Commit d8836005 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup 

Pull cgroup updates from Tejun Heo:

 - Christian extended clone3 so that processes can be spawned into
   cgroups directly.

   This is not only neat in terms of semantics but also avoids grabbing
   the global cgroup_threadgroup_rwsem for migration.

 - Daniel added !root xattr support to cgroupfs.

   Userland already uses xattrs on cgroupfs for bookkeeping. This will
   allow delegated cgroups to support such usages.

 - Prateek tried to make cpuset hotplug handling synchronous but that
   led to possible deadlock scenarios. Reverted.

 - Other minor changes including release_agent_path handling cleanup.

* 'for-5.7' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup:
  docs: cgroup-v1: Document the cpuset_v2_mode mount option
  Revert "cpuset: Make cpuset hotplug synchronous"
  cgroupfs: Support user xattrs
  kernfs: Add option to enable user xattrs
  kernfs: Add removed_size out param for simple_xattr_set
  kernfs: kvmalloc xattr value instead of kmalloc
  cgroup: Restructure release_agent_path handling
  selftests/cgroup: add tests for cloning into cgroups
  clone3: allow spawning processes into cgroups
  cgroup: add cgroup_may_write() helper
  cgroup: refactor fork helpers
  cgroup: add cgroup_get_from_file() helper
  cgroup: unify attach permission checking
  cpuset: Make cpuset hotplug synchronous
  cgroup.c: Use built-in RCU list checking
  kselftest/cgroup: add cgroup destruction test
  cgroup: Clean up css_set task traversal
parents f2c3bec3 0c05b9bd

Documentation/admin-guide/cgroup-v1/cpusets.rst

+11 −0
Original line number Diff line number Diff line
@@ -223,6 +223,17 @@ cpu_online_mask using a CPU hotplug notifier, and the mems file 
automatically tracks the value of node_states[N_MEMORY]--i.e.,

nodes with memory--using the cpuset_track_online_nodes() hook.



The cpuset.effective_cpus and cpuset.effective_mems files are

normally read-only copies of cpuset.cpus and cpuset.mems files

respectively.  If the cpuset cgroup filesystem is mounted with the

special "cpuset_v2_mode" option, the behavior of these files will become

similar to the corresponding files in cpuset v2.  In other words, hotplug

events will not change cpuset.cpus and cpuset.mems.  Those events will

only affect cpuset.effective_cpus and cpuset.effective_mems which show

the actual cpus and memory nodes that are currently used by this cpuset.

See Documentation/admin-guide/cgroup-v2.rst for more information about

cpuset v2 behavior.





1.4 What are exclusive cpusets ?

--------------------------------

fs/kernfs/inode.c

+90 −1
Original line number Diff line number Diff line
@@ -53,6 +53,8 @@ static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc) 
	kn->iattr->ia_ctime = kn->iattr->ia_atime;



	simple_xattrs_init(&kn->iattr->xattrs);

	atomic_set(&kn->iattr->nr_user_xattrs, 0);

	atomic_set(&kn->iattr->user_xattr_size, 0);

out_unlock:

	ret = kn->iattr;

	mutex_unlock(&iattr_mutex);
@@ -303,7 +305,7 @@ int kernfs_xattr_set(struct kernfs_node *kn, const char *name, 
	if (!attrs)

		return -ENOMEM;



	return simple_xattr_set(&attrs->xattrs, name, value, size, flags);

	return simple_xattr_set(&attrs->xattrs, name, value, size, flags, NULL);

}



static int kernfs_vfs_xattr_get(const struct xattr_handler *handler,
@@ -327,6 +329,86 @@ static int kernfs_vfs_xattr_set(const struct xattr_handler *handler, 
	return kernfs_xattr_set(kn, name, value, size, flags);

}



static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn,

				     const char *full_name,

				     struct simple_xattrs *xattrs,

				     const void *value, size_t size, int flags)

{

	atomic_t *sz = &kn->iattr->user_xattr_size;

	atomic_t *nr = &kn->iattr->nr_user_xattrs;

	ssize_t removed_size;

	int ret;



	if (atomic_inc_return(nr) > KERNFS_MAX_USER_XATTRS) {

		ret = -ENOSPC;

		goto dec_count_out;

	}



	if (atomic_add_return(size, sz) > KERNFS_USER_XATTR_SIZE_LIMIT) {

		ret = -ENOSPC;

		goto dec_size_out;

	}



	ret = simple_xattr_set(xattrs, full_name, value, size, flags,

			       &removed_size);



	if (!ret && removed_size >= 0)

		size = removed_size;

	else if (!ret)

		return 0;

dec_size_out:

	atomic_sub(size, sz);

dec_count_out:

	atomic_dec(nr);

	return ret;

}



static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn,

				    const char *full_name,

				    struct simple_xattrs *xattrs,

				    const void *value, size_t size, int flags)

{

	atomic_t *sz = &kn->iattr->user_xattr_size;

	atomic_t *nr = &kn->iattr->nr_user_xattrs;

	ssize_t removed_size;

	int ret;



	ret = simple_xattr_set(xattrs, full_name, value, size, flags,

			       &removed_size);



	if (removed_size >= 0) {

		atomic_sub(removed_size, sz);

		atomic_dec(nr);

	}



	return ret;

}



static int kernfs_vfs_user_xattr_set(const struct xattr_handler *handler,

				     struct dentry *unused, struct inode *inode,

				     const char *suffix, const void *value,

				     size_t size, int flags)

{

	const char *full_name = xattr_full_name(handler, suffix);

	struct kernfs_node *kn = inode->i_private;

	struct kernfs_iattrs *attrs;



	if (!(kernfs_root(kn)->flags & KERNFS_ROOT_SUPPORT_USER_XATTR))

		return -EOPNOTSUPP;



	attrs = kernfs_iattrs(kn);

	if (!attrs)

		return -ENOMEM;



	if (value)

		return kernfs_vfs_user_xattr_add(kn, full_name, &attrs->xattrs,

						 value, size, flags);

	else

		return kernfs_vfs_user_xattr_rm(kn, full_name, &attrs->xattrs,

						value, size, flags);



}



static const struct xattr_handler kernfs_trusted_xattr_handler = {

	.prefix = XATTR_TRUSTED_PREFIX,

	.get = kernfs_vfs_xattr_get,
@@ -339,8 +421,15 @@ static const struct xattr_handler kernfs_security_xattr_handler = { 
	.set = kernfs_vfs_xattr_set,

};



static const struct xattr_handler kernfs_user_xattr_handler = {

	.prefix = XATTR_USER_PREFIX,

	.get = kernfs_vfs_xattr_get,

	.set = kernfs_vfs_user_xattr_set,

};



const struct xattr_handler *kernfs_xattr_handlers[] = {

	&kernfs_trusted_xattr_handler,

	&kernfs_security_xattr_handler,

	&kernfs_user_xattr_handler,

	NULL

};

fs/kernfs/kernfs-internal.h

+2 −0
Original line number Diff line number Diff line
@@ -26,6 +26,8 @@ struct kernfs_iattrs { 
	struct timespec64	ia_ctime;



	struct simple_xattrs	xattrs;

	atomic_t		nr_user_xattrs;

	atomic_t		user_xattr_size;

};



/* +1 to avoid triggering overflow warning when negating it */

fs/xattr.c

+13 −4
Original line number Diff line number Diff line
@@ -817,7 +817,7 @@ struct simple_xattr *simple_xattr_alloc(const void *value, size_t size) 
	if (len < sizeof(*new_xattr))

		return NULL;



	new_xattr = kmalloc(len, GFP_KERNEL);

	new_xattr = kvmalloc(len, GFP_KERNEL);

	if (!new_xattr)

		return NULL;
@@ -860,6 +860,7 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, 
 * @value: value of the xattr. If %NULL, will remove the attribute.

 * @size: size of the new xattr

 * @flags: %XATTR_{CREATE|REPLACE}

 * @removed_size: returns size of the removed xattr, -1 if none removed

 *

 * %XATTR_CREATE is set, the xattr shouldn't exist already; otherwise fails

 * with -EEXIST.  If %XATTR_REPLACE is set, the xattr should exist;
@@ -868,7 +869,8 @@ int simple_xattr_get(struct simple_xattrs *xattrs, const char *name, 
 * Returns 0 on success, -errno on failure.

 */

int simple_xattr_set(struct simple_xattrs *xattrs, const char *name,

		     const void *value, size_t size, int flags)

		     const void *value, size_t size, int flags,

		     ssize_t *removed_size)

{

	struct simple_xattr *xattr;

	struct simple_xattr *new_xattr = NULL;
@@ -882,7 +884,7 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, 


		new_xattr->name = kstrdup(name, GFP_KERNEL);

		if (!new_xattr->name) {

			kfree(new_xattr);

			kvfree(new_xattr);

			return -ENOMEM;

		}

	}
@@ -895,8 +897,12 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, 
				err = -EEXIST;

			} else if (new_xattr) {

				list_replace(&xattr->list, &new_xattr->list);

				if (removed_size)

					*removed_size = xattr->size;

			} else {

				list_del(&xattr->list);

				if (removed_size)

					*removed_size = xattr->size;

			}

			goto out;

		}
@@ -908,11 +914,14 @@ int simple_xattr_set(struct simple_xattrs *xattrs, const char *name, 
		list_add(&new_xattr->list, &xattrs->head);

		xattr = NULL;

	}



	if (removed_size)

		*removed_size = -1;

out:

	spin_unlock(&xattrs->lock);

	if (xattr) {

		kfree(xattr->name);

		kfree(xattr);

		kvfree(xattr);

	}

	return err;

include/linux/cgroup-defs.h

+3 −2
Original line number Diff line number Diff line
@@ -633,8 +633,9 @@ struct cgroup_subsys { 
	void (*cancel_attach)(struct cgroup_taskset *tset);

	void (*attach)(struct cgroup_taskset *tset);

	void (*post_attach)(void);

	int (*can_fork)(struct task_struct *task);

	void (*cancel_fork)(struct task_struct *task);

	int (*can_fork)(struct task_struct *task,

			struct css_set *cset);

	void (*cancel_fork)(struct task_struct *task, struct css_set *cset);

	void (*fork)(struct task_struct *task);

	void (*exit)(struct task_struct *task);

	void (*release)(struct task_struct *task);

CRA Git | Maintained and supported by SUSTech CRA and CCSE