From a80c4adcb574821e534779c48ae13953b7d1d996 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 27 Jan 2023 13:46:50 -0500 Subject: ipc,namespace: make ipc namespace allocation wait for pending free Currently the ipc namespace allocation will fail when there are ipc_namespace structures pending to be freed. This results in the simple test case below, as well as some real world workloads, to get allocation failures even when the number of ipc namespaces in actual use is way below the limit. int main() { int i; for (i = 0; i < 100000; i++) { if (unshare(CLONE_NEWIPC) < 0) error(EXIT_FAILURE, errno, "unshare"); } } Make the allocation of an ipc_namespace wait for pending frees, so it will succeed. real 6m19.197s user 0m0.041s sys 0m1.019s Signed-off-by: Rik van Riel Reported-by: Chris Mason Signed-off-by: Al Viro --- ipc/namespace.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/ipc/namespace.c b/ipc/namespace.c index 8316ea585733..a26860a41dac 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -19,6 +19,12 @@ #include "util.h" +/* + * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. + */ +static void free_ipc(struct work_struct *unused); +static DECLARE_WORK(free_ipc_work, free_ipc); + static struct ucounts *inc_ipc_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_IPC_NAMESPACES); @@ -37,9 +43,18 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns, int err; err = -ENOSPC; + again: ucounts = inc_ipc_namespaces(user_ns); - if (!ucounts) + if (!ucounts) { + /* + * IPC namespaces are freed asynchronously, by free_ipc_work. + * If frees were pending, flush_work will wait, and + * return true. Fail the allocation if no frees are pending. + */ + if (flush_work(&free_ipc_work)) + goto again; goto fail; + } err = -ENOMEM; ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT); @@ -157,11 +172,6 @@ static void free_ipc(struct work_struct *unused) free_ipc_ns(n); } -/* - * The work queue is used to avoid the cost of synchronize_rcu in kern_unmount. - */ -static DECLARE_WORK(free_ipc_work, free_ipc); - /* * put_ipc_ns - drop a reference to an ipc namespace. * @ns: the namespace to put -- cgit v1.2.3 From da27f796a832122ee533c7685438dad1c4e338dd Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 27 Jan 2023 13:46:51 -0500 Subject: ipc,namespace: batch free ipc_namespace structures Instead of waiting for an RCU grace period between each ipc_namespace structure that is being freed, wait an RCU grace period for every batch of ipc_namespace structures. Thanks to Al Viro for the suggestion of the helper function. This speeds up the run time of the test case that allocates ipc_namespaces in a loop from 6 minutes, to a little over 1 second: real 0m1.192s user 0m0.038s sys 0m1.152s Signed-off-by: Rik van Riel Reported-by: Chris Mason Tested-by: Giuseppe Scrivano Suggested-by: Al Viro Signed-off-by: Al Viro --- fs/namespace.c | 18 ++++++++++++++---- include/linux/mount.h | 1 + ipc/mqueue.c | 5 ----- ipc/namespace.c | 13 ++++++++++--- ipc/util.h | 2 -- 5 files changed, 25 insertions(+), 14 deletions(-) diff --git a/fs/namespace.c b/fs/namespace.c index ab467ee58341..1ad4e5acef06 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1397,6 +1397,17 @@ struct vfsmount *mntget(struct vfsmount *mnt) } EXPORT_SYMBOL(mntget); +/* + * Make a mount point inaccessible to new lookups. + * Because there may still be current users, the caller MUST WAIT + * for an RCU grace period before destroying the mount point. + */ +void mnt_make_shortterm(struct vfsmount *mnt) +{ + if (mnt) + real_mount(mnt)->mnt_ns = NULL; +} + /** * path_is_mountpoint() - Check if path is a mount in the current namespace. * @path: path to check @@ -4573,8 +4584,8 @@ EXPORT_SYMBOL_GPL(kern_mount); void kern_unmount(struct vfsmount *mnt) { /* release long term mount so mount point can be released */ - if (!IS_ERR_OR_NULL(mnt)) { - real_mount(mnt)->mnt_ns = NULL; + if (!IS_ERR(mnt)) { + mnt_make_shortterm(mnt); synchronize_rcu(); /* yecchhh... */ mntput(mnt); } @@ -4586,8 +4597,7 @@ void kern_unmount_array(struct vfsmount *mnt[], unsigned int num) unsigned int i; for (i = 0; i < num; i++) - if (mnt[i]) - real_mount(mnt[i])->mnt_ns = NULL; + mnt_make_shortterm(mnt[i]); synchronize_rcu_expedited(); for (i = 0; i < num; i++) mntput(mnt[i]); diff --git a/include/linux/mount.h b/include/linux/mount.h index 62475996fac6..ec55a031aa8c 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -88,6 +88,7 @@ extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); +extern void mnt_make_shortterm(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index d09aa1c1e3e6..6c5bf7cce7fe 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -1709,11 +1709,6 @@ void mq_clear_sbinfo(struct ipc_namespace *ns) ns->mq_mnt->mnt_sb->s_fs_info = NULL; } -void mq_put_mnt(struct ipc_namespace *ns) -{ - kern_unmount(ns->mq_mnt); -} - static int __init init_mqueue_fs(void) { int error; diff --git a/ipc/namespace.c b/ipc/namespace.c index a26860a41dac..6ecc30effd3e 100644 --- a/ipc/namespace.c +++ b/ipc/namespace.c @@ -145,10 +145,11 @@ void free_ipcs(struct ipc_namespace *ns, struct ipc_ids *ids, static void free_ipc_ns(struct ipc_namespace *ns) { - /* mq_put_mnt() waits for a grace period as kern_unmount() - * uses synchronize_rcu(). + /* + * Caller needs to wait for an RCU grace period to have passed + * after making the mount point inaccessible to new accesses. */ - mq_put_mnt(ns); + mntput(ns->mq_mnt); sem_exit_ns(ns); msg_exit_ns(ns); shm_exit_ns(ns); @@ -168,6 +169,12 @@ static void free_ipc(struct work_struct *unused) struct llist_node *node = llist_del_all(&free_ipc_list); struct ipc_namespace *n, *t; + llist_for_each_entry_safe(n, t, node, mnt_llist) + mnt_make_shortterm(n->mq_mnt); + + /* Wait for any last users to have gone away. */ + synchronize_rcu(); + llist_for_each_entry_safe(n, t, node, mnt_llist) free_ipc_ns(n); } diff --git a/ipc/util.h b/ipc/util.h index b2906e366539..67bdd2aa2c28 100644 --- a/ipc/util.h +++ b/ipc/util.h @@ -56,10 +56,8 @@ struct pid_namespace; #ifdef CONFIG_POSIX_MQUEUE extern void mq_clear_sbinfo(struct ipc_namespace *ns); -extern void mq_put_mnt(struct ipc_namespace *ns); #else static inline void mq_clear_sbinfo(struct ipc_namespace *ns) { } -static inline void mq_put_mnt(struct ipc_namespace *ns) { } #endif #ifdef CONFIG_SYSVIPC -- cgit v1.2.3