aboutsummaryrefslogtreecommitdiff
path: root/kernel/bpf/verifier.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf/verifier.c')
-rw-r--r--kernel/bpf/verifier.c1585
1 files changed, 1226 insertions, 359 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index cf5f230360f5..bb78212fa5b2 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -25,6 +25,8 @@
#include <linux/btf_ids.h>
#include <linux/poison.h>
#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <net/xdp.h>
#include "disasm.h"
@@ -197,6 +199,7 @@ static int ref_set_non_owning(struct bpf_verifier_env *env,
struct bpf_reg_state *reg);
static void specialize_kfunc(struct bpf_verifier_env *env,
u32 func_id, u16 offset, unsigned long *addr);
+static bool is_trusted_reg(const struct bpf_reg_state *reg);
static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
@@ -240,6 +243,12 @@ static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
(poisoned ? BPF_MAP_KEY_POISON : 0ULL);
}
+static bool bpf_helper_call(const struct bpf_insn *insn)
+{
+ return insn->code == (BPF_JMP | BPF_CALL) &&
+ insn->src_reg == 0;
+}
+
static bool bpf_pseudo_call(const struct bpf_insn *insn)
{
return insn->code == (BPF_JMP | BPF_CALL) &&
@@ -273,11 +282,6 @@ struct bpf_call_arg_meta {
struct btf_field *kptr_field;
};
-struct btf_and_id {
- struct btf *btf;
- u32 btf_id;
-};
-
struct bpf_kfunc_call_arg_meta {
/* In parameters */
struct btf *btf;
@@ -296,10 +300,21 @@ struct bpf_kfunc_call_arg_meta {
u64 value;
bool found;
} arg_constant;
- union {
- struct btf_and_id arg_obj_drop;
- struct btf_and_id arg_refcount_acquire;
- };
+
+ /* arg_{btf,btf_id,owning_ref} are used by kfunc-specific handling,
+ * generally to pass info about user-defined local kptr types to later
+ * verification logic
+ * bpf_obj_drop
+ * Record the local kptr type to be drop'd
+ * bpf_refcount_acquire (via KF_ARG_PTR_TO_REFCOUNTED_KPTR arg type)
+ * Record the local kptr type to be refcount_incr'd and use
+ * arg_owning_ref to determine whether refcount_acquire should be
+ * fallible
+ */
+ struct btf *arg_btf;
+ u32 arg_btf_id;
+ bool arg_owning_ref;
+
struct {
struct btf_field *field;
} arg_list_head;
@@ -309,6 +324,7 @@ struct bpf_kfunc_call_arg_meta {
struct {
enum bpf_dynptr_type type;
u32 id;
+ u32 ref_obj_id;
} initialized_dynptr;
struct {
u8 spi;
@@ -429,8 +445,11 @@ static bool type_may_be_null(u32 type)
return type & PTR_MAYBE_NULL;
}
-static bool reg_type_not_null(enum bpf_reg_type type)
+static bool reg_not_null(const struct bpf_reg_state *reg)
{
+ enum bpf_reg_type type;
+
+ type = reg->type;
if (type_may_be_null(type))
return false;
@@ -440,6 +459,7 @@ static bool reg_type_not_null(enum bpf_reg_type type)
type == PTR_TO_MAP_VALUE ||
type == PTR_TO_MAP_KEY ||
type == PTR_TO_SOCK_COMMON ||
+ (type == PTR_TO_BTF_ID && is_trusted_reg(reg)) ||
type == PTR_TO_MEM;
}
@@ -468,6 +488,13 @@ static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
return rec;
}
+static bool subprog_is_global(const struct bpf_verifier_env *env, int subprog)
+{
+ struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux;
+
+ return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
+}
+
static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK);
@@ -515,6 +542,8 @@ static bool is_dynptr_ref_function(enum bpf_func_id func_id)
return func_id == BPF_FUNC_dynptr_data;
}
+static bool is_callback_calling_kfunc(u32 btf_id);
+
static bool is_callback_calling_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_for_each_map_elem ||
@@ -524,6 +553,11 @@ static bool is_callback_calling_function(enum bpf_func_id func_id)
func_id == BPF_FUNC_user_ringbuf_drain;
}
+static bool is_async_callback_calling_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_timer_set_callback;
+}
+
static bool is_storage_get_function(enum bpf_func_id func_id)
{
return func_id == BPF_FUNC_sk_storage_get ||
@@ -604,9 +638,9 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
type & PTR_TRUSTED ? "trusted_" : ""
);
- snprintf(env->type_str_buf, TYPE_STR_BUF_LEN, "%s%s%s",
+ snprintf(env->tmp_str_buf, TMP_STR_BUF_LEN, "%s%s%s",
prefix, str[base_type(type)], postfix);
- return env->type_str_buf;
+ return env->tmp_str_buf;
}
static char slot_type_char[] = {
@@ -847,11 +881,11 @@ static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env,
struct bpf_func_state *state, int spi);
static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
- enum bpf_arg_type arg_type, int insn_idx)
+ enum bpf_arg_type arg_type, int insn_idx, int clone_ref_obj_id)
{
struct bpf_func_state *state = func(env, reg);
enum bpf_dynptr_type type;
- int spi, i, id, err;
+ int spi, i, err;
spi = dynptr_get_spi(env, reg);
if (spi < 0)
@@ -887,7 +921,13 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
if (dynptr_type_refcounted(type)) {
/* The id is used to track proper releasing */
- id = acquire_reference_state(env, insn_idx);
+ int id;
+
+ if (clone_ref_obj_id)
+ id = clone_ref_obj_id;
+ else
+ id = acquire_reference_state(env, insn_idx);
+
if (id < 0)
return id;
@@ -901,24 +941,15 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
return 0;
}
-static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_func_state *state, int spi)
{
- struct bpf_func_state *state = func(env, reg);
- int spi, i;
-
- spi = dynptr_get_spi(env, reg);
- if (spi < 0)
- return spi;
+ int i;
for (i = 0; i < BPF_REG_SIZE; i++) {
state->stack[spi].slot_type[i] = STACK_INVALID;
state->stack[spi - 1].slot_type[i] = STACK_INVALID;
}
- /* Invalidate any slices associated with this dynptr */
- if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type))
- WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id));
-
__mark_reg_not_init(env, &state->stack[spi].spilled_ptr);
__mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr);
@@ -945,6 +976,50 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re
*/
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN;
+}
+
+static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+ struct bpf_func_state *state = func(env, reg);
+ int spi, ref_obj_id, i;
+
+ spi = dynptr_get_spi(env, reg);
+ if (spi < 0)
+ return spi;
+
+ if (!dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) {
+ invalidate_dynptr(env, state, spi);
+ return 0;
+ }
+
+ ref_obj_id = state->stack[spi].spilled_ptr.ref_obj_id;
+
+ /* If the dynptr has a ref_obj_id, then we need to invalidate
+ * two things:
+ *
+ * 1) Any dynptrs with a matching ref_obj_id (clones)
+ * 2) Any slices derived from this dynptr.
+ */
+
+ /* Invalidate any slices associated with this dynptr */
+ WARN_ON_ONCE(release_reference(env, ref_obj_id));
+
+ /* Invalidate any dynptr clones */
+ for (i = 1; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (state->stack[i].spilled_ptr.ref_obj_id != ref_obj_id)
+ continue;
+
+ /* it should always be the case that if the ref obj id
+ * matches then the stack slot also belongs to a
+ * dynptr
+ */
+ if (state->stack[i].slot_type[0] != STACK_DYNPTR) {
+ verbose(env, "verifier internal error: misconfigured ref_obj_id\n");
+ return -EFAULT;
+ }
+ if (state->stack[i].spilled_ptr.dynptr.first_slot)
+ invalidate_dynptr(env, state, i);
+ }
return 0;
}
@@ -1254,6 +1329,12 @@ static bool is_spilled_reg(const struct bpf_stack_state *stack)
return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
}
+static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack)
+{
+ return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL &&
+ stack->spilled_ptr.type == SCALAR_VALUE;
+}
+
static void scrub_spilled_slot(u8 *stype)
{
if (*stype != STACK_INVALID)
@@ -2775,7 +2856,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
- off = i + insn[i].off + 1;
+ if (code == (BPF_JMP32 | BPF_JA))
+ off = i + insn[i].imm + 1;
+ else
+ off = i + insn[i].off + 1;
if (off < subprog_start || off >= subprog_end) {
verbose(env, "jump out of range from insn %d to %d\n", i, off);
return -EINVAL;
@@ -2787,6 +2871,7 @@ next:
* or unconditional jump back
*/
if (code != (BPF_JMP | BPF_EXIT) &&
+ code != (BPF_JMP32 | BPF_JA) &&
code != (BPF_JMP | BPF_JA)) {
verbose(env, "last insn is not an exit or jmp\n");
return -EINVAL;
@@ -2932,8 +3017,10 @@ static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
}
}
+ if (class == BPF_ALU64 && op == BPF_END && (insn->imm == 16 || insn->imm == 32))
+ return false;
+
if (class == BPF_ALU64 || class == BPF_JMP ||
- /* BPF_END always use BPF_ALU class. */
(class == BPF_ALU && op == BPF_END && insn->imm == 64))
return true;
@@ -3144,12 +3231,172 @@ static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
return btf_name_by_offset(desc_btf, func->name_off);
}
+static inline void bt_init(struct backtrack_state *bt, u32 frame)
+{
+ bt->frame = frame;
+}
+
+static inline void bt_reset(struct backtrack_state *bt)
+{
+ struct bpf_verifier_env *env = bt->env;
+
+ memset(bt, 0, sizeof(*bt));
+ bt->env = env;
+}
+
+static inline u32 bt_empty(struct backtrack_state *bt)
+{
+ u64 mask = 0;
+ int i;
+
+ for (i = 0; i <= bt->frame; i++)
+ mask |= bt->reg_masks[i] | bt->stack_masks[i];
+
+ return mask == 0;
+}
+
+static inline int bt_subprog_enter(struct backtrack_state *bt)
+{
+ if (bt->frame == MAX_CALL_FRAMES - 1) {
+ verbose(bt->env, "BUG subprog enter from frame %d\n", bt->frame);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ bt->frame++;
+ return 0;
+}
+
+static inline int bt_subprog_exit(struct backtrack_state *bt)
+{
+ if (bt->frame == 0) {
+ verbose(bt->env, "BUG subprog exit from frame 0\n");
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ bt->frame--;
+ return 0;
+}
+
+static inline void bt_set_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg)
+{
+ bt->reg_masks[frame] |= 1 << reg;
+}
+
+static inline void bt_clear_frame_reg(struct backtrack_state *bt, u32 frame, u32 reg)
+{
+ bt->reg_masks[frame] &= ~(1 << reg);
+}
+
+static inline void bt_set_reg(struct backtrack_state *bt, u32 reg)
+{
+ bt_set_frame_reg(bt, bt->frame, reg);
+}
+
+static inline void bt_clear_reg(struct backtrack_state *bt, u32 reg)
+{
+ bt_clear_frame_reg(bt, bt->frame, reg);
+}
+
+static inline void bt_set_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+ bt->stack_masks[frame] |= 1ull << slot;
+}
+
+static inline void bt_clear_frame_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+ bt->stack_masks[frame] &= ~(1ull << slot);
+}
+
+static inline void bt_set_slot(struct backtrack_state *bt, u32 slot)
+{
+ bt_set_frame_slot(bt, bt->frame, slot);
+}
+
+static inline void bt_clear_slot(struct backtrack_state *bt, u32 slot)
+{
+ bt_clear_frame_slot(bt, bt->frame, slot);
+}
+
+static inline u32 bt_frame_reg_mask(struct backtrack_state *bt, u32 frame)
+{
+ return bt->reg_masks[frame];
+}
+
+static inline u32 bt_reg_mask(struct backtrack_state *bt)
+{
+ return bt->reg_masks[bt->frame];
+}
+
+static inline u64 bt_frame_stack_mask(struct backtrack_state *bt, u32 frame)
+{
+ return bt->stack_masks[frame];
+}
+
+static inline u64 bt_stack_mask(struct backtrack_state *bt)
+{
+ return bt->stack_masks[bt->frame];
+}
+
+static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
+{
+ return bt->reg_masks[bt->frame] & (1 << reg);
+}
+
+static inline bool bt_is_slot_set(struct backtrack_state *bt, u32 slot)
+{
+ return bt->stack_masks[bt->frame] & (1ull << slot);
+}
+
+/* format registers bitmask, e.g., "r0,r2,r4" for 0x15 mask */
+static void fmt_reg_mask(char *buf, ssize_t buf_sz, u32 reg_mask)
+{
+ DECLARE_BITMAP(mask, 64);
+ bool first = true;
+ int i, n;
+
+ buf[0] = '\0';
+
+ bitmap_from_u64(mask, reg_mask);
+ for_each_set_bit(i, mask, 32) {
+ n = snprintf(buf, buf_sz, "%sr%d", first ? "" : ",", i);
+ first = false;
+ buf += n;
+ buf_sz -= n;
+ if (buf_sz < 0)
+ break;
+ }
+}
+/* format stack slots bitmask, e.g., "-8,-24,-40" for 0x15 mask */
+static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
+{
+ DECLARE_BITMAP(mask, 64);
+ bool first = true;
+ int i, n;
+
+ buf[0] = '\0';
+
+ bitmap_from_u64(mask, stack_mask);
+ for_each_set_bit(i, mask, 64) {
+ n = snprintf(buf, buf_sz, "%s%d", first ? "" : ",", -(i + 1) * 8);
+ first = false;
+ buf += n;
+ buf_sz -= n;
+ if (buf_sz < 0)
+ break;
+ }
+}
+
/* For given verifier state backtrack_insn() is called from the last insn to
* the first insn. Its purpose is to compute a bitmask of registers and
* stack slots that needs precision in the parent verifier state.
+ *
+ * @idx is an index of the instruction we are currently processing;
+ * @subseq_idx is an index of the subsequent instruction that:
+ * - *would be* executed next, if jump history is viewed in forward order;
+ * - *was* processed previously during backtracking.
*/
-static int backtrack_insn(struct bpf_verifier_env *env, int idx,
- u32 *reg_mask, u64 *stack_mask)
+static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
+ struct backtrack_state *bt)
{
const struct bpf_insn_cbs cbs = {
.cb_call = disasm_kfunc_name,
@@ -3160,29 +3407,33 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
u8 class = BPF_CLASS(insn->code);
u8 opcode = BPF_OP(insn->code);
u8 mode = BPF_MODE(insn->code);
- u32 dreg = 1u << insn->dst_reg;
- u32 sreg = 1u << insn->src_reg;
- u32 spi;
+ u32 dreg = insn->dst_reg;
+ u32 sreg = insn->src_reg;
+ u32 spi, i;
if (insn->code == 0)
return 0;
if (env->log.level & BPF_LOG_LEVEL2) {
- verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
+ fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_reg_mask(bt));
+ verbose(env, "mark_precise: frame%d: regs=%s ",
+ bt->frame, env->tmp_str_buf);
+ fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN, bt_stack_mask(bt));
+ verbose(env, "stack=%s before ", env->tmp_str_buf);
verbose(env, "%d: ", idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
if (class == BPF_ALU || class == BPF_ALU64) {
- if (!(*reg_mask & dreg))
+ if (!bt_is_reg_set(bt, dreg))
return 0;
if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- /* dreg = sreg
+ /* dreg = sreg or dreg = (s8, s16, s32)sreg
* dreg needs precision after this insn
* sreg needs precision before this insn
*/
- *reg_mask &= ~dreg;
- *reg_mask |= sreg;
+ bt_clear_reg(bt, dreg);
+ bt_set_reg(bt, sreg);
} else {
/* dreg = K
* dreg needs precision after this insn.
@@ -3190,7 +3441,7 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
* as precise=true in this verifier state.
* No further markings in parent are necessary
*/
- *reg_mask &= ~dreg;
+ bt_clear_reg(bt, dreg);
}
} else {
if (BPF_SRC(insn->code) == BPF_X) {
@@ -3198,15 +3449,15 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
* both dreg and sreg need precision
* before this insn
*/
- *reg_mask |= sreg;
+ bt_set_reg(bt, sreg);
} /* else dreg += K
* dreg still needs precision before this insn
*/
}
} else if (class == BPF_LDX) {
- if (!(*reg_mask & dreg))
+ if (!bt_is_reg_set(bt, dreg))
return 0;
- *reg_mask &= ~dreg;
+ bt_clear_reg(bt, dreg);
/* scalars can only be spilled into stack w/o losing precision.
* Load from any other memory can be zero extended.
@@ -3227,9 +3478,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
- *stack_mask |= 1ull << spi;
+ bt_set_slot(bt, spi);
} else if (class == BPF_STX || class == BPF_ST) {
- if (*reg_mask & dreg)
+ if (bt_is_reg_set(bt, dreg))
/* stx & st shouldn't be using _scalar_ dst_reg
* to access memory. It means backtracking
* encountered a case of pointer subtraction.
@@ -3244,20 +3495,92 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
- if (!(*stack_mask & (1ull << spi)))
+ if (!bt_is_slot_set(bt, spi))
return 0;
- *stack_mask &= ~(1ull << spi);
+ bt_clear_slot(bt, spi);
if (class == BPF_STX)
- *reg_mask |= sreg;
+ bt_set_reg(bt, sreg);
} else if (class == BPF_JMP || class == BPF_JMP32) {
- if (opcode == BPF_CALL) {
- if (insn->src_reg == BPF_PSEUDO_CALL)
- return -ENOTSUPP;
- /* BPF helpers that invoke callback subprogs are
- * equivalent to BPF_PSEUDO_CALL above
+ if (bpf_pseudo_call(insn)) {
+ int subprog_insn_idx, subprog;
+
+ subprog_insn_idx = idx + insn->imm + 1;
+ subprog = find_subprog(env, subprog_insn_idx);
+ if (subprog < 0)
+ return -EFAULT;
+
+ if (subprog_is_global(env, subprog)) {
+ /* check that jump history doesn't have any
+ * extra instructions from subprog; the next
+ * instruction after call to global subprog
+ * should be literally next instruction in
+ * caller program
+ */
+ WARN_ONCE(idx + 1 != subseq_idx, "verifier backtracking bug");
+ /* r1-r5 are invalidated after subprog call,
+ * so for global func call it shouldn't be set
+ * anymore
+ */
+ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
+ verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ /* global subprog always sets R0 */
+ bt_clear_reg(bt, BPF_REG_0);
+ return 0;
+ } else {
+ /* static subprog call instruction, which
+ * means that we are exiting current subprog,
+ * so only r1-r5 could be still requested as
+ * precise, r0 and r6-r10 or any stack slot in
+ * the current frame should be zero by now
+ */
+ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
+ verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ /* we don't track register spills perfectly,
+ * so fallback to force-precise instead of failing */
+ if (bt_stack_mask(bt) != 0)
+ return -ENOTSUPP;
+ /* propagate r1-r5 to the caller */
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
+ if (bt_is_reg_set(bt, i)) {
+ bt_clear_reg(bt, i);
+ bt_set_frame_reg(bt, bt->frame - 1, i);
+ }
+ }
+ if (bt_subprog_exit(bt))
+ return -EFAULT;
+ return 0;
+ }
+ } else if ((bpf_helper_call(insn) &&
+ is_callback_calling_function(insn->imm) &&
+ !is_async_callback_calling_function(insn->imm)) ||
+ (bpf_pseudo_kfunc_call(insn) && is_callback_calling_kfunc(insn->imm))) {
+ /* callback-calling helper or kfunc call, which means
+ * we are exiting from subprog, but unlike the subprog
+ * call handling above, we shouldn't propagate
+ * precision of r1-r5 (if any requested), as they are
+ * not actually arguments passed directly to callback
+ * subprogs
*/
- if (insn->src_reg == 0 && is_callback_calling_function(insn->imm))
+ if (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) {
+ verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ if (bt_stack_mask(bt) != 0)
return -ENOTSUPP;
+ /* clear r1-r5 in callback subprog's mask */
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+ bt_clear_reg(bt, i);
+ if (bt_subprog_exit(bt))
+ return -EFAULT;
+ return 0;
+ } else if (opcode == BPF_CALL) {
/* kfunc with imm==0 is invalid and fixup_kfunc_call will
* catch this error later. Make backtracking conservative
* with ENOTSUPP.
@@ -3265,19 +3588,51 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && insn->imm == 0)
return -ENOTSUPP;
/* regular helper call sets R0 */
- *reg_mask &= ~1;
- if (*reg_mask & 0x3f) {
+ bt_clear_reg(bt, BPF_REG_0);
+ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
/* if backtracing was looking for registers R1-R5
* they should have been found already.
*/
- verbose(env, "BUG regs %x\n", *reg_mask);
+ verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
} else if (opcode == BPF_EXIT) {
- return -ENOTSUPP;
+ bool r0_precise;
+
+ if (bt_reg_mask(bt) & BPF_REGMASK_ARGS) {
+ /* if backtracing was looking for registers R1-R5
+ * they should have been found already.
+ */
+ verbose(env, "BUG regs %x\n", bt_reg_mask(bt));
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+
+ /* BPF_EXIT in subprog or callback always returns
+ * right after the call instruction, so by checking
+ * whether the instruction at subseq_idx-1 is subprog
+ * call or not we can distinguish actual exit from
+ * *subprog* from exit from *callback*. In the former
+ * case, we need to propagate r0 precision, if
+ * necessary. In the former we never do that.
+ */
+ r0_precise = subseq_idx - 1 >= 0 &&
+ bpf_pseudo_call(&env->prog->insnsi[subseq_idx - 1]) &&
+ bt_is_reg_set(bt, BPF_REG_0);
+
+ bt_clear_reg(bt, BPF_REG_0);
+ if (bt_subprog_enter(bt))
+ return -EFAULT;
+
+ if (r0_precise)
+ bt_set_reg(bt, BPF_REG_0);
+ /* r6-r9 and stack slots will stay set in caller frame
+ * bitmasks until we return back from callee(s)
+ */
+ return 0;
} else if (BPF_SRC(insn->code) == BPF_X) {
- if (!(*reg_mask & (dreg | sreg)))
+ if (!bt_is_reg_set(bt, dreg) && !bt_is_reg_set(bt, sreg))
return 0;
/* dreg <cond> sreg
* Both dreg and sreg need precision before
@@ -3285,7 +3640,8 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
* before it would be equally necessary to
* propagate it to dreg.
*/
- *reg_mask |= (sreg | dreg);
+ bt_set_reg(bt, dreg);
+ bt_set_reg(bt, sreg);
/* else dreg <cond> K
* Only dreg still needs precision before
* this insn, so for the K-based conditional
@@ -3293,9 +3649,9 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx,
*/
}
} else if (class == BPF_LD) {
- if (!(*reg_mask & dreg))
+ if (!bt_is_reg_set(bt, dreg))
return 0;
- *reg_mask &= ~dreg;
+ bt_clear_reg(bt, dreg);
/* It's ld_imm64 or ld_abs or ld_ind.
* For ld_imm64 no further tracking of precision
* into parent is necessary
@@ -3366,6 +3722,11 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
struct bpf_reg_state *reg;
int i, j;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "mark_precise: frame%d: falling back to forcing all scalars precise\n",
+ st->curframe);
+ }
+
/* big hammer: mark all scalars precise in this path.
* pop_stack may still get !precise scalars.
* We also skip current state and go straight to first parent state,
@@ -3377,17 +3738,25 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
func = st->frame[i];
for (j = 0; j < BPF_REG_FP; j++) {
reg = &func->regs[j];
- if (reg->type != SCALAR_VALUE)
+ if (reg->type != SCALAR_VALUE || reg->precise)
continue;
reg->precise = true;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "force_precise: frame%d: forcing r%d to be precise\n",
+ i, j);
+ }
}
for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
if (!is_spilled_reg(&func->stack[j]))
continue;
reg = &func->stack[j].spilled_ptr;
- if (reg->type != SCALAR_VALUE)
+ if (reg->type != SCALAR_VALUE || reg->precise)
continue;
reg->precise = true;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "force_precise: frame%d: forcing fp%d to be precise\n",
+ i, -(j + 1) * 8);
+ }
}
}
}
@@ -3418,6 +3787,96 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
}
}
+static bool idset_contains(struct bpf_idset *s, u32 id)
+{
+ u32 i;
+
+ for (i = 0; i < s->count; ++i)
+ if (s->ids[i] == id)
+ return true;
+
+ return false;
+}
+
+static int idset_push(struct bpf_idset *s, u32 id)
+{
+ if (WARN_ON_ONCE(s->count >= ARRAY_SIZE(s->ids)))
+ return -EFAULT;
+ s->ids[s->count++] = id;
+ return 0;
+}
+
+static void idset_reset(struct bpf_idset *s)
+{
+ s->count = 0;
+}
+
+/* Collect a set of IDs for all registers currently marked as precise in env->bt.
+ * Mark all registers with these IDs as precise.
+ */
+static int mark_precise_scalar_ids(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_idset *precise_ids = &env->idset_scratch;
+ struct backtrack_state *bt = &env->bt;
+ struct bpf_func_state *func;
+ struct bpf_reg_state *reg;
+ DECLARE_BITMAP(mask, 64);
+ int i, fr;
+
+ idset_reset(precise_ids);
+
+ for (fr = bt->frame; fr >= 0; fr--) {
+ func = st->frame[fr];
+
+ bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr));
+ for_each_set_bit(i, mask, 32) {
+ reg = &func->regs[i];
+ if (!reg->id || reg->type != SCALAR_VALUE)
+ continue;
+ if (idset_push(precise_ids, reg->id))
+ return -EFAULT;
+ }
+
+ bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
+ for_each_set_bit(i, mask, 64) {
+ if (i >= func->allocated_stack / BPF_REG_SIZE)
+ break;
+ if (!is_spilled_scalar_reg(&func->stack[i]))
+ continue;
+ reg = &func->stack[i].spilled_ptr;
+ if (!reg->id)
+ continue;
+ if (idset_push(precise_ids, reg->id))
+ return -EFAULT;
+ }
+ }
+
+ for (fr = 0; fr <= st->curframe; ++fr) {
+ func = st->frame[fr];
+
+ for (i = BPF_REG_0; i < BPF_REG_10; ++i) {
+ reg = &func->regs[i];
+ if (!reg->id)
+ continue;
+ if (!idset_contains(precise_ids, reg->id))
+ continue;
+ bt_set_frame_reg(bt, fr, i);
+ }
+ for (i = 0; i < func->allocated_stack / BPF_REG_SIZE; ++i) {
+ if (!is_spilled_scalar_reg(&func->stack[i]))
+ continue;
+ reg = &func->stack[i].spilled_ptr;
+ if (!reg->id)
+ continue;
+ if (!idset_contains(precise_ids, reg->id))
+ continue;
+ bt_set_frame_slot(bt, fr, i);
+ }
+ }
+
+ return 0;
+}
+
/*
* __mark_chain_precision() backtracks BPF program instruction sequence and
* chain of verifier states making sure that register *regno* (if regno >= 0)
@@ -3505,62 +3964,74 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
* mark_all_scalars_imprecise() to hopefully get more permissive and generic
* finalized states which help in short circuiting more future states.
*/
-static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno,
- int spi)
+static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
+ struct backtrack_state *bt = &env->bt;
struct bpf_verifier_state *st = env->cur_state;
int first_idx = st->first_insn_idx;
int last_idx = env->insn_idx;
+ int subseq_idx = -1;
struct bpf_func_state *func;
struct bpf_reg_state *reg;
- u32 reg_mask = regno >= 0 ? 1u << regno : 0;
- u64 stack_mask = spi >= 0 ? 1ull << spi : 0;
bool skip_first = true;
- bool new_marks = false;
- int i, err;
+ int i, fr, err;
if (!env->bpf_capable)
return 0;
+ /* set frame number from which we are starting to backtrack */
+ bt_init(bt, env->cur_state->curframe);
+
/* Do sanity checks against current state of register and/or stack
* slot, but don't set precise flag in current state, as precision
* tracking in the current state is unnecessary.
*/
- func = st->frame[frame];
+ func = st->frame[bt->frame];
if (regno >= 0) {
reg = &func->regs[regno];
if (reg->type != SCALAR_VALUE) {
WARN_ONCE(1, "backtracing misuse");
return -EFAULT;
}
- new_marks = true;
+ bt_set_reg(bt, regno);
}
- while (spi >= 0) {
- if (!is_spilled_reg(&func->stack[spi])) {
- stack_mask = 0;
- break;
- }
- reg = &func->stack[spi].spilled_ptr;
- if (reg->type != SCALAR_VALUE) {
- stack_mask = 0;
- break;
- }
- new_marks = true;
- break;
- }
-
- if (!new_marks)
- return 0;
- if (!reg_mask && !stack_mask)
+ if (bt_empty(bt))
return 0;
for (;;) {
DECLARE_BITMAP(mask, 64);
u32 history = st->jmp_history_cnt;
- if (env->log.level & BPF_LOG_LEVEL2)
- verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
+ bt->frame, last_idx, first_idx, subseq_idx);
+ }
+
+ /* If some register with scalar ID is marked as precise,
+ * make sure that all registers sharing this ID are also precise.
+ * This is needed to estimate effect of find_equal_scalars().
+ * Do this at the last instruction of each state,
+ * bpf_reg_state::id fields are valid for these instructions.
+ *
+ * Allows to track precision in situation like below:
+ *
+ * r2 = unknown value
+ * ...
+ * --- state #0 ---
+ * ...
+ * r1 = r2 // r1 and r2 now share the same ID
+ * ...
+ * --- state #1 {r1.id = A, r2.id = A} ---
+ * ...
+ * if (r2 > 10) goto exit; // find_equal_scalars() assigns range to r1
+ * ...
+ * --- state #2 {r1.id = A, r2.id = A} ---
+ * r3 = r10
+ * r3 += r1 // need to mark both r1 and r2
+ */
+ if (mark_precise_scalar_ids(env, st))
+ return -EFAULT;
if (last_idx < 0) {
/* we are at the entry into subprog, which
@@ -3571,12 +4042,13 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
if (st->curframe == 0 &&
st->frame[0]->subprogno > 0 &&
st->frame[0]->callsite == BPF_MAIN_FUNC &&
- stack_mask == 0 && (reg_mask & ~0x3e) == 0) {
- bitmap_from_u64(mask, reg_mask);
+ bt_stack_mask(bt) == 0 &&
+ (bt_reg_mask(bt) & ~BPF_REGMASK_ARGS) == 0) {
+ bitmap_from_u64(mask, bt_reg_mask(bt));
for_each_set_bit(i, mask, 32) {
reg = &st->frame[0]->regs[i];
if (reg->type != SCALAR_VALUE) {
- reg_mask &= ~(1u << i);
+ bt_clear_reg(bt, i);
continue;
}
reg->precise = true;
@@ -3584,8 +4056,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
return 0;
}
- verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n",
- st->frame[0]->subprogno, reg_mask, stack_mask);
+ verbose(env, "BUG backtracking func entry subprog %d reg_mask %x stack_mask %llx\n",
+ st->frame[0]->subprogno, bt_reg_mask(bt), bt_stack_mask(bt));
WARN_ONCE(1, "verifier backtracking bug");
return -EFAULT;
}
@@ -3595,15 +4067,16 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
err = 0;
skip_first = false;
} else {
- err = backtrack_insn(env, i, &reg_mask, &stack_mask);
+ err = backtrack_insn(env, i, subseq_idx, bt);
}
if (err == -ENOTSUPP) {
- mark_all_scalars_precise(env, st);
+ mark_all_scalars_precise(env, env->cur_state);
+ bt_reset(bt);
return 0;
} else if (err) {
return err;
}
- if (!reg_mask && !stack_mask)
+ if (bt_empty(bt))
/* Found assignment(s) into tracked register in this state.
* Since this state is already marked, just return.
* Nothing to be tracked further in the parent state.
@@ -3611,6 +4084,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
return 0;
if (i == first_idx)
break;
+ subseq_idx = i;
i = get_prev_insn_idx(st, i, &history);
if (i >= env->prog->len) {
/* This can happen if backtracking reached insn 0
@@ -3628,84 +4102,95 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int r
if (!st)
break;
- new_marks = false;
- func = st->frame[frame];
- bitmap_from_u64(mask, reg_mask);
- for_each_set_bit(i, mask, 32) {
- reg = &func->regs[i];
- if (reg->type != SCALAR_VALUE) {
- reg_mask &= ~(1u << i);
- continue;
+ for (fr = bt->frame; fr >= 0; fr--) {
+ func = st->frame[fr];
+ bitmap_from_u64(mask, bt_frame_reg_mask(bt, fr));
+ for_each_set_bit(i, mask, 32) {
+ reg = &func->regs[i];
+ if (reg->type != SCALAR_VALUE) {
+ bt_clear_frame_reg(bt, fr, i);
+ continue;
+ }
+ if (reg->precise)
+ bt_clear_frame_reg(bt, fr, i);
+ else
+ reg->precise = true;
}
- if (!reg->precise)
- new_marks = true;
- reg->precise = true;
- }
- bitmap_from_u64(mask, stack_mask);
- for_each_set_bit(i, mask, 64) {
- if (i >= func->allocated_stack / BPF_REG_SIZE) {
- /* the sequence of instructions:
- * 2: (bf) r3 = r10
- * 3: (7b) *(u64 *)(r3 -8) = r0
- * 4: (79) r4 = *(u64 *)(r10 -8)
- * doesn't contain jmps. It's backtracked
- * as a single block.
- * During backtracking insn 3 is not recognized as
- * stack access, so at the end of backtracking
- * stack slot fp-8 is still marked in stack_mask.
- * However the parent state may not have accessed
- * fp-8 and it's "unallocated" stack space.
- * In such case fallback to conservative.
- */
- mark_all_scalars_precise(env, st);
- return 0;
- }
+ bitmap_from_u64(mask, bt_frame_stack_mask(bt, fr));
+ for_each_set_bit(i, mask, 64) {
+ if (i >= func->allocated_stack / BPF_REG_SIZE) {
+ /* the sequence of instructions:
+ * 2: (bf) r3 = r10
+ * 3: (7b) *(u64 *)(r3 -8) = r0
+ * 4: (79) r4 = *(u64 *)(r10 -8)
+ * doesn't contain jmps. It's backtracked
+ * as a single block.
+ * During backtracking insn 3 is not recognized as
+ * stack access, so at the end of backtracking
+ * stack slot fp-8 is still marked in stack_mask.
+ * However the parent state may not have accessed
+ * fp-8 and it's "unallocated" stack space.
+ * In such case fallback to conservative.
+ */
+ mark_all_scalars_precise(env, env->cur_state);
+ bt_reset(bt);
+ return 0;
+ }
- if (!is_spilled_reg(&func->stack[i])) {
- stack_mask &= ~(1ull << i);
- continue;
+ if (!is_spilled_scalar_reg(&func->stack[i])) {
+ bt_clear_frame_slot(bt, fr, i);
+ continue;
+ }
+ reg = &func->stack[i].spilled_ptr;
+ if (reg->precise)
+ bt_clear_frame_slot(bt, fr, i);
+ else
+ reg->precise = true;
}
- reg = &func->stack[i].spilled_ptr;
- if (reg->type != SCALAR_VALUE) {
- stack_mask &= ~(1ull << i);
- continue;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
+ bt_frame_reg_mask(bt, fr));
+ verbose(env, "mark_precise: frame%d: parent state regs=%s ",
+ fr, env->tmp_str_buf);
+ fmt_stack_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
+ bt_frame_stack_mask(bt, fr));
+ verbose(env, "stack=%s: ", env->tmp_str_buf);
+ print_verifier_state(env, func, true);
}
- if (!reg->precise)
- new_marks = true;
- reg->precise = true;
- }
- if (env->log.level & BPF_LOG_LEVEL2) {
- verbose(env, "parent %s regs=%x stack=%llx marks:",
- new_marks ? "didn't have" : "already had",
- reg_mask, stack_mask);
- print_verifier_state(env, func, true);
}
- if (!reg_mask && !stack_mask)
- break;
- if (!new_marks)
- break;
+ if (bt_empty(bt))
+ return 0;
+ subseq_idx = first_idx;
last_idx = st->last_insn_idx;
first_idx = st->first_insn_idx;
}
+
+ /* if we still have requested precise regs or slots, we missed
+ * something (e.g., stack access through non-r10 register), so
+ * fallback to marking all precise
+ */
+ if (!bt_empty(bt)) {
+ mark_all_scalars_precise(env, env->cur_state);
+ bt_reset(bt);
+ }
+
return 0;
}
int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
- return __mark_chain_precision(env, env->cur_state->curframe, regno, -1);
-}
-
-static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno)
-{
- return __mark_chain_precision(env, frame, regno, -1);
+ return __mark_chain_precision(env, regno);
}
-static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi)
+/* mark_chain_precision_batch() assumes that env->bt is set in the caller to
+ * desired reg and stack masks across all relevant frames
+ */
+static int mark_chain_precision_batch(struct bpf_verifier_env *env)
{
- return __mark_chain_precision(env, frame, -1, spi);
+ return __mark_chain_precision(env, -1);
}
static bool is_spillable_regtype(enum bpf_reg_type type)
@@ -4070,6 +4555,7 @@ static void mark_reg_stack_read(struct bpf_verifier_env *env,
for (i = min_off; i < max_off; i++) {
slot = -i - 1;
spi = slot / BPF_REG_SIZE;
+ mark_stack_slot_scratched(env, spi);
stype = ptr_state->stack[spi].slot_type;
if (stype[slot % BPF_REG_SIZE] != STACK_ZERO)
break;
@@ -4121,6 +4607,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
stype = reg_state->stack[spi].slot_type;
reg = &reg_state->stack[spi].spilled_ptr;
+ mark_stack_slot_scratched(env, spi);
+
if (is_spilled_reg(&reg_state->stack[spi])) {
u8 spill_size = 1;
@@ -4502,20 +4990,22 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
struct bpf_reg_state *reg, u32 regno)
{
const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id);
- int perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+ int perm_flags;
const char *reg_name = "";
- /* Only unreferenced case accepts untrusted pointers */
- if (kptr_field->type == BPF_KPTR_UNREF)
- perm_flags |= PTR_UNTRUSTED;
+ if (btf_is_kernel(reg->btf)) {
+ perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;
+
+ /* Only unreferenced case accepts untrusted pointers */
+ if (kptr_field->type == BPF_KPTR_UNREF)
+ perm_flags |= PTR_UNTRUSTED;
+ } else {
+ perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
+ }
if (base_type(reg->type) != PTR_TO_BTF_ID || (type_flag(reg->type) & ~perm_flags))
goto bad_type;
- if (!btf_is_kernel(reg->btf)) {
- verbose(env, "R%d must point to kernel BTF\n", regno);
- return -EINVAL;
- }
/* We need to verify reg->type and reg->btf, before accessing reg->btf */
reg_name = btf_type_name(reg->btf, reg->btf_id);
@@ -4528,7 +5018,7 @@ static int map_kptr_match_type(struct bpf_verifier_env *env,
if (__check_ptr_off_reg(env, reg, regno, true))
return -EACCES;
- /* A full type match is needed, as BTF can be vmlinux or module BTF, and
+ /* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and
* we also need to take into account the reg->off.
*
* We want to support cases like:
@@ -4574,7 +5064,9 @@ bad_type:
*/
static bool in_rcu_cs(struct bpf_verifier_env *env)
{
- return env->cur_state->active_rcu_lock || !env->prog->aux->sleepable;
+ return env->cur_state->active_rcu_lock ||
+ env->cur_state->active_lock.ptr ||
+ !env->prog->aux->sleepable;
}
/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
@@ -4932,12 +5424,25 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
return reg->type == PTR_TO_FLOW_KEYS;
}
+static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
+#ifdef CONFIG_NET
+ [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
+ [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+ [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
+#endif
+ [CONST_PTR_TO_MAP] = btf_bpf_map_id,
+};
+
static bool is_trusted_reg(const struct bpf_reg_state *reg)
{
/* A referenced register is always trusted. */
if (reg->ref_obj_id)
return true;
+ /* Types listed in the reg2btf_ids are always trusted */
+ if (reg2btf_ids[base_type(reg->type)])
+ return true;
+
/* If a register is not referenced, it is trusted if it has 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
@@ -5093,16 +5598,17 @@ static int update_stack_depth(struct bpf_verifier_env *env,
* Since recursion is prevented by check_cfg() this algorithm
* only needs a local stack of MAX_CALL_FRAMES to remember callsites
*/
-static int check_max_stack_depth(struct bpf_verifier_env *env)
+static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx)
{
- int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
+ int depth = 0, frame = 0, i, subprog_end;
bool tail_call_reachable = false;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
int j;
+ i = subprog[idx].start;
process_func:
/* protect against potential stack overflow that might happen when
* bpf2bpf calls get combined with tailcalls. Limit the caller's stack
@@ -5141,7 +5647,7 @@ process_func:
continue_func:
subprog_end = subprog[idx + 1].start;
for (; i < subprog_end; i++) {
- int next_insn;
+ int next_insn, sidx;
if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i))
continue;
@@ -5151,21 +5657,23 @@ continue_func:
/* find the callee */
next_insn = i + insn[i].imm + 1;
- idx = find_subprog(env, next_insn);
- if (idx < 0) {
+ sidx = find_subprog(env, next_insn);
+ if (sidx < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
next_insn);
return -EFAULT;
}
- if (subprog[idx].is_async_cb) {
- if (subprog[idx].has_tail_call) {
+ if (subprog[sidx].is_async_cb) {
+ if (subprog[sidx].has_tail_call) {
verbose(env, "verifier bug. subprog has tail_call and async cb\n");
return -EFAULT;
}
- /* async callbacks don't increase bpf prog stack size */
- continue;
+ /* async callbacks don't increase bpf prog stack size unless called directly */
+ if (!bpf_pseudo_call(insn + i))
+ continue;
}
i = next_insn;
+ idx = sidx;
if (subprog[idx].has_tail_call)
tail_call_reachable = true;
@@ -5201,6 +5709,22 @@ continue_func:
goto continue_func;
}
+static int check_max_stack_depth(struct bpf_verifier_env *env)
+{
+ struct bpf_subprog_info *si = env->subprog_info;
+ int ret;
+
+ for (int i = 0; i < env->subprog_cnt; i++) {
+ if (!i || si[i].is_async_cb) {
+ ret = check_max_stack_depth_subprog(env, i);
+ if (ret < 0)
+ return ret;
+ }
+ continue;
+ }
+ return 0;
+}
+
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
const struct bpf_insn *insn, int idx)
@@ -5314,6 +5838,147 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
__reg_combine_64_into_32(reg);
}
+static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->smin_value = reg->s32_min_value = S8_MIN;
+ reg->smax_value = reg->s32_max_value = S8_MAX;
+ } else if (size == 2) {
+ reg->smin_value = reg->s32_min_value = S16_MIN;
+ reg->smax_value = reg->s32_max_value = S16_MAX;
+ } else {
+ /* size == 4 */
+ reg->smin_value = reg->s32_min_value = S32_MIN;
+ reg->smax_value = reg->s32_max_value = S32_MAX;
+ }
+ reg->umin_value = reg->u32_min_value = 0;
+ reg->umax_value = U64_MAX;
+ reg->u32_max_value = U32_MAX;
+ reg->var_off = tnum_unknown;
+}
+
+static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
+ u64 top_smax_value, top_smin_value;
+ u64 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u64_cval = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u64_cval);
+ else if (size == 2)
+ reg->var_off = tnum_const((s16)u64_cval);
+ else
+ /* size == 4 */
+ reg->var_off = tnum_const((s32)u64_cval);
+
+ u64_cval = reg->var_off.value;
+ reg->smax_value = reg->smin_value = u64_cval;
+ reg->umax_value = reg->umin_value = u64_cval;
+ reg->s32_max_value = reg->s32_min_value = u64_cval;
+ reg->u32_max_value = reg->u32_min_value = u64_cval;
+ return;
+ }
+
+ top_smax_value = ((u64)reg->smax_value >> num_bits) << num_bits;
+ top_smin_value = ((u64)reg->smin_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s64_min and s64_min after sign extension */
+ if (size == 1) {
+ init_s64_max = (s8)reg->smax_value;
+ init_s64_min = (s8)reg->smin_value;
+ } else if (size == 2) {
+ init_s64_max = (s16)reg->smax_value;
+ init_s64_min = (s16)reg->smin_value;
+ } else {
+ init_s64_max = (s32)reg->smax_value;
+ init_s64_min = (s32)reg->smin_value;
+ }
+
+ s64_max = max(init_s64_max, init_s64_min);
+ s64_min = min(init_s64_max, init_s64_min);
+
+ /* both of s64_max/s64_min positive or negative */
+ if ((s64_max >= 0) == (s64_min >= 0)) {
+ reg->smin_value = reg->s32_min_value = s64_min;
+ reg->smax_value = reg->s32_max_value = s64_max;
+ reg->umin_value = reg->u32_min_value = s64_min;
+ reg->umax_value = reg->u32_max_value = s64_max;
+ reg->var_off = tnum_range(s64_min, s64_max);
+ return;
+ }
+
+out:
+ set_sext64_default_val(reg, size);
+}
+
+static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
+{
+ if (size == 1) {
+ reg->s32_min_value = S8_MIN;
+ reg->s32_max_value = S8_MAX;
+ } else {
+ /* size == 2 */
+ reg->s32_min_value = S16_MIN;
+ reg->s32_max_value = S16_MAX;
+ }
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
+{
+ s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
+ u32 top_smax_value, top_smin_value;
+ u32 num_bits = size * 8;
+
+ if (tnum_is_const(reg->var_off)) {
+ u32_val = reg->var_off.value;
+ if (size == 1)
+ reg->var_off = tnum_const((s8)u32_val);
+ else
+ reg->var_off = tnum_const((s16)u32_val);
+
+ u32_val = reg->var_off.value;
+ reg->s32_min_value = reg->s32_max_value = u32_val;
+ reg->u32_min_value = reg->u32_max_value = u32_val;
+ return;
+ }
+
+ top_smax_value = ((u32)reg->s32_max_value >> num_bits) << num_bits;
+ top_smin_value = ((u32)reg->s32_min_value >> num_bits) << num_bits;
+
+ if (top_smax_value != top_smin_value)
+ goto out;
+
+ /* find the s32_min and s32_min after sign extension */
+ if (size == 1) {
+ init_s32_max = (s8)reg->s32_max_value;
+ init_s32_min = (s8)reg->s32_min_value;
+ } else {
+ /* size == 2 */
+ init_s32_max = (s16)reg->s32_max_value;
+ init_s32_min = (s16)reg->s32_min_value;
+ }
+ s32_max = max(init_s32_max, init_s32_min);
+ s32_min = min(init_s32_max, init_s32_min);
+
+ if ((s32_min >= 0) == (s32_max >= 0)) {
+ reg->s32_min_value = s32_min;
+ reg->s32_max_value = s32_max;
+ reg->u32_min_value = (u32)s32_min;
+ reg->u32_max_value = (u32)s32_max;
+ return;
+ }
+
+out:
+ set_sext32_default_val(reg, size);
+}
+
static bool bpf_map_is_rdonly(const struct bpf_map *map)
{
/* A map is considered read-only if the following condition are true:
@@ -5334,7 +5999,8 @@ static bool bpf_map_is_rdonly(const struct bpf_map *map)
!bpf_map_write_active(map);
}
-static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
+ bool is_ldsx)
{
void *ptr;
u64 addr;
@@ -5347,13 +6013,13 @@ static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
switch (size) {
case sizeof(u8):
- *val = (u64)*(u8 *)ptr;
+ *val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
break;
case sizeof(u16):
- *val = (u64)*(u16 *)ptr;
+ *val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
break;
case sizeof(u32):
- *val = (u64)*(u32 *)ptr;
+ *val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
break;
case sizeof(u64):
*val = *(u64 *)ptr;
@@ -5537,7 +6203,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
* program allocated objects (which always have ref_obj_id > 0),
* but not for untrusted PTR_TO_BTF_ID | MEM_ALLOC.
*/
- if (atype != BPF_READ && reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
+ if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) {
verbose(env, "only read is supported\n");
return -EACCES;
}
@@ -5586,6 +6252,11 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
type_is_rcu_or_null(env, reg, field_name, btf_id)) {
/* __rcu tagged pointers can be NULL */
flag |= MEM_RCU | PTR_MAYBE_NULL;
+
+ /* We always trust them */
+ if (type_is_rcu_or_null(env, reg, field_name, btf_id) &&
+ flag & PTR_UNTRUSTED)
+ flag &= ~PTR_UNTRUSTED;
} else if (flag & (MEM_PERCPU | MEM_USER)) {
/* keep as-is */
} else {
@@ -5767,7 +6438,7 @@ static int check_stack_access_within_bounds(
*/
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
int off, int bpf_size, enum bpf_access_type t,
- int value_regno, bool strict_alignment_once)
+ int value_regno, bool strict_alignment_once, bool is_ldsx)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_reg_state *reg = regs + regno;
@@ -5828,7 +6499,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
u64 val = 0;
err = bpf_map_direct_read(map, map_off, size,
- &val);
+ &val, is_ldsx);
if (err)
return err;
@@ -5998,8 +6669,11 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
regs[value_regno].type == SCALAR_VALUE) {
- /* b/h/w load zero-extends, mark upper bits as known 0 */
- coerce_reg_to_size(&regs[value_regno], size);
+ if (!is_ldsx)
+ /* b/h/w load zero-extends, mark upper bits as known 0 */
+ coerce_reg_to_size(&regs[value_regno], size);
+ else
+ coerce_reg_to_size_sx(&regs[value_regno], size);
}
return err;
}
@@ -6091,17 +6765,17 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
* case to simulate the register fill.
*/
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_READ, -1, true);
+ BPF_SIZE(insn->code), BPF_READ, -1, true, false);
if (!err && load_reg >= 0)
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
BPF_SIZE(insn->code), BPF_READ, load_reg,
- true);
+ true, false);
if (err)
return err;
/* Check whether we can write into the same memory. */
err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
- BPF_SIZE(insn->code), BPF_WRITE, -1, true);
+ BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
if (err)
return err;
@@ -6347,7 +7021,7 @@ static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
return zero_size_allowed ? 0 : -EACCES;
return check_mem_access(env, env->insn_idx, regno, offset, BPF_B,
- atype, -1, false);
+ atype, -1, false, false);
}
fallthrough;
@@ -6680,7 +7354,7 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno,
* type, and declare it as 'const struct bpf_dynptr *' in their prototype.
*/
static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn_idx,
- enum bpf_arg_type arg_type)
+ enum bpf_arg_type arg_type, int clone_ref_obj_id)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
int err;
@@ -6719,12 +7393,12 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
/* we write BPF_DW bits (8 bytes) at a time */
for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
- err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx);
+ err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx, clone_ref_obj_id);
} else /* MEM_RDONLY and None case from above */ {
/* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */
if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) {
@@ -6812,7 +7486,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id
for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
err = check_mem_access(env, insn_idx, regno,
- i, BPF_DW, BPF_WRITE, -1, false);
+ i, BPF_DW, BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -7146,14 +7820,18 @@ static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
* ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
* but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
*
+ * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type.
+ *
* Therefore we fold these flags depending on the arg_type before comparison.
*/
if (arg_type & MEM_RDONLY)
type &= ~MEM_RDONLY;
if (arg_type & PTR_MAYBE_NULL)
type &= ~PTR_MAYBE_NULL;
+ if (base_type(arg_type) == ARG_PTR_TO_MEM)
+ type &= ~DYNPTR_TYPE_FLAG_MASK;
- if (meta->func_id == BPF_FUNC_kptr_xchg && type & MEM_ALLOC)
+ if (meta->func_id == BPF_FUNC_kptr_xchg && type_is_alloc(type))
type &= ~MEM_ALLOC;
for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
@@ -7242,7 +7920,10 @@ found:
verbose(env, "verifier internal error: unimplemented handling of MEM_ALLOC\n");
return -EFAULT;
}
- /* Handled by helper specific checks */
+ if (meta->func_id == BPF_FUNC_kptr_xchg) {
+ if (map_kptr_match_type(env, meta->kptr_field, reg, regno))
+ return -EACCES;
+ }
break;
case PTR_TO_BTF_ID | MEM_PERCPU:
case PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED:
@@ -7294,17 +7975,6 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK)
return 0;
- if ((type_is_ptr_alloc_obj(type) || type_is_non_owning_ref(type)) && reg->off) {
- if (reg_find_field_offset(reg, reg->off, BPF_GRAPH_NODE_OR_ROOT))
- return __check_ptr_off_reg(env, reg, regno, true);
-
- verbose(env, "R%d must have zero offset when passed to release func\n",
- regno);
- verbose(env, "No graph node or root found at R%d type:%s off:%d\n", regno,
- btf_type_name(reg->btf, reg->btf_id), reg->off);
- return -EINVAL;
- }
-
/* Doing check_ptr_off_reg check for the offset will catch this
* because fixed_off_ok is false, but checking here allows us
* to give the user a better error message.
@@ -7339,6 +8009,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
case PTR_TO_BTF_ID | PTR_TRUSTED:
case PTR_TO_BTF_ID | MEM_RCU:
case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
+ case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU:
/* When referenced PTR_TO_BTF_ID is passed to release function,
* its fixed offset must be 0. In the other cases, fixed offset
* can be non-zero. This was already checked above. So pass
@@ -7634,7 +8305,7 @@ skip_type_check:
err = check_mem_size_reg(env, reg, regno, true, meta);
break;
case ARG_PTR_TO_DYNPTR:
- err = process_dynptr_func(env, regno, insn_idx, arg_type);
+ err = process_dynptr_func(env, regno, insn_idx, arg_type, 0);
if (err)
return err;
break;
@@ -8181,17 +8852,13 @@ static int set_callee_state(struct bpf_verifier_env *env,
struct bpf_func_state *caller,
struct bpf_func_state *callee, int insn_idx);
-static bool is_callback_calling_kfunc(u32 btf_id);
-
static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx, int subprog,
set_callee_state_fn set_callee_state_cb)
{
struct bpf_verifier_state *state = env->cur_state;
- struct bpf_func_info_aux *func_info_aux;
struct bpf_func_state *caller, *callee;
int err;
- bool is_global = false;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
@@ -8206,13 +8873,10 @@ static int __check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn
return -EFAULT;
}
- func_info_aux = env->prog->aux->func_info_aux;
- if (func_info_aux)
- is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
err = btf_check_subprog_call(env, subprog, caller->regs);
if (err == -EFAULT)
return err;
- if (is_global) {
+ if (subprog_is_global(env, subprog)) {
if (err) {
verbose(env, "Caller passes invalid args into func#%d\n",
subprog);
@@ -8639,19 +9303,33 @@ static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
{
struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
- if (ret_type != RET_INTEGER ||
- (func_id != BPF_FUNC_get_stack &&
- func_id != BPF_FUNC_get_task_stack &&
- func_id != BPF_FUNC_probe_read_str &&
- func_id != BPF_FUNC_probe_read_kernel_str &&
- func_id != BPF_FUNC_probe_read_user_str))
+ if (ret_type != RET_INTEGER)
return;
- ret_reg->smax_value = meta->msize_max_value;
- ret_reg->s32_max_value = meta->msize_max_value;
- ret_reg->smin_value = -MAX_ERRNO;
- ret_reg->s32_min_value = -MAX_ERRNO;
- reg_bounds_sync(ret_reg);
+ switch (func_id) {
+ case BPF_FUNC_get_stack:
+ case BPF_FUNC_get_task_stack:
+ case BPF_FUNC_probe_read_str:
+ case BPF_FUNC_probe_read_kernel_str:
+ case BPF_FUNC_probe_read_user_str:
+ ret_reg->smax_value = meta->msize_max_value;
+ ret_reg->s32_max_value = meta->msize_max_value;
+ ret_reg->smin_value = -MAX_ERRNO;
+ ret_reg->s32_min_value = -MAX_ERRNO;
+ reg_bounds_sync(ret_reg);
+ break;
+ case BPF_FUNC_get_smp_processor_id:
+ ret_reg->umax_value = nr_cpu_ids - 1;
+ ret_reg->u32_max_value = nr_cpu_ids - 1;
+ ret_reg->smax_value = nr_cpu_ids - 1;
+ ret_reg->s32_max_value = nr_cpu_ids - 1;
+ ret_reg->umin_value = 0;
+ ret_reg->u32_min_value = 0;
+ ret_reg->smin_value = 0;
+ ret_reg->s32_min_value = 0;
+ reg_bounds_sync(ret_reg);
+ break;
+ }
}
static int
@@ -8945,7 +9623,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
*/
for (i = 0; i < meta.access_size; i++) {
err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
}
@@ -9327,11 +10005,6 @@ static bool is_kfunc_acquire(struct bpf_kfunc_call_arg_meta *meta)
return meta->kfunc_flags & KF_ACQUIRE;
}
-static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
-{
- return meta->kfunc_flags & KF_RET_NULL;
-}
-
static bool is_kfunc_release(struct bpf_kfunc_call_arg_meta *meta)
{
return meta->kfunc_flags & KF_RELEASE;
@@ -9401,6 +10074,11 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf,
return __kfunc_param_match_suffix(btf, arg, "__szk");
}
+static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg)
+{
+ return __kfunc_param_match_suffix(btf, arg, "__opt");
+}
+
static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg)
{
return __kfunc_param_match_suffix(btf, arg, "__k");
@@ -9554,15 +10232,6 @@ static bool __btf_type_is_scalar_struct(struct bpf_verifier_env *env,
return true;
}
-
-static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
-#ifdef CONFIG_NET
- [PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
- [PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
- [PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
-#endif
-};
-
enum kfunc_ptr_arg_type {
KF_ARG_PTR_TO_CTX,
KF_ARG_PTR_TO_ALLOC_BTF_ID, /* Allocated object */
@@ -9598,6 +10267,7 @@ enum special_kfunc_type {
KF_bpf_dynptr_from_xdp,
KF_bpf_dynptr_slice,
KF_bpf_dynptr_slice_rdwr,
+ KF_bpf_dynptr_clone,
};
BTF_SET_START(special_kfunc_set)
@@ -9617,6 +10287,7 @@ BTF_ID(func, bpf_dynptr_from_skb)
BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
+BTF_ID(func, bpf_dynptr_clone)
BTF_SET_END(special_kfunc_set)
BTF_ID_LIST(special_kfunc_list)
@@ -9638,6 +10309,17 @@ BTF_ID(func, bpf_dynptr_from_skb)
BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
+BTF_ID(func, bpf_dynptr_clone)
+
+static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta)
+{
+ if (meta->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
+ meta->arg_owning_ref) {
+ return false;
+ }
+
+ return meta->kfunc_flags & KF_RET_NULL;
+}
static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta)
{
@@ -9794,6 +10476,7 @@ static int process_kf_arg_ptr_to_btf_id(struct bpf_verifier_env *env,
static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
struct bpf_verifier_state *state = env->cur_state;
+ struct btf_record *rec = reg_btf_record(reg);
if (!state->active_lock.ptr) {
verbose(env, "verifier internal error: ref_set_non_owning w/o active lock\n");
@@ -9806,6 +10489,9 @@ static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state
}
reg->type |= NON_OWN_REF;
+ if (rec->refcount_off >= 0)
+ reg->type |= MEM_RCU;
+
return 0;
}
@@ -10116,6 +10802,8 @@ __process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env,
node_off, btf_name_by_offset(reg->btf, t->name_off));
return -EINVAL;
}
+ meta->arg_btf = reg->btf;
+ meta->arg_btf_id = reg->btf_id;
if (node_off != field->graph_root.node_offset) {
verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n",
@@ -10326,13 +11014,14 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
if (meta->btf == btf_vmlinux &&
meta->func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
- meta->arg_obj_drop.btf = reg->btf;
- meta->arg_obj_drop.btf_id = reg->btf_id;
+ meta->arg_btf = reg->btf;
+ meta->arg_btf_id = reg->btf_id;
}
break;
case KF_ARG_PTR_TO_DYNPTR:
{
enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR;
+ int clone_ref_obj_id = 0;
if (reg->type != PTR_TO_STACK &&
reg->type != CONST_PTR_TO_DYNPTR) {
@@ -10346,12 +11035,28 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
if (is_kfunc_arg_uninit(btf, &args[i]))
dynptr_arg_type |= MEM_UNINIT;
- if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb])
+ if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
dynptr_arg_type |= DYNPTR_TYPE_SKB;
- else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp])
+ } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_xdp]) {
dynptr_arg_type |= DYNPTR_TYPE_XDP;
+ } else if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_clone] &&
+ (dynptr_arg_type & MEM_UNINIT)) {
+ enum bpf_dynptr_type parent_type = meta->initialized_dynptr.type;
+
+ if (parent_type == BPF_DYNPTR_TYPE_INVALID) {
+ verbose(env, "verifier internal error: no dynptr type for parent of clone\n");
+ return -EFAULT;
+ }
- ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type);
+ dynptr_arg_type |= (unsigned int)get_dynptr_type_flag(parent_type);
+ clone_ref_obj_id = meta->initialized_dynptr.ref_obj_id;
+ if (dynptr_type_refcounted(parent_type) && !clone_ref_obj_id) {
+ verbose(env, "verifier internal error: missing ref obj id for parent of clone\n");
+ return -EFAULT;
+ }
+ }
+
+ ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type, clone_ref_obj_id);
if (ret < 0)
return ret;
@@ -10364,6 +11069,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
}
meta->initialized_dynptr.id = id;
meta->initialized_dynptr.type = dynptr_get_type(env, reg);
+ meta->initialized_dynptr.ref_obj_id = dynptr_ref_obj_id(env, reg);
}
break;
@@ -10467,13 +11173,17 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
break;
case KF_ARG_PTR_TO_MEM_SIZE:
{
+ struct bpf_reg_state *buff_reg = &regs[regno];
+ const struct btf_param *buff_arg = &args[i];
struct bpf_reg_state *size_reg = &regs[regno + 1];
const struct btf_param *size_arg = &args[i + 1];
- ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
- if (ret < 0) {
- verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
- return ret;
+ if (!register_is_null(buff_reg) || !is_kfunc_arg_optional(meta->btf, buff_arg)) {
+ ret = check_kfunc_mem_size_reg(env, size_reg, regno + 1);
+ if (ret < 0) {
+ verbose(env, "arg#%d arg#%d memory, len pair leads to invalid memory access\n", i, i + 1);
+ return ret;
+ }
}
if (is_kfunc_arg_const_mem_size(meta->btf, size_arg, size_reg)) {
@@ -10497,10 +11207,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
meta->subprogno = reg->subprogno;
break;
case KF_ARG_PTR_TO_REFCOUNTED_KPTR:
- if (!type_is_ptr_alloc_obj(reg->type) && !type_is_non_owning_ref(reg->type)) {
+ if (!type_is_ptr_alloc_obj(reg->type)) {
verbose(env, "arg#%d is neither owning or non-owning ref\n", i);
return -EINVAL;
}
+ if (!type_is_non_owning_ref(reg->type))
+ meta->arg_owning_ref = true;
rec = reg_btf_record(reg);
if (!rec) {
@@ -10512,12 +11224,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
verbose(env, "arg#%d doesn't point to a type with bpf_refcount field\n", i);
return -EINVAL;
}
- if (rec->refcount_off >= 0) {
- verbose(env, "bpf_refcount_acquire calls are disabled for now\n");
- return -EINVAL;
- }
- meta->arg_refcount_acquire.btf = reg->btf;
- meta->arg_refcount_acquire.btf_id = reg->btf_id;
+
+ meta->arg_btf = reg->btf;
+ meta->arg_btf_id = reg->btf_id;
break;
}
}
@@ -10558,7 +11267,7 @@ static int fetch_kfunc_meta(struct bpf_verifier_env *env,
*kfunc_name = func_name;
func_proto = btf_type_by_id(desc_btf, func->type);
- kfunc_flags = btf_kfunc_id_set_contains(desc_btf, resolve_prog_type(env->prog), func_id);
+ kfunc_flags = btf_kfunc_id_set_contains(desc_btf, func_id, env->prog);
if (!kfunc_flags) {
return -EACCES;
}
@@ -10620,6 +11329,11 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
struct bpf_func_state *state;
struct bpf_reg_state *reg;
+ if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
+ verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
+ return -EACCES;
+ }
+
if (rcu_lock) {
verbose(env, "nested rcu read lock (kernel function %s)\n", func_name);
return -EINVAL;
@@ -10663,6 +11377,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
meta.func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
release_ref_obj_id = regs[BPF_REG_2].ref_obj_id;
insn_aux->insert_off = regs[BPF_REG_2].off;
+ insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id);
err = ref_convert_owning_non_owning(env, release_ref_obj_id);
if (err) {
verbose(env, "kfunc %s#%d conversion of owning ref to non-owning failed\n",
@@ -10749,12 +11464,12 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
} else if (meta.func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl]) {
mark_reg_known_zero(env, regs, BPF_REG_0);
regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
- regs[BPF_REG_0].btf = meta.arg_refcount_acquire.btf;
- regs[BPF_REG_0].btf_id = meta.arg_refcount_acquire.btf_id;
+ regs[BPF_REG_0].btf = meta.arg_btf;
+ regs[BPF_REG_0].btf_id = meta.arg_btf_id;
insn_aux->kptr_struct_meta =
- btf_find_struct_meta(meta.arg_refcount_acquire.btf,
- meta.arg_refcount_acquire.btf_id);
+ btf_find_struct_meta(meta.arg_btf,
+ meta.arg_btf_id);
} else if (meta.func_id == special_kfunc_list[KF_bpf_list_pop_front] ||
meta.func_id == special_kfunc_list[KF_bpf_list_pop_back]) {
struct btf_field *field = meta.arg_list_head.field;
@@ -10884,8 +11599,8 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
if (meta.btf == btf_vmlinux && btf_id_set_contains(&special_kfunc_set, meta.func_id)) {
if (meta.func_id == special_kfunc_list[KF_bpf_obj_drop_impl]) {
insn_aux->kptr_struct_meta =
- btf_find_struct_meta(meta.arg_obj_drop.btf,
- meta.arg_obj_drop.btf_id);
+ btf_find_struct_meta(meta.arg_btf,
+ meta.arg_btf_id);
}
}
}
@@ -12371,7 +13086,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else {
if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
(insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
- BPF_CLASS(insn->code) == BPF_ALU64) {
+ (BPF_CLASS(insn->code) == BPF_ALU64 &&
+ BPF_SRC(insn->code) != BPF_TO_LE)) {
verbose(env, "BPF_END uses reserved fields\n");
return -EINVAL;
}
@@ -12396,11 +13112,24 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else if (opcode == BPF_MOV) {
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0) {
verbose(env, "BPF_MOV uses reserved fields\n");
return -EINVAL;
}
+ if (BPF_CLASS(insn->code) == BPF_ALU) {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ } else {
+ if (insn->off != 0 && insn->off != 8 && insn->off != 16 &&
+ insn->off != 32) {
+ verbose(env, "BPF_MOV uses reserved fields\n");
+ return -EINVAL;
+ }
+ }
+
/* check src operand */
err = check_reg_arg(env, insn->src_reg, SRC_OP);
if (err)
@@ -12420,20 +13149,46 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (BPF_SRC(insn->code) == BPF_X) {
struct bpf_reg_state *src_reg = regs + insn->src_reg;
struct bpf_reg_state *dst_reg = regs + insn->dst_reg;
+ bool need_id = src_reg->type == SCALAR_VALUE && !src_reg->id &&
+ !tnum_is_const(src_reg->var_off);
if (BPF_CLASS(insn->code) == BPF_ALU64) {
- /* case: R1 = R2
- * copy register state to dest reg
- */
- if (src_reg->type == SCALAR_VALUE && !src_reg->id)
- /* Assign src and dst registers the same ID
- * that will be used by find_equal_scalars()
- * to propagate min/max range.
+ if (insn->off == 0) {
+ /* case: R1 = R2
+ * copy register state to dest reg
*/
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = DEF_NOT_SUBREG;
+ if (need_id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ /* case: R1 = (s8, s16 s32)R2 */
+ if (is_pointer_value(env, insn->src_reg)) {
+ verbose(env,
+ "R%d sign-extension part of pointer\n",
+ insn->src_reg);
+ return -EACCES;
+ } else if (src_reg->type == SCALAR_VALUE) {
+ bool no_sext;
+
+ no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
+ } else {
+ mark_reg_unknown(env, regs, insn->dst_reg);
+ }
+ }
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -12442,19 +13197,33 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
-
- if (is_src_reg_u32 && !src_reg->id)
- src_reg->id = ++env->id_gen;
- copy_register_state(dst_reg, src_reg);
- /* Make sure ID is cleared if src_reg is not in u32 range otherwise
- * dst_reg min/max could be incorrectly
- * propagated into src_reg by find_equal_scalars()
- */
- if (!is_src_reg_u32)
- dst_reg->id = 0;
- dst_reg->live |= REG_LIVE_WRITTEN;
- dst_reg->subreg_def = env->insn_idx + 1;
+ if (insn->off == 0) {
+ bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX;
+
+ if (is_src_reg_u32 && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ /* Make sure ID is cleared if src_reg is not in u32
+ * range otherwise dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ if (!is_src_reg_u32)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ } else {
+ /* case: W1 = (s8, s16)W2 */
+ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1));
+
+ if (no_sext && need_id)
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
+ if (!no_sext)
+ dst_reg->id = 0;
+ dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
+ coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
+ }
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
@@ -12485,7 +13254,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
} else { /* all other ALU ops: and, sub, xor, add, ... */
if (BPF_SRC(insn->code) == BPF_X) {
- if (insn->imm != 0 || insn->off != 0) {
+ if (insn->imm != 0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -12494,7 +13264,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
if (err)
return err;
} else {
- if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
+ if (insn->src_reg != BPF_REG_0 || insn->off > 1 ||
+ (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
verbose(env, "BPF_ALU uses reserved fields\n");
return -EINVAL;
}
@@ -12776,7 +13547,7 @@ static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
bool is_jmp32)
{
if (__is_pointer_value(false, reg)) {
- if (!reg_type_not_null(reg->type))
+ if (!reg_not_null(reg))
return -1;
/* If pointer is valid tests against zero will fail so we can
@@ -13279,6 +14050,12 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
return -EINVAL;
}
+ /* check src2 operand */
+ err = check_reg_arg(env, insn->dst_reg, SRC_OP);
+ if (err)
+ return err;
+
+ dst_reg = &regs[insn->dst_reg];
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13290,12 +14067,13 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
if (err)
return err;
- if (is_pointer_value(env, insn->src_reg)) {
+ src_reg = &regs[insn->src_reg];
+ if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) &&
+ is_pointer_value(env, insn->src_reg)) {
verbose(env, "R%d pointer comparison prohibited\n",
insn->src_reg);
return -EACCES;
}
- src_reg = &regs[insn->src_reg];
} else {
if (insn->src_reg != BPF_REG_0) {
verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
@@ -13303,12 +14081,6 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
}
- /* check src2 operand */
- err = check_reg_arg(env, insn->dst_reg, SRC_OP);
- if (err)
- return err;
-
- dst_reg = &regs[insn->dst_reg];
is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
if (BPF_SRC(insn->code) == BPF_K) {
@@ -14038,7 +14810,7 @@ static int visit_func_call_insn(int t, struct bpf_insn *insns,
static int visit_insn(int t, struct bpf_verifier_env *env)
{
struct bpf_insn *insns = env->prog->insnsi, *insn = &insns[t];
- int ret;
+ int ret, off;
if (bpf_pseudo_func(insn))
return visit_func_call_insn(t, insns, env, true);
@@ -14086,14 +14858,19 @@ static int visit_insn(int t, struct bpf_verifier_env *env)
if (BPF_SRC(insn->code) != BPF_K)
return -EINVAL;
+ if (BPF_CLASS(insn->code) == BPF_JMP)
+ off = insn->off;
+ else
+ off = insn->imm;
+
/* unconditional jump with single edge */
- ret = push_insn(t, t + insn->off + 1, FALLTHROUGH, env,
+ ret = push_insn(t, t + off + 1, FALLTHROUGH, env,
true);
if (ret)
return ret;
- mark_prune_point(env, t + insn->off + 1);
- mark_jmp_point(env, t + insn->off + 1);
+ mark_prune_point(env, t + off + 1);
+ mark_jmp_point(env, t + off + 1);
return ret;
@@ -14600,8 +15377,9 @@ static bool range_within(struct bpf_reg_state *old,
* So we look through our idmap to see if this old id has been seen before. If
* so, we require the new id to match; otherwise, we add the id pair to the map.
*/
-static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
+static bool check_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap)
{
+ struct bpf_id_pair *map = idmap->map;
unsigned int i;
/* either both IDs should be set or both should be zero */
@@ -14612,20 +15390,34 @@ static bool check_ids(u32 old_id, u32 cur_id, struct bpf_id_pair *idmap)
return true;
for (i = 0; i < BPF_ID_MAP_SIZE; i++) {
- if (!idmap[i].old) {
+ if (!map[i].old) {
/* Reached an empty slot; haven't seen this id before */
- idmap[i].old = old_id;
- idmap[i].cur = cur_id;
+ map[i].old = old_id;
+ map[i].cur = cur_id;
return true;
}
- if (idmap[i].old == old_id)
- return idmap[i].cur == cur_id;
+ if (map[i].old == old_id)
+ return map[i].cur == cur_id;
+ if (map[i].cur == cur_id)
+ return false;
}
/* We ran out of idmap slots, which should be impossible */
WARN_ON_ONCE(1);
return false;
}
+/* Similar to check_ids(), but allocate a unique temporary ID
+ * for 'old_id' or 'cur_id' of zero.
+ * This makes pairs like '0 vs unique ID', 'unique ID vs 0' valid.
+ */
+static bool check_scalar_ids(u32 old_id, u32 cur_id, struct bpf_idmap *idmap)
+{
+ old_id = old_id ? old_id : ++idmap->tmp_id_gen;
+ cur_id = cur_id ? cur_id : ++idmap->tmp_id_gen;
+
+ return check_ids(old_id, cur_id, idmap);
+}
+
static void clean_func_state(struct bpf_verifier_env *env,
struct bpf_func_state *st)
{
@@ -14724,7 +15516,7 @@ next:
static bool regs_exact(const struct bpf_reg_state *rold,
const struct bpf_reg_state *rcur,
- struct bpf_id_pair *idmap)
+ struct bpf_idmap *idmap)
{
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
check_ids(rold->id, rcur->id, idmap) &&
@@ -14733,7 +15525,7 @@ static bool regs_exact(const struct bpf_reg_state *rold,
/* Returns true if (rold safe implies rcur safe) */
static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
- struct bpf_reg_state *rcur, struct bpf_id_pair *idmap)
+ struct bpf_reg_state *rcur, struct bpf_idmap *idmap)
{
if (!(rold->live & REG_LIVE_READ))
/* explored state didn't use this */
@@ -14770,15 +15562,42 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
switch (base_type(rold->type)) {
case SCALAR_VALUE:
- if (regs_exact(rold, rcur, idmap))
- return true;
- if (env->explore_alu_limits)
- return false;
+ if (env->explore_alu_limits) {
+ /* explore_alu_limits disables tnum_in() and range_within()
+ * logic and requires everything to be strict
+ */
+ return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
+ check_scalar_ids(rold->id, rcur->id, idmap);
+ }
if (!rold->precise)
return true;
- /* new val must satisfy old val knowledge */
+ /* Why check_ids() for scalar registers?
+ *
+ * Consider the following BPF code:
+ * 1: r6 = ... unbound scalar, ID=a ...
+ * 2: r7 = ... unbound scalar, ID=b ...
+ * 3: if (r6 > r7) goto +1
+ * 4: r6 = r7
+ * 5: if (r6 > X) goto ...
+ * 6: ... memory operation using r7 ...
+ *
+ * First verification path is [1-6]:
+ * - at (4) same bpf_reg_state::id (b) would be assigned to r6 and r7;
+ * - at (5) r6 would be marked <= X, find_equal_scalars() would also mark
+ * r7 <= X, because r6 and r7 share same id.
+ * Next verification path is [1-4, 6].
+ *
+ * Instruction (6) would be reached in two states:
+ * I. r6{.id=b}, r7{.id=b} via path 1-6;
+ * II. r6{.id=a}, r7{.id=b} via path 1-4, 6.
+ *
+ * Use check_ids() to distinguish these states.
+ * ---
+ * Also verify that new value satisfies old value range knowledge.
+ */
return range_within(rold, rcur) &&
- tnum_in(rold->var_off, rcur->var_off);
+ tnum_in(rold->var_off, rcur->var_off) &&
+ check_scalar_ids(rold->id, rcur->id, idmap);
case PTR_TO_MAP_KEY:
case PTR_TO_MAP_VALUE:
case PTR_TO_MEM:
@@ -14824,7 +15643,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold,
}
static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
- struct bpf_func_state *cur, struct bpf_id_pair *idmap)
+ struct bpf_func_state *cur, struct bpf_idmap *idmap)
{
int i, spi;
@@ -14927,7 +15746,7 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
}
static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur,
- struct bpf_id_pair *idmap)
+ struct bpf_idmap *idmap)
{
int i;
@@ -14975,13 +15794,13 @@ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_stat
for (i = 0; i < MAX_BPF_REG; i++)
if (!regsafe(env, &old->regs[i], &cur->regs[i],
- env->idmap_scratch))
+ &env->idmap_scratch))
return false;
- if (!stacksafe(env, old, cur, env->idmap_scratch))
+ if (!stacksafe(env, old, cur, &env->idmap_scratch))
return false;
- if (!refsafe(old, cur, env->idmap_scratch))
+ if (!refsafe(old, cur, &env->idmap_scratch))
return false;
return true;
@@ -14996,7 +15815,8 @@ static bool states_equal(struct bpf_verifier_env *env,
if (old->curframe != cur->curframe)
return false;
- memset(env->idmap_scratch, 0, sizeof(env->idmap_scratch));
+ env->idmap_scratch.tmp_id_gen = env->id_gen;
+ memset(&env->idmap_scratch.map, 0, sizeof(env->idmap_scratch.map));
/* Verification state from speculative execution simulation
* must never prune a non-speculative execution one.
@@ -15014,7 +15834,7 @@ static bool states_equal(struct bpf_verifier_env *env,
return false;
if (old->active_lock.id &&
- !check_ids(old->active_lock.id, cur->active_lock.id, env->idmap_scratch))
+ !check_ids(old->active_lock.id, cur->active_lock.id, &env->idmap_scratch))
return false;
if (old->active_rcu_lock != cur->active_rcu_lock)
@@ -15121,20 +15941,25 @@ static int propagate_precision(struct bpf_verifier_env *env,
struct bpf_reg_state *state_reg;
struct bpf_func_state *state;
int i, err = 0, fr;
+ bool first;
for (fr = old->curframe; fr >= 0; fr--) {
state = old->frame[fr];
state_reg = state->regs;
+ first = true;
for (i = 0; i < BPF_REG_FP; i++, state_reg++) {
if (state_reg->type != SCALAR_VALUE ||
!state_reg->precise ||
!(state_reg->live & REG_LIVE_READ))
continue;
- if (env->log.level & BPF_LOG_LEVEL2)
- verbose(env, "frame %d: propagating r%d\n", fr, i);
- err = mark_chain_precision_frame(env, fr, i);
- if (err < 0)
- return err;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ if (first)
+ verbose(env, "frame %d: propagating r%d", fr, i);
+ else
+ verbose(env, ",r%d", i);
+ }
+ bt_set_frame_reg(&env->bt, fr, i);
+ first = false;
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
@@ -15145,14 +15970,24 @@ static int propagate_precision(struct bpf_verifier_env *env,
!state_reg->precise ||
!(state_reg->live & REG_LIVE_READ))
continue;
- if (env->log.level & BPF_LOG_LEVEL2)
- verbose(env, "frame %d: propagating fp%d\n",
- fr, (-i - 1) * BPF_REG_SIZE);
- err = mark_chain_precision_stack_frame(env, fr, i);
- if (err < 0)
- return err;
+ if (env->log.level & BPF_LOG_LEVEL2) {
+ if (first)
+ verbose(env, "frame %d: propagating fp%d",
+ fr, (-i - 1) * BPF_REG_SIZE);
+ else
+ verbose(env, ",fp%d", (-i - 1) * BPF_REG_SIZE);
+ }
+ bt_set_frame_slot(&env->bt, fr, i);
+ first = false;
}
+ if (!first)
+ verbose(env, "\n");
}
+
+ err = mark_chain_precision_batch(env);
+ if (err < 0)
+ return err;
+
return 0;
}
@@ -15582,7 +16417,7 @@ static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type typ
* Have to support a use case when one path through
* the program yields TRUSTED pointer while another
* is UNTRUSTED. Fallback to UNTRUSTED to generate
- * BPF_PROBE_MEM.
+ * BPF_PROBE_MEM/BPF_PROBE_MEMSX.
*/
*prev_type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
} else {
@@ -15723,7 +16558,8 @@ static int do_check(struct bpf_verifier_env *env)
*/
err = check_mem_access(env, env->insn_idx, insn->src_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_READ, insn->dst_reg, false);
+ BPF_READ, insn->dst_reg, false,
+ BPF_MODE(insn->code) == BPF_MEMSX);
if (err)
return err;
@@ -15760,7 +16596,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, insn->src_reg, false);
+ BPF_WRITE, insn->src_reg, false, false);
if (err)
return err;
@@ -15785,7 +16621,7 @@ static int do_check(struct bpf_verifier_env *env)
/* check that memory (dst_reg + off) is writeable */
err = check_mem_access(env, env->insn_idx, insn->dst_reg,
insn->off, BPF_SIZE(insn->code),
- BPF_WRITE, -1, false);
+ BPF_WRITE, -1, false, false);
if (err)
return err;
@@ -15830,15 +16666,18 @@ static int do_check(struct bpf_verifier_env *env)
mark_reg_scratched(env, BPF_REG_0);
} else if (opcode == BPF_JA) {
if (BPF_SRC(insn->code) != BPF_K ||
- insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
insn->dst_reg != BPF_REG_0 ||
- class == BPF_JMP32) {
+ (class == BPF_JMP && insn->imm != 0) ||
+ (class == BPF_JMP32 && insn->off != 0)) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
- env->insn_idx += insn->off + 1;
+ if (class == BPF_JMP)
+ env->insn_idx += insn->off + 1;
+ else
+ env->insn_idx += insn->imm + 1;
continue;
} else if (opcode == BPF_EXIT) {
@@ -15857,7 +16696,8 @@ static int do_check(struct bpf_verifier_env *env)
return -EINVAL;
}
- if (env->cur_state->active_rcu_lock) {
+ if (env->cur_state->active_rcu_lock &&
+ !in_rbtree_lock_required_cb(env)) {
verbose(env, "bpf_rcu_read_unlock is missing\n");
return -EINVAL;
}
@@ -16137,11 +16977,6 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
return -EINVAL;
}
-
- if (prog->aux->sleepable) {
- verbose(env, "sleepable progs cannot use bpf_spin_lock yet\n");
- return -EINVAL;
- }
}
if (btf_record_has_field(map->record, BPF_TIMER)) {
@@ -16213,7 +17048,8 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0)) {
+ ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
+ insn->imm != 0)) {
verbose(env, "BPF_LDX uses reserved fields\n");
return -EINVAL;
}
@@ -16684,13 +17520,13 @@ static bool insn_is_cond_jump(u8 code)
{
u8 op;
+ op = BPF_OP(code);
if (BPF_CLASS(code) == BPF_JMP32)
- return true;
+ return op != BPF_JA;
if (BPF_CLASS(code) != BPF_JMP)
return false;
- op = BPF_OP(code);
return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
}
@@ -16907,11 +17743,15 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
for (i = 0; i < insn_cnt; i++, insn++) {
bpf_convert_ctx_access_t convert_ctx_access;
+ u8 mode;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
- insn->code == (BPF_LDX | BPF_MEM | BPF_DW)) {
+ insn->code == (BPF_LDX | BPF_MEM | BPF_DW) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_B) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_H) ||
+ insn->code == (BPF_LDX | BPF_MEMSX | BPF_W)) {
type = BPF_READ;
} else if (insn->code == (BPF_STX | BPF_MEM | BPF_B) ||
insn->code == (BPF_STX | BPF_MEM | BPF_H) ||
@@ -16970,8 +17810,12 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
*/
case PTR_TO_BTF_ID | MEM_ALLOC | PTR_UNTRUSTED:
if (type == BPF_READ) {
- insn->code = BPF_LDX | BPF_PROBE_MEM |
- BPF_SIZE((insn)->code);
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ else
+ insn->code = BPF_LDX | BPF_PROBE_MEMSX |
+ BPF_SIZE((insn)->code);
env->prog->aux->num_exentries++;
}
continue;
@@ -16981,6 +17825,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
+ mode = BPF_MODE(insn->code);
/* If the read access is a narrower load of the field,
* convert to a 4/8-byte load, to minimum program type specific
@@ -17040,6 +17885,10 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
(1ULL << size * 8) - 1);
}
}
+ if (mode == BPF_MEMSX)
+ insn_buf[cnt++] = BPF_RAW_INSN(BPF_ALU64 | BPF_MOV | BPF_X,
+ insn->dst_reg, insn->dst_reg,
+ size * 8, 0);
new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
if (!new_prog)
@@ -17159,7 +18008,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
insn = func[i]->insnsi;
for (j = 0; j < func[i]->len; j++, insn++) {
if (BPF_CLASS(insn->code) == BPF_LDX &&
- BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ (BPF_MODE(insn->code) == BPF_PROBE_MEM ||
+ BPF_MODE(insn->code) == BPF_PROBE_MEMSX))
num_exentries++;
}
func[i]->aux->num_exentries = num_exentries;
@@ -17431,6 +18281,13 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
+ if (desc->func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl] &&
+ !kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
insn_buf[0] = addr[0];
insn_buf[1] = addr[1];
insn_buf[2] = *insn;
@@ -17438,6 +18295,7 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
} else if (desc->func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
desc->func_id == special_kfunc_list[KF_bpf_rbtree_add_impl]) {
+ struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
int struct_meta_reg = BPF_REG_3;
int node_offset_reg = BPF_REG_4;
@@ -17447,6 +18305,12 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
node_offset_reg = BPF_REG_5;
}
+ if (!kptr_struct_meta) {
+ verbose(env, "verifier internal error: kptr_struct_meta expected at insn_idx %d\n",
+ insn_idx);
+ return -EFAULT;
+ }
+
__fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg,
node_offset_reg, insn, insn_buf, cnt);
} else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
@@ -18617,7 +19481,8 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
* in the fmodret id set with the KF_SLEEPABLE flag.
*/
else {
- u32 *flags = btf_kfunc_is_modify_return(btf, btf_id);
+ u32 *flags = btf_kfunc_is_modify_return(btf, btf_id,
+ prog);
if (flags && (*flags & KF_SLEEPABLE))
ret = 0;
@@ -18645,7 +19510,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log,
return -EINVAL;
}
ret = -EINVAL;
- if (btf_kfunc_is_modify_return(btf, btf_id) ||
+ if (btf_kfunc_is_modify_return(btf, btf_id, prog) ||
!check_attach_modify_return(addr, tname))
ret = 0;
if (ret) {
@@ -18812,6 +19677,8 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
if (!env)
return -ENOMEM;
+ env->bt.env = env;
+
len = (*prog)->len;
env->insn_aux_data =
vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));