[Devel] [PATCH RH9 15/23] ms/memcg: enable accounting for new namesapces and struct nsproxy

Vasily Averin vvs at virtuozzo.com
Sun Sep 26 13:28:43 MSK 2021


Container admin can create new namespaces and force kernel to allocate up
to several pages of memory for the namespaces and its associated
structures.

Net and uts namespaces have enabled accounting for such allocations.  It
makes sense to account for rest ones to restrict the host's memory
consumption from inside the memcg-limited container.

Link: https://lkml.kernel.org/r/5525bcbf-533e-da27-79b7-158686c64e13@virtuozzo.com
Signed-off-by: Vasily Averin <vvs at virtuozzo.com>
Acked-by: Serge Hallyn <serge at hallyn.com>
Acked-by: Christian Brauner <christian.brauner at ubuntu.com>
Acked-by: Kirill Tkhai <ktkhai at virtuozzo.com>
Reviewed-by: Shakeel Butt <shakeelb at google.com>
Cc: Alexander Viro <viro at zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan at gmail.com>
Cc: Andrei Vagin <avagin at gmail.com>
Cc: Borislav Petkov <bp at alien8.de>
Cc: Borislav Petkov <bp at suse.de>
Cc: Dmitry Safonov <0x7f454c46 at gmail.com>
Cc: "Eric W. Biederman" <ebiederm at xmission.com>
Cc: Greg Kroah-Hartman <gregkh at linuxfoundation.org>
Cc: "H. Peter Anvin" <hpa at zytor.com>
Cc: Ingo Molnar <mingo at redhat.com>
Cc: "J. Bruce Fields" <bfields at fieldses.org>
Cc: Jeff Layton <jlayton at kernel.org>
Cc: Jens Axboe <axboe at kernel.dk>
Cc: Jiri Slaby <jirislaby at kernel.org>
Cc: Johannes Weiner <hannes at cmpxchg.org>
Cc: Michal Hocko <mhocko at kernel.org>
Cc: Oleg Nesterov <oleg at redhat.com>
Cc: Roman Gushchin <guro at fb.com>
Cc: Tejun Heo <tj at kernel.org>
Cc: Thomas Gleixner <tglx at linutronix.de>
Cc: Vladimir Davydov <vdavydov.dev at gmail.com>
Cc: Yutian Yang <nglaive at gmail.com>
Cc: Zefan Li <lizefan.x at bytedance.com>
Signed-off-by: Andrew Morton <akpm at linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds at linux-foundation.org>
(cherry picked from commit 30acd0bdfb86548172168a0cc71d455944de0683)
https://jira.sw.ru/browse/PSBM-133990
Signed-off-by: Vasily Averin <vvs at virtuozzo.com>
---
 fs/namespace.c            | 2 +-
 ipc/namespace.c           | 2 +-
 kernel/cgroup/namespace.c | 2 +-
 kernel/nsproxy.c          | 2 +-
 kernel/pid_namespace.c    | 2 +-
 kernel/time/namespace.c   | 4 ++--
 kernel/user_namespace.c   | 2 +-
 7 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/namespace.c b/fs/namespace.c
index e51b63ae233b..94a9817851cc 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3307,7 +3307,7 @@ static struct mnt_namespace *alloc_mnt_ns(struct user_namespace *user_ns, bool a
 	if (!ucounts)
 		return ERR_PTR(-ENOSPC);
 
-	new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL);
+	new_ns = kzalloc(sizeof(struct mnt_namespace), GFP_KERNEL_ACCOUNT);
 	if (!new_ns) {
 		dec_mnt_namespaces(ucounts);
 		return ERR_PTR(-ENOMEM);
diff --git a/ipc/namespace.c b/ipc/namespace.c
index 7bd0766ddc3b..ae83f0f2651b 100644
--- a/ipc/namespace.c
+++ b/ipc/namespace.c
@@ -42,7 +42,7 @@ static struct ipc_namespace *create_ipc_ns(struct user_namespace *user_ns,
 		goto fail;
 
 	err = -ENOMEM;
-	ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL);
+	ns = kzalloc(sizeof(struct ipc_namespace), GFP_KERNEL_ACCOUNT);
 	if (ns == NULL)
 		goto fail_dec;
 
diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c
index f5e8828c109c..0d5c29879a50 100644
--- a/kernel/cgroup/namespace.c
+++ b/kernel/cgroup/namespace.c
@@ -24,7 +24,7 @@ static struct cgroup_namespace *alloc_cgroup_ns(void)
 	struct cgroup_namespace *new_ns;
 	int ret;
 
-	new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL);
+	new_ns = kzalloc(sizeof(struct cgroup_namespace), GFP_KERNEL_ACCOUNT);
 	if (!new_ns)
 		return ERR_PTR(-ENOMEM);
 	ret = ns_alloc_inum(&new_ns->ns);
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index abc01fcad8c7..eec72ca962e2 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -568,6 +568,6 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags)
 
 int __init nsproxy_cache_init(void)
 {
-	nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC);
+	nsproxy_cachep = KMEM_CACHE(nsproxy, SLAB_PANIC|SLAB_ACCOUNT);
 	return 0;
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index cb5a25a8a0cc..a46a3723bc66 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -450,7 +450,7 @@ const struct proc_ns_operations pidns_for_children_operations = {
 
 static __init int pid_namespaces_init(void)
 {
-	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC);
+	pid_ns_cachep = KMEM_CACHE(pid_namespace, SLAB_PANIC | SLAB_ACCOUNT);
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
 	register_sysctl_paths(kern_path, pid_ns_ctl_table);
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index 12eab0d2ae28..aec832801c26 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -88,13 +88,13 @@ static struct time_namespace *clone_time_ns(struct user_namespace *user_ns,
 		goto fail;
 
 	err = -ENOMEM;
-	ns = kmalloc(sizeof(*ns), GFP_KERNEL);
+	ns = kmalloc(sizeof(*ns), GFP_KERNEL_ACCOUNT);
 	if (!ns)
 		goto fail_dec;
 
 	refcount_set(&ns->ns.count, 1);
 
-	ns->vvar_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
+	ns->vvar_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	if (!ns->vvar_page)
 		goto fail_free;
 
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index ef82d401dde8..6b2e3ca7ee99 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -1385,7 +1385,7 @@ const struct proc_ns_operations userns_operations = {
 
 static __init int user_namespaces_init(void)
 {
-	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC);
+	user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC | SLAB_ACCOUNT);
 	return 0;
 }
 subsys_initcall(user_namespaces_init);
-- 
2.25.1



More information about the Devel mailing list