From: Nadav Amit <namit@xxxxxxxxxx>
Calls to change_protection_range() on THP can trigger, at least on x86,
two TLB flushes for one page: one immediately, when pmdp_invalidate() is
called by change_huge_pmd(), and then another one later (that can be
batched) when change_protection_range() finishes.
The first TLB flush is only necessary to prevent the dirty bit (and with
a lesser importance the access bit) from changing while the PTE is
modified. However, this is not necessary as the x86 CPUs set the
dirty-bit atomically with an additional check that the PTE is (still)
present. One caveat is Intel's Knights Landing that has a bug and does
not do so.
Leverage this behavior to eliminate the unnecessary TLB flush in
change_huge_pmd(). Introduce a new arch specific pmdp_invalidate_ad()
that only invalidates the access and dirty bit from further changes.
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
---
arch/x86/include/asm/pgtable.h | 8 ++++++++
include/linux/pgtable.h | 5 +++++
mm/huge_memory.c | 7 ++++---
mm/pgtable-generic.c | 8 ++++++++
4 files changed, 25 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 448cd01eb3ec..18c3366f8f4d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1146,6 +1146,14 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
}
}
#endif
+
+#define __HAVE_ARCH_PMDP_INVALIDATE_AD
+static inline pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp)
+{
+ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
+}
+
/*
* Page table pages are page-aligned. The lower half of the top
* level is used for userspace and the top half for the kernel.
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e24d2c992b11..622efe0a9ef0 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -561,6 +561,11 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
#endif
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *pmdp);
+#endif
+
#ifndef __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t pte_a, pte_t pte_b)
{
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e5ea5f775d5c..435da011b1a2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1795,10 +1795,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
* The race makes MADV_DONTNEED miss the huge pmd and don't clear it
* which may break userspace.
*
- * pmdp_invalidate() is required to make sure we don't miss
- * dirty/young flags set by hardware.
+ * pmdp_invalidate_ad() is required to make sure we don't miss
+ * dirty/young flags (which are also known as access/dirty) cannot be
+ * further modifeid by the hardware.
*/
- entry = pmdp_invalidate(vma, addr, pmd);
+ entry = pmdp_invalidate_ad(vma, addr, pmd);
entry = pmd_modify(entry, newprot);
if (preserve_write)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4e640baf9794..b0ce6c7391bf 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -200,6 +200,14 @@ pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
}
#endif
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmdp)
+{
+ return pmdp_invalidate(vma, address, pmdp);
+}
+#endif
+
#ifndef pmdp_collapse_flush
pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
--
2.25.1
