[PATCH 11/25][V3] native versions for set pagetables

From: Glauber de Oliveira Costa
Date: Wed Aug 15 2007 - 08:54:55 EST


This patch turns the set_p{te,md,ud,gd} functions into their
native_ versions. There is no need to patch any caller.

Also, it adds pte_update() and pte_update_defer() calls whenever
we modify a page table entry. This last part was coded to match
i386 as close as possible.

Pieces of the header are moved to below the #ifdef CONFIG_PARAVIRT
site, as they are users of the newly defined set_* macros.

Signed-off-by: Glauber de Oliveira Costa <gcosta@xxxxxxxxxx>
Signed-off-by: Steven Rostedt <rostedt@xxxxxxxxxxx>
---
include/asm-x86_64/pgtable.h | 152 ++++++++++++++++++++++++-----------------
1 files changed, 89 insertions(+), 63 deletions(-)

diff --git a/include/asm-x86_64/pgtable.h b/include/asm-x86_64/pgtable.h
index c9d8764..dd572a2 100644
--- a/include/asm-x86_64/pgtable.h
+++ b/include/asm-x86_64/pgtable.h
@@ -57,55 +57,77 @@ extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
*/
#define PTRS_PER_PTE 512

-#ifndef __ASSEMBLY__
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else

-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
-#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
-#define pud_ERROR(e) \
- printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e))
-#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+#define set_pte native_set_pte
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+#define set_pmd native_set_pmd
+#define set_pud native_set_pud
+#define set_pgd native_set_pgd
+#define pte_clear(mm,addr,xp) do { set_pte_at(mm, addr, xp, __pte(0)); } while (0)
+#define pmd_clear(xp) do { set_pmd(xp, __pmd(0)); } while (0)
+#define pud_clear native_pud_clear
+#define pgd_clear native_pgd_clear
+#define pte_update(mm, addr, ptep) do { } while (0)
+#define pte_update_defer(mm, addr, ptep) do { } while (0)

-#define pgd_none(x) (!pgd_val(x))
-#define pud_none(x) (!pud_val(x))
+#endif
+
+#ifndef __ASSEMBLY__

-static inline void set_pte(pte_t *dst, pte_t val)
+static inline void native_set_pte(pte_t *dst, pte_t val)
{
- pte_val(*dst) = pte_val(val);
+ dst->pte = pte_val(val);
}
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)

-static inline void set_pmd(pmd_t *dst, pmd_t val)
+
+static inline void native_set_pmd(pmd_t *dst, pmd_t val)
{
- pmd_val(*dst) = pmd_val(val);
+ dst->pmd = pmd_val(val);
}

-static inline void set_pud(pud_t *dst, pud_t val)
+static inline void native_set_pud(pud_t *dst, pud_t val)
{
- pud_val(*dst) = pud_val(val);
+ dst->pud = pud_val(val);
}

-static inline void pud_clear (pud_t *pud)
+static inline void native_set_pgd(pgd_t *dst, pgd_t val)
{
- set_pud(pud, __pud(0));
+ dst->pgd = pgd_val(val);
}
-
-static inline void set_pgd(pgd_t *dst, pgd_t val)
+static inline void native_pud_clear (pud_t *pud)
{
- pgd_val(*dst) = pgd_val(val);
-}
+ set_pud(pud, __pud(0));
+}

-static inline void pgd_clear (pgd_t * pgd)
+static inline void native_pgd_clear (pgd_t * pgd)
{
set_pgd(pgd, __pgd(0));
}

-#define ptep_get_and_clear(mm,addr,xp) __pte(xchg(&(xp)->pte, 0))
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), pte_val(e))
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
+#define pud_ERROR(e) \
+ printk("%s:%d: bad pud %p(%016lx).\n", __FILE__, __LINE__, &(e), pud_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
+
+#define pgd_none(x) (!pgd_val(x))
+#define pud_none(x) (!pud_val(x))

struct mm_struct;

+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ pte_t pte = __pte(xchg(&ptep->pte, 0));
+ 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;
@@ -245,7 +267,6 @@ static inline unsigned long pmd_bad(pmd_t pmd)

#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? */
@@ -254,11 +275,11 @@ static inline unsigned long pmd_bad(pmd_t pmd)

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
- pte_t pte;
- pte_val(pte) = (page_nr << PAGE_SHIFT);
- pte_val(pte) |= pgprot_val(pgprot);
- pte_val(pte) &= __supported_pte_mask;
- return pte;
+ unsigned long pte;
+ pte = (page_nr << PAGE_SHIFT);
+ pte |= pgprot_val(pgprot);
+ pte &= __supported_pte_mask;
+ return __pte(pte);
}

/*
@@ -282,30 +303,6 @@ static inline pte_t pte_mkwrite(pte_t pte) { set_pte(&pte, __pte(pte_val(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;
-
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
-{
- if (!pte_young(*ptep))
- return 0;
- return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
-}
-
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
- clear_bit(_PAGE_BIT_RW, &ptep->pte);
-}
-
-/*
- * 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,
* and a page entry and page directory to the page they refer to.
@@ -339,7 +336,6 @@ static inline int pmd_large(pmd_t pte) {
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)

@@ -352,14 +348,43 @@ static inline int pmd_large(pmd_t pte) {
/* page, protection -> pte */
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
#define mk_pte_huge(entry) (pte_val(entry) |= _PAGE_PRESENT | _PAGE_PSE)
-
+
+struct vm_area_struct;
+
+#include <linux/mm.h>
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+ int ret = 0;
+ if (!pte_young(*ptep))
+ return 0;
+ ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte);
+ pte_update(vma->vm_mm, addr, ptep);
+ return ret;
+}
+
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+ clear_bit(_PAGE_BIT_RW, &ptep->pte);
+ pte_update(mm, addr, ptep);
+}
+
+/*
+ * 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;
+}
+
/* Change flags of a PTE */
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+static inline pte_t pte_modify(pte_t pte_old, pgprot_t newprot)
{
- pte_val(pte) &= _PAGE_CHG_MASK;
- pte_val(pte) |= pgprot_val(newprot);
- pte_val(pte) &= __supported_pte_mask;
- return pte;
+ unsigned long pte = pte_val(pte_old);
+ pte &= _PAGE_CHG_MASK;
+ pte |= pgprot_val(newprot);
+ pte &= __supported_pte_mask;
+ return __pte(pte);
}

#define pte_index(address) \
@@ -386,6 +411,7 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
int __changed = !pte_same(*(__ptep), __entry); \
if (__changed && __dirty) { \
set_pte(__ptep, __entry); \
+ pte_update_defer((__vma)->vm_mm, (__address), (__ptep)); \
flush_tlb_page(__vma, __address); \
} \
__changed; \
--
1.4.4.2

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/