Unverified Commit 13b0cce9 authored by Christian Brauner's avatar Christian Brauner
Browse files

Merge patch series "Introduce bpf_cgroup_read_xattr" 

Song Liu <song@kernel.org> says:

Introduce a new kfunc bpf_cgroup_read_xattr, which can read xattr from
cgroupfs nodes. The primary users are LSMs, cgroup programs, and sched_ext.

* patches from https://lore.kernel.org/20250623063854.1896364-1-song@kernel.org:
  selftests/bpf: Add tests for bpf_cgroup_read_xattr
  bpf: Mark cgroup_subsys_state->cgroup RCU safe
  bpf: Introduce bpf_cgroup_read_xattr to read xattr of cgroup's node
  kernfs: remove iattr_mutex

Link: https://lore.kernel.org/20250623063854.1896364-1-song@kernel.org


Signed-off-by: default avatarChristian Brauner <brauner@kernel.org>
parents 19272b37 f4fba2d6

fs/bpf_fs_kfuncs.c

+34 −0
Original line number Diff line number Diff line
@@ -9,6 +9,7 @@ 
#include <linux/fs.h>

#include <linux/fsnotify.h>

#include <linux/file.h>

#include <linux/kernfs.h>

#include <linux/mm.h>

#include <linux/xattr.h>
@@ -322,6 +323,39 @@ __bpf_kfunc int bpf_remove_dentry_xattr(struct dentry *dentry, const char *name_ 
	return ret;

}



#ifdef CONFIG_CGROUPS

/**

 * bpf_cgroup_read_xattr - read xattr of a cgroup's node in cgroupfs

 * @cgroup: cgroup to get xattr from

 * @name__str: name of the xattr

 * @value_p: output buffer of the xattr value

 *

 * Get xattr *name__str* of *cgroup* and store the output in *value_ptr*.

 *

 * For security reasons, only *name__str* with prefix "user." is allowed.

 *

 * Return: length of the xattr value on success, a negative value on error.

 */

__bpf_kfunc int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,

					struct bpf_dynptr *value_p)

{

	struct bpf_dynptr_kern *value_ptr = (struct bpf_dynptr_kern *)value_p;

	u32 value_len;

	void *value;



	/* Only allow reading "user.*" xattrs */

	if (strncmp(name__str, XATTR_USER_PREFIX, XATTR_USER_PREFIX_LEN))

		return -EPERM;



	value_len = __bpf_dynptr_size(value_ptr);

	value = __bpf_dynptr_data_rw(value_ptr, value_len);

	if (!value)

		return -EINVAL;



	return kernfs_xattr_get(cgroup->kn, name__str, value, value_len);

}

#endif /* CONFIG_CGROUPS */



__bpf_kfunc_end_defs();



BTF_KFUNCS_START(bpf_fs_kfunc_set_ids)

fs/kernfs/inode.c

+40 −34
Original line number Diff line number Diff line
@@ -24,45 +24,46 @@ static const struct inode_operations kernfs_iops = { 
	.listxattr	= kernfs_iop_listxattr,

};



static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, int alloc)

static struct kernfs_iattrs *__kernfs_iattrs(struct kernfs_node *kn, bool alloc)

{

	static DEFINE_MUTEX(iattr_mutex);

	struct kernfs_iattrs *ret;

	struct kernfs_iattrs *ret __free(kfree) = NULL;

	struct kernfs_iattrs *attr;



	mutex_lock(&iattr_mutex);

	attr = READ_ONCE(kn->iattr);

	if (attr || !alloc)

		return attr;



	if (kn->iattr || !alloc)

		goto out_unlock;



	kn->iattr = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL);

	if (!kn->iattr)

		goto out_unlock;

	ret = kmem_cache_zalloc(kernfs_iattrs_cache, GFP_KERNEL);

	if (!ret)

		return NULL;



	/* assign default attributes */

	kn->iattr->ia_uid = GLOBAL_ROOT_UID;

	kn->iattr->ia_gid = GLOBAL_ROOT_GID;



	ktime_get_real_ts64(&kn->iattr->ia_atime);

	kn->iattr->ia_mtime = kn->iattr->ia_atime;

	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);

	return ret;

	ret->ia_uid = GLOBAL_ROOT_UID;

	ret->ia_gid = GLOBAL_ROOT_GID;



	ktime_get_real_ts64(&ret->ia_atime);

	ret->ia_mtime = ret->ia_atime;

	ret->ia_ctime = ret->ia_atime;



	simple_xattrs_init(&ret->xattrs);

	atomic_set(&ret->nr_user_xattrs, 0);

	atomic_set(&ret->user_xattr_size, 0);



	/* If someone raced us, recognize it. */

	if (!try_cmpxchg(&kn->iattr, &attr, ret))

		return READ_ONCE(kn->iattr);



	return no_free_ptr(ret);

}



static struct kernfs_iattrs *kernfs_iattrs(struct kernfs_node *kn)

{

	return __kernfs_iattrs(kn, 1);

	return __kernfs_iattrs(kn, true);

}



static struct kernfs_iattrs *kernfs_iattrs_noalloc(struct kernfs_node *kn)

{

	return __kernfs_iattrs(kn, 0);

	return __kernfs_iattrs(kn, false);

}



int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
@@ -141,9 +142,9 @@ ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size) 
	struct kernfs_node *kn = kernfs_dentry_node(dentry);

	struct kernfs_iattrs *attrs;



	attrs = kernfs_iattrs(kn);

	attrs = kernfs_iattrs_noalloc(kn);

	if (!attrs)

		return -ENOMEM;

		return -ENODATA;



	return simple_xattr_list(d_inode(dentry), &attrs->xattrs, buf, size);

}
@@ -166,9 +167,10 @@ static inline void set_inode_attr(struct inode *inode, 


static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)

{

	struct kernfs_iattrs *attrs = kn->iattr;

	struct kernfs_iattrs *attrs;



	inode->i_mode = kn->mode;

	attrs = kernfs_iattrs_noalloc(kn);

	if (attrs)

		/*

		 * kernfs_node has non-default attributes get them from
@@ -306,7 +308,9 @@ int kernfs_xattr_set(struct kernfs_node *kn, const char *name, 
		     const void *value, size_t size, int flags)

{

	struct simple_xattr *old_xattr;

	struct kernfs_iattrs *attrs = kernfs_iattrs(kn);

	struct kernfs_iattrs *attrs;



	attrs = kernfs_iattrs(kn);

	if (!attrs)

		return -ENOMEM;
@@ -345,8 +349,9 @@ static int kernfs_vfs_user_xattr_add(struct kernfs_node *kn, 
				     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;

	struct kernfs_iattrs *attr = kernfs_iattrs_noalloc(kn);

	atomic_t *sz = &attr->user_xattr_size;

	atomic_t *nr = &attr->nr_user_xattrs;

	struct simple_xattr *old_xattr;

	int ret;
@@ -384,8 +389,9 @@ static int kernfs_vfs_user_xattr_rm(struct kernfs_node *kn, 
				    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;

	struct kernfs_iattrs *attr = kernfs_iattrs_noalloc(kn);

	atomic_t *sz = &attr->user_xattr_size;

	atomic_t *nr = &attr->nr_user_xattrs;

	struct simple_xattr *old_xattr;



	old_xattr = simple_xattr_set(xattrs, full_name, value, size, flags);

kernel/bpf/helpers.c

+3 −0
Original line number Diff line number Diff line
@@ -3397,6 +3397,9 @@ BTF_ID_FLAGS(func, bpf_iter_dmabuf_next, KF_ITER_NEXT | KF_RET_NULL | KF_SLEEPAB 
BTF_ID_FLAGS(func, bpf_iter_dmabuf_destroy, KF_ITER_DESTROY | KF_SLEEPABLE)

#endif

BTF_ID_FLAGS(func, __bpf_trap)

#ifdef CONFIG_CGROUPS

BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)

#endif

BTF_KFUNCS_END(common_btf_ids)



static const struct btf_kfunc_id_set common_kfunc_set = {

kernel/bpf/verifier.c

+5 −0
Original line number Diff line number Diff line
@@ -6993,6 +6993,10 @@ BTF_TYPE_SAFE_RCU(struct css_set) { 
	struct cgroup *dfl_cgrp;

};









BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state) {









	struct cgroup *cgroup;









};

















/* RCU trusted: these fields are trusted in RCU CS and can be NULL */









BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) {









	struct file __rcu *exe_file;








@@ -7043,6 +7047,7 @@ static bool type_is_rcu(struct bpf_verifier_env *env,







	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct));









	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup));









	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set));









	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state));

















	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu");









}
































tools/testing/selftests/bpf/bpf_experimental.h



+3
−0






























Original line number
Diff line number
Diff line







@@ -596,4 +596,7 @@ extern int bpf_iter_dmabuf_new(struct bpf_iter_dmabuf *it) __weak __ksym;







extern struct dma_buf *bpf_iter_dmabuf_next(struct bpf_iter_dmabuf *it) __weak __ksym;









extern void bpf_iter_dmabuf_destroy(struct bpf_iter_dmabuf *it) __weak __ksym;



















extern int bpf_cgroup_read_xattr(struct cgroup *cgroup, const char *name__str,









				 struct bpf_dynptr *value_p) __weak __ksym;



















#endif