mm: avoid unnecessary flush on change_huge_pmd()

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@vmware.com
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andrew Cooper <andrew.cooper3@citrix.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will@kernel.org>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Nick Piggin <npiggin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1e09519af14331c02136ab93e2ebe2478a21fdca..0821f87d495fc06e48f18ff0bfb23f294e3b3ab6 100644 (file)
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1168,6 +1168,11 @@ 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 3481b35cb4ec7e05ba76848e325d189adda24964..f16059e9a85e79a0a2b9738898c02cc2ffecc693 100644 (file)
--- 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 53750224e176e5e5b5592871fb9199427bd39e85..530b1817b58c1f79f630dcc0b71d4811db71c237 100644 (file)
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -570,6 +570,26 @@ 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 2befa9cfb46e2a53942e6ac99452684b419778dd..6f37f77eb48c4c72877dfccb6ae3faecd33af51d 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1801,10 +1801,10 @@ 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 6523fda274e51da61cee464f836b11a5f1cf1df2..90ab721a12a8282d2d3d09f835e17e70121b1316 100644 (file)
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -201,6 +201,14 @@ 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)