From 34c06254ff82a815fdccdfae7517a06c9b768cee Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 5 Nov 2015 00:12:24 -0500 Subject: cgroup: fix cftype->file_offset handling 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") introduced cftype->file_offset so that the handles for per-css file instances can be recorded. These handles then can be used, for example, to generate file modified notifications. Unfortunately, it made the wrong assumption that files are created once for a given css and removed on its destruction. Due to the dependencies among subsystems, a css may be hidden from userland and then later shown again. This is implemented by removing and re-creating the affected files, so the associated kernfs_node for a given cgroup file may change over time. This incorrect assumption led to the corruption of css->files lists. Reimplement cftype->file_offset handling so that cgroup_file->kn is protected by a lock and updated as files are created and destroyed. This also makes keeping them on per-cgroup list unnecessary. Signed-off-by: Tejun Heo Reported-by: James Sedgwick Fixes: 6f60eade2433 ("cgroup: generalize obtaining the handles of and notifying cgroup files") Acked-by: Johannes Weiner Acked-by: Zefan Li --- kernel/cgroup.c | 42 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 34 insertions(+), 8 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index f1603c153890..b316debadeb3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -97,6 +97,12 @@ static DEFINE_SPINLOCK(css_set_lock); */ static DEFINE_SPINLOCK(cgroup_idr_lock); +/* + * Protects cgroup_file->kn for !self csses. It synchronizes notifications + * against file removal/re-creation across css hiding. + */ +static DEFINE_SPINLOCK(cgroup_file_kn_lock); + /* * Protects cgroup_subsys->release_agent_path. Modifying it also requires * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. @@ -1393,6 +1399,16 @@ static void cgroup_rm_file(struct cgroup *cgrp, const struct cftype *cft) char name[CGROUP_FILE_NAME_MAX]; lockdep_assert_held(&cgroup_mutex); + + if (cft->file_offset) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, cft->ss); + struct cgroup_file *cfile = (void *)css + cft->file_offset; + + spin_lock_irq(&cgroup_file_kn_lock); + cfile->kn = NULL; + spin_unlock_irq(&cgroup_file_kn_lock); + } + kernfs_remove_by_name(cgrp->kn, cgroup_file_name(cgrp, cft, name)); } @@ -1856,7 +1872,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_LIST_HEAD(&cgrp->self.sibling); INIT_LIST_HEAD(&cgrp->self.children); - INIT_LIST_HEAD(&cgrp->self.files); INIT_LIST_HEAD(&cgrp->cset_links); INIT_LIST_HEAD(&cgrp->pidlists); mutex_init(&cgrp->pidlist_mutex); @@ -3313,9 +3328,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp, if (cft->file_offset) { struct cgroup_file *cfile = (void *)css + cft->file_offset; - kernfs_get(kn); + spin_lock_irq(&cgroup_file_kn_lock); cfile->kn = kn; - list_add(&cfile->node, &css->files); + spin_unlock_irq(&cgroup_file_kn_lock); } return 0; @@ -3552,6 +3567,22 @@ int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) return cgroup_add_cftypes(ss, cfts); } +/** + * cgroup_file_notify - generate a file modified event for a cgroup_file + * @cfile: target cgroup_file + * + * @cfile must have been obtained by setting cftype->file_offset. + */ +void cgroup_file_notify(struct cgroup_file *cfile) +{ + unsigned long flags; + + spin_lock_irqsave(&cgroup_file_kn_lock, flags); + if (cfile->kn) + kernfs_notify(cfile->kn); + spin_unlock_irqrestore(&cgroup_file_kn_lock, flags); +} + /** * cgroup_task_count - count the number of tasks in a cgroup. * @cgrp: the cgroup in question @@ -4613,13 +4644,9 @@ static void css_free_work_fn(struct work_struct *work) container_of(work, struct cgroup_subsys_state, destroy_work); struct cgroup_subsys *ss = css->ss; struct cgroup *cgrp = css->cgroup; - struct cgroup_file *cfile; percpu_ref_exit(&css->refcnt); - list_for_each_entry(cfile, &css->files, node) - kernfs_put(cfile->kn); - if (ss) { /* css free path */ int id = css->id; @@ -4724,7 +4751,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css, css->ss = ss; INIT_LIST_HEAD(&css->sibling); INIT_LIST_HEAD(&css->children); - INIT_LIST_HEAD(&css->files); css->serial_nr = css_serial_nr_next++; if (cgroup_parent(cgrp)) { -- cgit From 53254f900bd9ff1e3cc5628e76126bb403d9d160 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Nov 2015 14:55:41 -0500 Subject: cgroup: make css_set pin its css's to avoid use-afer-free A css_set represents the relationship between a set of tasks and css's. css_set never pinned the associated css's. This was okay because tasks used to always disassociate immediately (in RCU sense) - either a task is moved to a different css_set or exits and never accesses css_set again. Unfortunately, afcf6c8b7544 ("cgroup: add cgroup_subsys->free() method and use it to fix pids controller") and patches leading up to it made a zombie hold onto its css_set and deref the associated css's on its release. Nothing pins the css's after exit and it might have already been freed leading to use-after-free. general protection fault: 0000 [#1] PREEMPT SMP task: ffffffff81bf2500 ti: ffffffff81be4000 task.ti: ffffffff81be4000 RIP: 0010:[] [] pids_cancel.constprop.4+0x5/0x40 ... Call Trace: [] ? pids_free+0x3d/0xa0 [] cgroup_free+0x53/0xe0 [] __put_task_struct+0x42/0x130 [] delayed_put_task_struct+0x77/0x130 [] rcu_process_callbacks+0x2f4/0x820 [] ? rcu_process_callbacks+0x2b3/0x820 [] __do_softirq+0xd4/0x460 [] irq_exit+0x89/0xa0 [] smp_apic_timer_interrupt+0x42/0x50 [] apic_timer_interrupt+0x84/0x90 ... Code: 5b 5d c3 48 89 df 48 c7 c2 c9 f9 ae 81 48 c7 c6 91 2c ae 81 e8 1d 94 0e 00 31 c0 5b 5d c3 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 83 87 e0 00 00 00 ff 78 01 c3 80 3d 08 7a c1 00 00 74 02 RIP [] pids_cancel.constprop.4+0x5/0x40 RSP ---[ end trace 89a4a4b916b90c49 ]--- Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: disabled ---[ end Kernel panic - not syncing: Fatal exception in interrupt Fix it by making css_set pin the associate css's until its release. Signed-off-by: Tejun Heo Reported-by: Dave Jones Reported-by: Daniel Wagner Link: http://lkml.kernel.org/g/20151120041836.GA18390@codemonkey.org.uk Link: http://lkml.kernel.org/g/5652D448.3080002@bmw-carit.de Fixes: afcf6c8b7544 ("cgroup: add cgroup_subsys->free() method and use it to fix pids controller") --- kernel/cgroup.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index b316debadeb3..5cea63fe4095 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -760,9 +760,11 @@ static void put_css_set_locked(struct css_set *cset) if (!atomic_dec_and_test(&cset->refcount)) return; - /* This css_set is dead. unlink it and release cgroup refcounts */ - for_each_subsys(ss, ssid) + /* This css_set is dead. unlink it and release cgroup and css refs */ + for_each_subsys(ss, ssid) { list_del(&cset->e_cset_node[ssid]); + css_put(cset->subsys[ssid]); + } hash_del(&cset->hlist); css_set_count--; @@ -1062,9 +1064,13 @@ static struct css_set *find_css_set(struct css_set *old_cset, key = css_set_hash(cset->subsys); hash_add(css_set_table, &cset->hlist, key); - for_each_subsys(ss, ssid) + for_each_subsys(ss, ssid) { + struct cgroup_subsys_state *css = cset->subsys[ssid]; + list_add_tail(&cset->e_cset_node[ssid], - &cset->subsys[ssid]->cgroup->e_csets[ssid]); + &css->cgroup->e_csets[ssid]); + css_get(css); + } spin_unlock_bh(&css_set_lock); -- cgit From 1f7dd3e5a6e4f093017fff12232572ee1aa4639b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 3 Dec 2015 10:18:21 -0500 Subject: cgroup: fix handling of multi-destination migration from subtree_control enabling Consider the following v2 hierarchy. P0 (+memory) --- P1 (-memory) --- A \- B P0 has memory enabled in its subtree_control while P1 doesn't. If both A and B contain processes, they would belong to the memory css of P1. Now if memory is enabled on P1's subtree_control, memory csses should be created on both A and B and A's processes should be moved to the former and B's processes the latter. IOW, enabling controllers can cause atomic migrations into different csses. The core cgroup migration logic has been updated accordingly but the controller migration methods haven't and still assume that all tasks migrate to a single target css; furthermore, the methods were fed the css in which subtree_control was updated which is the parent of the target csses. pids controller depends on the migration methods to move charges and this made the controller attribute charges to the wrong csses often triggering the following warning by driving a counter negative. WARNING: CPU: 1 PID: 1 at kernel/cgroup_pids.c:97 pids_cancel.constprop.6+0x31/0x40() Modules linked in: CPU: 1 PID: 1 Comm: systemd Not tainted 4.4.0-rc1+ #29 ... ffffffff81f65382 ffff88007c043b90 ffffffff81551ffc 0000000000000000 ffff88007c043bc8 ffffffff810de202 ffff88007a752000 ffff88007a29ab00 ffff88007c043c80 ffff88007a1d8400 0000000000000001 ffff88007c043bd8 Call Trace: [] dump_stack+0x4e/0x82 [] warn_slowpath_common+0x82/0xc0 [] warn_slowpath_null+0x1a/0x20 [] pids_cancel.constprop.6+0x31/0x40 [] pids_can_attach+0x6d/0xf0 [] cgroup_taskset_migrate+0x6c/0x330 [] cgroup_migrate+0xf5/0x190 [] cgroup_attach_task+0x176/0x200 [] __cgroup_procs_write+0x2ad/0x460 [] cgroup_procs_write+0x14/0x20 [] cgroup_file_write+0x35/0x1c0 [] kernfs_fop_write+0x141/0x190 [] __vfs_write+0x28/0xe0 [] vfs_write+0xac/0x1a0 [] SyS_write+0x49/0xb0 [] entry_SYSCALL_64_fastpath+0x12/0x76 This patch fixes the bug by removing @css parameter from the three migration methods, ->can_attach, ->cancel_attach() and ->attach() and updating cgroup_taskset iteration helpers also return the destination css in addition to the task being migrated. All controllers are updated accordingly. * Controllers which don't care whether there are one or multiple target csses can be converted trivially. cpu, io, freezer, perf, netclassid and netprio fall in this category. * cpuset's current implementation assumes that there's single source and destination and thus doesn't support v2 hierarchy already. The only change made by this patchset is how that single destination css is obtained. * memory migration path already doesn't do anything on v2. How the single destination css is obtained is updated and the prep stage of mem_cgroup_can_attach() is reordered to accomodate the change. * pids is the only controller which was affected by this bug. It now correctly handles multi-destination migrations and no longer causes counter underflow from incorrect accounting. Signed-off-by: Tejun Heo Reported-and-tested-by: Daniel Wagner Cc: Aleksa Sarai --- kernel/cgroup.c | 43 ++++++++++++++++++++++++++++++++++--------- 1 file changed, 34 insertions(+), 9 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5cea63fe4095..470f6536b9e8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -2237,6 +2237,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the subsys currently being processed */ + int ssid; + /* * Fields for cgroup_taskset_*() iteration. * @@ -2299,25 +2302,29 @@ static void cgroup_taskset_add(struct task_struct *task, /** * cgroup_taskset_first - reset taskset and return the first task * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * @tset iteration is initialized and the first task is returned. */ -struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_first(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { tset->cur_cset = list_first_entry(tset->csets, struct css_set, mg_node); tset->cur_task = NULL; - return cgroup_taskset_next(tset); + return cgroup_taskset_next(tset, dst_cssp); } /** * cgroup_taskset_next - iterate to the next task in taskset * @tset: taskset of interest + * @dst_cssp: output variable for the destination css * * Return the next task in @tset. Iteration must have been initialized * with cgroup_taskset_first(). */ -struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) +struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset, + struct cgroup_subsys_state **dst_cssp) { struct css_set *cset = tset->cur_cset; struct task_struct *task = tset->cur_task; @@ -2332,6 +2339,18 @@ struct task_struct *cgroup_taskset_next(struct cgroup_taskset *tset) if (&task->cg_list != &cset->mg_tasks) { tset->cur_cset = cset; tset->cur_task = task; + + /* + * This function may be called both before and + * after cgroup_taskset_migrate(). The two cases + * can be distinguished by looking at whether @cset + * has its ->mg_dst_cset set. + */ + if (cset->mg_dst_cset) + *dst_cssp = cset->mg_dst_cset->subsys[tset->ssid]; + else + *dst_cssp = cset->subsys[tset->ssid]; + return task; } @@ -2367,7 +2386,8 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, /* check that we can legitimately attach to the cgroup */ for_each_e_css(css, i, dst_cgrp) { if (css->ss->can_attach) { - ret = css->ss->can_attach(css, tset); + tset->ssid = i; + ret = css->ss->can_attach(tset); if (ret) { failed_css = css; goto out_cancel_attach; @@ -2400,9 +2420,12 @@ static int cgroup_taskset_migrate(struct cgroup_taskset *tset, */ tset->csets = &tset->dst_csets; - for_each_e_css(css, i, dst_cgrp) - if (css->ss->attach) - css->ss->attach(css, tset); + for_each_e_css(css, i, dst_cgrp) { + if (css->ss->attach) { + tset->ssid = i; + css->ss->attach(tset); + } + } ret = 0; goto out_release_tset; @@ -2411,8 +2434,10 @@ out_cancel_attach: for_each_e_css(css, i, dst_cgrp) { if (css == failed_css) break; - if (css->ss->cancel_attach) - css->ss->cancel_attach(css, tset); + if (css->ss->cancel_attach) { + tset->ssid = i; + css->ss->cancel_attach(tset); + } } out_release_tset: spin_lock_bh(&css_set_lock); -- cgit