diff options
author | 2019-03-12 14:08:19 -0700 | |
---|---|---|
committer | 2019-03-12 14:08:19 -0700 | |
commit | 7b47a9e7c8f672b6fb0b77fca11a63a8a77f5a91 (patch) | |
tree | cf05645120ba2323c36acefdea6e62addf320f8c /kernel | |
parent | Merge branch 'work.iov_iter' of git://git.kernel.org/pub/scm/linux/kernel/git... (diff) | |
parent | afs: Use fs_context to pass parameters over automount (diff) | |
download | linux-7b47a9e7c8f672b6fb0b77fca11a63a8a77f5a91.tar.gz linux-7b47a9e7c8f672b6fb0b77fca11a63a8a77f5a91.tar.bz2 linux-7b47a9e7c8f672b6fb0b77fca11a63a8a77f5a91.zip |
Merge branch 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull vfs mount infrastructure updates from Al Viro:
"The rest of core infrastructure; no new syscalls in that pile, but the
old parts are switched to new infrastructure. At that point
conversions of individual filesystems can happen independently; some
are done here (afs, cgroup, procfs, etc.), there's also a large series
outside of that pile dealing with NFS (quite a bit of option-parsing
stuff is getting used there - it's one of the most convoluted
filesystems in terms of mount-related logics), but NFS bits are the
next cycle fodder.
It got seriously simplified since the last cycle; documentation is
probably the weakest bit at the moment - I considered dropping the
commit introducing Documentation/filesystems/mount_api.txt (cutting
the size increase by quarter ;-), but decided that it would be better
to fix it up after -rc1 instead.
That pile allows to do followup work in independent branches, which
should make life much easier for the next cycle. fs/super.c size
increase is unpleasant; there's a followup series that allows to
shrink it considerably, but I decided to leave that until the next
cycle"
* 'work.mount' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (41 commits)
afs: Use fs_context to pass parameters over automount
afs: Add fs_context support
vfs: Add some logging to the core users of the fs_context log
vfs: Implement logging through fs_context
vfs: Provide documentation for new mount API
vfs: Remove kern_mount_data()
hugetlbfs: Convert to fs_context
cpuset: Use fs_context
kernfs, sysfs, cgroup, intel_rdt: Support fs_context
cgroup: store a reference to cgroup_ns into cgroup_fs_context
cgroup1_get_tree(): separate "get cgroup_root to use" into a separate helper
cgroup_do_mount(): massage calling conventions
cgroup: stash cgroup_root reference into cgroup_fs_context
cgroup2: switch to option-by-option parsing
cgroup1: switch to option-by-option parsing
cgroup: take options parsing into ->parse_monolithic()
cgroup: fold cgroup1_mount() into cgroup1_get_tree()
cgroup: start switching to fs_context
ipc: Convert mqueue fs to fs_context
proc: Add fs_context support to procfs
...
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/cgroup/cgroup-internal.h | 49 | ||||
-rw-r--r-- | kernel/cgroup/cgroup-v1.c | 394 | ||||
-rw-r--r-- | kernel/cgroup/cgroup.c | 223 | ||||
-rw-r--r-- | kernel/cgroup/cpuset.c | 56 |
4 files changed, 416 insertions, 306 deletions
diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index c9a35f09e4b9..30e39f3932ad 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -7,6 +7,7 @@ #include <linux/workqueue.h> #include <linux/list.h> #include <linux/refcount.h> +#include <linux/fs_context.h> #define TRACE_CGROUP_PATH_LEN 1024 extern spinlock_t trace_cgroup_path_lock; @@ -37,6 +38,31 @@ extern void __init enable_debug_cgroup(void); } while (0) /* + * The cgroup filesystem superblock creation/mount context. + */ +struct cgroup_fs_context { + struct kernfs_fs_context kfc; + struct cgroup_root *root; + struct cgroup_namespace *ns; + unsigned int flags; /* CGRP_ROOT_* flags */ + + /* cgroup1 bits */ + bool cpuset_clone_children; + bool none; /* User explicitly requested empty subsystem */ + bool all_ss; /* Seen 'all' option */ + u16 subsys_mask; /* Selected subsystems */ + char *name; /* Hierarchy name */ + char *release_agent; /* Path for release notifications */ +}; + +static inline struct cgroup_fs_context *cgroup_fc2context(struct fs_context *fc) +{ + struct kernfs_fs_context *kfc = fc->fs_private; + + return container_of(kfc, struct cgroup_fs_context, kfc); +} + +/* * A cgroup can be associated with multiple css_sets as different tasks may * belong to different cgroups on different hierarchies. In the other * direction, a css_set is naturally associated with multiple cgroups. @@ -117,16 +143,6 @@ struct cgroup_mgctx { #define DEFINE_CGROUP_MGCTX(name) \ struct cgroup_mgctx name = CGROUP_MGCTX_INIT(name) -struct cgroup_sb_opts { - u16 subsys_mask; - unsigned int flags; - char *release_agent; - bool cpuset_clone_children; - char *name; - /* User explicitly requested empty subsystem */ - bool none; -}; - extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; @@ -197,12 +213,10 @@ int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns); void cgroup_free_root(struct cgroup_root *root); -void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts); +void init_cgroup_root(struct cgroup_fs_context *ctx); int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask); int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask); -struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags, - struct cgroup_root *root, unsigned long magic, - struct cgroup_namespace *ns); +int cgroup_do_get_tree(struct fs_context *fc); int cgroup_migrate_vet_dst(struct cgroup *dst_cgrp); void cgroup_migrate_finish(struct cgroup_mgctx *mgctx); @@ -246,14 +260,15 @@ extern const struct proc_ns_operations cgroupns_operations; */ extern struct cftype cgroup1_base_files[]; extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops; +extern const struct fs_parameter_description cgroup1_fs_parameters; int proc_cgroupstats_show(struct seq_file *m, void *v); bool cgroup1_ssid_disabled(int ssid); void cgroup1_pidlist_destroy_all(struct cgroup *cgrp); void cgroup1_release_agent(struct work_struct *work); void cgroup1_check_for_release(struct cgroup *cgrp); -struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, - void *data, unsigned long magic, - struct cgroup_namespace *ns); +int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param); +int cgroup1_get_tree(struct fs_context *fc); +int cgroup1_reconfigure(struct fs_context *ctx); #endif /* __CGROUP_INTERNAL_H */ diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index f94a7229974e..c126b34fd4ff 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -13,9 +13,12 @@ #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> +#include <linux/fs_parser.h> #include <trace/events/cgroup.h> +#define cg_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) + /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls @@ -906,172 +909,195 @@ static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_roo return 0; } -static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) -{ - char *token, *o = data; - bool all_ss = false, one_ss = false; - u16 mask = U16_MAX; - struct cgroup_subsys *ss; - int nr_opts = 0; - int i; - -#ifdef CONFIG_CPUSETS - mask = ~((u16)1 << cpuset_cgrp_id); -#endif - - memset(opts, 0, sizeof(*opts)); +enum cgroup1_param { + Opt_all, + Opt_clone_children, + Opt_cpuset_v2_mode, + Opt_name, + Opt_none, + Opt_noprefix, + Opt_release_agent, + Opt_xattr, +}; - while ((token = strsep(&o, ",")) != NULL) { - nr_opts++; +static const struct fs_parameter_spec cgroup1_param_specs[] = { + fsparam_flag ("all", Opt_all), + fsparam_flag ("clone_children", Opt_clone_children), + fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), + fsparam_string("name", Opt_name), + fsparam_flag ("none", Opt_none), + fsparam_flag ("noprefix", Opt_noprefix), + fsparam_string("release_agent", Opt_release_agent), + fsparam_flag ("xattr", Opt_xattr), + {} +}; - if (!*token) - return -EINVAL; - if (!strcmp(token, "none")) { - /* Explicitly have no subsystems */ - opts->none = true; - continue; - } - if (!strcmp(token, "all")) { - /* Mutually exclusive option 'all' + subsystem name */ - if (one_ss) - return -EINVAL; - all_ss = true; - continue; - } - if (!strcmp(token, "noprefix")) { - opts->flags |= CGRP_ROOT_NOPREFIX; - continue; - } - if (!strcmp(token, "clone_children")) { - 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; - } - if (!strncmp(token, "release_agent=", 14)) { - /* Specifying two release agents is forbidden */ - if (opts->release_agent) - return -EINVAL; - opts->release_agent = - kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); - if (!opts->release_agent) - return -ENOMEM; - continue; - } - if (!strncmp(token, "name=", 5)) { - const char *name = token + 5; - - /* blocked by boot param? */ - if (cgroup_no_v1_named) - return -ENOENT; - /* Can't specify an empty name */ - if (!strlen(name)) - return -EINVAL; - /* Must match [\w.-]+ */ - for (i = 0; i < strlen(name); i++) { - char c = name[i]; - if (isalnum(c)) - continue; - if ((c == '.') || (c == '-') || (c == '_')) - continue; - return -EINVAL; - } - /* Specifying two names is forbidden */ - if (opts->name) - return -EINVAL; - opts->name = kstrndup(name, - MAX_CGROUP_ROOT_NAMELEN - 1, - GFP_KERNEL); - if (!opts->name) - return -ENOMEM; +const struct fs_parameter_description cgroup1_fs_parameters = { + .name = "cgroup1", + .specs = cgroup1_param_specs, +}; - continue; +int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct cgroup_subsys *ss; + struct fs_parse_result result; + int opt, i; + + opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result); + if (opt == -ENOPARAM) { + if (strcmp(param->key, "source") == 0) { + fc->source = param->string; + param->string = NULL; + return 0; } - for_each_subsys(ss, i) { - if (strcmp(token, ss->legacy_name)) + if (strcmp(param->key, ss->legacy_name)) continue; - if (!cgroup_ssid_enabled(i)) + ctx->subsys_mask |= (1 << i); + return 0; + } + return cg_invalf(fc, "cgroup1: Unknown subsys name '%s'", param->key); + } + if (opt < 0) + return opt; + + switch (opt) { + case Opt_none: + /* Explicitly have no subsystems */ + ctx->none = true; + break; + case Opt_all: + ctx->all_ss = true; + break; + case Opt_noprefix: + ctx->flags |= CGRP_ROOT_NOPREFIX; + break; + case Opt_clone_children: + ctx->cpuset_clone_children = true; + break; + case Opt_cpuset_v2_mode: + ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; + break; + case Opt_xattr: + ctx->flags |= CGRP_ROOT_XATTR; + break; + case Opt_release_agent: + /* Specifying two release agents is forbidden */ + if (ctx->release_agent) + return cg_invalf(fc, "cgroup1: release_agent respecified"); + ctx->release_agent = param->string; + param->string = NULL; + break; + case Opt_name: + /* blocked by boot param? */ + if (cgroup_no_v1_named) + return -ENOENT; + /* Can't specify an empty name */ + if (!param->size) + return cg_invalf(fc, "cgroup1: Empty name"); + if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) + return cg_invalf(fc, "cgroup1: Name too long"); + /* Must match [\w.-]+ */ + for (i = 0; i < param->size; i++) { + char c = param->string[i]; + if (isalnum(c)) continue; - if (cgroup1_ssid_disabled(i)) + if ((c == '.') || (c == '-') || (c == '_')) continue; - - /* Mutually exclusive option 'all' + subsystem name */ - if (all_ss) - return -EINVAL; - opts->subsys_mask |= (1 << i); - one_ss = true; - - break; + return cg_invalf(fc, "cgroup1: Invalid name"); } - if (i == CGROUP_SUBSYS_COUNT) - return -ENOENT; + /* Specifying two names is forbidden */ + if (ctx->name) + return cg_invalf(fc, "cgroup1: name respecified"); + ctx->name = param->string; + param->string = NULL; + break; } + return 0; +} + +static int check_cgroupfs_options(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + u16 mask = U16_MAX; + u16 enabled = 0; + struct cgroup_subsys *ss; + int i; + +#ifdef CONFIG_CPUSETS + mask = ~((u16)1 << cpuset_cgrp_id); +#endif + for_each_subsys(ss, i) + if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) + enabled |= 1 << i; + + ctx->subsys_mask &= enabled; /* - * If the 'all' option was specified select all the subsystems, - * otherwise if 'none', 'name=' and a subsystem name options were - * not specified, let's default to 'all' + * In absense of 'none', 'name=' or subsystem name options, + * let's default to 'all'. */ - if (all_ss || (!one_ss && !opts->none && !opts->name)) - for_each_subsys(ss, i) - if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) - opts->subsys_mask |= (1 << i); + if (!ctx->subsys_mask && !ctx->none && !ctx->name) + ctx->all_ss = true; + + if (ctx->all_ss) { + /* Mutually exclusive option 'all' + subsystem name */ + if (ctx->subsys_mask) + return cg_invalf(fc, "cgroup1: subsys name conflicts with all"); + /* 'all' => select all the subsystems */ + ctx->subsys_mask = enabled; + } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ - if (!opts->subsys_mask && !opts->name) - return -EINVAL; + if (!ctx->subsys_mask && !ctx->name) + return cg_invalf(fc, "cgroup1: Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ - if ((opts->flags & CGRP_ROOT_NOPREFIX) && (opts->subsys_mask & mask)) - return -EINVAL; + if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) + return cg_invalf(fc, "cgroup1: noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ - if (opts->subsys_mask && opts->none) - return -EINVAL; + if (ctx->subsys_mask && ctx->none) + return cg_invalf(fc, "cgroup1: none used incorrectly"); return 0; } -static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) +int cgroup1_reconfigure(struct fs_context *fc) { - int ret = 0; + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); - struct cgroup_sb_opts opts; + int ret = 0; u16 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ - ret = parse_cgroupfs_options(data, &opts); + ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; - if (opts.subsys_mask != root->subsys_mask || opts.release_agent) + if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); - added_mask = opts.subsys_mask & ~root->subsys_mask; - removed_mask = root->subsys_mask & ~opts.subsys_mask; + added_mask = ctx->subsys_mask & ~root->subsys_mask; + removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ - if ((opts.flags ^ root->flags) || - (opts.name && strcmp(opts.name, root->name))) { - pr_err("option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"\n", - opts.flags, opts.name ?: "", root->flags, root->name); + if ((ctx->flags ^ root->flags) || + (ctx->name && strcmp(ctx->name, root->name))) { + cg_invalf(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", + ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } @@ -1088,17 +1114,15 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); - if (opts.release_agent) { + if (ctx->release_agent) { spin_lock(&release_agent_path_lock); - strcpy(root->release_agent_path, opts.release_agent); + strcpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: - kfree(opts.release_agent); - kfree(opts.name); mutex_unlock(&cgroup_mutex); return ret; } @@ -1106,28 +1130,30 @@ static int cgroup1_remount(struct kernfs_root *kf_root, int *flags, char *data) struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, - .remount_fs = cgroup1_remount, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; -struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, - void *data, unsigned long magic, - struct cgroup_namespace *ns) +/* + * The guts of cgroup1 mount - find or create cgroup_root to use. + * Called with cgroup_mutex held; returns 0 on success, -E... on + * error and positive - in case when the candidate is busy dying. + * On success it stashes a reference to cgroup_root into given + * cgroup_fs_context; that reference is *NOT* counting towards the + * cgroup_root refcount. + */ +static int cgroup1_root_to_use(struct fs_context *fc) { - struct cgroup_sb_opts opts; + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; - struct dentry *dentry; int i, ret; - cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); - /* First find the desired set of subsystems */ - ret = parse_cgroupfs_options(data, &opts); + ret = check_cgroupfs_options(fc); if (ret) - goto out_unlock; + return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may @@ -1137,16 +1163,12 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { - if (!(opts.subsys_mask & (1 << i)) || + if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; - if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) { - mutex_unlock(&cgroup_mutex); - msleep(10); - ret = restart_syscall(); - goto out_free; - } + if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) + return 1; /* restart */ cgroup_put(&ss->root->cgrp); } @@ -1161,8 +1183,8 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ - if (opts.name) { - if (strcmp(opts.name, root->name)) + if (ctx->name) { + if (strcmp(ctx->name, root->name)) continue; name_match = true; } @@ -1171,19 +1193,18 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ - if ((opts.subsys_mask || opts.none) && - (opts.subsys_mask != root->subsys_mask)) { + if ((ctx->subsys_mask || ctx->none) && + (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; - ret = -EBUSY; - goto out_unlock; + return -EBUSY; } - if (root->flags ^ opts.flags) + if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); - ret = 0; - goto out_unlock; + ctx->root = root; + return 0; } /* @@ -1191,55 +1212,58 @@ struct dentry *cgroup1_mount(struct file_system_type *fs_type, int flags, * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ - if (!opts.subsys_mask && !opts.none) { - ret = -EINVAL; - goto out_unlock; - } + if (!ctx->subsys_mask && !ctx->none) + return cg_invalf(fc, "cgroup1: No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ - if (ns != &init_cgroup_ns) { - ret = -EPERM; - goto out_unlock; - } + if (ctx->ns != &init_cgroup_ns) + return -EPERM; root = kzalloc(sizeof(*root), GFP_KERNEL); - if (!root) { - ret = -ENOMEM; - goto out_unlock; - } + if (!root) + return -ENOMEM; - init_cgroup_root(root, &opts); + ctx->root = root; + init_cgroup_root(ctx); - ret = cgroup_setup_root(root, opts.subsys_mask); + ret = cgroup_setup_root(root, ctx->subsys_mask); if (ret) cgroup_free_root(root); + return ret; +} -out_unlock: - if (!ret && !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) { - mutex_unlock(&cgroup_mutex); - msleep(10); - ret = restart_syscall(); - goto out_free; - } - mutex_unlock(&cgroup_mutex); -out_free: - kfree(opts.release_agent); - kfree(opts.name); +int cgroup1_get_tree(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + int ret; - if (ret) - return ERR_PTR(ret); + /* Check if the caller has permission to mount. */ + if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) + return -EPERM; + + cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); + + ret = cgroup1_root_to_use(fc); + if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) + ret = 1; /* restart */ - dentry = cgroup_do_mount(&cgroup_fs_type, flags, root, - CGROUP_SUPER_MAGIC, ns); + mutex_unlock(&cgroup_mutex); - if (!IS_ERR(dentry) && percpu_ref_is_dying(&root->cgrp.self.refcnt)) { - struct super_block *sb = dentry->d_sb; - dput(dentry); + if (!ret) + ret = cgroup_do_get_tree(fc); + + if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { + struct super_block *sb = fc->root->d_sb; + dput(fc->root); deactivate_locked_super(sb); + ret = 1; + } + + if (unlikely(ret > 0)) { msleep(10); - dentry = ERR_PTR(restart_syscall()); + return restart_syscall(); } - return dentry; + return ret; } static int __init cgroup1_wq_init(void) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index eef24a25bda7..3f2b4bde0f9c 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -54,6 +54,7 @@ #include <linux/proc_ns.h> #include <linux/nsproxy.h> #include <linux/file.h> +#include <linux/fs_parser.h> #include <linux/sched/cputime.h> #include <linux/psi.h> #include <net/sock.h> @@ -1772,26 +1773,37 @@ int cgroup_show_path(struct seq_file *sf, struct kernfs_node *kf_node, return len; } -static int parse_cgroup_root_flags(char *data, unsigned int *root_flags) -{ - char *token; +enum cgroup2_param { + Opt_nsdelegate, + nr__cgroup2_params +}; - *root_flags = 0; +static const struct fs_parameter_spec cgroup2_param_specs[] = { + fsparam_flag ("nsdelegate", Opt_nsdelegate), + {} +}; - if (!data || *data == '\0') - return 0; +static const struct fs_parameter_description cgroup2_fs_parameters = { + .name = "cgroup2", + .specs = cgroup2_param_specs, +}; - while ((token = strsep(&data, ",")) != NULL) { - if (!strcmp(token, "nsdelegate")) { - *root_flags |= CGRP_ROOT_NS_DELEGATE; - continue; - } +static int cgroup2_parse_param(struct fs_context *fc, struct fs_parameter *param) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + struct fs_parse_result result; + int opt; - pr_err("cgroup2: unknown option \"%s\"\n", token); - return -EINVAL; - } + opt = fs_parse(fc, &cgroup2_fs_parameters, param, &result); + if (opt < 0) + return opt; - return 0; + switch (opt) { + case Opt_nsdelegate: + ctx->flags |= CGRP_ROOT_NS_DELEGATE; + return 0; + } + return -EINVAL; } static void apply_cgroup_root_flags(unsigned int root_flags) @@ -1811,16 +1823,11 @@ static int cgroup_show_options(struct seq_file *seq, struct kernfs_root *kf_root return 0; } -static int cgroup_remount(struct kernfs_root *kf_root, int *flags, char *data) +static int cgroup_reconfigure(struct fs_context *fc) { - unsigned int root_flags; - int ret; - - ret = parse_cgroup_root_flags(data, &root_flags); - if (ret) - return ret; + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); - apply_cgroup_root_flags(root_flags); + apply_cgroup_root_flags(ctx->flags); return 0; } @@ -1908,8 +1915,9 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp) INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent); } -void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts) +void init_cgroup_root(struct cgroup_fs_context *ctx) { + struct cgroup_root *root = ctx->root; struct cgroup *cgrp = &root->cgrp; INIT_LIST_HEAD(&root->root_list); @@ -1918,12 +1926,12 @@ void init_cgroup_root(struct cgroup_root *root, struct cgroup_sb_opts *opts) init_cgroup_housekeeping(cgrp); idr_init(&root->cgroup_idr); - root->flags = opts->flags; - if (opts->release_agent) - strscpy(root->release_agent_path, opts->release_agent, PATH_MAX); - if (opts->name) - strscpy(root->name, opts->name, MAX_CGROUP_ROOT_NAMELEN); - if (opts->cpuset_clone_children) + root->flags = ctx->flags; + if (ctx->release_agent) + strscpy(root->release_agent_path, ctx->release_agent, PATH_MAX); + if (ctx->name) + strscpy(root->name, ctx->name, MAX_CGROUP_ROOT_NAMELEN); + if (ctx->cpuset_clone_children) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags); } @@ -2028,60 +2036,104 @@ out: return ret; } -struct dentry *cgroup_do_mount(struct file_system_type *fs_type, int flags, - struct cgroup_root *root, unsigned long magic, - struct cgroup_namespace *ns) +int cgroup_do_get_tree(struct fs_context *fc) { - struct dentry *dentry; - bool new_sb = false; + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + int ret; - dentry = kernfs_mount(fs_type, flags, root->kf_root, magic, &new_sb); + ctx->kfc.root = ctx->root->kf_root; + if (fc->fs_type == &cgroup2_fs_type) + ctx->kfc.magic = CGROUP2_SUPER_MAGIC; + else + ctx->kfc.magic = CGROUP_SUPER_MAGIC; + ret = kernfs_get_tree(fc); /* * In non-init cgroup namespace, instead of root cgroup's dentry, * we return the dentry corresponding to the cgroupns->root_cgrp. */ - if (!IS_ERR(dentry) && ns != &init_cgroup_ns) { + if (!ret && ctx->ns != &init_cgroup_ns) { struct dentry *nsdentry; - struct super_block *sb = dentry->d_sb; + struct super_block *sb = fc->root->d_sb; struct cgroup *cgrp; mutex_lock(&cgroup_mutex); spin_lock_irq(&css_set_lock); - cgrp = cset_cgroup_from_root(ns->root_cset, root); + cgrp = cset_cgroup_from_root(ctx->ns->root_cset, ctx->root); spin_unlock_irq(&css_set_lock); mutex_unlock(&cgroup_mutex); nsdentry = kernfs_node_dentry(cgrp->kn, sb); - dput(dentry); - if (IS_ERR(nsdentry)) + dput(fc->root); + fc->root = nsdentry; + if (IS_ERR(nsdentry)) { + ret = PTR_ERR(nsdentry); deactivate_locked_super(sb); - dentry = nsdentry; + } } - if (!new_sb) - cgroup_put(&root->cgrp); + if (!ctx->kfc.new_sb_created) + cgroup_put(&ctx->root->cgrp); - return dentry; + return ret; } -static struct dentry *cgroup_mount(struct file_system_type *fs_type, - int flags, const char *unused_dev_name, - void *data) +/* + * Destroy a cgroup filesystem context. + */ +static void cgroup_fs_context_free(struct fs_context *fc) { - struct cgroup_namespace *ns = current->nsproxy->cgroup_ns; - struct dentry *dentry; + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); + + kfree(ctx->name); + kfree(ctx->release_agent); + put_cgroup_ns(ctx->ns); + kernfs_free_fs_context(fc); + kfree(ctx); +} + +static int cgroup_get_tree(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; - get_cgroup_ns(ns); + cgrp_dfl_visible = true; + cgroup_get_live(&cgrp_dfl_root.cgrp); + ctx->root = &cgrp_dfl_root; - /* Check if the caller has permission to mount. */ - if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN)) { - put_cgroup_ns(ns); - return ERR_PTR(-EPERM); - } + ret = cgroup_do_get_tree(fc); + if (!ret) + apply_cgroup_root_flags(ctx->flags); + return ret; +} + +static const struct fs_context_operations cgroup_fs_context_ops = { + .free = cgroup_fs_context_free, + .parse_param = cgroup2_parse_param, + .get_tree = cgroup_get_tree, + .reconfigure = cgroup_reconfigure, +}; + +static const struct fs_context_operations cgroup1_fs_context_ops = { + .free = cgroup_fs_context_free, + .parse_param = cgroup1_parse_param, + .get_tree = cgroup1_get_tree, + .reconfigure = cgroup1_reconfigure, +}; + +/* + * Initialise the cgroup filesystem creation/reconfiguration context. Notably, + * we select the namespace we're going to use. + */ +static int cgroup_init_fs_context(struct fs_context *fc) +{ + struct cgroup_fs_context *ctx; + + ctx = kzalloc(sizeof(struct cgroup_fs_context), GFP_KERNEL); + if (!ctx) + return -ENOMEM; /* * The first time anyone tries to mount a cgroup, enable the list @@ -2090,29 +2142,18 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, if (!use_task_css_set_links) cgroup_enable_task_cg_lists(); - if (fs_type == &cgroup2_fs_type) { - unsigned int root_flags; - - ret = parse_cgroup_root_flags(data, &root_flags); - if (ret) { - put_cgroup_ns(ns); - return ERR_PTR(ret); - } - - cgrp_dfl_visible = true; - cgroup_get_live(&cgrp_dfl_root.cgrp); - - dentry = cgroup_do_mount(&cgroup2_fs_type, flags, &cgrp_dfl_root, - CGROUP2_SUPER_MAGIC, ns); - if (!IS_ERR(dentry)) - apply_cgroup_root_flags(root_flags); - } else { - dentry = cgroup1_mount(&cgroup_fs_type, flags, data, - CGROUP_SUPER_MAGIC, ns); - } - - put_cgroup_ns(ns); - return dentry; + ctx->ns = current->nsproxy->cgroup_ns; + get_cgroup_ns(ctx->ns); + fc->fs_private = &ctx->kfc; + if (fc->fs_type == &cgroup2_fs_type) + fc->ops = &cgroup_fs_context_ops; + else + fc->ops = &cgroup1_fs_context_ops; + if (fc->user_ns) + put_user_ns(fc->user_ns); + fc->user_ns = get_user_ns(ctx->ns->user_ns); + fc->global = true; + return 0; } static void cgroup_kill_sb(struct super_block *sb) @@ -2135,17 +2176,19 @@ static void cgroup_kill_sb(struct super_block *sb) } struct file_system_type cgroup_fs_type = { - .name = "cgroup", - .mount = cgroup_mount, - .kill_sb = cgroup_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .name = "cgroup", + .init_fs_context = cgroup_init_fs_context, + .parameters = &cgroup1_fs_parameters, + .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; static struct file_system_type cgroup2_fs_type = { - .name = "cgroup2", - .mount = cgroup_mount, - .kill_sb = cgroup_kill_sb, - .fs_flags = FS_USERNS_MOUNT, + .name = "cgroup2", + .init_fs_context = cgroup_init_fs_context, + .parameters = &cgroup2_fs_parameters, + .kill_sb = cgroup_kill_sb, + .fs_flags = FS_USERNS_MOUNT, }; int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, @@ -5280,7 +5323,6 @@ int cgroup_rmdir(struct kernfs_node *kn) static struct kernfs_syscall_ops cgroup_kf_syscall_ops = { .show_options = cgroup_show_options, - .remount_fs = cgroup_remount, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, @@ -5347,11 +5389,12 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss, bool early) */ int __init cgroup_init_early(void) { - static struct cgroup_sb_opts __initdata opts; + static struct cgroup_fs_context __initdata ctx; struct cgroup_subsys *ss; int i; - init_cgroup_root(&cgrp_dfl_root, &opts); + ctx.root = &cgrp_dfl_root; + init_cgroup_root(&ctx); cgrp_dfl_root.cgrp.self.flags |= CSS_NO_REF; RCU_INIT_POINTER(init_task.cgroups, &init_css_set); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 72afd55f70c6..4834c4214e9c 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -39,6 +39,7 @@ #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> +#include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> @@ -359,25 +360,52 @@ static inline bool is_in_v2_mode(void) * users. If someone tries to mount the "cpuset" filesystem, we * silently switch it to mount "cgroup" instead */ -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"); - struct dentry *ret = ERR_PTR(-ENODEV); - if (cgroup_fs) { - char mountopts[] = - "cpuset,noprefix," - "release_agent=/sbin/cpuset_release_agent"; - ret = cgroup_fs->mount(cgroup_fs, flags, - unused_dev_name, mountopts); - put_filesystem(cgroup_fs); +static int cpuset_get_tree(struct fs_context *fc) +{ + struct file_system_type *cgroup_fs; + struct fs_context *new_fc; + int ret; + + cgroup_fs = get_fs_type("cgroup"); + if (!cgroup_fs) + return -ENODEV; + + new_fc = fs_context_for_mount(cgroup_fs, fc->sb_flags); + if (IS_ERR(new_fc)) { + ret = PTR_ERR(new_fc); + } else { + static const char agent_path[] = "/sbin/cpuset_release_agent"; + ret = vfs_parse_fs_string(new_fc, "cpuset", NULL, 0); + if (!ret) + ret = vfs_parse_fs_string(new_fc, "noprefix", NULL, 0); + if (!ret) + ret = vfs_parse_fs_string(new_fc, "release_agent", + agent_path, sizeof(agent_path) - 1); + if (!ret) + ret = vfs_get_tree(new_fc); + if (!ret) { /* steal the result */ + fc->root = new_fc->root; + new_fc->root = NULL; + } + put_fs_context(new_fc); } + put_filesystem(cgroup_fs); return ret; } +static const struct fs_context_operations cpuset_fs_context_ops = { + .get_tree = cpuset_get_tree, +}; + +static int cpuset_init_fs_context(struct fs_context *fc) +{ + fc->ops = &cpuset_fs_context_ops; + return 0; +} + static struct file_system_type cpuset_fs_type = { - .name = "cpuset", - .mount = cpuset_mount, + .name = "cpuset", + .init_fs_context = cpuset_init_fs_context, }; /* |