aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c230
-rw-r--r--kernel/entry/common.c2
-rw-r--r--kernel/trace/trace.c10
-rw-r--r--kernel/trace/trace_dynevent.c6
-rw-r--r--kernel/user_namespace.c65
5 files changed, 230 insertions, 83 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 3a738724a380..0399ac092b36 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5856,40 +5856,51 @@ static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
return &env->insn_aux_data[env->insn_idx];
}
+enum {
+ REASON_BOUNDS = -1,
+ REASON_TYPE = -2,
+ REASON_PATHS = -3,
+ REASON_LIMIT = -4,
+ REASON_STACK = -5,
+};
+
static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
- u32 *ptr_limit, u8 opcode, bool off_is_neg)
+ const struct bpf_reg_state *off_reg,
+ u32 *alu_limit, u8 opcode)
{
+ bool off_is_neg = off_reg->smin_value < 0;
bool mask_to_left = (opcode == BPF_ADD && off_is_neg) ||
(opcode == BPF_SUB && !off_is_neg);
- u32 off, max;
+ u32 max = 0, ptr_limit = 0;
+
+ if (!tnum_is_const(off_reg->var_off) &&
+ (off_reg->smin_value < 0) != (off_reg->smax_value < 0))
+ return REASON_BOUNDS;
switch (ptr_reg->type) {
case PTR_TO_STACK:
/* Offset 0 is out-of-bounds, but acceptable start for the
- * left direction, see BPF_REG_FP.
+ * left direction, see BPF_REG_FP. Also, unknown scalar
+ * offset where we would need to deal with min/max bounds is
+ * currently prohibited for unprivileged.
*/
max = MAX_BPF_STACK + mask_to_left;
- /* Indirect variable offset stack access is prohibited in
- * unprivileged mode so it's not handled here.
- */
- off = ptr_reg->off + ptr_reg->var_off.value;
- if (mask_to_left)
- *ptr_limit = MAX_BPF_STACK + off;
- else
- *ptr_limit = -off - 1;
- return *ptr_limit >= max ? -ERANGE : 0;
+ ptr_limit = -(ptr_reg->var_off.value + ptr_reg->off);
+ break;
case PTR_TO_MAP_VALUE:
max = ptr_reg->map_ptr->value_size;
- 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 - 1;
- }
- return *ptr_limit >= max ? -ERANGE : 0;
+ ptr_limit = (mask_to_left ?
+ ptr_reg->smin_value :
+ ptr_reg->umax_value) + ptr_reg->off;
+ break;
default:
- return -EINVAL;
+ return REASON_TYPE;
}
+
+ if (ptr_limit >= max)
+ return REASON_LIMIT;
+ *alu_limit = ptr_limit;
+ return 0;
}
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
@@ -5907,7 +5918,7 @@ static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
if (aux->alu_state &&
(aux->alu_state != alu_state ||
aux->alu_limit != alu_limit))
- return -EACCES;
+ return REASON_PATHS;
/* Corresponding fixup done in fixup_bpf_calls(). */
aux->alu_state = alu_state;
@@ -5926,14 +5937,22 @@ static int sanitize_val_alu(struct bpf_verifier_env *env,
return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}
+static bool sanitize_needed(u8 opcode)
+{
+ return opcode == BPF_ADD || opcode == BPF_SUB;
+}
+
static int sanitize_ptr_alu(struct bpf_verifier_env *env,
struct bpf_insn *insn,
const struct bpf_reg_state *ptr_reg,
+ const struct bpf_reg_state *off_reg,
struct bpf_reg_state *dst_reg,
- bool off_is_neg)
+ struct bpf_insn_aux_data *tmp_aux,
+ const bool commit_window)
{
+ struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : tmp_aux;
struct bpf_verifier_state *vstate = env->cur_state;
- struct bpf_insn_aux_data *aux = cur_aux(env);
+ bool off_is_neg = off_reg->smin_value < 0;
bool ptr_is_dst_reg = ptr_reg == dst_reg;
u8 opcode = BPF_OP(insn->code);
u32 alu_state, alu_limit;
@@ -5951,18 +5970,33 @@ static int sanitize_ptr_alu(struct bpf_verifier_env *env,
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;
-
- err = retrieve_ptr_limit(ptr_reg, &alu_limit, opcode, off_is_neg);
+ err = retrieve_ptr_limit(ptr_reg, off_reg, &alu_limit, opcode);
if (err < 0)
return err;
+ if (commit_window) {
+ /* In commit phase we narrow the masking window based on
+ * the observed pointer move after the simulated operation.
+ */
+ alu_state = tmp_aux->alu_state;
+ alu_limit = abs(tmp_aux->alu_limit - alu_limit);
+ } else {
+ alu_state = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
+ alu_state |= ptr_is_dst_reg ?
+ BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;
+ }
+
err = update_alu_sanitation_state(aux, alu_state, alu_limit);
if (err < 0)
return err;
do_sim:
+ /* If we're in commit phase, we're done here given we already
+ * pushed the truncated dst_reg into the speculative verification
+ * stack.
+ */
+ if (commit_window)
+ return 0;
+
/* 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
@@ -5979,7 +6013,46 @@ do_sim:
ret = push_stack(env, env->insn_idx + 1, env->insn_idx, true);
if (!ptr_is_dst_reg && ret)
*dst_reg = tmp;
- return !ret ? -EFAULT : 0;
+ return !ret ? REASON_STACK : 0;
+}
+
+static int sanitize_err(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn, int reason,
+ const struct bpf_reg_state *off_reg,
+ const struct bpf_reg_state *dst_reg)
+{
+ static const char *err = "pointer arithmetic with it prohibited for !root";
+ const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
+ u32 dst = insn->dst_reg, src = insn->src_reg;
+
+ switch (reason) {
+ case REASON_BOUNDS:
+ verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
+ off_reg == dst_reg ? dst : src, err);
+ break;
+ case REASON_TYPE:
+ verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
+ off_reg == dst_reg ? src : dst, err);
+ break;
+ case REASON_PATHS:
+ verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
+ dst, op, err);
+ break;
+ case REASON_LIMIT:
+ verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
+ dst, op, err);
+ break;
+ case REASON_STACK:
+ verbose(env, "R%d could not be pushed for speculative verification, %s\n",
+ dst, err);
+ break;
+ default:
+ verbose(env, "verifier internal error: unknown reason (%d)\n",
+ reason);
+ break;
+ }
+
+ return -EACCES;
}
/* check that stack access falls within stack limits and that 'reg' doesn't
@@ -6016,6 +6089,37 @@ static int check_stack_access_for_ptr_arithmetic(
return 0;
}
+static int sanitize_check_bounds(struct bpf_verifier_env *env,
+ const struct bpf_insn *insn,
+ const struct bpf_reg_state *dst_reg)
+{
+ u32 dst = insn->dst_reg;
+
+ /* For unprivileged we require that resulting offset must be in bounds
+ * in order to be able to sanitize access later on.
+ */
+ if (env->bypass_spec_v1)
+ return 0;
+
+ switch (dst_reg->type) {
+ case PTR_TO_STACK:
+ if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
+ dst_reg->off + dst_reg->var_off.value))
+ return -EACCES;
+ break;
+ case PTR_TO_MAP_VALUE:
+ if (check_map_access(env, dst, dst_reg->off, 1, false)) {
+ verbose(env, "R%d pointer arithmetic of map value goes out of range, "
+ "prohibited for !root\n", dst);
+ return -EACCES;
+ }
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
* Caller should also handle BPF_MOV case separately.
@@ -6035,8 +6139,9 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
- u32 dst = insn->dst_reg, src = insn->src_reg;
+ struct bpf_insn_aux_data tmp_aux = {};
u8 opcode = BPF_OP(insn->code);
+ u32 dst = insn->dst_reg;
int ret;
dst_reg = &regs[dst];
@@ -6084,13 +6189,6 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
verbose(env, "R%d pointer arithmetic on %s prohibited\n",
dst, reg_type_str[ptr_reg->type]);
return -EACCES;
- case PTR_TO_MAP_VALUE:
- if (!env->allow_ptr_leaks && !known && (smin_val < 0) != (smax_val < 0)) {
- verbose(env, "R%d has unknown scalar with mixed signed bounds, pointer arithmetic with it prohibited for !root\n",
- off_reg == dst_reg ? dst : src);
- return -EACCES;
- }
- fallthrough;
default:
break;
}
@@ -6108,13 +6206,15 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
/* pointer types do not carry 32-bit bounds at the moment. */
__mark_reg32_unbounded(dst_reg);
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
+ &tmp_aux, false);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
+ }
+
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, paths, or prohibited types\n", dst);
- return ret;
- }
/* We can take a fixed offset as long as it doesn't overflow
* the s32 'off' field
*/
@@ -6165,11 +6265,6 @@ 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, paths, or prohibited types\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",
@@ -6250,21 +6345,13 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
__reg_deduce_bounds(dst_reg);
__reg_bound_offset(dst_reg);
- /* For unprivileged we require that resulting offset must be in bounds
- * in order to be able to sanitize access later on.
- */
- if (!env->bypass_spec_v1) {
- if (dst_reg->type == PTR_TO_MAP_VALUE &&
- check_map_access(env, dst, dst_reg->off, 1, false)) {
- verbose(env, "R%d pointer arithmetic of map value goes out of range, "
- "prohibited for !root\n", dst);
- return -EACCES;
- } else if (dst_reg->type == PTR_TO_STACK &&
- check_stack_access_for_ptr_arithmetic(
- env, dst, dst_reg, dst_reg->off +
- dst_reg->var_off.value)) {
- return -EACCES;
- }
+ if (sanitize_check_bounds(env, insn, dst_reg) < 0)
+ return -EACCES;
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
+ &tmp_aux, true);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, off_reg, dst_reg);
}
return 0;
@@ -6858,9 +6945,8 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
s32 s32_min_val, s32_max_val;
u32 u32_min_val, u32_max_val;
u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;
- u32 dst = insn->dst_reg;
- int ret;
bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
+ int ret;
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
@@ -6902,6 +6988,12 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
return 0;
}
+ if (sanitize_needed(opcode)) {
+ ret = sanitize_val_alu(env, insn);
+ if (ret < 0)
+ return sanitize_err(env, insn, ret, NULL, NULL);
+ }
+
/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
* There are two classes of instructions: The first class we track both
* alu32 and alu64 sign/unsigned bounds independently this provides the
@@ -6918,21 +7010,11 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
*/
switch (opcode) {
case BPF_ADD:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to add from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_add(dst_reg, &src_reg);
scalar_min_max_add(dst_reg, &src_reg);
dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
break;
case BPF_SUB:
- ret = sanitize_val_alu(env, insn);
- if (ret < 0) {
- verbose(env, "R%d tried to sub from different pointers or scalars\n", dst);
- return ret;
- }
scalar32_min_max_sub(dst_reg, &src_reg);
scalar_min_max_sub(dst_reg, &src_reg);
dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index 8442e5c9cfa2..2003d69bd6d5 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -422,7 +422,7 @@ noinstr void irqentry_exit(struct pt_regs *regs, irqentry_state_t state)
instrumentation_begin();
if (IS_ENABLED(CONFIG_PREEMPTION)) {
-#ifdef CONFIG_PREEMT_DYNAMIC
+#ifdef CONFIG_PREEMPT_DYNAMIC
static_call(irqentry_exit_cond_resched)();
#else
irqentry_exit_cond_resched();
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 5c777627212f..c0c9aa5cd8e2 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3545,7 +3545,11 @@ static char *trace_iter_expand_format(struct trace_iterator *iter)
{
char *tmp;
- if (iter->fmt == static_fmt_buf)
+ /*
+ * iter->tr is NULL when used with tp_printk, which makes
+ * this get called where it is not safe to call krealloc().
+ */
+ if (!iter->tr || iter->fmt == static_fmt_buf)
return NULL;
tmp = krealloc(iter->fmt, iter->fmt_size + STATIC_FMT_BUF_SIZE,
@@ -3566,7 +3570,7 @@ const char *trace_event_format(struct trace_iterator *iter, const char *fmt)
if (WARN_ON_ONCE(!fmt))
return fmt;
- if (iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
+ if (!iter->tr || iter->tr->trace_flags & TRACE_ITER_HASH_PTR)
return fmt;
p = fmt;
@@ -9692,7 +9696,7 @@ void __init early_trace_init(void)
{
if (tracepoint_printk) {
tracepoint_print_iter =
- kmalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
+ kzalloc(sizeof(*tracepoint_print_iter), GFP_KERNEL);
if (MEM_FAIL(!tracepoint_print_iter,
"Failed to allocate trace iterator\n"))
tracepoint_printk = 0;
diff --git a/kernel/trace/trace_dynevent.c b/kernel/trace/trace_dynevent.c
index dc971a68dda4..e57cc0870892 100644
--- a/kernel/trace/trace_dynevent.c
+++ b/kernel/trace/trace_dynevent.c
@@ -63,8 +63,10 @@ int dyn_event_release(const char *raw_command, struct dyn_event_operations *type
event = p + 1;
*p = '\0';
}
- if (event[0] == '\0')
- return -EINVAL;
+ if (event[0] == '\0') {
+ ret = -EINVAL;
+ goto out;
+ }
mutex_lock(&event_mutex);
for_each_dyn_event_safe(pos, n) {
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index af612945a4d0..9a4b980d695b 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -106,6 +106,7 @@ int create_user_ns(struct cred *new)
if (!ns)
goto fail_dec;
+ ns->parent_could_setfcap = cap_raised(new->cap_effective, CAP_SETFCAP);
ret = ns_alloc_inum(&ns->ns);
if (ret)
goto fail_free;
@@ -841,6 +842,60 @@ static int sort_idmaps(struct uid_gid_map *map)
return 0;
}
+/**
+ * verify_root_map() - check the uid 0 mapping
+ * @file: idmapping file
+ * @map_ns: user namespace of the target process
+ * @new_map: requested idmap
+ *
+ * If a process requests mapping parent uid 0 into the new ns, verify that the
+ * process writing the map had the CAP_SETFCAP capability as the target process
+ * will be able to write fscaps that are valid in ancestor user namespaces.
+ *
+ * Return: true if the mapping is allowed, false if not.
+ */
+static bool verify_root_map(const struct file *file,
+ struct user_namespace *map_ns,
+ struct uid_gid_map *new_map)
+{
+ int idx;
+ const struct user_namespace *file_ns = file->f_cred->user_ns;
+ struct uid_gid_extent *extent0 = NULL;
+
+ for (idx = 0; idx < new_map->nr_extents; idx++) {
+ if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS)
+ extent0 = &new_map->extent[idx];
+ else
+ extent0 = &new_map->forward[idx];
+ if (extent0->lower_first == 0)
+ break;
+
+ extent0 = NULL;
+ }
+
+ if (!extent0)
+ return true;
+
+ if (map_ns == file_ns) {
+ /* The process unshared its ns and is writing to its own
+ * /proc/self/uid_map. User already has full capabilites in
+ * the new namespace. Verify that the parent had CAP_SETFCAP
+ * when it unshared.
+ * */
+ if (!file_ns->parent_could_setfcap)
+ return false;
+ } else {
+ /* Process p1 is writing to uid_map of p2, who is in a child
+ * user namespace to p1's. Verify that the opener of the map
+ * file has CAP_SETFCAP against the parent of the new map
+ * namespace */
+ if (!file_ns_capable(file, map_ns->parent, CAP_SETFCAP))
+ return false;
+ }
+
+ return true;
+}
+
static ssize_t map_write(struct file *file, const char __user *buf,
size_t count, loff_t *ppos,
int cap_setid,
@@ -848,7 +903,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
struct uid_gid_map *parent_map)
{
struct seq_file *seq = file->private_data;
- struct user_namespace *ns = seq->private;
+ struct user_namespace *map_ns = seq->private;
struct uid_gid_map new_map;
unsigned idx;
struct uid_gid_extent extent;
@@ -895,7 +950,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
/*
* Adjusting namespace settings requires capabilities on the target.
*/
- if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
+ if (cap_valid(cap_setid) && !file_ns_capable(file, map_ns, CAP_SYS_ADMIN))
goto out;
/* Parse the user data */
@@ -965,7 +1020,7 @@ static ssize_t map_write(struct file *file, const char __user *buf,
ret = -EPERM;
/* Validate the user is allowed to use user id's mapped to. */
- if (!new_idmap_permitted(file, ns, cap_setid, &new_map))
+ if (!new_idmap_permitted(file, map_ns, cap_setid, &new_map))
goto out;
ret = -EPERM;
@@ -1086,6 +1141,10 @@ static bool new_idmap_permitted(const struct file *file,
struct uid_gid_map *new_map)
{
const struct cred *cred = file->f_cred;
+
+ if (cap_setid == CAP_SETUID && !verify_root_map(file, ns, new_map))
+ return false;
+
/* Don't allow mappings that would allow anything that wouldn't
* be allowed without the establishment of unprivileged mappings.
*/
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.