| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20220829212531.3184856-29-surenb@google.com>
Date: Mon, 29 Aug 2022 21:25:31 +0000
From: Suren Baghdasaryan <surenb@...gle.com>
To: akpm@...ux-foundation.org
Cc: michel@...pinasse.org, jglisse@...gle.com, mhocko@...e.com,
vbabka@...e.cz, hannes@...xchg.org, mgorman@...hsingularity.net,
dave@...olabs.net, willy@...radead.org, liam.howlett@...cle.com,
peterz@...radead.org, ldufour@...ux.ibm.com,
laurent.dufour@...ibm.com, paulmck@...nel.org, riel@...riel.com,
luto@...nel.org, songliubraving@...com, peterx@...hat.com,
david@...hat.com, dhowells@...hat.com, hughd@...gle.com,
bigeasy@...utronix.de, kent.overstreet@...ux.dev,
rientjes@...gle.com, axelrasmussen@...gle.com, joelaf@...gle.com,
minchan@...gle.com, surenb@...gle.com, kernel-team@...roid.com,
linux-mm@...ck.org, linux-arm-kernel@...ts.infradead.org,
linuxppc-dev@...ts.ozlabs.org, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: [RFC PATCH 28/28] kernel/fork: throttle call_rcu() calls in vm_area_free
call_rcu() can take a long time when callback offloading is enabled.
Its use in the vm_area_free can cause regressions in the exit path when
multiple VMAs are being freed. To minimize that impact, place VMAs into
a list and free them in groups using one call_rcu() call per group.
Signed-off-by: Suren Baghdasaryan <surenb@...gle.com>
---
include/linux/mm.h | 1 +
include/linux/mm_types.h | 11 ++++++-
kernel/fork.c | 68 +++++++++++++++++++++++++++++++++++-----
mm/init-mm.c | 3 ++
mm/mmap.c | 1 +
5 files changed, 75 insertions(+), 9 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a3cbaa7b9119..81dff694ac14 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -249,6 +249,7 @@ void setup_initial_init_mm(void *start_code, void *end_code,
struct vm_area_struct *vm_area_alloc(struct mm_struct *);
struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
void vm_area_free(struct vm_area_struct *);
+void drain_free_vmas(struct mm_struct *mm);
#ifndef CONFIG_MMU
extern struct rb_root nommu_region_tree;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 36562e702baf..6f3effc493b1 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -412,7 +412,11 @@ struct vm_area_struct {
struct vm_area_struct *vm_next, *vm_prev;
};
#ifdef CONFIG_PER_VMA_LOCK
- struct rcu_head vm_rcu; /* Used for deferred freeing. */
+ struct {
+ struct list_head vm_free_list;
+ /* Used for deferred freeing. */
+ struct rcu_head vm_rcu;
+ };
#endif
};
@@ -573,6 +577,11 @@ struct mm_struct {
*/
#ifdef CONFIG_PER_VMA_LOCK
int mm_lock_seq;
+ struct {
+ struct list_head head;
+ spinlock_t lock;
+ int size;
+ } vma_free_list;
#endif
diff --git a/kernel/fork.c b/kernel/fork.c
index b443ba3a247a..7c88710aed72 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -483,26 +483,75 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
}
#ifdef CONFIG_PER_VMA_LOCK
-static void __vm_area_free(struct rcu_head *head)
+static inline void __vm_area_free(struct vm_area_struct *vma)
{
- struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
- vm_rcu);
/* The vma should either have no lock holders or be write-locked. */
vma_assert_no_reader(vma);
kmem_cache_free(vm_area_cachep, vma);
}
-#endif
+
+static void vma_free_rcu_callback(struct rcu_head *head)
+{
+ struct vm_area_struct *first_vma;
+ struct vm_area_struct *vma, *vma2;
+
+ first_vma = container_of(head, struct vm_area_struct, vm_rcu);
+ list_for_each_entry_safe(vma, vma2, &first_vma->vm_free_list, vm_free_list)
+ __vm_area_free(vma);
+ __vm_area_free(first_vma);
+}
+
+void drain_free_vmas(struct mm_struct *mm)
+{
+ struct vm_area_struct *first_vma;
+ LIST_HEAD(to_destroy);
+
+ spin_lock(&mm->vma_free_list.lock);
+ list_splice_init(&mm->vma_free_list.head, &to_destroy);
+ mm->vma_free_list.size = 0;
+ spin_unlock(&mm->vma_free_list.lock);
+
+ if (list_empty(&to_destroy))
+ return;
+
+ first_vma = list_first_entry(&to_destroy, struct vm_area_struct, vm_free_list);
+ /* Remove the head which is allocated on the stack */
+ list_del(&to_destroy);
+
+ call_rcu(&first_vma->vm_rcu, vma_free_rcu_callback);
+}
+
+#define VM_AREA_FREE_LIST_MAX 32
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ bool drain;
+
+ free_anon_vma_name(vma);
+
+ spin_lock(&mm->vma_free_list.lock);
+ list_add(&vma->vm_free_list, &mm->vma_free_list.head);
+ mm->vma_free_list.size++;
+ drain = mm->vma_free_list.size > VM_AREA_FREE_LIST_MAX;
+ spin_unlock(&mm->vma_free_list.lock);
+
+ if (drain)
+ drain_free_vmas(mm);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+void drain_free_vmas(struct mm_struct *mm) {}
void vm_area_free(struct vm_area_struct *vma)
{
free_anon_vma_name(vma);
-#ifdef CONFIG_PER_VMA_LOCK
- call_rcu(&vma->vm_rcu, __vm_area_free);
-#else
kmem_cache_free(vm_area_cachep, vma);
-#endif
}
+#endif /* CONFIG_PER_VMA_LOCK */
+
static void account_kernel_stack(struct task_struct *tsk, int account)
{
if (IS_ENABLED(CONFIG_VMAP_STACK)) {
@@ -1137,6 +1186,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
INIT_LIST_HEAD(&mm->mmlist);
#ifdef CONFIG_PER_VMA_LOCK
WRITE_ONCE(mm->mm_lock_seq, 0);
+ INIT_LIST_HEAD(&mm->vma_free_list.head);
+ spin_lock_init(&mm->vma_free_list.lock);
+ mm->vma_free_list.size = 0;
#endif
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
diff --git a/mm/init-mm.c b/mm/init-mm.c
index 8399f90d631c..7b6d2460545f 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -39,6 +39,9 @@ struct mm_struct init_mm = {
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
#ifdef CONFIG_PER_VMA_LOCK
.mm_lock_seq = 0,
+ .vma_free_list.head = LIST_HEAD_INIT(init_mm.vma_free_list.head),
+ .vma_free_list.lock = __SPIN_LOCK_UNLOCKED(init_mm.vma_free_list.lock),
+ .vma_free_list.size = 0,
#endif
.user_ns = &init_user_ns,
.cpu_bitmap = CPU_BITS_NONE,
diff --git a/mm/mmap.c b/mm/mmap.c
index 1edfcd384f5e..d61b7ef84ba6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -3149,6 +3149,7 @@ void exit_mmap(struct mm_struct *mm)
}
mm->mmap = NULL;
mmap_write_unlock(mm);
+ drain_free_vmas(mm);
vm_unacct_memory(nr_accounted);
}
--
2.37.2.672.g94769d06f0-goog
Powered by blists - more mailing lists