diff mbox series

[081/262] lazy tlb: shoot lazies, a non-refcounting lazy tlb option

Message ID 20211105203854.-FBJlVYYh%akpm@linux-foundation.org (mailing list archive)
State New
Headers show
Series [001/262] scripts/spelling.txt: add more spellings to spelling.txt | expand

Commit Message

Andrew Morton Nov. 5, 2021, 8:38 p.m. UTC
From: Nicholas Piggin <npiggin@gmail.com>
Subject: lazy tlb: shoot lazies, a non-refcounting lazy tlb option

On big systems, the mm refcount can become highly contented when doing a
lot of context switching with threaded applications (particularly
switching between the idle thread and an application thread).

Abandoning lazy tlb slows switching down quite a bit in the important
user->idle->user cases, so instead implement a non-refcounted scheme that
causes __mmdrop() to IPI all CPUs in the mm_cpumask and shoot down any
remaining lazy ones.

Shootdown IPIs are some concern, but they have not been observed to be a
big problem with this scheme (the powerpc implementation generated 314
additional interrupts on a 144 CPU system during a kernel compile).  There
are a number of strategies that could be employed to reduce IPIs if they
turn out to be a problem for some workload.

[npiggin@gmail.com: update comments]
  Link: https://lkml.kernel.org/r/1623121901.mszkmmum0n.astroid@bobo.none
Link: https://lkml.kernel.org/r/20210605014216.446867-4-npiggin@gmail.com
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@ozlabs.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 arch/Kconfig  |   14 +++++++++++++
 kernel/fork.c |   51 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 65 insertions(+)
diff mbox series

Patch

--- a/arch/Kconfig~lazy-tlb-shoot-lazies-a-non-refcounting-lazy-tlb-option
+++ a/arch/Kconfig
@@ -441,6 +441,20 @@  config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
 # to a kthread ->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 ensure mm_cpumask(mm) contains at least all
+# possible CPUs in which the mm is lazy, and 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
--- a/kernel/fork.c~lazy-tlb-shoot-lazies-a-non-refcounting-lazy-tlb-option
+++ a/kernel/fork.c
@@ -686,6 +686,53 @@  static void check_mm(struct mm_struct *m
 #define allocate_mm()	(kmem_cache_alloc(mm_cachep, GFP_KERNEL))
 #define free_mm(mm)	(kmem_cache_free(mm_cachep, (mm)))
 
+static void do_shoot_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (current->active_mm == mm) {
+		WARN_ON_ONCE(current->mm);
+		current->active_mm = &init_mm;
+		switch_mm(mm, &init_mm, current);
+	}
+}
+
+static void do_check_lazy_tlb(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	WARN_ON_ONCE(current->active_mm == mm);
+}
+
+static void shoot_lazy_tlbs(struct mm_struct *mm)
+{
+	if (IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) {
+		/*
+		 * IPI overheads have not found to be expensive, but they could
+		 * be reduced in a number of possible ways, for example (in
+		 * roughly increasing order of complexity):
+		 * - A batch of mms requiring IPIs could be gathered and freed
+		 *   at once.
+		 * - CPUs could store their active mm somewhere that can be
+		 *   remotely checked without a lock, to filter out
+		 *   false-positives in the cpumask.
+		 * - After mm_users or mm_count reaches zero, switching away
+		 *   from the mm could clear mm_cpumask to reduce some IPIs
+		 *   (some batching or delaying would help).
+		 * - A delayed freeing and RCU-like quiescing sequence based on
+		 *   mm switching to avoid IPIs completely.
+		 */
+		on_each_cpu_mask(mm_cpumask(mm), do_shoot_lazy_tlb, (void *)mm, 1);
+		if (IS_ENABLED(CONFIG_DEBUG_VM))
+			on_each_cpu(do_check_lazy_tlb, (void *)mm, 1);
+	} else {
+		/*
+		 * In this case, lazy tlb mms are refounted and would not reach
+		 * __mmdrop until all CPUs have switched away and mmdrop()ed.
+		 */
+	}
+}
+
 /*
  * Called when the last reference to the mm
  * is dropped: either by a lazy thread or by
@@ -695,6 +742,10 @@  void __mmdrop(struct mm_struct *mm)
 {
 	BUG_ON(mm == &init_mm);
 	WARN_ON_ONCE(mm == current->mm);
+
+	/* Ensure no CPUs are using this as their lazy tlb mm */
+	shoot_lazy_tlbs(mm);
+
 	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);