From b0ae19811375031ae3b3fecc65b702a9c6e5cc28 Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Fri, 15 Oct 2010 04:21:18 +0900 Subject: security: remove unused parameter from security_task_setscheduler() All security modules shouldn't change sched_param parameter of security_task_setscheduler(). This is not only meaningless, but also make a harmful result if caller pass a static variable. This patch remove policy and sched_param parameter from security_task_setscheduler() becuase none of security module is using it. Cc: James Morris Signed-off-by: KOSAKI Motohiro Signed-off-by: James Morris --- kernel/cpuset.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index b23c0979bbe7..51b143e2a07a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1397,7 +1397,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, if (tsk->flags & PF_THREAD_BOUND) return -EINVAL; - ret = security_task_setscheduler(tsk, 0, NULL); + ret = security_task_setscheduler(tsk); if (ret) return ret; if (threadgroup) { @@ -1405,7 +1405,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, rcu_read_lock(); list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - ret = security_task_setscheduler(c, 0, NULL); + ret = security_task_setscheduler(c); if (ret) { rcu_read_unlock(); return ret; -- cgit v1.2.2 From f7e835710ab5f6e43933c983f38f2d2e262b718c Mon Sep 17 00:00:00 2001 From: Al Viro Date: Mon, 26 Jul 2010 13:23:11 +0400 Subject: convert cgroup and cpuset Signed-off-by: Al Viro --- kernel/cpuset.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 51b143e2a07a..4349935c2ad8 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -231,18 +231,17 @@ static DEFINE_SPINLOCK(cpuset_buffer_lock); * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ -static int cpuset_get_sb(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data, struct vfsmount *mnt) +static struct dentry *cpuset_mount(struct file_system_type *fs_type, + int flags, const char *unused_dev_name, void *data) { struct file_system_type *cgroup_fs = get_fs_type("cgroup"); - int ret = -ENODEV; + struct dentry *ret = ERR_PTR(-ENODEV); if (cgroup_fs) { char mountopts[] = "cpuset,noprefix," "release_agent=/sbin/cpuset_release_agent"; - ret = cgroup_fs->get_sb(cgroup_fs, flags, - unused_dev_name, mountopts, mnt); + ret = cgroup_fs->mount(cgroup_fs, flags, + unused_dev_name, mountopts); put_filesystem(cgroup_fs); } return ret; @@ -250,7 +249,7 @@ static int cpuset_get_sb(struct file_system_type *fs_type, static struct file_system_type cpuset_fs_type = { .name = "cpuset", - .get_sb = cpuset_get_sb, + .mount = cpuset_mount, }; /* -- cgit v1.2.2 From b75f38d659e6fc747eda64cb72f3920e29dd44a4 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Fri, 4 Mar 2011 17:36:21 -0800 Subject: cpuset: add a missing unlock in cpuset_write_resmask() Don't forget to release cgroup_mutex if alloc_trial_cpuset() fails. [akpm@linux-foundation.org: avoid multiple return points] Signed-off-by: Li Zefan Cc: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4349935c2ad8..e92e98189032 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1575,8 +1575,10 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, return -ENODEV; trialcs = alloc_trial_cpuset(cs); - if (!trialcs) - return -ENOMEM; + if (!trialcs) { + retval = -ENOMEM; + goto out; + } switch (cft->private) { case FILE_CPULIST: @@ -1591,6 +1593,7 @@ static int cpuset_write_resmask(struct cgroup *cgrp, struct cftype *cft, } free_trial_cpuset(trialcs); +out: cgroup_unlock(); return retval; } -- cgit v1.2.2 From 9303e0c4814d2a6afca878cc35433291e862169c Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 23 Mar 2011 16:42:45 -0700 Subject: cpuset: remove unneeded NODEMASK_ALLOC() in cpuset_sprintf_memlist() It's not necessary to copy cpuset->mems_allowed to a buffer allocated by NODEMASK_ALLOC(). Just pass it to nodelist_scnprintf(). As spotted by Paul, a side effect is we fix a bug that the function can return -ENOMEM but the caller doesn't expect negative return value. Therefore change the return value of cpuset_sprintf_cpulist() and cpuset_sprintf_memlist() from int to size_t. Signed-off-by: Li Zefan Acked-by: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e92e98189032..4683fe728c9b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1610,34 +1610,26 @@ out: * across a page fault. */ -static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs) +static size_t cpuset_sprintf_cpulist(char *page, struct cpuset *cs) { - int ret; + size_t count; mutex_lock(&callback_mutex); - ret = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed); + count = cpulist_scnprintf(page, PAGE_SIZE, cs->cpus_allowed); mutex_unlock(&callback_mutex); - return ret; + return count; } -static int cpuset_sprintf_memlist(char *page, struct cpuset *cs) +static size_t cpuset_sprintf_memlist(char *page, struct cpuset *cs) { - NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL); - int retval; - - if (mask == NULL) - return -ENOMEM; + size_t count; mutex_lock(&callback_mutex); - *mask = cs->mems_allowed; + count = nodelist_scnprintf(page, PAGE_SIZE, cs->mems_allowed); mutex_unlock(&callback_mutex); - retval = nodelist_scnprintf(page, PAGE_SIZE, *mask); - - NODEMASK_FREE(mask); - - return retval; + return count; } static ssize_t cpuset_common_file_read(struct cgroup *cont, -- cgit v1.2.2 From c8163ca8afcac0fc54593fc60d1e1110edbd0eb2 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 23 Mar 2011 16:42:46 -0700 Subject: cpuset: remove unneeded NODEMASK_ALLOC() in cpuset_attach() oldcs->mems_allowed is not modified during cpuset_attach(), so we don't have to copy it to a buffer allocated by NODEMASK_ALLOC(). Just pass it to cpuset_migrate_mm(). Signed-off-by: Li Zefan Cc: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4683fe728c9b..7f384f4013b2 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1438,10 +1438,9 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); - NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL); NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL); - if (from == NULL || to == NULL) + if (to == NULL) goto alloc_fail; if (cs == &top_cpuset) { @@ -1463,18 +1462,16 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, } /* change mm; only needs to be done once even if threadgroup */ - *from = oldcs->mems_allowed; *to = cs->mems_allowed; mm = get_task_mm(tsk); if (mm) { mpol_rebind_mm(mm, to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, from, to); + cpuset_migrate_mm(mm, &oldcs->mems_allowed, to); mmput(mm); } alloc_fail: - NODEMASK_FREE(from); NODEMASK_FREE(to); } -- cgit v1.2.2 From ee24d3797780eee6ffe581a7b78d27896f9b494a Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 23 Mar 2011 16:42:47 -0700 Subject: cpuset: fix unchecked calls to NODEMASK_ALLOC() Those functions that use NODEMASK_ALLOC() can't propagate errno to users, but will fail silently. Fix it by using a static nodemask_t variable for each function, and those variables are protected by cgroup_mutex; [akpm@linux-foundation.org: fix comment spelling, strengthen cgroup_lock comment] Signed-off-by: Li Zefan Cc: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 51 ++++++++++++++++----------------------------------- 1 file changed, 16 insertions(+), 35 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 7f384f4013b2..e472fe139192 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1015,17 +1015,12 @@ static void cpuset_change_nodemask(struct task_struct *p, struct cpuset *cs; int migrate; const nodemask_t *oldmem = scan->data; - NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL); - - if (!newmems) - return; + static nodemask_t newmems; /* protected by cgroup_mutex */ cs = cgroup_cs(scan->cg); - guarantee_online_mems(cs, newmems); + guarantee_online_mems(cs, &newmems); - cpuset_change_task_nodemask(p, newmems); - - NODEMASK_FREE(newmems); + cpuset_change_task_nodemask(p, &newmems); mm = get_task_mm(p); if (!mm) @@ -1438,41 +1433,35 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); - NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL); - - if (to == NULL) - goto alloc_fail; + static nodemask_t to; /* protected by cgroup_mutex */ if (cs == &top_cpuset) { cpumask_copy(cpus_attach, cpu_possible_mask); } else { guarantee_online_cpus(cs, cpus_attach); } - guarantee_online_mems(cs, to); + guarantee_online_mems(cs, &to); /* do per-task migration stuff possibly for each in the threadgroup */ - cpuset_attach_task(tsk, to, cs); + cpuset_attach_task(tsk, &to, cs); if (threadgroup) { struct task_struct *c; rcu_read_lock(); list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - cpuset_attach_task(c, to, cs); + cpuset_attach_task(c, &to, cs); } rcu_read_unlock(); } /* change mm; only needs to be done once even if threadgroup */ - *to = cs->mems_allowed; + to = cs->mems_allowed; mm = get_task_mm(tsk); if (mm) { - mpol_rebind_mm(mm, to); + mpol_rebind_mm(mm, &to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, &oldcs->mems_allowed, to); + cpuset_migrate_mm(mm, &oldcs->mems_allowed, &to); mmput(mm); } - -alloc_fail: - NODEMASK_FREE(to); } /* The various types of files and directories in a cpuset file system */ @@ -2055,10 +2044,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) struct cpuset *cp; /* scans cpusets being updated */ struct cpuset *child; /* scans child cpusets of cp */ struct cgroup *cont; - NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL); - - if (oldmems == NULL) - return; + static nodemask_t oldmems; /* protected by cgroup_mutex */ list_add_tail((struct list_head *)&root->stack_list, &queue); @@ -2075,7 +2061,7 @@ static void scan_for_empty_cpusets(struct cpuset *root) nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY])) continue; - *oldmems = cp->mems_allowed; + oldmems = cp->mems_allowed; /* Remove offline cpus and mems from this cpuset. */ mutex_lock(&callback_mutex); @@ -2091,10 +2077,9 @@ static void scan_for_empty_cpusets(struct cpuset *root) remove_tasks_in_empty_cpuset(cp); else { update_tasks_cpumask(cp, NULL); - update_tasks_nodemask(cp, oldmems, NULL); + update_tasks_nodemask(cp, &oldmems, NULL); } } - NODEMASK_FREE(oldmems); } /* @@ -2136,19 +2121,16 @@ void cpuset_update_active_cpus(void) static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { - NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL); - - if (oldmems == NULL) - return NOTIFY_DONE; + static nodemask_t oldmems; /* protected by cgroup_mutex */ cgroup_lock(); switch (action) { case MEM_ONLINE: - *oldmems = top_cpuset.mems_allowed; + oldmems = top_cpuset.mems_allowed; mutex_lock(&callback_mutex); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; mutex_unlock(&callback_mutex); - update_tasks_nodemask(&top_cpuset, oldmems, NULL); + update_tasks_nodemask(&top_cpuset, &oldmems, NULL); break; case MEM_OFFLINE: /* @@ -2162,7 +2144,6 @@ static int cpuset_track_online_nodes(struct notifier_block *self, } cgroup_unlock(); - NODEMASK_FREE(oldmems); return NOTIFY_OK; } #endif -- cgit v1.2.2 From 523fb486bfd94e3a3b16a42bcb21b1959cf14df8 Mon Sep 17 00:00:00 2001 From: Li Zefan Date: Wed, 23 Mar 2011 16:42:48 -0700 Subject: cpuset: hold callback_mutex in cpuset_post_clone() Chaning cpuset->mems/cpuset->cpus should be protected under callback_mutex. cpuset_clone() doesn't follow this rule. It's ok because it's called when creating and initializing a cgroup, but we'd better hold the lock to avoid subtil break in the future. Signed-off-by: Li Zefan Acked-by: Paul Menage Acked-by: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index e472fe139192..33eee16addb8 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1840,8 +1840,10 @@ static void cpuset_post_clone(struct cgroup_subsys *ss, cs = cgroup_cs(cgroup); parent_cs = cgroup_cs(parent); + mutex_lock(&callback_mutex); cs->mems_allowed = parent_cs->mems_allowed; cpumask_copy(cs->cpus_allowed, parent_cs->cpus_allowed); + mutex_unlock(&callback_mutex); return; } -- cgit v1.2.2 From 60495e7760d8ee364695006af37309b0755e0e17 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 7 Apr 2011 14:10:04 +0200 Subject: sched: Dynamic sched_domain::level Remove the SD_LV_ enum and use dynamic level assignments. Signed-off-by: Peter Zijlstra Cc: Mike Galbraith Cc: Nick Piggin Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20110407122942.969433965@chello.nl Signed-off-by: Ingo Molnar --- kernel/cpuset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 33eee16addb8..2bb8c2e98fff 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1159,7 +1159,7 @@ int current_cpuset_is_being_rebound(void) static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP - if (val < -1 || val >= SD_LV_MAX) + if (val < -1 || val >= sched_domain_level_max) return -EINVAL; #endif -- cgit v1.2.2 From f780bdb7c1c73009cb57adcf99ef50027d80bf3c Mon Sep 17 00:00:00 2001 From: Ben Blum Date: Thu, 26 May 2011 16:25:19 -0700 Subject: cgroups: add per-thread subsystem callbacks Add cgroup subsystem callbacks for per-thread attachment in atomic contexts Add can_attach_task(), pre_attach(), and attach_task() as new callbacks for cgroups's subsystem interface. Unlike can_attach and attach, these are for per-thread operations, to be called potentially many times when attaching an entire threadgroup. Also, the old "bool threadgroup" interface is removed, as replaced by this. All subsystems are modified for the new interface - of note is cpuset, which requires from/to nodemasks for attach to be globally scoped (though per-cpuset would work too) to persist from its pre_attach to attach_task and attach. This is a pre-patch for cgroup-procs-writable.patch. Signed-off-by: Ben Blum Cc: "Eric W. Biederman" Cc: Li Zefan Cc: Matt Helsley Reviewed-by: Paul Menage Cc: Oleg Nesterov Cc: David Rientjes Cc: Miao Xie Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 96 +++++++++++++++++++++++++++------------------------------ 1 file changed, 46 insertions(+), 50 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 2bb8c2e98fff..55b297d78adc 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1367,14 +1367,10 @@ static int fmeter_getrate(struct fmeter *fmp) return val; } -/* Protected by cgroup_lock */ -static cpumask_var_t cpus_attach; - /* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct task_struct *tsk, bool threadgroup) + struct task_struct *tsk) { - int ret; struct cpuset *cs = cgroup_cs(cont); if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) @@ -1391,29 +1387,42 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont, if (tsk->flags & PF_THREAD_BOUND) return -EINVAL; - ret = security_task_setscheduler(tsk); - if (ret) - return ret; - if (threadgroup) { - struct task_struct *c; - - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - ret = security_task_setscheduler(c); - if (ret) { - rcu_read_unlock(); - return ret; - } - } - rcu_read_unlock(); - } return 0; } -static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to, - struct cpuset *cs) +static int cpuset_can_attach_task(struct cgroup *cgrp, struct task_struct *task) +{ + return security_task_setscheduler(task); +} + +/* + * Protected by cgroup_lock. The nodemasks must be stored globally because + * dynamically allocating them is not allowed in pre_attach, and they must + * persist among pre_attach, attach_task, and attach. + */ +static cpumask_var_t cpus_attach; +static nodemask_t cpuset_attach_nodemask_from; +static nodemask_t cpuset_attach_nodemask_to; + +/* Set-up work for before attaching each task. */ +static void cpuset_pre_attach(struct cgroup *cont) +{ + struct cpuset *cs = cgroup_cs(cont); + + if (cs == &top_cpuset) + cpumask_copy(cpus_attach, cpu_possible_mask); + else + guarantee_online_cpus(cs, cpus_attach); + + guarantee_online_mems(cs, &cpuset_attach_nodemask_to); +} + +/* Per-thread attachment work. */ +static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk) { int err; + struct cpuset *cs = cgroup_cs(cont); + /* * can_attach beforehand should guarantee that this doesn't fail. * TODO: have a better way to handle failure here @@ -1421,45 +1430,29 @@ static void cpuset_attach_task(struct task_struct *tsk, nodemask_t *to, err = set_cpus_allowed_ptr(tsk, cpus_attach); WARN_ON_ONCE(err); - cpuset_change_task_nodemask(tsk, to); + cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, tsk); - } static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont, - struct cgroup *oldcont, struct task_struct *tsk, - bool threadgroup) + struct cgroup *oldcont, struct task_struct *tsk) { struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); - static nodemask_t to; /* protected by cgroup_mutex */ - if (cs == &top_cpuset) { - cpumask_copy(cpus_attach, cpu_possible_mask); - } else { - guarantee_online_cpus(cs, cpus_attach); - } - guarantee_online_mems(cs, &to); - - /* do per-task migration stuff possibly for each in the threadgroup */ - cpuset_attach_task(tsk, &to, cs); - if (threadgroup) { - struct task_struct *c; - rcu_read_lock(); - list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { - cpuset_attach_task(c, &to, cs); - } - rcu_read_unlock(); - } - - /* change mm; only needs to be done once even if threadgroup */ - to = cs->mems_allowed; + /* + * Change mm, possibly for multiple threads in a threadgroup. This is + * expensive and may sleep. + */ + cpuset_attach_nodemask_from = oldcs->mems_allowed; + cpuset_attach_nodemask_to = cs->mems_allowed; mm = get_task_mm(tsk); if (mm) { - mpol_rebind_mm(mm, &to); + mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); if (is_memory_migrate(cs)) - cpuset_migrate_mm(mm, &oldcs->mems_allowed, &to); + cpuset_migrate_mm(mm, &cpuset_attach_nodemask_from, + &cpuset_attach_nodemask_to); mmput(mm); } } @@ -1911,6 +1904,9 @@ struct cgroup_subsys cpuset_subsys = { .create = cpuset_create, .destroy = cpuset_destroy, .can_attach = cpuset_can_attach, + .can_attach_task = cpuset_can_attach_task, + .pre_attach = cpuset_pre_attach, + .attach_task = cpuset_attach_task, .attach = cpuset_attach, .populate = cpuset_populate, .post_clone = cpuset_post_clone, -- cgit v1.2.2 From a77aea92010acf54ad785047234418d5d68772e2 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Thu, 26 May 2011 16:25:23 -0700 Subject: cgroup: remove the ns_cgroup The ns_cgroup is an annoying cgroup at the namespace / cgroup frontier and leads to some problems: * cgroup creation is out-of-control * cgroup name can conflict when pids are looping * it is not possible to have a single process handling a lot of namespaces without falling in a exponential creation time * we may want to create a namespace without creating a cgroup The ns_cgroup was replaced by a compatibility flag 'clone_children', where a newly created cgroup will copy the parent cgroup values. The userspace has to manually create a cgroup and add a task to the 'tasks' file. This patch removes the ns_cgroup as suggested in the following thread: https://lists.linux-foundation.org/pipermail/containers/2009-June/018616.html The 'cgroup_clone' function is removed because it is no longer used. This is a userspace-visible change. Commit 45531757b45c ("cgroup: notify ns_cgroup deprecated") (merged into 2.6.27) caused the kernel to emit a printk warning users that the feature is planned for removal. Since that time we have heard from XXX users who were affected by this. Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Cc: Jamal Hadi Salim Reviewed-by: Li Zefan Acked-by: Paul Menage Acked-by: Matt Helsley Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cpuset.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 55b297d78adc..1ceeb049c827 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1802,10 +1802,9 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont) } /* - * post_clone() is called at the end of cgroup_clone(). - * 'cgroup' was just created automatically as a result of - * a cgroup_clone(), and the current task is about to - * be moved into 'cgroup'. + * post_clone() is called during cgroup_create() when the + * clone_children mount argument was specified. The cgroup + * can not yet have any tasks. * * Currently we refuse to set up the cgroup - thereby * refusing the task to be entered, and as a result refusing -- cgit v1.2.2 From 1e1b6c511d1b23cb7c3b619d82fc7bd9f620565d Mon Sep 17 00:00:00 2001 From: KOSAKI Motohiro Date: Thu, 19 May 2011 15:08:58 +0900 Subject: cpuset: Fix cpuset_cpus_allowed_fallback(), don't update tsk->rt.nr_cpus_allowed The rule is, we have to update tsk->rt.nr_cpus_allowed if we change tsk->cpus_allowed. Otherwise RT scheduler may confuse. Signed-off-by: KOSAKI Motohiro Cc: Oleg Nesterov Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/4DD4B3FA.5060901@jp.fujitsu.com Signed-off-by: Ingo Molnar --- kernel/cpuset.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/cpuset.c') diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 1ceeb049c827..9c9b7545c810 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2190,7 +2190,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) rcu_read_lock(); cs = task_cs(tsk); if (cs) - cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed); + do_set_cpus_allowed(tsk, cs->cpus_allowed); rcu_read_unlock(); /* @@ -2217,7 +2217,7 @@ int cpuset_cpus_allowed_fallback(struct task_struct *tsk) * Like above we can temporary set any mask and rely on * set_cpus_allowed_ptr() as synchronization point. */ - cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask); + do_set_cpus_allowed(tsk, cpu_possible_mask); cpu = cpumask_any(cpu_active_mask); } -- cgit v1.2.2