From 97978e6d1f2da0073416870410459694fbdbfd9b Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Oct 2010 15:33:35 -0700 Subject: cgroup: add clone_children control file The ns_cgroup is a control group interacting with the namespaces. When a new namespace is created, a corresponding cgroup is automatically created too. The cgroup name is the pid of the process who did 'unshare' or the child of 'clone'. This cgroup is tied with the namespace because it prevents a process to escape the control group and use the post_clone callback, so the child cgroup inherits the values of the parent cgroup. Unfortunately, the more we use this cgroup and the more we are facing problems with it: (1) when a process unshares, the cgroup name may conflict with a previous cgroup with the same pid, so unshare or clone return -EEXIST (2) the cgroup creation is out of control because there may have an application creating several namespaces where the system will automatically create several cgroups in his back and let them on the cgroupfs (eg. a vrf based on the network namespace). (3) the mix of (1) and (2) force an administrator to regularly check and clean these cgroups. This patchset removes the ns_cgroup by adding a new flag to the cgroup and the cgroupfs mount option. It enables the copy of the parent cgroup when a child cgroup is created. We can then safely remove the ns_cgroup as this flag brings a compatibility. We have now to manually create and add the task to a cgroup, which is consistent with the cgroup framework. This patch: Sent as an answer to a previous thread around the ns_cgroup. https://lists.linux-foundation.org/pipermail/containers/2009-June/018627.html It adds a control file 'clone_children' for a cgroup. This control file is a boolean specifying if the child cgroup should be a clone of the parent cgroup or not. The default value is 'false'. This flag makes the child cgroup to call the post_clone callback of all the subsystem, if it is available. At present, the cpuset is the only one which had implemented the post_clone callback. The option can be set at mount time by specifying the 'clone_children' mount option. Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Cc: Eric W. Biederman Acked-by: Paul Menage Reviewed-by: Li Zefan Cc: Jamal Hadi Salim Cc: Matt Helsley Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9270d532ec3c..4b218a46ddd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -243,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp) return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); } +static int clone_children(const struct cgroup *cgrp) +{ + return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); +} + /* * for_each_subsys() allows you to iterate on each subsystem attached to * an active hierarchy @@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs) seq_puts(seq, ",noprefix"); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); + if (clone_children(&root->top_cgroup)) + seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_printf(seq, ",name=%s", root->name); mutex_unlock(&cgroup_mutex); @@ -1050,6 +1057,7 @@ struct cgroup_sb_opts { unsigned long subsys_bits; unsigned long flags; char *release_agent; + bool clone_children; char *name; /* User explicitly requested empty subsystem */ bool none; @@ -1097,6 +1105,8 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) opts->none = true; } else if (!strcmp(token, "noprefix")) { set_bit(ROOT_NOPREFIX, &opts->flags); + } else if (!strcmp(token, "clone_children")) { + opts->clone_children = true; } else if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) @@ -1355,6 +1365,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts) strcpy(root->release_agent_path, opts->release_agent); if (opts->name) strcpy(root->name, opts->name); + if (opts->clone_children) + set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags); return root; } @@ -3173,6 +3185,23 @@ fail: return ret; } +static u64 cgroup_clone_children_read(struct cgroup *cgrp, + struct cftype *cft) +{ + return clone_children(cgrp); +} + +static int cgroup_clone_children_write(struct cgroup *cgrp, + struct cftype *cft, + u64 val) +{ + if (val) + set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + else + clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + return 0; +} + /* * for the common functions, 'private' gives the type of file */ @@ -3203,6 +3232,11 @@ static struct cftype files[] = { .write_string = cgroup_write_event_control, .mode = S_IWUGO, }, + { + .name = "cgroup.clone_children", + .read_u64 = cgroup_clone_children_read, + .write_u64 = cgroup_clone_children_write, + }, }; static struct cftype cft_release_agent = { @@ -3332,6 +3366,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (notify_on_release(parent)) set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags); + if (clone_children(parent)) + set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags); + for_each_subsys(root, ss) { struct cgroup_subsys_state *css = ss->create(ss, cgrp); @@ -3346,6 +3383,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, goto err_destroy; } /* At error, ->destroy() callback has to free assigned ID. */ + if (clone_children(parent) && ss->post_clone) + ss->post_clone(ss, cgrp); } cgroup_lock_hierarchy(root); -- cgit v1.2.2 From 32a8cf235e2f192eb002755076994525cdbaa35a Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Wed, 27 Oct 2010 15:33:37 -0700 Subject: cgroup: make the mount options parsing more accurate Current behavior: ================= (1) When we mount a cgroup, we can specify the 'all' option which means to enable all the cgroup subsystems. This is the default option when no option is specified. (2) If we want to mount a cgroup with a subset of the supported cgroup subsystems, we have to specify a subsystems name list for the mount option. (3) If we specify another option like 'noprefix' or 'release_agent', the actual code wants the 'all' or a subsystem name option specified also. Not critical but a bit not friendly as we should assume (1) in this case. (4) Logically, the 'all' option is mutually exclusive with a subsystem name, but this is not detected. In other words: succeed : mount -t cgroup -o all,freezer cgroup /cgroup => is it 'all' or 'freezer' ? fails : mount -t cgroup -o noprefix cgroup /cgroup => succeed if we do '-o noprefix,all' The following patches consolidate a bit the mount options check. New behavior: ============= (1) untouched (2) untouched (3) the 'all' option will be by default when specifying other than a subsystem name option (4) raises an error In other words: fails : mount -t cgroup -o all,freezer cgroup /cgroup succeed : mount -t cgroup -o noprefix cgroup /cgroup For the sake of lisibility, the if ... then ... else ... if ... indentation when parsing the options has been changed to: if ... then ... continue fi Signed-off-by: Daniel Lezcano Signed-off-by: Serge E. Hallyn Reviewed-by: Li Zefan Reviewed-by: Paul Menage Cc: Eric W. Biederman Cc: Jamal Hadi Salim Cc: Matt Helsley Cc: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 90 ++++++++++++++++++++++++++++++++++++++------------------- 1 file changed, 60 insertions(+), 30 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 4b218a46ddd3..3e6517e51fd3 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1074,7 +1074,8 @@ struct cgroup_sb_opts { */ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) { - char *token, *o = data ?: "all"; + char *token, *o = data; + bool all_ss = false, one_ss = false; unsigned long mask = (unsigned long)-1; int i; bool module_pin_failed = false; @@ -1090,24 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) while ((token = strsep(&o, ",")) != NULL) { if (!*token) return -EINVAL; - if (!strcmp(token, "all")) { - /* Add all non-disabled subsystems */ - opts->subsys_bits = 0; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - struct cgroup_subsys *ss = subsys[i]; - if (ss == NULL) - continue; - if (!ss->disabled) - opts->subsys_bits |= 1ul << i; - } - } else if (!strcmp(token, "none")) { + if (!strcmp(token, "none")) { /* Explicitly have no subsystems */ opts->none = true; - } else if (!strcmp(token, "noprefix")) { + continue; + } + if (!strcmp(token, "all")) { + /* Mutually exclusive option 'all' + subsystem name */ + if (one_ss) + return -EINVAL; + all_ss = true; + continue; + } + if (!strcmp(token, "noprefix")) { set_bit(ROOT_NOPREFIX, &opts->flags); - } else if (!strcmp(token, "clone_children")) { + continue; + } + if (!strcmp(token, "clone_children")) { opts->clone_children = true; - } else if (!strncmp(token, "release_agent=", 14)) { + continue; + } + if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) return -EINVAL; @@ -1115,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); if (!opts->release_agent) return -ENOMEM; - } else if (!strncmp(token, "name=", 5)) { + continue; + } + if (!strncmp(token, "name=", 5)) { const char *name = token + 5; /* Can't specify an empty name */ if (!strlen(name)) @@ -1137,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) GFP_KERNEL); if (!opts->name) return -ENOMEM; - } else { - struct cgroup_subsys *ss; - for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { - ss = subsys[i]; - if (ss == NULL) - continue; - if (!strcmp(token, ss->name)) { - if (!ss->disabled) - set_bit(i, &opts->subsys_bits); - break; - } - } - if (i == CGROUP_SUBSYS_COUNT) - return -ENOENT; + + continue; + } + + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; + if (strcmp(token, ss->name)) + continue; + if (ss->disabled) + continue; + + /* Mutually exclusive option 'all' + subsystem name */ + if (all_ss) + return -EINVAL; + set_bit(i, &opts->subsys_bits); + one_ss = true; + + break; + } + if (i == CGROUP_SUBSYS_COUNT) + return -ENOENT; + } + + /* + * If the 'all' option was specified select all the subsystems, + * otherwise 'all, 'none' and a subsystem name options were not + * specified, let's default to 'all' + */ + if (all_ss || (!all_ss && !one_ss && !opts->none)) { + for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) { + struct cgroup_subsys *ss = subsys[i]; + if (ss == NULL) + continue; + if (ss->disabled) + continue; + set_bit(i, &opts->subsys_bits); } } -- cgit v1.2.2 From f4a2589feaef0a9b737a3e582b37ee96695bb25f Mon Sep 17 00:00:00 2001 From: Evgeny Kuznetsov Date: Wed, 27 Oct 2010 15:33:37 -0700 Subject: cgroups: add check for strcpy destination string overflow Function "strcpy" is used without check for maximum allowed source string length and could cause destination string overflow. Check for string length is added before using "strcpy". Function now is return error if source string length is more than a maximum. akpm: presently considered NotABug, but add the check for general future-safeness and robustness. Signed-off-by: Evgeny Kuznetsov Acked-by: Paul Menage Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/cgroup.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 3e6517e51fd3..5cf366965d0c 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1922,6 +1922,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft, const char *buffer) { BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); + if (strlen(buffer) >= PATH_MAX) + return -EINVAL; if (!cgroup_lock_live_group(cgrp)) return -ENODEV; strcpy(cgrp->root->release_agent_path, buffer); -- 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/cgroup.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel/cgroup.c') diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 5cf366965d0c..66a416b42c18 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1460,9 +1460,9 @@ static int cgroup_get_rootdir(struct super_block *sb) return 0; } -static int cgroup_get_sb(struct file_system_type *fs_type, +static struct dentry *cgroup_mount(struct file_system_type *fs_type, int flags, const char *unused_dev_name, - void *data, struct vfsmount *mnt) + void *data) { struct cgroup_sb_opts opts; struct cgroupfs_root *root; @@ -1596,10 +1596,9 @@ static int cgroup_get_sb(struct file_system_type *fs_type, drop_parsed_module_refcounts(opts.subsys_bits); } - simple_set_mnt(mnt, sb); kfree(opts.release_agent); kfree(opts.name); - return 0; + return dget(sb->s_root); drop_new_super: deactivate_locked_super(sb); @@ -1608,7 +1607,7 @@ static int cgroup_get_sb(struct file_system_type *fs_type, out_err: kfree(opts.release_agent); kfree(opts.name); - return ret; + return ERR_PTR(ret); } static void cgroup_kill_sb(struct super_block *sb) { @@ -1658,7 +1657,7 @@ static void cgroup_kill_sb(struct super_block *sb) { static struct file_system_type cgroup_fs_type = { .name = "cgroup", - .get_sb = cgroup_get_sb, + .mount = cgroup_mount, .kill_sb = cgroup_kill_sb, }; -- cgit v1.2.2