summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorAlexei Starovoitov <ast@kernel.org>2020-05-13 16:03:54 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2020-05-15 17:29:41 +0200
commit2c78ee898d8f10ae6fb2fa23a3fbaec96b1b7366 (patch)
tree6f2c093168b9b2c532127994bd50ff9f8e82401e /kernel
parenta17b53c4a4b55ec322c132b6670743612229ee9c (diff)
downloadlinux-2c78ee898d8f10ae6fb2fa23a3fbaec96b1b7366.tar.bz2
bpf: Implement CAP_BPF
Implement permissions as stated in uapi/linux/capability.h In order to do that the verifier allow_ptr_leaks flag is split into four flags and they are set as: env->allow_ptr_leaks = bpf_allow_ptr_leaks(); env->bypass_spec_v1 = bpf_bypass_spec_v1(); env->bypass_spec_v4 = bpf_bypass_spec_v4(); env->bpf_capable = bpf_capable(); The first three currently equivalent to perfmon_capable(), since leaking kernel pointers and reading kernel memory via side channel attacks is roughly equivalent to reading kernel memory with cap_perfmon. 'bpf_capable' enables bounded loops, precision tracking, bpf to bpf calls and other verifier features. 'allow_ptr_leaks' enable ptr leaks, ptr conversions, subtraction of pointers. 'bypass_spec_v1' disables speculative analysis in the verifier, run time mitigations in bpf array, and enables indirect variable access in bpf programs. 'bypass_spec_v4' disables emission of sanitation code by the verifier. That means that the networking BPF program loaded with CAP_BPF + CAP_NET_ADMIN will have speculative checks done by the verifier and other spectre mitigation applied. Such networking BPF program will not be able to leak kernel pointers and will not be able to access arbitrary kernel memory. Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200513230355.7858-3-alexei.starovoitov@gmail.com
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/arraymap.c10
-rw-r--r--kernel/bpf/bpf_struct_ops.c2
-rw-r--r--kernel/bpf/core.c2
-rw-r--r--kernel/bpf/cpumap.c2
-rw-r--r--kernel/bpf/hashtab.c4
-rw-r--r--kernel/bpf/helpers.c4
-rw-r--r--kernel/bpf/lpm_trie.c2
-rw-r--r--kernel/bpf/map_in_map.c2
-rw-r--r--kernel/bpf/queue_stack_maps.c2
-rw-r--r--kernel/bpf/reuseport_array.c2
-rw-r--r--kernel/bpf/stackmap.c2
-rw-r--r--kernel/bpf/syscall.c89
-rw-r--r--kernel/bpf/verifier.c37
-rw-r--r--kernel/trace/bpf_trace.c3
14 files changed, 109 insertions, 54 deletions
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 95d77770353c..1d5bb0d983b2 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -77,7 +77,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
int ret, numa_node = bpf_map_attr_numa_node(attr);
u32 elem_size, index_mask, max_entries;
- bool unpriv = !capable(CAP_SYS_ADMIN);
+ bool bypass_spec_v1 = bpf_bypass_spec_v1();
u64 cost, array_size, mask64;
struct bpf_map_memory mem;
struct bpf_array *array;
@@ -95,7 +95,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
mask64 -= 1;
index_mask = mask64;
- if (unpriv) {
+ if (!bypass_spec_v1) {
/* round up array size to nearest power of 2,
* since cpu will speculate within index_mask limits
*/
@@ -149,7 +149,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr)
return ERR_PTR(-ENOMEM);
}
array->index_mask = index_mask;
- array->map.unpriv_array = unpriv;
+ array->map.bypass_spec_v1 = bypass_spec_v1;
/* copy mandatory map attributes */
bpf_map_init_from_attr(&array->map, attr);
@@ -219,7 +219,7 @@ static u32 array_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
- if (map->unpriv_array) {
+ if (!map->bypass_spec_v1) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 4);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
@@ -1053,7 +1053,7 @@ static u32 array_of_map_gen_lookup(struct bpf_map *map,
*insn++ = BPF_ALU64_IMM(BPF_ADD, map_ptr, offsetof(struct bpf_array, value));
*insn++ = BPF_LDX_MEM(BPF_W, ret, index, 0);
- if (map->unpriv_array) {
+ if (!map->bypass_spec_v1) {
*insn++ = BPF_JMP_IMM(BPF_JGE, ret, map->max_entries, 6);
*insn++ = BPF_ALU32_IMM(BPF_AND, ret, array->index_mask);
} else {
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 26cb51f2db72..c6b0decaa46a 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -557,7 +557,7 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr)
struct bpf_map *map;
int err;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6aa11de67315..c40ff4cf9880 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -646,7 +646,7 @@ static bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
void bpf_prog_kallsyms_add(struct bpf_prog *fp)
{
if (!bpf_prog_kallsyms_candidate(fp) ||
- !capable(CAP_SYS_ADMIN))
+ !bpf_capable())
return;
bpf_prog_ksym_set_addr(fp);
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index a71790dab12d..8b85bfddfac7 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -85,7 +85,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
u64 cost;
int ret;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
/* check sanity of attributes */
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index d541c8486c95..b4b288a3c3c9 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -359,9 +359,9 @@ static int htab_map_alloc_check(union bpf_attr *attr)
BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
offsetof(struct htab_elem, hash_node.pprev));
- if (lru && !capable(CAP_SYS_ADMIN))
+ if (lru && !bpf_capable())
/* LRU implementation is much complicated than other
- * maps. Hence, limit to CAP_SYS_ADMIN for now.
+ * maps. Hence, limit to CAP_BPF.
*/
return -EPERM;
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5c0290e0696e..886949fdcece 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -633,7 +633,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
break;
}
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return NULL;
switch (func_id) {
@@ -642,6 +642,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
case BPF_FUNC_spin_unlock:
return &bpf_spin_unlock_proto;
case BPF_FUNC_trace_printk:
+ if (!perfmon_capable())
+ return NULL;
return bpf_get_trace_printk_proto();
case BPF_FUNC_jiffies64:
return &bpf_jiffies64_proto;
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 65c236cf341e..c8cc4e4cf98d 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -543,7 +543,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr)
u64 cost = sizeof(*trie), cost_per_node;
int ret;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
/* check sanity of attributes */
diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index b3c48d1533cb..17738c93bec8 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -60,7 +60,7 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
/* Misc members not needed in bpf_map_meta_equal() check. */
inner_map_meta->ops = inner_map->ops;
if (inner_map->ops == &array_map_ops) {
- inner_map_meta->unpriv_array = inner_map->unpriv_array;
+ inner_map_meta->bypass_spec_v1 = inner_map->bypass_spec_v1;
container_of(inner_map_meta, struct bpf_array, map)->index_mask =
container_of(inner_map, struct bpf_array, map)->index_mask;
}
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 30e1373fd437..05c8e043b9d2 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -45,7 +45,7 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs)
/* Called from syscall */
static int queue_stack_map_alloc_check(union bpf_attr *attr)
{
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return -EPERM;
/* check sanity of attributes */
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
index 01badd3eda7a..21cde24386db 100644
--- a/kernel/bpf/reuseport_array.c
+++ b/kernel/bpf/reuseport_array.c
@@ -154,7 +154,7 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
struct bpf_map_memory mem;
u64 array_size;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
array_size = sizeof(*array);
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index db76339fe358..7b8381ce40a0 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -93,7 +93,7 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr)
u64 cost, n_buckets;
int err;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return ERR_PTR(-EPERM);
if (attr->map_flags & ~STACK_CREATE_FLAG_MASK)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index de2a75500233..79bcd8d056d2 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -1534,7 +1534,7 @@ static int map_freeze(const union bpf_attr *attr)
err = -EBUSY;
goto err_put;
}
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!bpf_capable()) {
err = -EPERM;
goto err_put;
}
@@ -2009,6 +2009,55 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type,
}
}
+static bool is_net_admin_prog_type(enum bpf_prog_type prog_type)
+{
+ switch (prog_type) {
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ case BPF_PROG_TYPE_XDP:
+ case BPF_PROG_TYPE_LWT_IN:
+ case BPF_PROG_TYPE_LWT_OUT:
+ case BPF_PROG_TYPE_LWT_XMIT:
+ case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SOCK:
+ case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_SOCK_OPS:
+ case BPF_PROG_TYPE_EXT: /* extends any prog */
+ return true;
+ case BPF_PROG_TYPE_CGROUP_SKB:
+ /* always unpriv */
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ /* equivalent to SOCKET_FILTER. need CAP_BPF only */
+ default:
+ return false;
+ }
+}
+
+static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
+{
+ switch (prog_type) {
+ case BPF_PROG_TYPE_KPROBE:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
+ case BPF_PROG_TYPE_TRACING:
+ case BPF_PROG_TYPE_LSM:
+ case BPF_PROG_TYPE_STRUCT_OPS: /* has access to struct sock */
+ case BPF_PROG_TYPE_EXT: /* extends any prog */
+ return true;
+ default:
+ return false;
+ }
+}
+
/* last field in 'union bpf_attr' used by this command */
#define BPF_PROG_LOAD_LAST_FIELD attach_prog_fd
@@ -2031,7 +2080,7 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&
(attr->prog_flags & BPF_F_ANY_ALIGNMENT) &&
- !capable(CAP_SYS_ADMIN))
+ !bpf_capable())
return -EPERM;
/* copy eBPF program license from user space */
@@ -2044,11 +2093,16 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr)
is_gpl = license_is_gpl_compatible(license);
if (attr->insn_cnt == 0 ||
- attr->insn_cnt > (capable(CAP_SYS_ADMIN) ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
+ attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS))
return -E2BIG;
if (type != BPF_PROG_TYPE_SOCKET_FILTER &&
type != BPF_PROG_TYPE_CGROUP_SKB &&
- !capable(CAP_SYS_ADMIN))
+ !bpf_capable())
+ return -EPERM;
+
+ if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN))
+ return -EPERM;
+ if (is_perfmon_prog_type(type) && !perfmon_capable())
return -EPERM;
bpf_prog_load_fixup_attach_type(attr);
@@ -2682,6 +2736,11 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
case BPF_PROG_TYPE_CGROUP_SOCKOPT:
return attach_type == prog->expected_attach_type ? 0 : -EINVAL;
case BPF_PROG_TYPE_CGROUP_SKB:
+ if (!capable(CAP_NET_ADMIN))
+ /* cg-skb progs can be loaded by unpriv user.
+ * check permissions at attach time.
+ */
+ return -EPERM;
return prog->enforce_expected_attach_type &&
prog->expected_attach_type != attach_type ?
-EINVAL : 0;
@@ -2747,9 +2806,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
struct bpf_prog *prog;
int ret;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
if (CHECK_ATTR(BPF_PROG_ATTACH))
return -EINVAL;
@@ -2804,9 +2860,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
if (CHECK_ATTR(BPF_PROG_DETACH))
return -EINVAL;
@@ -2819,6 +2872,8 @@ static int bpf_prog_detach(const union bpf_attr *attr)
case BPF_PROG_TYPE_LIRC_MODE2:
return lirc_prog_detach(attr);
case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
return skb_flow_dissector_bpf_prog_detach(attr);
case BPF_PROG_TYPE_CGROUP_DEVICE:
case BPF_PROG_TYPE_CGROUP_SKB:
@@ -2882,8 +2937,6 @@ static int bpf_prog_test_run(const union bpf_attr *attr,
struct bpf_prog *prog;
int ret = -ENOTSUPP;
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
if (CHECK_ATTR(BPF_PROG_TEST_RUN))
return -EINVAL;
@@ -3184,7 +3237,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog,
info.run_time_ns = stats.nsecs;
info.run_cnt = stats.cnt;
- if (!capable(CAP_SYS_ADMIN)) {
+ if (!bpf_capable()) {
info.jited_prog_len = 0;
info.xlated_prog_len = 0;
info.nr_jited_ksyms = 0;
@@ -3543,7 +3596,7 @@ static int bpf_btf_load(const union bpf_attr *attr)
if (CHECK_ATTR(BPF_BTF_LOAD))
return -EINVAL;
- if (!capable(CAP_SYS_ADMIN))
+ if (!bpf_capable())
return -EPERM;
return btf_new_fd(attr);
@@ -3766,9 +3819,6 @@ static int link_create(union bpf_attr *attr)
struct bpf_prog *prog;
int ret;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
if (CHECK_ATTR(BPF_LINK_CREATE))
return -EINVAL;
@@ -3817,9 +3867,6 @@ static int link_update(union bpf_attr *attr)
u32 flags;
int ret;
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
-
if (CHECK_ATTR(BPF_LINK_UPDATE))
return -EINVAL;
@@ -3988,7 +4035,7 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
union bpf_attr attr;
int err;
- if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN))
+ if (sysctl_unprivileged_bpf_disabled && !bpf_capable())
return -EPERM;
err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index a3f2af756fd6..180933f6fba9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1295,7 +1295,7 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env,
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
- reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks;
+ reg->precise = env->subprog_cnt > 1 || !env->bpf_capable;
__mark_reg_unbounded(reg);
}
@@ -1427,8 +1427,9 @@ static int check_subprogs(struct bpf_verifier_env *env)
continue;
if (insn[i].src_reg != BPF_PSEUDO_CALL)
continue;
- if (!env->allow_ptr_leaks) {
- verbose(env, "function calls to other bpf functions are allowed for root only\n");
+ if (!env->bpf_capable) {
+ verbose(env,
+ "function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
return -EPERM;
}
ret = add_subprog(env, i + insn[i].imm + 1);
@@ -1962,8 +1963,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
bool new_marks = false;
int i, err;
- if (!env->allow_ptr_leaks)
- /* backtracking is root only for now */
+ if (!env->bpf_capable)
return 0;
func = st->frame[st->curframe];
@@ -2211,7 +2211,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
reg = &cur->regs[value_regno];
if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
- !register_is_null(reg) && env->allow_ptr_leaks) {
+ !register_is_null(reg) && env->bpf_capable) {
if (dst_reg != BPF_REG_FP) {
/* The backtracking logic can only recognize explicit
* stack slot address like [fp - 8]. Other spill of
@@ -2237,7 +2237,7 @@ static int check_stack_write(struct bpf_verifier_env *env,
return -EINVAL;
}
- if (!env->allow_ptr_leaks) {
+ if (!env->bypass_spec_v4) {
bool sanitize = false;
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
@@ -3432,7 +3432,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
* Spectre masking for stack ALU.
* See also retrieve_ptr_limit().
*/
- if (!env->allow_ptr_leaks) {
+ if (!env->bypass_spec_v1) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
@@ -4435,10 +4435,10 @@ record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
if (!BPF_MAP_PTR(aux->map_ptr_state))
bpf_map_ptr_store(aux, meta->map_ptr,
- meta->map_ptr->unpriv_array);
+ !meta->map_ptr->bypass_spec_v1);
else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr)
bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
- meta->map_ptr->unpriv_array);
+ !meta->map_ptr->bypass_spec_v1);
return 0;
}
@@ -4807,7 +4807,7 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
- return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K;
+ return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
}
static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -5117,7 +5117,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
/* For unprivileged we require that resulting offset must be in bounds
* in order to be able to sanitize access later on.
*/
- if (!env->allow_ptr_leaks) {
+ if (!env->bypass_spec_v1) {
if (dst_reg->type == PTR_TO_MAP_VALUE &&
check_map_access(env, dst, dst_reg->off, 1, false)) {
verbose(env, "R%d pointer arithmetic of map value goes out of range, "
@@ -7244,7 +7244,7 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
insn_stack[env->cfg.cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
- if (loop_ok && env->allow_ptr_leaks)
+ if (loop_ok && env->bpf_capable)
return 0;
verbose_linfo(env, t, "%d: ", t);
verbose_linfo(env, w, "%d: ", w);
@@ -8353,7 +8353,7 @@ next:
if (env->max_states_per_insn < states_cnt)
env->max_states_per_insn = states_cnt;
- if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+ if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
return push_jmp_history(env, cur);
if (!add_new_state)
@@ -10014,7 +10014,7 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
insn->code = BPF_JMP | BPF_TAIL_CALL;
aux = &env->insn_aux_data[i + delta];
- if (env->allow_ptr_leaks && !expect_blinding &&
+ if (env->bpf_capable && !expect_blinding &&
prog->jit_requested &&
!bpf_map_key_poisoned(aux) &&
!bpf_map_ptr_poisoned(aux) &&
@@ -10758,7 +10758,7 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
- is_priv = capable(CAP_SYS_ADMIN);
+ is_priv = bpf_capable();
if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
mutex_lock(&bpf_verifier_lock);
@@ -10799,7 +10799,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
- env->allow_ptr_leaks = is_priv;
+ env->allow_ptr_leaks = bpf_allow_ptr_leaks();
+ 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;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d961428fb5b6..9a84d7fb4869 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -315,6 +315,9 @@ static const struct bpf_func_proto bpf_probe_write_user_proto = {
static const struct bpf_func_proto *bpf_get_probe_write_proto(void)
{
+ if (!capable(CAP_SYS_ADMIN))
+ return NULL;
+
pr_warn_ratelimited("%s[%d] is installing a program with bpf_probe_write_user helper that may corrupt user memory!",
current->comm, task_pid_nr(current));