lazy tlb: allow lazy tlb mm refcounting to be configurable

Add CONFIG_MMU_TLB_REFCOUNT which enables refcounting of the lazy tlb mm
when it is context switched.  This can be disabled by architectures that
don't require this refcounting if they clean up lazy tlb mms when the last
refcount is dropped.  Currently this is always enabled, so the patch
introduces no functional change.

Link: https://lkml.kernel.org/r/20230203071837.1136453-4-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

Documentation/mm/active_mm.rst

@@ -2,6 +2,12 @@
 Active MM
 =========
 
+Note, the mm_count refcount may no longer include the "lazy" users
+(running tasks with ->active_mm == mm && ->mm == NULL) on kernels
+with CONFIG_MMU_LAZY_TLB_REFCOUNT=n. Taking and releasing these lazy
+references must be done with mmgrab_lazy_tlb() and mmdrop_lazy_tlb()
+helpers, which abstract this config option.
+
 ::
 
  List:       linux-kernel

arch/Kconfig

@@ -465,6 +465,23 @@ 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
+
 config ARCH_HAVE_NMI_SAFE_CMPXCHG
 	bool
 

include/linux/sched/mm.h

@@ -82,17 +82,29 @@ static inline void mmdrop_sched(struct mm_struct *mm)
 /* Helpers for lazy TLB mm refcounting */
 static inline void mmgrab_lazy_tlb(struct mm_struct *mm)
 {
-	mmgrab(mm);
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
+		mmgrab(mm);
 }
 
 static inline void mmdrop_lazy_tlb(struct mm_struct *mm)
 {
-	mmdrop(mm);
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT)) {
+		mmdrop(mm);
+	} else {
+		/*
+		 * mmdrop_lazy_tlb must provide a full memory barrier, see the
+		 * membarrier comment finish_task_switch which relies on this.
+		 */
+		smp_mb();
+	}
 }
 
 static inline void mmdrop_lazy_tlb_sched(struct mm_struct *mm)
 {
-	mmdrop_sched(mm);
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_REFCOUNT))
+		mmdrop_sched(mm);
+	else
+		smp_mb(); /* see mmdrop_lazy_tlb() above */
 }
 
 /**