1 files changed, 32 insertions, 0 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index e3511afbb7f2..205fd23e0cad 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -465,6 +465,38 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 	  irqs disabled over activate_mm. Architectures that do IPI based TLB
 	  shootdowns should enable this.
 
+# Use normal mm refcounting for MMU_LAZY_TLB kernel thread references.
+# MMU_LAZY_TLB_REFCOUNT=n can improve the scalability of context switching
+# to/from kernel threads when the same mm is running on a lot of CPUs (a large
+# multi-threaded application), by reducing contention on the mm refcount.
+#
+# This can be disabled if the architecture ensures no CPUs are using an mm as a
+# "lazy tlb" beyond its final refcount (i.e., by the time __mmdrop frees the mm
+# or its kernel page tables). This could be arranged by arch_exit_mmap(), or
+# final exit(2) TLB flush, for example.
+#
+# To implement this, an arch *must*:
+# Ensure the _lazy_tlb variants of mmgrab/mmdrop are used when manipulating
+# the lazy tlb reference of a kthread's ->active_mm (non-arch code has been
+# converted already).
+config MMU_LAZY_TLB_REFCOUNT
+	def_bool y
+	depends on !MMU_LAZY_TLB_SHOOTDOWN
+
+# This option allows MMU_LAZY_TLB_REFCOUNT=n. It ensures no CPUs are using an
+# mm as a lazy tlb beyond its last reference count, by shooting down these
+# users before the mm is deallocated. __mmdrop() first IPIs all CPUs that may
+# be using the mm as a lazy tlb, so that they may switch themselves to using
+# init_mm for their active mm. mm_cpumask(mm) is used to determine which CPUs
+# may be using mm as a lazy tlb mm.
+#
+# To implement this, an arch *must*:
+# - At the time of the final mmdrop of the mm, ensure mm_cpumask(mm) contains
+#   at least all possible CPUs in which the mm is lazy.
+# - It must meet the requirements for MMU_LAZY_TLB_REFCOUNT=n (see above).
+config MMU_LAZY_TLB_SHOOTDOWN
+	bool
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool