This is a note to let you know that I've just added the patch titled
mm: avoid unnecessary flush on change_huge_pmd()
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
mm-avoid-unnecessary-flush-on-change_huge_pmd.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 6f73cf81e6438c334ae03321c915e9d376501fd8
Author: Nadav Amit <nadav.amit@xxxxxxxxx>
Date: Mon May 9 18:20:50 2022 -0700
mm: avoid unnecessary flush on change_huge_pmd()
[ Upstream commit 4f83145721f362c2f4d312edc4755269a2069488 ]
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.
Link: https://lkml.kernel.org/r/20220401180821.1986781-4-namit@xxxxxxxxxx
Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
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>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Stable-dep-of: 3a5a8d343e1c ("mm: fix race between __split_huge_pmd_locked() and GUP-fast")
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 448cd01eb3ecb..c04be133a6cd7 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1146,6 +1146,11 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
}
}
#endif
+
+#define __HAVE_ARCH_PMDP_INVALIDATE_AD
+extern pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma,
+ unsigned long address, pmd_t *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/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 3481b35cb4ec7..f16059e9a85e7 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -608,6 +608,16 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
return young;
}
+
+pmd_t pmdp_invalidate_ad(struct vm_area_struct *vma, unsigned long address,
+ pmd_t *pmdp)
+{
+ /*
+ * No flush is necessary. Once an invalid PTE is established, the PTE's
+ * access and dirty bits cannot be updated.
+ */
+ return pmdp_establish(vma, address, pmdp, pmd_mkinvalid(*pmdp));
+}
#endif
/**
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index d468efcf48f45..952969aa19ec1 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -562,6 +562,26 @@ extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp);
#endif
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE_AD
+
+/*
+ * pmdp_invalidate_ad() invalidates the PMD while changing a transparent
+ * hugepage mapping in the page tables. This function is similar to
+ * pmdp_invalidate(), but should only be used if the access and dirty bits would
+ * not be cleared by the software in the new PMD value. The function ensures
+ * that hardware changes of the access and dirty bits updates would not be lost.
+ *
+ * Doing so can allow in certain architectures to avoid a TLB flush in most
+ * cases. Yet, another TLB flush might be necessary later if the PMD update
+ * itself requires such flush (e.g., if protection was set to be stricter). Yet,
+ * even when a TLB flush is needed because of the update, the caller may be able
+ * to batch these TLB flushing operations, so fewer TLB flush operations are
+ * needed.
+ */
+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 8ab6316d85391..265ef8d1393c5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1798,10 +1798,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
* 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
+ * pmdp_invalidate_ad() is required to make sure we don't miss
* dirty/young flags set by hardware.
*/
- oldpmd = pmdp_invalidate(vma, addr, pmd);
+ oldpmd = pmdp_invalidate_ad(vma, addr, pmd);
entry = pmd_modify(oldpmd, newprot);
if (preserve_write)
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4e640baf97948..b0ce6c7391bf4 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)
