cgroup: move v1 mount functions to kernel/cgroup/cgroup-v1.c (1592c9b2) · Commits · 戴 / test

kernel/cgroup/cgroup-internal.h

+25 −3

Original line number	Original line	Diff line number	Diff line
	@@ -26,6 +26,16 @@ struct cgrp_cset_link {
	struct list_head cgrp_link;		struct list_head cgrp_link;
	};		};

			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 struct mutex cgroup_mutex;
	extern spinlock_t css_set_lock;		extern spinlock_t css_set_lock;
	extern struct cgroup_subsys *cgroup_subsys[];		extern struct cgroup_subsys *cgroup_subsys[];
	@@ -66,7 +76,13 @@ void cgroup_kn_unlock(struct kernfs_node *kn);
	int cgroup_path_ns_locked(struct cgroup cgrp, char buf, size_t buflen,		int cgroup_path_ns_locked(struct cgroup cgrp, char buf, size_t buflen,
	struct cgroup_namespace *ns);		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);
			int cgroup_setup_root(struct cgroup_root *root, u16 ss_mask);
	int rebind_subsystems(struct cgroup_root *dst_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);

	bool cgroup_may_migrate_to(struct cgroup *dst_cgrp);		bool cgroup_may_migrate_to(struct cgroup *dst_cgrp);
	void cgroup_migrate_finish(struct list_head *preloaded_csets);		void cgroup_migrate_finish(struct list_head *preloaded_csets);
	@@ -86,18 +102,24 @@ ssize_t cgroup_procs_write(struct kernfs_open_file of, char buf, size_t nbytes

	void cgroup_lock_and_drain_offline(struct cgroup *cgrp);		void cgroup_lock_and_drain_offline(struct cgroup *cgrp);

			int cgroup_mkdir(struct kernfs_node parent_kn, const char name, umode_t mode);
			int cgroup_rmdir(struct kernfs_node *kn);
			int cgroup_show_path(struct seq_file sf, struct kernfs_node kf_node,
			struct kernfs_root *kf_root);

	/*		/*
	* cgroup-v1.c		* cgroup-v1.c
	*/		*/
	extern spinlock_t release_agent_path_lock;
	extern struct cftype cgroup_legacy_base_files[];		extern struct cftype cgroup_legacy_base_files[];
	extern const struct file_operations proc_cgroupstats_operations;		extern const struct file_operations proc_cgroupstats_operations;
			extern struct kernfs_syscall_ops cgroup1_kf_syscall_ops;

	bool cgroup_ssid_no_v1(int ssid);		bool cgroup_ssid_no_v1(int ssid);
	void cgroup_pidlist_destroy_all(struct cgroup *cgrp);		void cgroup_pidlist_destroy_all(struct cgroup *cgrp);
	int cgroup1_rename(struct kernfs_node kn, struct kernfs_node new_parent,
	const char *new_name_str);
	void cgroup_release_agent(struct work_struct *work);		void cgroup_release_agent(struct work_struct *work);
	void check_for_release(struct cgroup *cgrp);		void 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);

	#endif /* __CGROUP_INTERNAL_H */		#endif /* __CGROUP_INTERNAL_H */

kernel/cgroup/cgroup-v1.c

+378 −3

Original line number	Original line	Diff line number	Diff line
	#include "cgroup-internal.h"		#include "cgroup-internal.h"

			#include <linux/ctype.h>
	#include <linux/kmod.h>		#include <linux/kmod.h>
	#include <linux/sort.h>		#include <linux/sort.h>
			#include <linux/delay.h>
	#include <linux/mm.h>		#include <linux/mm.h>
	#include <linux/slab.h>		#include <linux/slab.h>
	#include <linux/vmalloc.h>		#include <linux/vmalloc.h>
	@@ -32,7 +34,7 @@ static struct workqueue_struct *cgroup_pidlist_destroy_wq;
	* Protects cgroup_subsys->release_agent_path. Modifying it also requires		* Protects cgroup_subsys->release_agent_path. Modifying it also requires
	* cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.		* cgroup_mutex. Reading requires either cgroup_mutex or this spinlock.
	*/		*/
	DEFINE_SPINLOCK(release_agent_path_lock);		static DEFINE_SPINLOCK(release_agent_path_lock);

	bool cgroup_ssid_no_v1(int ssid)		bool cgroup_ssid_no_v1(int ssid)
	{		{
	@@ -800,7 +802,7 @@ out_free:
	/*		/*
	* cgroup_rename - Only allow simple rename of directories in place.		* cgroup_rename - Only allow simple rename of directories in place.
	*/		*/
	int cgroup1_rename(struct kernfs_node kn, struct kernfs_node new_parent,		static int cgroup1_rename(struct kernfs_node kn, struct kernfs_node new_parent,
	const char *new_name_str)		const char *new_name_str)
	{		{
	struct cgroup *cgrp = kn->priv;		struct cgroup *cgrp = kn->priv;
	@@ -832,6 +834,379 @@ int cgroup1_rename(struct kernfs_node kn, struct kernfs_node new_parent,
	return ret;		return ret;
	}		}

			static int cgroup1_show_options(struct seq_file seq, struct kernfs_root kf_root)
			{
			struct cgroup_root *root = cgroup_root_from_kf(kf_root);
			struct cgroup_subsys *ss;
			int ssid;

			for_each_subsys(ss, ssid)
			if (root->subsys_mask & (1 << ssid))
			seq_show_option(seq, ss->legacy_name, NULL);
			if (root->flags & CGRP_ROOT_NOPREFIX)
			seq_puts(seq, ",noprefix");
			if (root->flags & CGRP_ROOT_XATTR)
			seq_puts(seq, ",xattr");

			spin_lock(&release_agent_path_lock);
			if (strlen(root->release_agent_path))
			seq_show_option(seq, "release_agent",
			root->release_agent_path);
			spin_unlock(&release_agent_path_lock);

			if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags))
			seq_puts(seq, ",clone_children");
			if (strlen(root->name))
			seq_show_option(seq, "name", root->name);
			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));

			while ((token = strsep(&o, ",")) != NULL) {
			nr_opts++;

			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, "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;
			/* 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;

			continue;
			}

			for_each_subsys(ss, i) {
			if (strcmp(token, ss->legacy_name))
			continue;
			if (!cgroup_ssid_enabled(i))
			continue;
			if (cgroup_ssid_no_v1(i))
			continue;

			/* Mutually exclusive option 'all' + subsystem name */
			if (all_ss)
			return -EINVAL;
			opts->subsys_mask \|= (1 << i);
			one_ss = true;

			break;
			}
			if (i == CGROUP_SUBSYS_COUNT)
			return -ENOENT;
			}

			/*
			* 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'
			*/
			if (all_ss \|\| (!one_ss && !opts->none && !opts->name))
			for_each_subsys(ss, i)
			if (cgroup_ssid_enabled(i) && !cgroup_ssid_no_v1(i))
			opts->subsys_mask \|= (1 << i);

			/*
			* 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;

			/*
			* 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;

			/* Can't specify "none" and some subsystems */
			if (opts->subsys_mask && opts->none)
			return -EINVAL;

			return 0;
			}

			static int cgroup1_remount(struct kernfs_root kf_root, int flags, char *data)
			{
			int ret = 0;
			struct cgroup_root *root = cgroup_root_from_kf(kf_root);
			struct cgroup_sb_opts opts;
			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);
			if (ret)
			goto out_unlock;

			if (opts.subsys_mask != root->subsys_mask \|\| opts.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;

			/* 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);
			ret = -EINVAL;
			goto out_unlock;
			}

			/* remounting is not allowed for populated hierarchies */
			if (!list_empty(&root->cgrp.self.children)) {
			ret = -EBUSY;
			goto out_unlock;
			}

			ret = rebind_subsystems(root, added_mask);
			if (ret)
			goto out_unlock;

			WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask));

			if (opts.release_agent) {
			spin_lock(&release_agent_path_lock);
			strcpy(root->release_agent_path, opts.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;
			}

			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)
			{
			struct super_block *pinned_sb = NULL;
			struct cgroup_sb_opts opts;
			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);
			if (ret)
			goto out_unlock;

			/*
			* Destruction of cgroup root is asynchronous, so subsystems may
			* still be dying after the previous unmount. Let's drain the
			* dying subsystems. We just need to ensure that the ones
			* unmounted previously finish dying and don't care about new ones
			* starting. Testing ref liveliness is good enough.
			*/
			for_each_subsys(ss, i) {
			if (!(opts.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;
			}
			cgroup_put(&ss->root->cgrp);
			}

			for_each_root(root) {
			bool name_match = false;

			if (root == &cgrp_dfl_root)
			continue;

			/*
			* If we asked for a name then it must match. Also, if
			* name matches but sybsys_mask doesn't, we should fail.
			* Remember whether name matched.
			*/
			if (opts.name) {
			if (strcmp(opts.name, root->name))
			continue;
			name_match = true;
			}

			/*
			* 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 (!name_match)
			continue;
			ret = -EBUSY;
			goto out_unlock;
			}

			if (root->flags ^ opts.flags)
			pr_warn("new mount options do not match the existing superblock, will be ignored\n");

			/*
			* We want to reuse @root whose lifetime is governed by its
			* ->cgrp. Let's check whether @root is alive and keep it
			* that way. As cgroup_kill_sb() can happen anytime, we
			* want to block it by pinning the sb so that @root doesn't
			* get killed before mount is complete.
			*
			* With the sb pinned, tryget_live can reliably indicate
			* whether @root can be reused. If it's being killed,
			* drain it. We can use wait_queue for the wait but this
			* path is super cold. Let's just sleep a bit and retry.
			*/
			pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
			if (IS_ERR(pinned_sb) \|\|
			!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
			mutex_unlock(&cgroup_mutex);
			if (!IS_ERR_OR_NULL(pinned_sb))
			deactivate_super(pinned_sb);
			msleep(10);
			ret = restart_syscall();
			goto out_free;
			}

			ret = 0;
			goto out_unlock;
			}

			/*
			* No such thing, create a new one. name= matching without subsys
			* 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;
			}

			/* Hierarchies may only be created in the initial cgroup namespace. */
			if (ns != &init_cgroup_ns) {
			ret = -EPERM;
			goto out_unlock;
			}

			root = kzalloc(sizeof(*root), GFP_KERNEL);
			if (!root) {
			ret = -ENOMEM;
			goto out_unlock;
			}

			init_cgroup_root(root, &opts);

			ret = cgroup_setup_root(root, opts.subsys_mask);
			if (ret)
			cgroup_free_root(root);

			out_unlock:
			mutex_unlock(&cgroup_mutex);
			out_free:
			kfree(opts.release_agent);
			kfree(opts.name);

			if (ret)
			return ERR_PTR(ret);

			dentry = cgroup_do_mount(&cgroup_fs_type, flags, root,
			CGROUP_SUPER_MAGIC, ns);

			/*
			* If @pinned_sb, we're reusing an existing root and holding an
			* extra ref on its sb. Mount is complete. Put the extra ref.
			*/
			if (pinned_sb)
			deactivate_super(pinned_sb);

			return dentry;
			}

	static int __init cgroup1_wq_init(void)		static int __init cgroup1_wq_init(void)
	{		{
	/*		/*

kernel/cgroup/cgroup.c

+10 −400

File changed.

Preview size limit exceeded, changes collapsed.

Admin message