diff options
-rw-r--r-- | arch/Kconfig | 15 | ||||
-rw-r--r-- | kernel/fork.c | 65 | ||||
-rw-r--r-- | lib/Kconfig.debug | 10 |
3 files changed, 90 insertions, 0 deletions
diff --git a/arch/Kconfig b/arch/Kconfig index 643f8a04141e..205fd23e0cad 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -481,6 +481,21 @@ config ARCH_WANT_IRQS_OFF_ACTIVATE_MM # 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 diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..cea99f003f24 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -772,6 +772,67 @@ 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_check_lazy_tlb(void *arg) +{ + struct mm_struct *mm = arg; + + WARN_ON_ONCE(current->active_mm == 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 cleanup_lazy_tlbs(struct mm_struct *mm) +{ + if (!IS_ENABLED(CONFIG_MMU_LAZY_TLB_SHOOTDOWN)) { + /* + * In this case, lazy tlb mms are refounted and would not reach + * __mmdrop until all CPUs have switched away and mmdrop()ed. + */ + return; + } + + /* + * Lazy mm shootdown does not refcount "lazy tlb mm" usage, rather it + * requires lazy mm users to switch to another mm when the refcount + * drops to zero, before the mm is freed. This requires IPIs here to + * switch kernel threads to init_mm. + * + * archs that use IPIs to flush TLBs can piggy-back that lazy tlb mm + * switch with the final userspace teardown TLB flush which leaves the + * mm lazy on this CPU but no others, reducing the need for additional + * IPIs here. There are cases where a final IPI is still required here, + * such as the final mmdrop being performed on a different CPU than the + * one exiting, or kernel threads using the mm when userspace exits. + * + * IPI overheads have not found to be expensive, but they could be + * reduced in a number of possible ways, for example (roughly + * increasing order of complexity): + * - The last lazy reference created by exit_mm() could instead switch + * to init_mm, however it's probable this will run on the same CPU + * immediately afterwards, so this may not reduce IPIs much. + * - A batch of mms requiring IPIs could be gathered and freed at once. + * - CPUs store active_mm where it 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, perhaps together + * with some batching or delaying of the final IPIs. + * - 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_SHOOT_LAZIES)) + on_each_cpu(do_check_lazy_tlb, (void *)mm, 1); +} + /* * Called when the last reference to the mm * is dropped: either by a lazy thread or by @@ -783,6 +844,10 @@ 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 */ + cleanup_lazy_tlbs(mm); + WARN_ON_ONCE(mm == current->active_mm); mm_free_pgd(mm); destroy_context(mm); diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 39d1d93164bd..5cd8183bb4c1 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -791,6 +791,16 @@ config DEBUG_VM If unsure, say N. +config DEBUG_VM_SHOOT_LAZIES + bool "Debug MMU_LAZY_TLB_SHOOTDOWN implementation" + depends on DEBUG_VM + depends on MMU_LAZY_TLB_SHOOTDOWN + help + Enable additional IPIs that ensure lazy tlb mm references are removed + before the mm is freed. + + If unsure, say N. + config DEBUG_VM_MAPLE_TREE bool "Debug VM maple trees" depends on DEBUG_VM |