aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/bpf
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/bpf')
-rw-r--r--kernel/bpf/cpumap.c2
-rw-r--r--kernel/bpf/syscall.c16
-rw-r--r--kernel/bpf/verifier.c210
3 files changed, 142 insertions, 86 deletions
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 70f71b154fa5..3fe0b006d2d2 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -469,7 +469,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value,
return -EOVERFLOW;
/* Make sure CPU is a valid possible cpu */
- if (!cpu_possible(key_cpu))
+ if (key_cpu >= nr_cpumask_bits || !cpu_possible(key_cpu))
return -ENODEV;
if (qsize == 0) {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 966b7b34cde0..3b92aea18ae7 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -592,9 +592,7 @@ static void bpf_map_mmap_open(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- bpf_map_inc_with_uref(map);
-
- if (vma->vm_flags & VM_WRITE) {
+ if (vma->vm_flags & VM_MAYWRITE) {
mutex_lock(&map->freeze_mutex);
map->writecnt++;
mutex_unlock(&map->freeze_mutex);
@@ -606,13 +604,11 @@ static void bpf_map_mmap_close(struct vm_area_struct *vma)
{
struct bpf_map *map = vma->vm_file->private_data;
- if (vma->vm_flags & VM_WRITE) {
+ if (vma->vm_flags & VM_MAYWRITE) {
mutex_lock(&map->freeze_mutex);
map->writecnt--;
mutex_unlock(&map->freeze_mutex);
}
-
- bpf_map_put_with_uref(map);
}
static const struct vm_operations_struct bpf_map_default_vmops = {
@@ -641,14 +637,16 @@ static int bpf_map_mmap(struct file *filp, struct vm_area_struct *vma)
/* set default open/close callbacks */
vma->vm_ops = &bpf_map_default_vmops;
vma->vm_private_data = map;
+ vma->vm_flags &= ~VM_MAYEXEC;
+ if (!(vma->vm_flags & VM_WRITE))
+ /* disallow re-mapping with PROT_WRITE */
+ vma->vm_flags &= ~VM_MAYWRITE;
err = map->ops->map_mmap(map, vma);
if (err)
goto out;
- bpf_map_inc_with_uref(map);
-
- if (vma->vm_flags & VM_WRITE)
+ if (vma->vm_flags & VM_MAYWRITE)
map->writecnt++;
out:
mutex_unlock(&map->freeze_mutex);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1cc945daa9c8..1c53ccbd5b5d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -227,8 +227,7 @@ struct bpf_call_arg_meta {
bool pkt_access;
int regno;
int access_size;
- s64 msize_smax_value;
- u64 msize_umax_value;
+ u64 msize_max_value;
int ref_obj_id;
int func_id;
u32 btf_id;
@@ -1034,17 +1033,6 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
reg->umax_value));
}
-static void __reg_bound_offset32(struct bpf_reg_state *reg)
-{
- u64 mask = 0xffffFFFF;
- struct tnum range = tnum_range(reg->umin_value & mask,
- reg->umax_value & mask);
- struct tnum lo32 = tnum_cast(reg->var_off, 4);
- struct tnum hi32 = tnum_lshift(tnum_rshift(reg->var_off, 32), 32);
-
- reg->var_off = tnum_or(hi32, tnum_intersect(lo32, range));
-}
-
/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
@@ -1930,6 +1918,15 @@ static bool register_is_const(struct bpf_reg_state *reg)
return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
}
+static bool __is_pointer_value(bool allow_ptr_leaks,
+ const struct bpf_reg_state *reg)
+{
+ if (allow_ptr_leaks)
+ return false;
+
+ return reg->type != SCALAR_VALUE;
+}
+
static void save_register_state(struct bpf_func_state *state,
int spi, struct bpf_reg_state *reg)
{
@@ -2120,6 +2117,16 @@ static int check_stack_read(struct bpf_verifier_env *env,
* which resets stack/reg liveness for state transitions
*/
state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+ } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
+ /* If value_regno==-1, the caller is asking us whether
+ * it is acceptable to use this value as a SCALAR_VALUE
+ * (e.g. for XADD).
+ * We must not allow unprivileged callers to do that
+ * with spilled pointers.
+ */
+ verbose(env, "leaking pointer from stack off %d\n",
+ off);
+ return -EACCES;
}
mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
} else {
@@ -2485,15 +2492,6 @@ static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
return -EACCES;
}
-static bool __is_pointer_value(bool allow_ptr_leaks,
- const struct bpf_reg_state *reg)
-{
- if (allow_ptr_leaks)
- return false;
-
- return reg->type != SCALAR_VALUE;
-}
-
static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
{
return cur_regs(env) + regno;
@@ -2887,7 +2885,7 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
if (ret < 0)
return ret;
- if (atype == BPF_READ) {
+ if (atype == BPF_READ && value_regno >= 0) {
if (ret == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
return 0;
@@ -3579,8 +3577,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
/* remember the mem_size which may be used later
* to refine return values.
*/
- meta->msize_smax_value = reg->smax_value;
- meta->msize_umax_value = reg->umax_value;
+ meta->msize_max_value = reg->umax_value;
/* The register is SCALAR_VALUE; the access check
* happens using its boundaries.
@@ -4106,21 +4103,44 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
return 0;
}
-static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
- int func_id,
- struct bpf_call_arg_meta *meta)
+static int do_refine_retval_range(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, int ret_type,
+ int func_id, struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
+ struct bpf_reg_state tmp_reg = *ret_reg;
+ bool ret;
if (ret_type != RET_INTEGER ||
(func_id != BPF_FUNC_get_stack &&
func_id != BPF_FUNC_probe_read_str))
- return;
+ return 0;
+
+ /* Error case where ret is in interval [S32MIN, -1]. */
+ ret_reg->smin_value = S32_MIN;
+ ret_reg->smax_value = -1;
+
+ __reg_deduce_bounds(ret_reg);
+ __reg_bound_offset(ret_reg);
+ __update_reg_bounds(ret_reg);
+
+ ret = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
+ if (!ret)
+ return -EFAULT;
+
+ *ret_reg = tmp_reg;
+
+ /* Success case where ret is in range [0, msize_max_value]. */
+ ret_reg->smin_value = 0;
+ ret_reg->smax_value = meta->msize_max_value;
+ ret_reg->umin_value = ret_reg->smin_value;
+ ret_reg->umax_value = ret_reg->smax_value;
- ret_reg->smax_value = meta->msize_smax_value;
- ret_reg->umax_value = meta->msize_umax_value;
__reg_deduce_bounds(ret_reg);
__reg_bound_offset(ret_reg);
+ __update_reg_bounds(ret_reg);
+
+ return 0;
}
static int
@@ -4388,7 +4408,9 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
regs[BPF_REG_0].ref_obj_id = id;
}
- do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
+ err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
+ if (err)
+ return err;
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
@@ -5601,6 +5623,70 @@ static bool cmp_val_with_extended_s64(s64 sval, struct bpf_reg_state *reg)
reg->smax_value <= 0 && reg->smin_value >= S32_MIN);
}
+/* Constrain the possible values of @reg with unsigned upper bound @bound.
+ * If @is_exclusive, @bound is an exclusive limit, otherwise it is inclusive.
+ * If @is_jmp32, @bound is a 32-bit value that only constrains the low 32 bits
+ * of @reg.
+ */
+static void set_upper_bound(struct bpf_reg_state *reg, u64 bound, bool is_jmp32,
+ bool is_exclusive)
+{
+ if (is_exclusive) {
+ /* There are no values for `reg` that make `reg<0` true. */
+ if (bound == 0)
+ return;
+ bound--;
+ }
+ if (is_jmp32) {
+ /* Constrain the register's value in the tnum representation.
+ * For 64-bit comparisons this happens later in
+ * __reg_bound_offset(), but for 32-bit comparisons, we can be
+ * more precise than what can be derived from the updated
+ * numeric bounds.
+ */
+ struct tnum t = tnum_range(0, bound);
+
+ t.mask |= ~0xffffffffULL; /* upper half is unknown */
+ reg->var_off = tnum_intersect(reg->var_off, t);
+
+ /* Compute the 64-bit bound from the 32-bit bound. */
+ bound += gen_hi_max(reg->var_off);
+ }
+ reg->umax_value = min(reg->umax_value, bound);
+}
+
+/* Constrain the possible values of @reg with unsigned lower bound @bound.
+ * If @is_exclusive, @bound is an exclusive limit, otherwise it is inclusive.
+ * If @is_jmp32, @bound is a 32-bit value that only constrains the low 32 bits
+ * of @reg.
+ */
+static void set_lower_bound(struct bpf_reg_state *reg, u64 bound, bool is_jmp32,
+ bool is_exclusive)
+{
+ if (is_exclusive) {
+ /* There are no values for `reg` that make `reg>MAX` true. */
+ if (bound == (is_jmp32 ? U32_MAX : U64_MAX))
+ return;
+ bound++;
+ }
+ if (is_jmp32) {
+ /* Constrain the register's value in the tnum representation.
+ * For 64-bit comparisons this happens later in
+ * __reg_bound_offset(), but for 32-bit comparisons, we can be
+ * more precise than what can be derived from the updated
+ * numeric bounds.
+ */
+ struct tnum t = tnum_range(bound, U32_MAX);
+
+ t.mask |= ~0xffffffffULL; /* upper half is unknown */
+ reg->var_off = tnum_intersect(reg->var_off, t);
+
+ /* Compute the 64-bit bound from the 32-bit bound. */
+ bound += gen_hi_min(reg->var_off);
+ }
+ reg->umin_value = max(reg->umin_value, bound);
+}
+
/* Adjusts the register min/max values in the case that the dst_reg is the
* variable register that we are working on, and src_reg is a constant or we're
* simply doing a BPF_K check.
@@ -5656,15 +5742,8 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
case BPF_JGE:
case BPF_JGT:
{
- u64 false_umax = opcode == BPF_JGT ? val : val - 1;
- u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
-
- if (is_jmp32) {
- false_umax += gen_hi_max(false_reg->var_off);
- true_umin += gen_hi_min(true_reg->var_off);
- }
- false_reg->umax_value = min(false_reg->umax_value, false_umax);
- true_reg->umin_value = max(true_reg->umin_value, true_umin);
+ set_upper_bound(false_reg, val, is_jmp32, opcode == BPF_JGE);
+ set_lower_bound(true_reg, val, is_jmp32, opcode == BPF_JGT);
break;
}
case BPF_JSGE:
@@ -5685,15 +5764,8 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
case BPF_JLE:
case BPF_JLT:
{
- u64 false_umin = opcode == BPF_JLT ? val : val + 1;
- u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
-
- if (is_jmp32) {
- false_umin += gen_hi_min(false_reg->var_off);
- true_umax += gen_hi_max(true_reg->var_off);
- }
- false_reg->umin_value = max(false_reg->umin_value, false_umin);
- true_reg->umax_value = min(true_reg->umax_value, true_umax);
+ set_lower_bound(false_reg, val, is_jmp32, opcode == BPF_JLE);
+ set_upper_bound(true_reg, val, is_jmp32, opcode == BPF_JLT);
break;
}
case BPF_JSLE:
@@ -5717,10 +5789,6 @@ static void reg_set_min_max(struct bpf_reg_state *true_reg,
/* We might have learned some bits from the bounds. */
__reg_bound_offset(false_reg);
__reg_bound_offset(true_reg);
- if (is_jmp32) {
- __reg_bound_offset32(false_reg);
- __reg_bound_offset32(true_reg);
- }
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
@@ -5772,15 +5840,8 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
case BPF_JGE:
case BPF_JGT:
{
- u64 false_umin = opcode == BPF_JGT ? val : val + 1;
- u64 true_umax = opcode == BPF_JGT ? val - 1 : val;
-
- if (is_jmp32) {
- false_umin += gen_hi_min(false_reg->var_off);
- true_umax += gen_hi_max(true_reg->var_off);
- }
- false_reg->umin_value = max(false_reg->umin_value, false_umin);
- true_reg->umax_value = min(true_reg->umax_value, true_umax);
+ set_lower_bound(false_reg, val, is_jmp32, opcode == BPF_JGE);
+ set_upper_bound(true_reg, val, is_jmp32, opcode == BPF_JGT);
break;
}
case BPF_JSGE:
@@ -5798,15 +5859,8 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
case BPF_JLE:
case BPF_JLT:
{
- u64 false_umax = opcode == BPF_JLT ? val : val - 1;
- u64 true_umin = opcode == BPF_JLT ? val + 1 : val;
-
- if (is_jmp32) {
- false_umax += gen_hi_max(false_reg->var_off);
- true_umin += gen_hi_min(true_reg->var_off);
- }
- false_reg->umax_value = min(false_reg->umax_value, false_umax);
- true_reg->umin_value = max(true_reg->umin_value, true_umin);
+ set_upper_bound(false_reg, val, is_jmp32, opcode == BPF_JLE);
+ set_lower_bound(true_reg, val, is_jmp32, opcode == BPF_JLT);
break;
}
case BPF_JSLE:
@@ -5830,10 +5884,6 @@ static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
/* We might have learned some bits from the bounds. */
__reg_bound_offset(false_reg);
__reg_bound_offset(true_reg);
- if (is_jmp32) {
- __reg_bound_offset32(false_reg);
- __reg_bound_offset32(true_reg);
- }
/* Intersecting with the old var_off might have improved our bounds
* slightly. e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
* then new var_off is (0; 0x7f...fc) which improves our umax.
@@ -9842,6 +9892,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
return -EINVAL;
}
env->ops = bpf_verifier_ops[tgt_prog->type];
+ prog->expected_attach_type = tgt_prog->expected_attach_type;
}
if (!tgt_prog->jited) {
verbose(env, "Can attach to only JITed progs\n");
@@ -10175,6 +10226,13 @@ err_release_maps:
* them now. Otherwise free_used_maps() will release them.
*/
release_maps(env);
+
+ /* extension progs temporarily inherit the attach_type of their targets
+ for verification purposes, so set it back to zero before returning
+ */
+ if (env->prog->type == BPF_PROG_TYPE_EXT)
+ env->prog->expected_attach_type = 0;
+
*prog = env->prog;
err_unlock:
if (!is_priv)
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-05-26 15:01:48 +0000