linux/net/core/netclassid_cgroup.c

130 lines
2.9 KiB
C
Raw Normal View History

/*
* net/core/netclassid_cgroup.c Classid Cgroupfs Handling
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Authors: Thomas Graf <tgraf@suug.ch>
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/cgroup.h>
#include <linux/fdtable.h>
#include <net/cls_cgroup.h>
#include <net/sock.h>
static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
{
return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
}
struct cgroup_cls_state *task_cls_state(struct task_struct *p)
{
cgroup: net_cls: fix false-positive "suspicious RCU usage" In dev_queue_xmit() net_cls protected with rcu-bh. [ 270.730026] =============================== [ 270.730029] [ INFO: suspicious RCU usage. ] [ 270.730033] 4.2.0-rc3+ #2 Not tainted [ 270.730036] ------------------------------- [ 270.730040] include/linux/cgroup.h:353 suspicious rcu_dereference_check() usage! [ 270.730041] other info that might help us debug this: [ 270.730043] rcu_scheduler_active = 1, debug_locks = 1 [ 270.730045] 2 locks held by dhclient/748: [ 270.730046] #0: (rcu_read_lock_bh){......}, at: [<ffffffff81682b70>] __dev_queue_xmit+0x50/0x960 [ 270.730085] #1: (&qdisc_tx_lock){+.....}, at: [<ffffffff81682d60>] __dev_queue_xmit+0x240/0x960 [ 270.730090] stack backtrace: [ 270.730096] CPU: 0 PID: 748 Comm: dhclient Not tainted 4.2.0-rc3+ #2 [ 270.730098] Hardware name: OpenStack Foundation OpenStack Nova, BIOS Bochs 01/01/2011 [ 270.730100] 0000000000000001 ffff8800bafeba58 ffffffff817ad487 0000000000000007 [ 270.730103] ffff880232a0a780 ffff8800bafeba88 ffffffff810ca4f2 ffff88022fb23e00 [ 270.730105] ffff880232a0a780 ffff8800bafebb68 ffff8800bafebb68 ffff8800bafebaa8 [ 270.730108] Call Trace: [ 270.730121] [<ffffffff817ad487>] dump_stack+0x4c/0x65 [ 270.730148] [<ffffffff810ca4f2>] lockdep_rcu_suspicious+0xe2/0x120 [ 270.730153] [<ffffffff816a62d2>] task_cls_state+0x92/0xa0 [ 270.730158] [<ffffffffa00b534f>] cls_cgroup_classify+0x4f/0x120 [cls_cgroup] [ 270.730164] [<ffffffff816aac74>] tc_classify_compat+0x74/0xc0 [ 270.730166] [<ffffffff816ab573>] tc_classify+0x33/0x90 [ 270.730170] [<ffffffffa00bcb0a>] htb_enqueue+0xaa/0x4a0 [sch_htb] [ 270.730172] [<ffffffff81682e26>] __dev_queue_xmit+0x306/0x960 [ 270.730174] [<ffffffff81682b70>] ? __dev_queue_xmit+0x50/0x960 [ 270.730176] [<ffffffff816834a3>] dev_queue_xmit_sk+0x13/0x20 [ 270.730185] [<ffffffff81787770>] dev_queue_xmit+0x10/0x20 [ 270.730187] [<ffffffff8178b91c>] packet_snd.isra.62+0x54c/0x760 [ 270.730190] [<ffffffff8178be25>] packet_sendmsg+0x2f5/0x3f0 [ 270.730203] [<ffffffff81665245>] ? sock_def_readable+0x5/0x190 [ 270.730210] [<ffffffff817b64bb>] ? _raw_spin_unlock+0x2b/0x40 [ 270.730216] [<ffffffff8173bcbc>] ? unix_dgram_sendmsg+0x5cc/0x640 [ 270.730219] [<ffffffff8165f367>] sock_sendmsg+0x47/0x50 [ 270.730221] [<ffffffff8165f42f>] sock_write_iter+0x7f/0xd0 [ 270.730232] [<ffffffff811fd4c7>] __vfs_write+0xa7/0xf0 [ 270.730234] [<ffffffff811fe5b8>] vfs_write+0xb8/0x190 [ 270.730236] [<ffffffff811fe8c2>] SyS_write+0x52/0xb0 [ 270.730239] [<ffffffff817b6bae>] entry_SYSCALL_64_fastpath+0x12/0x76 Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-07-22 17:23:20 +08:00
return css_cls_state(task_css_check(p, net_cls_cgrp_id,
rcu_read_lock_bh_held()));
}
EXPORT_SYMBOL_GPL(task_cls_state);
static struct cgroup_subsys_state *
cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
{
struct cgroup_cls_state *cs;
cs = kzalloc(sizeof(*cs), GFP_KERNEL);
if (!cs)
return ERR_PTR(-ENOMEM);
return &cs->css;
}
static int cgrp_css_online(struct cgroup_subsys_state *css)
{
struct cgroup_cls_state *cs = css_cls_state(css);
struct cgroup_cls_state *parent = css_cls_state(css->parent);
if (parent)
cs->classid = parent->classid;
return 0;
}
static void cgrp_css_free(struct cgroup_subsys_state *css)
{
kfree(css_cls_state(css));
}
static int update_classid_sock(const void *v, struct file *file, unsigned n)
{
int err;
struct socket *sock = sock_from_file(file, &err);
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-08 06:38:53 +08:00
if (sock) {
spin_lock(&cgroup_sk_update_lock);
sock_cgroup_set_classid(&sock->sk->sk_cgrp_data,
(unsigned long)v);
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-08 06:38:53 +08:00
spin_unlock(&cgroup_sk_update_lock);
}
return 0;
}
static void update_classid(struct cgroup_subsys_state *css, void *v)
{
struct css_task_iter it;
struct task_struct *p;
css_task_iter_start(css, &it);
while ((p = css_task_iter_next(&it))) {
task_lock(p);
iterate_fd(p->files, 0, update_classid_sock, v);
task_unlock(p);
}
css_task_iter_end(&it);
}
static void cgrp_attach(struct cgroup_taskset *tset)
{
struct cgroup_subsys_state *css;
cgroup_taskset_first(tset, &css);
update_classid(css,
(void *)(unsigned long)css_cls_state(css)->classid);
}
static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
{
return css_cls_state(css)->classid;
}
static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
u64 value)
{
struct cgroup_cls_state *cs = css_cls_state(css);
sock, cgroup: add sock->sk_cgroup In cgroup v1, dealing with cgroup membership was difficult because the number of membership associations was unbound. As a result, cgroup v1 grew several controllers whose primary purpose is either tagging membership or pull in configuration knobs from other subsystems so that cgroup membership test can be avoided. net_cls and net_prio controllers are examples of the latter. They allow configuring network-specific attributes from cgroup side so that network subsystem can avoid testing cgroup membership; unfortunately, these are not only cumbersome but also problematic. Both net_cls and net_prio aren't properly hierarchical. Both inherit configuration from the parent on creation but there's no interaction afterwards. An ancestor doesn't restrict the behavior in its subtree in anyway and configuration changes aren't propagated downwards. Especially when combined with cgroup delegation, this is problematic because delegatees can mess up whatever network configuration implemented at the system level. net_prio would allow the delegatees to set whatever priority value regardless of CAP_NET_ADMIN and net_cls the same for classid. While it is possible to solve these issues from controller side by implementing hierarchical allowable ranges in both controllers, it would involve quite a bit of complexity in the controllers and further obfuscate network configuration as it becomes even more difficult to tell what's actually being configured looking from the network side. While not much can be done for v1 at this point, as membership handling is sane on cgroup v2, it'd be better to make cgroup matching behave like other network matches and classifiers than introducing further complications. In preparation, this patch updates sock->sk_cgrp_data handling so that it points to the v2 cgroup that sock was created in until either net_prio or net_cls is used. Once either of the two is used, sock->sk_cgrp_data reverts to its previous role of carrying prioidx and classid. This is to avoid adding yet another cgroup related field to struct sock. As the mode switching can happen at most once per boot, the switching mechanism is aimed at lowering hot path overhead. It may leak a finite, likely small, number of cgroup refs and report spurious prioidx or classid on switching; however, dynamic updates of prioidx and classid have always been racy and lossy - socks between creation and fd installation are never updated, config changes don't update existing sockets at all, and prioidx may index with dead and recycled cgroup IDs. Non-critical inaccuracies from small race windows won't make any noticeable difference. This patch doesn't make use of the pointer yet. The following patch will implement netfilter match for cgroup2 membership. v2: Use sock_cgroup_data to avoid inflating struct sock w/ another cgroup specific field. v3: Add comments explaining why sock_data_prioidx() and sock_data_classid() use different fallback values. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Daniel Wagner <daniel.wagner@bmw-carit.de> CC: Neil Horman <nhorman@tuxdriver.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2015-12-08 06:38:53 +08:00
cgroup_sk_alloc_disable();
cs->classid = (u32)value;
update_classid(css, (void *)(unsigned long)cs->classid);
return 0;
}
static struct cftype ss_files[] = {
{
.name = "classid",
.read_u64 = read_classid,
.write_u64 = write_classid,
},
{ } /* terminate */
};
cgroup: clean up cgroup_subsys names and initialization cgroup_subsys is a bit messier than it needs to be. * The name of a subsys can be different from its internal identifier defined in cgroup_subsys.h. Most subsystems use the matching name but three - cpu, memory and perf_event - use different ones. * cgroup_subsys_id enums are postfixed with _subsys_id and each cgroup_subsys is postfixed with _subsys. cgroup.h is widely included throughout various subsystems, it doesn't and shouldn't have claim on such generic names which don't have any qualifier indicating that they belong to cgroup. * cgroup_subsys->subsys_id should always equal the matching cgroup_subsys_id enum; however, we require each controller to initialize it and then BUG if they don't match, which is a bit silly. This patch cleans up cgroup_subsys names and initialization by doing the followings. * cgroup_subsys_id enums are now postfixed with _cgrp_id, and each cgroup_subsys with _cgrp_subsys. * With the above, renaming subsys identifiers to match the userland visible names doesn't cause any naming conflicts. All non-matching identifiers are renamed to match the official names. cpu_cgroup -> cpu mem_cgroup -> memory perf -> perf_event * controllers no longer need to initialize ->subsys_id and ->name. They're generated in cgroup core and set automatically during boot. * Redundant cgroup_subsys declarations removed. * While updating BUG_ON()s in cgroup_init_early(), convert them to WARN()s. BUGging that early during boot is stupid - the kernel can't print anything, even through serial console and the trap handler doesn't even link stack frame properly for back-tracing. This patch doesn't introduce any behavior changes. v2: Rebased on top of fe1217c4f3f7 ("net: net_cls: move cgroupfs classid handling into core"). Signed-off-by: Tejun Heo <tj@kernel.org> Acked-by: Neil Horman <nhorman@tuxdriver.com> Acked-by: "David S. Miller" <davem@davemloft.net> Acked-by: "Rafael J. Wysocki" <rjw@rjwysocki.net> Acked-by: Michal Hocko <mhocko@suse.cz> Acked-by: Peter Zijlstra <peterz@infradead.org> Acked-by: Aristeu Rozanski <aris@redhat.com> Acked-by: Ingo Molnar <mingo@redhat.com> Acked-by: Li Zefan <lizefan@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Balbir Singh <bsingharora@gmail.com> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Serge E. Hallyn <serue@us.ibm.com> Cc: Vivek Goyal <vgoyal@redhat.com> Cc: Thomas Graf <tgraf@suug.ch>
2014-02-08 23:36:58 +08:00
struct cgroup_subsys net_cls_cgrp_subsys = {
.css_alloc = cgrp_css_alloc,
.css_online = cgrp_css_online,
.css_free = cgrp_css_free,
.attach = cgrp_attach,
.legacy_cftypes = ss_files,
};