bpf: Fix accesses to uninit stack slots

Privileged programs are supposed to be able to read uninitialized stack
memory (ever since 6715df8d5) but, before this patch, these accesses
were permitted inconsistently. In particular, accesses were permitted
above state->allocated_stack, but not below it. In other words, if the
stack was already "large enough", the access was permitted, but
otherwise the access was rejected instead of being allowed to "grow the
stack". This undesired rejection was happening in two places:
- in check_stack_slot_within_bounds()
- in check_stack_range_initialized()
This patch arranges for these accesses to be permitted. A bunch of tests
that were relying on the old rejection had to change; all of them were
changed to add also run unprivileged, in which case the old behavior
persists. One tests couldn't be updated - global_func16 - because it
can't run unprivileged for other reasons.

This patch also fixes the tracking of the stack size for variable-offset
reads. This second fix is bundled in the same commit as the first one
because they're inter-related. Before this patch, writes to the stack
using registers containing a variable offset (as opposed to registers
with fixed, known values) were not properly contributing to the
function's needed stack size. As a result, it was possible for a program
to verify, but then to attempt to read out-of-bounds data at runtime
because a too small stack had been allocated for it.

Each function tracks the size of the stack it needs in
bpf_subprog_info.stack_depth, which is maintained by
update_stack_depth(). For regular memory accesses, check_mem_access()
was calling update_state_depth() but it was passing in only the fixed
part of the offset register, ignoring the variable offset. This was
incorrect; the minimum possible value of that register should be used
instead.

This tracking is now fixed by centralizing the tracking of stack size in
grow_stack_state(), and by lifting the calls to grow_stack_state() to
check_stack_access_within_bounds() as suggested by Andrii. The code is
now simpler and more convincingly tracks the correct maximum stack size.
check_stack_range_initialized() can now rely on enough stack having been
allocated for the access; this helps with the fix for the first issue.

A few tests were changed to also check the stack depth computation. The
one that fails without this patch is verifier_var_off:stack_write_priv_vs_unpriv.

Fixes: 01f810ace9ed3 ("bpf: Allow variable-offset stack access")
Reported-by: Hao Sun <sunhao.th@gmail.com>
Signed-off-by: Andrei Matei <andreimatei1@gmail.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20231208032519.260451-3-andreimatei1@gmail.com

Closes: https://lore.kernel.org/bpf/CABWLsev9g8UP_c3a=1qbuZUi20tGoUXoU07FPf-5FLvhOKOY+Q@mail.gmail.com/

1 files changed, 26 insertions, 39 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 0e77bb52542d..de1e29fa467e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1259,7 +1259,10 @@ static int resize_reference_state(struct bpf_func_state *state, size_t n)
 	return 0;
 }
 
-static int grow_stack_state(struct bpf_func_state *state, int size)
+/* Possibly update state->allocated_stack to be at least size bytes. Also
+ * possibly update the function's high-water mark in its bpf_subprog_info.
+ */
+static int grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size)
 {
 	size_t old_n = state->allocated_stack / BPF_REG_SIZE, n = size / BPF_REG_SIZE;
 
@@ -1271,6 +1274,11 @@ static int grow_stack_state(struct bpf_func_state *state, int size)
 		return -ENOMEM;
 
 	state->allocated_stack = size;
+
+	/* update known max for given subprogram */
+	if (env->subprog_info[state->subprogno].stack_depth < size)
+		env->subprog_info[state->subprogno].stack_depth = size;
+
 	return 0;
 }
 
@@ -4440,9 +4448,6 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	struct bpf_reg_state *reg = NULL;
 	int insn_flags = insn_stack_access_flags(state->frameno, spi);
 
-	err = grow_stack_state(state, round_up(slot + 1, BPF_REG_SIZE));
-	if (err)
-		return err;
 	/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
 	 * so it's aligned access and [off, off + size) are within stack limits
 	 */
@@ -4595,10 +4600,6 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env,
 	    (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0))
 		writing_zero = true;
 
-	err = grow_stack_state(state, round_up(-min_off, BPF_REG_SIZE));
-	if (err)
-		return err;
-
 	for (i = min_off; i < max_off; i++) {
 		int spi;
 
@@ -5774,20 +5775,6 @@ static int check_ptr_alignment(struct bpf_verifier_env *env,
 					   strict);
 }
 
-static int update_stack_depth(struct bpf_verifier_env *env,
-			      const struct bpf_func_state *func,
-			      int off)
-{
-	u16 stack = env->subprog_info[func->subprogno].stack_depth;
-
-	if (stack >= -off)
-		return 0;
-
-	/* update known max for given subprogram */
-	env->subprog_info[func->subprogno].stack_depth = -off;
-	return 0;
-}
-
 /* starting from main bpf function walk all instructions of the function
  * and recursively walk all callees that given function can call.
  * Ignore jump and exit insns.
@@ -6577,13 +6564,14 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env,
  * The minimum valid offset is -MAX_BPF_STACK for writes, and
  * -state->allocated_stack for reads.
  */
-static int check_stack_slot_within_bounds(s64 off,
-					  struct bpf_func_state *state,
-					  enum bpf_access_type t)
+static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
+                                          s64 off,
+                                          struct bpf_func_state *state,
+                                          enum bpf_access_type t)
 {
 	int min_valid_off;
 
-	if (t == BPF_WRITE)
+	if (t == BPF_WRITE || env->allow_uninit_stack)
 		min_valid_off = -MAX_BPF_STACK;
 	else
 		min_valid_off = -state->allocated_stack;
@@ -6632,7 +6620,7 @@ static int check_stack_access_within_bounds(
 		max_off = reg->smax_value + off + access_size;
 	}
 
-	err = check_stack_slot_within_bounds(min_off, state, type);
+	err = check_stack_slot_within_bounds(env, min_off, state, type);
 	if (!err && max_off > 0)
 		err = -EINVAL; /* out of stack access into non-negative offsets */
 
@@ -6647,8 +6635,10 @@ static int check_stack_access_within_bounds(
 			verbose(env, "invalid variable-offset%s stack R%d var_off=%s off=%d size=%d\n",
 				err_extra, regno, tn_buf, off, access_size);
 		}
+		return err;
 	}
-	return err;
+
+	return grow_stack_state(env, state, round_up(-min_off, BPF_REG_SIZE));
 }
 
 /* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -6663,7 +6653,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 {
 	struct bpf_reg_state *regs = cur_regs(env);
 	struct bpf_reg_state *reg = regs + regno;
-	struct bpf_func_state *state;
 	int size, err = 0;
 
 	size = bpf_size_to_bytes(bpf_size);
@@ -6806,11 +6795,6 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
 		if (err)
 			return err;
 
-		state = func(env, reg);
-		err = update_stack_depth(env, state, off);
-		if (err)
-			return err;
-
 		if (t == BPF_READ)
 			err = check_stack_read(env, regno, off, size,
 					       value_regno);
@@ -7004,7 +6988,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 
 /* When register 'regno' is used to read the stack (either directly or through
  * a helper function) make sure that it's within stack boundary and, depending
- * on the access type, that all elements of the stack are initialized.
+ * on the access type and privileges, that all elements of the stack are
+ * initialized.
  *
  * 'off' includes 'regno->off', but not its dynamic part (if any).
  *
@@ -7112,8 +7097,11 @@ static int check_stack_range_initialized(
 
 		slot = -i - 1;
 		spi = slot / BPF_REG_SIZE;
-		if (state->allocated_stack <= slot)
-			goto err;
+		if (state->allocated_stack <= slot) {
+			verbose(env, "verifier bug: allocated_stack too small");
+			return -EFAULT;
+		}
+
 		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
 		if (*stype == STACK_MISC)
 			goto mark;
@@ -7137,7 +7125,6 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-err:
 		if (tnum_is_const(reg->var_off)) {
 			verbose(env, "invalid%s read from stack R%d off %d+%d size %d\n",
 				err_extra, regno, min_off, i - min_off, access_size);
@@ -7162,7 +7149,7 @@ mark:
 		 * helper may write to the entire memory range.
 		 */
 	}
-	return update_stack_depth(env, state, min_off);
+	return 0;
 }
 
 static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,