mm: numa: pte_numa() and pmd_numa()

Implement pte_numa and pmd_numa.

We must atomically set the numa bit and clear the present bit to
define a pte_numa or pmd_numa.

Once a pte or pmd has been set as pte_numa or pmd_numa, the next time
a thread touches a virtual address in the corresponding virtual range,
a NUMA hinting page fault will trigger. The NUMA hinting page fault
will clear the NUMA bit and set the present bit again to resolve the
page fault.

The expectation is that a NUMA hinting page fault is used as part
of a placement policy that decides if a page should remain on the
current node or migrated to a different node.

Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>

1 files changed, 106 insertions, 0 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 48fc1dc1c74b..f27c83668d10 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -558,6 +558,112 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
+ * same bit too). It's set only when _PAGE_PRESET is not set and it's
+ * never set if _PAGE_PRESENT is set.
+ *
+ * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
+ * fault triggers on those regions if pte/pmd_numa returns true
+ * (because _PAGE_PRESENT is not set).
+ */
+#ifndef pte_numa
+static inline int pte_numa(pte_t pte)
+{
+        return (pte_flags(pte) &
+                (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+#ifndef pmd_numa
+static inline int pmd_numa(pmd_t pmd)
+{
+        return (pmd_flags(pmd) &
+                (_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+/*
+ * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
+ * because they're called by the NUMA hinting minor page fault. If we
+ * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
+ * would be forced to set it later while filling the TLB after we
+ * return to userland. That would trigger a second write to memory
+ * that we optimize away by setting _PAGE_ACCESSED here.
+ */
+#ifndef pte_mknonnuma
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+        pte = pte_clear_flags(pte, _PAGE_NUMA);
+        return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pmd_mknonnuma
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+        pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
+        return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pte_mknuma
+static inline pte_t pte_mknuma(pte_t pte)
+{
+        pte = pte_set_flags(pte, _PAGE_NUMA);
+        return pte_clear_flags(pte, _PAGE_PRESENT);
+}
+#endif
+
+#ifndef pmd_mknuma
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+        pmd = pmd_set_flags(pmd, _PAGE_NUMA);
+        return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+#endif
+#else
+extern int pte_numa(pte_t pte);
+extern int pmd_numa(pmd_t pmd);
+extern pte_t pte_mknonnuma(pte_t pte);
+extern pmd_t pmd_mknonnuma(pmd_t pmd);
+extern pte_t pte_mknuma(pte_t pte);
+extern pmd_t pmd_mknuma(pmd_t pmd);
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+#else
+static inline int pmd_numa(pmd_t pmd)
+{
+        return 0;
+}
+
+static inline int pte_numa(pte_t pte)
+{
+        return 0;
+}
+
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+        return pte;
+}
+
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+        return pmd;
+}
+
+static inline pte_t pte_mknuma(pte_t pte)
+{
+        return pte;
+}
+
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+        return pmd;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */