We need an atomic way to setup pmd page table entry, avoiding races with
CPU setting dirty/accessed bits. This is required to implement
pmdp_invalidate() that doesn't lose these bits.
On PAE we can avoid expensive cmpxchg8b for cases when new page table
entry is not present. If it's present, fallback to cpmxchg loop.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
---
arch/x86/include/asm/pgtable-3level.h | 37 ++++++++++++++++++++++++++++++++++-
arch/x86/include/asm/pgtable.h | 15 ++++++++++++++
2 files changed, 51 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index bc4af5453802..2c874cfc7789 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -158,7 +158,6 @@ static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
#endif
-#ifdef CONFIG_SMP
union split_pmd {
struct {
u32 pmd_low;
@@ -166,6 +165,8 @@ union split_pmd {
};
pmd_t pmd;
};
+
+#ifdef CONFIG_SMP
static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
{
union split_pmd res, *orig = (union split_pmd *)pmdp;
@@ -181,6 +182,40 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *pmdp)
#define native_pmdp_get_and_clear(xp) native_local_pmdp_get_and_clear(xp)
#endif
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+ pmd_t old;
+
+ /*
+ * If pmd has present bit cleared we can get away without expensive
+ * cmpxchg64: we can update pmdp half-by-half without racing with
+ * anybody.
+ */
+ if (!(pmd_val(pmd) & _PAGE_PRESENT)) {
+ union split_pmd old, new, *ptr;
+
+ ptr = (union split_pmd *)pmdp;
+
+ new.pmd = pmd;
+
+ /* xchg acts as a barrier before setting of the high bits */
+ old.pmd_low = xchg(&ptr->pmd_low, new.pmd_low);
+ old.pmd_high = ptr->pmd_high;
+ ptr->pmd_high = new.pmd_high;
+ return old.pmd;
+ }
+
+ {
+ old = *pmdp;
+ } while (cmpxchg64(&pmdp->pmd, old.pmd, pmd.pmd) != old.pmd);
+
+ return old;
+}
+#endif
+
#ifdef CONFIG_SMP
union split_pud {
struct {
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 95e2dfd75521..099ebe0053c3 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1094,6 +1094,21 @@ static inline int pud_write(pud_t pud)
return pud_flags(pud) & _PAGE_RW;
}
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp, pmd_t pmd)
+{
+ if (IS_ENABLED(CONFIG_SMP)) {
+ return xchg(pmdp, pmd);
+ } else {
+ pmd_t old = *pmdp;
+ *pmdp = pmd;
+ return old;
+ }
+}
+#endif
+
/*
* clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
*
--
2.15.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>
