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 loose these bits.
On PAE we have to use cmpxchg8b as we cannot assume what is value of new pmd and
setting it up half-by-half can expose broken corrupted entry to CPU.
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 | 18 ++++++++++++++++++
arch/x86/include/asm/pgtable.h | 14 ++++++++++++++
2 files changed, 32 insertions(+)
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 50d35e3185f5..471c8a851363 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -180,6 +180,24 @@ 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(pmd_t *pmdp, pmd_t pmd)
+{
+ pmd_t old;
+
+ /*
+ * We cannot assume what is value of pmd here, so there's no easy way
+ * to set if half by half. We have to fall back to cmpxchg64.
+ */
+ {
+ 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 f5af95a0c6b8..a924fc6a96b9 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1092,6 +1092,20 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
+#ifndef pmdp_establish
+#define pmdp_establish pmdp_establish
+static inline pmd_t pmdp_establish(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);
*
--
2.11.0
