From: Li Zefan This is one of the items in the plumber's wish list. For use cases: >> What would the use case be for this? > > Attaching meta information to services, in an easily discoverable > way. For example, in systemd we create one cgroup for each service, and > could then store data like the main pid of the specific service as an > xattr on the cgroup itself. That way we'd have almost all service state > in the cgroupfs, which would make it possible to terminate systemd and > later restart it without losing any state information. But there's more: > for example, some very peculiar services cannot be terminated on > shutdown (i.e. fakeraid DM stuff) and it would be really nice if the > services in question could just mark that on their cgroup, by setting an > xattr. On the more desktopy side of things there are other > possibilities: for example there are plans defining what an application > is along the lines of a cgroup (i.e. an app being a collection of > processes). With xattrs one could then attach an icon or human readable > program name on the cgroup. > > The key idea is that this would allow attaching runtime meta information > to cgroups and everything they model (services, apps, vms), that doesn't > need any complex userspace infrastructure, has good access control > (i.e. because the file system enforces that anyway, and there's the > "trusted." xattr namespace), notifications (inotify), and can easily be > shared among applications. > > Lennart v3: - instead of config option, use mount option to enable xattr support Signed-off-by: Li Zefan Signed-off-by: Aristeu Rozanski --- include/linux/cgroup.h | 13 ++++- kernel/cgroup.c | 118 ++++++++++++++++++++++++++++++++++++++++++------- 2 files changed, 112 insertions(+), 19 deletions(-) --- linus-2.6.orig/include/linux/cgroup.h 2012-07-02 10:21:58.055646941 -0400 +++ linus-2.6/include/linux/cgroup.h 2012-07-02 10:22:22.012584730 -0400 @@ -17,6 +17,7 @@ * Copyright (C) 2004-2006 Silicon Grap #include #include #include +#include #ifdef CONFIG_CGROUPS @@ -216,6 +217,9 @@ * count users of this cgroup. >0 means /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; + + /* directory xattrs */ + struct simple_xattrs xattrs; }; /* @@ -312,6 +316,9 @@ * If not 0, file mode is set to this v /* CFTYPE_* flags */ unsigned int flags; + /* file xattrs */ + struct simple_xattrs xattrs; + int (*open)(struct inode *inode, struct file *file); ssize_t (*read)(struct cgroup *cgrp, struct cftype *cft, struct file *file, @@ -397,7 +404,7 @@ * Returns 0 or -ve error code. */ struct cftype_set { struct list_head node; /* chained at subsys->cftsets */ - const struct cftype *cfts; + struct cftype *cfts; }; struct cgroup_scanner { @@ -409,8 +416,8 @@ struct cgroup_scanner { void *data; }; -int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts); -int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts); +int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); +int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts); int cgroup_is_removed(const struct cgroup *cgrp); --- linus-2.6.orig/kernel/cgroup.c 2012-07-02 10:21:58.059646980 -0400 +++ linus-2.6/kernel/cgroup.c 2012-07-02 10:22:22.017584857 -0400 @@ -276,7 +276,8 @@ inline int cgroup_is_removed(const struc /* bits in struct cgroupfs_root flags field */ enum { - ROOT_NOPREFIX, /* mounted subsystems have no named prefix */ + ROOT_NOPREFIX, /* mounted subsystems have no named prefix */ + ROOT_XATTR, /* supports extended attributes */ }; static int cgroup_is_releasable(const struct cgroup *cgrp) @@ -916,15 +917,19 @@ static void cgroup_diput(struct dentry * */ BUG_ON(!list_empty(&cgrp->pidlists)); + simple_xattrs_free(&cgrp->xattrs); + kfree_rcu(cgrp, rcu_head); } else { struct cfent *cfe = __d_cfe(dentry); struct cgroup *cgrp = dentry->d_parent->d_fsdata; + struct cftype *cft = cfe->type; WARN_ONCE(!list_empty(&cfe->node) && cgrp != &cgrp->root->top_cgroup, "cfe still linked for %s\n", cfe->type->name); kfree(cfe); + simple_xattrs_free(&cft->xattrs); } iput(inode); } @@ -1149,6 +1154,8 @@ static int cgroup_show_options(struct se seq_printf(seq, ",%s", ss->name); if (test_bit(ROOT_NOPREFIX, &root->flags)) seq_puts(seq, ",noprefix"); + if (test_bit(ROOT_XATTR, &root->flags)) + seq_puts(seq, ",xattr"); if (strlen(root->release_agent_path)) seq_printf(seq, ",release_agent=%s", root->release_agent_path); if (clone_children(&root->top_cgroup)) @@ -1217,6 +1224,10 @@ memset(opts, 0, sizeof(*opts)); opts->clone_children = true; continue; } + if (!strcmp(token, "xattr")) { + set_bit(ROOT_XATTR, &opts->flags); + continue; + } if (!strncmp(token, "release_agent=", 14)) { /* Specifying two release agents is forbidden */ if (opts->release_agent) @@ -1434,6 +1445,7 @@ static void init_cgroup_housekeeping(str mutex_init(&cgrp->pidlist_mutex); INIT_LIST_HEAD(&cgrp->event_list); spin_lock_init(&cgrp->event_list_lock); + simple_xattrs_init(&cgrp->xattrs); } static void init_cgroup_root(struct cgroupfs_root *root) @@ -1779,6 +1791,8 @@ ret = rebind_subsystems(root, 0); mutex_unlock(&cgroup_root_mutex); mutex_unlock(&cgroup_mutex); + simple_xattrs_free(&cgrp->xattrs); + kill_litter_super(sb); cgroup_drop_root(root); } @@ -2585,19 +2599,89 @@ static int cgroup_rename(struct inode *o return simple_rename(old_dir, old_dentry, new_dir, new_dentry); } +static struct simple_xattrs *__d_xattrs(struct dentry *dentry) +{ + if (S_ISDIR(dentry->d_inode->i_mode)) + return &__d_cgrp(dentry)->xattrs; + else + return &__d_cft(dentry)->xattrs; +} + +static inline int xattr_enabled(struct dentry *dentry) +{ + struct cgroupfs_root *root = dentry->d_sb->s_fs_info; + return test_bit(ROOT_XATTR, &root->flags); +} + +static bool is_valid_xattr(const char *name) +{ + if (!strncmp(name, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN) || + !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) || + !strncmp(name, XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN)) + return true; + return false; +} + +static int cgroup_setxattr(struct dentry *dentry, const char *name, + const void *val, size_t size, int flags) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_set(__d_xattrs(dentry), name, val, size, flags); +} + +static int cgroup_removexattr(struct dentry *dentry, const char *name) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_remove(__d_xattrs(dentry), name); +} + +static ssize_t cgroup_getxattr(struct dentry *dentry, const char *name, + void *buf, size_t size) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + if (!is_valid_xattr(name)) + return -EINVAL; + return simple_xattr_get(__d_xattrs(dentry), name, buf, size); +} + +static ssize_t cgroup_listxattr(struct dentry *dentry, char *buf, size_t size) +{ + if (!xattr_enabled(dentry)) + return -EOPNOTSUPP; + return simple_xattr_list(__d_xattrs(dentry), buf, size); +} + static const struct file_operations cgroup_file_operations = { - .read = cgroup_file_read, - .write = cgroup_file_write, - .llseek = generic_file_llseek, - .open = cgroup_file_open, - .release = cgroup_file_release, + .read = cgroup_file_read, + .write = cgroup_file_write, + .llseek = generic_file_llseek, + .open = cgroup_file_open, + .release = cgroup_file_release, +}; + +static const struct inode_operations cgroup_file_inode_operations = { + .setxattr = cgroup_setxattr, + .getxattr = cgroup_getxattr, + .listxattr = cgroup_listxattr, + .removexattr = cgroup_removexattr, }; static const struct inode_operations cgroup_dir_inode_operations = { - .lookup = cgroup_lookup, - .mkdir = cgroup_mkdir, - .rmdir = cgroup_rmdir, - .rename = cgroup_rename, + .lookup = cgroup_lookup, + .mkdir = cgroup_mkdir, + .rmdir = cgroup_rmdir, + .rename = cgroup_rename, + .setxattr = cgroup_setxattr, + .getxattr = cgroup_getxattr, + .listxattr = cgroup_listxattr, + .removexattr = cgroup_removexattr, }; static struct dentry *cgroup_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) @@ -2645,6 +2729,7 @@ static int cgroup_create_file(struct den } else if (S_ISREG(mode)) { inode->i_size = 0; inode->i_fop = &cgroup_file_operations; + inode->i_op = &cgroup_file_inode_operations; } d_instantiate(dentry, inode); dget(dentry); /* Extra count - pin the dentry in core */ @@ -2705,7 +2790,7 @@ umode_t mode = 0; } static int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys, - const struct cftype *cft) + struct cftype *cft) { struct dentry *dir = cgrp->dentry; struct cgroup *parent = __d_cgrp(dir); @@ -2716,6 +2801,7 @@ static int cgroup_add_file(struct cgroup char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 }; cft->subsys = subsys; + simple_xattrs_init(&cft->xattrs); /* does @cft->flags tell us to skip creation on @cgrp? */ if ((cft->flags & CFTYPE_NOT_ON_ROOT) && !cgrp->parent) @@ -2757,9 +2843,9 @@ out: } static int cgroup_addrm_files(struct cgroup *cgrp, struct cgroup_subsys *subsys, - const struct cftype cfts[], bool is_add) + struct cftype cfts[], bool is_add) { - const struct cftype *cft; + struct cftype *cft; int err, ret = 0; for (cft = cfts; cft->name[0] != '\0'; cft++) { @@ -2793,7 +2879,7 @@ static void cgroup_cfts_prepare(void) } static void cgroup_cfts_commit(struct cgroup_subsys *ss, - const struct cftype *cfts, bool is_add) + struct cftype *cfts, bool is_add) __releases(&cgroup_mutex) __releases(&cgroup_cft_mutex) { LIST_HEAD(pending); @@ -2844,7 +2930,7 @@ * Returns 0 on successful registration, * function currently returns 0 as long as @cfts registration is successful * even if some file creation attempts on existing cgroups fail. */ -int cgroup_add_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype_set *set; @@ -2874,7 +2960,7 @@ EXPORT_SYMBOL_GPL(cgroup_add_cftypes); * Returns 0 on successful unregistration, -ENOENT if @cfts is not * registered with @ss. */ -int cgroup_rm_cftypes(struct cgroup_subsys *ss, const struct cftype *cfts) +int cgroup_rm_cftypes(struct cgroup_subsys *ss, struct cftype *cfts) { struct cftype_set *set; -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/