All x86 modes and architectures have very similar pagetable
structures: the page flags, the accessors for testing/setting them,
and the combinations of page flags used for kernel and usermode
mappings are all the same. The main difference is between 32 and
64-bit pagetable entries, with the latter supporting the NX bit.
The most significant difference between the modes/architectures is the
number of levels in the pagetable (4 for 64-bit, 3 for 32-bit/PAE, 2
for non-PAE 32-bit). This accounts for the remaining code in the
various mode-specific headers.
I've tried to avoid changing formatting as much as possible, so that
the code motion is more obvious. A subsequent patch will clean things
up in place.
Signed-off-by: Jeremy Fitzhardinge <[email protected]>
---
include/asm-x86/pgtable-2level.h | 17 -
include/asm-x86/pgtable-3level.h | 38 ----
include/asm-x86/pgtable.h | 345 ++++++++++++++++++++++++++++++++++++++
include/asm-x86/pgtable_32.h | 229 -------------------------
include/asm-x86/pgtable_64.h | 287 ++++++-------------------------
5 files changed, 413 insertions(+), 503 deletions(-)
===================================================================
--- a/include/asm-x86/pgtable-2level.h
+++ b/include/asm-x86/pgtable-2level.h
@@ -15,25 +15,24 @@ static inline void native_set_pte(pte_t
{
*ptep = pte;
}
+
static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep , pte_t pte)
{
native_set_pte(ptep, pte);
}
+
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
*pmdp = pmd;
}
-#ifndef CONFIG_PARAVIRT
-#define set_pte(pteptr, pteval) native_set_pte(pteptr, pteval)
-#define set_pte_at(mm,addr,ptep,pteval) native_set_pte_at(mm, addr, ptep, pteval)
-#define set_pmd(pmdptr, pmdval) native_set_pmd(pmdptr, pmdval)
-#endif
+#undef set_pte_atomic
#define set_pte_atomic(pteptr, pteval) set_pte(pteptr,pteval)
#define set_pte_present(mm,addr,ptep,pteval) set_pte_at(mm,addr,ptep,pteval)
#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
+#undef pmd_clear
#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp)
@@ -50,12 +49,6 @@ static inline pte_t native_ptep_get_and_
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
#endif
-#define pte_page(x) pfn_to_page(pte_pfn(x))
-#define pte_none(x) (!(x).pte_low)
-#define pte_pfn(x) (pte_val(x) >> PAGE_SHIFT)
-#define pfn_pte(pfn, prot) __pte(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot) __pmd(((pfn) << PAGE_SHIFT) | pgprot_val(prot))
-
/*
* All present pages are kernel-executable:
*/
@@ -63,6 +56,8 @@ static inline int pte_exec_kernel(pte_t
{
return 1;
}
+
+#define __supported_pte_mask (~0ul)
/*
* Bits 0, 6 and 7 are taken, split up the 29 bits of offset
===================================================================
--- a/include/asm-x86/pgtable-3level.h
+++ b/include/asm-x86/pgtable-3level.h
@@ -94,17 +94,6 @@ static inline void native_pmd_clear(pmd_
*(tmp + 1) = 0;
}
-#ifndef CONFIG_PARAVIRT
-#define set_pte(ptep, pte) native_set_pte(ptep, pte)
-#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
-#define set_pte_present(mm, addr, ptep, pte) native_set_pte_present(mm, addr, ptep, pte)
-#define set_pte_atomic(ptep, pte) native_set_pte_atomic(ptep, pte)
-#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
-#define set_pud(pudp, pud) native_set_pud(pudp, pud)
-#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
-#define pmd_clear(pmd) native_pmd_clear(pmd)
-#endif
-
/*
* Pentium-II erratum A13: in PAE mode we explicitly have to flush
* the TLB via cr3 if the top-level pgd is changed...
@@ -119,10 +108,6 @@ static inline void pud_clear (pud_t * pu
#define pud_page_vaddr(pud) \
((unsigned long) __va(pud_val(pud) & PAGE_MASK))
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *) pud_page(*(pud)) + \
- pmd_index(address))
#ifdef CONFIG_SMP
static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
@@ -146,31 +131,8 @@ static inline int pte_same(pte_t a, pte_
return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
}
-#define pte_page(x) pfn_to_page(pte_pfn(x))
-
-static inline int pte_none(pte_t pte)
-{
- return !pte.pte_low && !pte.pte_high;
-}
-
-static inline unsigned long pte_pfn(pte_t pte)
-{
- return pte_val(pte) >> PAGE_SHIFT;
-}
-
extern unsigned long long __supported_pte_mask;
-static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
-{
- return __pte((((unsigned long long)page_nr << PAGE_SHIFT) |
- pgprot_val(pgprot)) & __supported_pte_mask);
-}
-
-static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
-{
- return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) |
- pgprot_val(pgprot)) & __supported_pte_mask);
-}
/*
* Bits 0, 6 and 7 are taken in the low part of the pte,
===================================================================
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -1,5 +1,350 @@
+#ifndef _ASM_X86_PGTABLE_H
+#define _ASM_X86_PGTABLE_H
+
+#include <linux/const.h>
+#include <asm/page.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+void paging_init(void);
+
+#endif /* !__ASSEMBLY__ */
+
+
+/*
+ * _PAGE_PSE set in the page directory entry just means that
+ * the page directory entry points directly to a 4MB-aligned block of
+ * memory.
+ */
+#define _PAGE_BIT_PRESENT 0
+#define _PAGE_BIT_RW 1
+#define _PAGE_BIT_USER 2
+#define _PAGE_BIT_PWT 3
+#define _PAGE_BIT_PCD 4
+#define _PAGE_BIT_ACCESSED 5
+#define _PAGE_BIT_DIRTY 6
+#define _PAGE_BIT_FILE 6
+#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
+#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
+#define _PAGE_BIT_UNUSED2 10
+#define _PAGE_BIT_UNUSED3 11
+#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
+
+
+#define _PAGE_PRESENT (_AC(1, UL) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW (_AC(1, UL) << _PAGE_BIT_RW)
+#define _PAGE_USER (_AC(1, UL) << _PAGE_BIT_USER)
+#define _PAGE_PWT (_AC(1, UL) << _PAGE_BIT_PWT)
+#define _PAGE_PCD (_AC(1, UL) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED (_AC(1, UL) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY (_AC(1, UL) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE (_AC(1, UL) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL (_AC(1, UL) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1 (_AC(1, UL) << _PAGE_BIT_UNUSED1)
+#define _PAGE_UNUSED2 (_AC(1, UL) << _PAGE_BIT_UNUSED2)
+#define _PAGE_UNUSED3 (_AC(1, UL) << _PAGE_BIT_UNUSED3)
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+#define _PAGE_NX (_AC(1, ULL) << _PAGE_BIT_NX)
+#else
+#define _PAGE_NX 0
+#endif
+
+/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE _PAGE_DIRTY /* nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_PROTNONE _PAGE_PSE /* if the user mapped it with PROT_NONE;
+ pte_present gives true */
+
+#ifndef __ASSEMBLY__
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; }
+static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_huge(pte_t pte) { return pte_val(pte) & _PAGE_PSE; }
+
+#endif /* __ASSEMBLY__ */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define set_pte(ptep, pte) native_set_pte(ptep, pte)
+#define set_pte_at(mm, addr, ptep, pte) \
+ native_set_pte_at(mm, addr, ptep, pte)
+
+#define set_pte_present(mm, addr, ptep, pte) \
+ native_set_pte_present(mm, addr, ptep, pte)
+#define set_pte_atomic(ptep, pte) \
+ native_set_pte_atomic(ptep, pte)
+
+#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
+#define set_pud(pudp, pud) native_set_pud(pudp, pud)
+#define pgd_clear(pgd) native_pgd_clear(pgd)
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pud_clear(pud) native_pud_clear(pud)
+#endif
+
+#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
+#define pmd_clear(pmd) native_pmd_clear(pmd)
+
+#define pte_update(mm, addr, ptep) do { } while (0)
+#define pte_update_defer(mm, addr, ptep) do { } while (0)
+
+#endif /* CONFIG_PARAVIRT */
+
#ifdef CONFIG_X86_32
# include "pgtable_32.h"
#else
# include "pgtable_64.h"
#endif
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define PUD_SIZE (_AC(1,UL) << PUD_SHIFT)
+#define PUD_MASK (~(PUD_SIZE-1))
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define PMD_SIZE (_AC(1,UL) << PMD_SHIFT)
+#define PMD_MASK (~(PMD_SIZE-1))
+#endif
+
+#define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT)
+#define PGDIR_MASK (~(PGDIR_SIZE-1))
+
+#define USER_PTRS_PER_PGD ((TASK_SIZE-1)/PGDIR_SIZE+1)
+
+#define FIRST_USER_ADDRESS 0
+
+#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
+#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
+
+#define _PAGE_TABLE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK \
+ (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_NONE \
+ __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+
+#define PAGE_SHARED_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY \
+ PAGE_COPY_NOEXEC
+#define PAGE_READONLY \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC \
+ __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#endif /* __ASSEMBLY__ */
+
+#define _PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
+#define _PAGE_KERNEL_EXEC \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+
+#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 | _PAGE_PWT)
+#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE)
+#define __PAGE_KERNEL_VSYSCALL \
+ (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define __PAGE_KERNEL_VSYSCALL_NOCACHE \
+ (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD | _PAGE_PWT)
+
+
+#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
+#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
+#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+
+/*
+ * Without NX, the i386 can't do page protection for execute, and
+ * considers that the same are read. Also, write permissions imply
+ * read permissions. This is the closest we can get..
+ */
+#define __P000 PAGE_NONE
+#define __P001 PAGE_READONLY
+#define __P010 PAGE_COPY
+#define __P011 PAGE_COPY
+#define __P100 PAGE_READONLY_EXEC
+#define __P101 PAGE_READONLY_EXEC
+#define __P110 PAGE_COPY_EXEC
+#define __P111 PAGE_COPY_EXEC
+
+#define __S000 PAGE_NONE
+#define __S001 PAGE_READONLY
+#define __S010 PAGE_SHARED
+#define __S011 PAGE_SHARED
+#define __S100 PAGE_READONLY_EXEC
+#define __S101 PAGE_READONLY_EXEC
+#define __S110 PAGE_SHARED_EXEC
+#define __S111 PAGE_SHARED_EXEC
+
+#ifndef __ASSEMBLY__
+
+static inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
+static inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
+static inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
+static inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
+static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
+static inline pte_t pte_mkhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
+static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
+
+#ifndef __PAGETABLE_PUD_FOLDED
+static inline bool pgd_bad(pgd_t pgd)
+{
+ return (pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+
+static inline bool pud_bad(pud_t pud)
+{
+ return (pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+#endif
+
+static inline bool pmd_bad(pmd_t pmd)
+{
+ return (pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+
+/* Change flags of a PTE */
+static inline pte_t pte_modify(pte_t pte_old, pgprot_t newprot)
+{
+ pteval_t pte = pte_val(pte_old);
+ pte &= _PAGE_CHG_MASK;
+ pte |= pgprot_val(newprot);
+ pte &= __supported_pte_mask;
+ return __pte(pte);
+}
+
+/* page, protection -> pte */
+#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline int pmd_large(pmd_t pte)
+{
+ return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+ ((_PAGE_PSE | _PAGE_PRESENT));
+}
+
+/* PMD - Level 2 access */
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PTE_MASK))
+#define pmd_page(pmd) (pfn_to_page(pmd_val(pmd) >> PAGE_SHIFT))
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
+{
+ return __pmd((((unsigned long long)page_nr << PAGE_SHIFT) |
+ pgprot_val(pgprot)) & __supported_pte_mask);
+}
+
+#ifndef __PAGETABLE_PMD_FOLDED
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(dir, address) \
+ ((pmd_t *) pud_page_vaddr(*(dir)) + pmd_index(address))
+
+#define pmd_pfn(x) ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
+
+#endif /* PAGETABLE_PMD_FOLDED */
+
+/* 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)
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address) \
+ (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) \
+ ((pte_t *) pmd_page_vaddr(*(dir)) + pte_index(address))
+
+#define pte_none(x) (!pte_val(x))
+#define pte_present(x) (pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+#define pages_to_mb(x) ((unsigned long)((x) >> (20-PAGE_SHIFT)))
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+#define pte_pfn(x) ((unsigned long)((pte_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT))
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+ pteval_t pte;
+ pte = (page_nr << PAGE_SHIFT);
+ pte |= pgprot_val(pgprot);
+ pte &= __supported_pte_mask;
+ return __pte(pte);
+}
+
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ pte_t pte = native_ptep_get_and_clear(ptep);
+ pte_update(mm, addr, ptep);
+ return pte;
+}
+
+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) {
+ /*
+ * 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_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+
+#include <asm-generic/pgtable.h>
+
+#endif /* __ASSEMBLY__ */
+#endif /* _ASM_X86_PGTABLE_H */
===================================================================
--- a/include/asm-x86/pgtable_32.h
+++ b/include/asm-x86/pgtable_32.h
@@ -25,12 +25,6 @@ struct mm_struct;
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 struct kmem_cache *pmd_cache;
extern spinlock_t pgd_lock;
@@ -39,8 +33,8 @@ void check_pgt_cache(void);
void pmd_ctor(struct kmem_cache *, void *);
void pgtable_cache_init(void);
-void paging_init(void);
+extern unsigned long long __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
/*
* The Linux x86 paging architecture is 'compile-time dual-mode', it
@@ -49,20 +43,9 @@ void paging_init(void);
*/
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level-defs.h>
-# define PMD_SIZE (1UL << PMD_SHIFT)
-# define PMD_MASK (~(PMD_SIZE-1))
#else
# include <asm/pgtable-2level-defs.h>
#endif
-
-#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
-
-#define USER_PTRS_PER_PGD (TASK_SIZE/PGDIR_SIZE)
-#define FIRST_USER_ADDRESS 0
-
-#define USER_PGD_PTRS (PAGE_OFFSET >> PGDIR_SHIFT)
-#define KERNEL_PGD_PTRS (PTRS_PER_PGD-USER_PGD_PTRS)
#define TWOLEVEL_PGDIR_SHIFT 22
#define BOOT_USER_PGD_PTRS (__PAGE_OFFSET >> TWOLEVEL_PGDIR_SHIFT)
@@ -85,113 +68,6 @@ void paging_init(void);
#endif
/*
- * _PAGE_PSE set in the page directory entry just means that
- * the page directory entry points directly to a 4MB-aligned block of
- * memory.
- */
-#define _PAGE_BIT_PRESENT 0
-#define _PAGE_BIT_RW 1
-#define _PAGE_BIT_USER 2
-#define _PAGE_BIT_PWT 3
-#define _PAGE_BIT_PCD 4
-#define _PAGE_BIT_ACCESSED 5
-#define _PAGE_BIT_DIRTY 6
-#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page, Pentium+, if present.. */
-#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
-#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
-#define _PAGE_BIT_UNUSED2 10
-#define _PAGE_BIT_UNUSED3 11
-#define _PAGE_BIT_NX 63
-
-#define _PAGE_PRESENT 0x001
-#define _PAGE_RW 0x002
-#define _PAGE_USER 0x004
-#define _PAGE_PWT 0x008
-#define _PAGE_PCD 0x010
-#define _PAGE_ACCESSED 0x020
-#define _PAGE_DIRTY 0x040
-#define _PAGE_PSE 0x080 /* 4 MB (or 2MB) page, Pentium+, if present.. */
-#define _PAGE_GLOBAL 0x100 /* Global TLB entry PPro+ */
-#define _PAGE_UNUSED1 0x200 /* available for programmer */
-#define _PAGE_UNUSED2 0x400
-#define _PAGE_UNUSED3 0x800
-
-/* If _PAGE_PRESENT is clear, we use these: */
-#define _PAGE_FILE 0x040 /* nonlinear file mapping, saved PTE; unset:swap */
-#define _PAGE_PROTNONE 0x080 /* if the user mapped it with PROT_NONE;
- pte_present gives true */
-#ifdef CONFIG_X86_PAE
-#define _PAGE_NX (1ULL<<_PAGE_BIT_NX)
-#else
-#define _PAGE_NX 0
-#endif
-
-#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define PAGE_NONE \
- __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED \
- __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-
-#define PAGE_SHARED_EXEC \
- __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY_NOEXEC \
- __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_COPY_EXEC \
- __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY \
- PAGE_COPY_NOEXEC
-#define PAGE_READONLY \
- __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_READONLY_EXEC \
- __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-
-#define _PAGE_KERNEL \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
-#define _PAGE_KERNEL_EXEC \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-
-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 | _PAGE_PWT)
-#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)
-
-/*
- * The i386 can't do page protection for execute, and considers that
- * the same are read. Also, write permissions imply read permissions.
- * This is the closest we can get..
- */
-#define __P000 PAGE_NONE
-#define __P001 PAGE_READONLY
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY_EXEC
-#define __P101 PAGE_READONLY_EXEC
-#define __P110 PAGE_COPY_EXEC
-#define __P111 PAGE_COPY_EXEC
-
-#define __S000 PAGE_NONE
-#define __S001 PAGE_READONLY
-#define __S010 PAGE_SHARED
-#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
-#define __S101 PAGE_READONLY_EXEC
-#define __S110 PAGE_SHARED_EXEC
-#define __S111 PAGE_SHARED_EXEC
-
-/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
* done without a 'access_ok(VERIFY_WRITE,..)'
@@ -201,37 +77,6 @@ extern unsigned long long __PAGE_KERNEL,
/* The boot page tables (all created as a single array) */
extern unsigned long pg0[];
-#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-/* 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_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-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 & _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_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_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 |= _PAGE_PSE; return pte; }
#ifdef CONFIG_X86_PAE
# include <asm/pgtable-3level.h>
@@ -307,30 +152,6 @@ static inline pte_t native_local_ptep_ge
__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)
-{
- 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) {
- /*
- * 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)
{
@@ -365,27 +186,6 @@ static inline void clone_pgd_range(pgd_t
* and a page entry and page directory to the page they refer to.
*/
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
- pte.pte_low &= _PAGE_CHG_MASK;
- pte.pte_low |= pgprot_val(newprot);
-#ifdef CONFIG_X86_PAE
- /*
- * Chop off the NX bit (if present), and add the NX portion of
- * the newprot (if present):
- */
- pte.pte_high &= ~(1 << (_PAGE_BIT_NX - 32));
- pte.pte_high |= (pgprot_val(newprot) >> 32) & \
- (__supported_pte_mask >> 32);
-#endif
- return pte;
-}
-
-#define pmd_large(pmd) \
-((pmd_val(pmd) & (_PAGE_PSE|_PAGE_PRESENT)) == (_PAGE_PSE|_PAGE_PRESENT))
-
/*
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
*
@@ -406,31 +206,6 @@ static inline pte_t pte_modify(pte_t pte
* of a process's
*/
#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-#define pmd_index(address) \
- (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this macro returns the index of the entry in the pte page which would
- * control the given virtual address
- */
-#define pte_index(address) \
- (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, 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
@@ -510,6 +285,4 @@ static inline void paravirt_pagetable_se
#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
remap_pfn_range(vma, vaddr, pfn, size, prot)
-#include <asm-generic/pgtable.h>
-
#endif /* _I386_PGTABLE_H */
===================================================================
--- a/include/asm-x86/pgtable_64.h
+++ b/include/asm-x86/pgtable_64.h
@@ -21,17 +21,14 @@ extern unsigned long __supported_pte_mas
#define swapper_pg_dir init_level4_pgt
-extern void paging_init(void);
extern void clear_kernel_mapping(unsigned long addr, unsigned long size);
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+#endif /* !__ASSEMBLY__ */
-#endif /* !__ASSEMBLY__ */
+#define __PAGE_KERNEL \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX | _PAGE_GLOBAL)
+#define __PAGE_KERNEL_EXEC \
+ (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
@@ -71,51 +68,71 @@ extern unsigned long empty_zero_page[PAG
#define pgd_none(x) (!pgd_val(x))
#define pud_none(x) (!pud_val(x))
-static inline void set_pte(pte_t *dst, pte_t val)
+struct mm_struct;
+
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *xp)
{
- *dst = val;
-}
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
-
-static inline void set_pmd(pmd_t *dst, pmd_t val)
-{
- *dst = val;
-}
-
-static inline void set_pud(pud_t *dst, pud_t val)
-{
- *dst = val;
+ *xp = native_make_pte(0);
}
-static inline void pud_clear (pud_t *pud)
+/* local pte updates need not use xchg for locking */
+static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
- set_pud(pud, __pud(0));
+ pte_t res = *ptep;
+
+ /* Pure native function needs no input for mm, addr */
+ native_pte_clear(NULL, 0, ptep);
+ return res;
}
-static inline void set_pgd(pgd_t *dst, pgd_t val)
+static inline pte_t native_ptep_get_and_clear(pte_t *xp)
{
- *dst = val;
-}
-
-static inline void pgd_clear (pgd_t * pgd)
-{
- set_pgd(pgd, __pgd(0));
+#ifdef CONFIG_SMP
+ return native_make_pte(xchg(&xp->pte, 0));
+#else
+ return native_local_ptep_get_and_clear(xp);
+#endif
}
-#define ptep_get_and_clear(mm,addr,xp) __pte(xchg(&(xp)->pte, 0))
+static inline void native_set_pte(pte_t *ptep , pte_t pte)
+{
+ *ptep = pte;
+}
-struct mm_struct;
+static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep , pte_t pte)
+{
+ native_set_pte(ptep, pte);
+}
-static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long addr, pte_t *ptep, int full)
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
- pte_t pte;
- if (full) {
- pte = *ptep;
- *ptep = __pte(0);
- } else {
- pte = ptep_get_and_clear(mm, addr, ptep);
- }
- return pte;
+ *pmdp = pmd;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+ native_set_pmd(pmd, native_make_pmd(0));
+}
+
+static inline void native_set_pud(pud_t *pudp, pud_t pud)
+{
+ *pudp = pud;
+}
+
+static inline void native_pud_clear(pud_t *pud)
+{
+ native_set_pud(pud, native_make_pud(0));
+}
+
+static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+ *pgdp = pgd;
+}
+
+static inline void native_pgd_clear(pgd_t * pgd)
+{
+ native_set_pgd(pgd, native_make_pgd(0));
}
#define pte_same(a, b) ((a).pte == (b).pte)
@@ -124,16 +141,6 @@ static inline pte_t ptep_get_and_clear_f
#endif /* !__ASSEMBLY__ */
-#define PMD_SIZE (_AC(1,UL) << PMD_SHIFT)
-#define PMD_MASK (~(PMD_SIZE-1))
-#define PUD_SIZE (_AC(1,UL) << PUD_SHIFT)
-#define PUD_MASK (~(PUD_SIZE-1))
-#define PGDIR_SIZE (_AC(1,UL) << PGDIR_SHIFT)
-#define PGDIR_MASK (~(PGDIR_SIZE-1))
-
-#define USER_PTRS_PER_PGD ((TASK_SIZE-1)/PGDIR_SIZE+1)
-#define FIRST_USER_ADDRESS 0
-
#define MAXMEM _AC(0x3fffffffffff, UL)
#define VMALLOC_START _AC(0xffffc20000000000, UL)
#define VMALLOC_END _AC(0xffffe1ffffffffff, UL)
@@ -141,150 +148,6 @@ static inline pte_t ptep_get_and_clear_f
#define MODULES_VADDR _AC(0xffffffff88000000, UL)
#define MODULES_END _AC(0xfffffffffff00000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
-
-#define _PAGE_BIT_PRESENT 0
-#define _PAGE_BIT_RW 1
-#define _PAGE_BIT_USER 2
-#define _PAGE_BIT_PWT 3
-#define _PAGE_BIT_PCD 4
-#define _PAGE_BIT_ACCESSED 5
-#define _PAGE_BIT_DIRTY 6
-#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
-#define _PAGE_BIT_FILE 6
-#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
-#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
-
-#define _PAGE_PRESENT (_AC(1, UL)<<_PAGE_BIT_PRESENT)
-#define _PAGE_RW (_AC(1, UL)<<_PAGE_BIT_RW)
-#define _PAGE_USER (_AC(1, UL)<<_PAGE_BIT_USER)
-#define _PAGE_PWT (_AC(1, UL)<<_PAGE_BIT_PWT)
-#define _PAGE_PCD (_AC(1, UL)<<_PAGE_BIT_PCD)
-#define _PAGE_ACCESSED (_AC(1, UL)<<_PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY (_AC(1, UL)<<_PAGE_BIT_DIRTY)
-/* 2MB page */
-#define _PAGE_PSE (_AC(1, UL)<<_PAGE_BIT_PSE)
-/* nonlinear file mapping, saved PTE; unset:swap */
-#define _PAGE_FILE (_AC(1, UL)<<_PAGE_BIT_FILE)
-/* Global TLB entry */
-#define _PAGE_GLOBAL (_AC(1, UL)<<_PAGE_BIT_GLOBAL)
-
-#define _PAGE_PROTNONE 0x080 /* If not present */
-#define _PAGE_NX (_AC(1, UL)<<_PAGE_BIT_NX)
-
-#define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define _PAGE_CHG_MASK (PTE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define PAGE_NONE __pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_COPY PAGE_COPY_NOEXEC
-#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_READONLY __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define __PAGE_KERNEL \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
-#define __PAGE_KERNEL_EXEC \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-#define __PAGE_KERNEL_NOCACHE \
- (_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_PCD | _PAGE_PWT | _PAGE_ACCESSED | _PAGE_NX)
-#define __PAGE_KERNEL_RO \
- (_PAGE_PRESENT | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_NX)
-#define __PAGE_KERNEL_VSYSCALL \
- (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define __PAGE_KERNEL_VSYSCALL_NOCACHE \
- (_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_LARGE \
- (__PAGE_KERNEL | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_EXEC \
- (__PAGE_KERNEL_EXEC | _PAGE_PSE)
-
-#define MAKE_GLOBAL(x) __pgprot((x) | _PAGE_GLOBAL)
-
-#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
-#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_VSYSCALL32 __pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
-
-/* xwr */
-#define __P000 PAGE_NONE
-#define __P001 PAGE_READONLY
-#define __P010 PAGE_COPY
-#define __P011 PAGE_COPY
-#define __P100 PAGE_READONLY_EXEC
-#define __P101 PAGE_READONLY_EXEC
-#define __P110 PAGE_COPY_EXEC
-#define __P111 PAGE_COPY_EXEC
-
-#define __S000 PAGE_NONE
-#define __S001 PAGE_READONLY
-#define __S010 PAGE_SHARED
-#define __S011 PAGE_SHARED
-#define __S100 PAGE_READONLY_EXEC
-#define __S101 PAGE_READONLY_EXEC
-#define __S110 PAGE_SHARED_EXEC
-#define __S111 PAGE_SHARED_EXEC
-
-#ifndef __ASSEMBLY__
-
-static inline unsigned long pgd_bad(pgd_t pgd)
-{
- return pgd_val(pgd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
-}
-
-static inline unsigned long pud_bad(pud_t pud)
-{
- return pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
-}
-
-static inline unsigned long pmd_bad(pmd_t pmd)
-{
- return pmd_val(pmd) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER);
-}
-
-#define pte_none(x) (!pte_val(x))
-#define pte_present(x) (pte_val(x) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT)) /* FIXME: is this right? */
-#define pte_page(x) pfn_to_page(pte_pfn(x))
-#define pte_pfn(x) ((pte_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
-
-static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
-{
- pteval_t pte;
- pte = (page_nr << PAGE_SHIFT);
- pte |= pgprot_val(pgprot);
- pte &= __supported_pte_mask;
- return __pte(pte);
-}
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-#define __LARGE_PTE (_PAGE_PSE|_PAGE_PRESENT)
-static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; }
-static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_huge(pte_t pte) { return pte_val(pte) & _PAGE_PSE; }
-
-static inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
-static inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
-static inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
-static inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
-static inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
-static inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
-static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
-static inline pte_t pte_mkhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
-static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
struct vm_area_struct;
@@ -300,15 +163,11 @@ static inline void ptep_set_wrprotect(st
clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
}
+#ifndef __ASSEMBLY__
/*
* Macro to mark a page protection value as "uncacheable".
*/
#define pgprot_noncached(prot) (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))
-
-static inline int pmd_large(pmd_t pte) {
- return (pmd_val(pte) & __LARGE_PTE) == __LARGE_PTE;
-}
-
/*
* Conversion functions: convert a page and protection to a page entry,
@@ -326,7 +185,7 @@ static inline int pmd_large(pmd_t pte) {
#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
#define mk_kernel_pgd(address) ((pgd_t){ (address) | _KERNPG_TABLE })
-/* PUD - Level3 access */
+/* PUD - Level 3 access */
/* to find an entry in a page-table-directory. */
#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PHYSICAL_PAGE_MASK))
#define pud_page(pud) (pfn_to_page(pud_val(pud) >> PAGE_SHIFT))
@@ -341,36 +200,14 @@ static inline int pmd_large(pmd_t pte) {
#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
#define pmd_offset(dir, address) ((pmd_t *) pud_page_vaddr(*(dir)) + \
pmd_index(address))
-#define pmd_none(x) (!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 pfn_pmd(nr,prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val(prot)))
-#define pmd_pfn(x) ((pmd_val(x) & __PHYSICAL_MASK) >> PAGE_SHIFT)
#define pte_to_pgoff(pte) ((pte_val(pte) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { ((off) << PAGE_SHIFT) | _PAGE_FILE })
#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
/* PTE - Level 1 access. */
-
-/* page, protection -> pte */
-#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
-/* Change flags of a PTE */
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
- pteval_t val = pte_val(pte);
- val &= _PAGE_CHG_MASK;
- val |= pgprot_val(newprot);
- val &= __supported_pte_mask;
- return __pte(val);
-}
-
-#define pte_index(address) \
- (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
- pte_index(address))
-
/* x86-64 always has all page tables mapped. */
#define pte_offset_map(dir,address) pte_offset_kernel(dir,address)
#define pte_offset_map_nested(dir,address) pte_offset_kernel(dir,address)
@@ -427,11 +264,9 @@ pte_t *lookup_address(unsigned long addr
(((o) & (1UL << (__VIRTUAL_MASK_SHIFT-1))) ? ((o) | (~__VIRTUAL_MASK)) : (o))
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#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 /* !__ASSEMBLY__ */
#endif /* _X86_64_PGTABLE_H */
--
On Wed, Dec 19, 2007 at 02:35:36PM -0800, Jeremy Fitzhardinge wrote:
> +static inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
> +static inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
> +static inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
> +static inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
> +static inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
> +static inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
> +static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
> +static inline pte_t pte_mkhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
> +static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
Is set_pte() really supposed to be used here? pte_val() and __pte()
are already hooked by paravirt_ops if needed, and it looks like we
don't want to call paravirt_ops set_pte() here.
I don't know if I understood fully the semantics of set_pte(), but
it seems that the paravirt_ops implementations expect set_pte() to be
called for PTEs that are actually inside existing pagetables (and not
for short-lived stack variables, like on this case).
Was this tested under Xen and/or VMI?
--
Eduardo
Eduardo Habkost wrote:
> On Wed, Dec 19, 2007 at 02:35:36PM -0800, Jeremy Fitzhardinge wrote:
>
>> +static inline pte_t pte_mkclean(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_DIRTY)); return pte; }
>> +static inline pte_t pte_mkold(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_ACCESSED)); return pte; }
>> +static inline pte_t pte_wrprotect(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_RW)); return pte; }
>> +static inline pte_t pte_mkexec(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_NX)); return pte; }
>> +static inline pte_t pte_mkdirty(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_DIRTY)); return pte; }
>> +static inline pte_t pte_mkyoung(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_ACCESSED)); return pte; }
>> +static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_RW)); return pte; }
>> +static inline pte_t pte_mkhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) | _PAGE_PSE)); return pte; }
>> +static inline pte_t pte_clrhuge(pte_t pte) { set_pte(&pte, __pte(pte_val(pte) & ~_PAGE_PSE)); return pte; }
>>
>
>
> Is set_pte() really supposed to be used here? pte_val() and __pte()
> are already hooked by paravirt_ops if needed, and it looks like we
> don't want to call paravirt_ops set_pte() here.
>
No, you're right. That looks pretty stupid. It will work, but it's
clearly sub-optimal.
> I don't know if I understood fully the semantics of set_pte(), but
> it seems that the paravirt_ops implementations expect set_pte() to be
> called for PTEs that are actually inside existing pagetables (and not
> for short-lived stack variables, like on this case).
>
> Was this tested under Xen and/or VMI?
>
Yes, Xen. It's always OK to use set_pte on something that isn't
actually part of a pagetable, since it can be used on pagetables which
are under construction. But it may end up doing too much work.
J