diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3f84f3e87704a48b47b0fe0d39308524dbac0610..27b74947cd2bd9de8e9dba3518fc876b2308a528 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -148,6 +148,7 @@ struct bpf_verifier_state {
/* call stack tracking */
struct bpf_func_state *frame[MAX_CALL_FRAMES];
u32 curframe;
+ bool speculative;
};
#define bpf_get_spilled_reg(slot, frame) \
@@ -167,15 +168,24 @@ struct bpf_verifier_state_list {
struct bpf_verifier_state_list *next;
};
+/* Possible states for alu_state member. */
+#define BPF_ALU_SANITIZE_SRC 1U
+#define BPF_ALU_SANITIZE_DST 2U
+#define BPF_ALU_NEG_VALUE (1U << 2)
+#define BPF_ALU_SANITIZE (BPF_ALU_SANITIZE_SRC | \
+ BPF_ALU_SANITIZE_DST)
+
struct bpf_insn_aux_data {
union {
enum bpf_reg_type ptr_type; /* pointer type for load/store insns */
unsigned long map_state; /* pointer/poison value for maps */
s32 call_imm; /* saved imm field of call insn */
+ u32 alu_limit; /* limit for add/sub register with pointer */
};
int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
int sanitize_stack_off; /* stack slot to be cleared */
bool seen; /* this insn was processed by the verifier */
+ u8 alu_state; /* used in combination with alu_limit */
};
#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 8e5da1ce5da454f48734df09e96d53278f242568..f6bc62a9ee8e9ddea251e353dfe4b6758560ba4f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -710,6 +710,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
free_func_state(dst_state->frame[i]);
dst_state->frame[i] = NULL;
}
+ dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
@@ -754,7 +755,8 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
}
static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
- int insn_idx, int prev_insn_idx)
+ int insn_idx, int prev_insn_idx,
+ bool speculative)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem;
@@ -772,6 +774,7 @@ static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
err = copy_verifier_state(&elem->st, cur);
if (err)
goto err;
+ elem->st.speculative |= speculative;
if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
verbose(env, "BPF program is too complex\n");
goto err;
@@ -3067,6 +3070,102 @@ static bool check_reg_sane_offset(struct bpf_verifier_env *env,
return true;
}
+static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+{
+ return &env->insn_aux_data[env->insn_idx];
+}
+
+static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
+ u32 *ptr_limit, u8 opcode, bool off_is_neg)
+{
+ bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
+ (opcode == BPF_SUB && !off_is_neg);
+ u32 off;
+
+ switch (ptr_reg->type) {
+ case PTR_TO_STACK:
+ off = ptr_reg->off + ptr_reg->var_off.value;
+ if (mask_to_left)
+ *ptr_limit = MAX_BPF_STACK + off;
+ else
+ *ptr_limit = -off;
+ return 0;
+ case PTR_TO_MAP_VALUE:
+ if (mask_to_left) {
+ *ptr_limit = ptr_reg->umax_value + ptr_reg->off;
+ } else {
+ off = ptr_reg->smin_value + ptr_reg->off;
+ *ptr_limit = ptr_reg->map_ptr->value_size - off;
+ }
+ return 0;
+ default:
+ return -EINVAL;
+ }
+}
+
+static int sanitize_ptr_alu(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ const struct bpf_reg_state *ptr_reg,
+ struct bpf_reg_state *dst_reg,
+ bool off_is_neg)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_insn_aux_data *aux = cur_aux(env);
+ bool ptr_is_dst_reg = ptr_reg == dst_reg;
+ u8 opcode = BPF_OP(insn->code);
+ u32 alu_state, alu_limit;
+ struct bpf_reg_state tmp;
+ bool ret;
+
+ if (env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K)
+ return 0;
+
+ /* We already marked aux for masking from non-speculative
+ * paths, thus we got here in the first place. We only care
+ * to explore bad access from here.
+ */
+ if (vstate->speculative)
+ goto do_sim;
+
+ alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+ alu_state |= ptr_is_dst_reg ?
+ BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+
+ if (retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg))
+ return 0;
+
+ /* If we arrived here from different branches with different
+ * limits to sanitize, then this won't work.
+ */
+ if (aux->alu_state &&
+ (aux->alu_state != alu_state ||
+ aux->alu_limit != alu_limit))
+ return -EACCES;
+
+ /* Corresponding fixup done in fixup_bpf_calls(). */
+ aux->alu_state = alu_state;
+ aux->alu_limit = alu_limit;
+
+do_sim:
+ /* Simulate and find potential out-of-bounds access under
+ * speculative execution from truncation as a result of
+ * masking when off was not within expected range. If off
+ * sits in dst, then we temporarily need to move ptr there
+ * to simulate dst (== 0) +/-= ptr. Needed, for example,
+ * for cases where we use K-based arithmetic in one direction
+ * and truncated reg-based in the other in order to explore
+ * bad access.
+ */
+ if (!ptr_is_dst_reg) {
+ tmp = *dst_reg;
+ *dst_reg = *ptr_reg;
+ }
+ ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
+ if (!ptr_is_dst_reg)
+ *dst_reg = tmp;
+ return !ret ? -EFAULT : 0;
+}
+
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
* If we return -EACCES, caller may want to try again treating pointer as a
@@ -3087,6 +3186,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
u32 dst = insn->dst_reg, src = insn->src_reg;
u8 opcode = BPF_OP(insn->code);
+ int ret;
dst_reg = ®s[dst];
@@ -3142,6 +3242,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
switch (opcode) {
case BPF_ADD:
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+ if (ret < 0) {
+ verbose(env, "R%d tried to add from different maps or paths\n", dst);
+ return ret;
+ }
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
@@ -3192,6 +3297,11 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
}
break;
case BPF_SUB:
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, dst_reg, smin_val < 0);
+ if (ret < 0) {
+ verbose(env, "R%d tried to sub from different maps or paths\n", dst);
+ return ret;
+ }
if (dst_reg == off_reg) {
/* scalar -= pointer. Creates an unknown scalar */
verbose(env, "R%d tried to subtract pointer from scalar\n",
@@ -4389,7 +4499,8 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
}
}
- other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
+ other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx,
+ false);
if (!other_branch)
return -EFAULT;
other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
@@ -5499,6 +5610,12 @@ static bool states_equal(struct bpf_verifier_env *env,
if (old->curframe != cur->curframe)
return false;
+ /* Verification state from speculative execution simulation
+ * must never prune a non-speculative execution one.
+ */
+ if (old->speculative && !cur->speculative)
+ return false;
+
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
@@ -5700,6 +5817,7 @@ static int do_check(struct bpf_verifier_env *env)
if (!state)
return -ENOMEM;
state->curframe = 0;
+ state->speculative = false;
state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
if (!state->frame[0]) {
kfree(state);
@@ -5739,8 +5857,10 @@ static int do_check(struct bpf_verifier_env *env)
/* found equivalent state, can prune the search */
if (env->log.level) {
if (do_print_state)
- verbose(env, "\nfrom %d to %d: safe\n",
- env->prev_insn_idx, env->insn_idx);
+ verbose(env, "\nfrom %d to %d%s: safe\n",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
else
verbose(env, "%d: safe\n", env->insn_idx);
}
@@ -5757,8 +5877,10 @@ static int do_check(struct bpf_verifier_env *env)
if (env->log.level > 1)
verbose(env, "%d:", env->insn_idx);
else
- verbose(env, "\nfrom %d to %d:",
- env->prev_insn_idx, env->insn_idx);
+ verbose(env, "\nfrom %d to %d%s:",
+ env->prev_insn_idx, env->insn_idx,
+ env->cur_state->speculative ?
+ " (speculative execution)" : "");
print_verifier_state(env, state->frame[state->curframe]);
do_print_state = false;
}
@@ -6750,6 +6872,57 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env)
continue;
}
+ if (insn->code == (BPF_ALU64 | BPF_ADD | BPF_X) ||
+ insn->code == (BPF_ALU64 | BPF_SUB | BPF_X)) {
+ const u8 code_add = BPF_ALU64 | BPF_ADD | BPF_X;
+ const u8 code_sub = BPF_ALU64 | BPF_SUB | BPF_X;
+ struct bpf_insn insn_buf[16];
+ struct bpf_insn *patch = &insn_buf[0];
+ bool issrc, isneg;
+ u32 off_reg;
+
+ aux = &env->insn_aux_data[i + delta];
+ if (!aux->alu_state)
+ continue;
+
+ isneg = aux->alu_state & BPF_ALU_NEG_VALUE;
+ issrc = (aux->alu_state & BPF_ALU_SANITIZE) ==
+ BPF_ALU_SANITIZE_SRC;
+
+ off_reg = issrc ? insn->src_reg : insn->dst_reg;
+ if (isneg)
+ *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+ *patch++ = BPF_MOV32_IMM(BPF_REG_AX, aux->alu_limit - 1);
+ *patch++ = BPF_ALU64_REG(BPF_SUB, BPF_REG_AX, off_reg);
+ *patch++ = BPF_ALU64_REG(BPF_OR, BPF_REG_AX, off_reg);
+ *patch++ = BPF_ALU64_IMM(BPF_NEG, BPF_REG_AX, 0);
+ *patch++ = BPF_ALU64_IMM(BPF_ARSH, BPF_REG_AX, 63);
+ if (issrc) {
+ *patch++ = BPF_ALU64_REG(BPF_AND, BPF_REG_AX,
+ off_reg);
+ insn->src_reg = BPF_REG_AX;
+ } else {
+ *patch++ = BPF_ALU64_REG(BPF_AND, off_reg,
+ BPF_REG_AX);
+ }
+ if (isneg)
+ insn->code = insn->code == code_add ?
+ code_sub : code_add;
+ *patch++ = *insn;
+ if (issrc && isneg)
+ *patch++ = BPF_ALU64_IMM(BPF_MUL, off_reg, -1);
+ cnt = patch - insn_buf;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
+ }
+
if (insn->code != (BPF_JMP | BPF_CALL))
continue;
if (insn->src_reg == BPF_PSEUDO_CALL)