diff options
29 files changed, 1624 insertions, 167 deletions
diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c index fe17c7f98e81..6d07693c6b9f 100644 --- a/drivers/media/rc/bpf-lirc.c +++ b/drivers/media/rc/bpf-lirc.c @@ -110,7 +110,7 @@ lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: - if (perfmon_capable()) + if (bpf_token_capable(prog->aux->token, CAP_PERFMON)) return bpf_get_trace_printk_proto(); fallthrough; default: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 10e5e4d8a00f..7a483f6b6d5f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -51,6 +51,10 @@ struct module; struct bpf_func_state; struct ftrace_ops; struct cgroup; +struct bpf_token; +struct user_namespace; +struct super_block; +struct inode; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -1457,6 +1461,7 @@ struct bpf_prog_aux { #ifdef CONFIG_SECURITY void *security; #endif + struct bpf_token *token; struct bpf_prog_offload *offload; struct btf *btf; struct bpf_func_info *func_info; @@ -1581,6 +1586,29 @@ struct bpf_link_primer { u32 id; }; +struct bpf_mount_opts { + umode_t mode; + + /* BPF token-related delegation options */ + u64 delegate_cmds; + u64 delegate_maps; + u64 delegate_progs; + u64 delegate_attachs; +}; + +struct bpf_token { + struct work_struct work; + atomic64_t refcnt; + struct user_namespace *userns; + u64 allowed_cmds; + u64 allowed_maps; + u64 allowed_progs; + u64 allowed_attachs; +#ifdef CONFIG_SECURITY + void *security; +#endif +}; + struct bpf_struct_ops_value; struct btf_member; @@ -2038,6 +2066,7 @@ static inline void bpf_enable_instrumentation(void) migrate_enable(); } +extern const struct super_operations bpf_super_ops; extern const struct file_operations bpf_map_fops; extern const struct file_operations bpf_prog_fops; extern const struct file_operations bpf_iter_fops; @@ -2172,24 +2201,26 @@ static inline void bpf_map_dec_elem_count(struct bpf_map *map) extern int sysctl_unprivileged_bpf_disabled; -static inline bool bpf_allow_ptr_leaks(void) +bool bpf_token_capable(const struct bpf_token *token, int cap); + +static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_allow_uninit_stack(void) +static inline bool bpf_allow_uninit_stack(const struct bpf_token *token) { - return perfmon_capable(); + return bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v1(void) +static inline bool bpf_bypass_spec_v1(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } -static inline bool bpf_bypass_spec_v4(void) +static inline bool bpf_bypass_spec_v4(const struct bpf_token *token) { - return cpu_mitigations_off() || perfmon_capable(); + return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON); } int bpf_map_new_fd(struct bpf_map *map, int flags); @@ -2206,8 +2237,21 @@ int bpf_link_new_fd(struct bpf_link *link); struct bpf_link *bpf_link_get_from_fd(u32 ufd); struct bpf_link *bpf_link_get_curr_or_next(u32 *id); +void bpf_token_inc(struct bpf_token *token); +void bpf_token_put(struct bpf_token *token); +int bpf_token_create(union bpf_attr *attr); +struct bpf_token *bpf_token_get_from_fd(u32 ufd); + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type); +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type); + int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname); int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags); +struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, + umode_t mode); #define BPF_ITER_FUNC_PREFIX "bpf_iter_" #define DEFINE_BPF_ITER_FUNC(target, args...) \ @@ -2451,7 +2495,8 @@ const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); -const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); +const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id, + const struct bpf_prog *prog); void bpf_task_storage_free(struct task_struct *task); void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); @@ -2570,6 +2615,24 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags) return -EOPNOTSUPP; } +static inline bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +static inline void bpf_token_inc(struct bpf_token *token) +{ +} + +static inline void bpf_token_put(struct bpf_token *token) +{ +} + +static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + return ERR_PTR(-EOPNOTSUPP); +} + static inline void __dev_flush(void) { } @@ -2693,7 +2756,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log, } static inline const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { return NULL; } diff --git a/include/linux/filter.h b/include/linux/filter.h index a4953fafc8cb..14354605ad26 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1139,7 +1139,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) return false; if (!bpf_jit_harden) return false; - if (bpf_jit_harden == 1 && bpf_capable()) + if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h index ff217a5ce552..3fdd00b452ac 100644 --- a/include/linux/lsm_hook_defs.h +++ b/include/linux/lsm_hook_defs.h @@ -398,10 +398,17 @@ LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule) LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size) LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode) LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog) -LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map) -LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map) -LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux) -LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux) +LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map) +LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) +LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog) +LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr, + struct path *path) +LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token) +LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd) +LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap) #endif /* CONFIG_BPF_SYSCALL */ LSM_HOOK(int, 0, locked_down, enum lockdown_reason what) diff --git a/include/linux/security.h b/include/linux/security.h index 1d1df326c881..00809d2d5c38 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -32,6 +32,7 @@ #include <linux/string.h> #include <linux/mm.h> #include <linux/sockptr.h> +#include <linux/bpf.h> struct linux_binprm; struct cred; @@ -2020,15 +2021,22 @@ static inline void securityfs_remove(struct dentry *dentry) union bpf_attr; struct bpf_map; struct bpf_prog; -struct bpf_prog_aux; +struct bpf_token; #ifdef CONFIG_SECURITY extern int security_bpf(int cmd, union bpf_attr *attr, unsigned int size); extern int security_bpf_map(struct bpf_map *map, fmode_t fmode); extern int security_bpf_prog(struct bpf_prog *prog); -extern int security_bpf_map_alloc(struct bpf_map *map); +extern int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token); extern void security_bpf_map_free(struct bpf_map *map); -extern int security_bpf_prog_alloc(struct bpf_prog_aux *aux); -extern void security_bpf_prog_free(struct bpf_prog_aux *aux); +extern int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token); +extern void security_bpf_prog_free(struct bpf_prog *prog); +extern int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path); +extern void security_bpf_token_free(struct bpf_token *token); +extern int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd); +extern int security_bpf_token_capable(const struct bpf_token *token, int cap); #else static inline int security_bpf(int cmd, union bpf_attr *attr, unsigned int size) @@ -2046,7 +2054,8 @@ static inline int security_bpf_prog(struct bpf_prog *prog) return 0; } -static inline int security_bpf_map_alloc(struct bpf_map *map) +static inline int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { return 0; } @@ -2054,13 +2063,33 @@ static inline int security_bpf_map_alloc(struct bpf_map *map) static inline void security_bpf_map_free(struct bpf_map *map) { } -static inline int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +static inline int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { return 0; } -static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) +static inline void security_bpf_prog_free(struct bpf_prog *prog) { } + +static inline int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + return 0; +} + +static inline void security_bpf_token_free(struct bpf_token *token) +{ } + +static inline int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return 0; +} + +static inline int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return 0; +} #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index e88746ba7d21..4df2d025c784 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -951,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -995,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1401,6 +1435,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1470,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1582,6 +1618,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { @@ -1712,6 +1749,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..4ce95acfcaa7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 4a4a67956e21..8d365bda9a8b 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e14c822f8911..7d2f96413a57 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,9 +260,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -345,9 +351,8 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 491d20038cbe..98e0e3835b28 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1630,7 +1630,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2191,7 +2191,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2348,7 +2348,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 4b813da8d6c0..ced511f44174 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -675,7 +675,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); @@ -2751,6 +2751,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index ee9bdf29246a..b3be5742d6f1 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1679,7 +1679,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1730,7 +1730,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1788,7 +1788,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 1aafb2ff2e95..5359a0929c35 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/kstrtox.h> #include "preload/bpf_preload.h" enum bpf_type { @@ -98,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -599,10 +600,36 @@ EXPORT_SYMBOL(bpf_prog_get_type_path); */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; + u64 mask; if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((opts->delegate_cmds & mask) == mask) + seq_printf(m, ",delegate_cmds=any"); + else if (opts->delegate_cmds) + seq_printf(m, ",delegate_cmds=0x%llx", opts->delegate_cmds); + + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((opts->delegate_maps & mask) == mask) + seq_printf(m, ",delegate_maps=any"); + else if (opts->delegate_maps) + seq_printf(m, ",delegate_maps=0x%llx", opts->delegate_maps); + + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((opts->delegate_progs & mask) == mask) + seq_printf(m, ",delegate_progs=any"); + else if (opts->delegate_progs) + seq_printf(m, ",delegate_progs=0x%llx", opts->delegate_progs); + + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((opts->delegate_attachs & mask) == mask) + seq_printf(m, ",delegate_attachs=any"); + else if (opts->delegate_attachs) + seq_printf(m, ",delegate_attachs=0x%llx", opts->delegate_attachs); return 0; } @@ -617,7 +644,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, @@ -626,22 +653,27 @@ static const struct super_operations bpf_super_ops = { enum { OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; - int opt; + int opt, err; + u64 msk; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -665,6 +697,28 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: + if (strcmp(param->string, "any") == 0) { + msk = ~0ULL; + } else { + err = kstrtou64(param->string, 0, &msk); + if (err) + return err; + } + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + switch (opt) { + case OPT_DELEGATE_CMDS: opts->delegate_cmds |= msk; break; + case OPT_DELEGATE_MAPS: opts->delegate_maps |= msk; break; + case OPT_DELEGATE_PROGS: opts->delegate_progs |= msk; break; + case OPT_DELEGATE_ATTACHS: opts->delegate_attachs |= msk; break; + default: return -EINVAL; + } + break; } return 0; @@ -739,10 +793,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -764,7 +822,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -786,17 +844,32 @@ static int bpf_init_fs_context(struct fs_context *fc) opts->mode = S_IRWXUGO; - fc->fs_private = opts; + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; + + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_litter_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index ebaccf77d56e..aff045eed375 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1009,8 +1009,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1038,7 +1038,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1121,11 +1121,17 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +static bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; @@ -1176,14 +1182,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (attr->map_token_fd) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1216,25 +1240,27 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1271,7 +1297,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1283,15 +1309,16 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1312,6 +1339,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } @@ -2133,7 +2162,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2579,13 +2608,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2602,10 +2633,31 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_REG_INVARIANTS)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_token_fd) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2614,21 +2666,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2638,27 +2692,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2666,7 +2726,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2676,7 +2737,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; @@ -2687,9 +2749,9 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2698,12 +2760,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog_sec; + goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2717,25 +2779,29 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog_sec; + goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token); + if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2781,13 +2847,16 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3777,7 +3846,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!capable(CAP_NET_ADMIN)) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ @@ -3980,7 +4049,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - if (!capable(CAP_NET_ADMIN)) + if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; @@ -4748,15 +4817,31 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_token_fd) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } @@ -5372,6 +5457,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5505,6 +5604,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; @@ -5611,7 +5713,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5661,7 +5763,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..17212efcde60 --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,263 @@ +#include <linux/bpf.h> +#include <linux/vmalloc.h> +#include <linux/fdtable.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/namei.h> +#include <linux/user_namespace.h> +#include <linux/security.h> + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + /* BPF token allows ns_capable() level of capabilities, but only if + * token's userns is *exactly* the same as current user's userns + */ + if (token && current_user_ns() == token->userns) { + if (ns_capable(token->userns, cap) || + (cap != CAP_SYS_ADMIN && ns_capable(token->userns, CAP_SYS_ADMIN))) + return security_bpf_token_capable(token, cap) == 0; + } + /* otherwise fallback to capable() checks */ + return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN)); +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + security_bpf_token_free(token); + put_user_ns(token->userns); + kvfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = (1ULL << __MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kvzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + mnt_opts = path.dentry->d_sb->s_fs_info; + token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; + + err = security_bpf_token_create(token, attr, &path); + if (err) + goto out_token; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + /* BPF token can be used only within exactly the same userns in which + * it was created + */ + if (!token || current_user_ns() != token->userns) + return false; + if (!(token->allowed_cmds & (1ULL << cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; +} + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & (1ULL << type); +} + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & (1ULL << prog_type)) && + (token->allowed_attachs & (1ULL << attach_type)); +} diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e5ce530641ba..45e85fb76d82 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -20597,7 +20597,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -20629,12 +20634,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 1648bde28f01..774cf476a892 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1626,7 +1626,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/core/filter.c b/net/core/filter.c index 0adaa4afa35f..adcfc2c25754 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -87,7 +87,7 @@ #include "dev.h" static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id); +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -7841,7 +7841,7 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -7934,7 +7934,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -7953,7 +7953,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8140,7 +8140,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8199,7 +8199,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) #endif #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } #if IS_MODULE(CONFIG_NF_CONNTRACK) && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES) @@ -8260,7 +8260,7 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8302,7 +8302,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8346,7 +8346,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8357,7 +8357,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8384,7 +8384,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -8559,7 +8559,7 @@ static bool cg_skb_is_valid_access(int off, int size, return false; case bpf_ctx_range(struct __sk_buff, data): case bpf_ctx_range(struct __sk_buff, data_end): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; } @@ -8571,7 +8571,7 @@ static bool cg_skb_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, cb[0], cb[4]): break; case bpf_ctx_range(struct __sk_buff, tstamp): - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return false; break; default: @@ -11215,7 +11215,7 @@ sk_reuseport_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -11397,7 +11397,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_sk_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id, prog); } } @@ -11731,7 +11731,7 @@ const struct bpf_func_proto bpf_sock_from_file_proto = { }; static const struct bpf_func_proto * -bpf_sk_base_func_proto(enum bpf_func_id func_id) +bpf_sk_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { const struct bpf_func_proto *func; @@ -11760,10 +11760,10 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; return func; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 39dcccf0f174..c7bbd8f3c708 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -191,7 +191,7 @@ bpf_tcp_ca_get_func_proto(enum bpf_func_id func_id, case BPF_FUNC_ktime_get_coarse_ns: return &bpf_ktime_get_coarse_ns_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c index e502ec00b2fe..1969facac91c 100644 --- a/net/netfilter/nf_bpf_link.c +++ b/net/netfilter/nf_bpf_link.c @@ -314,7 +314,7 @@ static bool nf_is_valid_access(int off, int size, enum bpf_access_type type, static const struct bpf_func_proto * bpf_nf_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } const struct bpf_verifier_ops netfilter_verifier_ops = { diff --git a/security/security.c b/security/security.c index dcb3e7014f9b..088a79c35c26 100644 --- a/security/security.c +++ b/security/security.c @@ -5167,29 +5167,87 @@ int security_bpf_prog(struct bpf_prog *prog) } /** - * security_bpf_map_alloc() - Allocate a bpf map LSM blob - * @map: bpf map + * security_bpf_map_create() - Check if BPF map creation is allowed + * @map: BPF map object + * @attr: BPF syscall attributes used to create BPF map + * @token: BPF token used to grant user access + * + * Do a check when the kernel creates a new BPF map. This is also the + * point where LSM blob is allocated for LSMs that need them. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) +{ + return call_int_hook(bpf_map_create, 0, map, attr, token); +} + +/** + * security_bpf_prog_load() - Check if loading of BPF program is allowed + * @prog: BPF program object + * @attr: BPF syscall attributes used to create BPF program + * @token: BPF token used to grant user access to BPF subsystem * - * Initialize the security field inside bpf map. + * Perform an access control check when the kernel loads a BPF program and + * allocates associated BPF program object. This hook is also responsible for + * allocating any required LSM state for the BPF program. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_map_alloc(struct bpf_map *map) +int security_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { - return call_int_hook(bpf_map_alloc_security, 0, map); + return call_int_hook(bpf_prog_load, 0, prog, attr, token); } /** - * security_bpf_prog_alloc() - Allocate a bpf program LSM blob - * @aux: bpf program aux info struct + * security_bpf_token_create() - Check if creating of BPF token is allowed + * @token: BPF token object + * @attr: BPF syscall attributes used to create BPF token + * @path: path pointing to BPF FS mount point from which BPF token is created * - * Initialize the security field inside bpf program. + * Do a check when the kernel instantiates a new BPF token object from BPF FS + * instance. This is also the point where LSM blob can be allocated for LSMs. * * Return: Returns 0 on success, error on failure. */ -int security_bpf_prog_alloc(struct bpf_prog_aux *aux) +int security_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) { - return call_int_hook(bpf_prog_alloc_security, 0, aux); + return call_int_hook(bpf_token_create, 0, token, attr, path); +} + +/** + * security_bpf_token_cmd() - Check if BPF token is allowed to delegate + * requested BPF syscall command + * @token: BPF token object + * @cmd: BPF syscall command requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF syscall command. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + return call_int_hook(bpf_token_cmd, 0, token, cmd); +} + +/** + * security_bpf_token_capable() - Check if BPF token is allowed to delegate + * requested BPF-related capability + * @token: BPF token object + * @cap: capabilities requested to be delegated by BPF token + * + * Do a check when the kernel decides whether provided BPF token should allow + * delegation of requested BPF-related capabilities. + * + * Return: Returns 0 on success, error on failure. + */ +int security_bpf_token_capable(const struct bpf_token *token, int cap) +{ + return call_int_hook(bpf_token_capable, 0, token, cap); } /** @@ -5200,18 +5258,29 @@ int security_bpf_prog_alloc(struct bpf_prog_aux *aux) */ void security_bpf_map_free(struct bpf_map *map) { - call_void_hook(bpf_map_free_security, map); + call_void_hook(bpf_map_free, map); +} + +/** + * security_bpf_prog_free() - Free a BPF program's LSM blob + * @prog: BPF program struct + * + * Clean up the security information stored inside BPF program. + */ +void security_bpf_prog_free(struct bpf_prog *prog) +{ + call_void_hook(bpf_prog_free, prog); } /** - * security_bpf_prog_free() - Free a bpf program's LSM blob - * @aux: bpf program aux info struct + * security_bpf_token_free() - Free a BPF token's LSM blob + * @token: BPF token struct * - * Clean up the security information stored inside bpf prog. + * Clean up the security information stored inside BPF token. */ -void security_bpf_prog_free(struct bpf_prog_aux *aux) +void security_bpf_token_free(struct bpf_token *token) { - call_void_hook(bpf_prog_free_security, aux); + call_void_hook(bpf_token_free, token); } #endif /* CONFIG_BPF_SYSCALL */ diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index feda711c6b7b..1501e95366a1 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -6783,7 +6783,8 @@ static int selinux_bpf_prog(struct bpf_prog *prog) BPF__PROG_RUN, NULL); } -static int selinux_bpf_map_alloc(struct bpf_map *map) +static int selinux_bpf_map_create(struct bpf_map *map, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6805,7 +6806,8 @@ static void selinux_bpf_map_free(struct bpf_map *map) kfree(bpfsec); } -static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) +static int selinux_bpf_prog_load(struct bpf_prog *prog, union bpf_attr *attr, + struct bpf_token *token) { struct bpf_security_struct *bpfsec; @@ -6814,16 +6816,39 @@ static int selinux_bpf_prog_alloc(struct bpf_prog_aux *aux) return -ENOMEM; bpfsec->sid = current_sid(); - aux->security = bpfsec; + prog->aux->security = bpfsec; return 0; } -static void selinux_bpf_prog_free(struct bpf_prog_aux *aux) +static void selinux_bpf_prog_free(struct bpf_prog *prog) { - struct bpf_security_struct *bpfsec = aux->security; + struct bpf_security_struct *bpfsec = prog->aux->security; - aux->security = NULL; + prog->aux->security = NULL; + kfree(bpfsec); +} + +static int selinux_bpf_token_create(struct bpf_token *token, union bpf_attr *attr, + struct path *path) +{ + struct bpf_security_struct *bpfsec; + + bpfsec = kzalloc(sizeof(*bpfsec), GFP_KERNEL); + if (!bpfsec) + return -ENOMEM; + + bpfsec->sid = current_sid(); + token->security = bpfsec; + + return 0; +} + +static void selinux_bpf_token_free(struct bpf_token *token) +{ + struct bpf_security_struct *bpfsec = token->security; + + token->security = NULL; kfree(bpfsec); } #endif @@ -7179,8 +7204,9 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(bpf, selinux_bpf), LSM_HOOK_INIT(bpf_map, selinux_bpf_map), LSM_HOOK_INIT(bpf_prog, selinux_bpf_prog), - LSM_HOOK_INIT(bpf_map_free_security, selinux_bpf_map_free), - LSM_HOOK_INIT(bpf_prog_free_security, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_map_free, selinux_bpf_map_free), + LSM_HOOK_INIT(bpf_prog_free, selinux_bpf_prog_free), + LSM_HOOK_INIT(bpf_token_free, selinux_bpf_token_free), #endif #ifdef CONFIG_PERF_EVENTS @@ -7237,8 +7263,9 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = { LSM_HOOK_INIT(audit_rule_init, selinux_audit_rule_init), #endif #ifdef CONFIG_BPF_SYSCALL - LSM_HOOK_INIT(bpf_map_alloc_security, selinux_bpf_map_alloc), - LSM_HOOK_INIT(bpf_prog_alloc_security, selinux_bpf_prog_alloc), + LSM_HOOK_INIT(bpf_map_create, selinux_bpf_map_create), + LSM_HOOK_INIT(bpf_prog_load, selinux_bpf_prog_load), + LSM_HOOK_INIT(bpf_token_create, selinux_bpf_token_create), #endif #ifdef CONFIG_PERF_EVENTS LSM_HOOK_INIT(perf_event_alloc, selinux_perf_event_alloc), diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index e88746ba7d21..4df2d025c784 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -847,6 +847,36 @@ union bpf_iter_link_info { * Returns zero on success. On error, -1 is returned and *errno* * is set appropriately. * + * BPF_TOKEN_CREATE + * Description + * Create BPF token with embedded information about what + * BPF-related functionality it allows: + * - a set of allowed bpf() syscall commands; + * - a set of allowed BPF map types to be created with + * BPF_MAP_CREATE command, if BPF_MAP_CREATE itself is allowed; + * - a set of allowed BPF program types and BPF program attach + * types to be loaded with BPF_PROG_LOAD command, if + * BPF_PROG_LOAD itself is allowed. + * + * BPF token is created (derived) from an instance of BPF FS, + * assuming it has necessary delegation mount options specified. + * This BPF token can be passed as an extra parameter to various + * bpf() syscall commands to grant BPF subsystem functionality to + * unprivileged processes. + * + * When created, BPF token is "associated" with the owning + * user namespace of BPF FS instance (super block) that it was + * derived from, and subsequent BPF operations performed with + * BPF token would be performing capabilities checks (i.e., + * CAP_BPF, CAP_PERFMON, CAP_NET_ADMIN, CAP_SYS_ADMIN) within + * that user namespace. Without BPF token, such capabilities + * have to be granted in init user namespace, making bpf() + * syscall incompatible with user namespace, for the most part. + * + * Return + * A new file descriptor (a nonnegative integer), or -1 if an + * error occurred (in which case, *errno* is set appropriately). + * * NOTES * eBPF objects (maps and programs) can be shared between processes. * @@ -901,6 +931,8 @@ enum bpf_cmd { BPF_ITER_CREATE, BPF_LINK_DETACH, BPF_PROG_BIND_MAP, + BPF_TOKEN_CREATE, + __MAX_BPF_CMD, }; enum bpf_map_type { @@ -951,6 +983,7 @@ enum bpf_map_type { BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, BPF_MAP_TYPE_CGRP_STORAGE, + __MAX_BPF_MAP_TYPE }; /* Note that tracing related programs such as @@ -995,6 +1028,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_SK_LOOKUP, BPF_PROG_TYPE_SYSCALL, /* a program that can execute syscalls */ BPF_PROG_TYPE_NETFILTER, + __MAX_BPF_PROG_TYPE }; enum bpf_attach_type { @@ -1401,6 +1435,7 @@ union bpf_attr { * to using 5 hash functions). */ __u64 map_extra; + __u32 map_token_fd; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -1470,6 +1505,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 log_true_size; + __u32 prog_token_fd; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1582,6 +1618,7 @@ union bpf_attr { * truncated), or smaller (if log buffer wasn't filled completely). */ __u32 btf_log_true_size; + __u32 btf_token_fd; }; struct { @@ -1712,6 +1749,11 @@ union bpf_attr { __u32 flags; /* extra flags */ } prog_bind_map; + struct { /* struct used by BPF_TOKEN_CREATE command */ + __u32 flags; + __u32 bpffs_fd; + } token_create; + } __attribute__((aligned(8))); /* The description below is an attempt at providing documentation to eBPF diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 9dc9625651dc..f4e1da3c6d5f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -169,7 +169,7 @@ int bpf_map_create(enum bpf_map_type map_type, __u32 max_entries, const struct bpf_map_create_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, map_extra); + const size_t attr_sz = offsetofend(union bpf_attr, map_token_fd); union bpf_attr attr; int fd; @@ -198,6 +198,8 @@ int bpf_map_create(enum bpf_map_type map_type, attr.numa_node = OPTS_GET(opts, numa_node, 0); attr.map_ifindex = OPTS_GET(opts, map_ifindex, 0); + attr.map_token_fd = OPTS_GET(opts, token_fd, 0); + fd = sys_bpf_fd(BPF_MAP_CREATE, &attr, attr_sz); return libbpf_err_errno(fd); } @@ -232,7 +234,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, size_t insn_cnt, struct bpf_prog_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, prog_token_fd); void *finfo = NULL, *linfo = NULL; const char *func_info, *line_info; __u32 log_size, log_level, attach_prog_fd, attach_btf_obj_fd; @@ -261,6 +263,7 @@ int bpf_prog_load(enum bpf_prog_type prog_type, attr.prog_flags = OPTS_GET(opts, prog_flags, 0); attr.prog_ifindex = OPTS_GET(opts, prog_ifindex, 0); attr.kern_version = OPTS_GET(opts, kern_version, 0); + attr.prog_token_fd = OPTS_GET(opts, token_fd, 0); if (prog_name && kernel_supports(NULL, FEAT_PROG_NAME)) libbpf_strlcpy(attr.prog_name, prog_name, sizeof(attr.prog_name)); @@ -1182,7 +1185,7 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts) { - const size_t attr_sz = offsetofend(union bpf_attr, btf_log_true_size); + const size_t attr_sz = offsetofend(union bpf_attr, btf_token_fd); union bpf_attr attr; char *log_buf; size_t log_size; @@ -1207,6 +1210,8 @@ int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts attr.btf = ptr_to_u64(btf_data); attr.btf_size = btf_size; + attr.btf_token_fd = OPTS_GET(opts, token_fd, 0); + /* log_level == 0 and log_buf != NULL means "try loading without * log_buf, but retry with log_buf and log_level=1 on error", which is * consistent across low-level and high-level BTF and program loading @@ -1287,3 +1292,20 @@ int bpf_prog_bind_map(int prog_fd, int map_fd, ret = sys_bpf(BPF_PROG_BIND_MAP, &attr, attr_sz); return libbpf_err_errno(ret); } + +int bpf_token_create(int bpffs_fd, struct bpf_token_create_opts *opts) +{ + const size_t attr_sz = offsetofend(union bpf_attr, token_create); + union bpf_attr attr; + int fd; + + if (!OPTS_VALID(opts, bpf_token_create_opts)) + return libbpf_err(-EINVAL); + + memset(&attr, 0, attr_sz); + attr.token_create.bpffs_fd = bpffs_fd; + attr.token_create.flags = OPTS_GET(opts, flags, 0); + + fd = sys_bpf_fd(BPF_TOKEN_CREATE, &attr, attr_sz); + return libbpf_err_errno(fd); +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index d0f53772bdc0..991b86bfe7e4 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -51,8 +51,11 @@ struct bpf_map_create_opts { __u32 numa_node; __u32 map_ifindex; + + __u32 token_fd; + size_t :0; }; -#define bpf_map_create_opts__last_field map_ifindex +#define bpf_map_create_opts__last_field token_fd LIBBPF_API int bpf_map_create(enum bpf_map_type map_type, const char *map_name, @@ -102,9 +105,10 @@ struct bpf_prog_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_prog_load_opts__last_field log_true_size +#define bpf_prog_load_opts__last_field token_fd LIBBPF_API int bpf_prog_load(enum bpf_prog_type prog_type, const char *prog_name, const char *license, @@ -130,9 +134,10 @@ struct bpf_btf_load_opts { * If kernel doesn't support this feature, log_size is left unchanged. */ __u32 log_true_size; + __u32 token_fd; size_t :0; }; -#define bpf_btf_load_opts__last_field log_true_size +#define bpf_btf_load_opts__last_field token_fd LIBBPF_API int bpf_btf_load(const void *btf_data, size_t btf_size, struct bpf_btf_load_opts *opts); @@ -640,6 +645,30 @@ struct bpf_test_run_opts { LIBBPF_API int bpf_prog_test_run_opts(int prog_fd, struct bpf_test_run_opts *opts); +struct bpf_token_create_opts { + size_t sz; /* size of this struct for forward/backward compatibility */ + __u32 flags; + size_t :0; +}; +#define bpf_token_create_opts__last_field flags + +/** + * @brief **bpf_token_create()** creates a new instance of BPF token derived + * from specified BPF FS mount point. + * + * BPF token created with this API can be passed to bpf() syscall for + * commands like BPF_PROG_LOAD, BPF_MAP_CREATE, etc. + * + * @param bpffs_fd FD for BPF FS instance from which to derive a BPF token + * instance. + * @param opts optional BPF token creation options, can be NULL + * + * @return BPF token FD > 0, on success; negative error code, otherwise (errno + * is also set to the error code) + */ +LIBBPF_API int bpf_token_create(int bpffs_fd, + struct bpf_token_create_opts *opts); + #ifdef __cplusplus } /* extern "C" */ #endif diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 91c5aef7dae7..df7657b65c47 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -401,6 +401,7 @@ LIBBPF_1.3.0 { bpf_program__attach_netkit; bpf_program__attach_tcx; bpf_program__attach_uprobe_multi; + bpf_token_create; ring__avail_data_size; ring__consume; ring__consumer_pos; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c index 9f766ddd946a..4ed46ed58a7b 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_probes.c @@ -30,6 +30,8 @@ void test_libbpf_probe_prog_types(void) if (prog_type == BPF_PROG_TYPE_UNSPEC) continue; + if (strcmp(prog_type_name, "__MAX_BPF_PROG_TYPE") == 0) + continue; if (!test__start_subtest(prog_type_name)) continue; @@ -68,6 +70,8 @@ void test_libbpf_probe_map_types(void) if (map_type == BPF_MAP_TYPE_UNSPEC) continue; + if (strcmp(map_type_name, "__MAX_BPF_MAP_TYPE") == 0) + continue; if (!test__start_subtest(map_type_name)) continue; diff --git a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c index c440ea3311ed..384bc1f7a65e 100644 --- a/tools/testing/selftests/bpf/prog_tests/libbpf_str.c +++ b/tools/testing/selftests/bpf/prog_tests/libbpf_str.c @@ -132,6 +132,9 @@ static void test_libbpf_bpf_map_type_str(void) const char *map_type_str; char buf[256]; + if (map_type == __MAX_BPF_MAP_TYPE) + continue; + map_type_name = btf__str_by_offset(btf, e->name_off); map_type_str = libbpf_bpf_map_type_str(map_type); ASSERT_OK_PTR(map_type_str, map_type_name); @@ -186,6 +189,9 @@ static void test_libbpf_bpf_prog_type_str(void) const char *prog_type_str; char buf[256]; + if (prog_type == __MAX_BPF_PROG_TYPE) + continue; + prog_type_name = btf__str_by_offset(btf, e->name_off); prog_type_str = libbpf_bpf_prog_type_str(prog_type); ASSERT_OK_PTR(prog_type_str, prog_type_name); diff --git a/tools/testing/selftests/bpf/prog_tests/token.c b/tools/testing/selftests/bpf/prog_tests/token.c new file mode 100644 index 000000000000..dc03790c6272 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/token.c @@ -0,0 +1,672 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#define _GNU_SOURCE +#include <test_progs.h> +#include <bpf/btf.h> +#include "cap_helpers.h" +#include <fcntl.h> +#include <sched.h> +#include <signal.h> +#include <unistd.h> +#include <linux/filter.h> +#include <linux/unistd.h> +#include <linux/mount.h> +#include <sys/socket.h> +#include <sys/syscall.h> +#include <sys/un.h> + +static inline int sys_mount(const char *dev_name, const char *dir_name, + const char *type, unsigned long flags, + const void *data) +{ + return syscall(__NR_mount, dev_name, dir_name, type, flags, data); +} + +static inline int sys_fsopen(const char *fsname, unsigned flags) +{ + return syscall(__NR_fsopen, fsname, flags); +} + +static inline int sys_fspick(int dfd, const char *path, unsigned flags) +{ + return syscall(__NR_fspick, dfd, path, flags); +} + +static inline int sys_fsconfig(int fs_fd, unsigned cmd, const char *key, const void *val, int aux) +{ + return syscall(__NR_fsconfig, fs_fd, cmd, key, val, aux); +} + +static inline int sys_fsmount(int fs_fd, unsigned flags, unsigned ms_flags) +{ + return syscall(__NR_fsmount, fs_fd, flags, ms_flags); +} + +static int drop_priv_caps(__u64 *old_caps) +{ + return cap_disable_effective((1ULL << CAP_BPF) | + (1ULL << CAP_PERFMON) | + (1ULL << CAP_NET_ADMIN) | + (1ULL << CAP_SYS_ADMIN), old_caps); +} + +static int restore_priv_caps(__u64 old_caps) +{ + return cap_enable_effective(old_caps, NULL); +} + +static int set_delegate_mask(int fs_fd, const char *key, __u64 mask) +{ + char buf[32]; + int err; + + snprintf(buf, sizeof(buf), "0x%llx", (unsigned long long)mask); + err = sys_fsconfig(fs_fd, FSCONFIG_SET_STRING, key, + mask == ~0ULL ? "any" : buf, 0); + if (err < 0) + err = -errno; + return err; +} + +#define zclose(fd) do { if (fd >= 0) close(fd); fd = -1; } while (0) + +struct bpffs_opts { + __u64 cmds; + __u64 maps; + __u64 progs; + __u64 attachs; +}; + +static int create_bpffs_fd(void) +{ + int fs_fd; + + /* create VFS context */ + fs_fd = sys_fsopen("bpf", 0); + ASSERT_GE(fs_fd, 0, "fs_fd"); + + return fs_fd; +} + +static int materialize_bpffs_fd(int fs_fd, struct bpffs_opts *opts) +{ + int mnt_fd, err; + + /* set up token delegation mount options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", opts->cmds); + if (!ASSERT_OK(err, "fs_cfg_cmds")) + return err; + err = set_delegate_mask(fs_fd, "delegate_maps", opts->maps); + if (!ASSERT_OK(err, "fs_cfg_maps")) + return err; + err = set_delegate_mask(fs_fd, "delegate_progs", opts->progs); + if (!ASSERT_OK(err, "fs_cfg_progs")) + return err; + err = set_delegate_mask(fs_fd, "delegate_attachs", opts->attachs); + if (!ASSERT_OK(err, "fs_cfg_attachs")) + return err; + + /* instantiate FS object */ + err = sys_fsconfig(fs_fd, FSCONFIG_CMD_CREATE, NULL, NULL, 0); + if (err < 0) + return -errno; + + /* create O_PATH fd for detached mount */ + mnt_fd = sys_fsmount(fs_fd, 0, 0); + if (err < 0) + return -errno; + + return mnt_fd; +} + +/* send FD over Unix domain (AF_UNIX) socket */ +static int sendfd(int sockfd, int fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1] = { fd }, err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(fds)); + memcpy(CMSG_DATA(cmsg), fds, sizeof(fds)); + + err = sendmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "sendmsg")) + return -EINVAL; + + return 0; +} + +/* receive FD over Unix domain (AF_UNIX) socket */ +static int recvfd(int sockfd, int *fd) +{ + struct msghdr msg = {}; + struct cmsghdr *cmsg; + int fds[1], err; + char iobuf[1]; + struct iovec io = { + .iov_base = iobuf, + .iov_len = sizeof(iobuf), + }; + union { + char buf[CMSG_SPACE(sizeof(fds))]; + struct cmsghdr align; + } u; + + msg.msg_iov = &io; + msg.msg_iovlen = 1; + msg.msg_control = u.buf; + msg.msg_controllen = sizeof(u.buf); + + err = recvmsg(sockfd, &msg, 0); + if (err < 0) + err = -errno; + if (!ASSERT_EQ(err, 1, "recvmsg")) + return -EINVAL; + + cmsg = CMSG_FIRSTHDR(&msg); + if (!ASSERT_OK_PTR(cmsg, "cmsg_null") || + !ASSERT_EQ(cmsg->cmsg_len, CMSG_LEN(sizeof(fds)), "cmsg_len") || + !ASSERT_EQ(cmsg->cmsg_level, SOL_SOCKET, "cmsg_level") || + !ASSERT_EQ(cmsg->cmsg_type, SCM_RIGHTS, "cmsg_type")) + return -EINVAL; + + memcpy(fds, CMSG_DATA(cmsg), sizeof(fds)); + *fd = fds[0]; + + return 0; +} + +static ssize_t write_nointr(int fd, const void *buf, size_t count) +{ + ssize_t ret; + + do { + ret = write(fd, buf, count); + } while (ret < 0 && errno == EINTR); + + return ret; +} + +static int write_file(const char *path, const void *buf, size_t count) +{ + int fd; + ssize_t ret; + + fd = open(path, O_WRONLY | O_CLOEXEC | O_NOCTTY | O_NOFOLLOW); + if (fd < 0) + return -1; + + ret = write_nointr(fd, buf, count); + close(fd); + if (ret < 0 || (size_t)ret != count) + return -1; + + return 0; +} + +static int create_and_enter_userns(void) +{ + uid_t uid; + gid_t gid; + char map[100]; + + uid = getuid(); + gid = getgid(); + + if (unshare(CLONE_NEWUSER)) + return -1; + + if (write_file("/proc/self/setgroups", "deny", sizeof("deny") - 1) && + errno != ENOENT) + return -1; + + snprintf(map, sizeof(map), "0 %d 1", uid); + if (write_file("/proc/self/uid_map", map, strlen(map))) + return -1; + + + snprintf(map, sizeof(map), "0 %d 1", gid); + if (write_file("/proc/self/gid_map", map, strlen(map))) + return -1; + + if (setgid(0)) + return -1; + + if (setuid(0)) + return -1; + + return 0; +} + +typedef int (*child_callback_fn)(int); + +static void child(int sock_fd, struct bpffs_opts *opts, child_callback_fn callback) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int mnt_fd = -1, fs_fd = -1, err = 0, bpffs_fd = -1; + + /* setup userns with root mappings */ + err = create_and_enter_userns(); + if (!ASSERT_OK(err, "create_and_enter_userns")) + goto cleanup; + + /* setup mountns to allow creating BPF FS (fsopen("bpf")) from unpriv process */ + err = unshare(CLONE_NEWNS); + if (!ASSERT_OK(err, "create_mountns")) + goto cleanup; + + err = sys_mount(NULL, "/", NULL, MS_REC | MS_PRIVATE, 0); + if (!ASSERT_OK(err, "remount_root")) + goto cleanup; + + fs_fd = create_bpffs_fd(); + if (!ASSERT_GE(fs_fd, 0, "create_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm"); + err = set_delegate_mask(fs_fd, "delegate_maps", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_maps_eperm"); + err = set_delegate_mask(fs_fd, "delegate_progs", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_progs_eperm"); + err = set_delegate_mask(fs_fd, "delegate_attachs", 0x1); + ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm"); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, fs_fd); + if (!ASSERT_OK(err, "send_fs_fd")) + goto cleanup; + zclose(fs_fd); + + /* avoid mucking around with mount namespaces and mounting at + * well-known path, just get detach-mounted BPF FS fd back from parent + */ + err = recvfd(sock_fd, &mnt_fd); + if (!ASSERT_OK(err, "recv_mnt_fd")) + goto cleanup; + + /* try to fspick() BPF FS and try to add some delegation options */ + fs_fd = sys_fspick(mnt_fd, "", FSPICK_EMPTY_PATH); + if (!ASSERT_GE(fs_fd, 0, "bpffs_fspick")) { + err = -EINVAL; + goto cleanup; + } + + /* ensure unprivileged child cannot reconfigure to set delegation options */ + err = set_delegate_mask(fs_fd, "delegate_cmds", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_cmd_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_maps", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_maps_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_progs", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_progs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + err = set_delegate_mask(fs_fd, "delegate_attachs", ~0ULL); + if (!ASSERT_EQ(err, -EPERM, "delegate_attachs_eperm_reconfig")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + bpffs_fd = openat(mnt_fd, ".", 0, O_RDWR); + if (!ASSERT_GE(bpffs_fd, 0, "bpffs_open")) { + err = -EINVAL; + goto cleanup; + } + + /* do custom test logic with customly set up BPF FS instance */ + err = callback(bpffs_fd); + if (!ASSERT_OK(err, "test_callback")) + goto cleanup; + + err = 0; +cleanup: + zclose(sock_fd); + zclose(mnt_fd); + zclose(fs_fd); + zclose(bpffs_fd); + + exit(-err); +} + +static int wait_for_pid(pid_t pid) +{ + int status, ret; + +again: + ret = waitpid(pid, &status, 0); + if (ret == -1) { + if (errno == EINTR) + goto again; + + return -1; + } + + if (!WIFEXITED(status)) + return -1; + + return WEXITSTATUS(status); +} + +static void parent(int child_pid, struct bpffs_opts *bpffs_opts, int sock_fd) +{ + int fs_fd = -1, mnt_fd = -1, err; + + err = recvfd(sock_fd, &fs_fd); + if (!ASSERT_OK(err, "recv_bpffs_fd")) + goto cleanup; + + mnt_fd = materialize_bpffs_fd(fs_fd, bpffs_opts); + if (!ASSERT_GE(mnt_fd, 0, "materialize_bpffs_fd")) { + err = -EINVAL; + goto cleanup; + } + zclose(fs_fd); + + /* pass BPF FS context object to parent */ + err = sendfd(sock_fd, mnt_fd); + if (!ASSERT_OK(err, "send_mnt_fd")) + goto cleanup; + zclose(mnt_fd); + + err = wait_for_pid(child_pid); + ASSERT_OK(err, "waitpid_child"); + +cleanup: + zclose(sock_fd); + zclose(fs_fd); + zclose(mnt_fd); + + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static void subtest_userns(struct bpffs_opts *bpffs_opts, child_callback_fn cb) +{ + int sock_fds[2] = { -1, -1 }; + int child_pid = 0, err; + + err = socketpair(AF_UNIX, SOCK_STREAM, 0, sock_fds); + if (!ASSERT_OK(err, "socketpair")) + goto cleanup; + + child_pid = fork(); + if (!ASSERT_GE(child_pid, 0, "fork")) + goto cleanup; + + if (child_pid == 0) { + zclose(sock_fds[0]); + return child(sock_fds[1], bpffs_opts, cb); + + } else { + zclose(sock_fds[1]); + return parent(child_pid, bpffs_opts, sock_fds[0]); + } + +cleanup: + zclose(sock_fds[0]); + zclose(sock_fds[1]); + if (child_pid > 0) + (void)kill(child_pid, SIGKILL); +} + +static int userns_map_create(int mnt_fd) +{ + LIBBPF_OPTS(bpf_map_create_opts, map_opts); + int err, token_fd = -1, map_fd = -1; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no token, no CAP_BPF -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* token without CAP_BPF -> fail */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_wo_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_w_token_wo_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* CAP_BPF without token -> fail */ + map_opts.token_fd = 0; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "wo_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_LT(map_fd, 0, "stack_map_wo_token_w_cap_bpf_should_fail")) { + err = -EINVAL; + goto cleanup; + } + + /* finally, namespaced CAP_BPF + token -> success */ + map_opts.token_fd = token_fd; + map_fd = bpf_map_create(BPF_MAP_TYPE_STACK, "w_token_w_bpf", 0, 8, 1, &map_opts); + if (!ASSERT_GT(map_fd, 0, "stack_map_w_token_w_cap_bpf")) { + err = -EINVAL; + goto cleanup; + } + +cleanup: + zclose(token_fd); + zclose(map_fd); + return err; +} + +static int userns_btf_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_btf_load_opts, btf_opts); + int err, token_fd = -1, btf_fd = -1; + const void *raw_btf_data; + struct btf *btf = NULL; + __u32 raw_btf_size; + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* while inside non-init userns, we need both a BPF token *and* + * CAP_BPF inside current userns to create privileged map; let's test + * that neither BPF token alone nor namespaced CAP_BPF is sufficient + */ + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* setup a trivial BTF data to load to the kernel */ + btf = btf__new_empty(); + if (!ASSERT_OK_PTR(btf, "empty_btf")) + goto cleanup; + + ASSERT_GT(btf__add_int(btf, "int", 4, 0), 0, "int_type"); + + raw_btf_data = btf__raw_data(btf, &raw_btf_size); + if (!ASSERT_OK_PTR(raw_btf_data, "raw_btf_data")) + goto cleanup; + + /* no token + no CAP_BPF -> failure */ + btf_opts.token_fd = 0; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "no_token_no_cap_should_fail")) + goto cleanup; + + /* token + no CAP_BPF -> failure */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_LT(btf_fd, 0, "token_no_cap_should_fail")) + goto cleanup; + + /* get back effective local CAP_BPF (and CAP_SYS_ADMIN) */ + err = restore_priv_caps(old_caps); + if (!ASSERT_OK(err, "restore_caps")) + goto cleanup; + + /* token + CAP_BPF -> success */ + btf_opts.token_fd = token_fd; + btf_fd = bpf_btf_load(raw_btf_data, raw_btf_size, &btf_opts); + if (!ASSERT_GT(btf_fd, 0, "token_and_cap_success")) + goto cleanup; + + err = 0; +cleanup: + btf__free(btf); + zclose(btf_fd); + zclose(token_fd); + return err; +} + +static int userns_prog_load(int mnt_fd) +{ + LIBBPF_OPTS(bpf_prog_load_opts, prog_opts); + int err, token_fd = -1, prog_fd = -1; + struct bpf_insn insns[] = { + /* bpf_jiffies64() requires CAP_BPF */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_jiffies64), + /* bpf_get_current_task() requires CAP_PERFMON */ + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_current_task), + /* r0 = 0; exit; */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }; + size_t insn_cnt = ARRAY_SIZE(insns); + __u64 old_caps = 0; + + /* create BPF token from BPF FS mount */ + token_fd = bpf_token_create(mnt_fd, NULL); + if (!ASSERT_GT(token_fd, 0, "token_create")) { + err = -EINVAL; + goto cleanup; + } + + /* validate we can successfully load BPF program with token; this + * being XDP program (CAP_NET_ADMIN) using bpf_jiffies64() (CAP_BPF) + * and bpf_get_current_task() (CAP_PERFMON) helpers validates we have + * BPF token wired properly in a bunch of places in the kernel + */ + prog_opts.token_fd = token_fd; + prog_opts.expected_attach_type = BPF_XDP; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_GT(prog_fd, 0, "prog_fd")) { + err = -EPERM; + goto cleanup; + } + + /* no token + caps -> failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = drop_priv_caps(&old_caps); + if (!ASSERT_OK(err, "drop_caps")) + goto cleanup; + + /* no caps + token -> failure */ + prog_opts.token_fd = token_fd; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + /* no caps + no token -> definitely a failure */ + prog_opts.token_fd = 0; + prog_fd = bpf_prog_load(BPF_PROG_TYPE_XDP, "token_prog", "GPL", + insns, insn_cnt, &prog_opts); + if (!ASSERT_EQ(prog_fd, -EPERM, "prog_fd_eperm")) { + err = -EPERM; + goto cleanup; + } + + err = 0; +cleanup: + zclose(prog_fd); + zclose(token_fd); + return err; +} + +void test_token(void) +{ + if (test__start_subtest("map_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_MAP_CREATE, + .maps = 1ULL << BPF_MAP_TYPE_STACK, + }; + + subtest_userns(&opts, userns_map_create); + } + if (test__start_subtest("btf_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_BTF_LOAD, + }; + + subtest_userns(&opts, userns_btf_load); + } + if (test__start_subtest("prog_token")) { + struct bpffs_opts opts = { + .cmds = 1ULL << BPF_PROG_LOAD, + .progs = 1ULL << BPF_PROG_TYPE_XDP, + .attachs = 1ULL << BPF_XDP, + }; + + subtest_userns(&opts, userns_prog_load); + } +} |