From 610467270fb368584b74567edd21c8cc5104490f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sat, 8 Jul 2017 07:17:02 -0400 Subject: cgroup: don't call migration methods if there are no tasks to migrate Subsystem migration methods shouldn't be called for empty migrations. cgroup_migrate_execute() implements this guarantee by bailing early if there are no source css_sets. This used to be correct before a79a908fd2b0 ("cgroup: introduce cgroup namespaces"), but no longer since the commit because css_sets can stay pinned without tasks in them. This caused cgroup_migrate_execute() call into cpuset migration methods with an empty cgroup_taskset. cpuset migration methods correctly assume that cgroup_taskset_first() never returns NULL; however, due to the bug, it can, leading to the following oops. Unable to handle kernel paging request for data at address 0x00000960 Faulting instruction address: 0xc0000000001d6868 Oops: Kernel access of bad area, sig: 11 [#1] ... CPU: 14 PID: 16947 Comm: kworker/14:0 Tainted: G W 4.12.0-rc4-next-20170609 #2 Workqueue: events cpuset_hotplug_workfn task: c00000000ca60580 task.stack: c00000000c728000 NIP: c0000000001d6868 LR: c0000000001d6858 CTR: c0000000001d6810 REGS: c00000000c72b720 TRAP: 0300 Tainted: GW (4.12.0-rc4-next-20170609) MSR: 8000000000009033 CR: 44722422 XER: 20000000 CFAR: c000000000008710 DAR: 0000000000000960 DSISR: 40000000 SOFTE: 1 GPR00: c0000000001d6858 c00000000c72b9a0 c000000001536e00 0000000000000000 GPR04: c00000000c72b9c0 0000000000000000 c00000000c72bad0 c000000766367678 GPR08: c000000766366d10 c00000000c72b958 c000000001736e00 0000000000000000 GPR12: c0000000001d6810 c00000000e749300 c000000000123ef8 c000000775af4180 GPR16: 0000000000000000 0000000000000000 c00000075480e9c0 c00000075480e9e0 GPR20: c00000075480e8c0 0000000000000001 0000000000000000 c00000000c72ba20 GPR24: c00000000c72baa0 c00000000c72bac0 c000000001407248 c00000000c72ba20 GPR28: c00000000141fc80 c00000000c72bac0 c00000000c6bc790 0000000000000000 NIP [c0000000001d6868] cpuset_can_attach+0x58/0x1b0 LR [c0000000001d6858] cpuset_can_attach+0x48/0x1b0 Call Trace: [c00000000c72b9a0] [c0000000001d6858] cpuset_can_attach+0x48/0x1b0 (unreliable) [c00000000c72ba00] [c0000000001cbe80] cgroup_migrate_execute+0xb0/0x450 [c00000000c72ba80] [c0000000001d3754] cgroup_transfer_tasks+0x1c4/0x360 [c00000000c72bba0] [c0000000001d923c] cpuset_hotplug_workfn+0x86c/0xa20 [c00000000c72bca0] [c00000000011aa44] process_one_work+0x1e4/0x580 [c00000000c72bd30] [c00000000011ae78] worker_thread+0x98/0x5c0 [c00000000c72bdc0] [c000000000124058] kthread+0x168/0x1b0 [c00000000c72be30] [c00000000000b2e8] ret_from_kernel_thread+0x5c/0x74 Instruction dump: f821ffa1 7c7d1b78 60000000 60000000 38810020 7fa3eb78 3f42ffed 4bff4c25 60000000 3b5a0448 3d420020 eb610020 7f43d378 e9290000 f92af200 ---[ end trace dcaaf98fb36d9e64 ]--- This patch fixes the bug by adding an explicit nr_tasks counter to cgroup_taskset and skipping calling the migration methods if the counter is zero. While at it, remove the now spurious check on no source css_sets. Signed-off-by: Tejun Heo Reported-and-tested-by: Abdul Haleem Cc: Roman Gushchin Cc: stable@vger.kernel.org # v4.6+ Fixes: a79a908fd2b0 ("cgroup: introduce cgroup namespaces") Link: http://lkml.kernel.org/r/1497266622.15415.39.camel@abdul.in.ibm.com --- kernel/cgroup/cgroup-internal.h | 3 +++ kernel/cgroup/cgroup.c | 58 ++++++++++++++++++++++------------------- 2 files changed, 34 insertions(+), 27 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 793565c05742..8b4c3c2f2509 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -33,6 +33,9 @@ struct cgroup_taskset { struct list_head src_csets; struct list_head dst_csets; + /* the number of tasks in the set */ + int nr_tasks; + /* the subsys currently being processed */ int ssid; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 620794a20a33..cc53111072d8 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2006,6 +2006,8 @@ static void cgroup_migrate_add_task(struct task_struct *task, if (!cset->mg_src_cgrp) return; + mgctx->tset.nr_tasks++; + list_move_tail(&task->cg_list, &cset->mg_tasks); if (list_empty(&cset->mg_node)) list_add_tail(&cset->mg_node, @@ -2094,21 +2096,19 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) struct css_set *cset, *tmp_cset; int ssid, failed_ssid, ret; - /* methods shouldn't be called if no task is actually migrating */ - if (list_empty(&tset->src_csets)) - return 0; - /* check that we can legitimately attach to the cgroup */ - do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { - if (ss->can_attach) { - tset->ssid = ssid; - ret = ss->can_attach(tset); - if (ret) { - failed_ssid = ssid; - goto out_cancel_attach; + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ss->can_attach) { + tset->ssid = ssid; + ret = ss->can_attach(tset); + if (ret) { + failed_ssid = ssid; + goto out_cancel_attach; + } } - } - } while_each_subsys_mask(); + } while_each_subsys_mask(); + } /* * Now that we're guaranteed success, proceed to move all tasks to @@ -2137,25 +2137,29 @@ static int cgroup_migrate_execute(struct cgroup_mgctx *mgctx) */ tset->csets = &tset->dst_csets; - do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { - if (ss->attach) { - tset->ssid = ssid; - ss->attach(tset); - } - } while_each_subsys_mask(); + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ss->attach) { + tset->ssid = ssid; + ss->attach(tset); + } + } while_each_subsys_mask(); + } ret = 0; goto out_release_tset; out_cancel_attach: - do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { - if (ssid == failed_ssid) - break; - if (ss->cancel_attach) { - tset->ssid = ssid; - ss->cancel_attach(tset); - } - } while_each_subsys_mask(); + if (tset->nr_tasks) { + do_each_subsys_mask(ss, ssid, mgctx->ss_mask) { + if (ssid == failed_ssid) + break; + if (ss->cancel_attach) { + tset->ssid = ssid; + ss->cancel_attach(tset); + } + } while_each_subsys_mask(); + } out_release_tset: spin_lock_irq(&css_set_lock); list_splice_init(&tset->dst_csets, &tset->src_csets); -- cgit v1.2.3 From 88e033e326307831922e34e7de0d694274dcc1c7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 16 Jul 2017 21:40:30 -0400 Subject: cgroup: remove now unused list_head @pending in cgroup_apply_cftypes() Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 1 - 1 file changed, 1 deletion(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 620794a20a33..4f02b5edd82c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3230,7 +3230,6 @@ restart: static int cgroup_apply_cftypes(struct cftype *cfts, bool is_add) { - LIST_HEAD(pending); struct cgroup_subsys *ss = cfts[0].ss; struct cgroup *root = &ss->root->cgrp; struct cgroup_subsys_state *css; -- cgit v1.2.3 From 788b950c62e06b02278a0fd380e1a0667996ce3c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 16 Jul 2017 21:43:33 -0400 Subject: cgroup: distinguish local and children populated states cgrp->populated_cnt counts both local (the cgroup's populated css_sets) and subtree proper (populated children) so that it's only zero when the whole subtree, including self, is empty. This patch splits the counter into two so that local and children populated states are tracked separately. It allows finer-grained tests on the state of the hierarchy which will be used to replace css_set walking local populated test. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 37 +++++++++++++++++++++---------------- 1 file changed, 21 insertions(+), 16 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4f02b5edd82c..5fe2644cd0f3 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -587,39 +587,44 @@ static bool css_set_populated(struct css_set *cset) } /** - * cgroup_update_populated - updated populated count of a cgroup + * cgroup_update_populated - update the populated count of a cgroup * @cgrp: the target cgroup * @populated: inc or dec populated count * * One of the css_sets associated with @cgrp is either getting its first - * task or losing the last. Update @cgrp->populated_cnt accordingly. The - * count is propagated towards root so that a given cgroup's populated_cnt - * is zero iff the cgroup and all its descendants don't contain any tasks. + * task or losing the last. Update @cgrp->nr_populated_* accordingly. The + * count is propagated towards root so that a given cgroup's + * nr_populated_children is zero iff none of its descendants contain any + * tasks. * - * @cgrp's interface file "cgroup.populated" is zero if - * @cgrp->populated_cnt is zero and 1 otherwise. When @cgrp->populated_cnt - * changes from or to zero, userland is notified that the content of the - * interface file has changed. This can be used to detect when @cgrp and - * its descendants become populated or empty. + * @cgrp's interface file "cgroup.populated" is zero if both + * @cgrp->nr_populated_csets and @cgrp->nr_populated_children are zero and + * 1 otherwise. When the sum changes from or to zero, userland is notified + * that the content of the interface file has changed. This can be used to + * detect when @cgrp and its descendants become populated or empty. */ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) { + struct cgroup *child = NULL; + int adj = populated ? 1 : -1; + lockdep_assert_held(&css_set_lock); do { - bool trigger; + bool was_populated = cgroup_is_populated(cgrp); - if (populated) - trigger = !cgrp->populated_cnt++; + if (!child) + cgrp->nr_populated_csets += adj; else - trigger = !--cgrp->populated_cnt; + cgrp->nr_populated_children += adj; - if (!trigger) + if (was_populated == cgroup_is_populated(cgrp)) break; cgroup1_check_for_release(cgrp); cgroup_file_notify(&cgrp->events_file); + child = cgrp; cgrp = cgroup_parent(cgrp); } while (cgrp); } @@ -630,7 +635,7 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) * @populated: whether @cset is populated or depopulated * * @cset is either getting the first task or losing the last. Update the - * ->populated_cnt of all associated cgroups accordingly. + * populated counters of all associated cgroups accordingly. */ static void css_set_update_populated(struct css_set *cset, bool populated) { @@ -653,7 +658,7 @@ static void css_set_update_populated(struct css_set *cset, bool populated) * css_set, @from_cset can be NULL. If @task is being disassociated * instead of moved, @to_cset can be NULL. * - * This function automatically handles populated_cnt updates and + * This function automatically handles populated counter updates and * css_task_iter adjustments but the caller is responsible for managing * @from_cset and @to_cset's reference counts. */ -- cgit v1.2.3 From 27f26753f8c063c4cd2f06318e977ae136574b28 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 16 Jul 2017 21:44:18 -0400 Subject: cgroup: replace css_set walking populated test with testing cgrp->nr_populated_csets Implement trivial cgroup_has_tasks() which tests whether cgrp->nr_populated_csets is zero and replace the explicit local populated test in cgroup_subtree_control(). This simplifies the code and cgroup_has_tasks() will be used in more places later. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 30 ++++++++---------------------- 1 file changed, 8 insertions(+), 22 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 5fe2644cd0f3..d5b62313c753 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -325,6 +325,11 @@ static struct cgroup *cgroup_parent(struct cgroup *cgrp) return NULL; } +static bool cgroup_has_tasks(struct cgroup *cgrp) +{ + return cgrp->nr_populated_csets; +} + /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { @@ -2971,28 +2976,9 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, * Except for the root, subtree_control must be zero for a cgroup * with tasks so that child cgroups don't compete against tasks. */ - if (enable && cgroup_parent(cgrp)) { - struct cgrp_cset_link *link; - - /* - * Because namespaces pin csets too, @cgrp->cset_links - * might not be empty even when @cgrp is empty. Walk and - * verify each cset. - */ - spin_lock_irq(&css_set_lock); - - ret = 0; - list_for_each_entry(link, &cgrp->cset_links, cset_link) { - if (css_set_populated(link->cset)) { - ret = -EBUSY; - break; - } - } - - spin_unlock_irq(&css_set_lock); - - if (ret) - goto out_unlock; + if (enable && cgroup_parent(cgrp) && cgroup_has_tasks(cgrp)) { + ret = -EBUSY; + goto out_unlock; } /* save and update control masks and prepare csses */ -- cgit v1.2.3 From 7af608e4f9530372aec6e940552bf76595f2e265 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 18 Jul 2017 17:57:46 -0400 Subject: cgroup: create dfl_root files on subsys registration On subsystem registration, css_populate_dir() is not called on the new root css, so the interface files for the subsystem on cgrp_dfl_root aren't created on registration. This is a residue from the days when cgrp_dfl_root was used only as the parking spot for unused subsystems, which no longer is true as it's used as the root for cgroup2. This is often fine as later operations tend to create them as a part of mount (cgroup1) or subtree_control operations (cgroup2); however, it's not difficult to mount cgroup2 with the controller interface files missing as Waiman found out. Fix it by invoking css_populate_dir() on the root css on subsys registration. Signed-off-by: Tejun Heo Reported-and-tested-by: Waiman Long Cc: stable@vger.kernel.org # v4.5+ Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cc53111072d8..744975947d01 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4673,6 +4673,10 @@ int __init cgroup_init(void) if (ss->bind) ss->bind(init_css_set.subsys[ssid]); + + mutex_lock(&cgroup_mutex); + css_populate_dir(init_css_set.subsys[ssid]); + mutex_unlock(&cgroup_mutex); } /* init_css_set.subsys[] has been updated, re-hash */ -- cgit v1.2.3 From 715c809d9a9e38d8fb9476757ddaf64c1a9f767f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:00 -0400 Subject: cgroup: reorganize cgroup.procs / task write path Currently, writes "cgroup.procs" and "cgroup.tasks" files are all handled by __cgroup_procs_write() on both v1 and v2. This patch reoragnizes the write path so that there are common helper functions that different write paths use. While this somewhat increases LOC, the different paths are no longer intertwined and each path has more flexibility to implement different behaviors which will be necessary for the planned v2 thread support. v3: - Restructured so that cgroup_procs_write_permission() takes @src_cgrp and @dst_cgrp. v2: - Rolled in Waiman's task reference count fix. - Updated on top of nsdelegate changes. Signed-off-by: Tejun Heo Cc: Waiman Long --- kernel/cgroup/cgroup-internal.h | 8 +- kernel/cgroup/cgroup-v1.c | 58 ++++++++++-- kernel/cgroup/cgroup.c | 192 ++++++++++++++++++++-------------------- 3 files changed, 152 insertions(+), 106 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 793565c05742..0e81c6109e91 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -180,10 +180,10 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup, int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); -ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, loff_t off, bool threadgroup); -ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, - loff_t off); +struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup) + __acquires(&cgroup_threadgroup_rwsem); +void cgroup_procs_write_finish(struct task_struct *task) + __releases(&cgroup_threadgroup_rwsem); void cgroup_lock_and_drain_offline(struct cgroup *cgrp); diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 7bf4b1533f34..60f72475863e 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -510,10 +510,58 @@ static int cgroup_pidlist_show(struct seq_file *s, void *v) return 0; } -static ssize_t cgroup_tasks_write(struct kernfs_open_file *of, - char *buf, size_t nbytes, loff_t off) +static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off, + bool threadgroup) { - return __cgroup_procs_write(of, buf, nbytes, off, false); + struct cgroup *cgrp; + struct task_struct *task; + const struct cred *cred, *tcred; + ssize_t ret; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENODEV; + + task = cgroup_procs_write_start(buf, threadgroup); + ret = PTR_ERR_OR_ZERO(task); + if (ret) + goto out_unlock; + + /* + * Even if we're attaching all tasks in the thread group, we only + * need to check permissions on one of them. + */ + cred = current_cred(); + tcred = get_task_cred(task); + if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && + !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->euid, tcred->suid)) + ret = -EACCES; + put_cred(tcred); + if (ret) + goto out_finish; + + ret = cgroup_attach_task(cgrp, task, threadgroup); + +out_finish: + cgroup_procs_write_finish(task); +out_unlock: + cgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + +static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup1_procs_write(of, buf, nbytes, off, true); +} + +static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, @@ -592,7 +640,7 @@ struct cftype cgroup1_base_files[] = { .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, - .write = cgroup_procs_write, + .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", @@ -611,7 +659,7 @@ struct cftype cgroup1_base_files[] = { .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, - .write = cgroup_tasks_write, + .write = cgroup1_tasks_write, }, { .name = "notify_on_release", diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d5b62313c753..e3bda0752501 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2421,96 +2421,23 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, return ret; } -static int cgroup_procs_write_permission(struct task_struct *task, - struct cgroup *dst_cgrp, - struct kernfs_open_file *of) -{ - struct super_block *sb = of->file->f_path.dentry->d_sb; - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; - struct cgroup *root_cgrp = ns->root_cset->dfl_cgrp; - struct cgroup *src_cgrp, *com_cgrp; - struct inode *inode; - int ret; - - if (!cgroup_on_dfl(dst_cgrp)) { - const struct cred *cred = current_cred(); - const struct cred *tcred = get_task_cred(task); - - /* - * even if we're attaching all tasks in the thread group, - * we only need to check permissions on one of them. - */ - if (uid_eq(cred->euid, GLOBAL_ROOT_UID) || - uid_eq(cred->euid, tcred->uid) || - uid_eq(cred->euid, tcred->suid)) - ret = 0; - else - ret = -EACCES; - - put_cred(tcred); - return ret; - } - - /* find the source cgroup */ - spin_lock_irq(&css_set_lock); - src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); - spin_unlock_irq(&css_set_lock); - - /* and the common ancestor */ - com_cgrp = src_cgrp; - while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) - com_cgrp = cgroup_parent(com_cgrp); - - /* %current should be authorized to migrate to the common ancestor */ - inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn); - if (!inode) - return -ENOMEM; - - ret = inode_permission(inode, MAY_WRITE); - iput(inode); - if (ret) - return ret; - - /* - * If namespaces are delegation boundaries, %current must be able - * to see both source and destination cgroups from its namespace. - */ - if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && - (!cgroup_is_descendant(src_cgrp, root_cgrp) || - !cgroup_is_descendant(dst_cgrp, root_cgrp))) - return -ENOENT; - - return 0; -} - -/* - * Find the task_struct of the task to attach by vpid and pass it along to the - * function to attach either it or all tasks in its threadgroup. Will lock - * cgroup_mutex and threadgroup. - */ -ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, - size_t nbytes, loff_t off, bool threadgroup) +struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup) + __acquires(&cgroup_threadgroup_rwsem) { struct task_struct *tsk; - struct cgroup_subsys *ss; - struct cgroup *cgrp; pid_t pid; - int ssid, ret; if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0) - return -EINVAL; - - cgrp = cgroup_kn_lock_live(of->kn, false); - if (!cgrp) - return -ENODEV; + return ERR_PTR(-EINVAL); percpu_down_write(&cgroup_threadgroup_rwsem); + rcu_read_lock(); if (pid) { tsk = find_task_by_vpid(pid); if (!tsk) { - ret = -ESRCH; - goto out_unlock_rcu; + tsk = ERR_PTR(-ESRCH); + goto out_unlock_threadgroup; } } else { tsk = current; @@ -2526,35 +2453,33 @@ ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf, * cgroup with no rt_runtime allocated. Just say no. */ if (tsk->no_cgroup_migration || (tsk->flags & PF_NO_SETAFFINITY)) { - ret = -EINVAL; - goto out_unlock_rcu; + tsk = ERR_PTR(-EINVAL); + goto out_unlock_threadgroup; } get_task_struct(tsk); + goto out_unlock_rcu; + +out_unlock_threadgroup: + percpu_up_write(&cgroup_threadgroup_rwsem); +out_unlock_rcu: rcu_read_unlock(); + return tsk; +} - ret = cgroup_procs_write_permission(tsk, cgrp, of); - if (!ret) - ret = cgroup_attach_task(cgrp, tsk, threadgroup); +void cgroup_procs_write_finish(struct task_struct *task) + __releases(&cgroup_threadgroup_rwsem) +{ + struct cgroup_subsys *ss; + int ssid; - put_task_struct(tsk); - goto out_unlock_threadgroup; + /* release reference from cgroup_procs_write_start() */ + put_task_struct(task); -out_unlock_rcu: - rcu_read_unlock(); -out_unlock_threadgroup: percpu_up_write(&cgroup_threadgroup_rwsem); for_each_subsys(ss, ssid) if (ss->post_attach) ss->post_attach(); - cgroup_kn_unlock(of->kn); - return ret ?: nbytes; -} - -ssize_t cgroup_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, - loff_t off) -{ - return __cgroup_procs_write(of, buf, nbytes, off, true); } static void cgroup_print_ss_mask(struct seq_file *seq, u16 ss_mask) @@ -3870,6 +3795,79 @@ static int cgroup_procs_show(struct seq_file *s, void *v) return 0; } +static int cgroup_procs_write_permission(struct cgroup *src_cgrp, + struct cgroup *dst_cgrp, + struct super_block *sb) +{ + struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; + struct cgroup *com_cgrp = src_cgrp; + struct inode *inode; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* find the common ancestor */ + while (!cgroup_is_descendant(dst_cgrp, com_cgrp)) + com_cgrp = cgroup_parent(com_cgrp); + + /* %current should be authorized to migrate to the common ancestor */ + inode = kernfs_get_inode(sb, com_cgrp->procs_file.kn); + if (!inode) + return -ENOMEM; + + ret = inode_permission(inode, MAY_WRITE); + iput(inode); + if (ret) + return ret; + + /* + * If namespaces are delegation boundaries, %current must be able + * to see both source and destination cgroups from its namespace. + */ + if ((cgrp_dfl_root.flags & CGRP_ROOT_NS_DELEGATE) && + (!cgroup_is_descendant(src_cgrp, ns->root_cset->dfl_cgrp) || + !cgroup_is_descendant(dst_cgrp, ns->root_cset->dfl_cgrp))) + return -ENOENT; + + return 0; +} + +static ssize_t cgroup_procs_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *src_cgrp, *dst_cgrp; + struct task_struct *task; + ssize_t ret; + + dst_cgrp = cgroup_kn_lock_live(of->kn, false); + if (!dst_cgrp) + return -ENODEV; + + task = cgroup_procs_write_start(buf, true); + ret = PTR_ERR_OR_ZERO(task); + if (ret) + goto out_unlock; + + /* find the source cgroup */ + spin_lock_irq(&css_set_lock); + src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); + spin_unlock_irq(&css_set_lock); + + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, + of->file->f_path.dentry->d_sb); + if (ret) + goto out_finish; + + ret = cgroup_attach_task(dst_cgrp, task, true); + +out_finish: + cgroup_procs_write_finish(task); +out_unlock: + cgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { { -- cgit v1.2.3 From bc2fb7ed089ffd16d26e1d95b898a37d2b37d201 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:01 -0400 Subject: cgroup: add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS css_task_iter currently always walks all tasks. With the scheduled cgroup v2 thread support, the iterator would need to handle multiple types of iteration. As a preparation, add @flags to css_task_iter_start() and implement CSS_TASK_ITER_PROCS. If the flag is not specified, it walks all tasks as before. When asserted, the iterator only walks the group leaders. For now, the only user of the flag is cgroup v2 "cgroup.procs" file which no longer needs to skip non-leader tasks in cgroup_procs_next(). Note that cgroup v1 "cgroup.procs" can't use the group leader walk as v1 "cgroup.procs" doesn't mean "list all thread group leaders in the cgroup" but "list all thread group id's with any threads in the cgroup". While at it, update cgroup_procs_show() to use task_pid_vnr() instead of task_tgid_vnr(). As the iteration guarantees that the function only sees group leaders, this doesn't change the output and will allow sharing the function for thread iteration. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-v1.c | 6 +++--- kernel/cgroup/cgroup.c | 24 ++++++++++++++---------- kernel/cgroup/cpuset.c | 6 +++--- kernel/cgroup/freezer.c | 6 +++--- 4 files changed, 23 insertions(+), 19 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 60f72475863e..167aaab04bf9 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -121,7 +121,7 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) * ->can_attach() fails. */ do { - css_task_iter_start(&from->self, &it); + css_task_iter_start(&from->self, 0, &it); task = css_task_iter_next(&it); if (task) get_task_struct(task); @@ -373,7 +373,7 @@ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, if (!array) return -ENOMEM; /* now, populate the array */ - css_task_iter_start(&cgrp->self, &it); + css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; @@ -749,7 +749,7 @@ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) } rcu_read_unlock(); - css_task_iter_start(&cgrp->self, &it); + css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e3bda0752501..3c5a37a9a892 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3643,6 +3643,7 @@ static void css_task_iter_advance(struct css_task_iter *it) lockdep_assert_held(&css_set_lock); WARN_ON_ONCE(!l); +repeat: /* * Advance iterator to find next entry. cset->tasks is consumed * first and then ->mg_tasks. After ->mg_tasks, we move onto the @@ -3657,11 +3658,18 @@ static void css_task_iter_advance(struct css_task_iter *it) css_task_iter_advance_css_set(it); else it->task_pos = l; + + /* if PROCS, skip over tasks which aren't group leaders */ + if ((it->flags & CSS_TASK_ITER_PROCS) && it->task_pos && + !thread_group_leader(list_entry(it->task_pos, struct task_struct, + cg_list))) + goto repeat; } /** * css_task_iter_start - initiate task iteration * @css: the css to walk tasks of + * @flags: CSS_TASK_ITER_* flags * @it: the task iterator to use * * Initiate iteration through the tasks of @css. The caller can call @@ -3669,7 +3677,7 @@ static void css_task_iter_advance(struct css_task_iter *it) * returns NULL. On completion of iteration, css_task_iter_end() must be * called. */ -void css_task_iter_start(struct cgroup_subsys_state *css, +void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { /* no one should try to iterate before mounting cgroups */ @@ -3680,6 +3688,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, spin_lock_irq(&css_set_lock); it->ss = css->ss; + it->flags = flags; if (it->ss) it->cset_pos = &css->cgroup->e_csets[css->ss->id]; @@ -3753,13 +3762,8 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct css_task_iter *it = of->priv; - struct task_struct *task; - - do { - task = css_task_iter_next(it); - } while (task && !thread_group_leader(task)); - return task; + return css_task_iter_next(it); } static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) @@ -3780,10 +3784,10 @@ static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) if (!it) return ERR_PTR(-ENOMEM); of->priv = it; - css_task_iter_start(&cgrp->self, it); + css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS, it); } else if (!(*pos)++) { css_task_iter_end(it); - css_task_iter_start(&cgrp->self, it); + css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS, it); } return cgroup_procs_next(s, NULL, NULL); @@ -3791,7 +3795,7 @@ static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) static int cgroup_procs_show(struct seq_file *s, void *v) { - seq_printf(s, "%d\n", task_tgid_vnr(v)); + seq_printf(s, "%d\n", task_pid_vnr(v)); return 0; } diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ca8376e5008c..252d70c9a49b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -861,7 +861,7 @@ static void update_tasks_cpumask(struct cpuset *cs) struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&cs->css, &it); + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) set_cpus_allowed_ptr(task, cs->effective_cpus); css_task_iter_end(&it); @@ -1091,7 +1091,7 @@ static void update_tasks_nodemask(struct cpuset *cs) * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ - css_task_iter_start(&cs->css, &it); + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; @@ -1284,7 +1284,7 @@ static void update_tasks_flags(struct cpuset *cs) struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&cs->css, &it); + css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); diff --git a/kernel/cgroup/freezer.c b/kernel/cgroup/freezer.c index 1b72d56edce5..08236798d173 100644 --- a/kernel/cgroup/freezer.c +++ b/kernel/cgroup/freezer.c @@ -268,7 +268,7 @@ static void update_if_frozen(struct cgroup_subsys_state *css) rcu_read_unlock(); /* are all tasks frozen? */ - css_task_iter_start(css, &it); + css_task_iter_start(css, 0, &it); while ((task = css_task_iter_next(&it))) { if (freezing(task)) { @@ -320,7 +320,7 @@ static void freeze_cgroup(struct freezer *freezer) struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&freezer->css, &it); + css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) freeze_task(task); css_task_iter_end(&it); @@ -331,7 +331,7 @@ static void unfreeze_cgroup(struct freezer *freezer) struct css_task_iter it; struct task_struct *task; - css_task_iter_start(&freezer->css, &it); + css_task_iter_start(&freezer->css, 0, &it); while ((task = css_task_iter_next(&it))) __thaw_task(task); css_task_iter_end(&it); -- cgit v1.2.3 From 454000adaa2a7420df6e56a42f22726d05872a3f Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:02 -0400 Subject: cgroup: introduce cgroup->dom_cgrp and threaded css_set handling cgroup v2 is in the process of growing thread granularity support. A threaded subtree is composed of a thread root and threaded cgroups which are proper members of the subtree. The root cgroup of the subtree serves as the domain cgroup to which the processes (as opposed to threads / tasks) of the subtree conceptually belong and domain-level resource consumptions not tied to any specific task are charged. Inside the subtree, threads won't be subject to process granularity or no-internal-task constraint and can be distributed arbitrarily across the subtree. This patch introduces cgroup->dom_cgrp along with threaded css_set handling. * cgroup->dom_cgrp points to self for normal and thread roots. For proper thread subtree members, points to the dom_cgrp (the thread root). * css_set->dom_cset points to self if for normal and thread roots. If threaded, points to the css_set which belongs to the cgrp->dom_cgrp. The dom_cgrp serves as the resource domain and keeps the matching csses available. The dom_cset holds those csses and makes them easily accessible. * All threaded csets are linked on their dom_csets to enable iteration of all threaded tasks. * cgroup->nr_threaded_children keeps track of the number of threaded children. This patch adds the above but doesn't actually use them yet. The following patches will build on top. v4: ->nr_threaded_children added. v3: ->proc_cgrp/cset renamed to ->dom_cgrp/cset. Updated for the new enable-threaded-per-cgroup behavior. v2: Added cgroup_is_threaded() helper. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 66 insertions(+), 3 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 3c5a37a9a892..c7e1c243b77d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -330,6 +330,11 @@ static bool cgroup_has_tasks(struct cgroup *cgrp) return cgrp->nr_populated_csets; } +static bool cgroup_is_threaded(struct cgroup *cgrp) +{ + return cgrp->dom_cgrp != cgrp; +} + /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { @@ -565,9 +570,11 @@ EXPORT_SYMBOL_GPL(of_css); */ struct css_set init_css_set = { .refcount = REFCOUNT_INIT(1), + .dom_cset = &init_css_set, .tasks = LIST_HEAD_INIT(init_css_set.tasks), .mg_tasks = LIST_HEAD_INIT(init_css_set.mg_tasks), .task_iters = LIST_HEAD_INIT(init_css_set.task_iters), + .threaded_csets = LIST_HEAD_INIT(init_css_set.threaded_csets), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), @@ -575,6 +582,11 @@ struct css_set init_css_set = { static int css_set_count = 1; /* 1 for init_css_set */ +static bool css_set_threaded(struct css_set *cset) +{ + return cset->dom_cset != cset; +} + /** * css_set_populated - does a css_set contain any tasks? * @cset: target css_set @@ -618,10 +630,14 @@ static void cgroup_update_populated(struct cgroup *cgrp, bool populated) do { bool was_populated = cgroup_is_populated(cgrp); - if (!child) + if (!child) { cgrp->nr_populated_csets += adj; - else - cgrp->nr_populated_children += adj; + } else { + if (cgroup_is_threaded(child)) + cgrp->nr_populated_threaded_children += adj; + else + cgrp->nr_populated_domain_children += adj; + } if (was_populated == cgroup_is_populated(cgrp)) break; @@ -747,6 +763,8 @@ void put_css_set_locked(struct css_set *cset) if (!refcount_dec_and_test(&cset->refcount)) return; + WARN_ON_ONCE(!list_empty(&cset->threaded_csets)); + /* 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]); @@ -763,6 +781,11 @@ void put_css_set_locked(struct css_set *cset) kfree(link); } + if (css_set_threaded(cset)) { + list_del(&cset->threaded_csets_node); + put_css_set_locked(cset->dom_cset); + } + kfree_rcu(cset, rcu_head); } @@ -781,6 +804,7 @@ static bool compare_css_sets(struct css_set *cset, struct cgroup *new_cgrp, struct cgroup_subsys_state *template[]) { + struct cgroup *new_dfl_cgrp; struct list_head *l1, *l2; /* @@ -791,6 +815,16 @@ static bool compare_css_sets(struct css_set *cset, if (memcmp(template, cset->subsys, sizeof(cset->subsys))) return false; + + /* @cset's domain should match the default cgroup's */ + if (cgroup_on_dfl(new_cgrp)) + new_dfl_cgrp = new_cgrp; + else + new_dfl_cgrp = old_cset->dfl_cgrp; + + if (new_dfl_cgrp->dom_cgrp != cset->dom_cset->dfl_cgrp) + return false; + /* * Compare cgroup pointers in order to distinguish between * different cgroups in hierarchies. As different cgroups may @@ -998,9 +1032,11 @@ static struct css_set *find_css_set(struct css_set *old_cset, } refcount_set(&cset->refcount, 1); + cset->dom_cset = cset; INIT_LIST_HEAD(&cset->tasks); INIT_LIST_HEAD(&cset->mg_tasks); INIT_LIST_HEAD(&cset->task_iters); + INIT_LIST_HEAD(&cset->threaded_csets); INIT_HLIST_NODE(&cset->hlist); INIT_LIST_HEAD(&cset->cgrp_links); INIT_LIST_HEAD(&cset->mg_preload_node); @@ -1038,6 +1074,28 @@ static struct css_set *find_css_set(struct css_set *old_cset, spin_unlock_irq(&css_set_lock); + /* + * If @cset should be threaded, look up the matching dom_cset and + * link them up. We first fully initialize @cset then look for the + * dom_cset. It's simpler this way and safe as @cset is guaranteed + * to stay empty until we return. + */ + if (cgroup_is_threaded(cset->dfl_cgrp)) { + struct css_set *dcset; + + dcset = find_css_set(cset, cset->dfl_cgrp->dom_cgrp); + if (!dcset) { + put_css_set(cset); + return NULL; + } + + spin_lock_irq(&css_set_lock); + cset->dom_cset = dcset; + list_add_tail(&cset->threaded_csets_node, + &dcset->threaded_csets); + spin_unlock_irq(&css_set_lock); + } + return cset; } @@ -1680,6 +1738,7 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) mutex_init(&cgrp->pidlist_mutex); cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; + cgrp->dom_cgrp = cgrp; for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); @@ -4408,6 +4467,7 @@ static void kill_css(struct cgroup_subsys_state *css) static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { + struct cgroup *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; @@ -4452,6 +4512,9 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) */ kernfs_remove(cgrp->kn); + if (parent && cgroup_is_threaded(cgrp)) + parent->nr_threaded_children--; + cgroup1_check_for_release(cgroup_parent(cgrp)); /* put the base reference */ -- cgit v1.2.3 From 450ee0c1feed657894e0b4bdd48f3974af9d394c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 15 May 2017 09:34:03 -0400 Subject: cgroup: implement CSS_TASK_ITER_THREADED cgroup v2 is in the process of growing thread granularity support. Once thread mode is enabled, the root cgroup of the subtree serves as the dom_cgrp to which the processes of the subtree conceptually belong and domain-level resource consumptions not tied to any specific task are charged. In the subtree, threads won't be subject to process granularity or no-internal-task constraint and can be distributed arbitrarily across the subtree. This patch implements a new task iterator flag CSS_TASK_ITER_THREADED, which, when used on a dom_cgrp, makes the iteration include the tasks on all the associated threaded css_sets. "cgroup.procs" read path is updated to use it so that reading the file on a proc_cgrp lists all processes. This will also be used by controller implementations which need to walk processes or tasks at the resource domain level. Task iteration is implemented nested in css_set iteration. If CSS_TASK_ITER_THREADED is specified, after walking tasks of each !threaded css_set, all the associated threaded css_sets are visited before moving onto the next !threaded css_set. v2: ->cur_pcset renamed to ->cur_dcset. Updated for the new enable-threaded-per-cgroup behavior. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 77 +++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 60 insertions(+), 17 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c7e1c243b77d..a1d59af274a9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3629,6 +3629,58 @@ bool css_has_online_children(struct cgroup_subsys_state *css) return ret; } +static struct css_set *css_task_iter_next_css_set(struct css_task_iter *it) +{ + struct list_head *l; + struct cgrp_cset_link *link; + struct css_set *cset; + + lockdep_assert_held(&css_set_lock); + + /* find the next threaded cset */ + if (it->tcset_pos) { + l = it->tcset_pos->next; + + if (l != it->tcset_head) { + it->tcset_pos = l; + return container_of(l, struct css_set, + threaded_csets_node); + } + + it->tcset_pos = NULL; + } + + /* find the next cset */ + l = it->cset_pos; + l = l->next; + if (l == it->cset_head) { + it->cset_pos = NULL; + return NULL; + } + + if (it->ss) { + cset = container_of(l, struct css_set, e_cset_node[it->ss->id]); + } else { + link = list_entry(l, struct cgrp_cset_link, cset_link); + cset = link->cset; + } + + it->cset_pos = l; + + /* initialize threaded css_set walking */ + if (it->flags & CSS_TASK_ITER_THREADED) { + if (it->cur_dcset) + put_css_set_locked(it->cur_dcset); + it->cur_dcset = cset; + get_css_set(cset); + + it->tcset_head = &cset->threaded_csets; + it->tcset_pos = &cset->threaded_csets; + } + + return cset; +} + /** * css_task_iter_advance_css_set - advance a task itererator to the next css_set * @it: the iterator to advance @@ -3637,32 +3689,19 @@ bool css_has_online_children(struct cgroup_subsys_state *css) */ static void css_task_iter_advance_css_set(struct css_task_iter *it) { - struct list_head *l = it->cset_pos; - struct cgrp_cset_link *link; struct css_set *cset; lockdep_assert_held(&css_set_lock); /* Advance to the next non-empty css_set */ do { - l = l->next; - if (l == it->cset_head) { - it->cset_pos = NULL; + cset = css_task_iter_next_css_set(it); + if (!cset) { it->task_pos = NULL; return; } - - if (it->ss) { - cset = container_of(l, struct css_set, - e_cset_node[it->ss->id]); - } else { - link = list_entry(l, struct cgrp_cset_link, cset_link); - cset = link->cset; - } } while (!css_set_populated(cset)); - it->cset_pos = l; - if (!list_empty(&cset->tasks)) it->task_pos = cset->tasks.next; else @@ -3805,6 +3844,9 @@ void css_task_iter_end(struct css_task_iter *it) spin_unlock_irq(&css_set_lock); } + if (it->cur_dcset) + put_css_set(it->cur_dcset); + if (it->cur_task) put_task_struct(it->cur_task); } @@ -3830,6 +3872,7 @@ static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct css_task_iter *it = of->priv; + unsigned iter_flags = CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED; /* * When a seq_file is seeked, it's always traversed sequentially @@ -3843,10 +3886,10 @@ static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) if (!it) return ERR_PTR(-ENOMEM); of->priv = it; - css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS, it); + css_task_iter_start(&cgrp->self, iter_flags, it); } else if (!(*pos)++) { css_task_iter_end(it); - css_task_iter_start(&cgrp->self, CSS_TASK_ITER_PROCS, it); + css_task_iter_start(&cgrp->self, iter_flags, it); } return cgroup_procs_next(s, NULL, NULL); -- cgit v1.2.3 From 8cfd8147df67e741d93b8783a3ea8f3c74f93a0e Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 21 Jul 2017 11:14:51 -0400 Subject: cgroup: implement cgroup v2 thread support This patch implements cgroup v2 thread support. The goal of the thread mode is supporting hierarchical accounting and control at thread granularity while staying inside the resource domain model which allows coordination across different resource controllers and handling of anonymous resource consumptions. A cgroup is always created as a domain and can be made threaded by writing to the "cgroup.type" file. When a cgroup becomes threaded, it becomes a member of a threaded subtree which is anchored at the closest ancestor which isn't threaded. The threads of the processes which are in a threaded subtree can be placed anywhere without being restricted by process granularity or no-internal-process constraint. Note that the threads aren't allowed to escape to a different threaded subtree. To be used inside a threaded subtree, a controller should explicitly support threaded mode and be able to handle internal competition in the way which is appropriate for the resource. The root of a threaded subtree, the nearest ancestor which isn't threaded, is called the threaded domain and serves as the resource domain for the whole subtree. This is the last cgroup where domain controllers are operational and where all the domain-level resource consumptions in the subtree are accounted. This allows threaded controllers to operate at thread granularity when requested while staying inside the scope of system-level resource distribution. As the root cgroup is exempt from the no-internal-process constraint, it can serve as both a threaded domain and a parent to normal cgroups, so, unlike non-root cgroups, the root cgroup can have both domain and threaded children. Internally, in a threaded subtree, each css_set has its ->dom_cset pointing to a matching css_set which belongs to the threaded domain. This ensures that thread root level cgroup_subsys_state for all threaded controllers are readily accessible for domain-level operations. This patch enables threaded mode for the pids and perf_events controllers. Neither has to worry about domain-level resource consumptions and it's enough to simply set the flag. For more details on the interface and behavior of the thread mode, please refer to the section 2-2-2 in Documentation/cgroup-v2.txt added by this patch. v5: - Dropped silly no-op ->dom_cgrp init from cgroup_create(). Spotted by Waiman. - Documentation updated as suggested by Waiman. - cgroup.type content slightly reformatted. - Mark the debug controller threaded. v4: - Updated to the general idea of marking specific cgroups domain/threaded as suggested by PeterZ. v3: - Dropped "join" and always make mixed children join the parent's threaded subtree. v2: - After discussions with Waiman, support for mixed thread mode is added. This should address the issue that Peter pointed out where any nesting should be avoided for thread subtrees while coexisting with other domain cgroups. - Enabling / disabling thread mode now piggy backs on the existing control mask update mechanism. - Bug fixes and cleanup. Signed-off-by: Tejun Heo Cc: Waiman Long Cc: Peter Zijlstra --- kernel/cgroup/cgroup-internal.h | 2 +- kernel/cgroup/cgroup-v1.c | 5 +- kernel/cgroup/cgroup.c | 355 +++++++++++++++++++++++++++++++++++++--- kernel/cgroup/debug.c | 1 + kernel/cgroup/pids.c | 1 + 5 files changed, 339 insertions(+), 25 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 0e81c6109e91..f10eb19ddf04 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -170,7 +170,7 @@ struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags, struct cgroup_root *root, unsigned long magic, struct cgroup_namespace *ns); -bool cgroup_may_migrate_to(struct cgroup *dst_cgrp); +int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); void cgroup_migrate_add_src(struct css_set *src_cset, struct cgroup *dst_cgrp, struct cgroup_mgctx *mgctx); diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 167aaab04bf9..f0e8601b13cb 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -99,8 +99,9 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) if (cgroup_on_dfl(to)) return -EINVAL; - if (!cgroup_may_migrate_to(to)) - return -EBUSY; + ret = cgroup_migrate_vet_dst(to); + if (ret) + return ret; mutex_lock(&cgroup_mutex); diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a1d59af274a9..c396e701c206 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -162,6 +162,9 @@ static u16 cgrp_dfl_inhibit_ss_mask; /* some controllers are implicitly enabled on the default hierarchy */ static u16 cgrp_dfl_implicit_ss_mask; +/* some controllers can be threaded on the default hierarchy */ +static u16 cgrp_dfl_threaded_ss_mask; + /* The list of hierarchy roots */ LIST_HEAD(cgroup_roots); static int cgroup_root_count; @@ -335,14 +338,93 @@ static bool cgroup_is_threaded(struct cgroup *cgrp) return cgrp->dom_cgrp != cgrp; } +/* can @cgrp host both domain and threaded children? */ +static bool cgroup_is_mixable(struct cgroup *cgrp) +{ + /* + * Root isn't under domain level resource control exempting it from + * the no-internal-process constraint, so it can serve as a thread + * root and a parent of resource domains at the same time. + */ + return !cgroup_parent(cgrp); +} + +/* can @cgrp become a thread root? should always be true for a thread root */ +static bool cgroup_can_be_thread_root(struct cgroup *cgrp) +{ + /* mixables don't care */ + if (cgroup_is_mixable(cgrp)) + return true; + + /* domain roots can't be nested under threaded */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* can only have either domain or threaded children */ + if (cgrp->nr_populated_domain_children) + return false; + + /* and no domain controllers can be enabled */ + if (cgrp->subtree_control & ~cgrp_dfl_threaded_ss_mask) + return false; + + return true; +} + +/* is @cgrp root of a threaded subtree? */ +static bool cgroup_is_thread_root(struct cgroup *cgrp) +{ + /* thread root should be a domain */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* a domain w/ threaded children is a thread root */ + if (cgrp->nr_threaded_children) + return true; + + /* + * A domain which has tasks and explicit threaded controllers + * enabled is a thread root. + */ + if (cgroup_has_tasks(cgrp) && + (cgrp->subtree_control & cgrp_dfl_threaded_ss_mask)) + return true; + + return false; +} + +/* a domain which isn't connected to the root w/o brekage can't be used */ +static bool cgroup_is_valid_domain(struct cgroup *cgrp) +{ + /* the cgroup itself can be a thread root */ + if (cgroup_is_threaded(cgrp)) + return false; + + /* but the ancestors can't be unless mixable */ + while ((cgrp = cgroup_parent(cgrp))) { + if (!cgroup_is_mixable(cgrp) && cgroup_is_thread_root(cgrp)) + return false; + if (cgroup_is_threaded(cgrp)) + return false; + } + + return true; +} + /* subsystems visibly enabled on a cgroup */ static u16 cgroup_control(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); u16 root_ss_mask = cgrp->root->subsys_mask; - if (parent) - return parent->subtree_control; + if (parent) { + u16 ss_mask = parent->subtree_control; + + /* threaded cgroups can only have threaded controllers */ + if (cgroup_is_threaded(cgrp)) + ss_mask &= cgrp_dfl_threaded_ss_mask; + return ss_mask; + } if (cgroup_on_dfl(cgrp)) root_ss_mask &= ~(cgrp_dfl_inhibit_ss_mask | @@ -355,8 +437,14 @@ static u16 cgroup_ss_mask(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); - if (parent) - return parent->subtree_ss_mask; + if (parent) { + u16 ss_mask = parent->subtree_ss_mask; + + /* threaded cgroups can only have threaded controllers */ + if (cgroup_is_threaded(cgrp)) + ss_mask &= cgrp_dfl_threaded_ss_mask; + return ss_mask; + } return cgrp->root->subsys_mask; } @@ -2237,17 +2325,40 @@ out_release_tset: } /** - * cgroup_may_migrate_to - verify whether a cgroup can be migration destination + * cgroup_migrate_vet_dst - verify whether a cgroup can be migration destination * @dst_cgrp: destination cgroup to test * - * On the default hierarchy, except for the root, subtree_control must be - * zero for migration destination cgroups with tasks so that child cgroups - * don't compete against tasks. + * On the default hierarchy, except for the mixable, (possible) thread root + * and threaded cgroups, subtree_control must be zero for migration + * destination cgroups with tasks so that child cgroups don't compete + * against tasks. */ -bool cgroup_may_migrate_to(struct cgroup *dst_cgrp) +int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp) { - return !cgroup_on_dfl(dst_cgrp) || !cgroup_parent(dst_cgrp) || - !dst_cgrp->subtree_control; + /* v1 doesn't have any restriction */ + if (!cgroup_on_dfl(dst_cgrp)) + return 0; + + /* verify @dst_cgrp can host resources */ + if (!cgroup_is_valid_domain(dst_cgrp->dom_cgrp)) + return -EOPNOTSUPP; + + /* mixables don't care */ + if (cgroup_is_mixable(dst_cgrp)) + return 0; + + /* + * If @dst_cgrp is already or can become a thread root or is + * threaded, it doesn't matter. + */ + if (cgroup_can_be_thread_root(dst_cgrp) || cgroup_is_threaded(dst_cgrp)) + return 0; + + /* apply no-internal-process constraint */ + if (dst_cgrp->subtree_control) + return -EBUSY; + + return 0; } /** @@ -2452,8 +2563,9 @@ int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, struct task_struct *task; int ret; - if (!cgroup_may_migrate_to(dst_cgrp)) - return -EBUSY; + ret = cgroup_migrate_vet_dst(dst_cgrp); + if (ret) + return ret; /* look up all src csets */ spin_lock_irq(&css_set_lock); @@ -2881,6 +2993,46 @@ static void cgroup_finalize_control(struct cgroup *cgrp, int ret) cgroup_apply_control_disable(cgrp); } +static int cgroup_vet_subtree_control_enable(struct cgroup *cgrp, u16 enable) +{ + u16 domain_enable = enable & ~cgrp_dfl_threaded_ss_mask; + + /* if nothing is getting enabled, nothing to worry about */ + if (!enable) + return 0; + + /* can @cgrp host any resources? */ + if (!cgroup_is_valid_domain(cgrp->dom_cgrp)) + return -EOPNOTSUPP; + + /* mixables don't care */ + if (cgroup_is_mixable(cgrp)) + return 0; + + if (domain_enable) { + /* can't enable domain controllers inside a thread subtree */ + if (cgroup_is_thread_root(cgrp) || cgroup_is_threaded(cgrp)) + return -EOPNOTSUPP; + } else { + /* + * Threaded controllers can handle internal competitions + * and are always allowed inside a (prospective) thread + * subtree. + */ + if (cgroup_can_be_thread_root(cgrp) || cgroup_is_threaded(cgrp)) + return 0; + } + + /* + * Controllers can't be enabled for a cgroup with tasks to avoid + * child cgroups competing against tasks. + */ + if (cgroup_has_tasks(cgrp)) + return -EBUSY; + + return 0; +} + /* change the enabled child controllers for a cgroup in the default hierarchy */ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, char *buf, size_t nbytes, @@ -2956,14 +3108,9 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, goto out_unlock; } - /* - * Except for the root, subtree_control must be zero for a cgroup - * with tasks so that child cgroups don't compete against tasks. - */ - if (enable && cgroup_parent(cgrp) && cgroup_has_tasks(cgrp)) { - ret = -EBUSY; + ret = cgroup_vet_subtree_control_enable(cgrp, enable); + if (ret) goto out_unlock; - } /* save and update control masks and prepare csses */ cgroup_save_control(cgrp); @@ -2982,6 +3129,84 @@ out_unlock: return ret ?: nbytes; } +static int cgroup_enable_threaded(struct cgroup *cgrp) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup *dom_cgrp = parent->dom_cgrp; + int ret; + + lockdep_assert_held(&cgroup_mutex); + + /* noop if already threaded */ + if (cgroup_is_threaded(cgrp)) + return 0; + + /* we're joining the parent's domain, ensure its validity */ + if (!cgroup_is_valid_domain(dom_cgrp) || + !cgroup_can_be_thread_root(dom_cgrp)) + return -EOPNOTSUPP; + + /* + * Allow enabling thread mode only on empty cgroups to avoid + * implicit migrations and recursive operations. + */ + if (cgroup_has_tasks(cgrp) || css_has_online_children(&cgrp->self)) + return -EBUSY; + + /* + * The following shouldn't cause actual migrations and should + * always succeed. + */ + cgroup_save_control(cgrp); + + cgrp->dom_cgrp = dom_cgrp; + ret = cgroup_apply_control(cgrp); + if (!ret) + parent->nr_threaded_children++; + else + cgrp->dom_cgrp = cgrp; + + cgroup_finalize_control(cgrp, ret); + return ret; +} + +static int cgroup_type_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + + if (cgroup_is_threaded(cgrp)) + seq_puts(seq, "threaded\n"); + else if (!cgroup_is_valid_domain(cgrp)) + seq_puts(seq, "domain invalid\n"); + else if (cgroup_is_thread_root(cgrp)) + seq_puts(seq, "domain threaded\n"); + else + seq_puts(seq, "domain\n"); + + return 0; +} + +static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + int ret; + + /* only switching to threaded mode is supported */ + if (strcmp(strstrip(buf), "threaded")) + return -EINVAL; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + /* threaded can only be enabled */ + ret = cgroup_enable_threaded(cgrp); + + cgroup_kn_unlock(of->kn); + return ret ?: nbytes; +} + static int cgroup_events_show(struct seq_file *seq, void *v) { seq_printf(seq, "populated %d\n", @@ -3867,12 +4092,12 @@ static void *cgroup_procs_next(struct seq_file *s, void *v, loff_t *pos) return css_task_iter_next(it); } -static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) +static void *__cgroup_procs_start(struct seq_file *s, loff_t *pos, + unsigned int iter_flags) { struct kernfs_open_file *of = s->private; struct cgroup *cgrp = seq_css(s)->cgroup; struct css_task_iter *it = of->priv; - unsigned iter_flags = CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED; /* * When a seq_file is seeked, it's always traversed sequentially @@ -3895,6 +4120,23 @@ static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) return cgroup_procs_next(s, NULL, NULL); } +static void *cgroup_procs_start(struct seq_file *s, loff_t *pos) +{ + struct cgroup *cgrp = seq_css(s)->cgroup; + + /* + * All processes of a threaded subtree belong to the domain cgroup + * of the subtree. Only threads can be distributed across the + * subtree. Reject reads on cgroup.procs in the subtree proper. + * They're always empty anyway. + */ + if (cgroup_is_threaded(cgrp)) + return ERR_PTR(-EOPNOTSUPP); + + return __cgroup_procs_start(s, pos, CSS_TASK_ITER_PROCS | + CSS_TASK_ITER_THREADED); +} + static int cgroup_procs_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", task_pid_vnr(v)); @@ -3974,8 +4216,63 @@ out_unlock: return ret ?: nbytes; } +static void *cgroup_threads_start(struct seq_file *s, loff_t *pos) +{ + return __cgroup_procs_start(s, pos, 0); +} + +static ssize_t cgroup_threads_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *src_cgrp, *dst_cgrp; + struct task_struct *task; + ssize_t ret; + + buf = strstrip(buf); + + dst_cgrp = cgroup_kn_lock_live(of->kn, false); + if (!dst_cgrp) + return -ENODEV; + + task = cgroup_procs_write_start(buf, false); + ret = PTR_ERR_OR_ZERO(task); + if (ret) + goto out_unlock; + + /* find the source cgroup */ + spin_lock_irq(&css_set_lock); + src_cgrp = task_cgroup_from_root(task, &cgrp_dfl_root); + spin_unlock_irq(&css_set_lock); + + /* thread migrations follow the cgroup.procs delegation rule */ + ret = cgroup_procs_write_permission(src_cgrp, dst_cgrp, + of->file->f_path.dentry->d_sb); + if (ret) + goto out_finish; + + /* and must be contained in the same domain */ + ret = -EOPNOTSUPP; + if (src_cgrp->dom_cgrp != dst_cgrp->dom_cgrp) + goto out_finish; + + ret = cgroup_attach_task(dst_cgrp, task, false); + +out_finish: + cgroup_procs_write_finish(task); +out_unlock: + cgroup_kn_unlock(of->kn); + + return ret ?: nbytes; +} + /* cgroup core interface files for the default hierarchy */ static struct cftype cgroup_base_files[] = { + { + .name = "cgroup.type", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cgroup_type_show, + .write = cgroup_type_write, + }, { .name = "cgroup.procs", .flags = CFTYPE_NS_DELEGATABLE, @@ -3986,6 +4283,14 @@ static struct cftype cgroup_base_files[] = { .seq_show = cgroup_procs_show, .write = cgroup_procs_write, }, + { + .name = "cgroup.threads", + .release = cgroup_procs_release, + .seq_start = cgroup_threads_start, + .seq_next = cgroup_procs_next, + .seq_show = cgroup_procs_show, + .write = cgroup_threads_write, + }, { .name = "cgroup.controllers", .seq_show = cgroup_controllers_show, @@ -4753,11 +5058,17 @@ int __init cgroup_init(void) cgrp_dfl_root.subsys_mask |= 1 << ss->id; + /* implicit controllers must be threaded too */ + WARN_ON(ss->implicit_on_dfl && !ss->threaded); + if (ss->implicit_on_dfl) cgrp_dfl_implicit_ss_mask |= 1 << ss->id; else if (!ss->dfl_cftypes) cgrp_dfl_inhibit_ss_mask |= 1 << ss->id; + if (ss->threaded) + cgrp_dfl_threaded_ss_mask |= 1 << ss->id; + if (ss->dfl_cftypes == ss->legacy_cftypes) { WARN_ON(cgroup_add_cftypes(ss, ss->dfl_cftypes)); } else { diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c index dac46af22782..787a242fa69d 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -352,6 +352,7 @@ static int __init enable_cgroup_debug(char *str) { debug_cgrp_subsys.dfl_cftypes = debug_files; debug_cgrp_subsys.implicit_on_dfl = true; + debug_cgrp_subsys.threaded = true; return 1; } __setup("cgroup_debug", enable_cgroup_debug); diff --git a/kernel/cgroup/pids.c b/kernel/cgroup/pids.c index 2237201d66d5..9829c67ebc0a 100644 --- a/kernel/cgroup/pids.c +++ b/kernel/cgroup/pids.c @@ -345,4 +345,5 @@ struct cgroup_subsys pids_cgrp_subsys = { .free = pids_free, .legacy_cftypes = pids_files, .dfl_cftypes = pids_files, + .threaded = true, }; -- cgit v1.2.3 From 7a0cf0e74ab6cfd8e561f5f12860d4ff8844905a Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Fri, 21 Jul 2017 11:14:51 -0400 Subject: cgroup: update debug controller to print out thread mode information Update debug controller so that it prints out debug info about thread mode. 1) The relationship between proc_cset and threaded_csets are displayed. 2) The status of being a thread root or threaded cgroup is displayed. This patch is extracted from Waiman's larger patch. v2: - Removed [thread root] / [threaded] from debug.cgroup_css_links file as the same information is available from cgroup.type. Suggested by Waiman. - Threaded marking is moved to the previous patch. Patch-originally-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-internal.h | 2 ++ kernel/cgroup/cgroup.c | 4 ++-- kernel/cgroup/debug.c | 52 ++++++++++++++++++++++++++++++----------- 3 files changed, 42 insertions(+), 16 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index f10eb19ddf04..c167a40278e6 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -153,6 +153,8 @@ static inline void get_css_set(struct css_set *cset) bool cgroup_ssid_enabled(int ssid); bool cgroup_on_dfl(const struct cgroup *cgrp); +bool cgroup_is_thread_root(struct cgroup *cgrp); +bool cgroup_is_threaded(struct cgroup *cgrp); struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root); struct cgroup *task_cgroup_from_root(struct task_struct *task, diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c396e701c206..e9a377dc5bdb 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -333,7 +333,7 @@ static bool cgroup_has_tasks(struct cgroup *cgrp) return cgrp->nr_populated_csets; } -static bool cgroup_is_threaded(struct cgroup *cgrp) +bool cgroup_is_threaded(struct cgroup *cgrp) { return cgrp->dom_cgrp != cgrp; } @@ -372,7 +372,7 @@ static bool cgroup_can_be_thread_root(struct cgroup *cgrp) } /* is @cgrp root of a threaded subtree? */ -static bool cgroup_is_thread_root(struct cgroup *cgrp) +bool cgroup_is_thread_root(struct cgroup *cgrp) { /* thread root should be a domain */ if (cgroup_is_threaded(cgrp)) diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c index 787a242fa69d..f661b4cc5efd 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -114,27 +114,49 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) { struct cgroup_subsys_state *css = seq_css(seq); struct cgrp_cset_link *link; - int dead_cnt = 0, extra_refs = 0; + int dead_cnt = 0, extra_refs = 0, threaded_csets = 0; spin_lock_irq(&css_set_lock); + list_for_each_entry(link, &css->cgroup->cset_links, cset_link) { struct css_set *cset = link->cset; struct task_struct *task; int count = 0; int refcnt = refcount_read(&cset->refcount); - seq_printf(seq, " %d", refcnt); - if (refcnt - cset->nr_tasks > 0) { - int extra = refcnt - cset->nr_tasks; - - seq_printf(seq, " +%d", extra); - /* - * Take out the one additional reference in - * init_css_set. - */ - if (cset == &init_css_set) - extra--; - extra_refs += extra; + /* + * Print out the proc_cset and threaded_cset relationship + * and highlight difference between refcount and task_count. + */ + seq_printf(seq, "css_set %pK", cset); + if (rcu_dereference_protected(cset->dom_cset, 1) != cset) { + threaded_csets++; + seq_printf(seq, "=>%pK", cset->dom_cset); + } + if (!list_empty(&cset->threaded_csets)) { + struct css_set *tcset; + int idx = 0; + + list_for_each_entry(tcset, &cset->threaded_csets, + threaded_csets_node) { + seq_puts(seq, idx ? "," : "<="); + seq_printf(seq, "%pK", tcset); + idx++; + } + } else { + seq_printf(seq, " %d", refcnt); + if (refcnt - cset->nr_tasks > 0) { + int extra = refcnt - cset->nr_tasks; + + seq_printf(seq, " +%d", extra); + /* + * Take out the one additional reference in + * init_css_set. + */ + if (cset == &init_css_set) + extra--; + extra_refs += extra; + } } seq_puts(seq, "\n"); @@ -163,10 +185,12 @@ static int cgroup_css_links_read(struct seq_file *seq, void *v) } spin_unlock_irq(&css_set_lock); - if (!dead_cnt && !extra_refs) + if (!dead_cnt && !extra_refs && !threaded_csets) return 0; seq_puts(seq, "\n"); + if (threaded_csets) + seq_printf(seq, "threaded css_sets = %d\n", threaded_csets); if (extra_refs) seq_printf(seq, "extra references = %d\n", extra_refs); if (dead_cnt) -- cgit v1.2.3 From 3c74541777302eec43a0d1327c4d58b8659a776b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 23 Jul 2017 08:14:15 -0400 Subject: cgroup: fix error return value from cgroup_subtree_control() While refactoring, f7b2814bb9b6 ("cgroup: factor out cgroup_{apply|finalize}_control() from cgroup_subtree_control_write()") broke error return value from the function. The return value from the last operation is always overridden to zero. Fix it. Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v4.6+ Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 744975947d01..df2e0f14a95d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3001,11 +3001,11 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of, cgrp->subtree_control &= ~disable; ret = cgroup_apply_control(cgrp); - cgroup_finalize_control(cgrp, ret); + if (ret) + goto out_unlock; kernfs_activate(cgrp->kn); - ret = 0; out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; -- cgit v1.2.3 From 918a8c2c4ea4fab8b7855b8da48bbaf0a733ebb0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Sun, 23 Jul 2017 08:18:26 -0400 Subject: cgroup: remove unnecessary empty check when enabling threaded mode cgroup_enable_threaded() checks that the cgroup doesn't have any tasks or children and fails the operation if so. This test is unnecessary because the first part is already checked by cgroup_can_be_thread_root() and the latter is unnecessary. The latter actually cause a behavioral oddity. Please consider the following hierarchy. All cgroups are domains. A / \ B C \ D If B is made threaded, C and D becomes invalid domains. Due to the no children restriction, threaded mode can't be enabled on C. For C and D, the only thing the user can do is removal. There is no reason for this restriction. Remove it. Acked-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 7 ------- 1 file changed, 7 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e9a377dc5bdb..e0a558c4d358 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3146,13 +3146,6 @@ static int cgroup_enable_threaded(struct cgroup *cgrp) !cgroup_can_be_thread_root(dom_cgrp)) return -EOPNOTSUPP; - /* - * Allow enabling thread mode only on empty cgroups to avoid - * implicit migrations and recursive operations. - */ - if (cgroup_has_tasks(cgrp) || css_has_online_children(&cgrp->self)) - return -EBUSY; - /* * The following shouldn't cause actual migrations and should * always succeed. -- cgit v1.2.3 From c705a00d77457b44ba3790fdf0627ecb8593a254 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 25 Jul 2017 13:20:18 -0400 Subject: cgroup: add comment to cgroup_enable_threaded() Explain cgroup_enable_threaded() and note that the function can never be called on the root cgroup. Signed-off-by: Tejun Heo Suggested-by: Waiman Long --- kernel/cgroup/cgroup.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index e0a558c4d358..85f6a112344b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3129,6 +3129,15 @@ out_unlock: return ret ?: nbytes; } +/** + * cgroup_enable_threaded - make @cgrp threaded + * @cgrp: the target cgroup + * + * Called when "threaded" is written to the cgroup.type interface file and + * tries to make @cgrp threaded and join the parent's resource domain. + * This function is never called on the root cgroup as cgroup.type doesn't + * exist on it. + */ static int cgroup_enable_threaded(struct cgroup *cgrp) { struct cgroup *parent = cgroup_parent(cgrp); -- cgit v1.2.3 From aa8188253474b4053bc2900d9fcb545ce68bdf5c Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:51 -0700 Subject: kernfs: add exportfs operations Now we have the facilities to implement exportfs operations. The idea is cgroup can export the fhandle info to userspace, then userspace uses fhandle to find the cgroup name. Another example is userspace can get fhandle for a cgroup and BPF uses the fhandle to filter info for the cgroup. Acked-by: Greg Kroah-Hartman Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- kernel/cgroup/cgroup.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 620794a20a33..6cefa277f39c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1737,7 +1737,8 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) &cgroup_kf_syscall_ops : &cgroup1_kf_syscall_ops; root->kf_root = kernfs_create_root(kf_sops, - KERNFS_ROOT_CREATE_DEACTIVATED, + KERNFS_ROOT_CREATE_DEACTIVATED | + KERNFS_ROOT_SUPPORT_EXPORTOP, root_cgrp); if (IS_ERR(root->kf_root)) { ret = PTR_ERR(root->kf_root); -- cgit v1.2.3 From 69fd5c391763bd94a40dd152bc72a7f230137150 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Wed, 12 Jul 2017 11:49:55 -0700 Subject: blktrace: add an option to allow displaying cgroup path By default we output cgroup id in blktrace. This adds an option to display cgroup path. Since get cgroup path is a relativly heavy operation, we don't enable it by default. with the option enabled, blktrace will output something like this: dd-1353 [007] d..2 293.015252: 8,0 /test/level D R 24 + 8 [dd] Signed-off-by: Shaohua Li Signed-off-by: Jens Axboe --- kernel/cgroup/cgroup.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 6cefa277f39c..2aba1c519138 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4701,6 +4701,18 @@ static int __init cgroup_wq_init(void) } core_initcall(cgroup_wq_init); +void cgroup_path_from_kernfs_id(const union kernfs_node_id *id, + char *buf, size_t buflen) +{ + struct kernfs_node *kn; + + kn = kernfs_get_node_by_id(cgrp_dfl_root.kf_root, id); + if (!kn) + return; + kernfs_path(kn, buf, buflen); + kernfs_put(kn); +} + /* * proc_cgroup_show() * - Print task's cgroup paths into seq_file, one line for each hierarchy -- cgit v1.2.3 From 0679dee03c6d706d57145ea92c23d08fa10a1999 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Aug 2017 17:55:29 +0100 Subject: cgroup: keep track of number of descent cgroups Keep track of the number of online and dying descent cgroups. This data will be used later to add an ability to control cgroup hierarchy (limit the depth and the number of descent cgroups) and display hierarchy stats. Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: cgroups@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- kernel/cgroup/cgroup.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 85f6a112344b..cfdbb1e780de 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4408,9 +4408,15 @@ static void css_release_work_fn(struct work_struct *work) if (ss->css_released) ss->css_released(css); } else { + struct cgroup *tcgrp; + /* cgroup release path */ trace_cgroup_release(cgrp); + for (tcgrp = cgroup_parent(cgrp); tcgrp; + tcgrp = cgroup_parent(tcgrp)) + tcgrp->nr_dying_descendants--; + cgroup_idr_remove(&cgrp->root->cgroup_idr, cgrp->id); cgrp->id = -1; @@ -4609,9 +4615,13 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->root = root; cgrp->level = level; - for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) + for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; + if (tcgrp != cgrp) + tcgrp->nr_descendants++; + } + if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); @@ -4817,7 +4827,7 @@ static void kill_css(struct cgroup_subsys_state *css) static int cgroup_destroy_locked(struct cgroup *cgrp) __releases(&cgroup_mutex) __acquires(&cgroup_mutex) { - struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup *tcgrp, *parent = cgroup_parent(cgrp); struct cgroup_subsys_state *css; struct cgrp_cset_link *link; int ssid; @@ -4865,6 +4875,11 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) if (parent && cgroup_is_threaded(cgrp)) parent->nr_threaded_children--; + for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) { + tcgrp->nr_descendants--; + tcgrp->nr_dying_descendants++; + } + cgroup1_check_for_release(cgroup_parent(cgrp)); /* put the base reference */ -- cgit v1.2.3 From 1a926e0bbab83bae8207d05a533173425e0496d1 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 28 Jul 2017 18:28:44 +0100 Subject: cgroup: implement hierarchy limits Creating cgroup hierearchies of unreasonable size can affect overall system performance. A user might want to limit the size of cgroup hierarchy. This is especially important if a user is delegating some cgroup sub-tree. To address this issue, introduce an ability to control the size of cgroup hierarchy. The cgroup.max.descendants control file allows to set the maximum allowed number of descendant cgroups. The cgroup.max.depth file controls the maximum depth of the cgroup tree. Both are single value r/w files, with "max" default value. The control files exist on each hierarchy level (including root). When a new cgroup is created, we check the total descendants and depth limits on each level, and if none of them are exceeded, a new cgroup is created. Only alive cgroups are counted, removed (dying) cgroups are ignored. Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: cgroups@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- kernel/cgroup/cgroup.c | 126 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 126 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index cfdbb1e780de..0fd9134e1720 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1827,6 +1827,8 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) cgrp->self.cgroup = cgrp; cgrp->self.flags |= CSS_ONLINE; cgrp->dom_cgrp = cgrp; + cgrp->max_descendants = INT_MAX; + cgrp->max_depth = INT_MAX; for_each_subsys(ss, ssid) INIT_LIST_HEAD(&cgrp->e_csets[ssid]); @@ -3209,6 +3211,92 @@ static ssize_t cgroup_type_write(struct kernfs_open_file *of, char *buf, return ret ?: nbytes; } +static int cgroup_max_descendants_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + int descendants = READ_ONCE(cgrp->max_descendants); + + if (descendants == INT_MAX) + seq_puts(seq, "max\n"); + else + seq_printf(seq, "%d\n", descendants); + + return 0; +} + +static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + int descendants; + ssize_t ret; + + buf = strstrip(buf); + if (!strcmp(buf, "max")) { + descendants = INT_MAX; + } else { + ret = kstrtoint(buf, 0, &descendants); + if (ret) + return ret; + } + + if (descendants < 0 || descendants > INT_MAX) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + cgrp->max_descendants = descendants; + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + +static int cgroup_max_depth_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + int depth = READ_ONCE(cgrp->max_depth); + + if (depth == INT_MAX) + seq_puts(seq, "max\n"); + else + seq_printf(seq, "%d\n", depth); + + return 0; +} + +static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct cgroup *cgrp; + ssize_t ret; + int depth; + + buf = strstrip(buf); + if (!strcmp(buf, "max")) { + depth = INT_MAX; + } else { + ret = kstrtoint(buf, 0, &depth); + if (ret) + return ret; + } + + if (depth < 0 || depth > INT_MAX) + return -ERANGE; + + cgrp = cgroup_kn_lock_live(of->kn, false); + if (!cgrp) + return -ENOENT; + + cgrp->max_depth = depth; + + cgroup_kn_unlock(of->kn); + + return nbytes; +} + static int cgroup_events_show(struct seq_file *seq, void *v) { seq_printf(seq, "populated %d\n", @@ -4309,6 +4397,16 @@ static struct cftype cgroup_base_files[] = { .file_offset = offsetof(struct cgroup, events_file), .seq_show = cgroup_events_show, }, + { + .name = "cgroup.max.descendants", + .seq_show = cgroup_max_descendants_show, + .write = cgroup_max_descendants_write, + }, + { + .name = "cgroup.max.depth", + .seq_show = cgroup_max_depth_show, + .write = cgroup_max_depth_write, + }, { } /* terminate */ }; @@ -4662,6 +4760,29 @@ out_free_cgrp: return ERR_PTR(ret); } +static bool cgroup_check_hierarchy_limits(struct cgroup *parent) +{ + struct cgroup *cgroup; + int ret = false; + int level = 1; + + lockdep_assert_held(&cgroup_mutex); + + for (cgroup = parent; cgroup; cgroup = cgroup_parent(cgroup)) { + if (cgroup->nr_descendants >= cgroup->max_descendants) + goto fail; + + if (level > cgroup->max_depth) + goto fail; + + level++; + } + + ret = true; +fail: + return ret; +} + int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) { struct cgroup *parent, *cgrp; @@ -4676,6 +4797,11 @@ int cgroup_mkdir(struct kernfs_node *parent_kn, const char *name, umode_t mode) if (!parent) return -ENODEV; + if (!cgroup_check_hierarchy_limits(parent)) { + ret = -EAGAIN; + goto out_unlock; + } + cgrp = cgroup_create(parent); if (IS_ERR(cgrp)) { ret = PTR_ERR(cgrp); -- cgit v1.2.3 From ec39225cca42c05ac36853d11d28f877fde5c42e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Aug 2017 17:55:31 +0100 Subject: cgroup: add cgroup.stat interface with basic hierarchy stats A cgroup can consume resources even after being deleted by a user. For example, writing back dirty pages should be accounted and limited, despite the corresponding cgroup might contain no processes and being deleted by a user. In the current implementation a cgroup can remain in such "dying" state for an undefined amount of time. For instance, if a memory cgroup contains a pge, mlocked by a process belonging to an other cgroup. Although the lifecycle of a dying cgroup is out of user's control, it's important to have some insight of what's going on under the hood. In particular, it's handy to have a counter which will allow to detect css leaks. To solve this problem, add a cgroup.stat interface to the base cgroup control files with the following metrics: nr_descendants total number of visible descendant cgroups nr_dying_descendants total number of dying descendant cgroups Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: cgroups@vger.kernel.org Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org --- kernel/cgroup/cgroup.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 0fd9134e1720..a06755a610e1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3304,6 +3304,18 @@ static int cgroup_events_show(struct seq_file *seq, void *v) return 0; } +static int cgroup_stats_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgroup = seq_css(seq)->cgroup; + + seq_printf(seq, "nr_descendants %d\n", + cgroup->nr_descendants); + seq_printf(seq, "nr_dying_descendants %d\n", + cgroup->nr_dying_descendants); + + return 0; +} + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4407,6 +4419,10 @@ static struct cftype cgroup_base_files[] = { .seq_show = cgroup_max_depth_show, .write = cgroup_max_depth_write, }, + { + .name = "cgroup.stat", + .seq_show = cgroup_stats_show, + }, { } /* terminate */ }; -- cgit v1.2.3 From 5a621e6c958e057c727a30c502f28bf2bc04adfd Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 2 Aug 2017 17:55:32 +0100 Subject: cgroup: re-use the parent pointer in cgroup_destroy_locked() As we already have a pointer to the parent cgroup in cgroup_destroy_locked(), we don't need to calculate it again to pass as an argument for cgroup1_check_for_release(). Signed-off-by: Roman Gushchin Suggested-by: Tejun Heo Signed-off-by: Tejun Heo Cc: Zefan Li Cc: Waiman Long Cc: Johannes Weiner Cc: kernel-team@fb.com Cc: linux-kernel@vger.kernel.org --- kernel/cgroup/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index a06755a610e1..92e599796220 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5022,7 +5022,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) tcgrp->nr_dying_descendants++; } - cgroup1_check_for_release(cgroup_parent(cgrp)); + cgroup1_check_for_release(parent); /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt); -- cgit v1.2.3 From 13d82fb77abb9625f3ca74f5c4cbedde0f412f01 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 2 Aug 2017 15:39:38 -0700 Subject: cgroup: short-circuit cset_cgroup_from_root() on the default hierarchy Each css_set directly points to the default cgroup it belongs to, so there's no reason to walk the cgrp_links list on the default hierarchy. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 92e599796220..f5ca55db1fe1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1311,6 +1311,8 @@ static struct cgroup *cset_cgroup_from_root(struct css_set *cset, if (cset == &init_css_set) { res = &root->cgrp; + } else if (root == &cgrp_dfl_root) { + res = cset->dfl_cgrp; } else { struct cgrp_cset_link *link; -- cgit v1.2.3 From 89affbf5d9ebb15c6460596822e8857ea2f9e735 Mon Sep 17 00:00:00 2001 From: Dima Zavin Date: Wed, 2 Aug 2017 13:32:18 -0700 Subject: cpuset: fix a deadlock due to incomplete patching of cpusets_enabled() In codepaths that use the begin/retry interface for reading mems_allowed_seq with irqs disabled, there exists a race condition that stalls the patch process after only modifying a subset of the static_branch call sites. This problem manifested itself as a deadlock in the slub allocator, inside get_any_partial. The loop reads mems_allowed_seq value (via read_mems_allowed_begin), performs the defrag operation, and then verifies the consistency of mem_allowed via the read_mems_allowed_retry and the cookie returned by xxx_begin. The issue here is that both begin and retry first check if cpusets are enabled via cpusets_enabled() static branch. This branch can be rewritted dynamically (via cpuset_inc) if a new cpuset is created. The x86 jump label code fully synchronizes across all CPUs for every entry it rewrites. If it rewrites only one of the callsites (specifically the one in read_mems_allowed_retry) and then waits for the smp_call_function(do_sync_core) to complete while a CPU is inside the begin/retry section with IRQs off and the mems_allowed value is changed, we can hang. This is because begin() will always return 0 (since it wasn't patched yet) while retry() will test the 0 against the actual value of the seq counter. The fix is to use two different static keys: one for begin (pre_enable_key) and one for retry (enable_key). In cpuset_inc(), we first bump the pre_enable key to ensure that cpuset_mems_allowed_begin() always return a valid seqcount if are enabling cpusets. Similarly, when disabling cpusets via cpuset_dec(), we first ensure that callers of cpuset_mems_allowed_retry() will start ignoring the seqcount value before we let cpuset_mems_allowed_begin() return 0. The relevant stack traces of the two stuck threads: CPU: 1 PID: 1415 Comm: mkdir Tainted: G L 4.9.36-00104-g540c51286237 #4 Hardware name: Default string Default string/Hardware, BIOS 4.29.1-20170526215256 05/26/2017 task: ffff8817f9c28000 task.stack: ffffc9000ffa4000 RIP: smp_call_function_many+0x1f9/0x260 Call Trace: smp_call_function+0x3b/0x70 on_each_cpu+0x2f/0x90 text_poke_bp+0x87/0xd0 arch_jump_label_transform+0x93/0x100 __jump_label_update+0x77/0x90 jump_label_update+0xaa/0xc0 static_key_slow_inc+0x9e/0xb0 cpuset_css_online+0x70/0x2e0 online_css+0x2c/0xa0 cgroup_apply_control_enable+0x27f/0x3d0 cgroup_mkdir+0x2b7/0x420 kernfs_iop_mkdir+0x5a/0x80 vfs_mkdir+0xf6/0x1a0 SyS_mkdir+0xb7/0xe0 entry_SYSCALL_64_fastpath+0x18/0xad ... CPU: 2 PID: 1 Comm: init Tainted: G L 4.9.36-00104-g540c51286237 #4 Hardware name: Default string Default string/Hardware, BIOS 4.29.1-20170526215256 05/26/2017 task: ffff8818087c0000 task.stack: ffffc90000030000 RIP: int3+0x39/0x70 Call Trace: <#DB> ? ___slab_alloc+0x28b/0x5a0 ? copy_process.part.40+0xf7/0x1de0 __slab_alloc.isra.80+0x54/0x90 copy_process.part.40+0xf7/0x1de0 copy_process.part.40+0xf7/0x1de0 kmem_cache_alloc_node+0x8a/0x280 copy_process.part.40+0xf7/0x1de0 _do_fork+0xe7/0x6c0 _raw_spin_unlock_irq+0x2d/0x60 trace_hardirqs_on_caller+0x136/0x1d0 entry_SYSCALL_64_fastpath+0x5/0xad do_syscall_64+0x27/0x350 SyS_clone+0x19/0x20 do_syscall_64+0x60/0x350 entry_SYSCALL64_slow_path+0x25/0x25 Link: http://lkml.kernel.org/r/20170731040113.14197-1-dmitriyz@waymo.com Fixes: 46e700abc44c ("mm, page_alloc: remove unnecessary taking of a seqlock when cpusets are disabled") Signed-off-by: Dima Zavin Reported-by: Cliff Spradlin Acked-by: Vlastimil Babka Cc: Peter Zijlstra Cc: Christopher Lameter Cc: Li Zefan Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Mel Gorman Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup/cpuset.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ca8376e5008c..8d5151688504 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -63,6 +63,7 @@ #include #include +DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ -- cgit v1.2.3 From be040bea9085a9c2b1700c9e60888777baeb96d5 Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 1 Aug 2017 17:24:06 +0200 Subject: cpuset: Make nr_cpusets private Any use of key->enabled (that is static_key_enabled and static_key_count) outside jump_label_lock should handle its own serialization. In the case of cpusets_enabled_key, the key is always incremented/decremented under cpuset_mutex, and hence the same rule applies to nr_cpusets. The rule *is* respected currently, but the mutex is static so nr_cpusets should be static too. Signed-off-by: Paolo Bonzini Signed-off-by: Peter Zijlstra (Intel) Acked-by: Zefan Li Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1501601046-35683-4-git-send-email-pbonzini@redhat.com Signed-off-by: Ingo Molnar --- kernel/cgroup/cpuset.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8d5151688504..9ed6a051a1b9 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -577,6 +577,13 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr, rcu_read_unlock(); } +/* Must be called with cpuset_mutex held. */ +static inline int nr_cpusets(void) +{ + /* jump label reference count + the top-level cpuset */ + return static_key_count(&cpusets_enabled_key.key) + 1; +} + /* * generate_sched_domains() * -- cgit v1.2.3 From 3e48930cc74f0c212ee1838f89ad0ca7fcf2fea1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Fri, 11 Aug 2017 05:49:01 -0700 Subject: cgroup: misc changes Misc trivial changes to prepare for future changes. No functional difference. * Expose cgroup_get(), cgroup_tryget() and cgroup_parent(). * Implement task_dfl_cgroup() which dereferences css_set->dfl_cgrp. * Rename cgroup_stats_show() to cgroup_stat_show() for consistency with the file name. Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 23 ++--------------------- 1 file changed, 2 insertions(+), 21 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index f5ca55db1fe1..c038ccf95b5d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -319,15 +319,6 @@ static void cgroup_idr_remove(struct idr *idr, int id) spin_unlock_bh(&cgroup_idr_lock); } -static struct cgroup *cgroup_parent(struct cgroup *cgrp) -{ - struct cgroup_subsys_state *parent_css = cgrp->self.parent; - - if (parent_css) - return container_of(parent_css, struct cgroup, self); - return NULL; -} - static bool cgroup_has_tasks(struct cgroup *cgrp) { return cgrp->nr_populated_csets; @@ -534,22 +525,12 @@ out_unlock: return css; } -static void __maybe_unused cgroup_get(struct cgroup *cgrp) -{ - css_get(&cgrp->self); -} - static void cgroup_get_live(struct cgroup *cgrp) { WARN_ON_ONCE(cgroup_is_dead(cgrp)); css_get(&cgrp->self); } -static bool cgroup_tryget(struct cgroup *cgrp) -{ - return css_tryget(&cgrp->self); -} - struct cgroup_subsys_state *of_css(struct kernfs_open_file *of) { struct cgroup *cgrp = of->kn->parent->priv; @@ -3306,7 +3287,7 @@ static int cgroup_events_show(struct seq_file *seq, void *v) return 0; } -static int cgroup_stats_show(struct seq_file *seq, void *v) +static int cgroup_stat_show(struct seq_file *seq, void *v) { struct cgroup *cgroup = seq_css(seq)->cgroup; @@ -4423,7 +4404,7 @@ static struct cftype cgroup_base_files[] = { }, { .name = "cgroup.stat", - .seq_show = cgroup_stats_show, + .seq_show = cgroup_stat_show, }, { } /* terminate */ }; -- cgit v1.2.3 From 696b98f244f77a79840bf420861c996d61c82637 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Wed, 9 Aug 2017 13:25:21 +0300 Subject: cgroup: remove unneeded checks "descendants" and "depth" are declared as int, so they can't be larger than INT_MAX. Static checkers complain and it's slightly confusing for humans as well so let's just remove these conditions. Signed-off-by: Dan Carpenter Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index c038ccf95b5d..1591e9b20122 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3223,7 +3223,7 @@ static ssize_t cgroup_max_descendants_write(struct kernfs_open_file *of, return ret; } - if (descendants < 0 || descendants > INT_MAX) + if (descendants < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); @@ -3266,7 +3266,7 @@ static ssize_t cgroup_max_depth_write(struct kernfs_open_file *of, return ret; } - if (depth < 0 || depth > INT_MAX) + if (depth < 0) return -ERANGE; cgrp = cgroup_kn_lock_live(of->kn, false); -- cgit v1.2.3 From e1cba4b85daa71b710384d451ff6238d5e4d1ff6 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 17 Aug 2017 15:33:09 -0400 Subject: cgroup: Add mount flag to enable cpuset to use v2 behavior in v1 cgroup A new mount option "cpuset_v2_mode" is added to the v1 cgroupfs filesystem to enable cpuset controller to use v2 behavior in a v1 cgroup. This mount option applies only to cpuset controller and have no effect on other controllers. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup-v1.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index f0e8601b13cb..024085daab1a 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -895,6 +895,8 @@ static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_roo seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); + if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) + seq_puts(seq, ",cpuset_v2_mode"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) @@ -949,6 +951,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) opts->cpuset_clone_children = true; continue; } + if (!strcmp(token, "cpuset_v2_mode")) { + opts->flags |= CGRP_ROOT_CPUSET_V2_MODE; + continue; + } if (!strcmp(token, "xattr")) { opts->flags |= CGRP_ROOT_XATTR; continue; -- cgit v1.2.3 From b8d1b8ee93df8ffbabbeadd65d39853cfad6d698 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 17 Aug 2017 15:33:10 -0400 Subject: cpuset: Allow v2 behavior in v1 cgroup Cpuset v2 has some useful behaviors that are not present in v1 because of backward compatibility concern. One of that is the restoration of the original cpu and memory node mask after a hot removal and addition event sequence. This patch makes the cpuset controller to check the CGRP_ROOT_CPUSET_V2_MODE flag and use the v2 behavior if it is set. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo --- kernel/cgroup/cpuset.c | 33 ++++++++++++++++++++------------- 1 file changed, 20 insertions(+), 13 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 252d70c9a49b..f3539a41c49d 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -298,6 +298,16 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); +/* + * Cgroup v2 behavior is used when on default hierarchy or the + * cgroup_v2_mode flag is set. + */ +static inline bool is_in_v2_mode(void) +{ + return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || + (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); +} + /* * This is ugly, but preserves the userspace API for existing cpuset * users. If someone tries to mount the "cpuset" filesystem, we @@ -488,8 +498,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial) /* On legacy hiearchy, we must be a subset of our parent cpuset. */ ret = -EACCES; - if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && - !is_cpuset_subset(trial, par)) + if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* @@ -895,8 +904,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && - cpumask_empty(new_cpus)) + if (is_in_v2_mode() && cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent->effective_cpus); /* Skip the whole subtree if the cpumask remains the same. */ @@ -913,7 +921,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus) cpumask_copy(cp->effective_cpus, new_cpus); spin_unlock_irq(&callback_lock); - WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); @@ -1149,8 +1157,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && - nodes_empty(*new_mems)) + if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ @@ -1167,7 +1174,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); - WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); @@ -1459,7 +1466,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset) /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; - if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && + if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; @@ -1977,7 +1984,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) cpuset_inc(); spin_lock_irq(&callback_lock); - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) { + if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; } @@ -2054,7 +2061,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css) mutex_lock(&cpuset_mutex); spin_lock_irq(&callback_lock); - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) { + if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { @@ -2248,7 +2255,7 @@ retry: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); - if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) + if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else @@ -2279,7 +2286,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work) static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; - bool on_dfl = cgroup_subsys_on_dfl(cpuset_cgrp_subsys); + bool on_dfl = is_in_v2_mode(); mutex_lock(&cpuset_mutex); -- cgit v1.2.3 From 1c08c22c874ac88799cab1f78c40f46110274915 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 24 Aug 2017 12:04:29 -0400 Subject: cpuset: Fix incorrect memory_pressure control file mapping The memory_pressure control file was incorrectly set up without a private value (0, by default). As a result, this control file was treated like memory_migrate on read. By adding back the FILE_MEMORY_PRESSURE private value, the correct memory pressure value will be returned. Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Fixes: 7dbdb199d3bf ("cgroup: replace cftype->mode with CFTYPE_WORLD_WRITABLE") Cc: stable@vger.kernel.org # v4.4+ --- kernel/cgroup/cpuset.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ca8376e5008c..8362bac0d179 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -1891,6 +1891,7 @@ static struct cftype files[] = { { .name = "memory_pressure", .read_u64 = cpuset_read_u64, + .private = FILE_MEMORY_PRESSURE, }, { -- cgit v1.2.3 From 77d1dfda0e79b41894880418f04794e92e4350e2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 8 Aug 2017 12:16:24 +0200 Subject: sched/topology, cpuset: Avoid spurious/wrong domain rebuilds When disabling cpuset.sched_load_balance we expect to be able to online CPUs without generating sched_domains. However this is currently completely broken. What happens is that we generate the sched_domains and then destroy them. This is because of the spurious 'default' domain build in cpuset_update_active_cpus(). That builds a single machine wide domain and then schedules a work to build the 'real' domains. The work then finds there are _no_ domains and destroys the lot again. Furthermore, if there actually were cpusets, building the machine wide domain is actively wrong, because it would allow tasks to 'escape' their cpuset. Also I don't think its needed, the scheduler really should respect the active mask. Reported-by: Ofer Levi(SW) Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Tejun Heo Cc: Thomas Gleixner Cc: Vineet.Gupta1@synopsys.com Cc: rusty@rustcorp.com.au Signed-off-by: Ingo Molnar --- kernel/cgroup/cpuset.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 8d5151688504..1d2369451939 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2343,13 +2343,7 @@ void cpuset_update_active_cpus(void) * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. - * - * We still need to do partition_sched_domains() synchronously; - * otherwise, the scheduler will get confused and put tasks to the - * dead CPU. Fall back to the default single domain. - * cpuset_hotplug_workfn() will rebuild it as necessary. */ - partition_sched_domains(1, NULL, NULL); schedule_work(&cpuset_hotplug_work); } -- cgit v1.2.3 From 65f3975f3584eee2da88b11f06f66e2d39fd30d0 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 6 Sep 2017 16:21:50 -0700 Subject: cgroup: revert fa06235b8eb0 ("cgroup: reset css on destruction") Commit fa06235b8eb0 ("cgroup: reset css on destruction") caused css_reset callback to be called from the offlining path. Although it solves the problem mentioned in the commit description ("For instance, memory cgroup needs to reset memory.low, otherwise pages charged to a dead cgroup might never get reclaimed."), generally speaking, it's not correct. An offline cgroup can still be a resource domain, and we shouldn't grant it more resources than it had before deletion. For instance, if an offline memory cgroup has dirty pages, we should still imply i/o limits during writeback. The css_reset callback is designed to return the cgroup state into the original state, that means reset all limits and counters. It's spomething different from the offlining, and we shouldn't use it from the offlining path. Instead, we should adjust necessary settings from the per-controller css_offline callbacks (e.g. reset memory.low). Link: http://lkml.kernel.org/r/20170727130428.28856-2-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: Tejun Heo Acked-by: Johannes Weiner Cc: Vladimir Davydov Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup/cgroup.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index df2e0f14a95d..f64fc967a9ef 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4100,9 +4100,6 @@ static void offline_css(struct cgroup_subsys_state *css) if (!(css->flags & CSS_ONLINE)) return; - if (ss->css_reset) - ss->css_reset(css); - if (ss->css_offline) ss->css_offline(css); -- cgit v1.2.3 From da99ecf117fce6570bd3989263d68ee0007e1249 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 6 Sep 2017 16:24:53 -0700 Subject: mm: replace TIF_MEMDIE checks by tsk_is_oom_victim TIF_MEMDIE is set only to the tasks whick were either directly selected by the OOM killer or passed through mark_oom_victim from the allocator path. tsk_is_oom_victim is more generic and allows to identify all tasks (threads) which share the mm with the oom victim. Please note that the freezer still needs to check TIF_MEMDIE because we cannot thaw tasks which do not participage in oom_victims counting otherwise a !TIF_MEMDIE task could interfere after oom_disbale returns. Link: http://lkml.kernel.org/r/20170810075019.28998-3-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: Mel Gorman Cc: Tetsuo Handa Cc: David Rientjes Cc: Johannes Weiner Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup/cpuset.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2f4039bafebb..e7485786db9b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -56,6 +56,7 @@ #include #include #include +#include #include #include @@ -2500,12 +2501,12 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, - * yes. If current has access to memory reserves due to TIF_MEMDIE, yes. + * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset - * unless the task has been OOM killed as is marked TIF_MEMDIE. + * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * @@ -2528,7 +2529,7 @@ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok - * TIF_MEMDIE - any node ok + * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ @@ -2546,7 +2547,7 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ - if (unlikely(test_thread_flag(TIF_MEMDIE))) + if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; -- cgit v1.2.3 From 50e76632339d4655859523a39249dd95ee5e93e7 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Sep 2017 11:13:38 +0200 Subject: sched/cpuset/pm: Fix cpuset vs. suspend-resume bugs Cpusets vs. suspend-resume is _completely_ broken. And it got noticed because it now resulted in non-cpuset usage breaking too. On suspend cpuset_cpu_inactive() doesn't call into cpuset_update_active_cpus() because it doesn't want to move tasks about, there is no need, all tasks are frozen and won't run again until after we've resumed everything. But this means that when we finally do call into cpuset_update_active_cpus() after resuming the last frozen cpu in cpuset_cpu_active(), the top_cpuset will not have any difference with the cpu_active_mask and this it will not in fact do _anything_. So the cpuset configuration will not be restored. This was largely hidden because we would unconditionally create identity domains and mobile users would not in fact use cpusets much. And servers what do use cpusets tend to not suspend-resume much. An addition problem is that we'd not in fact wait for the cpuset work to finish before resuming the tasks, allowing spurious migrations outside of the specified domains. Fix the rebuild by introducing cpuset_force_rebuild() and fix the ordering with cpuset_wait_for_hotplug(). Reported-by: Andy Lutomirski Signed-off-by: Peter Zijlstra (Intel) Cc: Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Tejun Heo Cc: Thomas Gleixner Fixes: deb7aa308ea2 ("cpuset: reorganize CPU / memory hotplug handling") Link: http://lkml.kernel.org/r/20170907091338.orwxrqkbfkki3c24@hirez.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/cgroup/cpuset.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 2f4039bafebb..0513ee39698b 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2267,6 +2267,13 @@ retry: mutex_unlock(&cpuset_mutex); } +static bool force_rebuild; + +void cpuset_force_rebuild(void) +{ + force_rebuild = true; +} + /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * @@ -2341,8 +2348,10 @@ static void cpuset_hotplug_workfn(struct work_struct *work) } /* rebuild sched domains if cpus_allowed has changed */ - if (cpus_updated) + if (cpus_updated || force_rebuild) { + force_rebuild = false; rebuild_sched_domains(); + } } void cpuset_update_active_cpus(void) @@ -2355,6 +2364,11 @@ void cpuset_update_active_cpus(void) schedule_work(&cpuset_hotplug_work); } +void cpuset_wait_for_hotplug(void) +{ + flush_work(&cpuset_hotplug_work); +} + /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. -- cgit v1.2.3 From c4fa6c43ce4b427350cfbb659436bfe3d9e09a1d Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Thu, 21 Sep 2017 09:54:13 -0400 Subject: cgroup: Reinit cgroup_taskset structure before cgroup_migrate_execute() returns The cgroup_taskset structure within the larger cgroup_mgctx structure is supposed to be used once and then discarded. That is not really the case in the hotplug code path: cpuset_hotplug_workfn() - cgroup_transfer_tasks() - cgroup_migrate() - cgroup_migrate_add_task() - cgroup_migrate_execute() In this case, the cgroup_migrate() function is called multiple time with the same cgroup_mgctx structure to transfer the tasks from one cgroup to another one-by-one. The second time cgroup_migrate() is called, the cgroup_taskset will be in an incorrect state and so may cause the system to panic. For example, [ 150.888410] Faulting instruction address: 0xc0000000001db648 [ 150.888414] Oops: Kernel access of bad area, sig: 11 [#1] [ 150.888417] SMP NR_CPUS=2048 [ 150.888417] NUMA [ 150.888419] pSeries : [ 150.888545] NIP [c0000000001db648] cpuset_can_attach+0x58/0x1b0 [ 150.888548] LR [c0000000001db638] cpuset_can_attach+0x48/0x1b0 [ 150.888551] Call Trace: [ 150.888554] [c0000005f65cb940] [c0000000001db638] cpuset_can_attach+0x48/0x1b 0 (unreliable) [ 150.888559] [c0000005f65cb9a0] [c0000000001cff04] cgroup_migrate_execute+0xc4/0x4b0 [ 150.888563] [c0000005f65cba20] [c0000000001d7d14] cgroup_transfer_tasks+0x1d4/0x370 [ 150.888568] [c0000005f65cbb70] [c0000000001ddcb0] cpuset_hotplug_workfn+0x710/0x8f0 [ 150.888572] [c0000005f65cbc80] [c00000000012032c] process_one_work+0x1ac/0x4d0 [ 150.888576] [c0000005f65cbd20] [c0000000001206f8] worker_thread+0xa8/0x5b0 [ 150.888580] [c0000005f65cbdc0] [c0000000001293f8] kthread+0x168/0x1b0 [ 150.888584] [c0000005f65cbe30] [c00000000000b368] ret_from_kernel_thread+0x5c/0x74 To allow reuse of the cgroup_mgctx structure, some fields in that structure are now re-initialized at the end of cgroup_migrate_execute() function call so that the structure can be reused again in a later iteration without causing problem. This bug was introduced in the commit e595cd706982 ("group: track migration context in cgroup_mgctx") in 4.11. This commit moves the cgroup_taskset initialization out of cgroup_migrate(). The commit 10467270fb3 ("cgroup: don't call migration methods if there are no tasks to migrate") helped, but did not completely resolve the problem. Fixes: e595cd706982bff0211e6fafe5a108421e747fbc ("group: track migration context in cgroup_mgctx") Signed-off-by: Waiman Long Signed-off-by: Tejun Heo Cc: stable@vger.kernel.org # v4.11+ --- kernel/cgroup/cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..44857278eb8a 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2311,6 +2311,14 @@ out_release_tset: list_del_init(&cset->mg_node); } spin_unlock_irq(&css_set_lock); + + /* + * Re-initialize the cgroup_taskset structure in case it is reused + * again in another cgroup_migrate_add_task()/cgroup_migrate_execute() + * iteration. + */ + tset->nr_tasks = 0; + tset->csets = &tset->src_csets; return ret; } -- cgit v1.2.3 From 041cd640b2f3c5607171c59d8712b503659d21f7 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Sep 2017 08:12:05 -0700 Subject: cgroup: Implement cgroup2 basic CPU usage accounting In cgroup1, while cpuacct isn't actually controlling any resources, it is a separate controller due to combination of two factors - 1. enabling cpu controller has significant side effects, and 2. we have to pick one of the hierarchies to account CPU usages on. cpuacct controller is effectively used to designate a hierarchy to track CPU usages on. cgroup2's unified hierarchy removes the second reason and we can account basic CPU usages by default. While we can use cpuacct for this purpose, both its interface and implementation leave a lot to be desired - it collects and exposes two sources of truth which don't agree with each other and some of the exposed statistics don't make much sense. Also, it propagates all the way up the hierarchy on each accounting event which is unnecessary. This patch adds basic resource accounting mechanism to cgroup2's unified hierarchy and accounts CPU usages using it. * All accountings are done per-cpu and don't propagate immediately. It just bumps the per-cgroup per-cpu counters and links to the parent's updated list if not already on it. * On a read, the per-cpu counters are collected into the global ones and then propagated upwards. Only the per-cpu counters which have changed since the last read are propagated. * CPU usage stats are collected and shown in "cgroup.stat" with "cpu." prefix. Total usage is collected from scheduling events. User/sys breakdown is sourced from tick sampling and adjusted to the usage using cputime_adjust(). This keeps the accounting side hot path O(1) and per-cpu and the read side O(nr_updated_since_last_read). v2: Minor changes and documentation updates as suggested by Waiman and Roman. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Ingo Molnar Cc: Li Zefan Cc: Johannes Weiner Cc: Waiman Long Cc: Roman Gushchin --- kernel/cgroup/Makefile | 2 +- kernel/cgroup/cgroup-internal.h | 8 + kernel/cgroup/cgroup.c | 24 ++- kernel/cgroup/stat.c | 334 ++++++++++++++++++++++++++++++++++++++++ 4 files changed, 365 insertions(+), 3 deletions(-) create mode 100644 kernel/cgroup/stat.c (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index ce693ccb8c58..0acee616e06c 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -1,4 +1,4 @@ -obj-y := cgroup.o namespace.o cgroup-v1.o +obj-y := cgroup.o stat.o namespace.o cgroup-v1.o obj-$(CONFIG_CGROUP_FREEZER) += freezer.o obj-$(CONFIG_CGROUP_PIDS) += pids.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 5151ff256c29..fa642c99586a 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -199,6 +199,14 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, int cgroup_task_count(const struct cgroup *cgrp); +/* + * stat.c + */ +void cgroup_stat_flush(struct cgroup *cgrp); +int cgroup_stat_init(struct cgroup *cgrp); +void cgroup_stat_exit(struct cgroup *cgrp); +void cgroup_stat_boot(void); + /* * namespace.c */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..d036625556c9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -142,12 +142,14 @@ static struct static_key_true *cgroup_subsys_on_dfl_key[] = { }; #undef SUBSYS +static DEFINE_PER_CPU(struct cgroup_cpu_stat, cgrp_dfl_root_cpu_stat); + /* * The default hierarchy, reserved for the subsystems that are otherwise * unattached - it never has more than a single cgroup, and all tasks are * part of that cgroup. */ -struct cgroup_root cgrp_dfl_root; +struct cgroup_root cgrp_dfl_root = { .cgrp.cpu_stat = &cgrp_dfl_root_cpu_stat }; EXPORT_SYMBOL_GPL(cgrp_dfl_root); /* @@ -3301,6 +3303,8 @@ static int cgroup_stat_show(struct seq_file *seq, void *v) seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); + cgroup_stat_show_cputime(seq, "cpu."); + return 0; } @@ -4471,6 +4475,8 @@ static void css_free_work_fn(struct work_struct *work) */ cgroup_put(cgroup_parent(cgrp)); kernfs_put(cgrp->kn); + if (cgroup_on_dfl(cgrp)) + cgroup_stat_exit(cgrp); kfree(cgrp); } else { /* @@ -4515,6 +4521,9 @@ static void css_release_work_fn(struct work_struct *work) /* cgroup release path */ trace_cgroup_release(cgrp); + if (cgroup_on_dfl(cgrp)) + cgroup_stat_flush(cgrp); + for (tcgrp = cgroup_parent(cgrp); tcgrp; tcgrp = cgroup_parent(tcgrp)) tcgrp->nr_dying_descendants--; @@ -4698,6 +4707,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (ret) goto out_free_cgrp; + if (cgroup_on_dfl(parent)) { + ret = cgroup_stat_init(cgrp); + if (ret) + goto out_cancel_ref; + } + /* * Temporarily set the pointer to NULL, so idr_find() won't return * a half-baked cgroup. @@ -4705,7 +4720,7 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->id = cgroup_idr_alloc(&root->cgroup_idr, NULL, 2, 0, GFP_KERNEL); if (cgrp->id < 0) { ret = -ENOMEM; - goto out_cancel_ref; + goto out_stat_exit; } init_cgroup_housekeeping(cgrp); @@ -4754,6 +4769,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) return cgrp; +out_stat_exit: + if (cgroup_on_dfl(parent)) + cgroup_stat_exit(cgrp); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5148,6 +5166,8 @@ int __init cgroup_init(void) BUG_ON(cgroup_init_cftypes(NULL, cgroup_base_files)); BUG_ON(cgroup_init_cftypes(NULL, cgroup1_base_files)); + cgroup_stat_boot(); + /* * The latency of the synchronize_sched() is too high for cgroups, * avoid it at the cost of forcing all readers into the slow path. diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c new file mode 100644 index 000000000000..9cce79e89320 --- /dev/null +++ b/kernel/cgroup/stat.c @@ -0,0 +1,334 @@ +#include "cgroup-internal.h" + +#include + +static DEFINE_MUTEX(cgroup_stat_mutex); +static DEFINE_PER_CPU(raw_spinlock_t, cgroup_cpu_stat_lock); + +static struct cgroup_cpu_stat *cgroup_cpu_stat(struct cgroup *cgrp, int cpu) +{ + return per_cpu_ptr(cgrp->cpu_stat, cpu); +} + +/** + * cgroup_cpu_stat_updated - keep track of updated cpu_stat + * @cgrp: target cgroup + * @cpu: cpu on which cpu_stat was updated + * + * @cgrp's cpu_stat on @cpu was updated. Put it on the parent's matching + * cpu_stat->updated_children list. See the comment on top of + * cgroup_cpu_stat definition for details. + */ +static void cgroup_cpu_stat_updated(struct cgroup *cgrp, int cpu) +{ + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu); + struct cgroup *parent; + unsigned long flags; + + /* + * Speculative already-on-list test. This may race leading to + * temporary inaccuracies, which is fine. + * + * Because @parent's updated_children is terminated with @parent + * instead of NULL, we can tell whether @cgrp is on the list by + * testing the next pointer for NULL. + */ + if (cgroup_cpu_stat(cgrp, cpu)->updated_next) + return; + + raw_spin_lock_irqsave(cpu_lock, flags); + + /* put @cgrp and all ancestors on the corresponding updated lists */ + for (parent = cgroup_parent(cgrp); parent; + cgrp = parent, parent = cgroup_parent(cgrp)) { + struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); + struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu); + + /* + * Both additions and removals are bottom-up. If a cgroup + * is already in the tree, all ancestors are. + */ + if (cstat->updated_next) + break; + + cstat->updated_next = pcstat->updated_children; + pcstat->updated_children = cgrp; + } + + raw_spin_unlock_irqrestore(cpu_lock, flags); +} + +/** + * cgroup_cpu_stat_pop_updated - iterate and dismantle cpu_stat updated tree + * @pos: current position + * @root: root of the tree to traversal + * @cpu: target cpu + * + * Walks the udpated cpu_stat tree on @cpu from @root. %NULL @pos starts + * the traversal and %NULL return indicates the end. During traversal, + * each returned cgroup is unlinked from the tree. Must be called with the + * matching cgroup_cpu_stat_lock held. + * + * The only ordering guarantee is that, for a parent and a child pair + * covered by a given traversal, if a child is visited, its parent is + * guaranteed to be visited afterwards. + */ +static struct cgroup *cgroup_cpu_stat_pop_updated(struct cgroup *pos, + struct cgroup *root, int cpu) +{ + struct cgroup_cpu_stat *cstat; + struct cgroup *parent; + + if (pos == root) + return NULL; + + /* + * We're gonna walk down to the first leaf and visit/remove it. We + * can pick whatever unvisited node as the starting point. + */ + if (!pos) + pos = root; + else + pos = cgroup_parent(pos); + + /* walk down to the first leaf */ + while (true) { + cstat = cgroup_cpu_stat(pos, cpu); + if (cstat->updated_children == pos) + break; + pos = cstat->updated_children; + } + + /* + * Unlink @pos from the tree. As the updated_children list is + * singly linked, we have to walk it to find the removal point. + * However, due to the way we traverse, @pos will be the first + * child in most cases. The only exception is @root. + */ + parent = cgroup_parent(pos); + if (parent && cstat->updated_next) { + struct cgroup_cpu_stat *pcstat = cgroup_cpu_stat(parent, cpu); + struct cgroup_cpu_stat *ncstat; + struct cgroup **nextp; + + nextp = &pcstat->updated_children; + while (true) { + ncstat = cgroup_cpu_stat(*nextp, cpu); + if (*nextp == pos) + break; + + WARN_ON_ONCE(*nextp == parent); + nextp = &ncstat->updated_next; + } + + *nextp = cstat->updated_next; + cstat->updated_next = NULL; + } + + return pos; +} + +static void cgroup_stat_accumulate(struct cgroup_stat *dst_stat, + struct cgroup_stat *src_stat) +{ + dst_stat->cputime.utime += src_stat->cputime.utime; + dst_stat->cputime.stime += src_stat->cputime.stime; + dst_stat->cputime.sum_exec_runtime += src_stat->cputime.sum_exec_runtime; +} + +static void cgroup_cpu_stat_flush_one(struct cgroup *cgrp, int cpu) +{ + struct cgroup *parent = cgroup_parent(cgrp); + struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); + struct task_cputime *last_cputime = &cstat->last_cputime; + struct task_cputime cputime; + struct cgroup_stat delta; + unsigned seq; + + lockdep_assert_held(&cgroup_stat_mutex); + + /* fetch the current per-cpu values */ + do { + seq = __u64_stats_fetch_begin(&cstat->sync); + cputime = cstat->cputime; + } while (__u64_stats_fetch_retry(&cstat->sync, seq)); + + /* accumulate the deltas to propgate */ + delta.cputime.utime = cputime.utime - last_cputime->utime; + delta.cputime.stime = cputime.stime - last_cputime->stime; + delta.cputime.sum_exec_runtime = cputime.sum_exec_runtime - + last_cputime->sum_exec_runtime; + *last_cputime = cputime; + + /* transfer the pending stat into delta */ + cgroup_stat_accumulate(&delta, &cgrp->pending_stat); + memset(&cgrp->pending_stat, 0, sizeof(cgrp->pending_stat)); + + /* propagate delta into the global stat and the parent's pending */ + cgroup_stat_accumulate(&cgrp->stat, &delta); + if (parent) + cgroup_stat_accumulate(&parent->pending_stat, &delta); +} + +/* see cgroup_stat_flush() */ +static void cgroup_stat_flush_locked(struct cgroup *cgrp) +{ + int cpu; + + lockdep_assert_held(&cgroup_stat_mutex); + + for_each_possible_cpu(cpu) { + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_cpu_stat_lock, cpu); + struct cgroup *pos = NULL; + + raw_spin_lock_irq(cpu_lock); + while ((pos = cgroup_cpu_stat_pop_updated(pos, cgrp, cpu))) + cgroup_cpu_stat_flush_one(pos, cpu); + raw_spin_unlock_irq(cpu_lock); + } +} + +/** + * cgroup_stat_flush - flush stats in @cgrp's subtree + * @cgrp: target cgroup + * + * Collect all per-cpu stats in @cgrp's subtree into the global counters + * and propagate them upwards. After this function returns, all cgroups in + * the subtree have up-to-date ->stat. + * + * This also gets all cgroups in the subtree including @cgrp off the + * ->updated_children lists. + */ +void cgroup_stat_flush(struct cgroup *cgrp) +{ + mutex_lock(&cgroup_stat_mutex); + cgroup_stat_flush_locked(cgrp); + mutex_unlock(&cgroup_stat_mutex); +} + +static struct cgroup_cpu_stat *cgroup_cpu_stat_account_begin(struct cgroup *cgrp) +{ + struct cgroup_cpu_stat *cstat; + + cstat = get_cpu_ptr(cgrp->cpu_stat); + u64_stats_update_begin(&cstat->sync); + return cstat; +} + +static void cgroup_cpu_stat_account_end(struct cgroup *cgrp, + struct cgroup_cpu_stat *cstat) +{ + u64_stats_update_end(&cstat->sync); + cgroup_cpu_stat_updated(cgrp, smp_processor_id()); + put_cpu_ptr(cstat); +} + +void __cgroup_account_cputime(struct cgroup *cgrp, u64 delta_exec) +{ + struct cgroup_cpu_stat *cstat; + + cstat = cgroup_cpu_stat_account_begin(cgrp); + cstat->cputime.sum_exec_runtime += delta_exec; + cgroup_cpu_stat_account_end(cgrp, cstat); +} + +void __cgroup_account_cputime_field(struct cgroup *cgrp, + enum cpu_usage_stat index, u64 delta_exec) +{ + struct cgroup_cpu_stat *cstat; + + cstat = cgroup_cpu_stat_account_begin(cgrp); + + switch (index) { + case CPUTIME_USER: + case CPUTIME_NICE: + cstat->cputime.utime += delta_exec; + break; + case CPUTIME_SYSTEM: + case CPUTIME_IRQ: + case CPUTIME_SOFTIRQ: + cstat->cputime.stime += delta_exec; + break; + default: + break; + } + + cgroup_cpu_stat_account_end(cgrp, cstat); +} + +void cgroup_stat_show_cputime(struct seq_file *seq, const char *prefix) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + u64 usage, utime, stime; + + if (!cgroup_parent(cgrp)) + return; + + mutex_lock(&cgroup_stat_mutex); + + cgroup_stat_flush_locked(cgrp); + + usage = cgrp->stat.cputime.sum_exec_runtime; + cputime_adjust(&cgrp->stat.cputime, &cgrp->stat.prev_cputime, + &utime, &stime); + + mutex_unlock(&cgroup_stat_mutex); + + do_div(usage, NSEC_PER_USEC); + do_div(utime, NSEC_PER_USEC); + do_div(stime, NSEC_PER_USEC); + + seq_printf(seq, "%susage_usec %llu\n" + "%suser_usec %llu\n" + "%ssystem_usec %llu\n", + prefix, usage, prefix, utime, prefix, stime); +} + +int cgroup_stat_init(struct cgroup *cgrp) +{ + int cpu; + + /* the root cgrp has cpu_stat preallocated */ + if (!cgrp->cpu_stat) { + cgrp->cpu_stat = alloc_percpu(struct cgroup_cpu_stat); + if (!cgrp->cpu_stat) + return -ENOMEM; + } + + /* ->updated_children list is self terminated */ + for_each_possible_cpu(cpu) + cgroup_cpu_stat(cgrp, cpu)->updated_children = cgrp; + + prev_cputime_init(&cgrp->stat.prev_cputime); + + return 0; +} + +void cgroup_stat_exit(struct cgroup *cgrp) +{ + int cpu; + + cgroup_stat_flush(cgrp); + + /* sanity check */ + for_each_possible_cpu(cpu) { + struct cgroup_cpu_stat *cstat = cgroup_cpu_stat(cgrp, cpu); + + if (WARN_ON_ONCE(cstat->updated_children != cgrp) || + WARN_ON_ONCE(cstat->updated_next)) + return; + } + + free_percpu(cgrp->cpu_stat); + cgrp->cpu_stat = NULL; +} + +void __init cgroup_stat_boot(void) +{ + int cpu; + + for_each_possible_cpu(cpu) + raw_spin_lock_init(per_cpu_ptr(&cgroup_cpu_stat_lock, cpu)); + + BUG_ON(cgroup_stat_init(&cgrp_dfl_root.cgrp)); +} -- cgit v1.2.3 From 38683148828165ea0b66ace93a9fedc2d3281e27 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 25 Sep 2017 13:50:20 -0700 Subject: cgroup: statically initialize init_css_set->dfl_cgrp MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Like other csets, init_css_set's dfl_cgrp is initialized when the cset gets linked. init_css_set gets linked in cgroup_init(). This has been fine till now but the recently added basic CPU usage accounting may end up accessing dfl_cgrp of init before cgroup_init() leading to the following oops. SELinux: Initializing. BUG: unable to handle kernel NULL pointer dereference at 00000000000000b0 IP: account_system_index_time+0x60/0x90 PGD 0 P4D 0 Oops: 0000 [#1] SMP Modules linked in: CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.14.0-rc2-00003-g041cd64 #10 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS +1.9.3-20161025_171302-gandalf 04/01/2014 task: ffffffff81e10480 task.stack: ffffffff81e00000 RIP: 0010:account_system_index_time+0x60/0x90 RSP: 0000:ffff880011e03cb8 EFLAGS: 00010002 RAX: ffffffff81ef8800 RBX: ffffffff81e10480 RCX: 0000000000000003 RDX: 0000000000000000 RSI: 00000000000f4240 RDI: 0000000000000000 RBP: ffff880011e03cc0 R08: 0000000000010000 R09: 0000000000000000 R10: 0000000000000020 R11: 0000003b9aca0000 R12: 000000000001c100 R13: 0000000000000000 R14: ffffffff81e10480 R15: ffffffff81e03cd8 FS: 0000000000000000(0000) GS:ffff880011e00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000b0 CR3: 0000000001e09000 CR4: 00000000000006b0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: account_system_time+0x45/0x60 account_process_tick+0x5a/0x140 update_process_times+0x22/0x60 tick_periodic+0x2b/0x90 tick_handle_periodic+0x25/0x70 timer_interrupt+0x15/0x20 __handle_irq_event_percpu+0x7e/0x1b0 handle_irq_event_percpu+0x23/0x60 handle_irq_event+0x42/0x70 handle_level_irq+0x83/0x100 handle_irq+0x6f/0x110 do_IRQ+0x46/0xd0 common_interrupt+0x9d/0x9d Fix it by statically initializing init_css_set.dfl_cgrp so that init's default cgroup is accessible from the get-go. Fixes: 041cd640b2f3 ("cgroup: Implement cgroup2 basic CPU usage accounting") Reported-by: “kbuild-all@01.org” Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d036625556c9..7975b20f1fd1 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -649,6 +649,14 @@ struct css_set init_css_set = { .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .mg_preload_node = LIST_HEAD_INIT(init_css_set.mg_preload_node), .mg_node = LIST_HEAD_INIT(init_css_set.mg_node), + + /* + * The following field is re-initialized when this cset gets linked + * in cgroup_init(). However, let's initialize the field + * statically too so that the default cgroup can be accessed safely + * early during boot. + */ + .dfl_cgrp = &cgrp_dfl_root.cgrp, }; static int css_set_count = 1; /* 1 for init_css_set */ -- cgit v1.2.3 From 324bda9e6c5add86ba2e1066476481c48132aca0 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:21 -0700 Subject: bpf: multi program support for cgroup+bpf introduce BPF_F_ALLOW_MULTI flag that can be used to attach multiple bpf programs to a cgroup. The difference between three possible flags for BPF_PROG_ATTACH command: - NONE(default): No further bpf programs allowed in the subtree. - BPF_F_ALLOW_OVERRIDE: If a sub-cgroup installs some bpf program, the program in this cgroup yields to sub-cgroup program. - BPF_F_ALLOW_MULTI: If a sub-cgroup installs some bpf program, that cgroup program gets run in addition to the program in this cgroup. NONE and BPF_F_ALLOW_OVERRIDE existed before. This patch doesn't change their behavior. It only clarifies the semantics in relation to new flag. Only one program is allowed to be attached to a cgroup with NONE or BPF_F_ALLOW_OVERRIDE flag. Multiple programs are allowed to be attached to a cgroup with BPF_F_ALLOW_MULTI flag. They are executed in FIFO order (those that were attached first, run first) The programs of sub-cgroup are executed first, then programs of this cgroup and then programs of parent cgroup. All eligible programs are executed regardless of return code from earlier programs. To allow efficient execution of multiple programs attached to a cgroup and to avoid penalizing cgroups without any programs attached introduce 'struct bpf_prog_array' which is RCU protected array of pointers to bpf programs. Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- kernel/cgroup/cgroup.c | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6551cd45238..57eb866ae78d 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1896,6 +1896,9 @@ int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask, int ref_flags) if (ret) goto destroy_root; + ret = cgroup_bpf_inherit(root_cgrp); + WARN_ON_ONCE(ret); + trace_cgroup_setup_root(root); /* @@ -4713,6 +4716,9 @@ static struct cgroup *cgroup_create(struct cgroup *parent) cgrp->self.parent = &parent->self; cgrp->root = root; cgrp->level = level; + ret = cgroup_bpf_inherit(cgrp); + if (ret) + goto out_idr_free; for (tcgrp = cgrp; tcgrp; tcgrp = cgroup_parent(tcgrp)) { cgrp->ancestor_ids[tcgrp->level] = tcgrp->id; @@ -4747,13 +4753,12 @@ static struct cgroup *cgroup_create(struct cgroup *parent) if (!cgroup_on_dfl(cgrp)) cgrp->subtree_control = cgroup_control(cgrp); - if (parent) - cgroup_bpf_inherit(cgrp, parent); - cgroup_propagate_control(cgrp); return cgrp; +out_idr_free: + cgroup_idr_remove(&root->cgroup_idr, cgrp->id); out_cancel_ref: percpu_ref_exit(&cgrp->self.refcnt); out_free_cgrp: @@ -5736,14 +5741,23 @@ void cgroup_sk_free(struct sock_cgroup_data *skcd) #endif /* CONFIG_SOCK_CGROUP_DATA */ #ifdef CONFIG_CGROUP_BPF -int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, - enum bpf_attach_type type, bool overridable) +int cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_attach(cgrp, prog, type, flags); + mutex_unlock(&cgroup_mutex); + return ret; +} +int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, + enum bpf_attach_type type, u32 flags) { - struct cgroup *parent = cgroup_parent(cgrp); int ret; mutex_lock(&cgroup_mutex); - ret = __cgroup_bpf_update(cgrp, parent, prog, type, overridable); + ret = __cgroup_bpf_detach(cgrp, prog, type, flags); mutex_unlock(&cgroup_mutex); return ret; } -- cgit v1.2.3 From 468e2f64d220fe2dc11caa2bcb9b3a1e50fc7321 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 2 Oct 2017 22:50:22 -0700 Subject: bpf: introduce BPF_PROG_QUERY command introduce BPF_PROG_QUERY command to retrieve a set of either attached programs to given cgroup or a set of effective programs that will execute for events within a cgroup Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: Martin KaFai Lau for cgroup bits Acked-by: Tejun Heo Signed-off-by: David S. Miller --- kernel/cgroup/cgroup.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 57eb866ae78d..269512b94a94 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5761,4 +5761,14 @@ int cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog, mutex_unlock(&cgroup_mutex); return ret; } +int cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + int ret; + + mutex_lock(&cgroup_mutex); + ret = __cgroup_bpf_query(cgrp, attr, uattr); + mutex_unlock(&cgroup_mutex); + return ret; +} #endif /* CONFIG_CGROUP_BPF */ -- cgit v1.2.3 From d41bf8c9deaed1a90b18d3ffc5639d4c19f0259a Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 23 Oct 2017 16:18:27 -0700 Subject: cgroup, sched: Move basic cpu stats from cgroup.stat to cpu.stat The basic cpu stat is currently shown with "cpu." prefix in cgroup.stat, and the same information is duplicated in cpu.stat when cpu controller is enabled. This is ugly and not very scalable as we want to expand the coverage of stat information which is always available. This patch makes cgroup core always create "cpu.stat" file and show the basic cpu stat there and calls the cpu controller to show the extra stats when enabled. This ensures that the same information isn't presented in multiple places and makes future expansion of basic stats easier. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra (Intel) --- kernel/cgroup/cgroup-internal.h | 1 + kernel/cgroup/cgroup.c | 60 +++++++++++++++++++++++++++++++++++++++-- kernel/cgroup/stat.c | 10 +++---- 3 files changed, 64 insertions(+), 7 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index fa642c99586a..4dc317090920 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -205,6 +205,7 @@ int cgroup_task_count(const struct cgroup *cgrp); void cgroup_stat_flush(struct cgroup *cgrp); int cgroup_stat_init(struct cgroup *cgrp); void cgroup_stat_exit(struct cgroup *cgrp); +void cgroup_stat_show_cputime(struct seq_file *seq); void cgroup_stat_boot(void); /* diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 7975b20f1fd1..d9773e49a1b4 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -463,6 +463,28 @@ static struct cgroup_subsys_state *cgroup_css(struct cgroup *cgrp, return &cgrp->self; } +/** + * cgroup_tryget_css - try to get a cgroup's css for the specified subsystem + * @cgrp: the cgroup of interest + * @ss: the subsystem of interest + * + * Find and get @cgrp's css assocaited with @ss. If the css doesn't exist + * or is offline, %NULL is returned. + */ +static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) +{ + struct cgroup_subsys_state *css; + + rcu_read_lock(); + css = cgroup_css(cgrp, ss); + if (!css || !css_tryget_online(css)) + css = NULL; + rcu_read_unlock(); + + return css; +} + /** * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest @@ -3311,11 +3333,40 @@ static int cgroup_stat_show(struct seq_file *seq, void *v) seq_printf(seq, "nr_dying_descendants %d\n", cgroup->nr_dying_descendants); - cgroup_stat_show_cputime(seq, "cpu."); - return 0; } +static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq, + struct cgroup *cgrp, int ssid) +{ + struct cgroup_subsys *ss = cgroup_subsys[ssid]; + struct cgroup_subsys_state *css; + int ret; + + if (!ss->css_extra_stat_show) + return 0; + + css = cgroup_tryget_css(cgrp, ss); + if (!css) + return 0; + + ret = ss->css_extra_stat_show(seq, css); + css_put(css); + return ret; +} + +static int cpu_stat_show(struct seq_file *seq, void *v) +{ + struct cgroup *cgrp = seq_css(seq)->cgroup; + int ret = 0; + + cgroup_stat_show_cputime(seq); +#ifdef CONFIG_CGROUP_SCHED + ret = cgroup_extra_stat_show(seq, cgrp, cpu_cgrp_id); +#endif + return ret; +} + static int cgroup_file_open(struct kernfs_open_file *of) { struct cftype *cft = of->kn->priv; @@ -4423,6 +4474,11 @@ static struct cftype cgroup_base_files[] = { .name = "cgroup.stat", .seq_show = cgroup_stat_show, }, + { + .name = "cpu.stat", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_stat_show, + }, { } /* terminate */ }; diff --git a/kernel/cgroup/stat.c b/kernel/cgroup/stat.c index 9cce79e89320..133b465691d6 100644 --- a/kernel/cgroup/stat.c +++ b/kernel/cgroup/stat.c @@ -256,7 +256,7 @@ void __cgroup_account_cputime_field(struct cgroup *cgrp, cgroup_cpu_stat_account_end(cgrp, cstat); } -void cgroup_stat_show_cputime(struct seq_file *seq, const char *prefix) +void cgroup_stat_show_cputime(struct seq_file *seq) { struct cgroup *cgrp = seq_css(seq)->cgroup; u64 usage, utime, stime; @@ -278,10 +278,10 @@ void cgroup_stat_show_cputime(struct seq_file *seq, const char *prefix) do_div(utime, NSEC_PER_USEC); do_div(stime, NSEC_PER_USEC); - seq_printf(seq, "%susage_usec %llu\n" - "%suser_usec %llu\n" - "%ssystem_usec %llu\n", - prefix, usage, prefix, utime, prefix, stime); + seq_printf(seq, "usage_usec %llu\n" + "user_usec %llu\n" + "system_usec %llu\n", + usage, utime, stime); } int cgroup_stat_init(struct cgroup *cgrp) -- cgit v1.2.3 From edb9382175c3ebdced8ffdb3e0f20052ad9fdbe9 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 27 Oct 2017 04:42:37 +0200 Subject: sched/isolation: Move isolcpus= handling to the housekeeping code We want to centralize the isolation features, to be done by the housekeeping subsystem and scheduler domain isolation is a significant part of it. No intended behaviour change, we just reuse the housekeeping cpumask and core code. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Mike Galbraith Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rik van Riel Cc: Wanpeng Li Link: http://lkml.kernel.org/r/1509072159-31808-11-git-send-email-frederic@kernel.org Signed-off-by: Ingo Molnar --- kernel/cgroup/cpuset.c | 15 +++++---------- 1 file changed, 5 insertions(+), 10 deletions(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 4657e2924ecb..f7efa7b4d825 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -57,7 +57,7 @@ #include #include #include - +#include #include #include #include @@ -656,7 +656,6 @@ static int generate_sched_domains(cpumask_var_t **domains, int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ - cpumask_var_t non_isolated_cpus; /* load balanced CPUs */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ @@ -666,10 +665,6 @@ static int generate_sched_domains(cpumask_var_t **domains, dattr = NULL; csa = NULL; - if (!alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL)) - goto done; - cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); - /* Special case for the 99% of systems with one, full, sched domain */ if (is_sched_load_balance(&top_cpuset)) { ndoms = 1; @@ -683,7 +678,7 @@ static int generate_sched_domains(cpumask_var_t **domains, update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, - non_isolated_cpus); + housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } @@ -707,7 +702,8 @@ static int generate_sched_domains(cpumask_var_t **domains, */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && - cpumask_intersects(cp->cpus_allowed, non_isolated_cpus))) + cpumask_intersects(cp->cpus_allowed, + housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (is_sched_load_balance(cp)) @@ -789,7 +785,7 @@ restart: if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); - cpumask_and(dp, dp, non_isolated_cpus); + cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); @@ -802,7 +798,6 @@ restart: BUG_ON(nslot != ndoms); done: - free_cpumask_var(non_isolated_cpus); kfree(csa); /* -- cgit v1.2.3 From c3ba13298709f46e72b22d087d0aa02bd012e4b0 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 30 Oct 2017 08:13:14 -0700 Subject: cgroup: mark @cgrp __maybe_unused in cpu_stat_show() The local variable @cgrp isn't used if !CONFIG_CGROUP_SCHED. Mark the variable with __maybe_unused to avoid a compile warning. Reported-by: "kbuild-all@01.org" Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d9773e49a1b4..d6ed725f36d9 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3357,7 +3357,7 @@ static int __maybe_unused cgroup_extra_stat_show(struct seq_file *seq, static int cpu_stat_show(struct seq_file *seq, void *v) { - struct cgroup *cgrp = seq_css(seq)->cgroup; + struct cgroup __maybe_unused *cgrp = seq_css(seq)->cgroup; int ret = 0; cgroup_stat_show_cputime(seq); -- cgit v1.2.3 From b24413180f5600bcb3bb70fbed5cf186b60864bd Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Wed, 1 Nov 2017 15:07:57 +0100 Subject: License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart Reviewed-by: Philippe Ombredanne Reviewed-by: Thomas Gleixner Signed-off-by: Greg Kroah-Hartman --- kernel/cgroup/Makefile | 1 + kernel/cgroup/cgroup-internal.h | 1 + kernel/cgroup/debug.c | 1 + kernel/cgroup/namespace.c | 1 + 4 files changed, 4 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/Makefile b/kernel/cgroup/Makefile index ce693ccb8c58..ae448f7632cc 100644 --- a/kernel/cgroup/Makefile +++ b/kernel/cgroup/Makefile @@ -1,3 +1,4 @@ +# SPDX-License-Identifier: GPL-2.0 obj-y := cgroup.o namespace.o cgroup-v1.o obj-$(CONFIG_CGROUP_FREEZER) += freezer.o diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index 5151ff256c29..bf54ade001be 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0 */ #ifndef __CGROUP_INTERNAL_H #define __CGROUP_INTERNAL_H diff --git a/kernel/cgroup/debug.c b/kernel/cgroup/debug.c index f661b4cc5efd..5f780d8f6a9d 100644 --- a/kernel/cgroup/debug.c +++ b/kernel/cgroup/debug.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* * Debug controller * diff --git a/kernel/cgroup/namespace.c b/kernel/cgroup/namespace.c index 66129eb4371d..b05f1dd58a62 100644 --- a/kernel/cgroup/namespace.c +++ b/kernel/cgroup/namespace.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 #include "cgroup-internal.h" #include -- cgit v1.2.3 From 01ee6cfb1483fe57c9cbd8e73817dfbf9bacffd3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 6 Nov 2017 13:30:28 -0500 Subject: cgroup: export list of delegatable control files using sysfs Delegatable cgroup v2 control files may require special handling (e.g. chowning), and the exact list of such files varies between kernel versions (and likely to be extended in the future). To guarantee correctness of this list and simplify the life of userspace (systemd, first of all), let's export the list via /sys/kernel/cgroup/delegate pseudo-file. Format is siple: each control file name is printed on a new line. Example: $ cat /sys/kernel/cgroup/delegate cgroup.procs cgroup.subtree_control Signed-off-by: Roman Gushchin Cc: Tejun Heo Cc: kernel-team@fb.com Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d6ed725f36d9..eed92ed624e5 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5832,3 +5832,64 @@ int cgroup_bpf_update(struct cgroup *cgrp, struct bpf_prog *prog, return ret; } #endif /* CONFIG_CGROUP_BPF */ + +#ifdef CONFIG_SYSFS +static ssize_t show_delegatable_files(struct cftype *files, char *buf, + ssize_t size, const char *prefix) +{ + struct cftype *cft; + ssize_t ret = 0; + + for (cft = files; cft && cft->name[0] != '\0'; cft++) { + if (!(cft->flags & CFTYPE_NS_DELEGATABLE)) + continue; + + if (prefix) + ret += snprintf(buf + ret, size - ret, "%s.", prefix); + + ret += snprintf(buf + ret, size - ret, "%s\n", cft->name); + + if (unlikely(ret >= size)) { + WARN_ON(1); + break; + } + } + + return ret; +} + +static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + struct cgroup_subsys *ss; + int ssid; + ssize_t ret = 0; + + ret = show_delegatable_files(cgroup_base_files, buf, PAGE_SIZE - ret, + NULL); + + for_each_subsys(ss, ssid) + ret += show_delegatable_files(ss->dfl_cftypes, buf + ret, + PAGE_SIZE - ret, + cgroup_subsys_name[ssid]); + + return ret; +} +static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); + +static struct attribute *cgroup_sysfs_attrs[] = { + &cgroup_delegate_attr.attr, + NULL, +}; + +static const struct attribute_group cgroup_sysfs_attr_group = { + .attrs = cgroup_sysfs_attrs, + .name = "cgroup", +}; + +static int __init cgroup_sysfs_init(void) +{ + return sysfs_create_group(kernel_kobj, &cgroup_sysfs_attr_group); +} +subsys_initcall(cgroup_sysfs_init); +#endif /* CONFIG_SYSFS */ -- cgit v1.2.3 From 5f2e673405b742be64e7c3604ed4ed3ac14f35ce Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 6 Nov 2017 13:30:29 -0500 Subject: cgroup: export list of cgroups v2 features using sysfs The active development of cgroups v2 sometimes leads to a creation of interfaces, which are not turned on by default (to provide backward compatibility). It's handy to know from userspace, which cgroup v2 features are supported without calculating it based on the kernel version. So, let's export the list of such features using /sys/kernel/cgroup/features pseudo-file. The list is hardcoded and has to be extended when new functionality is added. Each feature is printed on a new line. Example: $ cat /sys/kernel/cgroup/features nsdelegate Signed-off-by: Roman Gushchin Cc: Tejun Heo Cc: kernel-team@fb.com Signed-off-by: Tejun Heo --- kernel/cgroup/cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/cgroup') diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index eed92ed624e5..69e65d28fe98 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5877,8 +5877,16 @@ static ssize_t delegate_show(struct kobject *kobj, struct kobj_attribute *attr, } static struct kobj_attribute cgroup_delegate_attr = __ATTR_RO(delegate); +static ssize_t features_show(struct kobject *kobj, struct kobj_attribute *attr, + char *buf) +{ + return snprintf(buf, PAGE_SIZE, "nsdelegate\n"); +} +static struct kobj_attribute cgroup_features_attr = __ATTR_RO(features); + static struct attribute *cgroup_sysfs_attrs[] = { &cgroup_delegate_attr.attr, + &cgroup_features_attr.attr, NULL, }; -- cgit v1.2.3