#define pmd_none(x) (!pmd_val(x))
+/* 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)
-#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
-#define __LARGE_PTE (_PAGE_PSE | _PAGE_PRESENT)
-static inline int pte_user(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
-static inline int pte_read(pte_t pte) { return (pte).pte_low & _PAGE_USER; }
static inline int pte_dirty(pte_t pte) { return (pte).pte_low & _PAGE_DIRTY; }
static inline int pte_young(pte_t pte) { return (pte).pte_low & _PAGE_ACCESSED; }
static inline int pte_write(pte_t pte) { return (pte).pte_low & _PAGE_RW; }
-static inline int pte_huge(pte_t pte) { return ((pte).pte_low & __LARGE_PTE) == __LARGE_PTE; }
+static inline int pte_huge(pte_t pte) { return (pte).pte_low & _PAGE_PSE; }
/*
* The following only works if pte_present() is not true.
*/
static inline int pte_file(pte_t pte) { return (pte).pte_low & _PAGE_FILE; }
-static inline pte_t pte_rdprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
-static inline pte_t pte_exprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_USER; return pte; }
static inline pte_t pte_mkclean(pte_t pte) { (pte).pte_low &= ~_PAGE_DIRTY; return pte; }
static inline pte_t pte_mkold(pte_t pte) { (pte).pte_low &= ~_PAGE_ACCESSED; return pte; }
static inline pte_t pte_wrprotect(pte_t pte) { (pte).pte_low &= ~_PAGE_RW; return pte; }
-static inline pte_t pte_mkread(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
-static inline pte_t pte_mkexec(pte_t pte) { (pte).pte_low |= _PAGE_USER; return pte; }
static inline pte_t pte_mkdirty(pte_t pte) { (pte).pte_low |= _PAGE_DIRTY; return pte; }
static inline pte_t pte_mkyoung(pte_t pte) { (pte).pte_low |= _PAGE_ACCESSED; return pte; }
static inline pte_t pte_mkwrite(pte_t pte) { (pte).pte_low |= _PAGE_RW; return pte; }
-static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= __LARGE_PTE; return pte; }
+static inline pte_t pte_mkhuge(pte_t pte) { (pte).pte_low |= _PAGE_PSE; return pte; }
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level.h>
# include <asm/pgtable-2level.h>
#endif
-static inline int ptep_test_and_clear_dirty(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+#ifndef CONFIG_PARAVIRT
+/*
+ * Rules for using pte_update - it must be called after any PTE update which
+ * has not been done using the set_pte / clear_pte interfaces. It is used by
+ * shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
+ * updates should either be sets, clears, or set_pte_atomic for P->P
+ * transitions, which means this hook should only be called for user PTEs.
+ * This hook implies a P->P protection or access change has taken place, which
+ * requires a subsequent TLB flush. The notification can optionally be delayed
+ * until the TLB flush event by using the pte_update_defer form of the
+ * interface, but care must be taken to assure that the flush happens while
+ * still holding the same page table lock so that the shadow and primary pages
+ * do not become out of sync on SMP.
+ */
+#define pte_update(mm, addr, ptep) do { } while (0)
+#define pte_update_defer(mm, addr, ptep) do { } while (0)
+#endif
+
+/* local pte updates need not use xchg for locking */
+static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
- if (!pte_dirty(*ptep))
- return 0;
- return test_and_clear_bit(_PAGE_BIT_DIRTY, &ptep->pte_low);
+ pte_t res = *ptep;
+
+ /* Pure native function needs no input for mm, addr */
+ native_pte_clear(NULL, 0, ptep);
+ return res;
}
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+/*
+ * We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time.
+ */
+#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+#define ptep_set_access_flags(vma, address, ptep, entry, dirty) \
+({ \
+ int __changed = !pte_same(*(ptep), entry); \
+ if (__changed && dirty) { \
+ (ptep)->pte_low = (entry).pte_low; \
+ pte_update_defer((vma)->vm_mm, (address), (ptep)); \
+ flush_tlb_page(vma, address); \
+ } \
+ __changed; \
+})
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define ptep_test_and_clear_young(vma, addr, ptep) ({ \
+ int __ret = 0; \
+ if (pte_young(*(ptep))) \
+ __ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, \
+ &(ptep)->pte_low); \
+ if (__ret) \
+ pte_update((vma)->vm_mm, addr, ptep); \
+ __ret; \
+})
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+#define ptep_clear_flush_young(vma, address, ptep) \
+({ \
+ int __young; \
+ __young = ptep_test_and_clear_young((vma), (address), (ptep)); \
+ if (__young) \
+ flush_tlb_page(vma, address); \
+ __young; \
+})
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
- if (!pte_young(*ptep))
- return 0;
- return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
+ pte_t pte = native_ptep_get_and_clear(ptep);
+ pte_update(mm, addr, ptep);
+ return pte;
}
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
{
pte_t pte;
if (full) {
- pte = *ptep;
- *ptep = __pte(0);
+ /*
+ * Full address destruction in progress; paravirt does not
+ * care about updates and native needs no locking
+ */
+ pte = native_local_ptep_get_and_clear(ptep);
} else {
pte = ptep_get_and_clear(mm, addr, ptep);
}
return pte;
}
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
{
clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
+ pte_update(mm, addr, ptep);
+}
+
+/*
+ * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
+ *
+ * dst - pointer to pgd range anwhere on a pgd page
+ * src - ""
+ * count - the number of pgds to copy.
+ *
+ * dst and src can be on the same page, but the range must not overlap,
+ * and must not cross a page boundary.
+ */
+static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
+{
+ memcpy(dst, src, count * sizeof(pgd_t));
}
/*
return pte;
}
-#define page_pte(page) page_pte_prot(page, __pgprot(0))
-
#define pmd_large(pmd) \
((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
#define pte_index(address) \
(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
#define pte_offset_kernel(dir, address) \
- ((pte_t *) pmd_page_kernel(*(dir)) + pte_index(address))
+ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
+
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+#define pmd_page_vaddr(pmd) \
+ ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
/*
* Helper function that returns the kernel pagetable entry controlling
static inline int set_kernel_exec(unsigned long vaddr, int enable) { return 0;}
#endif
-extern void noexec_setup(const char *str);
-
#if defined(CONFIG_HIGHPTE)
#define pte_offset_map(dir, address) \
- ((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE0) + pte_index(address))
+ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE0) + pte_index(address))
#define pte_offset_map_nested(dir, address) \
- ((pte_t *)kmap_atomic(pmd_page(*(dir)),KM_PTE1) + pte_index(address))
+ ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)),KM_PTE1) + pte_index(address))
#define pte_unmap(pte) kunmap_atomic(pte, KM_PTE0)
#define pte_unmap_nested(pte) kunmap_atomic(pte, KM_PTE1)
#else
#define pte_unmap_nested(pte) do { } while (0)
#endif
+/* Clear a kernel PTE and flush it from the TLB */
+#define kpte_clear_flush(ptep, vaddr) \
+do { \
+ pte_clear(&init_mm, vaddr, ptep); \
+ __flush_tlb_one(vaddr); \
+} while (0)
+
/*
* The i386 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
- *
- * Also, we only update the dirty/accessed state if we set
- * the dirty bit by hand in the kernel, since the hardware
- * will do the accessed bit for us, and we don't want to
- * race with other CPU's that might be updating the dirty
- * bit at the same time.
*/
#define update_mmu_cache(vma,address,pte) do { } while (0)
-#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
- do { \
- if (__dirty) { \
- (__ptep)->pte_low = (__entry).pte_low; \
- flush_tlb_page(__vma, __address); \
- } \
- } while (0)
+
+void native_pagetable_setup_start(pgd_t *base);
+void native_pagetable_setup_done(pgd_t *base);
+
+#ifndef CONFIG_PARAVIRT
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+ native_pagetable_setup_start(base);
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+ native_pagetable_setup_done(base);
+}
+#endif /* !CONFIG_PARAVIRT */
#endif /* !__ASSEMBLY__ */
#define kern_addr_valid(addr) (1)
#endif /* CONFIG_FLATMEM */
-#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)
-
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-#define __HAVE_ARCH_PTE_SAME
#include <asm-generic/pgtable.h>
#endif /* _I386_PGTABLE_H */