* Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
*/
-#define pte_ERROR(e) \
- printk("%s:%d: bad pte %p(%08lx%08lx).\n", __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
-#define pmd_ERROR(e) \
- printk("%s:%d: bad pmd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pmd_val(e))
-#define pgd_ERROR(e) \
- printk("%s:%d: bad pgd %p(%016Lx).\n", __FILE__, __LINE__, &(e), pgd_val(e))
-
+#define pte_ERROR(e) \
+ printk("%s:%d: bad pte %p(%08lx%08lx).\n", \
+ __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
+#define pmd_ERROR(e) \
+ printk("%s:%d: bad pmd %p(%016Lx).\n", \
+ __FILE__, __LINE__, &(e), pmd_val(e))
+#define pgd_ERROR(e) \
+ printk("%s:%d: bad pgd %p(%016Lx).\n", \
+ __FILE__, __LINE__, &(e), pgd_val(e))
static inline int pud_none(pud_t pud)
{
return pud_val(pud) == 0;
}
+
static inline int pud_bad(pud_t pud)
{
return (pud_val(pud) & ~(PTE_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
}
+
static inline int pud_present(pud_t pud)
{
return pud_val(pud) & _PAGE_PRESENT;
* we are justified in merely clearing the PTE present bit, followed
* by a set. The ordering here is important.
*/
-static inline void native_set_pte_present(struct mm_struct *mm, unsigned long addr,
+static inline void native_set_pte_present(struct mm_struct *mm,
+ unsigned long addr,
pte_t *ptep, pte_t pte)
{
ptep->pte_low = 0;
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
- set_64bit((unsigned long long *)(ptep),native_pte_val(pte));
+ set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
}
+
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
- set_64bit((unsigned long long *)(pmdp),native_pmd_val(pmd));
+ set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
}
+
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
- set_64bit((unsigned long long *)(pudp),native_pud_val(pud));
+ set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
}
/*
* entry, so clear the bottom half first and enforce ordering with a compiler
* barrier.
*/
-static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
{
ptep->pte_low = 0;
smp_wmb();
static inline void pud_clear(pud_t *pudp)
{
+ unsigned long pgd;
+
set_pud(pudp, __pud(0));
/*
- * In principle we need to do a cr3 reload here to make sure
- * the processor recognizes the changed pgd. In practice, all
- * the places where pud_clear() gets called are followed by
- * full tlb flushes anyway, so we can defer the cost here.
- *
- * Specifically:
- *
- * mm/memory.c:free_pmd_range() - immediately after the
- * pud_clear() it does a pmd_free_tlb(). We change the
- * mmu_gather structure to do a full tlb flush (which has the
- * effect of reloading cr3) when the pagetable free is
- * complete.
+ * According to Intel App note "TLBs, Paging-Structure Caches,
+ * and Their Invalidation", April 2007, document 317080-001,
+ * section 8.1: in PAE mode we explicitly have to flush the
+ * TLB via cr3 if the top-level pgd is changed...
*
- * arch/x86/mm/hugetlbpage.c:huge_pmd_unshare() - the call to
- * this is followed by a flush_tlb_range, which on x86 does a
- * full tlb flush.
+ * Make sure the pud entry we're updating is within the
+ * current pgd to avoid unnecessary TLB flushes.
*/
+ pgd = read_cr3();
+ if (__pa(pudp) >= pgd && __pa(pudp) <
+ (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
+ write_cr3(pgd);
}
-#define pud_page(pud) \
-((struct page *) __va(pud_val(pud) & PAGE_MASK))
+#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PAGE_MASK))
-#define pud_page_vaddr(pud) \
-((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+#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))
+#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)
* put the 32 bits of offset into the high part.
*/
#define pte_to_pgoff(pte) ((pte).pte_high)
-#define pgoff_to_pte(off) ((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } })
+#define pgoff_to_pte(off) \
+ ((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } })
#define PTE_FILE_MAX_BITS 32
/* Encode and de-code a swap entry */