Add an infrastructure that maintains either a system-wide mm_struct
list or per-memcg mm_struct lists. Multiple threads can concurrently
work on the same mm_struct list, and each of them will be given a
different mm_struct. Those who finish early can optionally wait on the
rest after the iterator has reached the end of the list.
This infrastructure also tracks whether an mm_struct is being used on
any CPUs or has been used since the last time a worker looked at it.
In other words, workers will not be given an mm_struct that belongs to
a process that has been sleeping.
Signed-off-by: Yu Zhao <yuz...@google.com>
---
fs/exec.c | 2 +
include/linux/memcontrol.h | 4 +
include/linux/mm_types.h | 135 +++++++++++++++++++
include/linux/mmzone.h | 2 -
kernel/exit.c | 1 +
kernel/fork.c | 10 ++
kernel/kthread.c | 1 +
kernel/sched/core.c | 2 +
mm/memcontrol.c | 28 ++++
mm/vmscan.c | 263 +++++++++++++++++++++++++++++++++++++
10 files changed, 446 insertions(+), 2 deletions(-)
diff --git a/fs/exec.c b/fs/exec.c
index 18594f11c31f..c691d4d7720c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1008,6 +1008,7 @@ static int exec_mmap(struct mm_struct *mm)
active_mm = tsk->active_mm;
tsk->active_mm = mm;
tsk->mm = mm;
+ lru_gen_add_mm(mm);
/*
* This prevents preemption while active_mm is being loaded and
* it and mm are being updated, which could cause problems for
@@ -1018,6 +1019,7 @@ static int exec_mmap(struct mm_struct *mm)
if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
activate_mm(active_mm, mm);
+ lru_gen_switch_mm(active_mm, mm);
if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM))
local_irq_enable();
tsk->mm->vmacache_seqnum = 0;
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index f325aeb4b4e8..591557c5b7e2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -335,6 +335,10 @@ struct mem_cgroup {
struct deferred_split deferred_split_queue;
#endif
+#ifdef CONFIG_LRU_GEN
+ struct lru_gen_mm_list *mm_list;
+#endif
+
struct mem_cgroup_per_node *nodeinfo[0];
/* WARNING: nodeinfo must be the last member here */
};
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0974ad501a47..b8a038a016f2 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -15,6 +15,8 @@
#include <linux/page-flags-layout.h>
#include <linux/workqueue.h>
#include <linux/seqlock.h>
+#include <linux/nodemask.h>
+#include <linux/mmdebug.h>
#include <asm/mmu.h>
@@ -382,6 +384,8 @@ struct core_state {
struct completion startup;
};
+#define ANON_AND_FILE 2
+
struct kioctx_table;
struct mm_struct {
struct {
@@ -560,6 +564,22 @@ struct mm_struct {
#ifdef CONFIG_IOMMU_SUPPORT
u32 pasid;
+#endif
+#ifdef CONFIG_LRU_GEN
+ struct {
+ /* node of a global or per-memcg mm list */
+ struct list_head list;
+#ifdef CONFIG_MEMCG
+ /* points to memcg of the owner task above */
+ struct mem_cgroup *memcg;
+#endif
+ /* indicates this mm has been used since last walk */
+ nodemask_t nodes[ANON_AND_FILE];
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+ /* number of cpus that are using this mm */
+ atomic_t nr_cpus;
+#endif
+ } lru_gen;
#endif
} __randomize_layout;
@@ -587,6 +607,121 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
return (struct cpumask *)&mm->cpu_bitmap;
}
+#ifdef CONFIG_LRU_GEN
+
+struct lru_gen_mm_list {
+ /* head of a global or per-memcg mm list */
+ struct list_head head;
+ /* protects the list */
+ spinlock_t lock;
+ struct {
+ /* set to max_seq after each round of walk */
+ unsigned long cur_seq;
+ /* next mm on the list to walk */
+ struct list_head *iter;
+ /* to wait for last worker to finish */
+ struct wait_queue_head wait;
+ /* number of concurrent workers */
+ int nr_workers;
+ } nodes[0];
+};
+
+void lru_gen_init_mm(struct mm_struct *mm);
+void lru_gen_add_mm(struct mm_struct *mm);
+void lru_gen_del_mm(struct mm_struct *mm);
+#ifdef CONFIG_MEMCG
+int lru_gen_alloc_mm_list(struct mem_cgroup *memcg);
+void lru_gen_free_mm_list(struct mem_cgroup *memcg);
+void lru_gen_migrate_mm(struct mm_struct *mm);
+#endif
+
+/*
+ * Track usage so mms that haven't been used since last walk can be skipped.
+ *
+ * This function introduces a theoretical overhead for each mm switch, but it
+ * hasn't been measurable.
+ */
+static inline void lru_gen_switch_mm(struct mm_struct *old, struct mm_struct
*new)
+{
+ int file;
+
+ /* exclude init_mm, efi_mm, etc. */
+ if (!core_kernel_data((unsigned long)old)) {
+ VM_BUG_ON(old == &init_mm);
+
+ for (file = 0; file < ANON_AND_FILE; file++)
+ nodes_setall(old->lru_gen.nodes[file]);
+
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+ atomic_dec(&old->lru_gen.nr_cpus);
+ VM_BUG_ON_MM(atomic_read(&old->lru_gen.nr_cpus) < 0, old);
+#endif
+ } else
+ VM_BUG_ON_MM(READ_ONCE(old->lru_gen.list.prev) ||
+ READ_ONCE(old->lru_gen.list.next), old);
+
+ if (!core_kernel_data((unsigned long)new)) {
+ VM_BUG_ON(new == &init_mm);
+
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+ atomic_inc(&new->lru_gen.nr_cpus);
+ VM_BUG_ON_MM(atomic_read(&new->lru_gen.nr_cpus) < 0, new);
+#endif
+ } else
+ VM_BUG_ON_MM(READ_ONCE(new->lru_gen.list.prev) ||
+ READ_ONCE(new->lru_gen.list.next), new);
+}
+
+/* Returns whether the mm is being used on any cpus. */
+static inline bool lru_gen_mm_is_active(struct mm_struct *mm)
+{
+#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+ return !cpumask_empty(mm_cpumask(mm));
+#else
+ return atomic_read(&mm->lru_gen.nr_cpus);
+#endif
+}
+
+#else /* CONFIG_LRU_GEN */
+
+static inline void lru_gen_init_mm(struct mm_struct *mm)
+{
+}
+
+static inline void lru_gen_add_mm(struct mm_struct *mm)
+{
+}
+
+static inline void lru_gen_del_mm(struct mm_struct *mm)
+{
+}
+
+#ifdef CONFIG_MEMCG
+static inline int lru_gen_alloc_mm_list(struct mem_cgroup *memcg)
+{
+ return 0;
+}
+
+static inline void lru_gen_free_mm_list(struct mem_cgroup *memcg)
+{
+}
+
+static inline void lru_gen_migrate_mm(struct mm_struct *mm)
+{
+}
+#endif
+
+static inline void lru_gen_switch_mm(struct mm_struct *old, struct mm_struct
*new)
+{
+}
+
+static inline bool lru_gen_mm_is_active(struct mm_struct *mm)
+{
+ return false;
+}
+
+#endif /* CONFIG_LRU_GEN */
+
struct mmu_gather;
extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm);
extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct
*mm);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 47946cec7584..a99a1050565a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -285,8 +285,6 @@ static inline bool is_active_lru(enum lru_list lru)
return (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE);
}
-#define ANON_AND_FILE 2
-
enum lruvec_flags {
LRUVEC_CONGESTED, /* lruvec has many dirty pages
* backed by a congested BDI
diff --git a/kernel/exit.c b/kernel/exit.c
index 04029e35e69a..e4292717ce37 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -422,6 +422,7 @@ void mm_update_next_owner(struct mm_struct *mm)
goto retry;
}
WRITE_ONCE(mm->owner, c);
+ lru_gen_migrate_mm(mm);
task_unlock(c);
put_task_struct(c);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index d3171e8e88e5..e261b797955d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -665,6 +665,7 @@ static void check_mm(struct mm_struct *mm)
#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
VM_BUG_ON_MM(mm->pmd_huge_pte, mm);
#endif
+ VM_BUG_ON_MM(lru_gen_mm_is_active(mm), mm);
}
#define allocate_mm() (kmem_cache_alloc(mm_cachep, GFP_KERNEL))
@@ -1047,6 +1048,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm,
struct task_struct *p,
goto fail_nocontext;
mm->user_ns = get_user_ns(user_ns);
+ lru_gen_init_mm(mm);
return mm;
fail_nocontext:
@@ -1089,6 +1091,7 @@ static inline void __mmput(struct mm_struct *mm)
}
if (mm->binfmt)
module_put(mm->binfmt->module);
+ lru_gen_del_mm(mm);
mmdrop(mm);
}
@@ -2513,6 +2516,13 @@ pid_t kernel_clone(struct kernel_clone_args *args)
get_task_struct(p);
}
+ if (IS_ENABLED(CONFIG_LRU_GEN) && !(clone_flags & CLONE_VM)) {
+ /* lock p to synchronize with memcg migration */
+ task_lock(p);
+ lru_gen_add_mm(p->mm);
+ task_unlock(p);
+ }
+
wake_up_new_task(p);
/* forking complete and child started to run, tell ptracer */
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 1578973c5740..8da7767bb06a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -1303,6 +1303,7 @@ void kthread_use_mm(struct mm_struct *mm)
tsk->mm = mm;
membarrier_update_current_mm(mm);
switch_mm_irqs_off(active_mm, mm, tsk);
+ lru_gen_switch_mm(active_mm, mm);
local_irq_enable();
task_unlock(tsk);
#ifdef finish_arch_post_lock_switch
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ca2bb629595f..56274a14ce09 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4308,6 +4308,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
* finish_task_switch()'s mmdrop().
*/
switch_mm_irqs_off(prev->active_mm, next->mm, next);
+ lru_gen_switch_mm(prev->active_mm, next->mm);
if (!prev->mm) { // from kernel
/* will mmdrop() in finish_task_switch(). */
@@ -7599,6 +7600,7 @@ void idle_task_exit(void)
if (mm != &init_mm) {
switch_mm(mm, &init_mm, current);
+ lru_gen_switch_mm(mm, &init_mm);
finish_arch_post_lock_switch();
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 845eec01ef9d..5836780fe138 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5209,6 +5209,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
free_mem_cgroup_per_node_info(memcg, node);
free_percpu(memcg->vmstats_percpu);
free_percpu(memcg->vmstats_local);
+ lru_gen_free_mm_list(memcg);
kfree(memcg);
}
@@ -5261,6 +5262,9 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
if (alloc_mem_cgroup_per_node_info(memcg, node))
goto fail;
+ if (lru_gen_alloc_mm_list(memcg))
+ goto fail;
+
if (memcg_wb_domain_init(memcg, GFP_KERNEL))
goto fail;
@@ -6165,6 +6169,29 @@ static void mem_cgroup_move_task(void)
}
#endif
+#ifdef CONFIG_LRU_GEN
+static void mem_cgroup_attach(struct cgroup_taskset *tset)
+{
+ struct cgroup_subsys_state *css;
+ struct task_struct *task = NULL;
+
+ cgroup_taskset_for_each_leader(task, css, tset)
+ ;
+
+ if (!task)
+ return;
+
+ task_lock(task);
+ if (task->mm && task->mm->owner == task)
+ lru_gen_migrate_mm(task->mm);
+ task_unlock(task);
+}
+#else
+static void mem_cgroup_attach(struct cgroup_taskset *tset)
+{
+}
+#endif
+
static int seq_puts_memcg_tunable(struct seq_file *m, unsigned long value)
{
if (value == PAGE_COUNTER_MAX)
@@ -6505,6 +6532,7 @@ struct cgroup_subsys memory_cgrp_subsys = {
.css_free = mem_cgroup_css_free,
.css_reset = mem_cgroup_css_reset,
.can_attach = mem_cgroup_can_attach,
+ .attach = mem_cgroup_attach,
.cancel_attach = mem_cgroup_cancel_attach,
.post_attach = mem_cgroup_move_task,
.dfl_cftypes = memory_files,
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1a24d2e0a4cb..f7657ab0d4b7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4314,3 +4314,266 @@ void check_move_unevictable_pages(struct pagevec *pvec)
}
}
EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
+
+#ifdef CONFIG_LRU_GEN
+
+/******************************************************************************
+ * global and per-memcg mm list
+
******************************************************************************/
+
+/*
+ * After pages are faulted in, they become the youngest generation. They must
+ * go through aging process twice before they can be evicted. After first scan,
+ * their accessed bit set during initial faults are cleared and they become the
+ * second youngest generation. And second scan makes sure they haven't been
used
+ * since the first.
+ */
+#define MIN_NR_GENS 2
+
+static struct lru_gen_mm_list *global_mm_list;
+
+static struct lru_gen_mm_list *alloc_mm_list(void)
+{
+ int nid;
+ struct lru_gen_mm_list *mm_list;
+
+ mm_list = kzalloc(struct_size(mm_list, nodes, nr_node_ids), GFP_KERNEL);
+ if (!mm_list)
+ return NULL;
+
+ INIT_LIST_HEAD(&mm_list->head);
+ spin_lock_init(&mm_list->lock);
+
+ for_each_node(nid) {
+ mm_list->nodes[nid].cur_seq = MIN_NR_GENS - 1;
+ mm_list->nodes[nid].iter = &mm_list->head;
+ init_waitqueue_head(&mm_list->nodes[nid].wait);
+ }
+
+ return mm_list;
+}
+
+static struct lru_gen_mm_list *get_mm_list(struct mem_cgroup *memcg)
+{
+#ifdef CONFIG_MEMCG
+ if (!mem_cgroup_disabled())
+ return memcg ? memcg->mm_list : root_mem_cgroup->mm_list;
+#endif
+ VM_BUG_ON(memcg);
+
+ return global_mm_list;
+}
+
+void lru_gen_init_mm(struct mm_struct *mm)
+{
+ int file;
+
+ INIT_LIST_HEAD(&mm->lru_gen.list);
+#ifdef CONFIG_MEMCG
+ mm->lru_gen.memcg = NULL;
+#endif
+#ifndef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
+ atomic_set(&mm->lru_gen.nr_cpus, 0);
+#endif
+ for (file = 0; file < ANON_AND_FILE; file++)
+ nodes_clear(mm->lru_gen.nodes[file]);
+}
+
+void lru_gen_add_mm(struct mm_struct *mm)
+{
+ struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
+ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
+
+ VM_BUG_ON_MM(!list_empty(&mm->lru_gen.list), mm);
+#ifdef CONFIG_MEMCG
+ VM_BUG_ON_MM(mm->lru_gen.memcg, mm);
+ WRITE_ONCE(mm->lru_gen.memcg, memcg);
+#endif
+ spin_lock(&mm_list->lock);
+ list_add_tail(&mm->lru_gen.list, &mm_list->head);
+ spin_unlock(&mm_list->lock);
+}
+
+void lru_gen_del_mm(struct mm_struct *mm)
+{
+ int nid;
+#ifdef CONFIG_MEMCG
+ struct lru_gen_mm_list *mm_list = get_mm_list(mm->lru_gen.memcg);
+#else
+ struct lru_gen_mm_list *mm_list = get_mm_list(NULL);
+#endif
+
+ spin_lock(&mm_list->lock);
+
+ for_each_node(nid) {
+ if (mm_list->nodes[nid].iter != &mm->lru_gen.list)
+ continue;
+
+ mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+ if (mm_list->nodes[nid].iter == &mm_list->head)
+ WRITE_ONCE(mm_list->nodes[nid].cur_seq,
+ mm_list->nodes[nid].cur_seq + 1);
+ }
+
+ list_del_init(&mm->lru_gen.list);
+
+ spin_unlock(&mm_list->lock);
+
+#ifdef CONFIG_MEMCG
+ mem_cgroup_put(mm->lru_gen.memcg);
+ WRITE_ONCE(mm->lru_gen.memcg, NULL);
+#endif
+}
+
+#ifdef CONFIG_MEMCG
+int lru_gen_alloc_mm_list(struct mem_cgroup *memcg)
+{
+ if (mem_cgroup_disabled())
+ return 0;
+
+ memcg->mm_list = alloc_mm_list();
+
+ return memcg->mm_list ? 0 : -ENOMEM;
+}
+
+void lru_gen_free_mm_list(struct mem_cgroup *memcg)
+{
+ kfree(memcg->mm_list);
+ memcg->mm_list = NULL;
+}
+
+void lru_gen_migrate_mm(struct mm_struct *mm)
+{
+ struct mem_cgroup *memcg;
+
+ lockdep_assert_held(&mm->owner->alloc_lock);
+
+ if (mem_cgroup_disabled())
+ return;
+
+ rcu_read_lock();
+ memcg = mem_cgroup_from_task(mm->owner);
+ rcu_read_unlock();
+ if (memcg == mm->lru_gen.memcg)
+ return;
+
+ VM_BUG_ON_MM(!mm->lru_gen.memcg, mm);
+ VM_BUG_ON_MM(list_empty(&mm->lru_gen.list), mm);
+
+ lru_gen_del_mm(mm);
+ lru_gen_add_mm(mm);
+}
+
+static bool mm_has_migrated(struct mm_struct *mm, struct mem_cgroup *memcg)
+{
+ return READ_ONCE(mm->lru_gen.memcg) != memcg;
+}
+#else
+static bool mm_has_migrated(struct mm_struct *mm, struct mem_cgroup *memcg)
+{
+ return false;
+}
+#endif
+
+static bool should_skip_mm(struct mm_struct *mm, int nid, int swappiness)
+{
+ int file;
+ unsigned long size = 0;
+
+ if (mm_is_oom_victim(mm))
+ return true;
+
+ for (file = !swappiness; file < ANON_AND_FILE; file++) {
+ if (lru_gen_mm_is_active(mm) || node_isset(nid,
mm->lru_gen.nodes[file]))
+ size += file ? get_mm_counter(mm, MM_FILEPAGES) :
+ get_mm_counter(mm, MM_ANONPAGES) +
+ get_mm_counter(mm, MM_SHMEMPAGES);
+ }
+
+ if (size < SWAP_CLUSTER_MAX)
+ return true;
+
+ return !mmget_not_zero(mm);
+}
+
+/* To support multiple workers that concurrently walk mm list. */
+static bool get_next_mm(struct lruvec *lruvec, unsigned long next_seq,
+ int swappiness, struct mm_struct **iter)
+{
+ bool last = true;
+ struct mm_struct *mm = NULL;
+ int nid = lruvec_pgdat(lruvec)->node_id;
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ struct lru_gen_mm_list *mm_list = get_mm_list(memcg);
+
+ if (*iter)
+ mmput_async(*iter);
+ else if (next_seq <= READ_ONCE(mm_list->nodes[nid].cur_seq))
+ return false;
+
+ spin_lock(&mm_list->lock);
+
+ VM_BUG_ON(next_seq > mm_list->nodes[nid].cur_seq + 1);
+ VM_BUG_ON(*iter && next_seq < mm_list->nodes[nid].cur_seq);
+ VM_BUG_ON(*iter && !mm_list->nodes[nid].nr_workers);
+
+ if (next_seq <= mm_list->nodes[nid].cur_seq) {
+ last = *iter;
+ goto done;
+ }
+
+ if (mm_list->nodes[nid].iter == &mm_list->head) {
+ VM_BUG_ON(*iter || mm_list->nodes[nid].nr_workers);
+ mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+ }
+
+ while (!mm && mm_list->nodes[nid].iter != &mm_list->head) {
+ mm = list_entry(mm_list->nodes[nid].iter, struct mm_struct,
lru_gen.list);
+ mm_list->nodes[nid].iter = mm_list->nodes[nid].iter->next;
+ if (should_skip_mm(mm, nid, swappiness))
+ mm = NULL;
+ }
+
+ if (mm_list->nodes[nid].iter == &mm_list->head)
+ WRITE_ONCE(mm_list->nodes[nid].cur_seq,
+ mm_list->nodes[nid].cur_seq + 1);
+done:
+ if (*iter && !mm)
+ mm_list->nodes[nid].nr_workers--;
+ if (!*iter && mm)
+ mm_list->nodes[nid].nr_workers++;
+
+ last = last && !mm_list->nodes[nid].nr_workers &&
+ mm_list->nodes[nid].iter == &mm_list->head;
+
+ spin_unlock(&mm_list->lock);
+
+ *iter = mm;
+
+ return last;
+}
+
+/******************************************************************************
+ * initialization
+
******************************************************************************/
+
+static int __init init_lru_gen(void)
+{
+ if (mem_cgroup_disabled()) {
+ global_mm_list = alloc_mm_list();
+ if (!global_mm_list) {
+ pr_err("lru_gen: failed to allocate global mm list\n");
+ return -ENOMEM;
+ }
+ }
+
+ return 0;
+};
+/*
+ * We want to run as early as possible because some debug code, e.g.,
+ * dma_resv_lockdep(), calls mm_alloc() and mmput(). We only depend on mm_kobj,
+ * which is initialized one stage earlier by postcore_initcall().
+ */
+arch_initcall(init_lru_gen);
+
+#endif /* CONFIG_LRU_GEN */
--
2.31.0.rc2.261.g7f71774620-goog
