summaryrefslogtreecommitdiff
path: root/kernel/bpf
diff options
context:
space:
mode:
authorKumar Kartikeya Dwivedi <memxor@gmail.com>2023-01-21 03:22:32 +0300
committerAlexei Starovoitov <ast@kernel.org>2023-01-21 04:55:03 +0300
commitef8fc7a07c0e161841779d6fe3f6acd5a05c547c (patch)
tree72535d9c98ae327b830e00ba01bb9f6eed068959 /kernel/bpf
parent79168a669d8125453c8a271115f1ffd4294e61f6 (diff)
downloadlinux-ef8fc7a07c0e161841779d6fe3f6acd5a05c547c.tar.xz
bpf: Fix partial dynptr stack slot reads/writes
Currently, while reads are disallowed for dynptr stack slots, writes are not. Reads don't work from both direct access and helpers, while writes do work in both cases, but have the effect of overwriting the slot_type. While this is fine, handling for a few edge cases is missing. Firstly, a user can overwrite the stack slots of dynptr partially. Consider the following layout: spi: [d][d][?] 2 1 0 First slot is at spi 2, second at spi 1. Now, do a write of 1 to 8 bytes for spi 1. This will essentially either write STACK_MISC for all slot_types or STACK_MISC and STACK_ZERO (in case of size < BPF_REG_SIZE partial write of zeroes). The end result is that slot is scrubbed. Now, the layout is: spi: [d][m][?] 2 1 0 Suppose if user initializes spi = 1 as dynptr. We get: spi: [d][d][d] 2 1 0 But this time, both spi 2 and spi 1 have first_slot = true. Now, when passing spi 2 to dynptr helper, it will consider it as initialized as it does not check whether second slot has first_slot == false. And spi 1 should already work as normal. This effectively replaced size + offset of first dynptr, hence allowing invalid OOB reads and writes. Make a few changes to protect against this: When writing to PTR_TO_STACK using BPF insns, when we touch spi of a STACK_DYNPTR type, mark both first and second slot (regardless of which slot we touch) as STACK_INVALID. Reads are already prevented. Second, prevent writing to stack memory from helpers if the range may contain any STACK_DYNPTR slots. Reads are already prevented. For helpers, we cannot allow it to destroy dynptrs from the writes as depending on arguments, helper may take uninit_mem and dynptr both at the same time. This would mean that helper may write to uninit_mem before it reads the dynptr, which would be bad. PTR_TO_MEM: [?????dd] Depending on the code inside the helper, it may end up overwriting the dynptr contents first and then read those as the dynptr argument. Verifier would only simulate destruction when it does byte by byte access simulation in check_helper_call for meta.access_size, and fail to catch this case, as it happens after argument checks. The same would need to be done for any other non-trivial objects created on the stack in the future, such as bpf_list_head on stack, or bpf_rb_root on stack. A common misunderstanding in the current code is that MEM_UNINIT means writes, but note that writes may also be performed even without MEM_UNINIT in case of helpers, in that case the code after handling meta && meta->raw_mode will complain when it sees STACK_DYNPTR. So that invalid read case also covers writes to potential STACK_DYNPTR slots. The only loophole was in case of meta->raw_mode which simulated writes through instructions which could overwrite them. A future series sequenced after this will focus on the clean up of helper access checks and bugs around that. Fixes: 97e03f521050 ("bpf: Add verifier support for dynptrs") Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com> Link: https://lore.kernel.org/r/20230121002241.2113993-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/verifier.c88
1 files changed, 88 insertions, 0 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 76afdbea425a..5c7f29ca94ec 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -769,6 +769,8 @@ static void mark_dynptr_cb_reg(struct bpf_reg_state *reg,
__mark_dynptr_reg(reg, type, true);
}
+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)
@@ -863,6 +865,55 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re
return 0;
}
+static void __mark_reg_unknown(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg);
+
+static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env,
+ struct bpf_func_state *state, int spi)
+{
+ int i;
+
+ /* We always ensure that STACK_DYNPTR is never set partially,
+ * hence just checking for slot_type[0] is enough. This is
+ * different for STACK_SPILL, where it may be only set for
+ * 1 byte, so code has to use is_spilled_reg.
+ */
+ if (state->stack[spi].slot_type[0] != STACK_DYNPTR)
+ return 0;
+
+ /* Reposition spi to first slot */
+ if (!state->stack[spi].spilled_ptr.dynptr.first_slot)
+ spi = spi + 1;
+
+ if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) {
+ verbose(env, "cannot overwrite referenced dynptr\n");
+ return -EINVAL;
+ }
+
+ mark_stack_slot_scratched(env, spi);
+ mark_stack_slot_scratched(env, spi - 1);
+
+ /* Writing partially to one dynptr stack slot destroys both. */
+ 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;
+ }
+
+ /* TODO: Invalidate any slices associated with this dynptr */
+
+ /* Do not release reference state, we are destroying dynptr on stack,
+ * not using some helper to release it. Just reset register.
+ */
+ __mark_reg_not_init(env, &state->stack[spi].spilled_ptr);
+ __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr);
+
+ /* Same reason as unmark_stack_slots_dynptr above */
+ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+ state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
+ return 0;
+}
+
static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
struct bpf_func_state *state = func(env, reg);
@@ -3391,6 +3442,10 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
}
+ err = destroy_if_dynptr_stack_slot(env, state, spi);
+ if (err)
+ return err;
+
mark_stack_slot_scratched(env, spi);
if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
!register_is_null(reg) && env->bpf_capable) {
@@ -3504,6 +3559,14 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
if (err)
return err;
+ for (i = min_off; i < max_off; i++) {
+ int spi;
+
+ spi = __get_spi(i);
+ err = destroy_if_dynptr_stack_slot(env, state, spi);
+ if (err)
+ return err;
+ }
/* Variable offset writes destroy any spilled pointers in range. */
for (i = min_off; i < max_off; i++) {
@@ -5531,6 +5594,31 @@ static int check_stack_range_initialized(
}
if (meta && meta->raw_mode) {
+ /* Ensure we won't be overwriting dynptrs when simulating byte
+ * by byte access in check_helper_call using meta.access_size.
+ * This would be a problem if we have a helper in the future
+ * which takes:
+ *
+ * helper(uninit_mem, len, dynptr)
+ *
+ * Now, uninint_mem may overlap with dynptr pointer. Hence, it
+ * may end up writing to dynptr itself when touching memory from
+ * arg 1. This can be relaxed on a case by case basis for known
+ * safe cases, but reject due to the possibilitiy of aliasing by
+ * default.
+ */
+ for (i = min_off; i < max_off + access_size; i++) {
+ int stack_off = -i - 1;
+
+ spi = __get_spi(i);
+ /* raw_mode may write past allocated_stack */
+ if (state->allocated_stack <= stack_off)
+ continue;
+ if (state->stack[spi].slot_type[stack_off % BPF_REG_SIZE] == STACK_DYNPTR) {
+ verbose(env, "potential write to dynptr at off=%d disallowed\n", i);
+ return -EACCES;
+ }
+ }
meta->access_size = access_size;
meta->regno = regno;
return 0;