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.
Signed-off-by: Nicholas Piggin <npiggin@xxxxxxxxx>
---
arch/Kconfig | 13 +++++++++++++
kernel/fork.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 64 insertions(+)
diff --git a/arch/Kconfig b/arch/Kconfig
index 1cff045cdde6..f8136c893991 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -421,6 +421,19 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM
# Use normal mm refcounting for MMU_LAZY_TLB kernel thread references.
config MMU_LAZY_TLB_REFCOUNT
def_bool y
+ depends on !MMU_LAZY_TLB_SHOOTDOWN
+
+# Instead of refcounting the lazy mm struct for kernel thread references
+# (which can cause contention with multi-threaded apps on large multiprocessor
+# systems), this option causes __mmdrop to IPI all CPUs in the mm_cpumask and
+# switch to init_mm if they were using the to-be-freed mm as the lazy tlb. To
+# implement this, architectures must use _lazy_tlb variants of mm refcounting
+# when releasing kernel thread mm references, and mm_cpumask must include at
+# least all possible CPUs in which the mm might be lazy, at the time of the
+# final mmdrop. mmgrab/mmdrop in arch/ code must be switched to _lazy_tlb
+# postfix as necessary.
+config MMU_LAZY_TLB_SHOOTDOWN
+ bool
config ARCH_HAVE_NMI_SAFE_CMPXCHG
bool
diff --git a/kernel/fork.c b/kernel/fork.c
index dc06afd725cb..8085ff33c7f6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -674,6 +674,53 @@ static void check_mm(struct mm_struct *mm)
#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
@@ -683,6 +730,10 @@ 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);
--
2.23.0
