diff mbox series

[bpf-next,v4,01/12] bpf: Fix state pruning for STACK_DYNPTR stack slots

Message ID 20230120070355.1983560-2-memxor@gmail.com (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series Dynptr fixes | expand

Checks

Context Check Description
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-3 success Logs for build for aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-6 success Logs for build for x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-7 success Logs for llvm-toolchain
bpf/vmtest-bpf-next-VM_Test-8 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-4 success Logs for build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for test_maps on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-12 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for test_maps on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-14 fail Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for test_progs on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-17 success Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for test_progs on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-19 success Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-20 success Logs for test_progs_no_alu32 on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-22 success Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-23 success Logs for test_progs_no_alu32 on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-24 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-26 fail Logs for test_progs_no_alu32_parallel on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-28 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-29 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for test_progs_parallel on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-32 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-33 success Logs for test_progs_parallel on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-34 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-35 success Logs for test_verifier on aarch64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-36 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-37 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-38 success Logs for test_verifier on x86_64 with llvm-16
bpf/vmtest-bpf-next-VM_Test-16 success Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-31 success Logs for test_progs_parallel on s390x with gcc
bpf/vmtest-bpf-next-PR fail PR summary
bpf/vmtest-bpf-next-VM_Test-11 success Logs for test_maps on s390x with gcc
netdev/tree_selection success Clearly marked for bpf-next
netdev/fixes_present success Fixes tag not required for -next series
netdev/subject_prefix success Link
netdev/cover_letter success Series has a cover letter
netdev/patch_count success Link
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 10 this patch: 10
netdev/cc_maintainers warning 8 maintainers not CCed: kpsingh@kernel.org haoluo@google.com song@kernel.org yhs@fb.com martin.lau@linux.dev sdf@google.com john.fastabend@gmail.com jolsa@kernel.org
netdev/build_clang success Errors and warnings before: 1 this patch: 1
netdev/module_param success Was 0 now: 0
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success Fixes tag looks correct
netdev/build_allmodconfig_warn success Errors and warnings before: 10 this patch: 10
netdev/checkpatch warning WARNING: line length of 82 exceeds 80 columns WARNING: line length of 83 exceeds 80 columns WARNING: line length of 84 exceeds 80 columns WARNING: line length of 87 exceeds 80 columns WARNING: line length of 88 exceeds 80 columns
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0

Commit Message

Kumar Kartikeya Dwivedi Jan. 20, 2023, 7:03 a.m. UTC
The root of the problem is missing liveness marking for STACK_DYNPTR
slots. This leads to all kinds of problems inside stacksafe.

The verifier by default inside stacksafe ignores spilled_ptr in stack
slots which do not have REG_LIVE_READ marks. Since this is being checked
in the 'old' explored state, it must have already done clean_live_states
for this old bpf_func_state. Hence, it won't be receiving any more
liveness marks from to be explored insns (it has received REG_LIVE_DONE
marking from liveness point of view).

What this means is that verifier considers that it's safe to not compare
the stack slot if was never read by children states. While liveness
marks are usually propagated correctly following the parentage chain for
spilled registers (SCALAR_VALUE and PTR_* types), the same is not the
case for STACK_DYNPTR.

clean_live_states hence simply rewrites these stack slots to the type
STACK_INVALID since it sees no REG_LIVE_READ marks.

The end result is that we will never see STACK_DYNPTR slots in explored
state. Even if verifier was conservatively matching !REG_LIVE_READ
slots, very next check continuing the stacksafe loop on seeing
STACK_INVALID would again prevent further checks.

Now as long as verifier stores an explored state which we can compare to
when reaching a pruning point, we can abuse this bug to make verifier
prune search for obviously unsafe paths using STACK_DYNPTR slots
thinking they are never used hence safe.

Doing this in unprivileged mode is a bit challenging. add_new_state is
only set when seeing BPF_F_TEST_STATE_FREQ (which requires privileges)
or when jmps_processed difference is >= 2 and insn_processed difference
is >= 8. So coming up with the unprivileged case requires a little more
work, but it is still totally possible. The test case being discussed
below triggers the heuristic even in unprivileged mode.

However, it no longer works since commit
8addbfc7b308 ("bpf: Gate dynptr API behind CAP_BPF").

Let's try to study the test step by step.

Consider the following program (C style BPF ASM):

0  r0 = 0;
1  r6 = &ringbuf_map;
3  r1 = r6;
4  r2 = 8;
5  r3 = 0;
6  r4 = r10;
7  r4 -= -16;
8  call bpf_ringbuf_reserve_dynptr;
9  if r0 == 0 goto pc+1;
10 goto pc+1;
11 *(r10 - 16) = 0xeB9F;
12 r1 = r10;
13 r1 -= -16;
14 r2 = 0;
15 call bpf_ringbuf_discard_dynptr;
16 r0 = 0;
17 exit;

We know that insn 12 will be a pruning point, hence if we force
add_new_state for it, it will first verify the following path as
safe in straight line exploration:
0 1 3 4 5 6 7 8 9 -> 10 -> (12) 13 14 15 16 17

Then, when we arrive at insn 12 from the following path:
0 1 3 4 5 6 7 8 9 -> 11 (12)

We will find a state that has been verified as safe already at insn 12.
Since register state is same at this point, regsafe will pass. Next, in
stacksafe, for spi = 0 and spi = 1 (location of our dynptr) is skipped
seeing !REG_LIVE_READ. The rest matches, so stacksafe returns true.
Next, refsafe is also true as reference state is unchanged in both
states.

The states are considered equivalent and search is pruned.

Hence, we are able to construct a dynptr with arbitrary contents and use
the dynptr API to operate on this arbitrary pointer and arbitrary size +
offset.

To fix this, first define a mark_dynptr_read function that propagates
liveness marks whenever a valid initialized dynptr is accessed by dynptr
helpers. REG_LIVE_WRITTEN is marked whenever we initialize an
uninitialized dynptr. This is done in mark_stack_slots_dynptr. It allows
screening off mark_reg_read and not propagating marks upwards from that
point.

This ensures that we either set REG_LIVE_READ64 on both dynptr slots, or
none, so clean_live_states either sets both slots to STACK_INVALID or
none of them. This is the invariant the checks inside stacksafe rely on.

Next, do a complete comparison of both stack slots whenever they have
STACK_DYNPTR. Compare the dynptr type stored in the spilled_ptr, and
also whether both form the same first_slot. Only then is the later path
safe.

Fixes: 97e03f521050 ("bpf: Add verifier support for dynptrs")
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
---
 kernel/bpf/verifier.c | 88 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 84 insertions(+), 4 deletions(-)
diff mbox series

Patch

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index ca7db2ce70b9..39d8ee38c338 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -781,6 +781,9 @@  static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_
 		state->stack[spi - 1].spilled_ptr.ref_obj_id = id;
 	}
 
+	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+	state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
 	return 0;
 }
 
@@ -805,6 +808,31 @@  static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re
 
 	__mark_reg_not_init(env, &state->stack[spi].spilled_ptr);
 	__mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr);
+
+	/* Why do we need to set REG_LIVE_WRITTEN for STACK_INVALID slot?
+	 *
+	 * While we don't allow reading STACK_INVALID, it is still possible to
+	 * do <8 byte writes marking some but not all slots as STACK_MISC. Then,
+	 * helpers or insns can do partial read of that part without failing,
+	 * but check_stack_range_initialized, check_stack_read_var_off, and
+	 * check_stack_read_fixed_off will do mark_reg_read for all 8-bytes of
+	 * the slot conservatively. Hence we need to prevent those liveness
+	 * marking walks.
+	 *
+	 * This was not a problem before because STACK_INVALID is only set by
+	 * default (where the default reg state has its reg->parent as NULL), or
+	 * in clean_live_states after REG_LIVE_DONE (at which point
+	 * mark_reg_read won't walk reg->parent chain), but not randomly during
+	 * verifier state exploration (like we did above). Hence, for our case
+	 * parentage chain will still be live (i.e. reg->parent may be
+	 * non-NULL), while earlier reg->parent was NULL, so we need
+	 * REG_LIVE_WRITTEN to screen off read marker propagation when it is
+	 * done later on reads or by mark_dynptr_read as well to unnecessary
+	 * mark registers in verifier state.
+	 */
+	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+	state->stack[spi - 1].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
 	return 0;
 }
 
@@ -2390,6 +2418,30 @@  static int mark_reg_read(struct bpf_verifier_env *env,
 	return 0;
 }
 
+static int mark_dynptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi, ret;
+
+	/* For CONST_PTR_TO_DYNPTR, it must have already been done by
+	 * check_reg_arg in check_helper_call and mark_btf_func_reg_size in
+	 * check_kfunc_call.
+	 */
+	if (reg->type == CONST_PTR_TO_DYNPTR)
+		return 0;
+	spi = get_spi(reg->off);
+	/* Caller ensures dynptr is valid and initialized, which means spi is in
+	 * bounds and spi is the first dynptr slot. Simply mark stack slot as
+	 * read.
+	 */
+	ret = mark_reg_read(env, &state->stack[spi].spilled_ptr,
+			    state->stack[spi].spilled_ptr.parent, REG_LIVE_READ64);
+	if (ret)
+		return ret;
+	return mark_reg_read(env, &state->stack[spi - 1].spilled_ptr,
+			     state->stack[spi - 1].spilled_ptr.parent, REG_LIVE_READ64);
+}
+
 /* This function is supposed to be used by the following 32-bit optimization
  * code only. It returns TRUE if the source or destination register operates
  * on 64-bit, otherwise return FALSE.
@@ -5977,6 +6029,8 @@  int process_dynptr_func(struct bpf_verifier_env *env, int regno,
 
 		meta->uninit_dynptr_regno = regno;
 	} else /* MEM_RDONLY and None case from above */ {
+		int err;
+
 		/* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */
 		if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) {
 			verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n");
@@ -6010,6 +6064,10 @@  int process_dynptr_func(struct bpf_verifier_env *env, int regno,
 				err_extra, regno);
 			return -EINVAL;
 		}
+
+		err = mark_dynptr_read(env, reg);
+		if (err)
+			return err;
 	}
 	return 0;
 }
@@ -13215,10 +13273,9 @@  static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			return false;
 		if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1)
 			continue;
-		if (!is_spilled_reg(&old->stack[spi]))
-			continue;
-		if (!regsafe(env, &old->stack[spi].spilled_ptr,
-			     &cur->stack[spi].spilled_ptr, idmap))
+		/* Both old and cur are having same slot_type */
+		switch (old->stack[spi].slot_type[BPF_REG_SIZE - 1]) {
+		case STACK_SPILL:
 			/* when explored and current stack slot are both storing
 			 * spilled registers, check that stored pointers types
 			 * are the same as well.
@@ -13229,7 +13286,30 @@  static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			 * such verifier states are not equivalent.
 			 * return false to continue verification of this path
 			 */
+			if (!regsafe(env, &old->stack[spi].spilled_ptr,
+				     &cur->stack[spi].spilled_ptr, idmap))
+				return false;
+			break;
+		case STACK_DYNPTR:
+		{
+			const struct bpf_reg_state *old_reg, *cur_reg;
+
+			old_reg = &old->stack[spi].spilled_ptr;
+			cur_reg = &cur->stack[spi].spilled_ptr;
+			if (old_reg->dynptr.type != cur_reg->dynptr.type ||
+			    old_reg->dynptr.first_slot != cur_reg->dynptr.first_slot ||
+			    !check_ids(old_reg->ref_obj_id, cur_reg->ref_obj_id, idmap))
+				return false;
+			break;
+		}
+		case STACK_MISC:
+		case STACK_ZERO:
+		case STACK_INVALID:
+			continue;
+		/* Ensure that new unhandled slot types return false by default */
+		default:
 			return false;
+		}
 	}
 	return true;
 }