kern_mount_data is a relatively expensive operation when creating a new IPC namespace, so delay the mount until its first usage when not creating the the global namespace.
This is a net saving for new IPC namespaces that don't use mq_open(). In this case there won't be any kern_mount_data() cost at all. On my machine, the time for creating 1000 new IPC namespaces dropped from ~8s to ~2s. Signed-off-by: Giuseppe Scrivano <gscri...@redhat.com> --- v1 here: https://lkml.org/lkml/2017/11/27/427 v1 -> v2: Declare and use a mutex instead of a spinlock. include/linux/ipc_namespace.h | 2 +- ipc/mqueue.c | 48 ++++++++++++++++++++++++++++++++++--------- ipc/namespace.c | 2 +- 3 files changed, 40 insertions(+), 12 deletions(-) diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index b5630c8eb2f3..a06617c113f1 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -81,7 +81,7 @@ static inline void shm_destroy_orphaned(struct ipc_namespace *ns) {} #endif /* CONFIG_SYSVIPC */ #ifdef CONFIG_POSIX_MQUEUE -extern int mq_init_ns(struct ipc_namespace *ns); +extern int mq_init_ns(struct ipc_namespace *ns, bool mount); /* * POSIX Message Queue default values: * diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d24025626310..27a82a3fef50 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -87,6 +87,7 @@ struct mqueue_inode_info { unsigned long qsize; /* size of queue in memory (sum of all msgs) */ }; +static struct file_system_type mqueue_fs_type; static const struct inode_operations mqueue_dir_inode_operations; static const struct file_operations mqueue_file_operations; static const struct super_operations mqueue_super_ops; @@ -776,9 +777,24 @@ static int do_mq_open(const char __user *u_name, int oflag, umode_t mode, struct filename *name; int fd, error; struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; - struct vfsmount *mnt = ipc_ns->mq_mnt; - struct dentry *root = mnt->mnt_root; + struct vfsmount *mnt; + struct dentry *root; int ro; + static DEFINE_MUTEX(mnt_lock); + + mutex_lock(&mnt_lock); + mnt = ipc_ns->mq_mnt; + if (unlikely(!mnt)) { + mnt = kern_mount_data(&mqueue_fs_type, ipc_ns); + if (IS_ERR(mnt)) { + mutex_unlock(&mnt_lock); + return PTR_ERR(mnt); + } + ipc_ns->mq_mnt = mnt; + } + mutex_unlock(&mnt_lock); + + root = mnt->mnt_root; audit_mq_open(oflag, mode, attr); @@ -863,6 +879,9 @@ SYSCALL_DEFINE1(mq_unlink, const char __user *, u_name) struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns; struct vfsmount *mnt = ipc_ns->mq_mnt; + if (!mnt) + return -ENOENT; + name = getname(u_name); if (IS_ERR(name)) return PTR_ERR(name); @@ -1581,7 +1600,8 @@ static struct file_system_type mqueue_fs_type = { .fs_flags = FS_USERNS_MOUNT, }; -int mq_init_ns(struct ipc_namespace *ns) + +int mq_init_ns(struct ipc_namespace *ns, bool mount) { ns->mq_queues_count = 0; ns->mq_queues_max = DFLT_QUEUESMAX; @@ -1590,23 +1610,31 @@ int mq_init_ns(struct ipc_namespace *ns) ns->mq_msg_default = DFLT_MSG; ns->mq_msgsize_default = DFLT_MSGSIZE; - ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns); - if (IS_ERR(ns->mq_mnt)) { - int err = PTR_ERR(ns->mq_mnt); + if (!mount) ns->mq_mnt = NULL; - return err; + else { + int err; + + ns->mq_mnt = kern_mount_data(&mqueue_fs_type, ns); + if (IS_ERR(ns->mq_mnt)) { + err = PTR_ERR(ns->mq_mnt); + ns->mq_mnt = NULL; + return err; + } } return 0; } void mq_clear_sbinfo(struct ipc_namespace *ns) { - ns->mq_mnt->mnt_sb->s_fs_info = NULL; + if (ns->mq_mnt) + ns->mq_mnt->mnt_sb->s_fs_info = NULL; } void mq_put_mnt(struct ipc_namespace *ns) { - kern_unmount(ns->mq_mnt); + if (ns->mq_mnt) + kern_unmount(ns->mq_mnt); } static int __init init_mqueue_fs(void) @@ -1628,7 +1656,7 @@ static int __init init_mqueue_fs(void) spin_lock_init(&mq_lock); - error = mq_init_ns(&init_ipc_ns); + error = mq_init_ns(&init_ipc_ns, true); if (error) goto out_filesystem; diff --git a/ipc/namespace.c b/ipc/namespace.c index f59a89966f92..9d3689577f66 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -65,7 +65,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, if (err) goto fail_destroy_msg; - err = mq_init_ns(ns); + err = mq_init_ns(ns, false); if (err) goto fail_destroy_shm; -- 2.14.3
