aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/linux/bpf.h4
-rw-r--r--include/linux/bpf_verifier.h5
-rw-r--r--include/linux/compiler_types.h3
-rw-r--r--kernel/bpf/bpf_lsm.c6
-rw-r--r--kernel/bpf/btf.c3
-rw-r--r--kernel/bpf/helpers.c14
-rw-r--r--kernel/bpf/verifier.c167
-rw-r--r--kernel/trace/bpf_trace.c4
-rw-r--r--tools/testing/selftests/bpf/DENYLIST.aarch641
-rw-r--r--tools/testing/selftests/bpf/DENYLIST.s390x1
-rw-r--r--tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c158
-rw-r--r--tools/testing/selftests/bpf/progs/rcu_read_lock.c290
12 files changed, 621 insertions, 35 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c9eafa67f2a2..c6aa6912ea16 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -572,6 +572,9 @@ enum bpf_type_flag {
*/
PTR_TRUSTED = BIT(12 + BPF_BASE_TYPE_BITS),
+ /* MEM is tagged with rcu and memory access needs rcu_read_lock protection. */
+ MEM_RCU = BIT(13 + BPF_BASE_TYPE_BITS),
+
__BPF_TYPE_FLAG_MAX,
__BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
};
@@ -682,6 +685,7 @@ struct bpf_func_proto {
u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
bool gpl_only;
bool pkt_access;
+ bool might_sleep;
enum bpf_return_type ret_type;
union {
struct {
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 545152ac136c..c05aa6e1f6f5 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -344,6 +344,7 @@ struct bpf_verifier_state {
u32 id;
} active_lock;
bool speculative;
+ bool active_rcu_lock;
/* first and last insn idx of this verifier state */
u32 first_insn_idx;
@@ -445,6 +446,7 @@ struct bpf_insn_aux_data {
u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
bool zext_dst; /* this insn zero extends dst reg */
+ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
u8 alu_state; /* used in combination with alu_limit */
/* below fields are initialized once */
@@ -534,6 +536,7 @@ struct bpf_verifier_env {
bool bypass_spec_v1;
bool bypass_spec_v4;
bool seen_direct_write;
+ bool rcu_tag_supported;
struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
const struct bpf_line_info *prev_linfo;
struct bpf_verifier_log log;
@@ -680,7 +683,7 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
}
}
-#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED)
+#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | MEM_RCU | PTR_TRUSTED)
static inline bool bpf_type_has_unsafe_modifiers(u32 type)
{
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index eb0466236661..7c1afe0f4129 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -49,7 +49,8 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
# endif
# define __iomem
# define __percpu BTF_TYPE_TAG(percpu)
-# define __rcu
+# define __rcu BTF_TYPE_TAG(rcu)
+
# define __chk_user_ptr(x) (void)0
# define __chk_io_ptr(x) (void)0
/* context/locking */
diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
index d6c9b3705f24..ae0267f150b5 100644
--- a/kernel/bpf/bpf_lsm.c
+++ b/kernel/bpf/bpf_lsm.c
@@ -151,6 +151,7 @@ BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode)
static const struct bpf_func_proto bpf_ima_inode_hash_proto = {
.func = bpf_ima_inode_hash,
.gpl_only = false,
+ .might_sleep = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0],
@@ -169,6 +170,7 @@ BTF_ID_LIST_SINGLE(bpf_ima_file_hash_btf_ids, struct, file)
static const struct bpf_func_proto bpf_ima_file_hash_proto = {
.func = bpf_ima_file_hash,
.gpl_only = false,
+ .might_sleep = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
.arg1_btf_id = &bpf_ima_file_hash_btf_ids[0],
@@ -221,9 +223,9 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_bprm_opts_set:
return &bpf_bprm_opts_set_proto;
case BPF_FUNC_ima_inode_hash:
- return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL;
+ return &bpf_ima_inode_hash_proto;
case BPF_FUNC_ima_file_hash:
- return prog->aux->sleepable ? &bpf_ima_file_hash_proto : NULL;
+ return &bpf_ima_file_hash_proto;
case BPF_FUNC_get_attach_cookie:
return bpf_prog_has_trampoline(prog) ? &bpf_get_attach_cookie_proto : NULL;
#ifdef CONFIG_NET
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9dbfda2b5c6c..bd3369100239 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6238,6 +6238,9 @@ error:
/* check __percpu tag */
if (strcmp(tag_value, "percpu") == 0)
tmp_flag = MEM_PERCPU;
+ /* check __rcu tag */
+ if (strcmp(tag_value, "rcu") == 0)
+ tmp_flag = MEM_RCU;
}
stype = btf_type_skip_modifiers(btf, mtype->type, &id);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 2299bb0d89e5..a5a511430f2a 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -661,6 +661,7 @@ BPF_CALL_3(bpf_copy_from_user, void *, dst, u32, size,
const struct bpf_func_proto bpf_copy_from_user_proto = {
.func = bpf_copy_from_user,
.gpl_only = false,
+ .might_sleep = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
@@ -691,6 +692,7 @@ BPF_CALL_5(bpf_copy_from_user_task, void *, dst, u32, size,
const struct bpf_func_proto bpf_copy_from_user_task_proto = {
.func = bpf_copy_from_user_task,
.gpl_only = true,
+ .might_sleep = true,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_UNINIT_MEM,
.arg2_type = ARG_CONST_SIZE_OR_ZERO,
@@ -1988,6 +1990,16 @@ void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k)
return obj__ign;
}
+void bpf_rcu_read_lock(void)
+{
+ rcu_read_lock();
+}
+
+void bpf_rcu_read_unlock(void)
+{
+ rcu_read_unlock();
+}
+
__diag_pop();
BTF_SET8_START(generic_btf_ids)
@@ -2029,6 +2041,8 @@ BTF_ID(func, bpf_cgroup_release)
BTF_SET8_START(common_btf_ids)
BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx)
BTF_ID_FLAGS(func, bpf_rdonly_cast)
+BTF_ID_FLAGS(func, bpf_rcu_read_lock)
+BTF_ID_FLAGS(func, bpf_rcu_read_unlock)
BTF_SET8_END(common_btf_ids)
static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9528a066cfa5..f4500479f1c2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -527,6 +527,14 @@ static bool is_callback_calling_function(enum bpf_func_id func_id)
func_id == BPF_FUNC_user_ringbuf_drain;
}
+static bool is_storage_get_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_sk_storage_get ||
+ func_id == BPF_FUNC_inode_storage_get ||
+ func_id == BPF_FUNC_task_storage_get ||
+ func_id == BPF_FUNC_cgrp_storage_get;
+}
+
static bool helper_multiple_ref_obj_use(enum bpf_func_id func_id,
const struct bpf_map *map)
{
@@ -589,11 +597,12 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
strncpy(postfix, "_or_null", 16);
}
- snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s",
+ snprintf(prefix, sizeof(prefix), "%s%s%s%s%s%s%s",
type & MEM_RDONLY ? "rdonly_" : "",
type & MEM_RINGBUF ? "ringbuf_" : "",
type & MEM_USER ? "user_" : "",
type & MEM_PERCPU ? "percpu_" : "",
+ type & MEM_RCU ? "rcu_" : "",
type & PTR_UNTRUSTED ? "untrusted_" : "",
type & PTR_TRUSTED ? "trusted_" : ""
);
@@ -1220,6 +1229,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
dst_state->frame[i] = NULL;
}
dst_state->speculative = src->speculative;
+ dst_state->active_rcu_lock = src->active_rcu_lock;
dst_state->curframe = src->curframe;
dst_state->active_lock.ptr = src->active_lock.ptr;
dst_state->active_lock.id = src->active_lock.id;
@@ -4258,6 +4268,25 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
return reg->type == PTR_TO_FLOW_KEYS;
}
+static bool is_trusted_reg(const struct bpf_reg_state *reg)
+{
+ /* A referenced register is always trusted. */
+ if (reg->ref_obj_id)
+ return true;
+
+ /* If a register is not referenced, it is trusted if it has the
+ * MEM_ALLOC, MEM_RCU or PTR_TRUSTED type modifiers, and no others. Some of the
+ * other type modifiers may be safe, but we elect to take an opt-in
+ * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are
+ * not.
+ *
+ * Eventually, we should make PTR_TRUSTED the single source of truth
+ * for whether a register is trusted.
+ */
+ return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS &&
+ !bpf_type_has_unsafe_modifiers(reg->type);
+}
+
static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
const struct bpf_reg_state *reg,
int off, int size, bool strict)
@@ -4737,9 +4766,28 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
if (type_flag(reg->type) & PTR_UNTRUSTED)
flag |= PTR_UNTRUSTED;
- /* Any pointer obtained from walking a trusted pointer is no longer trusted. */
+ /* By default any pointer obtained from walking a trusted pointer is
+ * no longer trusted except the rcu case below.
+ */
flag &= ~PTR_TRUSTED;
+ if (flag & MEM_RCU) {
+ /* Mark value register as MEM_RCU only if it is protected by
+ * bpf_rcu_read_lock() and the ptr reg is trusted. MEM_RCU
+ * itself can already indicate trustedness inside the rcu
+ * read lock region. Also mark it as PTR_TRUSTED.
+ */
+ if (!env->cur_state->active_rcu_lock || !is_trusted_reg(reg))
+ flag &= ~MEM_RCU;
+ else
+ flag |= PTR_TRUSTED;
+ } else if (reg->type & MEM_RCU) {
+ /* ptr (reg) is marked as MEM_RCU, but the struct field is not tagged
+ * with __rcu. Mark the flag as PTR_UNTRUSTED conservatively.
+ */
+ flag |= PTR_UNTRUSTED;
+ }
+
if (atype == BPF_READ && value_regno >= 0)
mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
@@ -5897,6 +5945,7 @@ static const struct bpf_reg_types btf_ptr_types = {
.types = {
PTR_TO_BTF_ID,
PTR_TO_BTF_ID | PTR_TRUSTED,
+ PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED,
},
};
static const struct bpf_reg_types percpu_btf_ptr_types = {
@@ -6075,6 +6124,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
case PTR_TO_BTF_ID:
case PTR_TO_BTF_ID | MEM_ALLOC:
case PTR_TO_BTF_ID | PTR_TRUSTED:
+ case PTR_TO_BTF_ID | MEM_RCU | PTR_TRUSTED:
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_TRUSTED:
/* When referenced PTR_TO_BTF_ID is passed to release function,
* it's fixed offset must be 0. In the other cases, fixed offset
@@ -7516,6 +7566,11 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EINVAL;
}
+ if (!env->prog->aux->sleepable && fn->might_sleep) {
+ verbose(env, "helper call might sleep in a non-sleepable prog\n");
+ return -EINVAL;
+ }
+
/* With LD_ABS/IND some JITs save/restore skb from r1. */
changes_data = bpf_helper_changes_pkt_data(fn->func);
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
@@ -7534,6 +7589,17 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return err;
}
+ if (env->cur_state->active_rcu_lock) {
+ if (fn->might_sleep) {
+ verbose(env, "sleepable helper %s#%d in rcu_read_lock region\n",
+ func_id_name(func_id), func_id);
+ return -EINVAL;
+ }
+
+ if (env->prog->aux->sleepable && is_storage_get_function(func_id))
+ env->insn_aux_data[insn_idx].storage_get_func_atomic = true;
+ }
+
meta.func_id = func_id;
/* check args */
for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
@@ -7961,25 +8027,6 @@ static bool is_kfunc_arg_kptr_get(struct bpf_kfunc_call_arg_meta *meta, int arg)
return arg == 0 && (meta->kfunc_flags & KF_KPTR_GET);
}
-static bool is_trusted_reg(const struct bpf_reg_state *reg)
-{
- /* A referenced register is always trusted. */
- if (reg->ref_obj_id)
- return true;
-
- /* If a register is not referenced, it is trusted if it has either the
- * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the
- * other type modifiers may be safe, but we elect to take an opt-in
- * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are
- * not.
- *
- * Eventually, we should make PTR_TRUSTED the single source of truth
- * for whether a register is trusted.
- */
- return type_flag(reg->type) & BPF_REG_TRUSTED_MODIFIERS &&
- !bpf_type_has_unsafe_modifiers(reg->type);
-}
-
static bool __kfunc_param_match_suffix(const struct btf *btf,
const struct btf_param *arg,
const char *suffix)
@@ -8158,6 +8205,8 @@ enum special_kfunc_type {
KF_bpf_list_pop_back,
KF_bpf_cast_to_kern_ctx,
KF_bpf_rdonly_cast,
+ KF_bpf_rcu_read_lock,
+ KF_bpf_rcu_read_unlock,
};
BTF_SET_START(special_kfunc_set)
@@ -8180,6 +8229,18 @@ BTF_ID(func, bpf_list_pop_front)
BTF_ID(func, bpf_list_pop_back)
BTF_ID(func, bpf_cast_to_kern_ctx)
BTF_ID(func, bpf_rdonly_cast)
+BTF_ID(func, bpf_rcu_read_lock)
+BTF_ID(func, bpf_rcu_read_unlock)
+
+static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta)
+{
+ return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_lock];
+}
+
+static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_kfunc_call_arg_meta *meta)
+{
+ return meta->func_id == special_kfunc_list[KF_bpf_rcu_read_unlock];
+}
static enum kfunc_ptr_arg_type
get_kfunc_ptr_arg_type(struct bpf_verifier_env *env,
@@ -8812,6 +8873,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
const struct btf_type *t, *func, *func_proto, *ptr_type;
struct bpf_reg_state *regs = cur_regs(env);
const char *func_name, *ptr_type_name;
+ bool sleepable, rcu_lock, rcu_unlock;
struct bpf_kfunc_call_arg_meta meta;
u32 i, nargs, func_id, ptr_type_id;
int err, insn_idx = *insn_idx_p;
@@ -8853,11 +8915,45 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
return -EACCES;
}
- if (is_kfunc_sleepable(&meta) && !env->prog->aux->sleepable) {
+ sleepable = is_kfunc_sleepable(&meta);
+ if (sleepable && !env->prog->aux->sleepable) {
verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name);
return -EACCES;
}
+ rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
+ rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);
+ if ((rcu_lock || rcu_unlock) && !env->rcu_tag_supported) {
+ verbose(env, "no vmlinux btf rcu tag support for kfunc %s\n", func_name);
+ return -EACCES;
+ }
+
+ if (env->cur_state->active_rcu_lock) {
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ if (rcu_lock) {
+ verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
+ return -EINVAL;
+ } else if (rcu_unlock) {
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg->type & MEM_RCU) {
+ reg->type &= ~(MEM_RCU | PTR_TRUSTED);
+ reg->type |= PTR_UNTRUSTED;
+ }
+ }));
+ env->cur_state->active_rcu_lock = false;
+ } else if (sleepable) {
+ verbose(env, "kernel func %s is sleepable within rcu_read_lock region\n", func_name);
+ return -EACCES;
+ }
+ } else if (rcu_lock) {
+ env->cur_state->active_rcu_lock = true;
+ } else if (rcu_unlock) {
+ verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name);
+ return -EINVAL;
+ }
+
/* Check the arguments */
err = check_kfunc_args(env, &meta);
if (err < 0)
@@ -11749,6 +11845,11 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
return -EINVAL;
}
+ if (env->cur_state->active_rcu_lock) {
+ verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_rcu_read_lock-ed region\n");
+ return -EINVAL;
+ }
+
if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
@@ -13014,6 +13115,9 @@ static bool states_equal(struct bpf_verifier_env *env,
old->active_lock.id != cur->active_lock.id)
return false;
+ if (old->active_rcu_lock != cur->active_rcu_lock)
+ return false;
+
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
@@ -13701,6 +13805,11 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
+ if (env->cur_state->active_rcu_lock) {
+ verbose(env, "bpf_rcu_read_unlock is missing\n");
+ return -EINVAL;
+ }
+
/* We must do check_reference_leak here before
* prepare_func_exit to handle the case when
* state->curframe > 0, it may be a callback
@@ -15489,14 +15598,12 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
goto patch_call_imm;
}
- if (insn->imm == BPF_FUNC_task_storage_get ||
- insn->imm == BPF_FUNC_sk_storage_get ||
- insn->imm == BPF_FUNC_inode_storage_get ||
- insn->imm == BPF_FUNC_cgrp_storage_get) {
- if (env->prog->aux->sleepable)
- insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL);
- else
+ if (is_storage_get_function(insn->imm)) {
+ if (!env->prog->aux->sleepable ||
+ env->insn_aux_data[i + delta].storage_get_func_atomic)
insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC);
+ else
+ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL);
insn_buf[1] = *insn;
cnt = 2;
@@ -16575,6 +16682,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr)
env->bypass_spec_v1 = bpf_bypass_spec_v1();
env->bypass_spec_v4 = bpf_bypass_spec_v4();
env->bpf_capable = bpf_capable();
+ env->rcu_tag_supported = btf_vmlinux &&
+ btf_find_by_name_kind(btf_vmlinux, "rcu", BTF_KIND_TYPE_TAG) > 0;
if (is_priv)
env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 5b9008bc597b..3bbd3f0c810c 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -1485,9 +1485,9 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
case BPF_FUNC_get_task_stack:
return &bpf_get_task_stack_proto;
case BPF_FUNC_copy_from_user:
- return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+ return &bpf_copy_from_user_proto;
case BPF_FUNC_copy_from_user_task:
- return prog->aux->sleepable ? &bpf_copy_from_user_task_proto : NULL;
+ return &bpf_copy_from_user_task_proto;
case BPF_FUNC_snprintf_btf:
return &bpf_snprintf_btf_proto;
case BPF_FUNC_per_cpu_ptr:
diff --git a/tools/testing/selftests/bpf/DENYLIST.aarch64 b/tools/testing/selftests/bpf/DENYLIST.aarch64
index affc5aebbf0f..8e77515d56f6 100644
--- a/tools/testing/selftests/bpf/DENYLIST.aarch64
+++ b/tools/testing/selftests/bpf/DENYLIST.aarch64
@@ -45,6 +45,7 @@ modify_return # modify_return__attach failed
module_attach # skel_attach skeleton attach failed: -524
mptcp/base # run_test mptcp unexpected error: -524 (errno 524)
netcnt # packets unexpected packets: actual 10001 != expected 10000
+rcu_read_lock # failed to attach: ERROR: strerror_r(-524)=22
recursion # skel_attach unexpected error: -524 (errno 524)
ringbuf # skel_attach skeleton attachment failed: -1
setget_sockopt # attach_cgroup unexpected error: -524
diff --git a/tools/testing/selftests/bpf/DENYLIST.s390x b/tools/testing/selftests/bpf/DENYLIST.s390x
index b9a3d80204c6..648a8a1b6b78 100644
--- a/tools/testing/selftests/bpf/DENYLIST.s390x
+++ b/tools/testing/selftests/bpf/DENYLIST.s390x
@@ -43,6 +43,7 @@ module_attach # skel_attach skeleton attach failed: -
mptcp
netcnt # failed to load BPF skeleton 'netcnt_prog': -7 (?)
probe_user # check_kprobe_res wrong kprobe res from probe read (?)
+rcu_read_lock # failed to find kernel BTF type ID of '__x64_sys_getpgid': -3 (?)
recursion # skel_attach unexpected error: -524 (trampoline)
ringbuf # skel_load skeleton load failed (?)
select_reuseport # intermittently fails on new s390x setup
diff --git a/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
new file mode 100644
index 000000000000..447d8560ecb6
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/rcu_read_lock.c
@@ -0,0 +1,158 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates.*/
+
+#define _GNU_SOURCE
+#include <unistd.h>
+#include <sys/syscall.h>
+#include <sys/types.h>
+#include <test_progs.h>
+#include <bpf/btf.h>
+#include "rcu_read_lock.skel.h"
+#include "cgroup_helpers.h"
+
+static unsigned long long cgroup_id;
+
+static void test_success(void)
+{
+ struct rcu_read_lock *skel;
+ int err;
+
+ skel = rcu_read_lock__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->target_pid = syscall(SYS_gettid);
+
+ bpf_program__set_autoload(skel->progs.get_cgroup_id, true);
+ bpf_program__set_autoload(skel->progs.task_succ, true);
+ bpf_program__set_autoload(skel->progs.no_lock, true);
+ bpf_program__set_autoload(skel->progs.two_regions, true);
+ bpf_program__set_autoload(skel->progs.non_sleepable_1, true);
+ bpf_program__set_autoload(skel->progs.non_sleepable_2, true);
+ err = rcu_read_lock__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto out;
+
+ err = rcu_read_lock__attach(skel);
+ if (!ASSERT_OK(err, "skel_attach"))
+ goto out;
+
+ syscall(SYS_getpgid);
+
+ ASSERT_EQ(skel->bss->task_storage_val, 2, "task_storage_val");
+ ASSERT_EQ(skel->bss->cgroup_id, cgroup_id, "cgroup_id");
+out:
+ rcu_read_lock__destroy(skel);
+}
+
+static void test_rcuptr_acquire(void)
+{
+ struct rcu_read_lock *skel;
+ int err;
+
+ skel = rcu_read_lock__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ skel->bss->target_pid = syscall(SYS_gettid);
+
+ bpf_program__set_autoload(skel->progs.task_acquire, true);
+ err = rcu_read_lock__load(skel);
+ if (!ASSERT_OK(err, "skel_load"))
+ goto out;
+
+ err = rcu_read_lock__attach(skel);
+ ASSERT_OK(err, "skel_attach");
+out:
+ rcu_read_lock__destroy(skel);
+}
+
+static const char * const inproper_region_tests[] = {
+ "miss_lock",
+ "miss_unlock",
+ "non_sleepable_rcu_mismatch",
+ "inproper_sleepable_helper",
+ "inproper_sleepable_kfunc",
+ "nested_rcu_region",
+};
+
+static void test_inproper_region(void)
+{
+ struct rcu_read_lock *skel;
+ struct bpf_program *prog;
+ int i, err;
+
+ for (i = 0; i < ARRAY_SIZE(inproper_region_tests); i++) {
+ skel = rcu_read_lock__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ prog = bpf_object__find_program_by_name(skel->obj, inproper_region_tests[i]);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto out;
+ bpf_program__set_autoload(prog, true);
+ err = rcu_read_lock__load(skel);
+ ASSERT_ERR(err, "skel_load");
+out:
+ rcu_read_lock__destroy(skel);
+ }
+}
+
+static const char * const rcuptr_misuse_tests[] = {
+ "task_untrusted_non_rcuptr",
+ "task_untrusted_rcuptr",
+ "cross_rcu_region",
+};
+
+static void test_rcuptr_misuse(void)
+{
+ struct rcu_read_lock *skel;
+ struct bpf_program *prog;
+ int i, err;
+
+ for (i = 0; i < ARRAY_SIZE(rcuptr_misuse_tests); i++) {
+ skel = rcu_read_lock__open();
+ if (!ASSERT_OK_PTR(skel, "skel_open"))
+ return;
+
+ prog = bpf_object__find_program_by_name(skel->obj, rcuptr_misuse_tests[i]);
+ if (!ASSERT_OK_PTR(prog, "bpf_object__find_program_by_name"))
+ goto out;
+ bpf_program__set_autoload(prog, true);
+ err = rcu_read_lock__load(skel);
+ ASSERT_ERR(err, "skel_load");
+out:
+ rcu_read_lock__destroy(skel);
+ }
+}
+
+void test_rcu_read_lock(void)
+{
+ struct btf *vmlinux_btf;
+ int cgroup_fd;
+
+ vmlinux_btf = btf__load_vmlinux_btf();
+ if (!ASSERT_OK_PTR(vmlinux_btf, "could not load vmlinux BTF"))
+ return;
+ if (btf__find_by_name_kind(vmlinux_btf, "rcu", BTF_KIND_TYPE_TAG) < 0) {
+ test__skip();
+ goto out;
+ }
+
+ cgroup_fd = test__join_cgroup("/rcu_read_lock");
+ if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /rcu_read_lock"))
+ goto out;
+
+ cgroup_id = get_cgroup_id("/rcu_read_lock");
+ if (test__start_subtest("success"))
+ test_success();
+ if (test__start_subtest("rcuptr_acquire"))
+ test_rcuptr_acquire();
+ if (test__start_subtest("negative_tests_inproper_region"))
+ test_inproper_region();
+ if (test__start_subtest("negative_tests_rcuptr_misuse"))
+ test_rcuptr_misuse();
+ close(cgroup_fd);
+out:
+ btf__free(vmlinux_btf);
+}
diff --git a/tools/testing/selftests/bpf/progs/rcu_read_lock.c b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
new file mode 100644
index 000000000000..94a970076b98
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/rcu_read_lock.c
@@ -0,0 +1,290 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_tracing_net.h"
+#include "bpf_misc.h"
+
+char _license[] SEC("license") = "GPL";
+
+struct {
+ __uint(type, BPF_MAP_TYPE_TASK_STORAGE);
+ __uint(map_flags, BPF_F_NO_PREALLOC);
+ __type(key, int);
+ __type(value, long);
+} map_a SEC(".maps");
+
+__u32 user_data, key_serial, target_pid;
+__u64 flags, task_storage_val, cgroup_id;
+
+struct bpf_key *bpf_lookup_user_key(__u32 serial, __u64 flags) __ksym;
+void bpf_key_put(struct bpf_key *key) __ksym;
+void bpf_rcu_read_lock(void) __ksym;
+void bpf_rcu_read_unlock(void) __ksym;
+struct task_struct *bpf_task_acquire(struct task_struct *p) __ksym;
+void bpf_task_release(struct task_struct *p) __ksym;
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int get_cgroup_id(void *ctx)
+{
+ struct task_struct *task;
+
+ task = bpf_get_current_task_btf();
+ if (task->pid != target_pid)
+ return 0;
+
+ /* simulate bpf_get_current_cgroup_id() helper */
+ bpf_rcu_read_lock();
+ cgroup_id = task->cgroups->dfl_cgrp->kn->id;
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int task_succ(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+ long init_val = 2;
+ long *ptr;
+
+ task = bpf_get_current_task_btf();
+ if (task->pid != target_pid)
+ return 0;
+
+ bpf_rcu_read_lock();
+ /* region including helper using rcu ptr real_parent */
+ real_parent = task->real_parent;
+ ptr = bpf_task_storage_get(&map_a, real_parent, &init_val,
+ BPF_LOCAL_STORAGE_GET_F_CREATE);
+ if (!ptr)
+ goto out;
+ ptr = bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ if (!ptr)
+ goto out;
+ task_storage_val = *ptr;
+out:
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int no_lock(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ /* no bpf_rcu_read_lock(), old code still works */
+ task = bpf_get_current_task_btf();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int two_regions(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ /* two regions */
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ bpf_rcu_read_unlock();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+int non_sleepable_1(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+int non_sleepable_2(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ bpf_rcu_read_lock();
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_unlock();
+
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int task_acquire(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ /* acquire a reference which can be used outside rcu read lock region */
+ real_parent = bpf_task_acquire(real_parent);
+ bpf_rcu_read_unlock();
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_task_release(real_parent);
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int miss_lock(void *ctx)
+{
+ struct task_struct *task;
+ struct css_set *cgroups;
+ struct cgroup *dfl_cgrp;
+
+ /* missing bpf_rcu_read_lock() */
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ (void)bpf_task_storage_get(&map_a, task, 0, 0);
+ bpf_rcu_read_unlock();
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int miss_unlock(void *ctx)
+{
+ struct task_struct *task;
+ struct css_set *cgroups;
+ struct cgroup *dfl_cgrp;
+
+ /* missing bpf_rcu_read_unlock() */
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ (void)bpf_task_storage_get(&map_a, task, 0, 0);
+ return 0;
+}
+
+SEC("?fentry/" SYS_PREFIX "sys_getpgid")
+int non_sleepable_rcu_mismatch(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ task = bpf_get_current_task_btf();
+ /* non-sleepable: missing bpf_rcu_read_unlock() in one path */
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ if (real_parent)
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int inproper_sleepable_helper(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+ struct pt_regs *regs;
+ __u32 value = 0;
+ void *ptr;
+
+ task = bpf_get_current_task_btf();
+ /* sleepable helper in rcu read lock region */
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ regs = (struct pt_regs *)bpf_task_pt_regs(real_parent);
+ if (!regs) {
+ bpf_rcu_read_unlock();
+ return 0;
+ }
+
+ ptr = (void *)PT_REGS_IP(regs);
+ (void)bpf_copy_from_user_task(&value, sizeof(uint32_t), ptr, task, 0);
+ user_data = value;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?lsm.s/bpf")
+int BPF_PROG(inproper_sleepable_kfunc, int cmd, union bpf_attr *attr, unsigned int size)
+{
+ struct bpf_key *bkey;
+
+ /* sleepable kfunc in rcu read lock region */
+ bpf_rcu_read_lock();
+ bkey = bpf_lookup_user_key(key_serial, flags);
+ bpf_rcu_read_unlock();
+ if (!bkey)
+ return -1;
+ bpf_key_put(bkey);
+
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int nested_rcu_region(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ /* nested rcu read lock regions */
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int task_untrusted_non_rcuptr(void *ctx)
+{
+ struct task_struct *task, *last_wakee;
+
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ /* the pointer last_wakee marked as untrusted */
+ last_wakee = task->real_parent->last_wakee;
+ (void)bpf_task_storage_get(&map_a, last_wakee, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_getpgid")
+int task_untrusted_rcuptr(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ bpf_rcu_read_unlock();
+ /* helper use of rcu ptr outside the rcu read lock region */
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ return 0;
+}
+
+SEC("?fentry.s/" SYS_PREFIX "sys_nanosleep")
+int cross_rcu_region(void *ctx)
+{
+ struct task_struct *task, *real_parent;
+
+ /* rcu ptr define/use in different regions */
+ task = bpf_get_current_task_btf();
+ bpf_rcu_read_lock();
+ real_parent = task->real_parent;
+ bpf_rcu_read_unlock();
+ bpf_rcu_read_lock();
+ (void)bpf_task_storage_get(&map_a, real_parent, 0, 0);
+ bpf_rcu_read_unlock();
+ return 0;
+}
Powered by cgit, Gruvboxed by Blaster4385.