From a5969cabbb4660eab42b6ef0412cbbd1200cf14d Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Sat, 12 Oct 2024 07:10:09 +0000
Subject: [PATCH] 修改led为gpio
---
kernel/kernel/bpf/verifier.c | 8750 +++++++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 7,468 insertions(+), 1,282 deletions(-)
diff --git a/kernel/kernel/bpf/verifier.c b/kernel/kernel/bpf/verifier.c
index 30ac8ee..f6a239a 100644
--- a/kernel/kernel/bpf/verifier.c
+++ b/kernel/kernel/bpf/verifier.c
@@ -1,19 +1,14 @@
+// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
* Copyright (c) 2016 Facebook
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public
- * License as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
+ * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
*/
+#include <uapi/linux/btf.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
+#include <linux/btf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
@@ -23,16 +18,22 @@
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>
+#include <linux/ctype.h>
+#include <linux/error-injection.h>
+#include <linux/bpf_lsm.h>
+#include <linux/btf_ids.h>
#include "disasm.h"
static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
[_id] = & _name ## _verifier_ops,
#define BPF_MAP_TYPE(_id, _ops)
+#define BPF_LINK_TYPE(_id, _name)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
+#undef BPF_LINK_TYPE
};
/* bpf_check() is a static code analyzer that walks eBPF program
@@ -80,8 +81,8 @@
* (like pointer plus pointer becomes SCALAR_VALUE type)
*
* When verifier sees load or store instructions the type of base register
- * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK. These are three pointer
- * types recognized by check_mem_access() function.
+ * can be: PTR_TO_MAP_VALUE, PTR_TO_CTX, PTR_TO_STACK, PTR_TO_SOCKET. These are
+ * four pointer types recognized by check_mem_access() function.
*
* PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
* and the range of [ptr, ptr + map's value_size) is accessible.
@@ -140,6 +141,24 @@
*
* After the call R0 is set to return type of the function and registers R1-R5
* are set to NOT_INIT to indicate that they are no longer readable.
+ *
+ * The following reference types represent a potential reference to a kernel
+ * resource which, after first being allocated, must be checked and freed by
+ * the BPF program:
+ * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET
+ *
+ * When the verifier sees a helper call return a reference type, it allocates a
+ * pointer id for the reference and stores it in the current function state.
+ * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into
+ * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
+ * passes through a NULL-check conditional. For the branch wherein the state is
+ * changed to CONST_IMM, the verifier releases the reference.
+ *
+ * For each helper function that allocates a reference, such as
+ * bpf_sk_lookup_tcp(), there is a corresponding release function, such as
+ * bpf_sk_release(). When a reference type passes into the release function,
+ * the verifier also releases the reference. If any unchecked or unreleased
+ * reference remains at the end of the program, the verifier rejects it.
*/
/* verifier_state + insn_idx are pushed to stack when branch is encountered */
@@ -152,11 +171,15 @@
int insn_idx;
int prev_insn_idx;
struct bpf_verifier_stack_elem *next;
+ /* length of verifier log at the time this state was pushed on stack */
+ u32 log_pos;
};
-#define BPF_COMPLEXITY_LIMIT_INSNS 131072
-#define BPF_COMPLEXITY_LIMIT_STACK 1024
+#define BPF_COMPLEXITY_LIMIT_JMP_SEQ 8192
#define BPF_COMPLEXITY_LIMIT_STATES 64
+
+#define BPF_MAP_KEY_POISON (1ULL << 63)
+#define BPF_MAP_KEY_SEEN (1ULL << 62)
#define BPF_MAP_PTR_UNPRIV 1UL
#define BPF_MAP_PTR_POISON ((void *)((0xeB9FUL << 1) + \
@@ -165,12 +188,12 @@
static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
{
- return BPF_MAP_PTR(aux->map_state) == BPF_MAP_PTR_POISON;
+ return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON;
}
static bool bpf_map_ptr_unpriv(const struct bpf_insn_aux_data *aux)
{
- return aux->map_state & BPF_MAP_PTR_UNPRIV;
+ return aux->map_ptr_state & BPF_MAP_PTR_UNPRIV;
}
static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
@@ -178,8 +201,31 @@
{
BUILD_BUG_ON((unsigned long)BPF_MAP_PTR_POISON & BPF_MAP_PTR_UNPRIV);
unpriv |= bpf_map_ptr_unpriv(aux);
- aux->map_state = (unsigned long)map |
- (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
+ aux->map_ptr_state = (unsigned long)map |
+ (unpriv ? BPF_MAP_PTR_UNPRIV : 0UL);
+}
+
+static bool bpf_map_key_poisoned(const struct bpf_insn_aux_data *aux)
+{
+ return aux->map_key_state & BPF_MAP_KEY_POISON;
+}
+
+static bool bpf_map_key_unseen(const struct bpf_insn_aux_data *aux)
+{
+ return !(aux->map_key_state & BPF_MAP_KEY_SEEN);
+}
+
+static u64 bpf_map_key_immediate(const struct bpf_insn_aux_data *aux)
+{
+ return aux->map_key_state & ~(BPF_MAP_KEY_SEEN | BPF_MAP_KEY_POISON);
+}
+
+static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
+{
+ bool poisoned = bpf_map_key_poisoned(aux);
+
+ aux->map_key_state = state | BPF_MAP_KEY_SEEN |
+ (poisoned ? BPF_MAP_KEY_POISON : 0ULL);
}
struct bpf_call_arg_meta {
@@ -188,10 +234,38 @@
bool pkt_access;
int regno;
int access_size;
+ int mem_size;
u64 msize_max_value;
+ int ref_obj_id;
+ int func_id;
+ u32 btf_id;
+ u32 ret_btf_id;
};
+struct btf *btf_vmlinux;
+
static DEFINE_MUTEX(bpf_verifier_lock);
+
+static const struct bpf_line_info *
+find_linfo(const struct bpf_verifier_env *env, u32 insn_off)
+{
+ const struct bpf_line_info *linfo;
+ const struct bpf_prog *prog;
+ u32 i, nr_linfo;
+
+ prog = env->prog;
+ nr_linfo = prog->aux->nr_linfo;
+
+ if (!nr_linfo || insn_off >= prog->len)
+ return NULL;
+
+ linfo = prog->aux->linfo;
+ for (i = 1; i < nr_linfo; i++)
+ if (insn_off < linfo[i].insn_off)
+ break;
+
+ return &linfo[i - 1];
+}
void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
va_list args)
@@ -206,9 +280,25 @@
n = min(log->len_total - log->len_used - 1, n);
log->kbuf[n] = '\0';
+ if (log->level == BPF_LOG_KERNEL) {
+ pr_err("BPF:%s\n", log->kbuf);
+ return;
+ }
if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
log->len_used += n;
else
+ log->ubuf = NULL;
+}
+
+static void bpf_vlog_reset(struct bpf_verifier_log *log, u32 new_pos)
+{
+ char zero = 0;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ log->len_used = new_pos;
+ if (put_user(zero, log->ubuf + new_pos))
log->ubuf = NULL;
}
@@ -243,10 +333,167 @@
va_end(args);
}
+__printf(2, 3) void bpf_log(struct bpf_verifier_log *log,
+ const char *fmt, ...)
+{
+ va_list args;
+
+ if (!bpf_verifier_log_needed(log))
+ return;
+
+ va_start(args, fmt);
+ bpf_verifier_vlog(log, fmt, args);
+ va_end(args);
+}
+
+static const char *ltrim(const char *s)
+{
+ while (isspace(*s))
+ s++;
+
+ return s;
+}
+
+__printf(3, 4) static void verbose_linfo(struct bpf_verifier_env *env,
+ u32 insn_off,
+ const char *prefix_fmt, ...)
+{
+ const struct bpf_line_info *linfo;
+
+ if (!bpf_verifier_log_needed(&env->log))
+ return;
+
+ linfo = find_linfo(env, insn_off);
+ if (!linfo || linfo == env->prev_linfo)
+ return;
+
+ if (prefix_fmt) {
+ va_list args;
+
+ va_start(args, prefix_fmt);
+ bpf_verifier_vlog(&env->log, prefix_fmt, args);
+ va_end(args);
+ }
+
+ verbose(env, "%s\n",
+ ltrim(btf_name_by_offset(env->prog->aux->btf,
+ linfo->line_off)));
+
+ env->prev_linfo = linfo;
+}
+
static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
return type == PTR_TO_PACKET ||
type == PTR_TO_PACKET_META;
+}
+
+static bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+ return type == PTR_TO_SOCKET ||
+ type == PTR_TO_SOCK_COMMON ||
+ type == PTR_TO_TCP_SOCK ||
+ type == PTR_TO_XDP_SOCK;
+}
+
+static bool reg_type_not_null(enum bpf_reg_type type)
+{
+ return type == PTR_TO_SOCKET ||
+ type == PTR_TO_TCP_SOCK ||
+ type == PTR_TO_MAP_VALUE ||
+ type == PTR_TO_SOCK_COMMON;
+}
+
+static bool reg_type_may_be_null(enum bpf_reg_type type)
+{
+ return type == PTR_TO_MAP_VALUE_OR_NULL ||
+ type == PTR_TO_SOCKET_OR_NULL ||
+ type == PTR_TO_SOCK_COMMON_OR_NULL ||
+ type == PTR_TO_TCP_SOCK_OR_NULL ||
+ type == PTR_TO_BTF_ID_OR_NULL ||
+ type == PTR_TO_MEM_OR_NULL ||
+ type == PTR_TO_RDONLY_BUF_OR_NULL ||
+ type == PTR_TO_RDWR_BUF_OR_NULL;
+}
+
+static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
+{
+ return reg->type == PTR_TO_MAP_VALUE &&
+ map_value_has_spin_lock(reg->map_ptr);
+}
+
+static bool reg_type_may_be_refcounted_or_null(enum bpf_reg_type type)
+{
+ return type == PTR_TO_SOCKET ||
+ type == PTR_TO_SOCKET_OR_NULL ||
+ type == PTR_TO_TCP_SOCK ||
+ type == PTR_TO_TCP_SOCK_OR_NULL ||
+ type == PTR_TO_MEM ||
+ type == PTR_TO_MEM_OR_NULL;
+}
+
+static bool arg_type_may_be_refcounted(enum bpf_arg_type type)
+{
+ return type == ARG_PTR_TO_SOCK_COMMON;
+}
+
+static bool arg_type_may_be_null(enum bpf_arg_type type)
+{
+ return type == ARG_PTR_TO_MAP_VALUE_OR_NULL ||
+ type == ARG_PTR_TO_MEM_OR_NULL ||
+ type == ARG_PTR_TO_CTX_OR_NULL ||
+ type == ARG_PTR_TO_SOCKET_OR_NULL ||
+ type == ARG_PTR_TO_ALLOC_MEM_OR_NULL;
+}
+
+/* Determine whether the function releases some resources allocated by another
+ * function call. The first reference type argument will be assumed to be
+ * released by release_reference().
+ */
+static bool is_release_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_sk_release ||
+ func_id == BPF_FUNC_ringbuf_submit ||
+ func_id == BPF_FUNC_ringbuf_discard;
+}
+
+static bool may_be_acquire_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_sk_lookup_tcp ||
+ func_id == BPF_FUNC_sk_lookup_udp ||
+ func_id == BPF_FUNC_skc_lookup_tcp ||
+ func_id == BPF_FUNC_map_lookup_elem ||
+ func_id == BPF_FUNC_ringbuf_reserve;
+}
+
+static bool is_acquire_function(enum bpf_func_id func_id,
+ const struct bpf_map *map)
+{
+ enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC;
+
+ if (func_id == BPF_FUNC_sk_lookup_tcp ||
+ func_id == BPF_FUNC_sk_lookup_udp ||
+ func_id == BPF_FUNC_skc_lookup_tcp ||
+ func_id == BPF_FUNC_ringbuf_reserve)
+ return true;
+
+ if (func_id == BPF_FUNC_map_lookup_elem &&
+ (map_type == BPF_MAP_TYPE_SOCKMAP ||
+ map_type == BPF_MAP_TYPE_SOCKHASH))
+ return true;
+
+ return false;
+}
+
+static bool is_ptr_cast_function(enum bpf_func_id func_id)
+{
+ return func_id == BPF_FUNC_tcp_sock ||
+ func_id == BPF_FUNC_sk_fullsock ||
+ func_id == BPF_FUNC_skc_to_tcp_sock ||
+ func_id == BPF_FUNC_skc_to_tcp6_sock ||
+ func_id == BPF_FUNC_skc_to_udp6_sock ||
+ func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
+ func_id == BPF_FUNC_skc_to_tcp_request_sock;
}
/* string representation of 'enum bpf_reg_type' */
@@ -261,17 +508,44 @@
[PTR_TO_PACKET] = "pkt",
[PTR_TO_PACKET_META] = "pkt_meta",
[PTR_TO_PACKET_END] = "pkt_end",
+ [PTR_TO_FLOW_KEYS] = "flow_keys",
+ [PTR_TO_SOCKET] = "sock",
+ [PTR_TO_SOCKET_OR_NULL] = "sock_or_null",
+ [PTR_TO_SOCK_COMMON] = "sock_common",
+ [PTR_TO_SOCK_COMMON_OR_NULL] = "sock_common_or_null",
+ [PTR_TO_TCP_SOCK] = "tcp_sock",
+ [PTR_TO_TCP_SOCK_OR_NULL] = "tcp_sock_or_null",
+ [PTR_TO_TP_BUFFER] = "tp_buffer",
+ [PTR_TO_XDP_SOCK] = "xdp_sock",
+ [PTR_TO_BTF_ID] = "ptr_",
+ [PTR_TO_BTF_ID_OR_NULL] = "ptr_or_null_",
+ [PTR_TO_PERCPU_BTF_ID] = "percpu_ptr_",
+ [PTR_TO_MEM] = "mem",
+ [PTR_TO_MEM_OR_NULL] = "mem_or_null",
+ [PTR_TO_RDONLY_BUF] = "rdonly_buf",
+ [PTR_TO_RDONLY_BUF_OR_NULL] = "rdonly_buf_or_null",
+ [PTR_TO_RDWR_BUF] = "rdwr_buf",
+ [PTR_TO_RDWR_BUF_OR_NULL] = "rdwr_buf_or_null",
+};
+
+static char slot_type_char[] = {
+ [STACK_INVALID] = '?',
+ [STACK_SPILL] = 'r',
+ [STACK_MISC] = 'm',
+ [STACK_ZERO] = '0',
};
static void print_liveness(struct bpf_verifier_env *env,
enum bpf_reg_liveness live)
{
- if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+ if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN | REG_LIVE_DONE))
verbose(env, "_");
if (live & REG_LIVE_READ)
verbose(env, "r");
if (live & REG_LIVE_WRITTEN)
verbose(env, "w");
+ if (live & REG_LIVE_DONE)
+ verbose(env, "D");
}
static struct bpf_func_state *func(struct bpf_verifier_env *env,
@@ -280,6 +554,26 @@
struct bpf_verifier_state *cur = env->cur_state;
return cur->frame[reg->frameno];
+}
+
+const char *kernel_type_name(u32 id)
+{
+ return btf_name_by_offset(btf_vmlinux,
+ btf_type_by_id(btf_vmlinux, id)->name_off);
+}
+
+/* The reg state of a pointer or a bounded scalar was saved when
+ * it was spilled to the stack.
+ */
+static bool is_spilled_reg(const struct bpf_stack_state *stack)
+{
+ return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
+}
+
+static void scrub_spilled_slot(u8 *stype)
+{
+ if (*stype != STACK_INVALID)
+ *stype = STACK_MISC;
}
static void print_verifier_state(struct bpf_verifier_env *env,
@@ -299,14 +593,20 @@
verbose(env, " R%d", i);
print_liveness(env, reg->live);
verbose(env, "=%s", reg_type_str[t]);
+ if (t == SCALAR_VALUE && reg->precise)
+ verbose(env, "P");
if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
tnum_is_const(reg->var_off)) {
/* reg->off should be 0 for SCALAR_VALUE */
verbose(env, "%lld", reg->var_off.value + reg->off);
- if (t == PTR_TO_STACK)
- verbose(env, ",call_%d", func(env, reg)->callsite);
} else {
+ if (t == PTR_TO_BTF_ID ||
+ t == PTR_TO_BTF_ID_OR_NULL ||
+ t == PTR_TO_PERCPU_BTF_ID)
+ verbose(env, "%s", kernel_type_name(reg->btf_id));
verbose(env, "(id=%d", reg->id);
+ if (reg_type_may_be_refcounted_or_null(t))
+ verbose(env, ",ref_obj_id=%d", reg->ref_obj_id);
if (t != SCALAR_VALUE)
verbose(env, ",off=%d", reg->off);
if (type_is_pkt_pointer(t))
@@ -344,77 +644,189 @@
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
verbose(env, ",var_off=%s", tn_buf);
}
+ if (reg->s32_min_value != reg->smin_value &&
+ reg->s32_min_value != S32_MIN)
+ verbose(env, ",s32_min_value=%d",
+ (int)(reg->s32_min_value));
+ if (reg->s32_max_value != reg->smax_value &&
+ reg->s32_max_value != S32_MAX)
+ verbose(env, ",s32_max_value=%d",
+ (int)(reg->s32_max_value));
+ if (reg->u32_min_value != reg->umin_value &&
+ reg->u32_min_value != U32_MIN)
+ verbose(env, ",u32_min_value=%d",
+ (int)(reg->u32_min_value));
+ if (reg->u32_max_value != reg->umax_value &&
+ reg->u32_max_value != U32_MAX)
+ verbose(env, ",u32_max_value=%d",
+ (int)(reg->u32_max_value));
}
verbose(env, ")");
}
}
for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- if (state->stack[i].slot_type[0] == STACK_SPILL) {
- verbose(env, " fp%d",
- (-i - 1) * BPF_REG_SIZE);
- print_liveness(env, state->stack[i].spilled_ptr.live);
- verbose(env, "=%s",
- reg_type_str[state->stack[i].spilled_ptr.type]);
+ char types_buf[BPF_REG_SIZE + 1];
+ bool valid = false;
+ int j;
+
+ for (j = 0; j < BPF_REG_SIZE; j++) {
+ if (state->stack[i].slot_type[j] != STACK_INVALID)
+ valid = true;
+ types_buf[j] = slot_type_char[
+ state->stack[i].slot_type[j]];
}
- if (state->stack[i].slot_type[0] == STACK_ZERO)
- verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
+ types_buf[BPF_REG_SIZE] = 0;
+ if (!valid)
+ continue;
+ verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+ print_liveness(env, state->stack[i].spilled_ptr.live);
+ if (is_spilled_reg(&state->stack[i])) {
+ reg = &state->stack[i].spilled_ptr;
+ t = reg->type;
+ verbose(env, "=%s", reg_type_str[t]);
+ if (t == SCALAR_VALUE && reg->precise)
+ verbose(env, "P");
+ if (t == SCALAR_VALUE && tnum_is_const(reg->var_off))
+ verbose(env, "%lld", reg->var_off.value + reg->off);
+ } else {
+ verbose(env, "=%s", types_buf);
+ }
+ }
+ if (state->acquired_refs && state->refs[0].id) {
+ verbose(env, " refs=%d", state->refs[0].id);
+ for (i = 1; i < state->acquired_refs; i++)
+ if (state->refs[i].id)
+ verbose(env, ",%d", state->refs[i].id);
}
verbose(env, "\n");
}
-static int copy_stack_state(struct bpf_func_state *dst,
- const struct bpf_func_state *src)
-{
- if (!src->stack)
- return 0;
- if (WARN_ON_ONCE(dst->allocated_stack < src->allocated_stack)) {
- /* internal bug, make state invalid to reject the program */
- memset(dst, 0, sizeof(*dst));
- return -EFAULT;
- }
- memcpy(dst->stack, src->stack,
- sizeof(*src->stack) * (src->allocated_stack / BPF_REG_SIZE));
- return 0;
+#define COPY_STATE_FN(NAME, COUNT, FIELD, SIZE) \
+static int copy_##NAME##_state(struct bpf_func_state *dst, \
+ const struct bpf_func_state *src) \
+{ \
+ if (!src->FIELD) \
+ return 0; \
+ if (WARN_ON_ONCE(dst->COUNT < src->COUNT)) { \
+ /* internal bug, make state invalid to reject the program */ \
+ memset(dst, 0, sizeof(*dst)); \
+ return -EFAULT; \
+ } \
+ memcpy(dst->FIELD, src->FIELD, \
+ sizeof(*src->FIELD) * (src->COUNT / SIZE)); \
+ return 0; \
}
+/* copy_reference_state() */
+COPY_STATE_FN(reference, acquired_refs, refs, 1)
+/* copy_stack_state() */
+COPY_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
+#undef COPY_STATE_FN
+
+#define REALLOC_STATE_FN(NAME, COUNT, FIELD, SIZE) \
+static int realloc_##NAME##_state(struct bpf_func_state *state, int size, \
+ bool copy_old) \
+{ \
+ u32 old_size = state->COUNT; \
+ struct bpf_##NAME##_state *new_##FIELD; \
+ int slot = size / SIZE; \
+ \
+ if (size <= old_size || !size) { \
+ if (copy_old) \
+ return 0; \
+ state->COUNT = slot * SIZE; \
+ if (!size && old_size) { \
+ kfree(state->FIELD); \
+ state->FIELD = NULL; \
+ } \
+ return 0; \
+ } \
+ new_##FIELD = kmalloc_array(slot, sizeof(struct bpf_##NAME##_state), \
+ GFP_KERNEL); \
+ if (!new_##FIELD) \
+ return -ENOMEM; \
+ if (copy_old) { \
+ if (state->FIELD) \
+ memcpy(new_##FIELD, state->FIELD, \
+ sizeof(*new_##FIELD) * (old_size / SIZE)); \
+ memset(new_##FIELD + old_size / SIZE, 0, \
+ sizeof(*new_##FIELD) * (size - old_size) / SIZE); \
+ } \
+ state->COUNT = slot * SIZE; \
+ kfree(state->FIELD); \
+ state->FIELD = new_##FIELD; \
+ return 0; \
+}
+/* realloc_reference_state() */
+REALLOC_STATE_FN(reference, acquired_refs, refs, 1)
+/* realloc_stack_state() */
+REALLOC_STATE_FN(stack, allocated_stack, stack, BPF_REG_SIZE)
+#undef REALLOC_STATE_FN
/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
* make it consume minimal amount of memory. check_stack_write() access from
* the program calls into realloc_func_state() to grow the stack size.
- * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state
- * which this function copies over. It points to corresponding reg in previous
- * bpf_verifier_state which is never reallocated
+ * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
+ * which realloc_stack_state() copies over. It points to previous
+ * bpf_verifier_state which is never reallocated.
*/
-static int realloc_func_state(struct bpf_func_state *state, int size,
- bool copy_old)
+static int realloc_func_state(struct bpf_func_state *state, int stack_size,
+ int refs_size, bool copy_old)
{
- u32 old_size = state->allocated_stack;
- struct bpf_stack_state *new_stack;
- int slot = size / BPF_REG_SIZE;
+ int err = realloc_reference_state(state, refs_size, copy_old);
+ if (err)
+ return err;
+ return realloc_stack_state(state, stack_size, copy_old);
+}
- if (size <= old_size || !size) {
- if (copy_old)
+/* Acquire a pointer id from the env and update the state->refs to include
+ * this new pointer reference.
+ * On success, returns a valid pointer id to associate with the register
+ * On failure, returns a negative errno.
+ */
+static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
+{
+ struct bpf_func_state *state = cur_func(env);
+ int new_ofs = state->acquired_refs;
+ int id, err;
+
+ err = realloc_reference_state(state, state->acquired_refs + 1, true);
+ if (err)
+ return err;
+ id = ++env->id_gen;
+ state->refs[new_ofs].id = id;
+ state->refs[new_ofs].insn_idx = insn_idx;
+
+ return id;
+}
+
+/* release function corresponding to acquire_reference_state(). Idempotent. */
+static int release_reference_state(struct bpf_func_state *state, int ptr_id)
+{
+ int i, last_idx;
+
+ last_idx = state->acquired_refs - 1;
+ for (i = 0; i < state->acquired_refs; i++) {
+ if (state->refs[i].id == ptr_id) {
+ if (last_idx && i != last_idx)
+ memcpy(&state->refs[i], &state->refs[last_idx],
+ sizeof(*state->refs));
+ memset(&state->refs[last_idx], 0, sizeof(*state->refs));
+ state->acquired_refs--;
return 0;
- state->allocated_stack = slot * BPF_REG_SIZE;
- if (!size && old_size) {
- kfree(state->stack);
- state->stack = NULL;
}
- return 0;
}
- new_stack = kmalloc_array(slot, sizeof(struct bpf_stack_state),
- GFP_KERNEL);
- if (!new_stack)
- return -ENOMEM;
- if (copy_old) {
- if (state->stack)
- memcpy(new_stack, state->stack,
- sizeof(*new_stack) * (old_size / BPF_REG_SIZE));
- memset(new_stack + old_size / BPF_REG_SIZE, 0,
- sizeof(*new_stack) * (size - old_size) / BPF_REG_SIZE);
- }
- state->allocated_stack = slot * BPF_REG_SIZE;
- kfree(state->stack);
- state->stack = new_stack;
+ return -EINVAL;
+}
+
+static int transfer_reference_state(struct bpf_func_state *dst,
+ struct bpf_func_state *src)
+{
+ int err = realloc_reference_state(dst, src->acquired_refs, false);
+ if (err)
+ return err;
+ err = copy_reference_state(dst, src);
+ if (err)
+ return err;
return 0;
}
@@ -422,8 +834,16 @@
{
if (!state)
return;
+ kfree(state->refs);
kfree(state->stack);
kfree(state);
+}
+
+static void clear_jmp_history(struct bpf_verifier_state *state)
+{
+ kfree(state->jmp_history);
+ state->jmp_history = NULL;
+ state->jmp_history_cnt = 0;
}
static void free_verifier_state(struct bpf_verifier_state *state,
@@ -435,6 +855,7 @@
free_func_state(state->frame[i]);
state->frame[i] = NULL;
}
+ clear_jmp_history(state);
if (free_self)
kfree(state);
}
@@ -447,10 +868,14 @@
{
int err;
- err = realloc_func_state(dst, src->allocated_stack, false);
+ err = realloc_func_state(dst, src->allocated_stack, src->acquired_refs,
+ false);
if (err)
return err;
- memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
+ memcpy(dst, src, offsetof(struct bpf_func_state, acquired_refs));
+ err = copy_reference_state(dst, src);
+ if (err)
+ return err;
return copy_stack_state(dst, src);
}
@@ -458,7 +883,17 @@
const struct bpf_verifier_state *src)
{
struct bpf_func_state *dst;
+ u32 jmp_sz = sizeof(struct bpf_idx_pair) * src->jmp_history_cnt;
int i, err;
+
+ if (dst_state->jmp_history_cnt < src->jmp_history_cnt) {
+ kfree(dst_state->jmp_history);
+ dst_state->jmp_history = kmalloc(jmp_sz, GFP_USER);
+ if (!dst_state->jmp_history)
+ return -ENOMEM;
+ }
+ memcpy(dst_state->jmp_history, src->jmp_history, jmp_sz);
+ dst_state->jmp_history_cnt = src->jmp_history_cnt;
/* if dst has more stack frames then src frame, free them */
for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
@@ -467,6 +902,11 @@
}
dst_state->speculative = src->speculative;
dst_state->curframe = src->curframe;
+ dst_state->active_spin_lock = src->active_spin_lock;
+ dst_state->branches = src->branches;
+ dst_state->parent = src->parent;
+ dst_state->first_insn_idx = src->first_insn_idx;
+ dst_state->last_insn_idx = src->last_insn_idx;
for (i = 0; i <= src->curframe; i++) {
dst = dst_state->frame[i];
if (!dst) {
@@ -482,8 +922,25 @@
return 0;
}
+static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ while (st) {
+ u32 br = --st->branches;
+
+ /* WARN_ON(br > 1) technically makes sense here,
+ * but see comment in push_stack(), hence:
+ */
+ WARN_ONCE((int)br < 0,
+ "BUG update_branch_counts:branches_to_explore=%d\n",
+ br);
+ if (br)
+ break;
+ st = st->parent;
+ }
+}
+
static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
- int *insn_idx)
+ int *insn_idx, bool pop_log)
{
struct bpf_verifier_state *cur = env->cur_state;
struct bpf_verifier_stack_elem *elem, *head = env->head;
@@ -497,6 +954,8 @@
if (err)
return err;
}
+ if (pop_log)
+ bpf_vlog_reset(&env->log, head->log_pos);
if (insn_idx)
*insn_idx = head->insn_idx;
if (prev_insn_idx)
@@ -524,22 +983,36 @@
elem->insn_idx = insn_idx;
elem->prev_insn_idx = prev_insn_idx;
elem->next = env->head;
+ elem->log_pos = env->log.len_used;
env->head = elem;
env->stack_size++;
err = copy_verifier_state(&elem->st, cur);
if (err)
goto err;
elem->st.speculative |= speculative;
- if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
- verbose(env, "BPF program is too complex\n");
+ if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
+ verbose(env, "The sequence of %d jumps is too complex.\n",
+ env->stack_size);
goto err;
+ }
+ if (elem->st.parent) {
+ ++elem->st.parent->branches;
+ /* WARN_ON(branches > 2) technically makes sense here,
+ * but
+ * 1. speculative states will bump 'branches' for non-branch
+ * instructions
+ * 2. is_state_visited() heuristics may decide not to create
+ * a new state for a sequence of branches and all such current
+ * and cloned states will be pointing to a single parent state
+ * which might have large 'branches' count.
+ */
}
return &elem->st;
err:
free_verifier_state(env->cur_state, true);
env->cur_state = NULL;
/* pop all elements and return */
- while (!pop_stack(env, NULL, NULL));
+ while (!pop_stack(env, NULL, NULL, false));
return NULL;
}
@@ -548,7 +1021,23 @@
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
-static void __mark_reg_not_init(struct bpf_reg_state *reg);
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg);
+
+/* This helper doesn't clear reg->id */
+static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm)
+{
+ reg->var_off = tnum_const(imm);
+ reg->smin_value = (s64)imm;
+ reg->smax_value = (s64)imm;
+ reg->umin_value = imm;
+ reg->umax_value = imm;
+
+ reg->s32_min_value = (s32)imm;
+ reg->s32_max_value = (s32)imm;
+ reg->u32_min_value = (u32)imm;
+ reg->u32_max_value = (u32)imm;
+}
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
@@ -558,11 +1047,16 @@
/* Clear id, off, and union(map_ptr, range) */
memset(((u8 *)reg) + sizeof(reg->type), 0,
offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
- reg->var_off = tnum_const(imm);
- reg->smin_value = (s64)imm;
- reg->smax_value = (s64)imm;
- reg->umin_value = imm;
- reg->umax_value = imm;
+ ___mark_reg_known(reg, imm);
+}
+
+static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm)
+{
+ reg->var_off = tnum_const_subreg(reg->var_off, imm);
+ reg->s32_min_value = (s32)imm;
+ reg->s32_max_value = (s32)imm;
+ reg->u32_min_value = (u32)imm;
+ reg->u32_max_value = (u32)imm;
}
/* Mark the 'variable offset' part of a register as zero. This should be
@@ -586,7 +1080,7 @@
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
@@ -617,8 +1111,52 @@
tnum_equals_const(reg->var_off, 0);
}
-/* Attempts to improve min/max values based on var_off information */
-static void __update_reg_bounds(struct bpf_reg_state *reg)
+/* Reset the min/max bounds of a register */
+static void __mark_reg_unbounded(struct bpf_reg_state *reg)
+{
+ reg->smin_value = S64_MIN;
+ reg->smax_value = S64_MAX;
+ reg->umin_value = 0;
+ reg->umax_value = U64_MAX;
+
+ reg->s32_min_value = S32_MIN;
+ reg->s32_max_value = S32_MAX;
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void __mark_reg64_unbounded(struct bpf_reg_state *reg)
+{
+ reg->smin_value = S64_MIN;
+ reg->smax_value = S64_MAX;
+ reg->umin_value = 0;
+ reg->umax_value = U64_MAX;
+}
+
+static void __mark_reg32_unbounded(struct bpf_reg_state *reg)
+{
+ reg->s32_min_value = S32_MIN;
+ reg->s32_max_value = S32_MAX;
+ reg->u32_min_value = 0;
+ reg->u32_max_value = U32_MAX;
+}
+
+static void __update_reg32_bounds(struct bpf_reg_state *reg)
+{
+ struct tnum var32_off = tnum_subreg(reg->var_off);
+
+ /* min signed is max(sign bit) | min(other bits) */
+ reg->s32_min_value = max_t(s32, reg->s32_min_value,
+ var32_off.value | (var32_off.mask & S32_MIN));
+ /* max signed is min(sign bit) | max(other bits) */
+ reg->s32_max_value = min_t(s32, reg->s32_max_value,
+ var32_off.value | (var32_off.mask & S32_MAX));
+ reg->u32_min_value = max_t(u32, reg->u32_min_value, (u32)var32_off.value);
+ reg->u32_max_value = min(reg->u32_max_value,
+ (u32)(var32_off.value | var32_off.mask));
+}
+
+static void __update_reg64_bounds(struct bpf_reg_state *reg)
{
/* min signed is max(sign bit) | min(other bits) */
reg->smin_value = max_t(s64, reg->smin_value,
@@ -631,8 +1169,48 @@
reg->var_off.value | reg->var_off.mask);
}
+static void __update_reg_bounds(struct bpf_reg_state *reg)
+{
+ __update_reg32_bounds(reg);
+ __update_reg64_bounds(reg);
+}
+
/* Uses signed min/max values to inform unsigned, and vice-versa */
-static void __reg_deduce_bounds(struct bpf_reg_state *reg)
+static void __reg32_deduce_bounds(struct bpf_reg_state *reg)
+{
+ /* Learn sign from signed bounds.
+ * If we cannot cross the sign boundary, then signed and unsigned bounds
+ * are the same, so combine. This works even in the negative case, e.g.
+ * -3 s<= x s<= -1 implies 0xf...fd u<= x u<= 0xf...ff.
+ */
+ if (reg->s32_min_value >= 0 || reg->s32_max_value < 0) {
+ reg->s32_min_value = reg->u32_min_value =
+ max_t(u32, reg->s32_min_value, reg->u32_min_value);
+ reg->s32_max_value = reg->u32_max_value =
+ min_t(u32, reg->s32_max_value, reg->u32_max_value);
+ return;
+ }
+ /* Learn sign from unsigned bounds. Signed bounds cross the sign
+ * boundary, so we must be careful.
+ */
+ if ((s32)reg->u32_max_value >= 0) {
+ /* Positive. We can't learn anything from the smin, but smax
+ * is positive, hence safe.
+ */
+ reg->s32_min_value = reg->u32_min_value;
+ reg->s32_max_value = reg->u32_max_value =
+ min_t(u32, reg->s32_max_value, reg->u32_max_value);
+ } else if ((s32)reg->u32_min_value < 0) {
+ /* Negative. We can't learn anything from the smax, but smin
+ * is negative, hence safe.
+ */
+ reg->s32_min_value = reg->u32_min_value =
+ max_t(u32, reg->s32_min_value, reg->u32_min_value);
+ reg->s32_max_value = reg->u32_max_value;
+ }
+}
+
+static void __reg64_deduce_bounds(struct bpf_reg_state *reg)
{
/* Learn sign from signed bounds.
* If we cannot cross the sign boundary, then signed and unsigned bounds
@@ -666,25 +1244,112 @@
}
}
+static void __reg_deduce_bounds(struct bpf_reg_state *reg)
+{
+ __reg32_deduce_bounds(reg);
+ __reg64_deduce_bounds(reg);
+}
+
/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
- reg->var_off = tnum_intersect(reg->var_off,
- tnum_range(reg->umin_value,
- reg->umax_value));
+ struct tnum var64_off = tnum_intersect(reg->var_off,
+ tnum_range(reg->umin_value,
+ reg->umax_value));
+ struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off),
+ tnum_range(reg->u32_min_value,
+ reg->u32_max_value));
+
+ reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
}
-/* Reset the min/max bounds of a register */
-static void __mark_reg_unbounded(struct bpf_reg_state *reg)
+static void reg_bounds_sync(struct bpf_reg_state *reg)
{
- reg->smin_value = S64_MIN;
- reg->smax_value = S64_MAX;
- reg->umin_value = 0;
- reg->umax_value = U64_MAX;
+ /* We might have learned new bounds from the var_off. */
+ __update_reg_bounds(reg);
+ /* We might have learned something about the sign bit. */
+ __reg_deduce_bounds(reg);
+ /* We might have learned some bits from the bounds. */
+ __reg_bound_offset(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.
+ */
+ __update_reg_bounds(reg);
+}
+
+static bool __reg32_bound_s64(s32 a)
+{
+ return a >= 0 && a <= S32_MAX;
+}
+
+static void __reg_assign_32_into_64(struct bpf_reg_state *reg)
+{
+ reg->umin_value = reg->u32_min_value;
+ reg->umax_value = reg->u32_max_value;
+
+ /* Attempt to pull 32-bit signed bounds into 64-bit bounds but must
+ * be positive otherwise set to worse case bounds and refine later
+ * from tnum.
+ */
+ if (__reg32_bound_s64(reg->s32_min_value) &&
+ __reg32_bound_s64(reg->s32_max_value)) {
+ reg->smin_value = reg->s32_min_value;
+ reg->smax_value = reg->s32_max_value;
+ } else {
+ reg->smin_value = 0;
+ reg->smax_value = U32_MAX;
+ }
+}
+
+static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
+{
+ /* special case when 64-bit register has upper 32-bit register
+ * zeroed. Typically happens after zext or <<32, >>32 sequence
+ * allowing us to use 32-bit bounds directly,
+ */
+ if (tnum_equals_const(tnum_clear_subreg(reg->var_off), 0)) {
+ __reg_assign_32_into_64(reg);
+ } else {
+ /* Otherwise the best we can do is push lower 32bit known and
+ * unknown bits into register (var_off set from jmp logic)
+ * then learn as much as possible from the 64-bit tnum
+ * known and unknown bits. The previous smin/smax bounds are
+ * invalid here because of jmp32 compare so mark them unknown
+ * so they do not impact tnum bounds calculation.
+ */
+ __mark_reg64_unbounded(reg);
+ }
+ reg_bounds_sync(reg);
+}
+
+static bool __reg64_bound_s32(s64 a)
+{
+ return a >= S32_MIN && a <= S32_MAX;
+}
+
+static bool __reg64_bound_u32(u64 a)
+{
+ return a >= U32_MIN && a <= U32_MAX;
+}
+
+static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
+{
+ __mark_reg32_unbounded(reg);
+ if (__reg64_bound_s32(reg->smin_value) && __reg64_bound_s32(reg->smax_value)) {
+ reg->s32_min_value = (s32)reg->smin_value;
+ reg->s32_max_value = (s32)reg->smax_value;
+ }
+ if (__reg64_bound_u32(reg->umin_value) && __reg64_bound_u32(reg->umax_value)) {
+ reg->u32_min_value = (u32)reg->umin_value;
+ reg->u32_max_value = (u32)reg->umax_value;
+ }
+ reg_bounds_sync(reg);
}
/* Mark a register as having a completely unknown (scalar) value. */
-static void __mark_reg_unknown(struct bpf_reg_state *reg)
+static void __mark_reg_unknown(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
/*
* Clear type, id, off, and union(map_ptr, range) and
@@ -694,6 +1359,7 @@
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
+ reg->precise = !env->bpf_capable;
__mark_reg_unbounded(reg);
}
@@ -704,15 +1370,16 @@
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- __mark_reg_unknown(regs + regno);
+ __mark_reg_unknown(env, regs + regno);
}
-static void __mark_reg_not_init(struct bpf_reg_state *reg)
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
reg->type = NOT_INIT;
}
@@ -723,12 +1390,26 @@
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
}
+static void mark_btf_ld_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs, u32 regno,
+ enum bpf_reg_type reg_type, u32 btf_id)
+{
+ if (reg_type == SCALAR_VALUE) {
+ mark_reg_unknown(env, regs, regno);
+ return;
+ }
+ mark_reg_known_zero(env, regs, regno);
+ regs[regno].type = PTR_TO_BTF_ID;
+ regs[regno].btf_id = btf_id;
+}
+
+#define DEF_NOT_SUBREG (0)
static void init_reg_state(struct bpf_verifier_env *env,
struct bpf_func_state *state)
{
@@ -739,16 +1420,13 @@
mark_reg_not_init(env, regs, i);
regs[i].live = REG_LIVE_NONE;
regs[i].parent = NULL;
+ regs[i].subreg_def = DEF_NOT_SUBREG;
}
/* frame pointer */
regs[BPF_REG_FP].type = PTR_TO_STACK;
mark_reg_known_zero(env, regs, BPF_REG_FP);
regs[BPF_REG_FP].frameno = state->frameno;
-
- /* 1st arg to a function */
- regs[BPF_REG_1].type = PTR_TO_CTX;
- mark_reg_known_zero(env, regs, BPF_REG_1);
}
#define BPF_MAIN_FUNC (-1)
@@ -826,13 +1504,10 @@
continue;
if (insn[i].src_reg != BPF_PSEUDO_CALL)
continue;
- if (!env->allow_ptr_leaks) {
- verbose(env, "function calls to other bpf functions are allowed for root only\n");
+ if (!env->bpf_capable) {
+ verbose(env,
+ "function calls to other bpf functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
return -EPERM;
- }
- if (bpf_prog_is_dev_bound(env->prog->aux)) {
- verbose(env, "function calls in offloaded programs are not supported yet\n");
- return -EINVAL;
}
ret = add_subprog(env, i + insn[i].imm + 1);
if (ret < 0)
@@ -844,7 +1519,7 @@
*/
subprog[env->subprog_cnt].start = insn_cnt;
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2)
for (i = 0; i < env->subprog_cnt; i++)
verbose(env, "func#%d @%d\n", i, subprog[i].start);
@@ -854,7 +1529,14 @@
for (i = 0; i < insn_cnt; i++) {
u8 code = insn[i].code;
- if (BPF_CLASS(code) != BPF_JMP)
+ if (code == (BPF_JMP | BPF_CALL) &&
+ insn[i].imm == BPF_FUNC_tail_call &&
+ insn[i].src_reg != BPF_PSEUDO_CALL)
+ subprog[cur_subprog].has_tail_call = true;
+ if (BPF_CLASS(code) == BPF_LD &&
+ (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+ subprog[cur_subprog].has_ld_abs = true;
+ if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
goto next;
if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
goto next;
@@ -888,21 +1570,165 @@
*/
static int mark_reg_read(struct bpf_verifier_env *env,
const struct bpf_reg_state *state,
- struct bpf_reg_state *parent)
+ struct bpf_reg_state *parent, u8 flag)
{
bool writes = parent == state->parent; /* Observe write marks */
+ int cnt = 0;
while (parent) {
/* if read wasn't screened by an earlier write ... */
if (writes && state->live & REG_LIVE_WRITTEN)
break;
+ if (parent->live & REG_LIVE_DONE) {
+ verbose(env, "verifier BUG type %s var_off %lld off %d\n",
+ reg_type_str[parent->type],
+ parent->var_off.value, parent->off);
+ return -EFAULT;
+ }
+ /* The first condition is more likely to be true than the
+ * second, checked it first.
+ */
+ if ((parent->live & REG_LIVE_READ) == flag ||
+ parent->live & REG_LIVE_READ64)
+ /* The parentage chain never changes and
+ * this parent was already marked as LIVE_READ.
+ * There is no need to keep walking the chain again and
+ * keep re-marking all parents as LIVE_READ.
+ * This case happens when the same register is read
+ * multiple times without writes into it in-between.
+ * Also, if parent has the stronger REG_LIVE_READ64 set,
+ * then no need to set the weak REG_LIVE_READ32.
+ */
+ break;
/* ... then we depend on parent's value */
- parent->live |= REG_LIVE_READ;
+ parent->live |= flag;
+ /* REG_LIVE_READ64 overrides REG_LIVE_READ32. */
+ if (flag == REG_LIVE_READ64)
+ parent->live &= ~REG_LIVE_READ32;
state = parent;
parent = state->parent;
writes = true;
+ cnt++;
}
+
+ if (env->longest_mark_read_walk < cnt)
+ env->longest_mark_read_walk = cnt;
return 0;
+}
+
+/* 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.
+ */
+static bool is_reg64(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ u32 regno, struct bpf_reg_state *reg, enum reg_arg_type t)
+{
+ u8 code, class, op;
+
+ code = insn->code;
+ class = BPF_CLASS(code);
+ op = BPF_OP(code);
+ if (class == BPF_JMP) {
+ /* BPF_EXIT for "main" will reach here. Return TRUE
+ * conservatively.
+ */
+ if (op == BPF_EXIT)
+ return true;
+ if (op == BPF_CALL) {
+ /* BPF to BPF call will reach here because of marking
+ * caller saved clobber with DST_OP_NO_MARK for which we
+ * don't care the register def because they are anyway
+ * marked as NOT_INIT already.
+ */
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ return false;
+ /* Helper call will reach here because of arg type
+ * check, conservatively return TRUE.
+ */
+ if (t == SRC_OP)
+ return true;
+
+ return false;
+ }
+ }
+
+ if (class == BPF_ALU64 || class == BPF_JMP ||
+ /* BPF_END always use BPF_ALU class. */
+ (class == BPF_ALU && op == BPF_END && insn->imm == 64))
+ return true;
+
+ if (class == BPF_ALU || class == BPF_JMP32)
+ return false;
+
+ if (class == BPF_LDX) {
+ if (t != SRC_OP)
+ return BPF_SIZE(code) == BPF_DW;
+ /* LDX source must be ptr. */
+ return true;
+ }
+
+ if (class == BPF_STX) {
+ if (reg->type != SCALAR_VALUE)
+ return true;
+ return BPF_SIZE(code) == BPF_DW;
+ }
+
+ if (class == BPF_LD) {
+ u8 mode = BPF_MODE(code);
+
+ /* LD_IMM64 */
+ if (mode == BPF_IMM)
+ return true;
+
+ /* Both LD_IND and LD_ABS return 32-bit data. */
+ if (t != SRC_OP)
+ return false;
+
+ /* Implicit ctx ptr. */
+ if (regno == BPF_REG_6)
+ return true;
+
+ /* Explicit source could be any width. */
+ return true;
+ }
+
+ if (class == BPF_ST)
+ /* The only source register for BPF_ST is a ptr. */
+ return true;
+
+ /* Conservatively return true at default. */
+ return true;
+}
+
+/* Return TRUE if INSN doesn't have explicit value define. */
+static bool insn_no_def(struct bpf_insn *insn)
+{
+ u8 class = BPF_CLASS(insn->code);
+
+ return (class == BPF_JMP || class == BPF_JMP32 ||
+ class == BPF_STX || class == BPF_ST);
+}
+
+/* Return TRUE if INSN has defined any 32-bit value explicitly. */
+static bool insn_has_def32(struct bpf_verifier_env *env, struct bpf_insn *insn)
+{
+ if (insn_no_def(insn))
+ return false;
+
+ return !is_reg64(env, insn, insn->dst_reg, NULL, DST_OP);
+}
+
+static void mark_insn_zext(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
+{
+ s32 def_idx = reg->subreg_def;
+
+ if (def_idx == DEF_NOT_SUBREG)
+ return;
+
+ env->insn_aux_data[def_idx - 1].zext_dst = true;
+ /* The dst will be zero extended, so won't be sub-register anymore. */
+ reg->subreg_def = DEF_NOT_SUBREG;
}
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
@@ -910,34 +1736,631 @@
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *regs = state->regs;
+ struct bpf_insn *insn = env->prog->insnsi + env->insn_idx;
+ struct bpf_reg_state *reg, *regs = state->regs;
+ bool rw64;
if (regno >= MAX_BPF_REG) {
verbose(env, "R%d is invalid\n", regno);
return -EINVAL;
}
+ reg = ®s[regno];
+ rw64 = is_reg64(env, insn, regno, reg, t);
if (t == SRC_OP) {
/* check whether register used as source operand can be read */
- if (regs[regno].type == NOT_INIT) {
+ if (reg->type == NOT_INIT) {
verbose(env, "R%d !read_ok\n", regno);
return -EACCES;
}
/* We don't need to worry about FP liveness because it's read-only */
- if (regno != BPF_REG_FP)
- return mark_reg_read(env, ®s[regno],
- regs[regno].parent);
+ if (regno == BPF_REG_FP)
+ return 0;
+
+ if (rw64)
+ mark_insn_zext(env, reg);
+
+ return mark_reg_read(env, reg, reg->parent,
+ rw64 ? REG_LIVE_READ64 : REG_LIVE_READ32);
} else {
/* check whether register used as dest operand can be written to */
if (regno == BPF_REG_FP) {
verbose(env, "frame pointer is read only\n");
return -EACCES;
}
- regs[regno].live |= REG_LIVE_WRITTEN;
+ reg->live |= REG_LIVE_WRITTEN;
+ reg->subreg_def = rw64 ? DEF_NOT_SUBREG : env->insn_idx + 1;
if (t == DST_OP)
mark_reg_unknown(env, regs, regno);
}
return 0;
+}
+
+/* for any branch, call, exit record the history of jmps in the given state */
+static int push_jmp_history(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *cur)
+{
+ u32 cnt = cur->jmp_history_cnt;
+ struct bpf_idx_pair *p;
+
+ cnt++;
+ p = krealloc(cur->jmp_history, cnt * sizeof(*p), GFP_USER);
+ if (!p)
+ return -ENOMEM;
+ p[cnt - 1].idx = env->insn_idx;
+ p[cnt - 1].prev_idx = env->prev_insn_idx;
+ cur->jmp_history = p;
+ cur->jmp_history_cnt = cnt;
+ return 0;
+}
+
+/* Backtrack one insn at a time. If idx is not at the top of recorded
+ * history then previous instruction came from straight line execution.
+ */
+static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
+ u32 *history)
+{
+ u32 cnt = *history;
+
+ if (cnt && st->jmp_history[cnt - 1].idx == i) {
+ i = st->jmp_history[cnt - 1].prev_idx;
+ (*history)--;
+ } else {
+ i--;
+ }
+ return i;
+}
+
+/* For given verifier state backtrack_insn() is called from the last insn to
+ * the first insn. Its purpose is to compute a bitmask of registers and
+ * stack slots that needs precision in the parent verifier state.
+ */
+static int backtrack_insn(struct bpf_verifier_env *env, int idx,
+ u32 *reg_mask, u64 *stack_mask)
+{
+ const struct bpf_insn_cbs cbs = {
+ .cb_print = verbose,
+ .private_data = env,
+ };
+ struct bpf_insn *insn = env->prog->insnsi + idx;
+ u8 class = BPF_CLASS(insn->code);
+ u8 opcode = BPF_OP(insn->code);
+ u8 mode = BPF_MODE(insn->code);
+ u32 dreg = 1u << insn->dst_reg;
+ u32 sreg = 1u << insn->src_reg;
+ u32 spi;
+
+ if (insn->code == 0)
+ return 0;
+ if (env->log.level & BPF_LOG_LEVEL) {
+ verbose(env, "regs=%x stack=%llx before ", *reg_mask, *stack_mask);
+ verbose(env, "%d: ", idx);
+ print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
+ }
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ if (!(*reg_mask & dreg))
+ return 0;
+ if (opcode == BPF_MOV) {
+ if (BPF_SRC(insn->code) == BPF_X) {
+ /* dreg = sreg
+ * dreg needs precision after this insn
+ * sreg needs precision before this insn
+ */
+ *reg_mask &= ~dreg;
+ *reg_mask |= sreg;
+ } else {
+ /* dreg = K
+ * dreg needs precision after this insn.
+ * Corresponding register is already marked
+ * as precise=true in this verifier state.
+ * No further markings in parent are necessary
+ */
+ *reg_mask &= ~dreg;
+ }
+ } else {
+ if (BPF_SRC(insn->code) == BPF_X) {
+ /* dreg += sreg
+ * both dreg and sreg need precision
+ * before this insn
+ */
+ *reg_mask |= sreg;
+ } /* else dreg += K
+ * dreg still needs precision before this insn
+ */
+ }
+ } else if (class == BPF_LDX) {
+ if (!(*reg_mask & dreg))
+ return 0;
+ *reg_mask &= ~dreg;
+
+ /* scalars can only be spilled into stack w/o losing precision.
+ * Load from any other memory can be zero extended.
+ * The desire to keep that precision is already indicated
+ * by 'precise' mark in corresponding register of this state.
+ * No further tracking necessary.
+ */
+ if (insn->src_reg != BPF_REG_FP)
+ return 0;
+
+ /* dreg = *(u64 *)[fp - off] was a fill from the stack.
+ * that [fp - off] slot contains scalar that needs to be
+ * tracked with precision
+ */
+ spi = (-insn->off - 1) / BPF_REG_SIZE;
+ if (spi >= 64) {
+ verbose(env, "BUG spi %d\n", spi);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ *stack_mask |= 1ull << spi;
+ } else if (class == BPF_STX || class == BPF_ST) {
+ if (*reg_mask & dreg)
+ /* stx & st shouldn't be using _scalar_ dst_reg
+ * to access memory. It means backtracking
+ * encountered a case of pointer subtraction.
+ */
+ return -ENOTSUPP;
+ /* scalars can only be spilled into stack */
+ if (insn->dst_reg != BPF_REG_FP)
+ return 0;
+ spi = (-insn->off - 1) / BPF_REG_SIZE;
+ if (spi >= 64) {
+ verbose(env, "BUG spi %d\n", spi);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ if (!(*stack_mask & (1ull << spi)))
+ return 0;
+ *stack_mask &= ~(1ull << spi);
+ if (class == BPF_STX)
+ *reg_mask |= sreg;
+ } else if (class == BPF_JMP || class == BPF_JMP32) {
+ if (opcode == BPF_CALL) {
+ if (insn->src_reg == BPF_PSEUDO_CALL)
+ return -ENOTSUPP;
+ /* regular helper call sets R0 */
+ *reg_mask &= ~1;
+ if (*reg_mask & 0x3f) {
+ /* if backtracing was looking for registers R1-R5
+ * they should have been found already.
+ */
+ verbose(env, "BUG regs %x\n", *reg_mask);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ } else if (opcode == BPF_EXIT) {
+ return -ENOTSUPP;
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ if (!(*reg_mask & (dreg | sreg)))
+ return 0;
+ /* dreg <cond> sreg
+ * Both dreg and sreg need precision before
+ * this insn. If only sreg was marked precise
+ * before it would be equally necessary to
+ * propagate it to dreg.
+ */
+ *reg_mask |= (sreg | dreg);
+ /* else dreg <cond> K
+ * Only dreg still needs precision before
+ * this insn, so for the K-based conditional
+ * there is nothing new to be marked.
+ */
+ }
+ } else if (class == BPF_LD) {
+ if (!(*reg_mask & dreg))
+ return 0;
+ *reg_mask &= ~dreg;
+ /* It's ld_imm64 or ld_abs or ld_ind.
+ * For ld_imm64 no further tracking of precision
+ * into parent is necessary
+ */
+ if (mode == BPF_IND || mode == BPF_ABS)
+ /* to be analyzed */
+ return -ENOTSUPP;
+ }
+ return 0;
+}
+
+/* the scalar precision tracking algorithm:
+ * . at the start all registers have precise=false.
+ * . scalar ranges are tracked as normal through alu and jmp insns.
+ * . once precise value of the scalar register is used in:
+ * . ptr + scalar alu
+ * . if (scalar cond K|scalar)
+ * . helper_call(.., scalar, ...) where ARG_CONST is expected
+ * backtrack through the verifier states and mark all registers and
+ * stack slots with spilled constants that these scalar regisers
+ * should be precise.
+ * . during state pruning two registers (or spilled stack slots)
+ * are equivalent if both are not precise.
+ *
+ * Note the verifier cannot simply walk register parentage chain,
+ * since many different registers and stack slots could have been
+ * used to compute single precise scalar.
+ *
+ * The approach of starting with precise=true for all registers and then
+ * backtrack to mark a register as not precise when the verifier detects
+ * that program doesn't care about specific value (e.g., when helper
+ * takes register as ARG_ANYTHING parameter) is not safe.
+ *
+ * It's ok to walk single parentage chain of the verifier states.
+ * It's possible that this backtracking will go all the way till 1st insn.
+ * All other branches will be explored for needing precision later.
+ *
+ * The backtracking needs to deal with cases like:
+ * R8=map_value(id=0,off=0,ks=4,vs=1952,imm=0) R9_w=map_value(id=0,off=40,ks=4,vs=1952,imm=0)
+ * r9 -= r8
+ * r5 = r9
+ * if r5 > 0x79f goto pc+7
+ * R5_w=inv(id=0,umax_value=1951,var_off=(0x0; 0x7ff))
+ * r5 += 1
+ * ...
+ * call bpf_perf_event_output#25
+ * where .arg5_type = ARG_CONST_SIZE_OR_ZERO
+ *
+ * and this case:
+ * r6 = 1
+ * call foo // uses callee's r6 inside to compute r0
+ * r0 += r6
+ * if r0 == 0 goto
+ *
+ * to track above reg_mask/stack_mask needs to be independent for each frame.
+ *
+ * Also if parent's curframe > frame where backtracking started,
+ * the verifier need to mark registers in both frames, otherwise callees
+ * may incorrectly prune callers. This is similar to
+ * commit 7640ead93924 ("bpf: verifier: make sure callees don't prune with caller differences")
+ *
+ * For now backtracking falls back into conservative marking.
+ */
+static void mark_all_scalars_precise(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st)
+{
+ struct bpf_func_state *func;
+ struct bpf_reg_state *reg;
+ int i, j;
+
+ /* big hammer: mark all scalars precise in this path.
+ * pop_stack may still get !precise scalars.
+ * We also skip current state and go straight to first parent state,
+ * because precision markings in current non-checkpointed state are
+ * not needed. See why in the comment in __mark_chain_precision below.
+ */
+ for (st = st->parent; st; st = st->parent) {
+ for (i = 0; i <= st->curframe; i++) {
+ func = st->frame[i];
+ for (j = 0; j < BPF_REG_FP; j++) {
+ reg = &func->regs[j];
+ if (reg->type != SCALAR_VALUE)
+ continue;
+ reg->precise = true;
+ }
+ for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
+ if (!is_spilled_reg(&func->stack[j]))
+ continue;
+ reg = &func->stack[j].spilled_ptr;
+ if (reg->type != SCALAR_VALUE)
+ continue;
+ reg->precise = true;
+ }
+ }
+ }
+}
+
+static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+ struct bpf_func_state *func;
+ struct bpf_reg_state *reg;
+ int i, j;
+
+ for (i = 0; i <= st->curframe; i++) {
+ func = st->frame[i];
+ for (j = 0; j < BPF_REG_FP; j++) {
+ reg = &func->regs[j];
+ if (reg->type != SCALAR_VALUE)
+ continue;
+ reg->precise = false;
+ }
+ for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
+ if (!is_spilled_reg(&func->stack[j]))
+ continue;
+ reg = &func->stack[j].spilled_ptr;
+ if (reg->type != SCALAR_VALUE)
+ continue;
+ reg->precise = false;
+ }
+ }
+}
+
+/*
+ * __mark_chain_precision() backtracks BPF program instruction sequence and
+ * chain of verifier states making sure that register *regno* (if regno >= 0)
+ * and/or stack slot *spi* (if spi >= 0) are marked as precisely tracked
+ * SCALARS, as well as any other registers and slots that contribute to
+ * a tracked state of given registers/stack slots, depending on specific BPF
+ * assembly instructions (see backtrack_insns() for exact instruction handling
+ * logic). This backtracking relies on recorded jmp_history and is able to
+ * traverse entire chain of parent states. This process ends only when all the
+ * necessary registers/slots and their transitive dependencies are marked as
+ * precise.
+ *
+ * One important and subtle aspect is that precise marks *do not matter* in
+ * the currently verified state (current state). It is important to understand
+ * why this is the case.
+ *
+ * First, note that current state is the state that is not yet "checkpointed",
+ * i.e., it is not yet put into env->explored_states, and it has no children
+ * states as well. It's ephemeral, and can end up either a) being discarded if
+ * compatible explored state is found at some point or BPF_EXIT instruction is
+ * reached or b) checkpointed and put into env->explored_states, branching out
+ * into one or more children states.
+ *
+ * In the former case, precise markings in current state are completely
+ * ignored by state comparison code (see regsafe() for details). Only
+ * checkpointed ("old") state precise markings are important, and if old
+ * state's register/slot is precise, regsafe() assumes current state's
+ * register/slot as precise and checks value ranges exactly and precisely. If
+ * states turn out to be compatible, current state's necessary precise
+ * markings and any required parent states' precise markings are enforced
+ * after the fact with propagate_precision() logic, after the fact. But it's
+ * important to realize that in this case, even after marking current state
+ * registers/slots as precise, we immediately discard current state. So what
+ * actually matters is any of the precise markings propagated into current
+ * state's parent states, which are always checkpointed (due to b) case above).
+ * As such, for scenario a) it doesn't matter if current state has precise
+ * markings set or not.
+ *
+ * Now, for the scenario b), checkpointing and forking into child(ren)
+ * state(s). Note that before current state gets to checkpointing step, any
+ * processed instruction always assumes precise SCALAR register/slot
+ * knowledge: if precise value or range is useful to prune jump branch, BPF
+ * verifier takes this opportunity enthusiastically. Similarly, when
+ * register's value is used to calculate offset or memory address, exact
+ * knowledge of SCALAR range is assumed, checked, and enforced. So, similar to
+ * what we mentioned above about state comparison ignoring precise markings
+ * during state comparison, BPF verifier ignores and also assumes precise
+ * markings *at will* during instruction verification process. But as verifier
+ * assumes precision, it also propagates any precision dependencies across
+ * parent states, which are not yet finalized, so can be further restricted
+ * based on new knowledge gained from restrictions enforced by their children
+ * states. This is so that once those parent states are finalized, i.e., when
+ * they have no more active children state, state comparison logic in
+ * is_state_visited() would enforce strict and precise SCALAR ranges, if
+ * required for correctness.
+ *
+ * To build a bit more intuition, note also that once a state is checkpointed,
+ * the path we took to get to that state is not important. This is crucial
+ * property for state pruning. When state is checkpointed and finalized at
+ * some instruction index, it can be correctly and safely used to "short
+ * circuit" any *compatible* state that reaches exactly the same instruction
+ * index. I.e., if we jumped to that instruction from a completely different
+ * code path than original finalized state was derived from, it doesn't
+ * matter, current state can be discarded because from that instruction
+ * forward having a compatible state will ensure we will safely reach the
+ * exit. States describe preconditions for further exploration, but completely
+ * forget the history of how we got here.
+ *
+ * This also means that even if we needed precise SCALAR range to get to
+ * finalized state, but from that point forward *that same* SCALAR register is
+ * never used in a precise context (i.e., it's precise value is not needed for
+ * correctness), it's correct and safe to mark such register as "imprecise"
+ * (i.e., precise marking set to false). This is what we rely on when we do
+ * not set precise marking in current state. If no child state requires
+ * precision for any given SCALAR register, it's safe to dictate that it can
+ * be imprecise. If any child state does require this register to be precise,
+ * we'll mark it precise later retroactively during precise markings
+ * propagation from child state to parent states.
+ *
+ * Skipping precise marking setting in current state is a mild version of
+ * relying on the above observation. But we can utilize this property even
+ * more aggressively by proactively forgetting any precise marking in the
+ * current state (which we inherited from the parent state), right before we
+ * checkpoint it and branch off into new child state. This is done by
+ * mark_all_scalars_imprecise() to hopefully get more permissive and generic
+ * finalized states which help in short circuiting more future states.
+ */
+static int __mark_chain_precision(struct bpf_verifier_env *env, int frame, int regno,
+ int spi)
+{
+ struct bpf_verifier_state *st = env->cur_state;
+ int first_idx = st->first_insn_idx;
+ int last_idx = env->insn_idx;
+ struct bpf_func_state *func;
+ struct bpf_reg_state *reg;
+ u32 reg_mask = regno >= 0 ? 1u << regno : 0;
+ u64 stack_mask = spi >= 0 ? 1ull << spi : 0;
+ bool skip_first = true;
+ bool new_marks = false;
+ int i, err;
+
+ if (!env->bpf_capable)
+ return 0;
+
+ /* Do sanity checks against current state of register and/or stack
+ * slot, but don't set precise flag in current state, as precision
+ * tracking in the current state is unnecessary.
+ */
+ func = st->frame[frame];
+ if (regno >= 0) {
+ reg = &func->regs[regno];
+ if (reg->type != SCALAR_VALUE) {
+ WARN_ONCE(1, "backtracing misuse");
+ return -EFAULT;
+ }
+ new_marks = true;
+ }
+
+ while (spi >= 0) {
+ if (!is_spilled_reg(&func->stack[spi])) {
+ stack_mask = 0;
+ break;
+ }
+ reg = &func->stack[spi].spilled_ptr;
+ if (reg->type != SCALAR_VALUE) {
+ stack_mask = 0;
+ break;
+ }
+ new_marks = true;
+ break;
+ }
+
+ if (!new_marks)
+ return 0;
+ if (!reg_mask && !stack_mask)
+ return 0;
+
+ for (;;) {
+ DECLARE_BITMAP(mask, 64);
+ u32 history = st->jmp_history_cnt;
+
+ if (env->log.level & BPF_LOG_LEVEL)
+ verbose(env, "last_idx %d first_idx %d\n", last_idx, first_idx);
+
+ if (last_idx < 0) {
+ /* we are at the entry into subprog, which
+ * is expected for global funcs, but only if
+ * requested precise registers are R1-R5
+ * (which are global func's input arguments)
+ */
+ if (st->curframe == 0 &&
+ st->frame[0]->subprogno > 0 &&
+ st->frame[0]->callsite == BPF_MAIN_FUNC &&
+ stack_mask == 0 && (reg_mask & ~0x3e) == 0) {
+ bitmap_from_u64(mask, reg_mask);
+ for_each_set_bit(i, mask, 32) {
+ reg = &st->frame[0]->regs[i];
+ if (reg->type != SCALAR_VALUE) {
+ reg_mask &= ~(1u << i);
+ continue;
+ }
+ reg->precise = true;
+ }
+ return 0;
+ }
+
+ verbose(env, "BUG backtracing func entry subprog %d reg_mask %x stack_mask %llx\n",
+ st->frame[0]->subprogno, reg_mask, stack_mask);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+
+ for (i = last_idx;;) {
+ if (skip_first) {
+ err = 0;
+ skip_first = false;
+ } else {
+ err = backtrack_insn(env, i, ®_mask, &stack_mask);
+ }
+ if (err == -ENOTSUPP) {
+ mark_all_scalars_precise(env, st);
+ return 0;
+ } else if (err) {
+ return err;
+ }
+ if (!reg_mask && !stack_mask)
+ /* Found assignment(s) into tracked register in this state.
+ * Since this state is already marked, just return.
+ * Nothing to be tracked further in the parent state.
+ */
+ return 0;
+ if (i == first_idx)
+ break;
+ i = get_prev_insn_idx(st, i, &history);
+ if (i >= env->prog->len) {
+ /* This can happen if backtracking reached insn 0
+ * and there are still reg_mask or stack_mask
+ * to backtrack.
+ * It means the backtracking missed the spot where
+ * particular register was initialized with a constant.
+ */
+ verbose(env, "BUG backtracking idx %d\n", i);
+ WARN_ONCE(1, "verifier backtracking bug");
+ return -EFAULT;
+ }
+ }
+ st = st->parent;
+ if (!st)
+ break;
+
+ new_marks = false;
+ func = st->frame[frame];
+ bitmap_from_u64(mask, reg_mask);
+ for_each_set_bit(i, mask, 32) {
+ reg = &func->regs[i];
+ if (reg->type != SCALAR_VALUE) {
+ reg_mask &= ~(1u << i);
+ continue;
+ }
+ if (!reg->precise)
+ new_marks = true;
+ reg->precise = true;
+ }
+
+ bitmap_from_u64(mask, stack_mask);
+ for_each_set_bit(i, mask, 64) {
+ if (i >= func->allocated_stack / BPF_REG_SIZE) {
+ /* the sequence of instructions:
+ * 2: (bf) r3 = r10
+ * 3: (7b) *(u64 *)(r3 -8) = r0
+ * 4: (79) r4 = *(u64 *)(r10 -8)
+ * doesn't contain jmps. It's backtracked
+ * as a single block.
+ * During backtracking insn 3 is not recognized as
+ * stack access, so at the end of backtracking
+ * stack slot fp-8 is still marked in stack_mask.
+ * However the parent state may not have accessed
+ * fp-8 and it's "unallocated" stack space.
+ * In such case fallback to conservative.
+ */
+ mark_all_scalars_precise(env, st);
+ return 0;
+ }
+
+ if (!is_spilled_reg(&func->stack[i])) {
+ stack_mask &= ~(1ull << i);
+ continue;
+ }
+ reg = &func->stack[i].spilled_ptr;
+ if (reg->type != SCALAR_VALUE) {
+ stack_mask &= ~(1ull << i);
+ continue;
+ }
+ if (!reg->precise)
+ new_marks = true;
+ reg->precise = true;
+ }
+ if (env->log.level & BPF_LOG_LEVEL) {
+ print_verifier_state(env, func);
+ verbose(env, "parent %s regs=%x stack=%llx marks\n",
+ new_marks ? "didn't have" : "already had",
+ reg_mask, stack_mask);
+ }
+
+ if (!reg_mask && !stack_mask)
+ break;
+ if (!new_marks)
+ break;
+
+ last_idx = st->last_insn_idx;
+ first_idx = st->first_insn_idx;
+ }
+ return 0;
+}
+
+static int mark_chain_precision(struct bpf_verifier_env *env, int regno)
+{
+ return __mark_chain_precision(env, env->cur_state->curframe, regno, -1);
+}
+
+static int mark_chain_precision_frame(struct bpf_verifier_env *env, int frame, int regno)
+{
+ return __mark_chain_precision(env, frame, regno, -1);
+}
+
+static int mark_chain_precision_stack_frame(struct bpf_verifier_env *env, int frame, int spi)
+{
+ return __mark_chain_precision(env, frame, -1, spi);
}
static bool is_spillable_regtype(enum bpf_reg_type type)
@@ -950,7 +2373,24 @@
case PTR_TO_PACKET:
case PTR_TO_PACKET_META:
case PTR_TO_PACKET_END:
+ case PTR_TO_FLOW_KEYS:
case CONST_PTR_TO_MAP:
+ case PTR_TO_SOCKET:
+ case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
+ case PTR_TO_XDP_SOCK:
+ case PTR_TO_BTF_ID:
+ case PTR_TO_BTF_ID_OR_NULL:
+ case PTR_TO_RDONLY_BUF:
+ case PTR_TO_RDONLY_BUF_OR_NULL:
+ case PTR_TO_RDWR_BUF:
+ case PTR_TO_RDWR_BUF_OR_NULL:
+ case PTR_TO_PERCPU_BTF_ID:
+ case PTR_TO_MEM:
+ case PTR_TO_MEM_OR_NULL:
return true;
default:
return false;
@@ -968,31 +2408,80 @@
return reg->type == SCALAR_VALUE && tnum_is_const(reg->var_off);
}
+static bool __is_scalar_unbounded(struct bpf_reg_state *reg)
+{
+ return tnum_is_unknown(reg->var_off) &&
+ reg->smin_value == S64_MIN && reg->smax_value == S64_MAX &&
+ reg->umin_value == 0 && reg->umax_value == U64_MAX &&
+ reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX &&
+ reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX;
+}
+
+static bool register_is_bounded(struct bpf_reg_state *reg)
+{
+ return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg);
+}
+
+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;
+}
+
+/* Copy src state preserving dst->parent and dst->live fields */
+static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src)
+{
+ struct bpf_reg_state *parent = dst->parent;
+ enum bpf_reg_liveness live = dst->live;
+
+ *dst = *src;
+ dst->parent = parent;
+ dst->live = live;
+}
+
static void save_register_state(struct bpf_func_state *state,
- int spi, struct bpf_reg_state *reg)
+ int spi, struct bpf_reg_state *reg,
+ int size)
{
int i;
- state->stack[spi].spilled_ptr = *reg;
- state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+ copy_register_state(&state->stack[spi].spilled_ptr, reg);
+ if (size == BPF_REG_SIZE)
+ state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
- for (i = 0; i < BPF_REG_SIZE; i++)
- state->stack[spi].slot_type[i] = STACK_SPILL;
+ for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--)
+ state->stack[spi].slot_type[i - 1] = STACK_SPILL;
+
+ /* size < 8 bytes spill */
+ for (; i; i--)
+ scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
}
-/* check_stack_read/write functions track spill/fill of registers,
+static bool is_bpf_st_mem(struct bpf_insn *insn)
+{
+ return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM;
+}
+
+/* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
* stack boundary and alignment are checked in check_mem_access()
*/
-static int check_stack_write(struct bpf_verifier_env *env,
- struct bpf_func_state *state, /* func where register points to */
- int off, int size, int value_regno, int insn_idx)
+static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
+ /* stack frame we're writing to */
+ struct bpf_func_state *state,
+ int off, int size, int value_regno,
+ int insn_idx)
{
struct bpf_func_state *cur; /* state of the current function */
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
+ struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
struct bpf_reg_state *reg = NULL;
+ u32 dst_reg = insn->dst_reg;
err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
- true);
+ state->acquired_refs, true);
if (err)
return err;
/* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
@@ -1008,11 +2497,13 @@
cur = env->cur_state->frame[env->cur_state->curframe];
if (value_regno >= 0)
reg = &cur->regs[value_regno];
- if (!env->allow_ptr_leaks) {
+ if (!env->bypass_spec_v4) {
bool sanitize = reg && is_spillable_regtype(reg->type);
for (i = 0; i < size; i++) {
- if (state->stack[spi].slot_type[i] == STACK_INVALID) {
+ u8 type = state->stack[spi].slot_type[i];
+
+ if (type != STACK_MISC && type != STACK_ZERO) {
sanitize = true;
break;
}
@@ -1022,12 +2513,34 @@
env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
}
- if (reg && size == BPF_REG_SIZE && register_is_const(reg) &&
- !register_is_null(reg) && env->allow_ptr_leaks) {
- save_register_state(state, spi, reg);
+ if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
+ !register_is_null(reg) && env->bpf_capable) {
+ if (dst_reg != BPF_REG_FP) {
+ /* The backtracking logic can only recognize explicit
+ * stack slot address like [fp - 8]. Other spill of
+ * scalar via different register has to be conervative.
+ * Backtrack from here and mark all registers as precise
+ * that contributed into 'reg' being a constant.
+ */
+ err = mark_chain_precision(env, value_regno);
+ if (err)
+ return err;
+ }
+ save_register_state(state, spi, reg, size);
+ /* Break the relation on a narrowing spill. */
+ if (fls64(reg->umax_value) > BITS_PER_BYTE * size)
+ state->stack[spi].spilled_ptr.id = 0;
+ } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) &&
+ insn->imm != 0 && env->bpf_capable) {
+ struct bpf_reg_state fake_reg = {};
+
+ __mark_reg_known(&fake_reg, (u32)insn->imm);
+ fake_reg.type = SCALAR_VALUE;
+ save_register_state(state, spi, &fake_reg, size);
} else if (reg && is_spillable_regtype(reg->type)) {
/* register containing pointer is being spilled into stack */
if (size != BPF_REG_SIZE) {
+ verbose_linfo(env, insn_idx, "; ");
verbose(env, "invalid size of register spill\n");
return -EACCES;
}
@@ -1035,16 +2548,16 @@
verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
return -EINVAL;
}
- save_register_state(state, spi, reg);
+ save_register_state(state, spi, reg, size);
} else {
u8 type = STACK_MISC;
/* regular write of data into stack destroys any spilled ptr */
state->stack[spi].spilled_ptr.type = NOT_INIT;
/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
- if (state->stack[spi].slot_type[0] == STACK_SPILL)
+ if (is_spilled_reg(&state->stack[spi]))
for (i = 0; i < BPF_REG_SIZE; i++)
- state->stack[spi].slot_type[i] = STACK_MISC;
+ scrub_spilled_slot(&state->stack[spi].slot_type[i]);
/* only mark the slot as written if all 8 bytes were written
* otherwise read propagation may incorrectly stop too soon
@@ -1058,8 +2571,14 @@
state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
/* when we zero initialize stack slots mark them as such */
- if (reg && register_is_null(reg))
+ if ((reg && register_is_null(reg)) ||
+ (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) {
+ /* backtracking doesn't work for STACK_ZERO yet. */
+ err = mark_chain_precision(env, value_regno);
+ if (err)
+ return err;
type = STACK_ZERO;
+ }
/* Mark slots affected by this stack write. */
for (i = 0; i < size; i++)
@@ -1069,140 +2588,477 @@
return 0;
}
-static int check_stack_read(struct bpf_verifier_env *env,
- struct bpf_func_state *reg_state /* func where register points to */,
- int off, int size, int value_regno)
+/* Write the stack: 'stack[ptr_regno + off] = value_regno'. 'ptr_regno' is
+ * known to contain a variable offset.
+ * This function checks whether the write is permitted and conservatively
+ * tracks the effects of the write, considering that each stack slot in the
+ * dynamic range is potentially written to.
+ *
+ * 'off' includes 'regno->off'.
+ * 'value_regno' can be -1, meaning that an unknown value is being written to
+ * the stack.
+ *
+ * Spilled pointers in range are not marked as written because we don't know
+ * what's going to be actually written. This means that read propagation for
+ * future reads cannot be terminated by this write.
+ *
+ * For privileged programs, uninitialized stack slots are considered
+ * initialized by this write (even though we don't know exactly what offsets
+ * are going to be written to). The idea is that we don't want the verifier to
+ * reject future reads that access slots written to through variable offsets.
+ */
+static int check_stack_write_var_off(struct bpf_verifier_env *env,
+ /* func where register points to */
+ struct bpf_func_state *state,
+ int ptr_regno, int off, int size,
+ int value_regno, int insn_idx)
+{
+ struct bpf_func_state *cur; /* state of the current function */
+ int min_off, max_off;
+ int i, err;
+ struct bpf_reg_state *ptr_reg = NULL, *value_reg = NULL;
+ bool writing_zero = false;
+ /* set if the fact that we're writing a zero is used to let any
+ * stack slots remain STACK_ZERO
+ */
+ bool zero_used = false;
+
+ cur = env->cur_state->frame[env->cur_state->curframe];
+ ptr_reg = &cur->regs[ptr_regno];
+ min_off = ptr_reg->smin_value + off;
+ max_off = ptr_reg->smax_value + off + size;
+ if (value_regno >= 0)
+ value_reg = &cur->regs[value_regno];
+ if (value_reg && register_is_null(value_reg))
+ writing_zero = true;
+
+ err = realloc_func_state(state, round_up(-min_off, BPF_REG_SIZE),
+ state->acquired_refs, true);
+ if (err)
+ return err;
+
+
+ /* Variable offset writes destroy any spilled pointers in range. */
+ for (i = min_off; i < max_off; i++) {
+ u8 new_type, *stype;
+ int slot, spi;
+
+ slot = -i - 1;
+ spi = slot / BPF_REG_SIZE;
+ stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+
+ if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) {
+ /* Reject the write if range we may write to has not
+ * been initialized beforehand. If we didn't reject
+ * here, the ptr status would be erased below (even
+ * though not all slots are actually overwritten),
+ * possibly opening the door to leaks.
+ *
+ * We do however catch STACK_INVALID case below, and
+ * only allow reading possibly uninitialized memory
+ * later for CAP_PERFMON, as the write may not happen to
+ * that slot.
+ */
+ verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d",
+ insn_idx, i);
+ return -EINVAL;
+ }
+
+ /* Erase all spilled pointers. */
+ state->stack[spi].spilled_ptr.type = NOT_INIT;
+
+ /* Update the slot type. */
+ new_type = STACK_MISC;
+ if (writing_zero && *stype == STACK_ZERO) {
+ new_type = STACK_ZERO;
+ zero_used = true;
+ }
+ /* If the slot is STACK_INVALID, we check whether it's OK to
+ * pretend that it will be initialized by this write. The slot
+ * might not actually be written to, and so if we mark it as
+ * initialized future reads might leak uninitialized memory.
+ * For privileged programs, we will accept such reads to slots
+ * that may or may not be written because, if we're reject
+ * them, the error would be too confusing.
+ */
+ if (*stype == STACK_INVALID && !env->allow_uninit_stack) {
+ verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d",
+ insn_idx, i);
+ return -EINVAL;
+ }
+ *stype = new_type;
+ }
+ if (zero_used) {
+ /* backtracking doesn't work for STACK_ZERO yet. */
+ err = mark_chain_precision(env, value_regno);
+ if (err)
+ return err;
+ }
+ return 0;
+}
+
+/* When register 'dst_regno' is assigned some values from stack[min_off,
+ * max_off), we set the register's type according to the types of the
+ * respective stack slots. If all the stack values are known to be zeros, then
+ * so is the destination reg. Otherwise, the register is considered to be
+ * SCALAR. This function does not deal with register filling; the caller must
+ * ensure that all spilled registers in the stack range have been marked as
+ * read.
+ */
+static void mark_reg_stack_read(struct bpf_verifier_env *env,
+ /* func where src register points to */
+ struct bpf_func_state *ptr_state,
+ int min_off, int max_off, int dst_regno)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ int i, slot, spi;
+ u8 *stype;
+ int zeros = 0;
+
+ for (i = min_off; i < max_off; i++) {
+ slot = -i - 1;
+ spi = slot / BPF_REG_SIZE;
+ stype = ptr_state->stack[spi].slot_type;
+ if (stype[slot % BPF_REG_SIZE] != STACK_ZERO)
+ break;
+ zeros++;
+ }
+ if (zeros == max_off - min_off) {
+ /* any access_size read into register is zero extended,
+ * so the whole register == const_zero
+ */
+ __mark_reg_const_zero(&state->regs[dst_regno]);
+ /* backtracking doesn't support STACK_ZERO yet,
+ * so mark it precise here, so that later
+ * backtracking can stop here.
+ * Backtracking may not need this if this register
+ * doesn't participate in pointer adjustment.
+ * Forward propagation of precise flag is not
+ * necessary either. This mark is only to stop
+ * backtracking. Any register that contributed
+ * to const 0 was marked precise before spill.
+ */
+ state->regs[dst_regno].precise = true;
+ } else {
+ /* have read misc data from the stack */
+ mark_reg_unknown(env, state->regs, dst_regno);
+ }
+ state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
+}
+
+/* Read the stack at 'off' and put the results into the register indicated by
+ * 'dst_regno'. It handles reg filling if the addressed stack slot is a
+ * spilled reg.
+ *
+ * 'dst_regno' can be -1, meaning that the read value is not going to a
+ * register.
+ *
+ * The access is assumed to be within the current stack bounds.
+ */
+static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
+ /* func where src register points to */
+ struct bpf_func_state *reg_state,
+ int off, int size, int dst_regno)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
struct bpf_reg_state *reg;
- u8 *stype;
+ u8 *stype, type;
- if (reg_state->allocated_stack <= slot) {
- verbose(env, "invalid read from stack off %d+0 size %d\n",
- off, size);
- return -EACCES;
- }
stype = reg_state->stack[spi].slot_type;
reg = ®_state->stack[spi].spilled_ptr;
- if (stype[0] == STACK_SPILL) {
- if (size != BPF_REG_SIZE) {
+ if (is_spilled_reg(®_state->stack[spi])) {
+ u8 spill_size = 1;
+
+ for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--)
+ spill_size++;
+
+ if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) {
if (reg->type != SCALAR_VALUE) {
+ verbose_linfo(env, env->insn_idx, "; ");
verbose(env, "invalid size of register fill\n");
return -EACCES;
}
- if (value_regno >= 0) {
- mark_reg_unknown(env, state->regs, value_regno);
- state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+
+ mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+ if (dst_regno < 0)
+ return 0;
+
+ if (!(off % BPF_REG_SIZE) && size == spill_size) {
+ /* The earlier check_reg_arg() has decided the
+ * subreg_def for this insn. Save it first.
+ */
+ s32 subreg_def = state->regs[dst_regno].subreg_def;
+
+ copy_register_state(&state->regs[dst_regno], reg);
+ state->regs[dst_regno].subreg_def = subreg_def;
+ } else {
+ for (i = 0; i < size; i++) {
+ type = stype[(slot - i) % BPF_REG_SIZE];
+ if (type == STACK_SPILL)
+ continue;
+ if (type == STACK_MISC)
+ continue;
+ verbose(env, "invalid read from stack off %d+%d size %d\n",
+ off, i, size);
+ return -EACCES;
+ }
+ mark_reg_unknown(env, state->regs, dst_regno);
}
- mark_reg_read(env, reg, reg->parent);
+ state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
return 0;
}
- for (i = 1; i < BPF_REG_SIZE; i++) {
- if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
- verbose(env, "corrupted spill memory\n");
- return -EACCES;
- }
- }
- if (value_regno >= 0) {
+ if (dst_regno >= 0) {
/* restore register state from stack */
- state->regs[value_regno] = *reg;
+ copy_register_state(&state->regs[dst_regno], reg);
/* mark reg as written since spilled pointer state likely
* has its liveness marks cleared by is_state_visited()
* which resets stack/reg liveness for state transitions
*/
- state->regs[value_regno].live |= REG_LIVE_WRITTEN;
+ state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
+ } else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
+ /* If dst_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);
+ mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
} else {
- int zeros = 0;
-
for (i = 0; i < size; i++) {
- if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
+ type = stype[(slot - i) % BPF_REG_SIZE];
+ if (type == STACK_MISC)
continue;
- if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
- zeros++;
+ if (type == STACK_ZERO)
continue;
- }
verbose(env, "invalid read from stack off %d+%d size %d\n",
off, i, size);
return -EACCES;
}
- mark_reg_read(env, reg, reg->parent);
- if (value_regno >= 0) {
- if (zeros == size) {
- /* any size read into register is zero extended,
- * so the whole register == const_zero
- */
- __mark_reg_const_zero(&state->regs[value_regno]);
- } else {
- /* have read misc data from the stack */
- mark_reg_unknown(env, state->regs, value_regno);
- }
- state->regs[value_regno].live |= REG_LIVE_WRITTEN;
- }
+ mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+ if (dst_regno >= 0)
+ mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
}
return 0;
}
-static int check_stack_access(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg,
- int off, int size)
+enum stack_access_src {
+ ACCESS_DIRECT = 1, /* the access is performed by an instruction */
+ ACCESS_HELPER = 2, /* the access is performed by a helper */
+};
+
+static int check_stack_range_initialized(struct bpf_verifier_env *env,
+ int regno, int off, int access_size,
+ bool zero_size_allowed,
+ enum stack_access_src type,
+ struct bpf_call_arg_meta *meta);
+
+static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
{
- /* Stack accesses must be at a fixed offset, so that we
- * can determine what type of data were returned. See
- * check_stack_read().
+ return cur_regs(env) + regno;
+}
+
+/* Read the stack at 'ptr_regno + off' and put the result into the register
+ * 'dst_regno'.
+ * 'off' includes the pointer register's fixed offset(i.e. 'ptr_regno.off'),
+ * but not its variable offset.
+ * 'size' is assumed to be <= reg size and the access is assumed to be aligned.
+ *
+ * As opposed to check_stack_read_fixed_off, this function doesn't deal with
+ * filling registers (i.e. reads of spilled register cannot be detected when
+ * the offset is not fixed). We conservatively mark 'dst_regno' as containing
+ * SCALAR_VALUE. That's why we assert that the 'ptr_regno' has a variable
+ * offset; for a fixed offset check_stack_read_fixed_off should be used
+ * instead.
+ */
+static int check_stack_read_var_off(struct bpf_verifier_env *env,
+ int ptr_regno, int off, int size, int dst_regno)
+{
+ /* The state of the source register. */
+ struct bpf_reg_state *reg = reg_state(env, ptr_regno);
+ struct bpf_func_state *ptr_state = func(env, reg);
+ int err;
+ int min_off, max_off;
+
+ /* Note that we pass a NULL meta, so raw access will not be permitted.
*/
- if (!tnum_is_const(reg->var_off)) {
+ err = check_stack_range_initialized(env, ptr_regno, off, size,
+ false, ACCESS_DIRECT, NULL);
+ if (err)
+ return err;
+
+ min_off = reg->smin_value + off;
+ max_off = reg->smax_value + off;
+ mark_reg_stack_read(env, ptr_state, min_off, max_off + size, dst_regno);
+ return 0;
+}
+
+/* check_stack_read dispatches to check_stack_read_fixed_off or
+ * check_stack_read_var_off.
+ *
+ * The caller must ensure that the offset falls within the allocated stack
+ * bounds.
+ *
+ * 'dst_regno' is a register which will receive the value from the stack. It
+ * can be -1, meaning that the read value is not going to a register.
+ */
+static int check_stack_read(struct bpf_verifier_env *env,
+ int ptr_regno, int off, int size,
+ int dst_regno)
+{
+ struct bpf_reg_state *reg = reg_state(env, ptr_regno);
+ struct bpf_func_state *state = func(env, reg);
+ int err;
+ /* Some accesses are only permitted with a static offset. */
+ bool var_off = !tnum_is_const(reg->var_off);
+
+ /* The offset is required to be static when reads don't go to a
+ * register, in order to not leak pointers (see
+ * check_stack_read_fixed_off).
+ */
+ if (dst_regno < 0 && var_off) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "variable stack access var_off=%s off=%d size=%d\n",
+ verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n",
tn_buf, off, size);
return -EACCES;
}
-
- if (off >= 0 || off < -MAX_BPF_STACK) {
- verbose(env, "invalid stack off=%d size=%d\n", off, size);
- return -EACCES;
+ /* Variable offset is prohibited for unprivileged mode for simplicity
+ * since it requires corresponding support in Spectre masking for stack
+ * ALU. See also retrieve_ptr_limit(). The check in
+ * check_stack_access_for_ptr_arithmetic() called by
+ * adjust_ptr_min_max_vals() prevents users from creating stack pointers
+ * with variable offsets, therefore no check is required here. Further,
+ * just checking it here would be insufficient as speculative stack
+ * writes could still lead to unsafe speculative behaviour.
+ */
+ if (!var_off) {
+ off += reg->var_off.value;
+ err = check_stack_read_fixed_off(env, state, off, size,
+ dst_regno);
+ } else {
+ /* Variable offset stack reads need more conservative handling
+ * than fixed offset ones. Note that dst_regno >= 0 on this
+ * branch.
+ */
+ err = check_stack_read_var_off(env, ptr_regno, off, size,
+ dst_regno);
}
-
- return 0;
+ return err;
}
-/* check read/write into map element returned by bpf_map_lookup_elem() */
-static int __check_map_access(struct bpf_verifier_env *env, u32 regno, int off,
- int size, bool zero_size_allowed)
+
+/* check_stack_write dispatches to check_stack_write_fixed_off or
+ * check_stack_write_var_off.
+ *
+ * 'ptr_regno' is the register used as a pointer into the stack.
+ * 'off' includes 'ptr_regno->off', but not its variable offset (if any).
+ * 'value_regno' is the register whose value we're writing to the stack. It can
+ * be -1, meaning that we're not writing from a register.
+ *
+ * The caller must ensure that the offset falls within the maximum stack size.
+ */
+static int check_stack_write(struct bpf_verifier_env *env,
+ int ptr_regno, int off, int size,
+ int value_regno, int insn_idx)
+{
+ struct bpf_reg_state *reg = reg_state(env, ptr_regno);
+ struct bpf_func_state *state = func(env, reg);
+ int err;
+
+ if (tnum_is_const(reg->var_off)) {
+ off += reg->var_off.value;
+ err = check_stack_write_fixed_off(env, state, off, size,
+ value_regno, insn_idx);
+ } else {
+ /* Variable offset stack reads need more conservative handling
+ * than fixed offset ones.
+ */
+ err = check_stack_write_var_off(env, state,
+ ptr_regno, off, size,
+ value_regno, insn_idx);
+ }
+ return err;
+}
+
+static int check_map_access_type(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, enum bpf_access_type type)
{
struct bpf_reg_state *regs = cur_regs(env);
struct bpf_map *map = regs[regno].map_ptr;
+ u32 cap = bpf_map_flags_to_cap(map);
- if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
- off + size > map->value_size) {
- verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
+ if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
+ verbose(env, "write into map forbidden, value_size=%d off=%d size=%d\n",
map->value_size, off, size);
return -EACCES;
}
+
+ if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
+ verbose(env, "read from map forbidden, value_size=%d off=%d size=%d\n",
+ map->value_size, off, size);
+ return -EACCES;
+ }
+
return 0;
}
-/* check read/write into a map element with possible variable offset */
-static int check_map_access(struct bpf_verifier_env *env, u32 regno,
- int off, int size, bool zero_size_allowed)
+/* check read/write into memory region (e.g., map value, ringbuf sample, etc) */
+static int __check_mem_access(struct bpf_verifier_env *env, int regno,
+ int off, int size, u32 mem_size,
+ bool zero_size_allowed)
+{
+ bool size_ok = size > 0 || (size == 0 && zero_size_allowed);
+ struct bpf_reg_state *reg;
+
+ if (off >= 0 && size_ok && (u64)off + size <= mem_size)
+ return 0;
+
+ reg = &cur_regs(env)[regno];
+ switch (reg->type) {
+ case PTR_TO_MAP_VALUE:
+ verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
+ mem_size, off, size);
+ break;
+ case PTR_TO_PACKET:
+ case PTR_TO_PACKET_META:
+ case PTR_TO_PACKET_END:
+ verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
+ off, size, regno, reg->id, off, mem_size);
+ break;
+ case PTR_TO_MEM:
+ default:
+ verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n",
+ mem_size, off, size);
+ }
+
+ return -EACCES;
+}
+
+/* check read/write into a memory region with possible variable offset */
+static int check_mem_region_access(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, u32 mem_size,
+ bool zero_size_allowed)
{
struct bpf_verifier_state *vstate = env->cur_state;
struct bpf_func_state *state = vstate->frame[vstate->curframe];
struct bpf_reg_state *reg = &state->regs[regno];
int err;
- /* We may have adjusted the register to this map value, so we
+ /* We may have adjusted the register pointing to memory region, so we
* need to try adding each of min_value and max_value to off
* to make sure our theoretical access will be safe.
*/
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, state);
/* The minimum value is only important with signed
@@ -1219,10 +3075,10 @@
regno);
return -EACCES;
}
- err = __check_map_access(env, regno, reg->smin_value + off, size,
- zero_size_allowed);
+ err = __check_mem_access(env, regno, reg->smin_value + off, size,
+ mem_size, zero_size_allowed);
if (err) {
- verbose(env, "R%d min value is outside of the array range\n",
+ verbose(env, "R%d min value is outside of the allowed memory range\n",
regno);
return err;
}
@@ -1232,33 +3088,79 @@
* If reg->umax_value + off could overflow, treat that as unbounded too.
*/
if (reg->umax_value >= BPF_MAX_VAR_OFF) {
- verbose(env, "R%d unbounded memory access, make sure to bounds check any array access into a map\n",
+ verbose(env, "R%d unbounded memory access, make sure to bounds check any such access\n",
regno);
return -EACCES;
}
- err = __check_map_access(env, regno, reg->umax_value + off, size,
- zero_size_allowed);
- if (err)
- verbose(env, "R%d max value is outside of the array range\n",
+ err = __check_mem_access(env, regno, reg->umax_value + off, size,
+ mem_size, zero_size_allowed);
+ if (err) {
+ verbose(env, "R%d max value is outside of the allowed memory range\n",
regno);
+ return err;
+ }
+
+ return 0;
+}
+
+/* check read/write into a map element with possible variable offset */
+static int check_map_access(struct bpf_verifier_env *env, u32 regno,
+ int off, int size, bool zero_size_allowed)
+{
+ struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *reg = &state->regs[regno];
+ struct bpf_map *map = reg->map_ptr;
+ int err;
+
+ err = check_mem_region_access(env, regno, off, size, map->value_size,
+ zero_size_allowed);
+ if (err)
+ return err;
+
+ if (map_value_has_spin_lock(map)) {
+ u32 lock = map->spin_lock_off;
+
+ /* if any part of struct bpf_spin_lock can be touched by
+ * load/store reject this program.
+ * To check that [x1, x2) overlaps with [y1, y2)
+ * it is sufficient to check x1 < y2 && y1 < x2.
+ */
+ if (reg->smin_value + off < lock + sizeof(struct bpf_spin_lock) &&
+ lock < reg->umax_value + off + size) {
+ verbose(env, "bpf_spin_lock cannot be accessed directly by load/store\n");
+ return -EACCES;
+ }
+ }
return err;
}
#define MAX_PACKET_OFF 0xffff
+static enum bpf_prog_type resolve_prog_type(struct bpf_prog *prog)
+{
+ return prog->aux->dst_prog ? prog->aux->dst_prog->type : prog->type;
+}
+
static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
const struct bpf_call_arg_meta *meta,
enum bpf_access_type t)
{
- switch (env->prog->type) {
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+
+ switch (prog_type) {
+ /* Program types only with direct read access go here! */
case BPF_PROG_TYPE_LWT_IN:
case BPF_PROG_TYPE_LWT_OUT:
case BPF_PROG_TYPE_LWT_SEG6LOCAL:
case BPF_PROG_TYPE_SK_REUSEPORT:
- /* dst_input() and dst_output() can't write for now */
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_CGROUP_SKB:
if (t == BPF_WRITE)
return false;
- /* fallthrough */
+ fallthrough;
+
+ /* Program types with direct read + write access go here! */
case BPF_PROG_TYPE_SCHED_CLS:
case BPF_PROG_TYPE_SCHED_ACT:
case BPF_PROG_TYPE_XDP:
@@ -1270,24 +3172,16 @@
env->seen_direct_write = true;
return true;
+
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
+ if (t == BPF_WRITE)
+ env->seen_direct_write = true;
+
+ return true;
+
default:
return false;
}
-}
-
-static int __check_packet_access(struct bpf_verifier_env *env, u32 regno,
- int off, int size, bool zero_size_allowed)
-{
- struct bpf_reg_state *regs = cur_regs(env);
- struct bpf_reg_state *reg = ®s[regno];
-
- if (off < 0 || size < 0 || (size == 0 && !zero_size_allowed) ||
- (u64)off + size > reg->range) {
- verbose(env, "invalid access to packet, off=%d size=%d, R%d(id=%d,off=%d,r=%d)\n",
- off, size, regno, reg->id, reg->off, reg->range);
- return -EACCES;
- }
- return 0;
}
static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
@@ -1310,20 +3204,36 @@
regno);
return -EACCES;
}
- err = __check_packet_access(env, regno, off, size, zero_size_allowed);
+
+ err = reg->range < 0 ? -EINVAL :
+ __check_mem_access(env, regno, off, size, reg->range,
+ zero_size_allowed);
if (err) {
verbose(env, "R%d offset is outside of the packet\n", regno);
return err;
}
+
+ /* __check_mem_access has made sure "off + size - 1" is within u16.
+ * reg->umax_value can't be bigger than MAX_PACKET_OFF which is 0xffff,
+ * otherwise find_good_pkt_pointers would have refused to set range info
+ * that __check_mem_access would have rejected this pkt access.
+ * Therefore, "off + reg->umax_value + size - 1" won't overflow u32.
+ */
+ env->prog->aux->max_pkt_offset =
+ max_t(u32, env->prog->aux->max_pkt_offset,
+ off + reg->umax_value + size - 1);
+
return err;
}
/* check access to 'struct bpf_context' fields. Supports fixed offsets only */
static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
- enum bpf_access_type t, enum bpf_reg_type *reg_type)
+ enum bpf_access_type t, enum bpf_reg_type *reg_type,
+ u32 *btf_id)
{
struct bpf_insn_access_aux info = {
.reg_type = *reg_type,
+ .log = &env->log,
};
if (env->ops->is_valid_access &&
@@ -1337,7 +3247,10 @@
*/
*reg_type = info.reg_type;
- env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
+ if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL)
+ *btf_id = info.btf_id;
+ else
+ env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size;
/* remember the offset of last byte accessed in ctx */
if (env->prog->aux->max_ctx_offset < off + size)
env->prog->aux->max_ctx_offset = off + size;
@@ -1348,32 +3261,95 @@
return -EACCES;
}
-static bool __is_pointer_value(bool allow_ptr_leaks,
- const struct bpf_reg_state *reg)
+static int check_flow_keys_access(struct bpf_verifier_env *env, int off,
+ int size)
{
- if (allow_ptr_leaks)
- return false;
+ if (size < 0 || off < 0 ||
+ (u64)off + size > sizeof(struct bpf_flow_keys)) {
+ verbose(env, "invalid access to flow keys off=%d size=%d\n",
+ off, size);
+ return -EACCES;
+ }
+ return 0;
+}
- return reg->type != SCALAR_VALUE;
+static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
+ u32 regno, int off, int size,
+ enum bpf_access_type t)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = ®s[regno];
+ struct bpf_insn_access_aux info = {};
+ bool valid;
+
+ if (reg->smin_value < 0) {
+ verbose(env, "R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n",
+ regno);
+ return -EACCES;
+ }
+
+ switch (reg->type) {
+ case PTR_TO_SOCK_COMMON:
+ valid = bpf_sock_common_is_valid_access(off, size, t, &info);
+ break;
+ case PTR_TO_SOCKET:
+ valid = bpf_sock_is_valid_access(off, size, t, &info);
+ break;
+ case PTR_TO_TCP_SOCK:
+ valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
+ break;
+ case PTR_TO_XDP_SOCK:
+ valid = bpf_xdp_sock_is_valid_access(off, size, t, &info);
+ break;
+ default:
+ valid = false;
+ }
+
+
+ if (valid) {
+ env->insn_aux_data[insn_idx].ctx_field_size =
+ info.ctx_field_size;
+ return 0;
+ }
+
+ verbose(env, "R%d invalid %s access off=%d size=%d\n",
+ regno, reg_type_str[reg->type], off, size);
+
+ return -EACCES;
}
static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
- return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
+ return __is_pointer_value(env->allow_ptr_leaks, reg_state(env, regno));
}
static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
- const struct bpf_reg_state *reg = cur_regs(env) + regno;
+ const struct bpf_reg_state *reg = reg_state(env, regno);
return reg->type == PTR_TO_CTX;
}
+static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = reg_state(env, regno);
+
+ return type_is_sk_pointer(reg->type);
+}
+
static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
{
- const struct bpf_reg_state *reg = cur_regs(env) + regno;
+ const struct bpf_reg_state *reg = reg_state(env, regno);
return type_is_pkt_pointer(reg->type);
+}
+
+static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
+{
+ const struct bpf_reg_state *reg = reg_state(env, regno);
+
+ /* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */
+ return reg->type == PTR_TO_FLOW_KEYS;
}
static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
@@ -1449,6 +3425,9 @@
* right in front, treat it the very same way.
*/
return check_pkt_ptr_alignment(env, reg, off, size, strict);
+ case PTR_TO_FLOW_KEYS:
+ pointer_desc = "flow keys ";
+ break;
case PTR_TO_MAP_VALUE:
pointer_desc = "value ";
break;
@@ -1457,11 +3436,23 @@
break;
case PTR_TO_STACK:
pointer_desc = "stack ";
- /* The stack spill tracking logic in check_stack_write()
- * and check_stack_read() relies on stack accesses being
+ /* The stack spill tracking logic in check_stack_write_fixed_off()
+ * and check_stack_read_fixed_off() relies on stack accesses being
* aligned.
*/
strict = true;
+ break;
+ case PTR_TO_SOCKET:
+ pointer_desc = "sock ";
+ break;
+ case PTR_TO_SOCK_COMMON:
+ pointer_desc = "sock_common ";
+ break;
+ case PTR_TO_TCP_SOCK:
+ pointer_desc = "tcp_sock ";
+ break;
+ case PTR_TO_XDP_SOCK:
+ pointer_desc = "xdp_sock ";
break;
default:
break;
@@ -1495,10 +3486,37 @@
int depth = 0, frame = 0, idx = 0, i = 0, subprog_end;
struct bpf_subprog_info *subprog = env->subprog_info;
struct bpf_insn *insn = env->prog->insnsi;
+ bool tail_call_reachable = false;
int ret_insn[MAX_CALL_FRAMES];
int ret_prog[MAX_CALL_FRAMES];
+ int j;
process_func:
+ /* protect against potential stack overflow that might happen when
+ * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
+ * depth for such case down to 256 so that the worst case scenario
+ * would result in 8k stack size (32 which is tailcall limit * 256 =
+ * 8k).
+ *
+ * To get the idea what might happen, see an example:
+ * func1 -> sub rsp, 128
+ * subfunc1 -> sub rsp, 256
+ * tailcall1 -> add rsp, 256
+ * func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
+ * subfunc2 -> sub rsp, 64
+ * subfunc22 -> sub rsp, 128
+ * tailcall2 -> add rsp, 128
+ * func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
+ *
+ * tailcall will unwind the current stack frame but it will not get rid
+ * of caller's stack as shown on the example above.
+ */
+ if (idx && subprog[idx].has_tail_call && depth >= 256) {
+ verbose(env,
+ "tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
+ depth);
+ return -EACCES;
+ }
/* round up to 32-bytes, since this is granularity
* of interpreter stack size
*/
@@ -1527,13 +3545,29 @@
i);
return -EFAULT;
}
+
+ if (subprog[idx].has_tail_call)
+ tail_call_reachable = true;
+
frame++;
if (frame >= MAX_CALL_FRAMES) {
- WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
- return -EFAULT;
+ verbose(env, "the call stack of %d frames is too deep !\n",
+ frame);
+ return -E2BIG;
}
goto process_func;
}
+ /* if tail call got detected across bpf2bpf calls then mark each of the
+ * currently present subprog frames as tail call reachable subprogs;
+ * this info will be utilized by JIT so that we will be preserving the
+ * tail call counter throughout bpf2bpf calls combined with tailcalls
+ */
+ if (tail_call_reachable)
+ for (j = 0; j < frame; j++)
+ subprog[ret_prog[j]].tail_call_reachable = true;
+ if (subprog[0].tail_call_reachable)
+ env->prog->aux->tail_call_reachable = true;
+
/* end of for() loop means the last insn of the 'subprog'
* was reached. Doesn't matter whether it was JA or EXIT
*/
@@ -1562,8 +3596,8 @@
}
#endif
-static int check_ctx_reg(struct bpf_verifier_env *env,
- const struct bpf_reg_state *reg, int regno)
+int check_ctx_reg(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg, int regno)
{
/* Access to ctx or passing it to a helper is only allowed in
* its original, unmodified form.
@@ -1584,6 +3618,72 @@
}
return 0;
+}
+
+static int __check_buffer_access(struct bpf_verifier_env *env,
+ const char *buf_info,
+ const struct bpf_reg_state *reg,
+ int regno, int off, int size)
+{
+ if (off < 0) {
+ verbose(env,
+ "R%d invalid %s buffer access: off=%d, size=%d\n",
+ regno, buf_info, off, size);
+ return -EACCES;
+ }
+ if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env,
+ "R%d invalid variable buffer offset: off=%d, var_off=%s\n",
+ regno, off, tn_buf);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
+static int check_tp_buffer_access(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ int regno, int off, int size)
+{
+ int err;
+
+ err = __check_buffer_access(env, "tracepoint", reg, regno, off, size);
+ if (err)
+ return err;
+
+ if (off + size > env->prog->aux->max_tp_access)
+ env->prog->aux->max_tp_access = off + size;
+
+ return 0;
+}
+
+static int check_buffer_access(struct bpf_verifier_env *env,
+ const struct bpf_reg_state *reg,
+ int regno, int off, int size,
+ bool zero_size_allowed,
+ const char *buf_info,
+ u32 *max_access)
+{
+ int err;
+
+ err = __check_buffer_access(env, buf_info, reg, regno, off, size);
+ if (err)
+ return err;
+
+ if (off + size > *max_access)
+ *max_access = off + size;
+
+ return 0;
+}
+
+/* BPF architecture zero extends alu32 ops into 64-bit registesr */
+static void zext_32_to_64(struct bpf_reg_state *reg)
+{
+ reg->var_off = tnum_subreg(reg->var_off);
+ __reg_assign_32_into_64(reg);
}
/* truncate register to smaller size (in bytes)
@@ -1607,6 +3707,255 @@
}
reg->smin_value = reg->umin_value;
reg->smax_value = reg->umax_value;
+
+ /* If size is smaller than 32bit register the 32bit register
+ * values are also truncated so we push 64-bit bounds into
+ * 32-bit bounds. Above were truncated < 32-bits already.
+ */
+ if (size >= 4)
+ return;
+ __reg_combine_64_into_32(reg);
+}
+
+static bool bpf_map_is_rdonly(const struct bpf_map *map)
+{
+ /* A map is considered read-only if the following condition are true:
+ *
+ * 1) BPF program side cannot change any of the map content. The
+ * BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
+ * and was set at map creation time.
+ * 2) The map value(s) have been initialized from user space by a
+ * loader and then "frozen", such that no new map update/delete
+ * operations from syscall side are possible for the rest of
+ * the map's lifetime from that point onwards.
+ * 3) Any parallel/pending map update/delete operations from syscall
+ * side have been completed. Only after that point, it's safe to
+ * assume that map value(s) are immutable.
+ */
+ return (map->map_flags & BPF_F_RDONLY_PROG) &&
+ READ_ONCE(map->frozen) &&
+ !bpf_map_write_active(map);
+}
+
+static int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val)
+{
+ void *ptr;
+ u64 addr;
+ int err;
+
+ err = map->ops->map_direct_value_addr(map, &addr, off);
+ if (err)
+ return err;
+ ptr = (void *)(long)addr + off;
+
+ switch (size) {
+ case sizeof(u8):
+ *val = (u64)*(u8 *)ptr;
+ break;
+ case sizeof(u16):
+ *val = (u64)*(u16 *)ptr;
+ break;
+ case sizeof(u32):
+ *val = (u64)*(u32 *)ptr;
+ break;
+ case sizeof(u64):
+ *val = *(u64 *)ptr;
+ break;
+ default:
+ return -EINVAL;
+ }
+ return 0;
+}
+
+static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs,
+ int regno, int off, int size,
+ enum bpf_access_type atype,
+ int value_regno)
+{
+ struct bpf_reg_state *reg = regs + regno;
+ const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id);
+ const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ u32 btf_id;
+ int ret;
+
+ if (off < 0) {
+ verbose(env,
+ "R%d is ptr_%s invalid negative access: off=%d\n",
+ regno, tname, off);
+ return -EACCES;
+ }
+ if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env,
+ "R%d is ptr_%s invalid variable offset: off=%d, var_off=%s\n",
+ regno, tname, off, tn_buf);
+ return -EACCES;
+ }
+
+ if (env->ops->btf_struct_access) {
+ ret = env->ops->btf_struct_access(&env->log, t, off, size,
+ atype, &btf_id);
+ } else {
+ if (atype != BPF_READ) {
+ verbose(env, "only read is supported\n");
+ return -EACCES;
+ }
+
+ ret = btf_struct_access(&env->log, t, off, size, atype,
+ &btf_id);
+ }
+
+ if (ret < 0)
+ return ret;
+
+ if (atype == BPF_READ && value_regno >= 0)
+ mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
+ return 0;
+}
+
+static int check_ptr_to_map_access(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs,
+ int regno, int off, int size,
+ enum bpf_access_type atype,
+ int value_regno)
+{
+ struct bpf_reg_state *reg = regs + regno;
+ struct bpf_map *map = reg->map_ptr;
+ const struct btf_type *t;
+ const char *tname;
+ u32 btf_id;
+ int ret;
+
+ if (!btf_vmlinux) {
+ verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n");
+ return -ENOTSUPP;
+ }
+
+ if (!map->ops->map_btf_id || !*map->ops->map_btf_id) {
+ verbose(env, "map_ptr access not supported for map type %d\n",
+ map->map_type);
+ return -ENOTSUPP;
+ }
+
+ t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id);
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+
+ if (!env->allow_ptr_to_map_access) {
+ verbose(env,
+ "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
+ tname);
+ return -EPERM;
+ }
+
+ if (off < 0) {
+ verbose(env, "R%d is %s invalid negative access: off=%d\n",
+ regno, tname, off);
+ return -EACCES;
+ }
+
+ if (atype != BPF_READ) {
+ verbose(env, "only read from %s is supported\n", tname);
+ return -EACCES;
+ }
+
+ ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id);
+ if (ret < 0)
+ return ret;
+
+ if (value_regno >= 0)
+ mark_btf_ld_reg(env, regs, value_regno, ret, btf_id);
+
+ return 0;
+}
+
+/* Check that the stack access at the given offset is within bounds. The
+ * maximum valid offset is -1.
+ *
+ * The minimum valid offset is -MAX_BPF_STACK for writes, and
+ * -state->allocated_stack for reads.
+ */
+static int check_stack_slot_within_bounds(int off,
+ struct bpf_func_state *state,
+ enum bpf_access_type t)
+{
+ int min_valid_off;
+
+ if (t == BPF_WRITE)
+ min_valid_off = -MAX_BPF_STACK;
+ else
+ min_valid_off = -state->allocated_stack;
+
+ if (off < min_valid_off || off > -1)
+ return -EACCES;
+ return 0;
+}
+
+/* Check that the stack access at 'regno + off' falls within the maximum stack
+ * bounds.
+ *
+ * 'off' includes `regno->offset`, but not its dynamic part (if any).
+ */
+static int check_stack_access_within_bounds(
+ struct bpf_verifier_env *env,
+ int regno, int off, int access_size,
+ enum stack_access_src src, enum bpf_access_type type)
+{
+ struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *reg = regs + regno;
+ struct bpf_func_state *state = func(env, reg);
+ int min_off, max_off;
+ int err;
+ char *err_extra;
+
+ if (src == ACCESS_HELPER)
+ /* We don't know if helpers are reading or writing (or both). */
+ err_extra = " indirect access to";
+ else if (type == BPF_READ)
+ err_extra = " read from";
+ else
+ err_extra = " write to";
+
+ if (tnum_is_const(reg->var_off)) {
+ min_off = reg->var_off.value + off;
+ if (access_size > 0)
+ max_off = min_off + access_size - 1;
+ else
+ max_off = min_off;
+ } else {
+ if (reg->smax_value >= BPF_MAX_VAR_OFF ||
+ reg->smin_value <= -BPF_MAX_VAR_OFF) {
+ verbose(env, "invalid unbounded variable-offset%s stack R%d\n",
+ err_extra, regno);
+ return -EACCES;
+ }
+ min_off = reg->smin_value + off;
+ if (access_size > 0)
+ max_off = reg->smax_value + off + access_size - 1;
+ else
+ max_off = min_off;
+ }
+
+ err = check_stack_slot_within_bounds(min_off, state, type);
+ if (!err)
+ err = check_stack_slot_within_bounds(max_off, state, type);
+
+ if (err) {
+ if (tnum_is_const(reg->var_off)) {
+ verbose(env, "invalid%s stack R%d off=%d size=%d\n",
+ err_extra, regno, off, access_size);
+ } else {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "invalid variable-offset%s stack R%d var_off=%s size=%d\n",
+ err_extra, regno, tn_buf, access_size);
+ }
+ }
+ return err;
}
/* check whether memory at (regno + off) is accessible for t = (read | write)
@@ -1642,13 +3991,44 @@
verbose(env, "R%d leaks addr into map\n", value_regno);
return -EACCES;
}
-
+ err = check_map_access_type(env, regno, off, size, t);
+ if (err)
+ return err;
err = check_map_access(env, regno, off, size, false);
+ if (!err && t == BPF_READ && value_regno >= 0) {
+ struct bpf_map *map = reg->map_ptr;
+
+ /* if map is read-only, track its contents as scalars */
+ if (tnum_is_const(reg->var_off) &&
+ bpf_map_is_rdonly(map) &&
+ map->ops->map_direct_value_addr) {
+ int map_off = off + reg->var_off.value;
+ u64 val = 0;
+
+ err = bpf_map_direct_read(map, map_off, size,
+ &val);
+ if (err)
+ return err;
+
+ regs[value_regno].type = SCALAR_VALUE;
+ __mark_reg_known(®s[value_regno], val);
+ } else {
+ mark_reg_unknown(env, regs, value_regno);
+ }
+ }
+ } else if (reg->type == PTR_TO_MEM) {
+ if (t == BPF_WRITE && value_regno >= 0 &&
+ is_pointer_value(env, value_regno)) {
+ verbose(env, "R%d leaks addr into mem\n", value_regno);
+ return -EACCES;
+ }
+ err = check_mem_region_access(env, regno, off, size,
+ reg->mem_size, false);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
-
} else if (reg->type == PTR_TO_CTX) {
enum bpf_reg_type reg_type = SCALAR_VALUE;
+ u32 btf_id = 0;
if (t == BPF_WRITE && value_regno >= 0 &&
is_pointer_value(env, value_regno)) {
@@ -1660,23 +4040,37 @@
if (err < 0)
return err;
- err = check_ctx_access(env, insn_idx, off, size, t, ®_type);
+ err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id);
+ if (err)
+ verbose_linfo(env, insn_idx, "; ");
if (!err && t == BPF_READ && value_regno >= 0) {
/* ctx access returns either a scalar, or a
* PTR_TO_PACKET[_META,_END]. In the latter
* case, we know the offset is zero.
*/
- if (reg_type == SCALAR_VALUE)
+ if (reg_type == SCALAR_VALUE) {
mark_reg_unknown(env, regs, value_regno);
- else
+ } else {
mark_reg_known_zero(env, regs,
value_regno);
+ if (reg_type_may_be_null(reg_type))
+ regs[value_regno].id = ++env->id_gen;
+ /* A load of ctx field could have different
+ * actual load size with the one encoded in the
+ * insn. When the dst is PTR, it is for sure not
+ * a sub-register.
+ */
+ regs[value_regno].subreg_def = DEF_NOT_SUBREG;
+ if (reg_type == PTR_TO_BTF_ID ||
+ reg_type == PTR_TO_BTF_ID_OR_NULL)
+ regs[value_regno].btf_id = btf_id;
+ }
regs[value_regno].type = reg_type;
}
} else if (reg->type == PTR_TO_STACK) {
- off += reg->var_off.value;
- err = check_stack_access(env, reg, off, size);
+ /* Basic bounds checks. */
+ err = check_stack_access_within_bounds(env, regno, off, size, ACCESS_DIRECT, t);
if (err)
return err;
@@ -1685,12 +4079,12 @@
if (err)
return err;
- if (t == BPF_WRITE)
- err = check_stack_write(env, state, off, size,
- value_regno, insn_idx);
- else
- err = check_stack_read(env, state, off, size,
+ if (t == BPF_READ)
+ err = check_stack_read(env, regno, off, size,
value_regno);
+ else
+ err = check_stack_write(env, regno, off, size,
+ value_regno, insn_idx);
} else if (reg_is_pkt_pointer(reg)) {
if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
verbose(env, "cannot write into packet\n");
@@ -1703,6 +4097,53 @@
return -EACCES;
}
err = check_packet_access(env, regno, off, size, false);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_FLOW_KEYS) {
+ if (t == BPF_WRITE && value_regno >= 0 &&
+ is_pointer_value(env, value_regno)) {
+ verbose(env, "R%d leaks addr into flow keys\n",
+ value_regno);
+ return -EACCES;
+ }
+
+ err = check_flow_keys_access(env, off, size);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (type_is_sk_pointer(reg->type)) {
+ if (t == BPF_WRITE) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str[reg->type]);
+ return -EACCES;
+ }
+ err = check_sock_access(env, insn_idx, regno, off, size, t);
+ if (!err && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_TP_BUFFER) {
+ err = check_tp_buffer_access(env, reg, regno, off, size);
+ if (!err && t == BPF_READ && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_BTF_ID) {
+ err = check_ptr_to_btf_access(env, regs, regno, off, size, t,
+ value_regno);
+ } else if (reg->type == CONST_PTR_TO_MAP) {
+ err = check_ptr_to_map_access(env, regs, regno, off, size, t,
+ value_regno);
+ } else if (reg->type == PTR_TO_RDONLY_BUF) {
+ if (t == BPF_WRITE) {
+ verbose(env, "R%d cannot write into %s\n",
+ regno, reg_type_str[reg->type]);
+ return -EACCES;
+ }
+ err = check_buffer_access(env, reg, regno, off, size, false,
+ "rdonly",
+ &env->prog->aux->max_rdonly_access);
+ if (!err && value_regno >= 0)
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_RDWR_BUF) {
+ err = check_buffer_access(env, reg, regno, off, size, false,
+ "rdwr",
+ &env->prog->aux->max_rdwr_access);
if (!err && t == BPF_READ && value_regno >= 0)
mark_reg_unknown(env, regs, value_regno);
} else {
@@ -1745,10 +4186,12 @@
}
if (is_ctx_reg(env, insn->dst_reg) ||
- is_pkt_reg(env, insn->dst_reg)) {
+ is_pkt_reg(env, insn->dst_reg) ||
+ is_flow_key_reg(env, insn->dst_reg) ||
+ is_sk_reg(env, insn->dst_reg)) {
verbose(env, "BPF_XADD stores into R%d %s is not allowed\n",
- insn->dst_reg, is_ctx_reg(env, insn->dst_reg) ?
- "context" : "packet");
+ insn->dst_reg,
+ reg_type_str[reg_state(env, insn->dst_reg)->type]);
return -EACCES;
}
@@ -1763,73 +4206,65 @@
BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}
-static int __check_stack_boundary(struct bpf_verifier_env *env, u32 regno,
- int off, int access_size,
- bool zero_size_allowed)
-{
- struct bpf_reg_state *reg = cur_regs(env) + regno;
-
- if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
- access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
- if (tnum_is_const(reg->var_off)) {
- verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
- regno, off, access_size);
- } else {
- char tn_buf[48];
-
- tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "invalid stack type R%d var_off=%s access_size=%d\n",
- regno, tn_buf, access_size);
- }
- return -EACCES;
- }
- return 0;
-}
-
-/* when register 'regno' is passed into function that will read 'access_size'
- * bytes from that pointer, make sure that it's within stack boundary
- * and all elements of stack are initialized.
- * Unlike most pointer bounds-checking functions, this one doesn't take an
- * 'off' argument, so it has to add in reg->off itself.
+/* 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.
+ *
+ * 'off' includes 'regno->off', but not its dynamic part (if any).
+ *
+ * All registers that have been spilled on the stack in the slots within the
+ * read offsets are marked as read.
*/
-static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
- int access_size, bool zero_size_allowed,
- struct bpf_call_arg_meta *meta)
+static int check_stack_range_initialized(
+ struct bpf_verifier_env *env, int regno, int off,
+ int access_size, bool zero_size_allowed,
+ enum stack_access_src type, struct bpf_call_arg_meta *meta)
{
- struct bpf_reg_state *reg = cur_regs(env) + regno;
+ struct bpf_reg_state *reg = reg_state(env, regno);
struct bpf_func_state *state = func(env, reg);
int err, min_off, max_off, i, j, slot, spi;
+ char *err_extra = type == ACCESS_HELPER ? " indirect" : "";
+ enum bpf_access_type bounds_check_type;
+ /* Some accesses can write anything into the stack, others are
+ * read-only.
+ */
+ bool clobber = false;
- if (reg->type != PTR_TO_STACK) {
- /* Allow zero-byte read from NULL, regardless of pointer type */
- if (zero_size_allowed && access_size == 0 &&
- register_is_null(reg))
- return 0;
-
- verbose(env, "R%d type=%s expected=%s\n", regno,
- reg_type_str[reg->type],
- reg_type_str[PTR_TO_STACK]);
+ if (access_size == 0 && !zero_size_allowed) {
+ verbose(env, "invalid zero-sized read\n");
return -EACCES;
}
+ if (type == ACCESS_HELPER) {
+ /* The bounds checks for writes are more permissive than for
+ * reads. However, if raw_mode is not set, we'll do extra
+ * checks below.
+ */
+ bounds_check_type = BPF_WRITE;
+ clobber = true;
+ } else {
+ bounds_check_type = BPF_READ;
+ }
+ err = check_stack_access_within_bounds(env, regno, off, access_size,
+ type, bounds_check_type);
+ if (err)
+ return err;
+
+
if (tnum_is_const(reg->var_off)) {
- min_off = max_off = reg->var_off.value + reg->off;
- err = __check_stack_boundary(env, regno, min_off, access_size,
- zero_size_allowed);
- if (err)
- return err;
+ min_off = max_off = reg->var_off.value + off;
} else {
/* Variable offset is prohibited for unprivileged mode for
* simplicity since it requires corresponding support in
* Spectre masking for stack ALU.
* See also retrieve_ptr_limit().
*/
- if (!env->allow_ptr_leaks) {
+ if (!env->bypass_spec_v1) {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "R%d indirect variable offset stack access prohibited for !root, var_off=%s\n",
- regno, tn_buf);
+ verbose(env, "R%d%s variable offset stack access prohibited for !root, var_off=%s\n",
+ regno, err_extra, tn_buf);
return -EACCES;
}
/* Only initialized buffer on stack is allowed to be accessed
@@ -1841,28 +4276,8 @@
if (meta && meta->raw_mode)
meta = NULL;
- if (reg->smax_value >= BPF_MAX_VAR_OFF ||
- reg->smax_value <= -BPF_MAX_VAR_OFF) {
- verbose(env, "R%d unbounded indirect variable offset stack access\n",
- regno);
- return -EACCES;
- }
- min_off = reg->smin_value + reg->off;
- max_off = reg->smax_value + reg->off;
- err = __check_stack_boundary(env, regno, min_off, access_size,
- zero_size_allowed);
- if (err) {
- verbose(env, "R%d min value is outside of stack bound\n",
- regno);
- return err;
- }
- err = __check_stack_boundary(env, regno, max_off, access_size,
- zero_size_allowed);
- if (err) {
- verbose(env, "R%d max value is outside of stack bound\n",
- regno);
- return err;
- }
+ min_off = reg->smin_value + off;
+ max_off = reg->smax_value + off;
}
if (meta && meta->raw_mode) {
@@ -1882,28 +4297,38 @@
if (*stype == STACK_MISC)
goto mark;
if (*stype == STACK_ZERO) {
- /* helper can write anything into the stack */
- *stype = STACK_MISC;
+ if (clobber) {
+ /* helper can write anything into the stack */
+ *stype = STACK_MISC;
+ }
goto mark;
}
- if (state->stack[spi].slot_type[0] == STACK_SPILL &&
- state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
- __mark_reg_unknown(&state->stack[spi].spilled_ptr);
- for (j = 0; j < BPF_REG_SIZE; j++)
- state->stack[spi].slot_type[j] = STACK_MISC;
+
+ if (is_spilled_reg(&state->stack[spi]) &&
+ state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
+ goto mark;
+
+ if (is_spilled_reg(&state->stack[spi]) &&
+ (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
+ env->allow_ptr_leaks)) {
+ if (clobber) {
+ __mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
+ for (j = 0; j < BPF_REG_SIZE; j++)
+ scrub_spilled_slot(&state->stack[spi].slot_type[j]);
+ }
goto mark;
}
err:
if (tnum_is_const(reg->var_off)) {
- verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
- min_off, i - min_off, access_size);
+ 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);
} else {
char tn_buf[48];
tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
- verbose(env, "invalid indirect read from stack var_off %s+%d size %d\n",
- tn_buf, i - min_off, access_size);
+ verbose(env, "invalid%s read from stack R%d var_off %s+%d size %d\n",
+ err_extra, regno, tn_buf, i - min_off, access_size);
}
return -EACCES;
mark:
@@ -1911,7 +4336,8 @@
* the whole slot to be marked as 'read'
*/
mark_reg_read(env, &state->stack[spi].spilled_ptr,
- state->stack[spi].spilled_ptr.parent);
+ state->stack[spi].spilled_ptr.parent,
+ REG_LIVE_READ64);
}
return update_stack_depth(env, state, min_off);
}
@@ -1928,12 +4354,125 @@
return check_packet_access(env, regno, reg->off, access_size,
zero_size_allowed);
case PTR_TO_MAP_VALUE:
+ if (check_map_access_type(env, regno, reg->off, access_size,
+ meta && meta->raw_mode ? BPF_WRITE :
+ BPF_READ))
+ return -EACCES;
return check_map_access(env, regno, reg->off, access_size,
zero_size_allowed);
- default: /* scalar_value|ptr_to_stack or invalid ptr */
- return check_stack_boundary(env, regno, access_size,
- zero_size_allowed, meta);
+ case PTR_TO_MEM:
+ return check_mem_region_access(env, regno, reg->off,
+ access_size, reg->mem_size,
+ zero_size_allowed);
+ case PTR_TO_RDONLY_BUF:
+ if (meta && meta->raw_mode)
+ return -EACCES;
+ return check_buffer_access(env, reg, regno, reg->off,
+ access_size, zero_size_allowed,
+ "rdonly",
+ &env->prog->aux->max_rdonly_access);
+ case PTR_TO_RDWR_BUF:
+ return check_buffer_access(env, reg, regno, reg->off,
+ access_size, zero_size_allowed,
+ "rdwr",
+ &env->prog->aux->max_rdwr_access);
+ case PTR_TO_STACK:
+ return check_stack_range_initialized(
+ env,
+ regno, reg->off, access_size,
+ zero_size_allowed, ACCESS_HELPER, meta);
+ default: /* scalar_value or invalid ptr */
+ /* Allow zero-byte read from NULL, regardless of pointer type */
+ if (zero_size_allowed && access_size == 0 &&
+ register_is_null(reg))
+ return 0;
+
+ verbose(env, "R%d type=%s expected=%s\n", regno,
+ reg_type_str[reg->type],
+ reg_type_str[PTR_TO_STACK]);
+ return -EACCES;
}
+}
+
+/* Implementation details:
+ * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL
+ * Two bpf_map_lookups (even with the same key) will have different reg->id.
+ * For traditional PTR_TO_MAP_VALUE the verifier clears reg->id after
+ * value_or_null->value transition, since the verifier only cares about
+ * the range of access to valid map value pointer and doesn't care about actual
+ * address of the map element.
+ * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps
+ * reg->id > 0 after value_or_null->value transition. By doing so
+ * two bpf_map_lookups will be considered two different pointers that
+ * point to different bpf_spin_locks.
+ * The verifier allows taking only one bpf_spin_lock at a time to avoid
+ * dead-locks.
+ * Since only one bpf_spin_lock is allowed the checks are simpler than
+ * reg_is_refcounted() logic. The verifier needs to remember only
+ * one spin_lock instead of array of acquired_refs.
+ * cur_state->active_spin_lock remembers which map value element got locked
+ * and clears it after bpf_spin_unlock.
+ */
+static int process_spin_lock(struct bpf_verifier_env *env, int regno,
+ bool is_lock)
+{
+ struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
+ struct bpf_verifier_state *cur = env->cur_state;
+ bool is_const = tnum_is_const(reg->var_off);
+ struct bpf_map *map = reg->map_ptr;
+ u64 val = reg->var_off.value;
+
+ if (!is_const) {
+ verbose(env,
+ "R%d doesn't have constant offset. bpf_spin_lock has to be at the constant offset\n",
+ regno);
+ return -EINVAL;
+ }
+ if (!map->btf) {
+ verbose(env,
+ "map '%s' has to have BTF in order to use bpf_spin_lock\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (!map_value_has_spin_lock(map)) {
+ if (map->spin_lock_off == -E2BIG)
+ verbose(env,
+ "map '%s' has more than one 'struct bpf_spin_lock'\n",
+ map->name);
+ else if (map->spin_lock_off == -ENOENT)
+ verbose(env,
+ "map '%s' doesn't have 'struct bpf_spin_lock'\n",
+ map->name);
+ else
+ verbose(env,
+ "map '%s' is not a struct type or bpf_spin_lock is mangled\n",
+ map->name);
+ return -EINVAL;
+ }
+ if (map->spin_lock_off != val + reg->off) {
+ verbose(env, "off %lld doesn't point to 'struct bpf_spin_lock'\n",
+ val + reg->off);
+ return -EINVAL;
+ }
+ if (is_lock) {
+ if (cur->active_spin_lock) {
+ verbose(env,
+ "Locking two bpf_spin_locks are not allowed\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = reg->id;
+ } else {
+ if (!cur->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock without taking a lock\n");
+ return -EINVAL;
+ }
+ if (cur->active_spin_lock != reg->id) {
+ verbose(env, "bpf_spin_unlock of different lock\n");
+ return -EINVAL;
+ }
+ cur->active_spin_lock = 0;
+ }
+ return 0;
}
static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
@@ -1949,12 +4488,215 @@
type == ARG_CONST_SIZE_OR_ZERO;
}
-static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
+static bool arg_type_is_alloc_size(enum bpf_arg_type type)
+{
+ return type == ARG_CONST_ALLOC_SIZE_OR_ZERO;
+}
+
+static bool arg_type_is_int_ptr(enum bpf_arg_type type)
+{
+ return type == ARG_PTR_TO_INT ||
+ type == ARG_PTR_TO_LONG;
+}
+
+static int int_ptr_type_to_size(enum bpf_arg_type type)
+{
+ if (type == ARG_PTR_TO_INT)
+ return sizeof(u32);
+ else if (type == ARG_PTR_TO_LONG)
+ return sizeof(u64);
+
+ return -EINVAL;
+}
+
+static int resolve_map_arg_type(struct bpf_verifier_env *env,
+ const struct bpf_call_arg_meta *meta,
+ enum bpf_arg_type *arg_type)
+{
+ if (!meta->map_ptr) {
+ /* kernel subsystem misconfigured verifier */
+ verbose(env, "invalid map_ptr to access map->type\n");
+ return -EACCES;
+ }
+
+ switch (meta->map_ptr->map_type) {
+ case BPF_MAP_TYPE_SOCKMAP:
+ case BPF_MAP_TYPE_SOCKHASH:
+ if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
+ *arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
+ } else {
+ verbose(env, "invalid arg_type for sockmap/sockhash\n");
+ return -EINVAL;
+ }
+ break;
+
+ default:
+ break;
+ }
+ return 0;
+}
+
+struct bpf_reg_types {
+ const enum bpf_reg_type types[10];
+ u32 *btf_id;
+};
+
+static const struct bpf_reg_types map_key_value_types = {
+ .types = {
+ PTR_TO_STACK,
+ PTR_TO_PACKET,
+ PTR_TO_PACKET_META,
+ PTR_TO_MAP_VALUE,
+ },
+};
+
+static const struct bpf_reg_types sock_types = {
+ .types = {
+ PTR_TO_SOCK_COMMON,
+ PTR_TO_SOCKET,
+ PTR_TO_TCP_SOCK,
+ PTR_TO_XDP_SOCK,
+ },
+};
+
+#ifdef CONFIG_NET
+static const struct bpf_reg_types btf_id_sock_common_types = {
+ .types = {
+ PTR_TO_SOCK_COMMON,
+ PTR_TO_SOCKET,
+ PTR_TO_TCP_SOCK,
+ PTR_TO_XDP_SOCK,
+ PTR_TO_BTF_ID,
+ },
+ .btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
+};
+#endif
+
+static const struct bpf_reg_types mem_types = {
+ .types = {
+ PTR_TO_STACK,
+ PTR_TO_PACKET,
+ PTR_TO_PACKET_META,
+ PTR_TO_MAP_VALUE,
+ PTR_TO_MEM,
+ PTR_TO_RDONLY_BUF,
+ PTR_TO_RDWR_BUF,
+ },
+};
+
+static const struct bpf_reg_types int_ptr_types = {
+ .types = {
+ PTR_TO_STACK,
+ PTR_TO_PACKET,
+ PTR_TO_PACKET_META,
+ PTR_TO_MAP_VALUE,
+ },
+};
+
+static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
+static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
+static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
+static const struct bpf_reg_types alloc_mem_types = { .types = { PTR_TO_MEM } };
+static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
+static const struct bpf_reg_types btf_ptr_types = { .types = { PTR_TO_BTF_ID } };
+static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALUE } };
+static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
+
+static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
+ [ARG_PTR_TO_MAP_KEY] = &map_key_value_types,
+ [ARG_PTR_TO_MAP_VALUE] = &map_key_value_types,
+ [ARG_PTR_TO_UNINIT_MAP_VALUE] = &map_key_value_types,
+ [ARG_PTR_TO_MAP_VALUE_OR_NULL] = &map_key_value_types,
+ [ARG_CONST_SIZE] = &scalar_types,
+ [ARG_CONST_SIZE_OR_ZERO] = &scalar_types,
+ [ARG_CONST_ALLOC_SIZE_OR_ZERO] = &scalar_types,
+ [ARG_CONST_MAP_PTR] = &const_map_ptr_types,
+ [ARG_PTR_TO_CTX] = &context_types,
+ [ARG_PTR_TO_CTX_OR_NULL] = &context_types,
+ [ARG_PTR_TO_SOCK_COMMON] = &sock_types,
+#ifdef CONFIG_NET
+ [ARG_PTR_TO_BTF_ID_SOCK_COMMON] = &btf_id_sock_common_types,
+#endif
+ [ARG_PTR_TO_SOCKET] = &fullsock_types,
+ [ARG_PTR_TO_SOCKET_OR_NULL] = &fullsock_types,
+ [ARG_PTR_TO_BTF_ID] = &btf_ptr_types,
+ [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types,
+ [ARG_PTR_TO_MEM] = &mem_types,
+ [ARG_PTR_TO_MEM_OR_NULL] = &mem_types,
+ [ARG_PTR_TO_UNINIT_MEM] = &mem_types,
+ [ARG_PTR_TO_ALLOC_MEM] = &alloc_mem_types,
+ [ARG_PTR_TO_ALLOC_MEM_OR_NULL] = &alloc_mem_types,
+ [ARG_PTR_TO_INT] = &int_ptr_types,
+ [ARG_PTR_TO_LONG] = &int_ptr_types,
+ [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
+};
+
+static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
enum bpf_arg_type arg_type,
- struct bpf_call_arg_meta *meta)
+ const u32 *arg_btf_id)
{
struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
- enum bpf_reg_type expected_type, type = reg->type;
+ enum bpf_reg_type expected, type = reg->type;
+ const struct bpf_reg_types *compatible;
+ int i, j;
+
+ compatible = compatible_reg_types[arg_type];
+ if (!compatible) {
+ verbose(env, "verifier internal error: unsupported arg type %d\n", arg_type);
+ return -EFAULT;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
+ expected = compatible->types[i];
+ if (expected == NOT_INIT)
+ break;
+
+ if (type == expected)
+ goto found;
+ }
+
+ verbose(env, "R%d type=%s expected=", regno, reg_type_str[type]);
+ for (j = 0; j + 1 < i; j++)
+ verbose(env, "%s, ", reg_type_str[compatible->types[j]]);
+ verbose(env, "%s\n", reg_type_str[compatible->types[j]]);
+ return -EACCES;
+
+found:
+ if (type == PTR_TO_BTF_ID) {
+ if (!arg_btf_id) {
+ if (!compatible->btf_id) {
+ verbose(env, "verifier internal error: missing arg compatible BTF ID\n");
+ return -EFAULT;
+ }
+ arg_btf_id = compatible->btf_id;
+ }
+
+ if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id,
+ *arg_btf_id)) {
+ verbose(env, "R%d is of type %s but %s is expected\n",
+ regno, kernel_type_name(reg->btf_id),
+ kernel_type_name(*arg_btf_id));
+ return -EACCES;
+ }
+
+ if (!tnum_is_const(reg->var_off) || reg->var_off.value) {
+ verbose(env, "R%d is a pointer to in-kernel struct with non-zero offset\n",
+ regno);
+ return -EACCES;
+ }
+ }
+
+ return 0;
+}
+
+static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+ struct bpf_call_arg_meta *meta,
+ const struct bpf_func_proto *fn)
+{
+ u32 regno = BPF_REG_1 + arg;
+ struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
+ enum bpf_arg_type arg_type = fn->arg_type[arg];
+ enum bpf_reg_type type = reg->type;
int err = 0;
if (arg_type == ARG_DONTCARE)
@@ -1979,45 +4721,39 @@
return -EACCES;
}
- if (arg_type == ARG_PTR_TO_MAP_KEY ||
- arg_type == ARG_PTR_TO_MAP_VALUE) {
- expected_type = PTR_TO_STACK;
- if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE &&
- type != expected_type)
- goto err_type;
- } else if (arg_type == ARG_CONST_SIZE ||
- arg_type == ARG_CONST_SIZE_OR_ZERO) {
- expected_type = SCALAR_VALUE;
- if (type != expected_type)
- goto err_type;
- } else if (arg_type == ARG_CONST_MAP_PTR) {
- expected_type = CONST_PTR_TO_MAP;
- if (type != expected_type)
- goto err_type;
- } else if (arg_type == ARG_PTR_TO_CTX) {
- expected_type = PTR_TO_CTX;
- if (type != expected_type)
- goto err_type;
+ if (arg_type == ARG_PTR_TO_MAP_VALUE ||
+ arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE ||
+ arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL) {
+ err = resolve_map_arg_type(env, meta, &arg_type);
+ if (err)
+ return err;
+ }
+
+ if (register_is_null(reg) && arg_type_may_be_null(arg_type))
+ /* A NULL register has a SCALAR_VALUE type, so skip
+ * type checking.
+ */
+ goto skip_type_check;
+
+ err = check_reg_type(env, regno, arg_type, fn->arg_btf_id[arg]);
+ if (err)
+ return err;
+
+ if (type == PTR_TO_CTX) {
err = check_ctx_reg(env, reg, regno);
if (err < 0)
return err;
- } else if (arg_type_is_mem_ptr(arg_type)) {
- expected_type = PTR_TO_STACK;
- /* One exception here. In case function allows for NULL to be
- * passed in as argument, it's a SCALAR_VALUE type. Final test
- * happens during stack boundary checking.
- */
- if (register_is_null(reg) &&
- arg_type == ARG_PTR_TO_MEM_OR_NULL)
- /* final test in check_stack_boundary() */;
- else if (!type_is_pkt_pointer(type) &&
- type != PTR_TO_MAP_VALUE &&
- type != expected_type)
- goto err_type;
- meta->raw_mode = arg_type == ARG_PTR_TO_UNINIT_MEM;
- } else {
- verbose(env, "unsupported arg_type %d\n", arg_type);
- return -EFAULT;
+ }
+
+skip_type_check:
+ if (reg->ref_obj_id) {
+ if (meta->ref_obj_id) {
+ verbose(env, "verifier internal error: more than one arg with ref_obj_id R%d %u %u\n",
+ regno, reg->ref_obj_id,
+ meta->ref_obj_id);
+ return -EFAULT;
+ }
+ meta->ref_obj_id = reg->ref_obj_id;
}
if (arg_type == ARG_CONST_MAP_PTR) {
@@ -2040,7 +4776,10 @@
err = check_helper_mem_access(env, regno,
meta->map_ptr->key_size, false,
NULL);
- } else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
+ } else if (arg_type == ARG_PTR_TO_MAP_VALUE ||
+ (arg_type == ARG_PTR_TO_MAP_VALUE_OR_NULL &&
+ !register_is_null(reg)) ||
+ arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE) {
/* bpf_map_xxx(..., map_ptr, ..., value) call:
* check [value, value + map->value_size) validity
*/
@@ -2049,14 +4788,42 @@
verbose(env, "invalid map_ptr to access map->value\n");
return -EACCES;
}
+ meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MAP_VALUE);
err = check_helper_mem_access(env, regno,
meta->map_ptr->value_size, false,
- NULL);
+ meta);
+ } else if (arg_type == ARG_PTR_TO_PERCPU_BTF_ID) {
+ if (!reg->btf_id) {
+ verbose(env, "Helper has invalid btf_id in R%d\n", regno);
+ return -EACCES;
+ }
+ meta->ret_btf_id = reg->btf_id;
+ } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) {
+ if (meta->func_id == BPF_FUNC_spin_lock) {
+ if (process_spin_lock(env, regno, true))
+ return -EACCES;
+ } else if (meta->func_id == BPF_FUNC_spin_unlock) {
+ if (process_spin_lock(env, regno, false))
+ return -EACCES;
+ } else {
+ verbose(env, "verifier internal error\n");
+ return -EFAULT;
+ }
+ } else if (arg_type_is_mem_ptr(arg_type)) {
+ /* The access to this pointer is only checked when we hit the
+ * next is_mem_size argument below.
+ */
+ meta->raw_mode = (arg_type == ARG_PTR_TO_UNINIT_MEM);
} else if (arg_type_is_mem_size(arg_type)) {
bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
- /* remember the mem_size which may be used later
- * to refine return values.
+ /* This is used to refine r0 return value bounds for helpers
+ * that enforce this value as an upper bound on return values.
+ * See do_refine_retval_range() for helpers that can refine
+ * the return value. C type of helper is u32 so we pull register
+ * bound from umax_value however, if negative verifier errors
+ * out. Only upper bounds can be learned because retval is an
+ * int type and negative retvals are allowed.
*/
meta->msize_max_value = reg->umax_value;
@@ -2093,13 +4860,62 @@
err = check_helper_mem_access(env, regno - 1,
reg->umax_value,
zero_size_allowed, meta);
+ if (!err)
+ err = mark_chain_precision(env, regno);
+ } else if (arg_type_is_alloc_size(arg_type)) {
+ if (!tnum_is_const(reg->var_off)) {
+ verbose(env, "R%d unbounded size, use 'var &= const' or 'if (var < const)'\n",
+ regno);
+ return -EACCES;
+ }
+ meta->mem_size = reg->var_off.value;
+ } else if (arg_type_is_int_ptr(arg_type)) {
+ int size = int_ptr_type_to_size(arg_type);
+
+ err = check_helper_mem_access(env, regno, size, false, meta);
+ if (err)
+ return err;
+ err = check_ptr_alignment(env, reg, 0, size, true);
}
return err;
-err_type:
- verbose(env, "R%d type=%s expected=%s\n", regno,
- reg_type_str[type], reg_type_str[expected_type]);
- return -EACCES;
+}
+
+static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
+{
+ enum bpf_attach_type eatype = env->prog->expected_attach_type;
+ enum bpf_prog_type type = resolve_prog_type(env->prog);
+
+ if (func_id != BPF_FUNC_map_update_elem)
+ return false;
+
+ /* It's not possible to get access to a locked struct sock in these
+ * contexts, so updating is safe.
+ */
+ switch (type) {
+ case BPF_PROG_TYPE_TRACING:
+ if (eatype == BPF_TRACE_ITER)
+ return true;
+ break;
+ case BPF_PROG_TYPE_SOCKET_FILTER:
+ case BPF_PROG_TYPE_SCHED_CLS:
+ case BPF_PROG_TYPE_SCHED_ACT:
+ case BPF_PROG_TYPE_XDP:
+ case BPF_PROG_TYPE_SK_REUSEPORT:
+ case BPF_PROG_TYPE_FLOW_DISSECTOR:
+ case BPF_PROG_TYPE_SK_LOOKUP:
+ return true;
+ default:
+ break;
+ }
+
+ verbose(env, "cannot update sockmap in this context\n");
+ return false;
+}
+
+static bool allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
+{
+ return env->prog->jit_requested && IS_ENABLED(CONFIG_X86_64);
}
static int check_map_func_compatibility(struct bpf_verifier_env *env,
@@ -2117,7 +4933,15 @@
case BPF_MAP_TYPE_PERF_EVENT_ARRAY:
if (func_id != BPF_FUNC_perf_event_read &&
func_id != BPF_FUNC_perf_event_output &&
- func_id != BPF_FUNC_perf_event_read_value)
+ func_id != BPF_FUNC_skb_output &&
+ func_id != BPF_FUNC_perf_event_read_value &&
+ func_id != BPF_FUNC_xdp_output)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_RINGBUF:
+ if (func_id != BPF_FUNC_ringbuf_output &&
+ func_id != BPF_FUNC_ringbuf_reserve &&
+ func_id != BPF_FUNC_ringbuf_query)
goto error;
break;
case BPF_MAP_TYPE_STACK_TRACE:
@@ -2130,23 +4954,26 @@
goto error;
break;
case BPF_MAP_TYPE_CGROUP_STORAGE:
+ case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
if (func_id != BPF_FUNC_get_local_storage)
goto error;
break;
- /* devmap returns a pointer to a live net_device ifindex that we cannot
- * allow to be modified from bpf side. So do not allow lookup elements
- * for now.
- */
case BPF_MAP_TYPE_DEVMAP:
- if (func_id != BPF_FUNC_redirect_map)
+ case BPF_MAP_TYPE_DEVMAP_HASH:
+ if (func_id != BPF_FUNC_redirect_map &&
+ func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
/* Restrict bpf side of cpumap and xskmap, open when use-cases
* appear.
*/
case BPF_MAP_TYPE_CPUMAP:
- case BPF_MAP_TYPE_XSKMAP:
if (func_id != BPF_FUNC_redirect_map)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_XSKMAP:
+ if (func_id != BPF_FUNC_redirect_map &&
+ func_id != BPF_FUNC_map_lookup_elem)
goto error;
break;
case BPF_MAP_TYPE_ARRAY_OF_MAPS:
@@ -2158,18 +4985,41 @@
if (func_id != BPF_FUNC_sk_redirect_map &&
func_id != BPF_FUNC_sock_map_update &&
func_id != BPF_FUNC_map_delete_elem &&
- func_id != BPF_FUNC_msg_redirect_map)
+ func_id != BPF_FUNC_msg_redirect_map &&
+ func_id != BPF_FUNC_sk_select_reuseport &&
+ func_id != BPF_FUNC_map_lookup_elem &&
+ !may_update_sockmap(env, func_id))
goto error;
break;
case BPF_MAP_TYPE_SOCKHASH:
if (func_id != BPF_FUNC_sk_redirect_hash &&
func_id != BPF_FUNC_sock_hash_update &&
func_id != BPF_FUNC_map_delete_elem &&
- func_id != BPF_FUNC_msg_redirect_hash)
+ func_id != BPF_FUNC_msg_redirect_hash &&
+ func_id != BPF_FUNC_sk_select_reuseport &&
+ func_id != BPF_FUNC_map_lookup_elem &&
+ !may_update_sockmap(env, func_id))
goto error;
break;
case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
if (func_id != BPF_FUNC_sk_select_reuseport)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_QUEUE:
+ case BPF_MAP_TYPE_STACK:
+ if (func_id != BPF_FUNC_map_peek_elem &&
+ func_id != BPF_FUNC_map_pop_elem &&
+ func_id != BPF_FUNC_map_push_elem)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_SK_STORAGE:
+ if (func_id != BPF_FUNC_sk_storage_get &&
+ func_id != BPF_FUNC_sk_storage_delete)
+ goto error;
+ break;
+ case BPF_MAP_TYPE_INODE_STORAGE:
+ if (func_id != BPF_FUNC_inode_storage_get &&
+ func_id != BPF_FUNC_inode_storage_delete)
goto error;
break;
default:
@@ -2181,15 +5031,23 @@
case BPF_FUNC_tail_call:
if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
goto error;
- if (env->subprog_cnt > 1) {
- verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
+ if (env->subprog_cnt > 1 && !allow_tail_call_in_subprogs(env)) {
+ verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
return -EINVAL;
}
break;
case BPF_FUNC_perf_event_read:
case BPF_FUNC_perf_event_output:
case BPF_FUNC_perf_event_read_value:
+ case BPF_FUNC_skb_output:
+ case BPF_FUNC_xdp_output:
if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
+ goto error;
+ break;
+ case BPF_FUNC_ringbuf_output:
+ case BPF_FUNC_ringbuf_reserve:
+ case BPF_FUNC_ringbuf_query:
+ if (map->map_type != BPF_MAP_TYPE_RINGBUF)
goto error;
break;
case BPF_FUNC_get_stackid:
@@ -2203,6 +5061,7 @@
break;
case BPF_FUNC_redirect_map:
if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
+ map->map_type != BPF_MAP_TYPE_DEVMAP_HASH &&
map->map_type != BPF_MAP_TYPE_CPUMAP &&
map->map_type != BPF_MAP_TYPE_XSKMAP)
goto error;
@@ -2220,11 +5079,31 @@
goto error;
break;
case BPF_FUNC_get_local_storage:
- if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+ if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
+ map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
goto error;
break;
case BPF_FUNC_sk_select_reuseport:
- if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+ if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
+ map->map_type != BPF_MAP_TYPE_SOCKMAP &&
+ map->map_type != BPF_MAP_TYPE_SOCKHASH)
+ goto error;
+ break;
+ case BPF_FUNC_map_peek_elem:
+ case BPF_FUNC_map_pop_elem:
+ case BPF_FUNC_map_push_elem:
+ if (map->map_type != BPF_MAP_TYPE_QUEUE &&
+ map->map_type != BPF_MAP_TYPE_STACK)
+ goto error;
+ break;
+ case BPF_FUNC_sk_storage_get:
+ case BPF_FUNC_sk_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
+ goto error;
+ break;
+ case BPF_FUNC_inode_storage_get:
+ case BPF_FUNC_inode_storage_delete:
+ if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
goto error;
break;
default:
@@ -2287,49 +5166,142 @@
return true;
}
-static int check_func_proto(const struct bpf_func_proto *fn)
+static bool check_refcount_ok(const struct bpf_func_proto *fn, int func_id)
+{
+ int count = 0;
+
+ if (arg_type_may_be_refcounted(fn->arg1_type))
+ count++;
+ if (arg_type_may_be_refcounted(fn->arg2_type))
+ count++;
+ if (arg_type_may_be_refcounted(fn->arg3_type))
+ count++;
+ if (arg_type_may_be_refcounted(fn->arg4_type))
+ count++;
+ if (arg_type_may_be_refcounted(fn->arg5_type))
+ count++;
+
+ /* A reference acquiring function cannot acquire
+ * another refcounted ptr.
+ */
+ if (may_be_acquire_function(func_id) && count)
+ return false;
+
+ /* We only support one arg being unreferenced at the moment,
+ * which is sufficient for the helper functions we have right now.
+ */
+ return count <= 1;
+}
+
+static bool check_btf_id_ok(const struct bpf_func_proto *fn)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
+ if (fn->arg_type[i] == ARG_PTR_TO_BTF_ID && !fn->arg_btf_id[i])
+ return false;
+
+ if (fn->arg_type[i] != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i])
+ return false;
+ }
+
+ return true;
+}
+
+static int check_func_proto(const struct bpf_func_proto *fn, int func_id)
{
return check_raw_mode_ok(fn) &&
- check_arg_pair_ok(fn) ? 0 : -EINVAL;
+ check_arg_pair_ok(fn) &&
+ check_btf_id_ok(fn) &&
+ check_refcount_ok(fn, func_id) ? 0 : -EINVAL;
}
/* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
* are now invalid, so turn them into unknown SCALAR_VALUE.
*/
-static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
- struct bpf_func_state *state)
-{
- struct bpf_reg_state *regs = state->regs, *reg;
- int i;
-
- for (i = 0; i < MAX_BPF_REG; i++)
- if (reg_is_pkt_pointer_any(®s[i]))
- mark_reg_unknown(env, regs, i);
-
- for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- if (state->stack[i].slot_type[0] != STACK_SPILL)
- continue;
- reg = &state->stack[i].spilled_ptr;
- if (reg_is_pkt_pointer_any(reg))
- __mark_reg_unknown(reg);
- }
-}
-
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
- struct bpf_verifier_state *vstate = env->cur_state;
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg_is_pkt_pointer_any(reg))
+ __mark_reg_unknown(env, reg);
+ }));
+}
+
+enum {
+ AT_PKT_END = -1,
+ BEYOND_PKT_END = -2,
+};
+
+static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
+{
+ struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ struct bpf_reg_state *reg = &state->regs[regn];
+
+ if (reg->type != PTR_TO_PACKET)
+ /* PTR_TO_PACKET_META is not supported yet */
+ return;
+
+ /* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
+ * How far beyond pkt_end it goes is unknown.
+ * if (!range_open) it's the case of pkt >= pkt_end
+ * if (range_open) it's the case of pkt > pkt_end
+ * hence this pointer is at least 1 byte bigger than pkt_end
+ */
+ if (range_open)
+ reg->range = BEYOND_PKT_END;
+ else
+ reg->range = AT_PKT_END;
+}
+
+/* The pointer with the specified id has released its reference to kernel
+ * resources. Identify all copies of the same pointer and clear the reference.
+ */
+static int release_reference(struct bpf_verifier_env *env,
+ int ref_obj_id)
+{
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+ int err;
+
+ err = release_reference_state(cur_func(env), ref_obj_id);
+ if (err)
+ return err;
+
+ bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
+ if (reg->ref_obj_id == ref_obj_id) {
+ if (!env->allow_ptr_leaks)
+ __mark_reg_not_init(env, reg);
+ else
+ __mark_reg_unknown(env, reg);
+ }
+ }));
+
+ return 0;
+}
+
+static void clear_caller_saved_regs(struct bpf_verifier_env *env,
+ struct bpf_reg_state *regs)
+{
int i;
- for (i = 0; i <= vstate->curframe; i++)
- __clear_all_pkt_pointers(env, vstate->frame[i]);
+ /* after the call registers r0 - r5 were scratched */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ mark_reg_not_init(env, regs, caller_saved[i]);
+ check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ }
}
static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
int *insn_idx)
{
struct bpf_verifier_state *state = env->cur_state;
+ struct bpf_func_info_aux *func_info_aux;
struct bpf_func_state *caller, *callee;
- int i, subprog, target_insn;
+ int i, err, subprog, target_insn;
+ bool is_global = false;
if (state->curframe + 1 >= MAX_CALL_FRAMES) {
verbose(env, "the call stack of %d frames is too deep\n",
@@ -2352,6 +5324,33 @@
return -EFAULT;
}
+ func_info_aux = env->prog->aux->func_info_aux;
+ if (func_info_aux)
+ is_global = func_info_aux[subprog].linkage == BTF_FUNC_GLOBAL;
+ err = btf_check_func_arg_match(env, subprog, caller->regs);
+ if (err == -EFAULT)
+ return err;
+ if (is_global) {
+ if (err) {
+ verbose(env, "Caller passes invalid args into func#%d\n",
+ subprog);
+ return err;
+ } else {
+ if (env->log.level & BPF_LOG_LEVEL)
+ verbose(env,
+ "Func#%d is global and valid. Skipping.\n",
+ subprog);
+ clear_caller_saved_regs(env, caller->regs);
+
+ /* All global functions return a 64-bit SCALAR_VALUE */
+ mark_reg_unknown(env, caller->regs, BPF_REG_0);
+ caller->regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
+ /* continue with next insn after call */
+ return 0;
+ }
+ }
+
callee = kzalloc(sizeof(*callee), GFP_KERNEL);
if (!callee)
return -ENOMEM;
@@ -2367,17 +5366,18 @@
state->curframe + 1 /* frameno within this callchain */,
subprog /* subprog number within this prog */);
+ /* Transfer references to the callee */
+ err = transfer_reference_state(callee, caller);
+ if (err)
+ return err;
+
/* copy r1 - r5 args that callee can access. The copy includes parent
* pointers, which connects us up to the liveness chain
*/
for (i = BPF_REG_1; i <= BPF_REG_5; i++)
callee->regs[i] = caller->regs[i];
- /* after the call registers r0 - r5 were scratched */
- for (i = 0; i < CALLER_SAVED_REGS; i++) {
- mark_reg_not_init(env, caller->regs, caller_saved[i]);
- check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
- }
+ clear_caller_saved_regs(env, caller->regs);
/* only increment it after check_reg_arg() finished */
state->curframe++;
@@ -2385,7 +5385,7 @@
/* and go analyze first insn of the callee */
*insn_idx = target_insn;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "caller:\n");
print_verifier_state(env, caller);
verbose(env, "callee:\n");
@@ -2399,6 +5399,7 @@
struct bpf_verifier_state *state = env->cur_state;
struct bpf_func_state *caller, *callee;
struct bpf_reg_state *r0;
+ int err;
callee = state->frame[state->curframe];
r0 = &callee->regs[BPF_REG_0];
@@ -2418,8 +5419,13 @@
/* return to the caller whatever r0 had in the callee */
caller->regs[BPF_REG_0] = *r0;
+ /* Transfer references to the caller */
+ err = transfer_reference_state(caller, callee);
+ if (err)
+ return err;
+
*insn_idx = callee->callsite + 1;
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
verbose(env, "returning from callee:\n");
print_verifier_state(env, callee);
verbose(env, "to caller at %d:\n", *insn_idx);
@@ -2431,44 +5437,24 @@
return 0;
}
-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)
+static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type,
+ int func_id,
+ struct bpf_call_arg_meta *meta)
{
struct bpf_reg_state *ret_reg = ®s[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 0;
+ func_id != BPF_FUNC_probe_read_str &&
+ func_id != BPF_FUNC_probe_read_kernel_str &&
+ func_id != BPF_FUNC_probe_read_user_str))
+ return;
- /* 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;
-
- __reg_deduce_bounds(ret_reg);
- __reg_bound_offset(ret_reg);
- __update_reg_bounds(ret_reg);
-
- return 0;
+ ret_reg->s32_max_value = meta->msize_max_value;
+ ret_reg->smin_value = -MAX_ERRNO;
+ ret_reg->s32_min_value = -MAX_ERRNO;
+ reg_bounds_sync(ret_reg);
}
static int
@@ -2476,25 +5462,91 @@
int func_id, int insn_idx)
{
struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+ struct bpf_map *map = meta->map_ptr;
if (func_id != BPF_FUNC_tail_call &&
func_id != BPF_FUNC_map_lookup_elem &&
func_id != BPF_FUNC_map_update_elem &&
- func_id != BPF_FUNC_map_delete_elem)
+ func_id != BPF_FUNC_map_delete_elem &&
+ func_id != BPF_FUNC_map_push_elem &&
+ func_id != BPF_FUNC_map_pop_elem &&
+ func_id != BPF_FUNC_map_peek_elem)
return 0;
- if (meta->map_ptr == NULL) {
+ if (map == NULL) {
verbose(env, "kernel subsystem misconfigured verifier\n");
return -EINVAL;
}
- if (!BPF_MAP_PTR(aux->map_state))
+ /* In case of read-only, some additional restrictions
+ * need to be applied in order to prevent altering the
+ * state of the map from program side.
+ */
+ if ((map->map_flags & BPF_F_RDONLY_PROG) &&
+ (func_id == BPF_FUNC_map_delete_elem ||
+ func_id == BPF_FUNC_map_update_elem ||
+ func_id == BPF_FUNC_map_push_elem ||
+ func_id == BPF_FUNC_map_pop_elem)) {
+ verbose(env, "write into map forbidden\n");
+ return -EACCES;
+ }
+
+ if (!BPF_MAP_PTR(aux->map_ptr_state))
bpf_map_ptr_store(aux, meta->map_ptr,
- meta->map_ptr->unpriv_array);
- else if (BPF_MAP_PTR(aux->map_state) != meta->map_ptr)
+ !meta->map_ptr->bypass_spec_v1);
+ else if (BPF_MAP_PTR(aux->map_ptr_state) != meta->map_ptr)
bpf_map_ptr_store(aux, BPF_MAP_PTR_POISON,
- meta->map_ptr->unpriv_array);
+ !meta->map_ptr->bypass_spec_v1);
return 0;
+}
+
+static int
+record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
+ int func_id, int insn_idx)
+{
+ struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
+ struct bpf_reg_state *regs = cur_regs(env), *reg;
+ struct bpf_map *map = meta->map_ptr;
+ u64 val, max;
+ int err;
+
+ if (func_id != BPF_FUNC_tail_call)
+ return 0;
+ if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) {
+ verbose(env, "kernel subsystem misconfigured verifier\n");
+ return -EINVAL;
+ }
+
+ reg = ®s[BPF_REG_3];
+ val = reg->var_off.value;
+ max = map->max_entries;
+
+ if (!(register_is_const(reg) && val < max)) {
+ bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
+ return 0;
+ }
+
+ err = mark_chain_precision(env, BPF_REG_3);
+ if (err)
+ return err;
+ if (bpf_map_key_unseen(aux))
+ bpf_map_key_store(aux, val);
+ else if (!bpf_map_key_poisoned(aux) &&
+ bpf_map_key_immediate(aux) != val)
+ bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
+ return 0;
+}
+
+static int check_reference_leak(struct bpf_verifier_env *env)
+{
+ struct bpf_func_state *state = cur_func(env);
+ int i;
+
+ for (i = 0; i < state->acquired_refs; i++) {
+ verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
+ state->refs[i].id, state->refs[i].insn_idx);
+ }
+ return state->acquired_refs ? -EINVAL : 0;
}
static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
@@ -2526,6 +5578,11 @@
return -EINVAL;
}
+ if (fn->allowed && !fn->allowed(env->prog)) {
+ verbose(env, "helper call is not allowed in probe\n");
+ return -EINVAL;
+ }
+
/* With LD_ABS/IND some JITs save/restore skb from r1. */
changes_data = bpf_helper_changes_pkt_data(fn->func);
if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
@@ -2537,31 +5594,26 @@
memset(&meta, 0, sizeof(meta));
meta.pkt_access = fn->pkt_access;
- err = check_func_proto(fn);
+ err = check_func_proto(fn, func_id);
if (err) {
verbose(env, "kernel subsystem misconfigured func %s#%d\n",
func_id_name(func_id), func_id);
return err;
}
+ meta.func_id = func_id;
/* check args */
- err = check_func_arg(env, BPF_REG_1, fn->arg1_type, &meta);
- if (err)
- return err;
- err = check_func_arg(env, BPF_REG_2, fn->arg2_type, &meta);
- if (err)
- return err;
- err = check_func_arg(env, BPF_REG_3, fn->arg3_type, &meta);
- if (err)
- return err;
- err = check_func_arg(env, BPF_REG_4, fn->arg4_type, &meta);
- if (err)
- return err;
- err = check_func_arg(env, BPF_REG_5, fn->arg5_type, &meta);
+ for (i = 0; i < 5; i++) {
+ err = check_func_arg(env, i, &meta, fn);
+ if (err)
+ return err;
+ }
+
+ err = record_func_map(env, &meta, func_id, insn_idx);
if (err)
return err;
- err = record_func_map(env, &meta, func_id, insn_idx);
+ err = record_func_key(env, &meta, func_id, insn_idx);
if (err)
return err;
@@ -2573,6 +5625,21 @@
BPF_WRITE, -1, false);
if (err)
return err;
+ }
+
+ if (func_id == BPF_FUNC_tail_call) {
+ err = check_reference_leak(env);
+ if (err) {
+ verbose(env, "tail_call would lead to reference leak\n");
+ return err;
+ }
+ } else if (is_release_function(func_id)) {
+ err = release_reference(env, meta.ref_obj_id);
+ if (err) {
+ verbose(env, "func %s#%d reference has not been acquired before\n",
+ func_id_name(func_id), func_id);
+ return err;
+ }
}
regs = cur_regs(env);
@@ -2592,6 +5659,9 @@
check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
}
+ /* helper call returns 64-bit value. */
+ regs[BPF_REG_0].subreg_def = DEF_NOT_SUBREG;
+
/* update return register (already marked as written above) */
if (fn->ret_type == RET_INTEGER) {
/* sets type to SCALAR_VALUE */
@@ -2600,10 +5670,6 @@
regs[BPF_REG_0].type = NOT_INIT;
} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
fn->ret_type == RET_PTR_TO_MAP_VALUE) {
- if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
- else
- regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
/* There is no offset yet applied, variable or fixed */
mark_reg_known_zero(env, regs, BPF_REG_0);
/* remember map_ptr, so that check_map_access()
@@ -2616,22 +5682,99 @@
return -EINVAL;
}
regs[BPF_REG_0].map_ptr = meta.map_ptr;
- regs[BPF_REG_0].id = ++env->id_gen;
+ if (fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+ if (map_value_has_spin_lock(meta.map_ptr))
+ regs[BPF_REG_0].id = ++env->id_gen;
+ } else {
+ regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+ }
+ } else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
+ } else if (fn->ret_type == RET_PTR_TO_ALLOC_MEM_OR_NULL) {
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].mem_size = meta.mem_size;
+ } else if (fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL ||
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID) {
+ const struct btf_type *t;
+
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL);
+ if (!btf_type_is_struct(t)) {
+ u32 tsize;
+ const struct btf_type *ret;
+ const char *tname;
+
+ /* resolve the type size of ksym. */
+ ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+ if (IS_ERR(ret)) {
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ verbose(env, "unable to resolve the size of type '%s': %ld\n",
+ tname, PTR_ERR(ret));
+ return -EINVAL;
+ }
+ regs[BPF_REG_0].type =
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+ PTR_TO_MEM : PTR_TO_MEM_OR_NULL;
+ regs[BPF_REG_0].mem_size = tsize;
+ } else {
+ regs[BPF_REG_0].type =
+ fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ?
+ PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL;
+ regs[BPF_REG_0].btf_id = meta.ret_btf_id;
+ }
+ } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL) {
+ int ret_btf_id;
+
+ mark_reg_known_zero(env, regs, BPF_REG_0);
+ regs[BPF_REG_0].type = PTR_TO_BTF_ID_OR_NULL;
+ ret_btf_id = *fn->ret_btf_id;
+ if (ret_btf_id == 0) {
+ verbose(env, "invalid return type %d of func %s#%d\n",
+ fn->ret_type, func_id_name(func_id), func_id);
+ return -EINVAL;
+ }
+ regs[BPF_REG_0].btf_id = ret_btf_id;
} else {
verbose(env, "unknown return type %d of func %s#%d\n",
fn->ret_type, func_id_name(func_id), func_id);
return -EINVAL;
}
- err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
- if (err)
- return err;
+ if (reg_type_may_be_null(regs[BPF_REG_0].type))
+ regs[BPF_REG_0].id = ++env->id_gen;
+
+ if (is_ptr_cast_function(func_id)) {
+ /* For release_reference() */
+ regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+ } else if (is_acquire_function(func_id, meta.map_ptr)) {
+ int id = acquire_reference_state(env, insn_idx);
+
+ if (id < 0)
+ return id;
+ /* For mark_ptr_or_null_reg() */
+ regs[BPF_REG_0].id = id;
+ /* For release_reference() */
+ regs[BPF_REG_0].ref_obj_id = id;
+ }
+
+ do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
err = check_map_func_compatibility(env, meta.map_ptr, func_id);
if (err)
return err;
- if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) {
+ if ((func_id == BPF_FUNC_get_stack ||
+ func_id == BPF_FUNC_get_task_stack) &&
+ !env->prog->has_callchain_buf) {
const char *err_str;
#ifdef CONFIG_PERF_EVENTS
@@ -2649,6 +5792,9 @@
env->prog->has_callchain_buf = true;
}
+ if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
+ env->prog->call_get_stack = true;
+
if (changes_data)
clear_all_pkt_pointers(env);
return 0;
@@ -2664,10 +5810,30 @@
return res < a;
}
+static bool signed_add32_overflows(s32 a, s32 b)
+{
+ /* Do the add in u32, where overflow is well-defined */
+ s32 res = (s32)((u32)a + (u32)b);
+
+ if (b < 0)
+ return res > a;
+ return res < a;
+}
+
static bool signed_sub_overflows(s64 a, s64 b)
{
/* Do the sub in u64, where overflow is well-defined */
s64 res = (s64)((u64)a - (u64)b);
+
+ if (b < 0)
+ return res < a;
+ return res > a;
+}
+
+static bool signed_sub32_overflows(s32 a, s32 b)
+{
+ /* Do the sub in u32, where overflow is well-defined */
+ s32 res = (s32)((u32)a - (u32)b);
if (b < 0)
return res < a;
@@ -2756,7 +5922,7 @@
static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
const struct bpf_insn *insn)
{
- return env->allow_ptr_leaks || BPF_SRC(insn->code) == BPF_K;
+ return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
}
static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -2905,7 +6071,7 @@
*/
if (!ptr_is_dst_reg) {
tmp = *dst_reg;
- *dst_reg = *ptr_reg;
+ copy_register_state(dst_reg, ptr_reg);
}
ret = sanitize_speculative_path(env, NULL, env->insn_idx + 1,
env->insn_idx);
@@ -2924,7 +6090,7 @@
* rewrite/sanitize them.
*/
if (!vstate->speculative)
- env->insn_aux_data[env->insn_idx].seen = true;
+ env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
}
static int sanitize_err(struct bpf_verifier_env *env,
@@ -2966,6 +6132,40 @@
return -EACCES;
}
+/* check that stack access falls within stack limits and that 'reg' doesn't
+ * have a variable offset.
+ *
+ * Variable offset is prohibited for unprivileged mode for simplicity since it
+ * requires corresponding support in Spectre masking for stack ALU. See also
+ * retrieve_ptr_limit().
+ *
+ *
+ * 'off' includes 'reg->off'.
+ */
+static int check_stack_access_for_ptr_arithmetic(
+ struct bpf_verifier_env *env,
+ int regno,
+ const struct bpf_reg_state *reg,
+ int off)
+{
+ if (!tnum_is_const(reg->var_off)) {
+ char tn_buf[48];
+
+ tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
+ verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n",
+ regno, tn_buf, off);
+ return -EACCES;
+ }
+
+ if (off >= 0 || off < -MAX_BPF_STACK) {
+ verbose(env, "R%d stack pointer arithmetic goes out of range, "
+ "prohibited for !root; off=%d\n", regno, off);
+ return -EACCES;
+ }
+
+ return 0;
+}
+
static int sanitize_check_bounds(struct bpf_verifier_env *env,
const struct bpf_insn *insn,
const struct bpf_reg_state *dst_reg)
@@ -2975,17 +6175,14 @@
/* For unprivileged we require that resulting offset must be in bounds
* in order to be able to sanitize access later on.
*/
- if (env->allow_ptr_leaks)
+ if (env->bypass_spec_v1)
return 0;
switch (dst_reg->type) {
case PTR_TO_STACK:
- if (check_stack_access(env, dst_reg, dst_reg->off +
- dst_reg->var_off.value, 1)) {
- verbose(env, "R%d stack pointer arithmetic goes out of range, "
- "prohibited for !root\n", dst);
+ 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)) {
@@ -3031,32 +6228,46 @@
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
if (BPF_CLASS(insn->code) != BPF_ALU64) {
/* 32-bit ALU ops on pointers produce (meaningless) scalars */
+ if (opcode == BPF_SUB && env->allow_ptr_leaks) {
+ __mark_reg_unknown(env, dst_reg);
+ return 0;
+ }
+
verbose(env,
"R%d 32-bit pointer arithmetic prohibited\n",
dst);
return -EACCES;
}
- if (ptr_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
- verbose(env, "R%d pointer arithmetic on PTR_TO_MAP_VALUE_OR_NULL prohibited, null-check it first\n",
- dst);
+ switch (ptr_reg->type) {
+ case PTR_TO_MAP_VALUE_OR_NULL:
+ verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
+ dst, reg_type_str[ptr_reg->type]);
return -EACCES;
- }
- if (ptr_reg->type == CONST_PTR_TO_MAP) {
- verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
- dst);
+ case CONST_PTR_TO_MAP:
+ /* smin_val represents the known value */
+ if (known && smin_val == 0 && opcode == BPF_ADD)
+ break;
+ fallthrough;
+ case PTR_TO_PACKET_END:
+ case PTR_TO_SOCKET:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_XDP_SOCK:
+reject:
+ verbose(env, "R%d pointer arithmetic on %s prohibited\n",
+ dst, reg_type_str[ptr_reg->type]);
return -EACCES;
- }
- if (ptr_reg->type == PTR_TO_PACKET_END) {
- verbose(env, "R%d pointer arithmetic on PTR_TO_PACKET_END prohibited\n",
- dst);
- return -EACCES;
+ default:
+ if (reg_type_may_be_null(ptr_reg->type))
+ goto reject;
+ break;
}
/* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
@@ -3068,6 +6279,9 @@
if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
!check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
return -EINVAL;
+
+ /* 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,
@@ -3203,11 +6417,7 @@
if (!check_reg_sane_offset(env, dst_reg, ptr_reg->type))
return -EINVAL;
-
- __update_reg_bounds(dst_reg);
- __reg_deduce_bounds(dst_reg);
- __reg_bound_offset(dst_reg);
-
+ reg_bounds_sync(dst_reg);
if (sanitize_check_bounds(env, insn, dst_reg) < 0)
return -EACCES;
if (sanitize_needed(opcode)) {
@@ -3218,6 +6428,573 @@
}
return 0;
+}
+
+static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s32 smin_val = src_reg->s32_min_value;
+ s32 smax_val = src_reg->s32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+
+ if (signed_add32_overflows(dst_reg->s32_min_value, smin_val) ||
+ signed_add32_overflows(dst_reg->s32_max_value, smax_val)) {
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ } else {
+ dst_reg->s32_min_value += smin_val;
+ dst_reg->s32_max_value += smax_val;
+ }
+ if (dst_reg->u32_min_value + umin_val < umin_val ||
+ dst_reg->u32_max_value + umax_val < umax_val) {
+ dst_reg->u32_min_value = 0;
+ dst_reg->u32_max_value = U32_MAX;
+ } else {
+ dst_reg->u32_min_value += umin_val;
+ dst_reg->u32_max_value += umax_val;
+ }
+}
+
+static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s64 smin_val = src_reg->smin_value;
+ s64 smax_val = src_reg->smax_value;
+ u64 umin_val = src_reg->umin_value;
+ u64 umax_val = src_reg->umax_value;
+
+ if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
+ signed_add_overflows(dst_reg->smax_value, smax_val)) {
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value += smin_val;
+ dst_reg->smax_value += smax_val;
+ }
+ if (dst_reg->umin_value + umin_val < umin_val ||
+ dst_reg->umax_value + umax_val < umax_val) {
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ dst_reg->umin_value += umin_val;
+ dst_reg->umax_value += umax_val;
+ }
+}
+
+static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s32 smin_val = src_reg->s32_min_value;
+ s32 smax_val = src_reg->s32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+
+ if (signed_sub32_overflows(dst_reg->s32_min_value, smax_val) ||
+ signed_sub32_overflows(dst_reg->s32_max_value, smin_val)) {
+ /* Overflow possible, we know nothing */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ } else {
+ dst_reg->s32_min_value -= smax_val;
+ dst_reg->s32_max_value -= smin_val;
+ }
+ if (dst_reg->u32_min_value < umax_val) {
+ /* Overflow possible, we know nothing */
+ dst_reg->u32_min_value = 0;
+ dst_reg->u32_max_value = U32_MAX;
+ } else {
+ /* Cannot overflow (as long as bounds are consistent) */
+ dst_reg->u32_min_value -= umax_val;
+ dst_reg->u32_max_value -= umin_val;
+ }
+}
+
+static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s64 smin_val = src_reg->smin_value;
+ s64 smax_val = src_reg->smax_value;
+ u64 umin_val = src_reg->umin_value;
+ u64 umax_val = src_reg->umax_value;
+
+ if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
+ signed_sub_overflows(dst_reg->smax_value, smin_val)) {
+ /* Overflow possible, we know nothing */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value -= smax_val;
+ dst_reg->smax_value -= smin_val;
+ }
+ if (dst_reg->umin_value < umax_val) {
+ /* Overflow possible, we know nothing */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ /* Cannot overflow (as long as bounds are consistent) */
+ dst_reg->umin_value -= umax_val;
+ dst_reg->umax_value -= umin_val;
+ }
+}
+
+static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+
+ if (smin_val < 0 || dst_reg->s32_min_value < 0) {
+ /* Ain't nobody got time to multiply that sign */
+ __mark_reg32_unbounded(dst_reg);
+ return;
+ }
+ /* Both values are positive, so we can work with unsigned and
+ * copy the result to signed (unless it exceeds S32_MAX).
+ */
+ if (umax_val > U16_MAX || dst_reg->u32_max_value > U16_MAX) {
+ /* Potential overflow, we know nothing */
+ __mark_reg32_unbounded(dst_reg);
+ return;
+ }
+ dst_reg->u32_min_value *= umin_val;
+ dst_reg->u32_max_value *= umax_val;
+ if (dst_reg->u32_max_value > S32_MAX) {
+ /* Overflow possible, we know nothing */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ } else {
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
+ }
+}
+
+static void scalar_min_max_mul(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ s64 smin_val = src_reg->smin_value;
+ u64 umin_val = src_reg->umin_value;
+ u64 umax_val = src_reg->umax_value;
+
+ if (smin_val < 0 || dst_reg->smin_value < 0) {
+ /* Ain't nobody got time to multiply that sign */
+ __mark_reg64_unbounded(dst_reg);
+ return;
+ }
+ /* Both values are positive, so we can work with unsigned and
+ * copy the result to signed (unless it exceeds S64_MAX).
+ */
+ if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
+ /* Potential overflow, we know nothing */
+ __mark_reg64_unbounded(dst_reg);
+ return;
+ }
+ dst_reg->umin_value *= umin_val;
+ dst_reg->umax_value *= umax_val;
+ if (dst_reg->umax_value > S64_MAX) {
+ /* Overflow possible, we know nothing */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+}
+
+static void scalar32_min_max_and(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_subreg_is_const(src_reg->var_off);
+ bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
+ struct tnum var32_off = tnum_subreg(dst_reg->var_off);
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umax_val = src_reg->u32_max_value;
+
+ if (src_known && dst_known) {
+ __mark_reg32_known(dst_reg, var32_off.value);
+ return;
+ }
+
+ /* We get our minimum from the var_off, since that's inherently
+ * bitwise. Our maximum is the minimum of the operands' maxima.
+ */
+ dst_reg->u32_min_value = var32_off.value;
+ dst_reg->u32_max_value = min(dst_reg->u32_max_value, umax_val);
+ if (dst_reg->s32_min_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ANDing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ } else {
+ /* ANDing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
+ }
+}
+
+static void scalar_min_max_and(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_is_const(src_reg->var_off);
+ bool dst_known = tnum_is_const(dst_reg->var_off);
+ s64 smin_val = src_reg->smin_value;
+ u64 umax_val = src_reg->umax_value;
+
+ if (src_known && dst_known) {
+ __mark_reg_known(dst_reg, dst_reg->var_off.value);
+ return;
+ }
+
+ /* We get our minimum from the var_off, since that's inherently
+ * bitwise. Our maximum is the minimum of the operands' maxima.
+ */
+ dst_reg->umin_value = dst_reg->var_off.value;
+ dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
+ if (dst_reg->smin_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ANDing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ /* ANDing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_subreg_is_const(src_reg->var_off);
+ bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
+ struct tnum var32_off = tnum_subreg(dst_reg->var_off);
+ s32 smin_val = src_reg->s32_min_value;
+ u32 umin_val = src_reg->u32_min_value;
+
+ if (src_known && dst_known) {
+ __mark_reg32_known(dst_reg, var32_off.value);
+ return;
+ }
+
+ /* We get our maximum from the var_off, and our minimum is the
+ * maximum of the operands' minima
+ */
+ dst_reg->u32_min_value = max(dst_reg->u32_min_value, umin_val);
+ dst_reg->u32_max_value = var32_off.value | var32_off.mask;
+ if (dst_reg->s32_min_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ORing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ } else {
+ /* ORing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
+ }
+}
+
+static void scalar_min_max_or(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_is_const(src_reg->var_off);
+ bool dst_known = tnum_is_const(dst_reg->var_off);
+ s64 smin_val = src_reg->smin_value;
+ u64 umin_val = src_reg->umin_value;
+
+ if (src_known && dst_known) {
+ __mark_reg_known(dst_reg, dst_reg->var_off.value);
+ return;
+ }
+
+ /* We get our maximum from the var_off, and our minimum is the
+ * maximum of the operands' minima
+ */
+ dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
+ dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask;
+ if (dst_reg->smin_value < 0 || smin_val < 0) {
+ /* Lose signed bounds when ORing negative numbers,
+ * ain't nobody got time for that.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ } else {
+ /* ORing two positives gives a positive, so safe to
+ * cast result into s64.
+ */
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ }
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_subreg_is_const(src_reg->var_off);
+ bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
+ struct tnum var32_off = tnum_subreg(dst_reg->var_off);
+ s32 smin_val = src_reg->s32_min_value;
+
+ if (src_known && dst_known) {
+ __mark_reg32_known(dst_reg, var32_off.value);
+ return;
+ }
+
+ /* We get both minimum and maximum from the var32_off. */
+ dst_reg->u32_min_value = var32_off.value;
+ dst_reg->u32_max_value = var32_off.value | var32_off.mask;
+
+ if (dst_reg->s32_min_value >= 0 && smin_val >= 0) {
+ /* XORing two positive sign numbers gives a positive,
+ * so safe to cast u32 result into s32.
+ */
+ dst_reg->s32_min_value = dst_reg->u32_min_value;
+ dst_reg->s32_max_value = dst_reg->u32_max_value;
+ } else {
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ }
+}
+
+static void scalar_min_max_xor(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ bool src_known = tnum_is_const(src_reg->var_off);
+ bool dst_known = tnum_is_const(dst_reg->var_off);
+ s64 smin_val = src_reg->smin_value;
+
+ if (src_known && dst_known) {
+ /* dst_reg->var_off.value has been updated earlier */
+ __mark_reg_known(dst_reg, dst_reg->var_off.value);
+ return;
+ }
+
+ /* We get both minimum and maximum from the var_off. */
+ dst_reg->umin_value = dst_reg->var_off.value;
+ dst_reg->umax_value = dst_reg->var_off.value | dst_reg->var_off.mask;
+
+ if (dst_reg->smin_value >= 0 && smin_val >= 0) {
+ /* XORing two positive sign numbers gives a positive,
+ * so safe to cast u64 result into s64.
+ */
+ dst_reg->smin_value = dst_reg->umin_value;
+ dst_reg->smax_value = dst_reg->umax_value;
+ } else {
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ }
+
+ __update_reg_bounds(dst_reg);
+}
+
+static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
+ u64 umin_val, u64 umax_val)
+{
+ /* We lose all sign bit information (except what we can pick
+ * up from var_off)
+ */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+ /* If we might shift our top bit out, then we know nothing */
+ if (umax_val > 31 || dst_reg->u32_max_value > 1ULL << (31 - umax_val)) {
+ dst_reg->u32_min_value = 0;
+ dst_reg->u32_max_value = U32_MAX;
+ } else {
+ dst_reg->u32_min_value <<= umin_val;
+ dst_reg->u32_max_value <<= umax_val;
+ }
+}
+
+static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ u32 umax_val = src_reg->u32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+ /* u32 alu operation will zext upper bits */
+ struct tnum subreg = tnum_subreg(dst_reg->var_off);
+
+ __scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
+ dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val));
+ /* Not required but being careful mark reg64 bounds as unknown so
+ * that we are forced to pick them up from tnum and zext later and
+ * if some path skips this step we are still safe.
+ */
+ __mark_reg64_unbounded(dst_reg);
+ __update_reg32_bounds(dst_reg);
+}
+
+static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg,
+ u64 umin_val, u64 umax_val)
+{
+ /* Special case <<32 because it is a common compiler pattern to sign
+ * extend subreg by doing <<32 s>>32. In this case if 32bit bounds are
+ * positive we know this shift will also be positive so we can track
+ * bounds correctly. Otherwise we lose all sign bit information except
+ * what we can pick up from var_off. Perhaps we can generalize this
+ * later to shifts of any length.
+ */
+ if (umin_val == 32 && umax_val == 32 && dst_reg->s32_max_value >= 0)
+ dst_reg->smax_value = (s64)dst_reg->s32_max_value << 32;
+ else
+ dst_reg->smax_value = S64_MAX;
+
+ if (umin_val == 32 && umax_val == 32 && dst_reg->s32_min_value >= 0)
+ dst_reg->smin_value = (s64)dst_reg->s32_min_value << 32;
+ else
+ dst_reg->smin_value = S64_MIN;
+
+ /* If we might shift our top bit out, then we know nothing */
+ if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+ } else {
+ dst_reg->umin_value <<= umin_val;
+ dst_reg->umax_value <<= umax_val;
+ }
+}
+
+static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ u64 umax_val = src_reg->umax_value;
+ u64 umin_val = src_reg->umin_value;
+
+ /* scalar64 calc uses 32bit unshifted bounds so must be called first */
+ __scalar64_min_max_lsh(dst_reg, umin_val, umax_val);
+ __scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
+
+ dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
+ /* We may learn something more from the var_off */
+ __update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ struct tnum subreg = tnum_subreg(dst_reg->var_off);
+ u32 umax_val = src_reg->u32_max_value;
+ u32 umin_val = src_reg->u32_min_value;
+
+ /* BPF_RSH is an unsigned shift. If the value in dst_reg might
+ * be negative, then either:
+ * 1) src_reg might be zero, so the sign bit of the result is
+ * unknown, so we lose our signed bounds
+ * 2) it's known negative, thus the unsigned bounds capture the
+ * signed bounds
+ * 3) the signed bounds cross zero, so they tell us nothing
+ * about the result
+ * If the value in dst_reg is known nonnegative, then again the
+ * unsigned bounts capture the signed bounds.
+ * Thus, in all cases it suffices to blow away our signed bounds
+ * and rely on inferring new ones from the unsigned bounds and
+ * var_off of the result.
+ */
+ dst_reg->s32_min_value = S32_MIN;
+ dst_reg->s32_max_value = S32_MAX;
+
+ dst_reg->var_off = tnum_rshift(subreg, umin_val);
+ dst_reg->u32_min_value >>= umax_val;
+ dst_reg->u32_max_value >>= umin_val;
+
+ __mark_reg64_unbounded(dst_reg);
+ __update_reg32_bounds(dst_reg);
+}
+
+static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ u64 umax_val = src_reg->umax_value;
+ u64 umin_val = src_reg->umin_value;
+
+ /* BPF_RSH is an unsigned shift. If the value in dst_reg might
+ * be negative, then either:
+ * 1) src_reg might be zero, so the sign bit of the result is
+ * unknown, so we lose our signed bounds
+ * 2) it's known negative, thus the unsigned bounds capture the
+ * signed bounds
+ * 3) the signed bounds cross zero, so they tell us nothing
+ * about the result
+ * If the value in dst_reg is known nonnegative, then again the
+ * unsigned bounts capture the signed bounds.
+ * Thus, in all cases it suffices to blow away our signed bounds
+ * and rely on inferring new ones from the unsigned bounds and
+ * var_off of the result.
+ */
+ dst_reg->smin_value = S64_MIN;
+ dst_reg->smax_value = S64_MAX;
+ dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
+ dst_reg->umin_value >>= umax_val;
+ dst_reg->umax_value >>= umin_val;
+
+ /* Its not easy to operate on alu32 bounds here because it depends
+ * on bits being shifted in. Take easy way out and mark unbounded
+ * so we can recalculate later from tnum.
+ */
+ __mark_reg32_unbounded(dst_reg);
+ __update_reg_bounds(dst_reg);
+}
+
+static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ u64 umin_val = src_reg->u32_min_value;
+
+ /* Upon reaching here, src_known is true and
+ * umax_val is equal to umin_val.
+ */
+ dst_reg->s32_min_value = (u32)(((s32)dst_reg->s32_min_value) >> umin_val);
+ dst_reg->s32_max_value = (u32)(((s32)dst_reg->s32_max_value) >> umin_val);
+
+ dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32);
+
+ /* blow away the dst_reg umin_value/umax_value and rely on
+ * dst_reg var_off to refine the result.
+ */
+ dst_reg->u32_min_value = 0;
+ dst_reg->u32_max_value = U32_MAX;
+
+ __mark_reg64_unbounded(dst_reg);
+ __update_reg32_bounds(dst_reg);
+}
+
+static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg)
+{
+ u64 umin_val = src_reg->umin_value;
+
+ /* Upon reaching here, src_known is true and umax_val is equal
+ * to umin_val.
+ */
+ dst_reg->smin_value >>= umin_val;
+ dst_reg->smax_value >>= umin_val;
+
+ dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64);
+
+ /* blow away the dst_reg umin_value/umax_value and rely on
+ * dst_reg var_off to refine the result.
+ */
+ dst_reg->umin_value = 0;
+ dst_reg->umax_value = U64_MAX;
+
+ /* Its not easy to operate on alu32 bounds here because it depends
+ * on bits being shifted in from upper 32-bits. Take easy way out
+ * and mark unbounded so we can recalculate later from tnum.
+ */
+ __mark_reg32_unbounded(dst_reg);
+ __update_reg_bounds(dst_reg);
}
/* WARNING: This function does calculations on 64-bit values, but the actual
@@ -3231,40 +7008,52 @@
{
struct bpf_reg_state *regs = cur_regs(env);
u8 opcode = BPF_OP(insn->code);
- bool src_known, dst_known;
+ bool src_known;
s64 smin_val, smax_val;
u64 umin_val, umax_val;
+ 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;
+ bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
int ret;
-
- if (insn_bitness == 32) {
- /* Relevant for 32-bit RSH: Information can propagate towards
- * LSB, so it isn't sufficient to only truncate the output to
- * 32 bits.
- */
- coerce_reg_to_size(dst_reg, 4);
- coerce_reg_to_size(&src_reg, 4);
- }
smin_val = src_reg.smin_value;
smax_val = src_reg.smax_value;
umin_val = src_reg.umin_value;
umax_val = src_reg.umax_value;
- src_known = tnum_is_const(src_reg.var_off);
- dst_known = tnum_is_const(dst_reg->var_off);
- if ((src_known && (smin_val != smax_val || umin_val != umax_val)) ||
- smin_val > smax_val || umin_val > umax_val) {
- /* Taint dst register if offset had invalid bounds derived from
- * e.g. dead branches.
- */
- __mark_reg_unknown(dst_reg);
- return 0;
+ s32_min_val = src_reg.s32_min_value;
+ s32_max_val = src_reg.s32_max_value;
+ u32_min_val = src_reg.u32_min_value;
+ u32_max_val = src_reg.u32_max_value;
+
+ if (alu32) {
+ src_known = tnum_subreg_is_const(src_reg.var_off);
+ if ((src_known &&
+ (s32_min_val != s32_max_val || u32_min_val != u32_max_val)) ||
+ s32_min_val > s32_max_val || u32_min_val > u32_max_val) {
+ /* Taint dst register if offset had invalid bounds
+ * derived from e.g. dead branches.
+ */
+ __mark_reg_unknown(env, dst_reg);
+ return 0;
+ }
+ } else {
+ src_known = tnum_is_const(src_reg.var_off);
+ if ((src_known &&
+ (smin_val != smax_val || umin_val != umax_val)) ||
+ smin_val > smax_val || umin_val > umax_val) {
+ /* Taint dst register if offset had invalid bounds
+ * derived from e.g. dead branches.
+ */
+ __mark_reg_unknown(env, dst_reg);
+ return 0;
+ }
}
if (!src_known &&
opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
@@ -3274,132 +7063,50 @@
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
+ * greatest amount of precision when alu operations are mixed with jmp32
+ * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD,
+ * and BPF_OR. This is possible because these ops have fairly easy to
+ * understand and calculate behavior in both 32-bit and 64-bit alu ops.
+ * See alu32 verifier tests for examples. The second class of
+ * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy
+ * with regards to tracking sign/unsigned bounds because the bits may
+ * cross subreg boundaries in the alu64 case. When this happens we mark
+ * the reg unbounded in the subreg bound space and use the resulting
+ * tnum to calculate an approximation of the sign/unsigned bounds.
+ */
switch (opcode) {
case BPF_ADD:
- if (signed_add_overflows(dst_reg->smin_value, smin_val) ||
- signed_add_overflows(dst_reg->smax_value, smax_val)) {
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- } else {
- dst_reg->smin_value += smin_val;
- dst_reg->smax_value += smax_val;
- }
- if (dst_reg->umin_value + umin_val < umin_val ||
- dst_reg->umax_value + umax_val < umax_val) {
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- } else {
- dst_reg->umin_value += umin_val;
- dst_reg->umax_value += umax_val;
- }
+ 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:
- if (signed_sub_overflows(dst_reg->smin_value, smax_val) ||
- signed_sub_overflows(dst_reg->smax_value, smin_val)) {
- /* Overflow possible, we know nothing */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- } else {
- dst_reg->smin_value -= smax_val;
- dst_reg->smax_value -= smin_val;
- }
- if (dst_reg->umin_value < umax_val) {
- /* Overflow possible, we know nothing */
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- } else {
- /* Cannot overflow (as long as bounds are consistent) */
- dst_reg->umin_value -= umax_val;
- dst_reg->umax_value -= umin_val;
- }
+ 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);
break;
case BPF_MUL:
dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
- if (smin_val < 0 || dst_reg->smin_value < 0) {
- /* Ain't nobody got time to multiply that sign */
- __mark_reg_unbounded(dst_reg);
- __update_reg_bounds(dst_reg);
- break;
- }
- /* Both values are positive, so we can work with unsigned and
- * copy the result to signed (unless it exceeds S64_MAX).
- */
- if (umax_val > U32_MAX || dst_reg->umax_value > U32_MAX) {
- /* Potential overflow, we know nothing */
- __mark_reg_unbounded(dst_reg);
- /* (except what we can learn from the var_off) */
- __update_reg_bounds(dst_reg);
- break;
- }
- dst_reg->umin_value *= umin_val;
- dst_reg->umax_value *= umax_val;
- if (dst_reg->umax_value > S64_MAX) {
- /* Overflow possible, we know nothing */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- } else {
- dst_reg->smin_value = dst_reg->umin_value;
- dst_reg->smax_value = dst_reg->umax_value;
- }
+ scalar32_min_max_mul(dst_reg, &src_reg);
+ scalar_min_max_mul(dst_reg, &src_reg);
break;
case BPF_AND:
- if (src_known && dst_known) {
- __mark_reg_known(dst_reg, dst_reg->var_off.value &
- src_reg.var_off.value);
- break;
- }
- /* We get our minimum from the var_off, since that's inherently
- * bitwise. Our maximum is the minimum of the operands' maxima.
- */
dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
- dst_reg->umin_value = dst_reg->var_off.value;
- dst_reg->umax_value = min(dst_reg->umax_value, umax_val);
- if (dst_reg->smin_value < 0 || smin_val < 0) {
- /* Lose signed bounds when ANDing negative numbers,
- * ain't nobody got time for that.
- */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- } else {
- /* ANDing two positives gives a positive, so safe to
- * cast result into s64.
- */
- dst_reg->smin_value = dst_reg->umin_value;
- dst_reg->smax_value = dst_reg->umax_value;
- }
- /* We may learn something more from the var_off */
- __update_reg_bounds(dst_reg);
+ scalar32_min_max_and(dst_reg, &src_reg);
+ scalar_min_max_and(dst_reg, &src_reg);
break;
case BPF_OR:
- if (src_known && dst_known) {
- __mark_reg_known(dst_reg, dst_reg->var_off.value |
- src_reg.var_off.value);
- break;
- }
- /* We get our maximum from the var_off, and our minimum is the
- * maximum of the operands' minima
- */
dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
- dst_reg->umin_value = max(dst_reg->umin_value, umin_val);
- dst_reg->umax_value = dst_reg->var_off.value |
- dst_reg->var_off.mask;
- if (dst_reg->smin_value < 0 || smin_val < 0) {
- /* Lose signed bounds when ORing negative numbers,
- * ain't nobody got time for that.
- */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- } else {
- /* ORing two positives gives a positive, so safe to
- * cast result into s64.
- */
- dst_reg->smin_value = dst_reg->umin_value;
- dst_reg->smax_value = dst_reg->umax_value;
- }
- /* We may learn something more from the var_off */
- __update_reg_bounds(dst_reg);
+ scalar32_min_max_or(dst_reg, &src_reg);
+ scalar_min_max_or(dst_reg, &src_reg);
+ break;
+ case BPF_XOR:
+ dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off);
+ scalar32_min_max_xor(dst_reg, &src_reg);
+ scalar_min_max_xor(dst_reg, &src_reg);
break;
case BPF_LSH:
if (umax_val >= insn_bitness) {
@@ -3409,22 +7116,10 @@
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
- /* We lose all sign bit information (except what we can pick
- * up from var_off)
- */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- /* If we might shift our top bit out, then we know nothing */
- if (dst_reg->umax_value > 1ULL << (63 - umax_val)) {
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- } else {
- dst_reg->umin_value <<= umin_val;
- dst_reg->umax_value <<= umax_val;
- }
- dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
- /* We may learn something more from the var_off */
- __update_reg_bounds(dst_reg);
+ if (alu32)
+ scalar32_min_max_lsh(dst_reg, &src_reg);
+ else
+ scalar_min_max_lsh(dst_reg, &src_reg);
break;
case BPF_RSH:
if (umax_val >= insn_bitness) {
@@ -3434,27 +7129,10 @@
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
- /* BPF_RSH is an unsigned shift. If the value in dst_reg might
- * be negative, then either:
- * 1) src_reg might be zero, so the sign bit of the result is
- * unknown, so we lose our signed bounds
- * 2) it's known negative, thus the unsigned bounds capture the
- * signed bounds
- * 3) the signed bounds cross zero, so they tell us nothing
- * about the result
- * If the value in dst_reg is known nonnegative, then again the
- * unsigned bounts capture the signed bounds.
- * Thus, in all cases it suffices to blow away our signed bounds
- * and rely on inferring new ones from the unsigned bounds and
- * var_off of the result.
- */
- dst_reg->smin_value = S64_MIN;
- dst_reg->smax_value = S64_MAX;
- dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val);
- dst_reg->umin_value >>= umax_val;
- dst_reg->umax_value >>= umin_val;
- /* We may learn something more from the var_off */
- __update_reg_bounds(dst_reg);
+ if (alu32)
+ scalar32_min_max_rsh(dst_reg, &src_reg);
+ else
+ scalar_min_max_rsh(dst_reg, &src_reg);
break;
case BPF_ARSH:
if (umax_val >= insn_bitness) {
@@ -3464,40 +7142,20 @@
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
-
- /* Upon reaching here, src_known is true and
- * umax_val is equal to umin_val.
- */
- if (insn_bitness == 32) {
- dst_reg->smin_value = (u32)(((s32)dst_reg->smin_value) >> umin_val);
- dst_reg->smax_value = (u32)(((s32)dst_reg->smax_value) >> umin_val);
- } else {
- dst_reg->smin_value >>= umin_val;
- dst_reg->smax_value >>= umin_val;
- }
-
- dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val,
- insn_bitness);
-
- /* blow away the dst_reg umin_value/umax_value and rely on
- * dst_reg var_off to refine the result.
- */
- dst_reg->umin_value = 0;
- dst_reg->umax_value = U64_MAX;
- __update_reg_bounds(dst_reg);
+ if (alu32)
+ scalar32_min_max_arsh(dst_reg, &src_reg);
+ else
+ scalar_min_max_arsh(dst_reg, &src_reg);
break;
default:
mark_reg_unknown(env, regs, insn->dst_reg);
break;
}
- if (BPF_CLASS(insn->code) != BPF_ALU64) {
- /* 32-bit ALU ops are (32,32)->32 */
- coerce_reg_to_size(dst_reg, 4);
- }
-
- __reg_deduce_bounds(dst_reg);
- __reg_bound_offset(dst_reg);
+ /* ALU32 ops are zero extended into 64bit register */
+ if (alu32)
+ zext_32_to_64(dst_reg);
+ reg_bounds_sync(dst_reg);
return 0;
}
@@ -3512,11 +7170,17 @@
struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
u8 opcode = BPF_OP(insn->code);
+ int err;
dst_reg = ®s[insn->dst_reg];
src_reg = NULL;
if (dst_reg->type != SCALAR_VALUE)
ptr_reg = dst_reg;
+ else
+ /* Make sure ID is cleared otherwise dst_reg min/max could be
+ * incorrectly propagated into other registers by find_equal_scalars()
+ */
+ dst_reg->id = 0;
if (BPF_SRC(insn->code) == BPF_X) {
src_reg = ®s[insn->src_reg];
if (src_reg->type != SCALAR_VALUE) {
@@ -3538,13 +7202,24 @@
* This is legal, but we have to reverse our
* src/dest handling in computing the range
*/
+ err = mark_chain_precision(env, insn->dst_reg);
+ if (err)
+ return err;
return adjust_ptr_min_max_vals(env, insn,
src_reg, dst_reg);
}
} else if (ptr_reg) {
/* pointer += scalar */
+ err = mark_chain_precision(env, insn->src_reg);
+ if (err)
+ return err;
return adjust_ptr_min_max_vals(env, insn,
dst_reg, src_reg);
+ } else if (dst_reg->precise) {
+ /* if dst_reg is precise, src_reg should be precise as well */
+ err = mark_chain_precision(env, insn->src_reg);
+ if (err)
+ return err;
}
} else {
/* Pretend the src is a reg with a known value, since we only
@@ -3644,8 +7319,15 @@
/* case: R1 = R2
* copy register state to dest reg
*/
- *dst_reg = *src_reg;
+ if (src_reg->type == SCALAR_VALUE && !src_reg->id)
+ /* Assign src and dst registers the same ID
+ * that will be used by find_equal_scalars()
+ * to propagate min/max range.
+ */
+ src_reg->id = ++env->id_gen;
+ copy_register_state(dst_reg, src_reg);
dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = DEF_NOT_SUBREG;
} else {
/* R1 = (u32) R2 */
if (is_pointer_value(env, insn->src_reg)) {
@@ -3654,13 +7336,20 @@
insn->src_reg);
return -EACCES;
} else if (src_reg->type == SCALAR_VALUE) {
- *dst_reg = *src_reg;
+ copy_register_state(dst_reg, src_reg);
+ /* Make sure ID is cleared otherwise
+ * dst_reg min/max could be incorrectly
+ * propagated into src_reg by find_equal_scalars()
+ */
+ dst_reg->id = 0;
dst_reg->live |= REG_LIVE_WRITTEN;
+ dst_reg->subreg_def = env->insn_idx + 1;
} else {
mark_reg_unknown(env, regs,
insn->dst_reg);
}
- coerce_reg_to_size(dst_reg, 4);
+ zext_32_to_64(dst_reg);
+ reg_bounds_sync(dst_reg);
}
} else {
/* case: R = imm
@@ -3711,11 +7400,6 @@
return -EINVAL;
}
- if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
- verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
- return -EINVAL;
- }
-
if ((opcode == BPF_LSH || opcode == BPF_RSH ||
opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
@@ -3742,10 +7426,9 @@
enum bpf_reg_type type,
bool range_right_open)
{
- struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *regs = state->regs, *reg;
- u16 new_range;
- int i, j;
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+ int new_range;
if (dst_reg->off < 0 ||
(dst_reg->off == 0 && range_right_open))
@@ -3810,33 +7493,90 @@
* the range won't allow anything.
* dst_reg->off is known < MAX_PACKET_OFF, therefore it fits in a u16.
*/
- for (i = 0; i < MAX_BPF_REG; i++)
- if (regs[i].type == type && regs[i].id == dst_reg->id)
+ bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+ if (reg->type == type && reg->id == dst_reg->id)
/* keep the maximum range already checked */
- regs[i].range = max(regs[i].range, new_range);
-
- for (j = 0; j <= vstate->curframe; j++) {
- state = vstate->frame[j];
- for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- if (state->stack[i].slot_type[0] != STACK_SPILL)
- continue;
- reg = &state->stack[i].spilled_ptr;
- if (reg->type == type && reg->id == dst_reg->id)
- reg->range = max(reg->range, new_range);
- }
- }
+ reg->range = max(reg->range, new_range);
+ }));
}
-/* compute branch direction of the expression "if (reg opcode val) goto target;"
- * and return:
- * 1 - branch will be taken and "goto target" will be executed
- * 0 - branch will not be taken and fall-through to next insn
- * -1 - unknown. Example: "if (reg < 5)" is unknown when register value range [0,10]
- */
-static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+static int is_branch32_taken(struct bpf_reg_state *reg, u32 val, u8 opcode)
{
- if (__is_pointer_value(false, reg))
- return -1;
+ struct tnum subreg = tnum_subreg(reg->var_off);
+ s32 sval = (s32)val;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ if (tnum_is_const(subreg))
+ return !!tnum_equals_const(subreg, val);
+ break;
+ case BPF_JNE:
+ if (tnum_is_const(subreg))
+ return !tnum_equals_const(subreg, val);
+ break;
+ case BPF_JSET:
+ if ((~subreg.mask & subreg.value) & val)
+ return 1;
+ if (!((subreg.mask | subreg.value) & val))
+ return 0;
+ break;
+ case BPF_JGT:
+ if (reg->u32_min_value > val)
+ return 1;
+ else if (reg->u32_max_value <= val)
+ return 0;
+ break;
+ case BPF_JSGT:
+ if (reg->s32_min_value > sval)
+ return 1;
+ else if (reg->s32_max_value <= sval)
+ return 0;
+ break;
+ case BPF_JLT:
+ if (reg->u32_max_value < val)
+ return 1;
+ else if (reg->u32_min_value >= val)
+ return 0;
+ break;
+ case BPF_JSLT:
+ if (reg->s32_max_value < sval)
+ return 1;
+ else if (reg->s32_min_value >= sval)
+ return 0;
+ break;
+ case BPF_JGE:
+ if (reg->u32_min_value >= val)
+ return 1;
+ else if (reg->u32_max_value < val)
+ return 0;
+ break;
+ case BPF_JSGE:
+ if (reg->s32_min_value >= sval)
+ return 1;
+ else if (reg->s32_max_value < sval)
+ return 0;
+ break;
+ case BPF_JLE:
+ if (reg->u32_max_value <= val)
+ return 1;
+ else if (reg->u32_min_value > val)
+ return 0;
+ break;
+ case BPF_JSLE:
+ if (reg->s32_max_value <= sval)
+ return 1;
+ else if (reg->s32_min_value > sval)
+ return 0;
+ break;
+ }
+
+ return -1;
+}
+
+
+static int is_branch64_taken(struct bpf_reg_state *reg, u64 val, u8 opcode)
+{
+ s64 sval = (s64)val;
switch (opcode) {
case BPF_JEQ:
@@ -3847,6 +7587,12 @@
if (tnum_is_const(reg->var_off))
return !tnum_equals_const(reg->var_off, val);
break;
+ case BPF_JSET:
+ if ((~reg->var_off.mask & reg->var_off.value) & val)
+ return 1;
+ if (!((reg->var_off.mask | reg->var_off.value) & val))
+ return 0;
+ break;
case BPF_JGT:
if (reg->umin_value > val)
return 1;
@@ -3854,9 +7600,9 @@
return 0;
break;
case BPF_JSGT:
- if (reg->smin_value > (s64)val)
+ if (reg->smin_value > sval)
return 1;
- else if (reg->smax_value < (s64)val)
+ else if (reg->smax_value <= sval)
return 0;
break;
case BPF_JLT:
@@ -3866,9 +7612,9 @@
return 0;
break;
case BPF_JSLT:
- if (reg->smax_value < (s64)val)
+ if (reg->smax_value < sval)
return 1;
- else if (reg->smin_value >= (s64)val)
+ else if (reg->smin_value >= sval)
return 0;
break;
case BPF_JGE:
@@ -3878,9 +7624,9 @@
return 0;
break;
case BPF_JSGE:
- if (reg->smin_value >= (s64)val)
+ if (reg->smin_value >= sval)
return 1;
- else if (reg->smax_value < (s64)val)
+ else if (reg->smax_value < sval)
return 0;
break;
case BPF_JLE:
@@ -3890,13 +7636,109 @@
return 0;
break;
case BPF_JSLE:
- if (reg->smax_value <= (s64)val)
+ if (reg->smax_value <= sval)
return 1;
- else if (reg->smin_value > (s64)val)
+ else if (reg->smin_value > sval)
return 0;
break;
}
+ return -1;
+}
+
+/* compute branch direction of the expression "if (reg opcode val) goto target;"
+ * and return:
+ * 1 - branch will be taken and "goto target" will be executed
+ * 0 - branch will not be taken and fall-through to next insn
+ * -1 - unknown. Example: "if (reg < 5)" is unknown when register value
+ * range [0,10]
+ */
+static int is_branch_taken(struct bpf_reg_state *reg, u64 val, u8 opcode,
+ bool is_jmp32)
+{
+ if (__is_pointer_value(false, reg)) {
+ if (!reg_type_not_null(reg->type))
+ return -1;
+
+ /* If pointer is valid tests against zero will fail so we can
+ * use this to direct branch taken.
+ */
+ if (val != 0)
+ return -1;
+
+ switch (opcode) {
+ case BPF_JEQ:
+ return 0;
+ case BPF_JNE:
+ return 1;
+ default:
+ return -1;
+ }
+ }
+
+ if (is_jmp32)
+ return is_branch32_taken(reg, val, opcode);
+ return is_branch64_taken(reg, val, opcode);
+}
+
+static int flip_opcode(u32 opcode)
+{
+ /* How can we transform "a <op> b" into "b <op> a"? */
+ static const u8 opcode_flip[16] = {
+ /* these stay the same */
+ [BPF_JEQ >> 4] = BPF_JEQ,
+ [BPF_JNE >> 4] = BPF_JNE,
+ [BPF_JSET >> 4] = BPF_JSET,
+ /* these swap "lesser" and "greater" (L and G in the opcodes) */
+ [BPF_JGE >> 4] = BPF_JLE,
+ [BPF_JGT >> 4] = BPF_JLT,
+ [BPF_JLE >> 4] = BPF_JGE,
+ [BPF_JLT >> 4] = BPF_JGT,
+ [BPF_JSGE >> 4] = BPF_JSLE,
+ [BPF_JSGT >> 4] = BPF_JSLT,
+ [BPF_JSLE >> 4] = BPF_JSGE,
+ [BPF_JSLT >> 4] = BPF_JSGT
+ };
+ return opcode_flip[opcode >> 4];
+}
+
+static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
+ struct bpf_reg_state *src_reg,
+ u8 opcode)
+{
+ struct bpf_reg_state *pkt;
+
+ if (src_reg->type == PTR_TO_PACKET_END) {
+ pkt = dst_reg;
+ } else if (dst_reg->type == PTR_TO_PACKET_END) {
+ pkt = src_reg;
+ opcode = flip_opcode(opcode);
+ } else {
+ return -1;
+ }
+
+ if (pkt->range >= 0)
+ return -1;
+
+ switch (opcode) {
+ case BPF_JLE:
+ /* pkt <= pkt_end */
+ fallthrough;
+ case BPF_JGT:
+ /* pkt > pkt_end */
+ if (pkt->range == BEYOND_PKT_END)
+ /* pkt has at last one extra byte beyond pkt_end */
+ return opcode == BPF_JGT;
+ break;
+ case BPF_JLT:
+ /* pkt < pkt_end */
+ fallthrough;
+ case BPF_JGE:
+ /* pkt >= pkt_end */
+ if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
+ return opcode == BPF_JGE;
+ break;
+ }
return -1;
}
@@ -3906,9 +7748,17 @@
* In JEQ/JNE cases we also adjust the var_off values.
*/
static void reg_set_min_max(struct bpf_reg_state *true_reg,
- struct bpf_reg_state *false_reg, u64 val,
- u8 opcode)
+ struct bpf_reg_state *false_reg,
+ u64 val, u32 val32,
+ u8 opcode, bool is_jmp32)
{
+ struct tnum false_32off = tnum_subreg(false_reg->var_off);
+ struct tnum false_64off = false_reg->var_off;
+ struct tnum true_32off = tnum_subreg(true_reg->var_off);
+ struct tnum true_64off = true_reg->var_off;
+ s64 sval = (s64)val;
+ s32 sval32 = (s32)val32;
+
/* If the dst_reg is a pointer, we can't learn anything about its
* variable offset from the compare (unless src_reg were a pointer into
* the same object, but we don't bother with that.
@@ -3919,137 +7769,155 @@
return;
switch (opcode) {
+ /* JEQ/JNE comparison doesn't change the register equivalence.
+ *
+ * r1 = r2;
+ * if (r1 == 42) goto label;
+ * ...
+ * label: // here both r1 and r2 are known to be 42.
+ *
+ * Hence when marking register as known preserve it's ID.
+ */
case BPF_JEQ:
- /* If this is false then we know nothing Jon Snow, but if it is
- * true then we know for sure.
- */
- __mark_reg_known(true_reg, val);
+ if (is_jmp32) {
+ __mark_reg32_known(true_reg, val32);
+ true_32off = tnum_subreg(true_reg->var_off);
+ } else {
+ ___mark_reg_known(true_reg, val);
+ true_64off = true_reg->var_off;
+ }
break;
case BPF_JNE:
- /* If this is true we know nothing Jon Snow, but if it is false
- * we know the value for sure;
- */
- __mark_reg_known(false_reg, val);
+ if (is_jmp32) {
+ __mark_reg32_known(false_reg, val32);
+ false_32off = tnum_subreg(false_reg->var_off);
+ } else {
+ ___mark_reg_known(false_reg, val);
+ false_64off = false_reg->var_off;
+ }
break;
- case BPF_JGT:
- false_reg->umax_value = min(false_reg->umax_value, val);
- true_reg->umin_value = max(true_reg->umin_value, val + 1);
- break;
- case BPF_JSGT:
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
- break;
- case BPF_JLT:
- false_reg->umin_value = max(false_reg->umin_value, val);
- true_reg->umax_value = min(true_reg->umax_value, val - 1);
- break;
- case BPF_JSLT:
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
+ case BPF_JSET:
+ if (is_jmp32) {
+ false_32off = tnum_and(false_32off, tnum_const(~val32));
+ if (is_power_of_2(val32))
+ true_32off = tnum_or(true_32off,
+ tnum_const(val32));
+ } else {
+ false_64off = tnum_and(false_64off, tnum_const(~val));
+ if (is_power_of_2(val))
+ true_64off = tnum_or(true_64off,
+ tnum_const(val));
+ }
break;
case BPF_JGE:
- false_reg->umax_value = min(false_reg->umax_value, val - 1);
- true_reg->umin_value = max(true_reg->umin_value, val);
- break;
- case BPF_JSGE:
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
- break;
- case BPF_JLE:
- false_reg->umin_value = max(false_reg->umin_value, val + 1);
- true_reg->umax_value = min(true_reg->umax_value, val);
- break;
- case BPF_JSLE:
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
- break;
- default:
+ case BPF_JGT:
+ {
+ if (is_jmp32) {
+ u32 false_umax = opcode == BPF_JGT ? val32 : val32 - 1;
+ u32 true_umin = opcode == BPF_JGT ? val32 + 1 : val32;
+
+ false_reg->u32_max_value = min(false_reg->u32_max_value,
+ false_umax);
+ true_reg->u32_min_value = max(true_reg->u32_min_value,
+ true_umin);
+ } else {
+ u64 false_umax = opcode == BPF_JGT ? val : val - 1;
+ u64 true_umin = opcode == BPF_JGT ? val + 1 : val;
+
+ false_reg->umax_value = min(false_reg->umax_value, false_umax);
+ true_reg->umin_value = max(true_reg->umin_value, true_umin);
+ }
break;
}
+ case BPF_JSGE:
+ case BPF_JSGT:
+ {
+ if (is_jmp32) {
+ s32 false_smax = opcode == BPF_JSGT ? sval32 : sval32 - 1;
+ s32 true_smin = opcode == BPF_JSGT ? sval32 + 1 : sval32;
- __reg_deduce_bounds(false_reg);
- __reg_deduce_bounds(true_reg);
- /* We might have learned some bits from the bounds. */
- __reg_bound_offset(false_reg);
- __reg_bound_offset(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.
- */
- __update_reg_bounds(false_reg);
- __update_reg_bounds(true_reg);
+ false_reg->s32_max_value = min(false_reg->s32_max_value, false_smax);
+ true_reg->s32_min_value = max(true_reg->s32_min_value, true_smin);
+ } else {
+ s64 false_smax = opcode == BPF_JSGT ? sval : sval - 1;
+ s64 true_smin = opcode == BPF_JSGT ? sval + 1 : sval;
+
+ false_reg->smax_value = min(false_reg->smax_value, false_smax);
+ true_reg->smin_value = max(true_reg->smin_value, true_smin);
+ }
+ break;
+ }
+ case BPF_JLE:
+ case BPF_JLT:
+ {
+ if (is_jmp32) {
+ u32 false_umin = opcode == BPF_JLT ? val32 : val32 + 1;
+ u32 true_umax = opcode == BPF_JLT ? val32 - 1 : val32;
+
+ false_reg->u32_min_value = max(false_reg->u32_min_value,
+ false_umin);
+ true_reg->u32_max_value = min(true_reg->u32_max_value,
+ true_umax);
+ } else {
+ u64 false_umin = opcode == BPF_JLT ? val : val + 1;
+ u64 true_umax = opcode == BPF_JLT ? val - 1 : val;
+
+ false_reg->umin_value = max(false_reg->umin_value, false_umin);
+ true_reg->umax_value = min(true_reg->umax_value, true_umax);
+ }
+ break;
+ }
+ case BPF_JSLE:
+ case BPF_JSLT:
+ {
+ if (is_jmp32) {
+ s32 false_smin = opcode == BPF_JSLT ? sval32 : sval32 + 1;
+ s32 true_smax = opcode == BPF_JSLT ? sval32 - 1 : sval32;
+
+ false_reg->s32_min_value = max(false_reg->s32_min_value, false_smin);
+ true_reg->s32_max_value = min(true_reg->s32_max_value, true_smax);
+ } else {
+ s64 false_smin = opcode == BPF_JSLT ? sval : sval + 1;
+ s64 true_smax = opcode == BPF_JSLT ? sval - 1 : sval;
+
+ false_reg->smin_value = max(false_reg->smin_value, false_smin);
+ true_reg->smax_value = min(true_reg->smax_value, true_smax);
+ }
+ break;
+ }
+ default:
+ return;
+ }
+
+ if (is_jmp32) {
+ false_reg->var_off = tnum_or(tnum_clear_subreg(false_64off),
+ tnum_subreg(false_32off));
+ true_reg->var_off = tnum_or(tnum_clear_subreg(true_64off),
+ tnum_subreg(true_32off));
+ __reg_combine_32_into_64(false_reg);
+ __reg_combine_32_into_64(true_reg);
+ } else {
+ false_reg->var_off = false_64off;
+ true_reg->var_off = true_64off;
+ __reg_combine_64_into_32(false_reg);
+ __reg_combine_64_into_32(true_reg);
+ }
}
/* Same as above, but for the case that dst_reg holds a constant and src_reg is
* the variable reg.
*/
static void reg_set_min_max_inv(struct bpf_reg_state *true_reg,
- struct bpf_reg_state *false_reg, u64 val,
- u8 opcode)
+ struct bpf_reg_state *false_reg,
+ u64 val, u32 val32,
+ u8 opcode, bool is_jmp32)
{
- if (__is_pointer_value(false, false_reg))
- return;
-
- switch (opcode) {
- case BPF_JEQ:
- /* If this is false then we know nothing Jon Snow, but if it is
- * true then we know for sure.
- */
- __mark_reg_known(true_reg, val);
- break;
- case BPF_JNE:
- /* If this is true we know nothing Jon Snow, but if it is false
- * we know the value for sure;
- */
- __mark_reg_known(false_reg, val);
- break;
- case BPF_JGT:
- true_reg->umax_value = min(true_reg->umax_value, val - 1);
- false_reg->umin_value = max(false_reg->umin_value, val);
- break;
- case BPF_JSGT:
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val - 1);
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val);
- break;
- case BPF_JLT:
- true_reg->umin_value = max(true_reg->umin_value, val + 1);
- false_reg->umax_value = min(false_reg->umax_value, val);
- break;
- case BPF_JSLT:
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val + 1);
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val);
- break;
- case BPF_JGE:
- true_reg->umax_value = min(true_reg->umax_value, val);
- false_reg->umin_value = max(false_reg->umin_value, val + 1);
- break;
- case BPF_JSGE:
- true_reg->smax_value = min_t(s64, true_reg->smax_value, val);
- false_reg->smin_value = max_t(s64, false_reg->smin_value, val + 1);
- break;
- case BPF_JLE:
- true_reg->umin_value = max(true_reg->umin_value, val);
- false_reg->umax_value = min(false_reg->umax_value, val - 1);
- break;
- case BPF_JSLE:
- true_reg->smin_value = max_t(s64, true_reg->smin_value, val);
- false_reg->smax_value = min_t(s64, false_reg->smax_value, val - 1);
- break;
- default:
- break;
- }
-
- __reg_deduce_bounds(false_reg);
- __reg_deduce_bounds(true_reg);
- /* We might have learned some bits from the bounds. */
- __reg_bound_offset(false_reg);
- __reg_bound_offset(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.
+ opcode = flip_opcode(opcode);
+ /* This uses zero as "not present in table"; luckily the zero opcode,
+ * BPF_JA, can't get here.
*/
- __update_reg_bounds(false_reg);
- __update_reg_bounds(true_reg);
+ if (opcode)
+ reg_set_min_max(true_reg, false_reg, val, val32, opcode, is_jmp32);
}
/* Regs are known to be equal, so intersect their min/max/var_off */
@@ -4066,21 +7934,8 @@
dst_reg->smax_value);
src_reg->var_off = dst_reg->var_off = tnum_intersect(src_reg->var_off,
dst_reg->var_off);
- /* We might have learned new bounds from the var_off. */
- __update_reg_bounds(src_reg);
- __update_reg_bounds(dst_reg);
- /* We might have learned something about the sign bit. */
- __reg_deduce_bounds(src_reg);
- __reg_deduce_bounds(dst_reg);
- /* We might have learned some bits from the bounds. */
- __reg_bound_offset(src_reg);
- __reg_bound_offset(dst_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.
- */
- __update_reg_bounds(src_reg);
- __update_reg_bounds(dst_reg);
+ reg_bounds_sync(src_reg);
+ reg_bounds_sync(dst_reg);
}
static void reg_combine_min_max(struct bpf_reg_state *true_src,
@@ -4099,60 +7954,93 @@
}
}
-static void mark_map_reg(struct bpf_reg_state *regs, u32 regno, u32 id,
- bool is_null)
+static void mark_ptr_or_null_reg(struct bpf_func_state *state,
+ struct bpf_reg_state *reg, u32 id,
+ bool is_null)
{
- struct bpf_reg_state *reg = ®s[regno];
-
- if (reg->type == PTR_TO_MAP_VALUE_OR_NULL && reg->id == id) {
- /* Old offset (both fixed and variable parts) should
- * have been known-zero, because we don't allow pointer
- * arithmetic on pointers that might be NULL.
- */
+ if (reg_type_may_be_null(reg->type) && reg->id == id &&
+ !WARN_ON_ONCE(!reg->id)) {
if (WARN_ON_ONCE(reg->smin_value || reg->smax_value ||
!tnum_equals_const(reg->var_off, 0) ||
reg->off)) {
- __mark_reg_known_zero(reg);
- reg->off = 0;
+ /* Old offset (both fixed and variable parts) should
+ * have been known-zero, because we don't allow pointer
+ * arithmetic on pointers that might be NULL. If we
+ * see this happening, don't convert the register.
+ */
+ return;
}
if (is_null) {
reg->type = SCALAR_VALUE;
- } else if (reg->map_ptr->inner_map_meta) {
- reg->type = CONST_PTR_TO_MAP;
- reg->map_ptr = reg->map_ptr->inner_map_meta;
- } else {
- reg->type = PTR_TO_MAP_VALUE;
+ } else if (reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
+ const struct bpf_map *map = reg->map_ptr;
+
+ if (map->inner_map_meta) {
+ reg->type = CONST_PTR_TO_MAP;
+ reg->map_ptr = map->inner_map_meta;
+ } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
+ reg->type = PTR_TO_XDP_SOCK;
+ } else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH) {
+ reg->type = PTR_TO_SOCKET;
+ } else {
+ reg->type = PTR_TO_MAP_VALUE;
+ }
+ } else if (reg->type == PTR_TO_SOCKET_OR_NULL) {
+ reg->type = PTR_TO_SOCKET;
+ } else if (reg->type == PTR_TO_SOCK_COMMON_OR_NULL) {
+ reg->type = PTR_TO_SOCK_COMMON;
+ } else if (reg->type == PTR_TO_TCP_SOCK_OR_NULL) {
+ reg->type = PTR_TO_TCP_SOCK;
+ } else if (reg->type == PTR_TO_BTF_ID_OR_NULL) {
+ reg->type = PTR_TO_BTF_ID;
+ } else if (reg->type == PTR_TO_MEM_OR_NULL) {
+ reg->type = PTR_TO_MEM;
+ } else if (reg->type == PTR_TO_RDONLY_BUF_OR_NULL) {
+ reg->type = PTR_TO_RDONLY_BUF;
+ } else if (reg->type == PTR_TO_RDWR_BUF_OR_NULL) {
+ reg->type = PTR_TO_RDWR_BUF;
}
- /* We don't need id from this point onwards anymore, thus we
- * should better reset it, so that state pruning has chances
- * to take effect.
- */
- reg->id = 0;
+ if (is_null) {
+ /* We don't need id and ref_obj_id from this point
+ * onwards anymore, thus we should better reset it,
+ * so that state pruning has chances to take effect.
+ */
+ reg->id = 0;
+ reg->ref_obj_id = 0;
+ } else if (!reg_may_point_to_spin_lock(reg)) {
+ /* For not-NULL ptr, reg->ref_obj_id will be reset
+ * in release_reference().
+ *
+ * reg->id is still used by spin_lock ptr. Other
+ * than spin_lock ptr type, reg->id can be reset.
+ */
+ reg->id = 0;
+ }
}
}
/* The logic is similar to find_good_pkt_pointers(), both could eventually
* be folded together at some point.
*/
-static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno,
- bool is_null)
+static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
+ bool is_null)
{
struct bpf_func_state *state = vstate->frame[vstate->curframe];
- struct bpf_reg_state *regs = state->regs;
+ struct bpf_reg_state *regs = state->regs, *reg;
+ u32 ref_obj_id = regs[regno].ref_obj_id;
u32 id = regs[regno].id;
- int i, j;
- for (i = 0; i < MAX_BPF_REG; i++)
- mark_map_reg(regs, i, id, is_null);
+ if (ref_obj_id && ref_obj_id == id && is_null)
+ /* regs[regno] is in the " == NULL" branch.
+ * No one could have freed the reference state before
+ * doing the NULL check.
+ */
+ WARN_ON_ONCE(release_reference_state(state, id));
- for (j = 0; j <= vstate->curframe; j++) {
- state = vstate->frame[j];
- for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- if (state->stack[i].slot_type[0] != STACK_SPILL)
- continue;
- mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
- }
- }
+ bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+ mark_ptr_or_null_reg(state, reg, id, is_null);
+ }));
}
static bool try_match_pkt_pointers(const struct bpf_insn *insn,
@@ -4164,6 +8052,10 @@
if (BPF_SRC(insn->code) != BPF_X)
return false;
+ /* Pointers are always 64-bit. */
+ if (BPF_CLASS(insn->code) == BPF_JMP32)
+ return false;
+
switch (BPF_OP(insn->code)) {
case BPF_JGT:
if ((dst_reg->type == PTR_TO_PACKET &&
@@ -4173,6 +8065,7 @@
/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(other_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -4180,6 +8073,7 @@
/* pkt_end > pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(this_branch, insn->src_reg, false);
} else {
return false;
}
@@ -4192,6 +8086,7 @@
/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(this_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -4199,6 +8094,7 @@
/* pkt_end < pkt_data', pkt_data > pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(other_branch, insn->src_reg, true);
} else {
return false;
}
@@ -4211,6 +8107,7 @@
/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
find_good_pkt_pointers(this_branch, dst_reg,
dst_reg->type, true);
+ mark_pkt_end(other_branch, insn->dst_reg, false);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -4218,6 +8115,7 @@
/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
find_good_pkt_pointers(other_branch, src_reg,
src_reg->type, false);
+ mark_pkt_end(this_branch, insn->src_reg, true);
} else {
return false;
}
@@ -4230,6 +8128,7 @@
/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
find_good_pkt_pointers(other_branch, dst_reg,
dst_reg->type, false);
+ mark_pkt_end(this_branch, insn->dst_reg, true);
} else if ((dst_reg->type == PTR_TO_PACKET_END &&
src_reg->type == PTR_TO_PACKET) ||
(reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
@@ -4237,6 +8136,7 @@
/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
find_good_pkt_pointers(this_branch, src_reg,
src_reg->type, true);
+ mark_pkt_end(other_branch, insn->src_reg, false);
} else {
return false;
}
@@ -4248,6 +8148,18 @@
return true;
}
+static void find_equal_scalars(struct bpf_verifier_state *vstate,
+ struct bpf_reg_state *known_reg)
+{
+ struct bpf_func_state *state;
+ struct bpf_reg_state *reg;
+
+ bpf_for_each_reg_in_vstate(vstate, state, reg, ({
+ if (reg->type == SCALAR_VALUE && reg->id == known_reg->id)
+ copy_register_state(reg, known_reg);
+ }));
+}
+
static int check_cond_jmp_op(struct bpf_verifier_env *env,
struct bpf_insn *insn, int *insn_idx)
{
@@ -4256,17 +8168,19 @@
struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
u8 opcode = BPF_OP(insn->code);
+ bool is_jmp32;
int pred = -1;
int err;
- if (opcode > BPF_JSLE) {
- verbose(env, "invalid BPF_JMP opcode %x\n", opcode);
+ /* Only conditional jumps are expected to reach here. */
+ if (opcode == BPF_JA || opcode > BPF_JSLE) {
+ verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode);
return -EINVAL;
}
if (BPF_SRC(insn->code) == BPF_X) {
if (insn->imm != 0) {
- verbose(env, "BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
@@ -4283,7 +8197,7 @@
src_reg = ®s[insn->src_reg];
} else {
if (insn->src_reg != BPF_REG_0) {
- verbose(env, "BPF_JMP uses reserved fields\n");
+ verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
return -EINVAL;
}
}
@@ -4294,20 +8208,47 @@
return err;
dst_reg = ®s[insn->dst_reg];
+ is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
- if (BPF_SRC(insn->code) == BPF_K)
- pred = is_branch_taken(dst_reg, insn->imm, opcode);
- else if (src_reg->type == SCALAR_VALUE &&
- tnum_is_const(src_reg->var_off))
- pred = is_branch_taken(dst_reg, src_reg->var_off.value,
- opcode);
+ if (BPF_SRC(insn->code) == BPF_K) {
+ pred = is_branch_taken(dst_reg, insn->imm, opcode, is_jmp32);
+ } else if (src_reg->type == SCALAR_VALUE &&
+ is_jmp32 && tnum_is_const(tnum_subreg(src_reg->var_off))) {
+ pred = is_branch_taken(dst_reg,
+ tnum_subreg(src_reg->var_off).value,
+ opcode,
+ is_jmp32);
+ } else if (src_reg->type == SCALAR_VALUE &&
+ !is_jmp32 && tnum_is_const(src_reg->var_off)) {
+ pred = is_branch_taken(dst_reg,
+ src_reg->var_off.value,
+ opcode,
+ is_jmp32);
+ } else if (reg_is_pkt_pointer_any(dst_reg) &&
+ reg_is_pkt_pointer_any(src_reg) &&
+ !is_jmp32) {
+ pred = is_pkt_ptr_branch_taken(dst_reg, src_reg, opcode);
+ }
+
+ if (pred >= 0) {
+ /* If we get here with a dst_reg pointer type it is because
+ * above is_branch_taken() special cased the 0 comparison.
+ */
+ if (!__is_pointer_value(false, dst_reg))
+ err = mark_chain_precision(env, insn->dst_reg);
+ if (BPF_SRC(insn->code) == BPF_X && !err &&
+ !__is_pointer_value(false, src_reg))
+ err = mark_chain_precision(env, insn->src_reg);
+ if (err)
+ return err;
+ }
if (pred == 1) {
/* Only follow the goto, ignore fall-through. If needed, push
* the fall-through branch for simulation under speculative
* execution.
*/
- if (!env->allow_ptr_leaks &&
+ if (!env->bypass_spec_v1 &&
!sanitize_speculative_path(env, insn, *insn_idx + 1,
*insn_idx))
return -EFAULT;
@@ -4318,7 +8259,7 @@
* program will go. If needed, push the goto branch for
* simulation under speculative execution.
*/
- if (!env->allow_ptr_leaks &&
+ if (!env->bypass_spec_v1 &&
!sanitize_speculative_path(env, insn,
*insn_idx + insn->off + 1,
*insn_idx))
@@ -4340,37 +8281,65 @@
* comparable.
*/
if (BPF_SRC(insn->code) == BPF_X) {
+ struct bpf_reg_state *src_reg = ®s[insn->src_reg];
+
if (dst_reg->type == SCALAR_VALUE &&
- regs[insn->src_reg].type == SCALAR_VALUE) {
- if (tnum_is_const(regs[insn->src_reg].var_off))
+ src_reg->type == SCALAR_VALUE) {
+ if (tnum_is_const(src_reg->var_off) ||
+ (is_jmp32 &&
+ tnum_is_const(tnum_subreg(src_reg->var_off))))
reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg, regs[insn->src_reg].var_off.value,
- opcode);
- else if (tnum_is_const(dst_reg->var_off))
+ dst_reg,
+ src_reg->var_off.value,
+ tnum_subreg(src_reg->var_off).value,
+ opcode, is_jmp32);
+ else if (tnum_is_const(dst_reg->var_off) ||
+ (is_jmp32 &&
+ tnum_is_const(tnum_subreg(dst_reg->var_off))))
reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
- ®s[insn->src_reg],
- dst_reg->var_off.value, opcode);
- else if (opcode == BPF_JEQ || opcode == BPF_JNE)
+ src_reg,
+ dst_reg->var_off.value,
+ tnum_subreg(dst_reg->var_off).value,
+ opcode, is_jmp32);
+ else if (!is_jmp32 &&
+ (opcode == BPF_JEQ || opcode == BPF_JNE))
/* Comparing for equality, we can combine knowledge */
reg_combine_min_max(&other_branch_regs[insn->src_reg],
&other_branch_regs[insn->dst_reg],
- ®s[insn->src_reg],
- ®s[insn->dst_reg], opcode);
+ src_reg, dst_reg, opcode);
+ if (src_reg->id &&
+ !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
+ find_equal_scalars(this_branch, src_reg);
+ find_equal_scalars(other_branch, &other_branch_regs[insn->src_reg]);
+ }
+
}
} else if (dst_reg->type == SCALAR_VALUE) {
reg_set_min_max(&other_branch_regs[insn->dst_reg],
- dst_reg, insn->imm, opcode);
+ dst_reg, insn->imm, (u32)insn->imm,
+ opcode, is_jmp32);
}
- /* detect if R == 0 where R is returned from bpf_map_lookup_elem() */
- if (BPF_SRC(insn->code) == BPF_K &&
+ if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
+ !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
+ find_equal_scalars(this_branch, dst_reg);
+ find_equal_scalars(other_branch, &other_branch_regs[insn->dst_reg]);
+ }
+
+ /* detect if R == 0 where R is returned from bpf_map_lookup_elem().
+ * NOTE: these optimizations below are related with pointer comparison
+ * which will never be JMP32.
+ */
+ if (!is_jmp32 && BPF_SRC(insn->code) == BPF_K &&
insn->imm == 0 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
- dst_reg->type == PTR_TO_MAP_VALUE_OR_NULL) {
- /* Mark all identical map registers in each branch as either
+ reg_type_may_be_null(dst_reg->type)) {
+ /* Mark all identical registers in each branch as either
* safe or unknown depending R == 0 or R != 0 conditional.
*/
- mark_map_regs(this_branch, insn->dst_reg, opcode == BPF_JNE);
- mark_map_regs(other_branch, insn->dst_reg, opcode == BPF_JEQ);
+ mark_ptr_or_null_regs(this_branch, insn->dst_reg,
+ opcode == BPF_JNE);
+ mark_ptr_or_null_regs(other_branch, insn->dst_reg,
+ opcode == BPF_JEQ);
} else if (!try_match_pkt_pointers(insn, dst_reg, ®s[insn->src_reg],
this_branch, other_branch) &&
is_pointer_value(env, insn->dst_reg)) {
@@ -4378,23 +8347,18 @@
insn->dst_reg);
return -EACCES;
}
- if (env->log.level)
+ if (env->log.level & BPF_LOG_LEVEL)
print_verifier_state(env, this_branch->frame[this_branch->curframe]);
return 0;
-}
-
-/* return the map pointer stored inside BPF_LD_IMM64 instruction */
-static struct bpf_map *ld_imm64_to_map_ptr(struct bpf_insn *insn)
-{
- u64 imm64 = ((u64) (u32) insn[0].imm) | ((u64) (u32) insn[1].imm) << 32;
-
- return (struct bpf_map *) (unsigned long) imm64;
}
/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
+ struct bpf_insn_aux_data *aux = cur_aux(env);
struct bpf_reg_state *regs = cur_regs(env);
+ struct bpf_reg_state *dst_reg;
+ struct bpf_map *map;
int err;
if (BPF_SIZE(insn->code) != BPF_DW) {
@@ -4410,19 +8374,50 @@
if (err)
return err;
+ dst_reg = ®s[insn->dst_reg];
if (insn->src_reg == 0) {
u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;
- regs[insn->dst_reg].type = SCALAR_VALUE;
+ dst_reg->type = SCALAR_VALUE;
__mark_reg_known(®s[insn->dst_reg], imm);
return 0;
}
- /* replace_map_fd_with_map_ptr() should have caught bad ld_imm64 */
- BUG_ON(insn->src_reg != BPF_PSEUDO_MAP_FD);
+ if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
+ mark_reg_known_zero(env, regs, insn->dst_reg);
- regs[insn->dst_reg].type = CONST_PTR_TO_MAP;
- regs[insn->dst_reg].map_ptr = ld_imm64_to_map_ptr(insn);
+ dst_reg->type = aux->btf_var.reg_type;
+ switch (dst_reg->type) {
+ case PTR_TO_MEM:
+ dst_reg->mem_size = aux->btf_var.mem_size;
+ break;
+ case PTR_TO_BTF_ID:
+ case PTR_TO_PERCPU_BTF_ID:
+ dst_reg->btf_id = aux->btf_var.btf_id;
+ break;
+ default:
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EFAULT;
+ }
+ return 0;
+ }
+
+ map = env->used_maps[aux->map_index];
+ mark_reg_known_zero(env, regs, insn->dst_reg);
+ dst_reg->map_ptr = map;
+
+ if (insn->src_reg == BPF_PSEUDO_MAP_VALUE) {
+ dst_reg->type = PTR_TO_MAP_VALUE;
+ dst_reg->off = aux->map_off;
+ if (map_value_has_spin_lock(map))
+ dst_reg->id = ++env->id_gen;
+ } else if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ dst_reg->type = CONST_PTR_TO_MAP;
+ } else {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
return 0;
}
@@ -4460,25 +8455,13 @@
u8 mode = BPF_MODE(insn->code);
int i, err;
- if (!may_access_skb(env->prog->type)) {
+ if (!may_access_skb(resolve_prog_type(env->prog))) {
verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
return -EINVAL;
}
if (!env->ops->gen_ld_abs) {
verbose(env, "bpf verifier is misconfigured\n");
- return -EINVAL;
- }
-
- if (env->subprog_cnt > 1) {
- /* when program has LD_ABS insn JITs and interpreter assume
- * that r1 == ctx == skb which is not the case for callees
- * that can have arbitrary arguments. It's problematic
- * for main prog as well since JITs would need to analyze
- * all functions in order to make proper register save/restore
- * decisions in the main prog. Hence disallow LD_ABS with calls
- */
- verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
return -EINVAL;
}
@@ -4493,6 +8476,21 @@
err = check_reg_arg(env, ctx_reg, SRC_OP);
if (err)
return err;
+
+ /* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as
+ * gen_ld_abs() may terminate the program at runtime, leading to
+ * reference leak.
+ */
+ err = check_reference_leak(env);
+ if (err) {
+ verbose(env, "BPF_LD_[ABS|IND] cannot be mixed with socket references\n");
+ return err;
+ }
+
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "BPF_LD_[ABS|IND] cannot be used inside bpf_spin_lock-ed region\n");
+ return -EINVAL;
+ }
if (regs[ctx_reg].type != PTR_TO_CTX) {
verbose(env,
@@ -4522,29 +8520,106 @@
* Already marked as written above.
*/
mark_reg_unknown(env, regs, BPF_REG_0);
+ /* ld_abs load up to 32-bit skb data. */
+ regs[BPF_REG_0].subreg_def = env->insn_idx + 1;
return 0;
}
static int check_return_code(struct bpf_verifier_env *env)
{
+ struct tnum enforce_attach_type_range = tnum_unknown;
+ const struct bpf_prog *prog = env->prog;
struct bpf_reg_state *reg;
struct tnum range = tnum_range(0, 1);
+ enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
+ int err;
+ const bool is_subprog = env->cur_state->frame[0]->subprogno;
- switch (env->prog->type) {
+ /* LSM and struct_ops func-ptr's return type could be "void" */
+ if (!is_subprog &&
+ (prog_type == BPF_PROG_TYPE_STRUCT_OPS ||
+ prog_type == BPF_PROG_TYPE_LSM) &&
+ !prog->aux->attach_func_proto->type)
+ return 0;
+
+ /* eBPF calling convetion is such that R0 is used
+ * to return the value from eBPF program.
+ * Make sure that it's readable at this time
+ * of bpf_exit, which means that program wrote
+ * something into it earlier
+ */
+ err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ if (err)
+ return err;
+
+ if (is_pointer_value(env, BPF_REG_0)) {
+ verbose(env, "R0 leaks addr as return value\n");
+ return -EACCES;
+ }
+
+ reg = cur_regs(env) + BPF_REG_0;
+ if (is_subprog) {
+ if (reg->type != SCALAR_VALUE) {
+ verbose(env, "At subprogram exit the register R0 is not a scalar value (%s)\n",
+ reg_type_str[reg->type]);
+ return -EINVAL;
+ }
+ return 0;
+ }
+
+ switch (prog_type) {
case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
if (env->prog->expected_attach_type == BPF_CGROUP_UDP4_RECVMSG ||
- env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG)
+ env->prog->expected_attach_type == BPF_CGROUP_UDP6_RECVMSG ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET4_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETPEERNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET4_GETSOCKNAME ||
+ env->prog->expected_attach_type == BPF_CGROUP_INET6_GETSOCKNAME)
range = tnum_range(1, 1);
+ break;
case BPF_PROG_TYPE_CGROUP_SKB:
+ if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS) {
+ range = tnum_range(0, 3);
+ enforce_attach_type_range = tnum_range(2, 3);
+ }
+ break;
case BPF_PROG_TYPE_CGROUP_SOCK:
case BPF_PROG_TYPE_SOCK_OPS:
case BPF_PROG_TYPE_CGROUP_DEVICE:
+ case BPF_PROG_TYPE_CGROUP_SYSCTL:
+ case BPF_PROG_TYPE_CGROUP_SOCKOPT:
break;
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ if (!env->prog->aux->attach_btf_id)
+ return 0;
+ range = tnum_const(0);
+ break;
+ case BPF_PROG_TYPE_TRACING:
+ switch (env->prog->expected_attach_type) {
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ range = tnum_const(0);
+ break;
+ case BPF_TRACE_RAW_TP:
+ case BPF_MODIFY_RETURN:
+ return 0;
+ case BPF_TRACE_ITER:
+ break;
+ default:
+ return -ENOTSUPP;
+ }
+ break;
+ case BPF_PROG_TYPE_SK_LOOKUP:
+ range = tnum_range(SK_DROP, SK_PASS);
+ break;
+ case BPF_PROG_TYPE_EXT:
+ /* freplace program can return anything as its return value
+ * depends on the to-be-replaced kernel func or bpf program.
+ */
default:
return 0;
}
- reg = cur_regs(env) + BPF_REG_0;
if (reg->type != SCALAR_VALUE) {
verbose(env, "At program exit the register R0 is not a known value (%s)\n",
reg_type_str[reg->type]);
@@ -4565,6 +8640,10 @@
verbose(env, " should have been in %s\n", tn_buf);
return -EINVAL;
}
+
+ if (!tnum_is_unknown(enforce_attach_type_range) &&
+ tnum_in(enforce_attach_type_range, reg->var_off))
+ env->prog->enforce_expected_attach_type = 1;
return 0;
}
@@ -4608,19 +8687,37 @@
BRANCH = 2,
};
-#define STATE_LIST_MARK ((struct bpf_verifier_state_list *) -1L)
+static u32 state_htab_size(struct bpf_verifier_env *env)
+{
+ return env->prog->len;
+}
-static int *insn_stack; /* stack of insns to process */
-static int cur_stack; /* current stack index */
-static int *insn_state;
+static struct bpf_verifier_state_list **explored_state(
+ struct bpf_verifier_env *env,
+ int idx)
+{
+ struct bpf_verifier_state *cur = env->cur_state;
+ struct bpf_func_state *state = cur->frame[cur->curframe];
+
+ return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
+}
+
+static void init_explored_state(struct bpf_verifier_env *env, int idx)
+{
+ env->insn_aux_data[idx].prune_point = true;
+}
/* t, w, e - match pseudo-code above:
* t - index of current instruction
* w - next instruction
* e - edge
*/
-static int push_insn(int t, int w, int e, struct bpf_verifier_env *env)
+static int push_insn(int t, int w, int e, struct bpf_verifier_env *env,
+ bool loop_ok)
{
+ int *insn_stack = env->cfg.insn_stack;
+ int *insn_state = env->cfg.insn_state;
+
if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH))
return 0;
@@ -4628,23 +8725,28 @@
return 0;
if (w < 0 || w >= env->prog->len) {
+ verbose_linfo(env, t, "%d: ", t);
verbose(env, "jump out of range from insn %d to %d\n", t, w);
return -EINVAL;
}
if (e == BRANCH)
/* mark branch target for state pruning */
- env->explored_states[w] = STATE_LIST_MARK;
+ init_explored_state(env, w);
if (insn_state[w] == 0) {
/* tree-edge */
insn_state[t] = DISCOVERED | e;
insn_state[w] = DISCOVERED;
- if (cur_stack >= env->prog->len)
+ if (env->cfg.cur_stack >= env->prog->len)
return -E2BIG;
- insn_stack[cur_stack++] = w;
+ insn_stack[env->cfg.cur_stack++] = w;
return 1;
} else if ((insn_state[w] & 0xF0) == DISCOVERED) {
+ if (loop_ok && env->bpf_capable)
+ return 0;
+ verbose_linfo(env, t, "%d: ", t);
+ verbose_linfo(env, w, "%d: ", w);
verbose(env, "back-edge from insn %d to %d\n", t, w);
return -EINVAL;
} else if (insn_state[w] == EXPLORED) {
@@ -4664,48 +8766,47 @@
{
struct bpf_insn *insns = env->prog->insnsi;
int insn_cnt = env->prog->len;
+ int *insn_stack, *insn_state;
int ret = 0;
int i, t;
- ret = check_subprogs(env);
- if (ret < 0)
- return ret;
-
- insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_state)
return -ENOMEM;
- insn_stack = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+ insn_stack = env->cfg.insn_stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
if (!insn_stack) {
- kfree(insn_state);
+ kvfree(insn_state);
return -ENOMEM;
}
insn_state[0] = DISCOVERED; /* mark 1st insn as discovered */
insn_stack[0] = 0; /* 0 is the first instruction */
- cur_stack = 1;
+ env->cfg.cur_stack = 1;
peek_stack:
- if (cur_stack == 0)
+ if (env->cfg.cur_stack == 0)
goto check_state;
- t = insn_stack[cur_stack - 1];
+ t = insn_stack[env->cfg.cur_stack - 1];
- if (BPF_CLASS(insns[t].code) == BPF_JMP) {
+ if (BPF_CLASS(insns[t].code) == BPF_JMP ||
+ BPF_CLASS(insns[t].code) == BPF_JMP32) {
u8 opcode = BPF_OP(insns[t].code);
if (opcode == BPF_EXIT) {
goto mark_explored;
} else if (opcode == BPF_CALL) {
- ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
if (t + 1 < insn_cnt)
- env->explored_states[t + 1] = STATE_LIST_MARK;
+ init_explored_state(env, t + 1);
if (insns[t].src_reg == BPF_PSEUDO_CALL) {
- env->explored_states[t] = STATE_LIST_MARK;
- ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
+ init_explored_state(env, t);
+ ret = push_insn(t, t + insns[t].imm + 1, BRANCH,
+ env, false);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
@@ -4718,26 +8819,31 @@
}
/* unconditional jump with single edge */
ret = push_insn(t, t + insns[t].off + 1,
- FALLTHROUGH, env);
+ FALLTHROUGH, env, true);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
+ /* unconditional jmp is not a good pruning point,
+ * but it's marked, since backtracking needs
+ * to record jmp history in is_state_visited().
+ */
+ init_explored_state(env, t + insns[t].off + 1);
/* tell verifier to check for equivalent states
* after every call and jump
*/
if (t + 1 < insn_cnt)
- env->explored_states[t + 1] = STATE_LIST_MARK;
+ init_explored_state(env, t + 1);
} else {
/* conditional jump with two edges */
- env->explored_states[t] = STATE_LIST_MARK;
- ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ init_explored_state(env, t);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env, true);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
goto err_free;
- ret = push_insn(t, t + insns[t].off + 1, BRANCH, env);
+ ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
@@ -4747,7 +8853,7 @@
/* all other non-branch instructions with single
* fall-through edge
*/
- ret = push_insn(t, t + 1, FALLTHROUGH, env);
+ ret = push_insn(t, t + 1, FALLTHROUGH, env, false);
if (ret == 1)
goto peek_stack;
else if (ret < 0)
@@ -4756,7 +8862,7 @@
mark_explored:
insn_state[t] = EXPLORED;
- if (cur_stack-- <= 0) {
+ if (env->cfg.cur_stack-- <= 0) {
verbose(env, "pop stack internal bug\n");
ret = -EFAULT;
goto err_free;
@@ -4774,9 +8880,329 @@
ret = 0; /* cfg looks good */
err_free:
- kfree(insn_state);
- kfree(insn_stack);
+ kvfree(insn_state);
+ kvfree(insn_stack);
+ env->cfg.insn_state = env->cfg.insn_stack = NULL;
return ret;
+}
+
+static int check_abnormal_return(struct bpf_verifier_env *env)
+{
+ int i;
+
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (env->subprog_info[i].has_ld_abs) {
+ verbose(env, "LD_ABS is not allowed in subprogs without BTF\n");
+ return -EINVAL;
+ }
+ if (env->subprog_info[i].has_tail_call) {
+ verbose(env, "tail_call is not allowed in subprogs without BTF\n");
+ return -EINVAL;
+ }
+ }
+ return 0;
+}
+
+/* The minimum supported BTF func info size */
+#define MIN_BPF_FUNCINFO_SIZE 8
+#define MAX_FUNCINFO_REC_SIZE 252
+
+static int check_btf_func(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ const struct btf_type *type, *func_proto, *ret_type;
+ u32 i, nfuncs, urec_size, min_size;
+ u32 krec_size = sizeof(struct bpf_func_info);
+ struct bpf_func_info *krecord;
+ struct bpf_func_info_aux *info_aux = NULL;
+ struct bpf_prog *prog;
+ const struct btf *btf;
+ void __user *urecord;
+ u32 prev_offset = 0;
+ bool scalar_return;
+ int ret = -ENOMEM;
+
+ nfuncs = attr->func_info_cnt;
+ if (!nfuncs) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+
+ if (nfuncs != env->subprog_cnt) {
+ verbose(env, "number of funcs in func_info doesn't match number of subprogs\n");
+ return -EINVAL;
+ }
+
+ urec_size = attr->func_info_rec_size;
+ if (urec_size < MIN_BPF_FUNCINFO_SIZE ||
+ urec_size > MAX_FUNCINFO_REC_SIZE ||
+ urec_size % sizeof(u32)) {
+ verbose(env, "invalid func info rec size %u\n", urec_size);
+ return -EINVAL;
+ }
+
+ prog = env->prog;
+ btf = prog->aux->btf;
+
+ urecord = u64_to_user_ptr(attr->func_info);
+ min_size = min_t(u32, krec_size, urec_size);
+
+ krecord = kvcalloc(nfuncs, krec_size, GFP_KERNEL | __GFP_NOWARN);
+ if (!krecord)
+ return -ENOMEM;
+ info_aux = kcalloc(nfuncs, sizeof(*info_aux), GFP_KERNEL | __GFP_NOWARN);
+ if (!info_aux)
+ goto err_free;
+
+ for (i = 0; i < nfuncs; i++) {
+ ret = bpf_check_uarg_tail_zero(urecord, krec_size, urec_size);
+ if (ret) {
+ if (ret == -E2BIG) {
+ verbose(env, "nonzero tailing record in func info");
+ /* set the size kernel expects so loader can zero
+ * out the rest of the record.
+ */
+ if (put_user(min_size, &uattr->func_info_rec_size))
+ ret = -EFAULT;
+ }
+ goto err_free;
+ }
+
+ if (copy_from_user(&krecord[i], urecord, min_size)) {
+ ret = -EFAULT;
+ goto err_free;
+ }
+
+ /* check insn_off */
+ ret = -EINVAL;
+ if (i == 0) {
+ if (krecord[i].insn_off) {
+ verbose(env,
+ "nonzero insn_off %u for the first func info record",
+ krecord[i].insn_off);
+ goto err_free;
+ }
+ } else if (krecord[i].insn_off <= prev_offset) {
+ verbose(env,
+ "same or smaller insn offset (%u) than previous func info record (%u)",
+ krecord[i].insn_off, prev_offset);
+ goto err_free;
+ }
+
+ if (env->subprog_info[i].start != krecord[i].insn_off) {
+ verbose(env, "func_info BTF section doesn't match subprog layout in BPF program\n");
+ goto err_free;
+ }
+
+ /* check type_id */
+ type = btf_type_by_id(btf, krecord[i].type_id);
+ if (!type || !btf_type_is_func(type)) {
+ verbose(env, "invalid type id %d in func info",
+ krecord[i].type_id);
+ goto err_free;
+ }
+ info_aux[i].linkage = BTF_INFO_VLEN(type->info);
+
+ func_proto = btf_type_by_id(btf, type->type);
+ if (unlikely(!func_proto || !btf_type_is_func_proto(func_proto)))
+ /* btf_func_check() already verified it during BTF load */
+ goto err_free;
+ ret_type = btf_type_skip_modifiers(btf, func_proto->type, NULL);
+ scalar_return =
+ btf_type_is_small_int(ret_type) || btf_type_is_enum(ret_type);
+ if (i && !scalar_return && env->subprog_info[i].has_ld_abs) {
+ verbose(env, "LD_ABS is only allowed in functions that return 'int'.\n");
+ goto err_free;
+ }
+ if (i && !scalar_return && env->subprog_info[i].has_tail_call) {
+ verbose(env, "tail_call is only allowed in functions that return 'int'.\n");
+ goto err_free;
+ }
+
+ prev_offset = krecord[i].insn_off;
+ urecord += urec_size;
+ }
+
+ prog->aux->func_info = krecord;
+ prog->aux->func_info_cnt = nfuncs;
+ prog->aux->func_info_aux = info_aux;
+ return 0;
+
+err_free:
+ kvfree(krecord);
+ kfree(info_aux);
+ return ret;
+}
+
+static void adjust_btf_func(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ int i;
+
+ if (!aux->func_info)
+ return;
+
+ for (i = 0; i < env->subprog_cnt; i++)
+ aux->func_info[i].insn_off = env->subprog_info[i].start;
+}
+
+#define MIN_BPF_LINEINFO_SIZE (offsetof(struct bpf_line_info, line_col) + \
+ sizeof(((struct bpf_line_info *)(0))->line_col))
+#define MAX_LINEINFO_REC_SIZE MAX_FUNCINFO_REC_SIZE
+
+static int check_btf_line(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ u32 i, s, nr_linfo, ncopy, expected_size, rec_size, prev_offset = 0;
+ struct bpf_subprog_info *sub;
+ struct bpf_line_info *linfo;
+ struct bpf_prog *prog;
+ const struct btf *btf;
+ void __user *ulinfo;
+ int err;
+
+ nr_linfo = attr->line_info_cnt;
+ if (!nr_linfo)
+ return 0;
+ if (nr_linfo > INT_MAX / sizeof(struct bpf_line_info))
+ return -EINVAL;
+
+ rec_size = attr->line_info_rec_size;
+ if (rec_size < MIN_BPF_LINEINFO_SIZE ||
+ rec_size > MAX_LINEINFO_REC_SIZE ||
+ rec_size & (sizeof(u32) - 1))
+ return -EINVAL;
+
+ /* Need to zero it in case the userspace may
+ * pass in a smaller bpf_line_info object.
+ */
+ linfo = kvcalloc(nr_linfo, sizeof(struct bpf_line_info),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!linfo)
+ return -ENOMEM;
+
+ prog = env->prog;
+ btf = prog->aux->btf;
+
+ s = 0;
+ sub = env->subprog_info;
+ ulinfo = u64_to_user_ptr(attr->line_info);
+ expected_size = sizeof(struct bpf_line_info);
+ ncopy = min_t(u32, expected_size, rec_size);
+ for (i = 0; i < nr_linfo; i++) {
+ err = bpf_check_uarg_tail_zero(ulinfo, expected_size, rec_size);
+ if (err) {
+ if (err == -E2BIG) {
+ verbose(env, "nonzero tailing record in line_info");
+ if (put_user(expected_size,
+ &uattr->line_info_rec_size))
+ err = -EFAULT;
+ }
+ goto err_free;
+ }
+
+ if (copy_from_user(&linfo[i], ulinfo, ncopy)) {
+ err = -EFAULT;
+ goto err_free;
+ }
+
+ /*
+ * Check insn_off to ensure
+ * 1) strictly increasing AND
+ * 2) bounded by prog->len
+ *
+ * The linfo[0].insn_off == 0 check logically falls into
+ * the later "missing bpf_line_info for func..." case
+ * because the first linfo[0].insn_off must be the
+ * first sub also and the first sub must have
+ * subprog_info[0].start == 0.
+ */
+ if ((i && linfo[i].insn_off <= prev_offset) ||
+ linfo[i].insn_off >= prog->len) {
+ verbose(env, "Invalid line_info[%u].insn_off:%u (prev_offset:%u prog->len:%u)\n",
+ i, linfo[i].insn_off, prev_offset,
+ prog->len);
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ if (!prog->insnsi[linfo[i].insn_off].code) {
+ verbose(env,
+ "Invalid insn code at line_info[%u].insn_off\n",
+ i);
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ if (!btf_name_by_offset(btf, linfo[i].line_off) ||
+ !btf_name_by_offset(btf, linfo[i].file_name_off)) {
+ verbose(env, "Invalid line_info[%u].line_off or .file_name_off\n", i);
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ if (s != env->subprog_cnt) {
+ if (linfo[i].insn_off == sub[s].start) {
+ sub[s].linfo_idx = i;
+ s++;
+ } else if (sub[s].start < linfo[i].insn_off) {
+ verbose(env, "missing bpf_line_info for func#%u\n", s);
+ err = -EINVAL;
+ goto err_free;
+ }
+ }
+
+ prev_offset = linfo[i].insn_off;
+ ulinfo += rec_size;
+ }
+
+ if (s != env->subprog_cnt) {
+ verbose(env, "missing bpf_line_info for %u funcs starting from func#%u\n",
+ env->subprog_cnt - s, s);
+ err = -EINVAL;
+ goto err_free;
+ }
+
+ prog->aux->linfo = linfo;
+ prog->aux->nr_linfo = nr_linfo;
+
+ return 0;
+
+err_free:
+ kvfree(linfo);
+ return err;
+}
+
+static int check_btf_info(struct bpf_verifier_env *env,
+ const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct btf *btf;
+ int err;
+
+ if (!attr->func_info_cnt && !attr->line_info_cnt) {
+ if (check_abnormal_return(env))
+ return -EINVAL;
+ return 0;
+ }
+
+ btf = btf_get_by_fd(attr->prog_btf_fd);
+ if (IS_ERR(btf))
+ return PTR_ERR(btf);
+ env->prog->aux->btf = btf;
+
+ err = check_btf_func(env, attr, uattr);
+ if (err)
+ return err;
+
+ err = check_btf_line(env, attr, uattr);
+ if (err)
+ return err;
+
+ return 0;
}
/* check %cur's range satisfies %old's */
@@ -4786,7 +9212,11 @@
return old->umin_value <= cur->umin_value &&
old->umax_value >= cur->umax_value &&
old->smin_value <= cur->smin_value &&
- old->smax_value >= cur->smax_value;
+ old->smax_value >= cur->smax_value &&
+ old->u32_min_value <= cur->u32_min_value &&
+ old->u32_max_value >= cur->u32_max_value &&
+ old->s32_min_value <= cur->s32_min_value &&
+ old->s32_max_value >= cur->s32_max_value;
}
/* If in the old state two registers had the same id, then they need to have
@@ -4816,6 +9246,102 @@
/* We ran out of idmap slots, which should be impossible */
WARN_ON_ONCE(1);
return false;
+}
+
+static void clean_func_state(struct bpf_verifier_env *env,
+ struct bpf_func_state *st)
+{
+ enum bpf_reg_liveness live;
+ int i, j;
+
+ for (i = 0; i < BPF_REG_FP; i++) {
+ live = st->regs[i].live;
+ /* liveness must not touch this register anymore */
+ st->regs[i].live |= REG_LIVE_DONE;
+ if (!(live & REG_LIVE_READ))
+ /* since the register is unused, clear its state
+ * to make further comparison simpler
+ */
+ __mark_reg_not_init(env, &st->regs[i]);
+ }
+
+ for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
+ live = st->stack[i].spilled_ptr.live;
+ /* liveness must not touch this stack slot anymore */
+ st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
+ if (!(live & REG_LIVE_READ)) {
+ __mark_reg_not_init(env, &st->stack[i].spilled_ptr);
+ for (j = 0; j < BPF_REG_SIZE; j++)
+ st->stack[i].slot_type[j] = STACK_INVALID;
+ }
+ }
+}
+
+static void clean_verifier_state(struct bpf_verifier_env *env,
+ struct bpf_verifier_state *st)
+{
+ int i;
+
+ if (st->frame[0]->regs[0].live & REG_LIVE_DONE)
+ /* all regs in this state in all frames were already marked */
+ return;
+
+ for (i = 0; i <= st->curframe; i++)
+ clean_func_state(env, st->frame[i]);
+}
+
+/* the parentage chains form a tree.
+ * the verifier states are added to state lists at given insn and
+ * pushed into state stack for future exploration.
+ * when the verifier reaches bpf_exit insn some of the verifer states
+ * stored in the state lists have their final liveness state already,
+ * but a lot of states will get revised from liveness point of view when
+ * the verifier explores other branches.
+ * Example:
+ * 1: r0 = 1
+ * 2: if r1 == 100 goto pc+1
+ * 3: r0 = 2
+ * 4: exit
+ * when the verifier reaches exit insn the register r0 in the state list of
+ * insn 2 will be seen as !REG_LIVE_READ. Then the verifier pops the other_branch
+ * of insn 2 and goes exploring further. At the insn 4 it will walk the
+ * parentage chain from insn 4 into insn 2 and will mark r0 as REG_LIVE_READ.
+ *
+ * Since the verifier pushes the branch states as it sees them while exploring
+ * the program the condition of walking the branch instruction for the second
+ * time means that all states below this branch were already explored and
+ * their final liveness markes are already propagated.
+ * Hence when the verifier completes the search of state list in is_state_visited()
+ * we can call this clean_live_states() function to mark all liveness states
+ * as REG_LIVE_DONE to indicate that 'parent' pointers of 'struct bpf_reg_state'
+ * will not be used.
+ * This function also clears the registers and stack for states that !READ
+ * to simplify state merging.
+ *
+ * Important note here that walking the same branch instruction in the callee
+ * doesn't meant that the states are DONE. The verifier has to compare
+ * the callsites
+ */
+static void clean_live_states(struct bpf_verifier_env *env, int insn,
+ struct bpf_verifier_state *cur)
+{
+ struct bpf_verifier_state_list *sl;
+ int i;
+
+ sl = *explored_state(env, insn);
+ while (sl) {
+ if (sl->state.branches)
+ goto next;
+ if (sl->state.insn_idx != insn ||
+ sl->state.curframe != cur->curframe)
+ goto next;
+ for (i = 0; i <= cur->curframe; i++)
+ if (sl->state.frame[i]->callsite != cur->frame[i]->callsite)
+ goto next;
+ clean_verifier_state(env, &sl->state);
+next:
+ sl = sl->next;
+ }
}
/* Returns true if (rold safe implies rcur safe) */
@@ -4849,6 +9375,8 @@
if (env->explore_alu_limits)
return false;
if (rcur->type == SCALAR_VALUE) {
+ if (!rold->precise)
+ return true;
/* new val must satisfy old val knowledge */
return range_within(rold, rcur) &&
tnum_in(rold->var_off, rcur->var_off);
@@ -4865,8 +9393,11 @@
case PTR_TO_MAP_VALUE:
/* If the new min/max/var_off satisfy the old ones and
* everything else matches, we are OK.
- * We don't care about the 'id' value, because nothing
- * uses it for PTR_TO_MAP_VALUE (only for ..._OR_NULL)
+ * 'id' is not compared, since it's only used for maps with
+ * bpf_spin_lock inside map element and in such cases if
+ * the rest of the prog is valid for one map element then
+ * it's valid for all map elements regardless of the key
+ * used in bpf_map_lookup()
*/
return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 &&
range_within(rold, rcur) &&
@@ -4911,6 +9442,14 @@
case PTR_TO_CTX:
case CONST_PTR_TO_MAP:
case PTR_TO_PACKET_END:
+ case PTR_TO_FLOW_KEYS:
+ case PTR_TO_SOCKET:
+ case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
+ case PTR_TO_XDP_SOCK:
/* Only valid matches are exact, which memcmp() above
* would have accepted
*/
@@ -4929,12 +9468,6 @@
{
int i, spi;
- /* if explored stack has more populated slots than current stack
- * such stacks are not equivalent
- */
- if (old->allocated_stack > cur->allocated_stack)
- return false;
-
/* walk slots of the explored stack and ignore any additional
* slots in the current stack, since explored(safe) state
* didn't use them
@@ -4942,12 +9475,21 @@
for (i = 0; i < old->allocated_stack; i++) {
spi = i / BPF_REG_SIZE;
- if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)) {
+ i += BPF_REG_SIZE - 1;
/* explored state didn't use this */
continue;
+ }
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
continue;
+
+ /* explored stack has more populated slots than current stack
+ * and these slots were used
+ */
+ if (i >= cur->allocated_stack)
+ return false;
+
/* if old state was safe with misc data in the stack
* it will be safe with zero-initialized stack.
* The opposite is not true
@@ -4958,14 +9500,14 @@
if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
cur->stack[spi].slot_type[i % BPF_REG_SIZE])
/* Ex: old explored (safe) state has STACK_SPILL in
- * this stack slot, but current has has STACK_MISC ->
+ * this stack slot, but current has STACK_MISC ->
* this verifier states are not equivalent,
* return false to continue verification of this path
*/
return false;
- if (i % BPF_REG_SIZE)
+ if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1)
continue;
- if (old->stack[spi].slot_type[0] != STACK_SPILL)
+ if (!is_spilled_reg(&old->stack[spi]))
continue;
if (!regsafe(env, &old->stack[spi].spilled_ptr,
&cur->stack[spi].spilled_ptr, idmap))
@@ -4982,6 +9524,14 @@
return false;
}
return true;
+}
+
+static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur)
+{
+ if (old->acquired_refs != cur->acquired_refs)
+ return false;
+ return !memcmp(old->refs, cur->refs,
+ sizeof(*old->refs) * old->acquired_refs);
}
/* compare two verifier states
@@ -5024,6 +9574,9 @@
if (!stacksafe(env, old, cur, env->idmap_scratch))
return false;
+ if (!refsafe(old, cur))
+ return false;
+
return true;
}
@@ -5042,6 +9595,9 @@
if (old->speculative && !cur->speculative)
return false;
+ if (old->active_spin_lock != cur->active_spin_lock)
+ return false;
+
/* for states to be equal callsites have to be the same
* and all frame states need to be equivalent
*/
@@ -5052,6 +9608,35 @@
return false;
}
return true;
+}
+
+/* Return 0 if no propagation happened. Return negative error code if error
+ * happened. Otherwise, return the propagated bit.
+ */
+static int propagate_liveness_reg(struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg,
+ struct bpf_reg_state *parent_reg)
+{
+ u8 parent_flag = parent_reg->live & REG_LIVE_READ;
+ u8 flag = reg->live & REG_LIVE_READ;
+ int err;
+
+ /* When comes here, read flags of PARENT_REG or REG could be any of
+ * REG_LIVE_READ64, REG_LIVE_READ32, REG_LIVE_NONE. There is no need
+ * of propagation if PARENT_REG has strongest REG_LIVE_READ64.
+ */
+ if (parent_flag == REG_LIVE_READ64 ||
+ /* Or if there is no read flag from REG. */
+ !flag ||
+ /* Or if the read flag from REG is the same as PARENT_REG. */
+ parent_flag == flag)
+ return 0;
+
+ err = mark_reg_read(env, reg, parent_reg, flag);
+ if (err)
+ return err;
+
+ return flag;
}
/* A write screens off any subsequent reads; but write marks come from the
@@ -5065,8 +9650,9 @@
const struct bpf_verifier_state *vstate,
struct bpf_verifier_state *vparent)
{
- int i, frame, err = 0;
+ struct bpf_reg_state *state_reg, *parent_reg;
struct bpf_func_state *state, *parent;
+ int i, frame, err = 0;
if (vparent->curframe != vstate->curframe) {
WARN(1, "propagate_live: parent frame %d current frame %d\n",
@@ -5075,50 +9661,160 @@
}
/* Propagate read liveness of registers... */
BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
- /* We don't need to worry about FP liveness because it's read-only */
- for (i = 0; i < BPF_REG_FP; i++) {
- if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
- continue;
- if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
- err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i],
- &vparent->frame[vstate->curframe]->regs[i]);
- if (err)
+ for (frame = 0; frame <= vstate->curframe; frame++) {
+ parent = vparent->frame[frame];
+ state = vstate->frame[frame];
+ parent_reg = parent->regs;
+ state_reg = state->regs;
+ /* We don't need to worry about FP liveness, it's read-only */
+ for (i = frame < vstate->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++) {
+ err = propagate_liveness_reg(env, &state_reg[i],
+ &parent_reg[i]);
+ if (err < 0)
+ return err;
+ if (err == REG_LIVE_READ64)
+ mark_insn_zext(env, &parent_reg[i]);
+ }
+
+ /* Propagate stack slots. */
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
+ i < parent->allocated_stack / BPF_REG_SIZE; i++) {
+ parent_reg = &parent->stack[i].spilled_ptr;
+ state_reg = &state->stack[i].spilled_ptr;
+ err = propagate_liveness_reg(env, state_reg,
+ parent_reg);
+ if (err < 0)
return err;
}
}
+ return 0;
+}
- /* ... and stack slots */
- for (frame = 0; frame <= vstate->curframe; frame++) {
- state = vstate->frame[frame];
- parent = vparent->frame[frame];
- for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
- i < parent->allocated_stack / BPF_REG_SIZE; i++) {
- if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
+/* find precise scalars in the previous equivalent state and
+ * propagate them into the current state
+ */
+static int propagate_precision(struct bpf_verifier_env *env,
+ const struct bpf_verifier_state *old)
+{
+ struct bpf_reg_state *state_reg;
+ struct bpf_func_state *state;
+ int i, err = 0, fr;
+
+ for (fr = old->curframe; fr >= 0; fr--) {
+ state = old->frame[fr];
+ state_reg = state->regs;
+ for (i = 0; i < BPF_REG_FP; i++, state_reg++) {
+ if (state_reg->type != SCALAR_VALUE ||
+ !state_reg->precise ||
+ !(state_reg->live & REG_LIVE_READ))
continue;
- if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
- mark_reg_read(env, &state->stack[i].spilled_ptr,
- &parent->stack[i].spilled_ptr);
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "frame %d: propagating r%d\n", fr, i);
+ err = mark_chain_precision_frame(env, fr, i);
+ if (err < 0)
+ return err;
+ }
+
+ for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ if (!is_spilled_reg(&state->stack[i]))
+ continue;
+ state_reg = &state->stack[i].spilled_ptr;
+ if (state_reg->type != SCALAR_VALUE ||
+ !state_reg->precise ||
+ !(state_reg->live & REG_LIVE_READ))
+ continue;
+ if (env->log.level & BPF_LOG_LEVEL2)
+ verbose(env, "frame %d: propagating fp%d\n",
+ fr, (-i - 1) * BPF_REG_SIZE);
+ err = mark_chain_precision_stack_frame(env, fr, i);
+ if (err < 0)
+ return err;
}
}
- return err;
+ return 0;
}
+
+static bool states_maybe_looping(struct bpf_verifier_state *old,
+ struct bpf_verifier_state *cur)
+{
+ struct bpf_func_state *fold, *fcur;
+ int i, fr = cur->curframe;
+
+ if (old->curframe != fr)
+ return false;
+
+ fold = old->frame[fr];
+ fcur = cur->frame[fr];
+ for (i = 0; i < MAX_BPF_REG; i++)
+ if (memcmp(&fold->regs[i], &fcur->regs[i],
+ offsetof(struct bpf_reg_state, parent)))
+ return false;
+ return true;
+}
+
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
{
struct bpf_verifier_state_list *new_sl;
- struct bpf_verifier_state_list *sl;
+ struct bpf_verifier_state_list *sl, **pprev;
struct bpf_verifier_state *cur = env->cur_state, *new;
int i, j, err, states_cnt = 0;
+ bool add_new_state = env->test_state_freq ? true : false;
- sl = env->explored_states[insn_idx];
- if (!sl)
+ cur->last_insn_idx = env->prev_insn_idx;
+ if (!env->insn_aux_data[insn_idx].prune_point)
/* this 'insn_idx' instruction wasn't marked, so we will not
* be doing state search here
*/
return 0;
- while (sl != STATE_LIST_MARK) {
+ /* bpf progs typically have pruning point every 4 instructions
+ * http://vger.kernel.org/bpfconf2019.html#session-1
+ * Do not add new state for future pruning if the verifier hasn't seen
+ * at least 2 jumps and at least 8 instructions.
+ * This heuristics helps decrease 'total_states' and 'peak_states' metric.
+ * In tests that amounts to up to 50% reduction into total verifier
+ * memory consumption and 20% verifier time speedup.
+ */
+ if (env->jmps_processed - env->prev_jmps_processed >= 2 &&
+ env->insn_processed - env->prev_insn_processed >= 8)
+ add_new_state = true;
+
+ pprev = explored_state(env, insn_idx);
+ sl = *pprev;
+
+ clean_live_states(env, insn_idx, cur);
+
+ while (sl) {
+ states_cnt++;
+ if (sl->state.insn_idx != insn_idx)
+ goto next;
+ if (sl->state.branches) {
+ if (states_maybe_looping(&sl->state, cur) &&
+ states_equal(env, &sl->state, cur)) {
+ verbose_linfo(env, insn_idx, "; ");
+ verbose(env, "infinite loop detected at insn %d\n", insn_idx);
+ return -EINVAL;
+ }
+ /* if the verifier is processing a loop, avoid adding new state
+ * too often, since different loop iterations have distinct
+ * states and may not help future pruning.
+ * This threshold shouldn't be too low to make sure that
+ * a loop with large bound will be rejected quickly.
+ * The most abusive loop will be:
+ * r1 += 1
+ * if r1 < 1000000 goto pc-2
+ * 1M insn_procssed limit / 100 == 10k peak states.
+ * This threshold shouldn't be too high either, since states
+ * at the end of the loop are likely to be useful in pruning.
+ */
+ if (env->jmps_processed - env->prev_jmps_processed < 20 &&
+ env->insn_processed - env->prev_insn_processed < 100)
+ add_new_state = false;
+ goto miss;
+ }
if (states_equal(env, &sl->state, cur)) {
+ sl->hit_cnt++;
/* reached equivalent register/stack state,
* prune the search.
* Registers read by the continuation are read by us.
@@ -5130,27 +9826,91 @@
* this state and will pop a new one.
*/
err = propagate_liveness(env, &sl->state, cur);
+
+ /* if previous state reached the exit with precision and
+ * current state is equivalent to it (except precsion marks)
+ * the precision needs to be propagated back in
+ * the current state.
+ */
+ err = err ? : push_jmp_history(env, cur);
+ err = err ? : propagate_precision(env, &sl->state);
if (err)
return err;
return 1;
}
- sl = sl->next;
- states_cnt++;
+miss:
+ /* when new state is not going to be added do not increase miss count.
+ * Otherwise several loop iterations will remove the state
+ * recorded earlier. The goal of these heuristics is to have
+ * states from some iterations of the loop (some in the beginning
+ * and some at the end) to help pruning.
+ */
+ if (add_new_state)
+ sl->miss_cnt++;
+ /* heuristic to determine whether this state is beneficial
+ * to keep checking from state equivalence point of view.
+ * Higher numbers increase max_states_per_insn and verification time,
+ * but do not meaningfully decrease insn_processed.
+ */
+ if (sl->miss_cnt > sl->hit_cnt * 3 + 3) {
+ /* the state is unlikely to be useful. Remove it to
+ * speed up verification
+ */
+ *pprev = sl->next;
+ if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE) {
+ u32 br = sl->state.branches;
+
+ WARN_ONCE(br,
+ "BUG live_done but branches_to_explore %d\n",
+ br);
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ env->peak_states--;
+ } else {
+ /* cannot free this state, since parentage chain may
+ * walk it later. Add it for free_list instead to
+ * be freed at the end of verification
+ */
+ sl->next = env->free_list;
+ env->free_list = sl;
+ }
+ sl = *pprev;
+ continue;
+ }
+next:
+ pprev = &sl->next;
+ sl = *pprev;
}
- if (!env->allow_ptr_leaks && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
- return 0;
+ if (env->max_states_per_insn < states_cnt)
+ env->max_states_per_insn = states_cnt;
- /* there were no equivalent states, remember current one.
- * technically the current state is not proven to be safe yet,
+ if (!env->bpf_capable && states_cnt > BPF_COMPLEXITY_LIMIT_STATES)
+ return push_jmp_history(env, cur);
+
+ if (!add_new_state)
+ return push_jmp_history(env, cur);
+
+ /* There were no equivalent states, remember the current one.
+ * Technically the current state is not proven to be safe yet,
* but it will either reach outer most bpf_exit (which means it's safe)
- * or it will be rejected. Since there are no loops, we won't be
+ * or it will be rejected. When there are no loops the verifier won't be
* seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
- * again on the way to bpf_exit
+ * again on the way to bpf_exit.
+ * When looping the sl->state.branches will be > 0 and this state
+ * will not be considered for equivalence until branches == 0.
*/
new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
if (!new_sl)
return -ENOMEM;
+ env->total_states++;
+ env->peak_states++;
+ env->prev_jmps_processed = env->jmps_processed;
+ env->prev_insn_processed = env->insn_processed;
+
+ /* forget precise markings we inherited, see __mark_chain_precision */
+ if (env->bpf_capable)
+ mark_all_scalars_imprecise(env, cur);
/* add new state to the head of linked list */
new = &new_sl->state;
@@ -5160,19 +9920,34 @@
kfree(new_sl);
return err;
}
- new_sl->next = env->explored_states[insn_idx];
- env->explored_states[insn_idx] = new_sl;
- /* connect new state to parentage chain */
- for (i = 0; i < BPF_REG_FP; i++)
- cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i];
+ new->insn_idx = insn_idx;
+ WARN_ONCE(new->branches != 1,
+ "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx);
+
+ cur->parent = new;
+ cur->first_insn_idx = insn_idx;
+ clear_jmp_history(cur);
+ new_sl->next = *explored_state(env, insn_idx);
+ *explored_state(env, insn_idx) = new_sl;
+ /* connect new state to parentage chain. Current frame needs all
+ * registers connected. Only r6 - r9 of the callers are alive (pushed
+ * to the stack implicitly by JITs) so in callers' frames connect just
+ * r6 - r9 as an optimization. Callers will have r1 - r5 connected to
+ * the state of the call instruction (with WRITTEN set), and r0 comes
+ * from callee with its full parentage chain, anyway.
+ */
/* clear write marks in current state: the writes we did are not writes
* our child did, so they don't screen off its reads from us.
* (There are no read marks in current state, because reads always mark
* their parent and current state never has children yet. Only
* explored_states can get read marks.)
*/
- for (i = 0; i < BPF_REG_FP; i++)
- cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;
+ for (j = 0; j <= cur->curframe; j++) {
+ for (i = j < cur->curframe ? BPF_REG_6 : 0; i < BPF_REG_FP; i++)
+ cur->frame[j]->regs[i].parent = &new->frame[j]->regs[i];
+ for (i = 0; i < BPF_REG_FP; i++)
+ cur->frame[j]->regs[i].live = REG_LIVE_NONE;
+ }
/* all stack frames are accessible from callee, clear them all */
for (j = 0; j <= cur->curframe; j++) {
@@ -5188,36 +9963,60 @@
return 0;
}
+/* Return true if it's OK to have the same insn return a different type. */
+static bool reg_type_mismatch_ok(enum bpf_reg_type type)
+{
+ switch (type) {
+ case PTR_TO_CTX:
+ case PTR_TO_SOCKET:
+ case PTR_TO_SOCKET_OR_NULL:
+ case PTR_TO_SOCK_COMMON:
+ case PTR_TO_SOCK_COMMON_OR_NULL:
+ case PTR_TO_TCP_SOCK:
+ case PTR_TO_TCP_SOCK_OR_NULL:
+ case PTR_TO_XDP_SOCK:
+ case PTR_TO_BTF_ID:
+ case PTR_TO_BTF_ID_OR_NULL:
+ return false;
+ default:
+ return true;
+ }
+}
+
+/* If an instruction was previously used with particular pointer types, then we
+ * need to be careful to avoid cases such as the below, where it may be ok
+ * for one branch accessing the pointer, but not ok for the other branch:
+ *
+ * R1 = sock_ptr
+ * goto X;
+ * ...
+ * R1 = some_other_valid_ptr;
+ * goto X;
+ * ...
+ * R2 = *(u32 *)(R1 + 0);
+ */
+static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
+{
+ return src != prev && (!reg_type_mismatch_ok(src) ||
+ !reg_type_mismatch_ok(prev));
+}
+
static int do_check(struct bpf_verifier_env *env)
{
- struct bpf_verifier_state *state;
+ bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+ struct bpf_verifier_state *state = env->cur_state;
struct bpf_insn *insns = env->prog->insnsi;
struct bpf_reg_state *regs;
- int insn_cnt = env->prog->len, i;
- int insn_processed = 0;
+ int insn_cnt = env->prog->len;
bool do_print_state = false;
-
- state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
- if (!state)
- return -ENOMEM;
- state->curframe = 0;
- state->speculative = false;
- state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
- if (!state->frame[0]) {
- kfree(state);
- return -ENOMEM;
- }
- env->cur_state = state;
- init_func_state(env, state->frame[0],
- BPF_MAIN_FUNC /* callsite */,
- 0 /* frameno */,
- 0 /* subprogno, zero == main subprog */);
+ int prev_insn_idx = -1;
for (;;) {
struct bpf_insn *insn;
u8 class;
int err;
+ env->prev_insn_idx = prev_insn_idx;
if (env->insn_idx >= insn_cnt) {
verbose(env, "invalid insn idx %d insn_cnt %d\n",
env->insn_idx, insn_cnt);
@@ -5227,10 +10026,10 @@
insn = &insns[env->insn_idx];
class = BPF_CLASS(insn->code);
- if (++insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
+ if (++env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
verbose(env,
"BPF program is too large. Processed %d insn\n",
- insn_processed);
+ env->insn_processed);
return -E2BIG;
}
@@ -5239,7 +10038,7 @@
return err;
if (err == 1) {
/* found equivalent state, can prune the search */
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
if (do_print_state)
verbose(env, "\nfrom %d to %d%s: safe\n",
env->prev_insn_idx, env->insn_idx,
@@ -5257,8 +10056,9 @@
if (need_resched())
cond_resched();
- if (env->log.level > 1 || (env->log.level && do_print_state)) {
- if (env->log.level > 1)
+ if (env->log.level & BPF_LOG_LEVEL2 ||
+ (env->log.level & BPF_LOG_LEVEL && do_print_state)) {
+ if (env->log.level & BPF_LOG_LEVEL2)
verbose(env, "%d:", env->insn_idx);
else
verbose(env, "\nfrom %d to %d%s:",
@@ -5269,12 +10069,13 @@
do_print_state = false;
}
- if (env->log.level) {
+ if (env->log.level & BPF_LOG_LEVEL) {
const struct bpf_insn_cbs cbs = {
.cb_print = verbose,
.private_data = env,
};
+ verbose_linfo(env, env->insn_idx, "; ");
verbose(env, "%d: ", env->insn_idx);
print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}
@@ -5288,6 +10089,7 @@
regs = cur_regs(env);
sanitize_mark_insn_seen(env);
+ prev_insn_idx = env->insn_idx;
if (class == BPF_ALU || class == BPF_ALU64) {
err = check_alu_op(env, insn);
@@ -5328,9 +10130,7 @@
*/
*prev_src_type = src_reg_type;
- } else if (src_reg_type != *prev_src_type &&
- (src_reg_type == PTR_TO_CTX ||
- *prev_src_type == PTR_TO_CTX)) {
+ } else if (reg_type_mismatch(src_reg_type, *prev_src_type)) {
/* ABuser program is trying to use the same insn
* dst_reg = *(u32*) (src_reg + off)
* with different pointer types:
@@ -5375,9 +10175,7 @@
if (*prev_dst_type == NOT_INIT) {
*prev_dst_type = dst_reg_type;
- } else if (dst_reg_type != *prev_dst_type &&
- (dst_reg_type == PTR_TO_CTX ||
- *prev_dst_type == PTR_TO_CTX)) {
+ } else if (reg_type_mismatch(dst_reg_type, *prev_dst_type)) {
verbose(env, "same insn cannot be used with different pointers\n");
return -EINVAL;
}
@@ -5394,8 +10192,9 @@
return err;
if (is_ctx_reg(env, insn->dst_reg)) {
- verbose(env, "BPF_ST stores into R%d context is not allowed\n",
- insn->dst_reg);
+ verbose(env, "BPF_ST stores into R%d %s is not allowed\n",
+ insn->dst_reg,
+ reg_type_str[reg_state(env, insn->dst_reg)->type]);
return -EACCES;
}
@@ -5406,19 +10205,27 @@
if (err)
return err;
- } else if (class == BPF_JMP) {
+ } else if (class == BPF_JMP || class == BPF_JMP32) {
u8 opcode = BPF_OP(insn->code);
+ env->jmps_processed++;
if (opcode == BPF_CALL) {
if (BPF_SRC(insn->code) != BPF_K ||
insn->off != 0 ||
(insn->src_reg != BPF_REG_0 &&
insn->src_reg != BPF_PSEUDO_CALL) ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_CALL uses reserved fields\n");
return -EINVAL;
}
+ if (env->cur_state->active_spin_lock &&
+ (insn->src_reg == BPF_PSEUDO_CALL ||
+ insn->imm != BPF_FUNC_spin_unlock)) {
+ verbose(env, "function calls are not allowed while holding a lock\n");
+ return -EINVAL;
+ }
if (insn->src_reg == BPF_PSEUDO_CALL)
err = check_func_call(env, insn, &env->insn_idx);
else
@@ -5430,7 +10237,8 @@
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_JA uses reserved fields\n");
return -EINVAL;
}
@@ -5442,14 +10250,19 @@
if (BPF_SRC(insn->code) != BPF_K ||
insn->imm != 0 ||
insn->src_reg != BPF_REG_0 ||
- insn->dst_reg != BPF_REG_0) {
+ insn->dst_reg != BPF_REG_0 ||
+ class == BPF_JMP32) {
verbose(env, "BPF_EXIT uses reserved fields\n");
+ return -EINVAL;
+ }
+
+ if (env->cur_state->active_spin_lock) {
+ verbose(env, "bpf_spin_unlock is missing\n");
return -EINVAL;
}
if (state->curframe) {
/* exit from nested function */
- env->prev_insn_idx = env->insn_idx;
err = prepare_func_exit(env, &env->insn_idx);
if (err)
return err;
@@ -5457,27 +10270,17 @@
continue;
}
- /* eBPF calling convetion is such that R0 is used
- * to return the value from eBPF program.
- * Make sure that it's readable at this time
- * of bpf_exit, which means that program wrote
- * something into it earlier
- */
- err = check_reg_arg(env, BPF_REG_0, SRC_OP);
+ err = check_reference_leak(env);
if (err)
return err;
-
- if (is_pointer_value(env, BPF_REG_0)) {
- verbose(env, "R0 leaks addr as return value\n");
- return -EACCES;
- }
err = check_return_code(env);
if (err)
return err;
process_bpf_exit:
- err = pop_stack(env, &env->prev_insn_idx,
- &env->insn_idx);
+ update_branch_counts(env, env->cur_state);
+ err = pop_stack(env, &prev_insn_idx,
+ &env->insn_idx, pop_log);
if (err < 0) {
if (err != -ENOENT)
return err;
@@ -5518,17 +10321,93 @@
env->insn_idx++;
}
- verbose(env, "processed %d insns (limit %d), stack depth ",
- insn_processed, BPF_COMPLEXITY_LIMIT_INSNS);
- for (i = 0; i < env->subprog_cnt; i++) {
- u32 depth = env->subprog_info[i].stack_depth;
+ return 0;
+}
- verbose(env, "%d", depth);
- if (i + 1 < env->subprog_cnt)
- verbose(env, "+");
+/* replace pseudo btf_id with kernel symbol address */
+static int check_pseudo_btf_id(struct bpf_verifier_env *env,
+ struct bpf_insn *insn,
+ struct bpf_insn_aux_data *aux)
+{
+ const struct btf_var_secinfo *vsi;
+ const struct btf_type *datasec;
+ const struct btf_type *t;
+ const char *sym_name;
+ bool percpu = false;
+ u32 type, id = insn->imm;
+ s32 datasec_id;
+ u64 addr;
+ int i;
+
+ if (!btf_vmlinux) {
+ verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
+ return -EINVAL;
}
- verbose(env, "\n");
- env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+
+ if (insn[1].imm != 0) {
+ verbose(env, "reserved field (insn[1].imm) is used in pseudo_btf_id ldimm64 insn.\n");
+ return -EINVAL;
+ }
+
+ t = btf_type_by_id(btf_vmlinux, id);
+ if (!t) {
+ verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
+ return -ENOENT;
+ }
+
+ if (!btf_type_is_var(t)) {
+ verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR.\n",
+ id);
+ return -EINVAL;
+ }
+
+ sym_name = btf_name_by_offset(btf_vmlinux, t->name_off);
+ addr = kallsyms_lookup_name(sym_name);
+ if (!addr) {
+ verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
+ sym_name);
+ return -ENOENT;
+ }
+
+ datasec_id = btf_find_by_name_kind(btf_vmlinux, ".data..percpu",
+ BTF_KIND_DATASEC);
+ if (datasec_id > 0) {
+ datasec = btf_type_by_id(btf_vmlinux, datasec_id);
+ for_each_vsi(i, datasec, vsi) {
+ if (vsi->type == id) {
+ percpu = true;
+ break;
+ }
+ }
+ }
+
+ insn[0].imm = (u32)addr;
+ insn[1].imm = addr >> 32;
+
+ type = t->type;
+ t = btf_type_skip_modifiers(btf_vmlinux, type, NULL);
+ if (percpu) {
+ aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID;
+ aux->btf_var.btf_id = type;
+ } else if (!btf_type_is_struct(t)) {
+ const struct btf_type *ret;
+ const char *tname;
+ u32 tsize;
+
+ /* resolve the type size of ksym. */
+ ret = btf_resolve_size(btf_vmlinux, t, &tsize);
+ if (IS_ERR(ret)) {
+ tname = btf_name_by_offset(btf_vmlinux, t->name_off);
+ verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
+ tname, PTR_ERR(ret));
+ return -EINVAL;
+ }
+ aux->btf_var.reg_type = PTR_TO_MEM;
+ aux->btf_var.mem_size = tsize;
+ } else {
+ aux->btf_var.reg_type = PTR_TO_BTF_ID;
+ aux->btf_var.btf_id = type;
+ }
return 0;
}
@@ -5540,26 +10419,69 @@
!(map->map_flags & BPF_F_NO_PREALLOC);
}
+static bool is_tracing_prog_type(enum bpf_prog_type type)
+{
+ switch (type) {
+ case BPF_PROG_TYPE_KPROBE:
+ case BPF_PROG_TYPE_TRACEPOINT:
+ case BPF_PROG_TYPE_PERF_EVENT:
+ case BPF_PROG_TYPE_RAW_TRACEPOINT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static bool is_preallocated_map(struct bpf_map *map)
+{
+ if (!check_map_prealloc(map))
+ return false;
+ if (map->inner_map_meta && !check_map_prealloc(map->inner_map_meta))
+ return false;
+ return true;
+}
+
static int check_map_prog_compatibility(struct bpf_verifier_env *env,
struct bpf_map *map,
struct bpf_prog *prog)
{
- /* Make sure that BPF_PROG_TYPE_PERF_EVENT programs only use
- * preallocated hash maps, since doing memory allocation
- * in overflow_handler can crash depending on where nmi got
- * triggered.
+ enum bpf_prog_type prog_type = resolve_prog_type(prog);
+ /*
+ * Validate that trace type programs use preallocated hash maps.
+ *
+ * For programs attached to PERF events this is mandatory as the
+ * perf NMI can hit any arbitrary code sequence.
+ *
+ * All other trace types using preallocated hash maps are unsafe as
+ * well because tracepoint or kprobes can be inside locked regions
+ * of the memory allocator or at a place where a recursion into the
+ * memory allocator would see inconsistent state.
+ *
+ * On RT enabled kernels run-time allocation of all trace type
+ * programs is strictly prohibited due to lock type constraints. On
+ * !RT kernels it is allowed for backwards compatibility reasons for
+ * now, but warnings are emitted so developers are made aware of
+ * the unsafety and can fix their programs before this is enforced.
*/
- if (prog->type == BPF_PROG_TYPE_PERF_EVENT) {
- if (!check_map_prealloc(map)) {
+ if (is_tracing_prog_type(prog_type) && !is_preallocated_map(map)) {
+ if (prog_type == BPF_PROG_TYPE_PERF_EVENT) {
verbose(env, "perf_event programs can only use preallocated hash map\n");
return -EINVAL;
}
- if (map->inner_map_meta &&
- !check_map_prealloc(map->inner_map_meta)) {
- verbose(env, "perf_event programs can only use preallocated inner hash map\n");
+ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+ verbose(env, "trace type programs can only use preallocated hash map\n");
return -EINVAL;
}
+ WARN_ONCE(1, "trace type BPF program uses run-time allocation\n");
+ verbose(env, "trace type programs with run-time allocated hash maps are unsafe. Switch to preallocated hash maps.\n");
+ }
+
+ if ((is_tracing_prog_type(prog_type) ||
+ prog_type == BPF_PROG_TYPE_SOCKET_FILTER) &&
+ map_value_has_spin_lock(map)) {
+ verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
+ return -EINVAL;
}
if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
@@ -5568,13 +10490,45 @@
return -EINVAL;
}
+ if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
+ verbose(env, "bpf_struct_ops map cannot be used in prog\n");
+ return -EINVAL;
+ }
+
+ if (prog->aux->sleepable)
+ switch (map->map_type) {
+ case BPF_MAP_TYPE_HASH:
+ case BPF_MAP_TYPE_LRU_HASH:
+ case BPF_MAP_TYPE_ARRAY:
+ if (!is_preallocated_map(map)) {
+ verbose(env,
+ "Sleepable programs can only use preallocated hash maps\n");
+ return -EINVAL;
+ }
+ break;
+ default:
+ verbose(env,
+ "Sleepable programs can only use array and hash maps\n");
+ return -EINVAL;
+ }
+
return 0;
}
-/* look for pseudo eBPF instructions that access map FDs and
- * replace them with actual map pointers
+static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
+{
+ return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
+ map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
+}
+
+/* find and rewrite pseudo imm in ld_imm64 instructions:
+ *
+ * 1. if it accesses map FD, replace it with actual map pointer.
+ * 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
+ *
+ * NOTE: btf_vmlinux is required for converting pseudo btf_id.
*/
-static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
+static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env)
{
struct bpf_insn *insn = env->prog->insnsi;
int insn_cnt = env->prog->len;
@@ -5599,8 +10553,10 @@
}
if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
+ struct bpf_insn_aux_data *aux;
struct bpf_map *map;
struct fd f;
+ u64 addr;
if (i == insn_cnt - 1 || insn[1].code != 0 ||
insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
@@ -5609,21 +10565,35 @@
return -EINVAL;
}
- if (insn->src_reg == 0)
+ if (insn[0].src_reg == 0)
/* valid generic load 64-bit imm */
goto next_insn;
- if (insn->src_reg != BPF_PSEUDO_MAP_FD) {
+ if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
+ aux = &env->insn_aux_data[i];
+ err = check_pseudo_btf_id(env, insn, aux);
+ if (err)
+ return err;
+ goto next_insn;
+ }
+
+ /* In final convert_pseudo_ld_imm64() step, this is
+ * converted into regular 64-bit imm load insn.
+ */
+ if ((insn[0].src_reg != BPF_PSEUDO_MAP_FD &&
+ insn[0].src_reg != BPF_PSEUDO_MAP_VALUE) ||
+ (insn[0].src_reg == BPF_PSEUDO_MAP_FD &&
+ insn[1].imm != 0)) {
verbose(env,
"unrecognized bpf_ld_imm64 insn\n");
return -EINVAL;
}
- f = fdget(insn->imm);
+ f = fdget(insn[0].imm);
map = __bpf_map_get(f);
if (IS_ERR(map)) {
verbose(env, "fd %d is not pointing to valid bpf_map\n",
- insn->imm);
+ insn[0].imm);
return PTR_ERR(map);
}
@@ -5633,16 +10603,47 @@
return err;
}
- /* store map pointer inside BPF_LD_IMM64 instruction */
- insn[0].imm = (u32) (unsigned long) map;
- insn[1].imm = ((u64) (unsigned long) map) >> 32;
+ aux = &env->insn_aux_data[i];
+ if (insn->src_reg == BPF_PSEUDO_MAP_FD) {
+ addr = (unsigned long)map;
+ } else {
+ u32 off = insn[1].imm;
+
+ if (off >= BPF_MAX_VAR_OFF) {
+ verbose(env, "direct value offset of %u is not allowed\n", off);
+ fdput(f);
+ return -EINVAL;
+ }
+
+ if (!map->ops->map_direct_value_addr) {
+ verbose(env, "no direct value access support for this map type\n");
+ fdput(f);
+ return -EINVAL;
+ }
+
+ err = map->ops->map_direct_value_addr(map, &addr, off);
+ if (err) {
+ verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
+ map->value_size, off);
+ fdput(f);
+ return err;
+ }
+
+ aux->map_off = off;
+ addr += off;
+ }
+
+ insn[0].imm = (u32)addr;
+ insn[1].imm = addr >> 32;
/* check whether we recorded this map already */
- for (j = 0; j < env->used_map_cnt; j++)
+ for (j = 0; j < env->used_map_cnt; j++) {
if (env->used_maps[j] == map) {
+ aux->map_index = j;
fdput(f);
goto next_insn;
}
+ }
if (env->used_map_cnt >= MAX_USED_MAPS) {
fdput(f);
@@ -5654,17 +10655,14 @@
* will be used by the valid program until it's unloaded
* and all maps are released in free_used_maps()
*/
- map = bpf_map_inc(map, false);
- if (IS_ERR(map)) {
- fdput(f);
- return PTR_ERR(map);
- }
+ bpf_map_inc(map);
+
+ aux->map_index = env->used_map_cnt;
env->used_maps[env->used_map_cnt++] = map;
- if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
- bpf_cgroup_storage_assign(env->prog, map)) {
- verbose(env,
- "only one cgroup storage is allowed\n");
+ if (bpf_map_is_cgroup_storage(map) &&
+ bpf_cgroup_storage_assign(env->prog->aux, map)) {
+ verbose(env, "only one cgroup storage of each type is allowed\n");
fdput(f);
return -EBUSY;
}
@@ -5693,14 +10691,8 @@
/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
- int i;
-
- if (env->prog->aux->cgroup_storage)
- bpf_cgroup_storage_release(env->prog,
- env->prog->aux->cgroup_storage);
-
- for (i = 0; i < env->used_map_cnt; i++)
- bpf_map_put(env->used_maps[i]);
+ __bpf_free_used_maps(env->prog->aux, env->used_maps,
+ env->used_map_cnt);
}
/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
@@ -5719,29 +10711,36 @@
* insni[off, off + cnt). Adjust corresponding insn_aux_data by copying
* [0, off) and [off, end) to new locations, so the patched range stays zero
*/
-static int adjust_insn_aux_data(struct bpf_verifier_env *env, u32 prog_len,
- u32 off, u32 cnt)
+static void adjust_insn_aux_data(struct bpf_verifier_env *env,
+ struct bpf_insn_aux_data *new_data,
+ struct bpf_prog *new_prog, u32 off, u32 cnt)
{
- struct bpf_insn_aux_data *new_data, *old_data = env->insn_aux_data;
- bool old_seen = old_data[off].seen;
+ struct bpf_insn_aux_data *old_data = env->insn_aux_data;
+ struct bpf_insn *insn = new_prog->insnsi;
+ u32 old_seen = old_data[off].seen;
+ u32 prog_len;
int i;
+ /* aux info at OFF always needs adjustment, no matter fast path
+ * (cnt == 1) is taken or not. There is no guarantee INSN at OFF is the
+ * original insn at old prog.
+ */
+ old_data[off].zext_dst = insn_has_def32(env, insn + off + cnt - 1);
+
if (cnt == 1)
- return 0;
- new_data = vzalloc(array_size(prog_len,
- sizeof(struct bpf_insn_aux_data)));
- if (!new_data)
- return -ENOMEM;
+ return;
+ prog_len = new_prog->len;
+
memcpy(new_data, old_data, sizeof(struct bpf_insn_aux_data) * off);
memcpy(new_data + off + cnt - 1, old_data + off,
sizeof(struct bpf_insn_aux_data) * (prog_len - off - cnt + 1));
for (i = off; i < off + cnt - 1; i++) {
/* Expand insni[off]'s seen count to the patched range. */
new_data[i].seen = old_seen;
+ new_data[i].zext_dst = insn_has_def32(env, insn + i);
}
env->insn_aux_data = new_data;
vfree(old_data);
- return 0;
}
static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
@@ -5758,18 +10757,193 @@
}
}
+static void adjust_poke_descs(struct bpf_prog *prog, u32 off, u32 len)
+{
+ struct bpf_jit_poke_descriptor *tab = prog->aux->poke_tab;
+ int i, sz = prog->aux->size_poke_tab;
+ struct bpf_jit_poke_descriptor *desc;
+
+ for (i = 0; i < sz; i++) {
+ desc = &tab[i];
+ if (desc->insn_idx <= off)
+ continue;
+ desc->insn_idx += len - 1;
+ }
+}
+
static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
const struct bpf_insn *patch, u32 len)
{
struct bpf_prog *new_prog;
+ struct bpf_insn_aux_data *new_data = NULL;
+
+ if (len > 1) {
+ new_data = vzalloc(array_size(env->prog->len + len - 1,
+ sizeof(struct bpf_insn_aux_data)));
+ if (!new_data)
+ return NULL;
+ }
new_prog = bpf_patch_insn_single(env->prog, off, patch, len);
- if (!new_prog)
+ if (IS_ERR(new_prog)) {
+ if (PTR_ERR(new_prog) == -ERANGE)
+ verbose(env,
+ "insn %d cannot be patched due to 16-bit range\n",
+ env->insn_aux_data[off].orig_idx);
+ vfree(new_data);
return NULL;
- if (adjust_insn_aux_data(env, new_prog->len, off, len))
- return NULL;
+ }
+ adjust_insn_aux_data(env, new_data, new_prog, off, len);
adjust_subprog_starts(env, off, len);
+ adjust_poke_descs(new_prog, off, len);
return new_prog;
+}
+
+static int adjust_subprog_starts_after_remove(struct bpf_verifier_env *env,
+ u32 off, u32 cnt)
+{
+ int i, j;
+
+ /* find first prog starting at or after off (first to remove) */
+ for (i = 0; i < env->subprog_cnt; i++)
+ if (env->subprog_info[i].start >= off)
+ break;
+ /* find first prog starting at or after off + cnt (first to stay) */
+ for (j = i; j < env->subprog_cnt; j++)
+ if (env->subprog_info[j].start >= off + cnt)
+ break;
+ /* if j doesn't start exactly at off + cnt, we are just removing
+ * the front of previous prog
+ */
+ if (env->subprog_info[j].start != off + cnt)
+ j--;
+
+ if (j > i) {
+ struct bpf_prog_aux *aux = env->prog->aux;
+ int move;
+
+ /* move fake 'exit' subprog as well */
+ move = env->subprog_cnt + 1 - j;
+
+ memmove(env->subprog_info + i,
+ env->subprog_info + j,
+ sizeof(*env->subprog_info) * move);
+ env->subprog_cnt -= j - i;
+
+ /* remove func_info */
+ if (aux->func_info) {
+ move = aux->func_info_cnt - j;
+
+ memmove(aux->func_info + i,
+ aux->func_info + j,
+ sizeof(*aux->func_info) * move);
+ aux->func_info_cnt -= j - i;
+ /* func_info->insn_off is set after all code rewrites,
+ * in adjust_btf_func() - no need to adjust
+ */
+ }
+ } else {
+ /* convert i from "first prog to remove" to "first to adjust" */
+ if (env->subprog_info[i].start == off)
+ i++;
+ }
+
+ /* update fake 'exit' subprog as well */
+ for (; i <= env->subprog_cnt; i++)
+ env->subprog_info[i].start -= cnt;
+
+ return 0;
+}
+
+static int bpf_adj_linfo_after_remove(struct bpf_verifier_env *env, u32 off,
+ u32 cnt)
+{
+ struct bpf_prog *prog = env->prog;
+ u32 i, l_off, l_cnt, nr_linfo;
+ struct bpf_line_info *linfo;
+
+ nr_linfo = prog->aux->nr_linfo;
+ if (!nr_linfo)
+ return 0;
+
+ linfo = prog->aux->linfo;
+
+ /* find first line info to remove, count lines to be removed */
+ for (i = 0; i < nr_linfo; i++)
+ if (linfo[i].insn_off >= off)
+ break;
+
+ l_off = i;
+ l_cnt = 0;
+ for (; i < nr_linfo; i++)
+ if (linfo[i].insn_off < off + cnt)
+ l_cnt++;
+ else
+ break;
+
+ /* First live insn doesn't match first live linfo, it needs to "inherit"
+ * last removed linfo. prog is already modified, so prog->len == off
+ * means no live instructions after (tail of the program was removed).
+ */
+ if (prog->len != off && l_cnt &&
+ (i == nr_linfo || linfo[i].insn_off != off + cnt)) {
+ l_cnt--;
+ linfo[--i].insn_off = off + cnt;
+ }
+
+ /* remove the line info which refer to the removed instructions */
+ if (l_cnt) {
+ memmove(linfo + l_off, linfo + i,
+ sizeof(*linfo) * (nr_linfo - i));
+
+ prog->aux->nr_linfo -= l_cnt;
+ nr_linfo = prog->aux->nr_linfo;
+ }
+
+ /* pull all linfo[i].insn_off >= off + cnt in by cnt */
+ for (i = l_off; i < nr_linfo; i++)
+ linfo[i].insn_off -= cnt;
+
+ /* fix up all subprogs (incl. 'exit') which start >= off */
+ for (i = 0; i <= env->subprog_cnt; i++)
+ if (env->subprog_info[i].linfo_idx > l_off) {
+ /* program may have started in the removed region but
+ * may not be fully removed
+ */
+ if (env->subprog_info[i].linfo_idx >= l_off + l_cnt)
+ env->subprog_info[i].linfo_idx -= l_cnt;
+ else
+ env->subprog_info[i].linfo_idx = l_off;
+ }
+
+ return 0;
+}
+
+static int verifier_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ unsigned int orig_prog_len = env->prog->len;
+ int err;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux))
+ bpf_prog_offload_remove_insns(env, off, cnt);
+
+ err = bpf_remove_insns(env->prog, off, cnt);
+ if (err)
+ return err;
+
+ err = adjust_subprog_starts_after_remove(env, off, cnt);
+ if (err)
+ return err;
+
+ err = bpf_adj_linfo_after_remove(env, off, cnt);
+ if (err)
+ return err;
+
+ memmove(aux_data + off, aux_data + off + cnt,
+ sizeof(*aux_data) * (orig_prog_len - off - cnt));
+
+ return 0;
}
/* The verifier does more data flow analysis than llvm and will not
@@ -5795,11 +10969,177 @@
if (aux_data[i].seen)
continue;
memcpy(insn + i, &trap, sizeof(trap));
+ aux_data[i].zext_dst = false;
}
}
-/* convert load instructions that access fields of 'struct __sk_buff'
- * into sequence of instructions that access fields of 'struct sk_buff'
+static bool insn_is_cond_jump(u8 code)
+{
+ u8 op;
+
+ if (BPF_CLASS(code) == BPF_JMP32)
+ return true;
+
+ if (BPF_CLASS(code) != BPF_JMP)
+ return false;
+
+ op = BPF_OP(code);
+ return op != BPF_JA && op != BPF_EXIT && op != BPF_CALL;
+}
+
+static void opt_hard_wire_dead_code_branches(struct bpf_verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+ struct bpf_insn *insn = env->prog->insnsi;
+ const int insn_cnt = env->prog->len;
+ int i;
+
+ for (i = 0; i < insn_cnt; i++, insn++) {
+ if (!insn_is_cond_jump(insn->code))
+ continue;
+
+ if (!aux_data[i + 1].seen)
+ ja.off = insn->off;
+ else if (!aux_data[i + 1 + insn->off].seen)
+ ja.off = 0;
+ else
+ continue;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux))
+ bpf_prog_offload_replace_insn(env, i, &ja);
+
+ memcpy(insn, &ja, sizeof(ja));
+ }
+}
+
+static int opt_remove_dead_code(struct bpf_verifier_env *env)
+{
+ struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
+ int insn_cnt = env->prog->len;
+ int i, err;
+
+ for (i = 0; i < insn_cnt; i++) {
+ int j;
+
+ j = 0;
+ while (i + j < insn_cnt && !aux_data[i + j].seen)
+ j++;
+ if (!j)
+ continue;
+
+ err = verifier_remove_insns(env, i, j);
+ if (err)
+ return err;
+ insn_cnt = env->prog->len;
+ }
+
+ return 0;
+}
+
+static int opt_remove_nops(struct bpf_verifier_env *env)
+{
+ const struct bpf_insn ja = BPF_JMP_IMM(BPF_JA, 0, 0, 0);
+ struct bpf_insn *insn = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int i, err;
+
+ for (i = 0; i < insn_cnt; i++) {
+ if (memcmp(&insn[i], &ja, sizeof(ja)))
+ continue;
+
+ err = verifier_remove_insns(env, i, 1);
+ if (err)
+ return err;
+ insn_cnt--;
+ i--;
+ }
+
+ return 0;
+}
+
+static int opt_subreg_zext_lo32_rnd_hi32(struct bpf_verifier_env *env,
+ const union bpf_attr *attr)
+{
+ struct bpf_insn *patch, zext_patch[2], rnd_hi32_patch[4];
+ struct bpf_insn_aux_data *aux = env->insn_aux_data;
+ int i, patch_len, delta = 0, len = env->prog->len;
+ struct bpf_insn *insns = env->prog->insnsi;
+ struct bpf_prog *new_prog;
+ bool rnd_hi32;
+
+ rnd_hi32 = attr->prog_flags & BPF_F_TEST_RND_HI32;
+ zext_patch[1] = BPF_ZEXT_REG(0);
+ rnd_hi32_patch[1] = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, 0);
+ rnd_hi32_patch[2] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_AX, 32);
+ rnd_hi32_patch[3] = BPF_ALU64_REG(BPF_OR, 0, BPF_REG_AX);
+ for (i = 0; i < len; i++) {
+ int adj_idx = i + delta;
+ struct bpf_insn insn;
+
+ insn = insns[adj_idx];
+ if (!aux[adj_idx].zext_dst) {
+ u8 code, class;
+ u32 imm_rnd;
+
+ if (!rnd_hi32)
+ continue;
+
+ code = insn.code;
+ class = BPF_CLASS(code);
+ if (insn_no_def(&insn))
+ continue;
+
+ /* NOTE: arg "reg" (the fourth one) is only used for
+ * BPF_STX which has been ruled out in above
+ * check, it is safe to pass NULL here.
+ */
+ if (is_reg64(env, &insn, insn.dst_reg, NULL, DST_OP)) {
+ if (class == BPF_LD &&
+ BPF_MODE(code) == BPF_IMM)
+ i++;
+ continue;
+ }
+
+ /* ctx load could be transformed into wider load. */
+ if (class == BPF_LDX &&
+ aux[adj_idx].ptr_type == PTR_TO_CTX)
+ continue;
+
+ imm_rnd = get_random_int();
+ rnd_hi32_patch[0] = insn;
+ rnd_hi32_patch[1].imm = imm_rnd;
+ rnd_hi32_patch[3].dst_reg = insn.dst_reg;
+ patch = rnd_hi32_patch;
+ patch_len = 4;
+ goto apply_patch_buffer;
+ }
+
+ if (!bpf_jit_needs_zext())
+ continue;
+
+ zext_patch[0] = insn;
+ zext_patch[1].dst_reg = insn.dst_reg;
+ zext_patch[1].src_reg = insn.dst_reg;
+ patch = zext_patch;
+ patch_len = 2;
+apply_patch_buffer:
+ new_prog = bpf_patch_insn_data(env, adj_idx, patch, patch_len);
+ if (!new_prog)
+ return -ENOMEM;
+ env->prog = new_prog;
+ insns = new_prog->insnsi;
+ aux = env->insn_aux_data;
+ delta += patch_len - 1;
+ }
+
+ return 0;
+}
+
+/* convert load instructions that access fields of a context type into a
+ * sequence of instructions that access fields of the underlying structure:
+ * struct __sk_buff -> struct sk_buff
+ * struct bpf_sock_ops -> struct sock
*/
static int convert_ctx_accesses(struct bpf_verifier_env *env)
{
@@ -5812,7 +11152,11 @@
enum bpf_access_type type;
bool is_narrower_load;
- if (ops->gen_prologue) {
+ if (ops->gen_prologue || env->seen_direct_write) {
+ if (!ops->gen_prologue) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
cnt = ops->gen_prologue(insn_buf, env->seen_direct_write,
env->prog);
if (cnt >= ARRAY_SIZE(insn_buf)) {
@@ -5828,12 +11172,13 @@
}
}
- if (!ops->convert_ctx_access || bpf_prog_is_dev_bound(env->prog->aux))
+ if (bpf_prog_is_dev_bound(env->prog->aux))
return 0;
insn = env->prog->insnsi + delta;
for (i = 0; i < insn_cnt; i++, insn++) {
+ bpf_convert_ctx_access_t convert_ctx_access;
bool ctx_access;
if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
@@ -5877,8 +11222,35 @@
if (!ctx_access)
continue;
- if (env->insn_aux_data[i + delta].ptr_type != PTR_TO_CTX)
+ switch (env->insn_aux_data[i + delta].ptr_type) {
+ case PTR_TO_CTX:
+ if (!ops->convert_ctx_access)
+ continue;
+ convert_ctx_access = ops->convert_ctx_access;
+ break;
+ case PTR_TO_SOCKET:
+ case PTR_TO_SOCK_COMMON:
+ convert_ctx_access = bpf_sock_convert_ctx_access;
+ break;
+ case PTR_TO_TCP_SOCK:
+ convert_ctx_access = bpf_tcp_sock_convert_ctx_access;
+ break;
+ case PTR_TO_XDP_SOCK:
+ convert_ctx_access = bpf_xdp_sock_convert_ctx_access;
+ break;
+ case PTR_TO_BTF_ID:
+ if (type == BPF_READ) {
+ insn->code = BPF_LDX | BPF_PROBE_MEM |
+ BPF_SIZE((insn)->code);
+ env->prog->aux->num_exentries++;
+ } else if (resolve_prog_type(env->prog) != BPF_PROG_TYPE_STRUCT_OPS) {
+ verbose(env, "Writes through BTF pointers are not allowed\n");
+ return -EINVAL;
+ }
continue;
+ default:
+ continue;
+ }
ctx_field_size = env->insn_aux_data[i + delta].ctx_field_size;
size = BPF_LDST_BYTES(insn);
@@ -5910,8 +11282,8 @@
}
target_size = 0;
- cnt = ops->convert_ctx_access(type, insn, insn_buf, env->prog,
- &target_size);
+ cnt = convert_ctx_access(type, insn, insn_buf, env->prog,
+ &target_size);
if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf) ||
(ctx_field_size && !target_size)) {
verbose(env, "bpf verifier is misconfigured\n");
@@ -5919,8 +11291,12 @@
}
if (is_narrower_load && size < target_size) {
- u8 shift = (off & (size_default - 1)) * 8;
-
+ u8 shift = bpf_ctx_narrow_access_offset(
+ off, size, size_default) * 8;
+ if (shift && cnt + 1 >= ARRAY_SIZE(insn_buf)) {
+ verbose(env, "bpf verifier narrow ctx load misconfigured\n");
+ return -EINVAL;
+ }
if (ctx_field_size <= 4) {
if (shift)
insn_buf[cnt++] = BPF_ALU32_IMM(BPF_RSH,
@@ -5933,7 +11309,7 @@
insn_buf[cnt++] = BPF_ALU64_IMM(BPF_RSH,
insn->dst_reg,
shift);
- insn_buf[cnt++] = BPF_ALU64_IMM(BPF_AND, insn->dst_reg,
+ insn_buf[cnt++] = BPF_ALU32_IMM(BPF_AND, insn->dst_reg,
(1ULL << size * 8) - 1);
}
}
@@ -5956,9 +11332,10 @@
{
struct bpf_prog *prog = env->prog, **func, *tmp;
int i, j, subprog_start, subprog_end = 0, len, subprog;
+ struct bpf_map *map_ptr;
struct bpf_insn *insn;
void *old_bpf_func;
- int err = -ENOMEM;
+ int err, num_exentries;
if (env->subprog_cnt <= 1)
return 0;
@@ -5989,6 +11366,11 @@
insn->imm = 1;
}
+ err = bpf_prog_alloc_jited_linfo(prog);
+ if (err)
+ goto out_undo_insn;
+
+ err = -ENOMEM;
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
goto out_undo_insn;
@@ -5998,7 +11380,12 @@
subprog_end = env->subprog_info[i + 1].start;
len = subprog_end - subprog_start;
- func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
+ /* BPF_PROG_RUN doesn't call subprogs directly,
+ * hence main prog stats include the runtime of subprogs.
+ * subprogs don't have IDs and not reachable via prog_get_next_id
+ * func[i]->aux->stats will never be accessed and stays NULL
+ */
+ func[i] = bpf_prog_alloc_no_stats(bpf_prog_size(len), GFP_USER);
if (!func[i])
goto out_free;
memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
@@ -6008,12 +11395,53 @@
if (bpf_prog_calc_tag(func[i]))
goto out_free;
func[i]->is_func = 1;
- /* Use bpf_prog_F_tag to indicate functions in stack traces.
- * Long term would need debug info to populate names
- */
+ func[i]->aux->func_idx = i;
+ /* the btf and func_info will be freed only at prog->aux */
+ func[i]->aux->btf = prog->aux->btf;
+ func[i]->aux->func_info = prog->aux->func_info;
+ func[i]->aux->func_info_cnt = prog->aux->func_info_cnt;
+
+ for (j = 0; j < prog->aux->size_poke_tab; j++) {
+ u32 insn_idx = prog->aux->poke_tab[j].insn_idx;
+ int ret;
+
+ if (!(insn_idx >= subprog_start &&
+ insn_idx <= subprog_end))
+ continue;
+
+ ret = bpf_jit_add_poke_descriptor(func[i],
+ &prog->aux->poke_tab[j]);
+ if (ret < 0) {
+ verbose(env, "adding tail call poke descriptor failed\n");
+ goto out_free;
+ }
+
+ func[i]->insnsi[insn_idx - subprog_start].imm = ret + 1;
+
+ map_ptr = func[i]->aux->poke_tab[ret].tail_call.map;
+ ret = map_ptr->ops->map_poke_track(map_ptr, func[i]->aux);
+ if (ret < 0) {
+ verbose(env, "tracking tail call prog failed\n");
+ goto out_free;
+ }
+ }
+
func[i]->aux->name[0] = 'F';
func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
func[i]->jit_requested = 1;
+ func[i]->aux->linfo = prog->aux->linfo;
+ func[i]->aux->nr_linfo = prog->aux->nr_linfo;
+ func[i]->aux->jited_linfo = prog->aux->jited_linfo;
+ func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx;
+ num_exentries = 0;
+ insn = func[i]->insnsi;
+ for (j = 0; j < func[i]->len; j++, insn++) {
+ if (BPF_CLASS(insn->code) == BPF_LDX &&
+ BPF_MODE(insn->code) == BPF_PROBE_MEM)
+ num_exentries++;
+ }
+ func[i]->aux->num_exentries = num_exentries;
+ func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable;
func[i] = bpf_int_jit_compile(func[i]);
if (!func[i]->jited) {
err = -ENOTSUPP;
@@ -6021,6 +11449,19 @@
}
cond_resched();
}
+
+ /* Untrack main program's aux structs so that during map_poke_run()
+ * we will not stumble upon the unfilled poke descriptors; each
+ * of the main program's poke descs got distributed across subprogs
+ * and got tracked onto map, so we are sure that none of them will
+ * be missed after the operation below
+ */
+ for (i = 0; i < prog->aux->size_poke_tab; i++) {
+ map_ptr = prog->aux->poke_tab[i].tail_call.map;
+
+ map_ptr->ops->map_poke_untrack(map_ptr, prog->aux);
+ }
+
/* at this point all bpf functions were successfully JITed
* now populate all bpf_calls with correct addresses and
* run last pass of JIT
@@ -6032,9 +11473,8 @@
insn->src_reg != BPF_PSEUDO_CALL)
continue;
subprog = insn->off;
- insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
- func[subprog]->bpf_func -
- __bpf_call_base;
+ insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
+ __bpf_call_base;
}
/* we use the aux data to keep a list of the start addresses
@@ -6087,11 +11527,19 @@
prog->bpf_func = func[0]->bpf_func;
prog->aux->func = func;
prog->aux->func_cnt = env->subprog_cnt;
+ bpf_prog_free_unused_jited_linfo(prog);
return 0;
out_free:
- for (i = 0; i < env->subprog_cnt; i++)
- if (func[i])
- bpf_jit_free(func[i]);
+ for (i = 0; i < env->subprog_cnt; i++) {
+ if (!func[i])
+ continue;
+
+ for (j = 0; j < func[i]->aux->size_poke_tab; j++) {
+ map_ptr = func[i]->aux->poke_tab[j].tail_call.map;
+ map_ptr->ops->map_poke_untrack(map_ptr, func[i]->aux);
+ }
+ bpf_jit_free(func[i]);
+ }
kfree(func);
out_undo_insn:
/* cleanup main prog to be interpreted */
@@ -6103,6 +11551,7 @@
insn->off = 0;
insn->imm = env->insn_aux_data[i].call_imm;
}
+ bpf_prog_free_jited_linfo(prog);
return err;
}
@@ -6113,10 +11562,10 @@
struct bpf_insn *insn = prog->insnsi;
int i, depth;
#endif
- int err;
+ int err = 0;
- err = 0;
- if (env->prog->jit_requested) {
+ if (env->prog->jit_requested &&
+ !bpf_prog_is_dev_bound(env->prog->aux)) {
err = jit_subprogs(env);
if (err == 0)
return 0;
@@ -6124,6 +11573,13 @@
return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ if (env->subprog_cnt > 1 && env->prog->aux->tail_call_reachable) {
+ /* When JIT fails the progs with bpf2bpf calls and tail_calls
+ * have to be rejected, since interpreter doesn't support them yet.
+ */
+ verbose(env, "tail_calls are not allowed in non-JITed programs with bpf-to-bpf calls\n");
+ return -EINVAL;
+ }
for (i = 0; i < prog->len; i++, insn++) {
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
@@ -6146,6 +11602,7 @@
static int fixup_bpf_calls(struct bpf_verifier_env *env)
{
struct bpf_prog *prog = env->prog;
+ bool expect_blinding = bpf_jit_blinding_enabled(prog);
struct bpf_insn *insn = prog->insnsi;
const struct bpf_func_proto *fn;
const int insn_cnt = prog->len;
@@ -6154,7 +11611,7 @@
struct bpf_insn insn_buf[16];
struct bpf_prog *new_prog;
struct bpf_map *map_ptr;
- int i, cnt, delta = 0;
+ int i, ret, cnt, delta = 0;
for (i = 0; i < insn_cnt; i++, insn++) {
if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) ||
@@ -6162,31 +11619,30 @@
insn->code == (BPF_ALU | BPF_MOD | BPF_X) ||
insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
bool is64 = BPF_CLASS(insn->code) == BPF_ALU64;
- struct bpf_insn mask_and_div[] = {
- BPF_MOV_REG(BPF_CLASS(insn->code), BPF_REG_AX, insn->src_reg),
+ bool isdiv = BPF_OP(insn->code) == BPF_DIV;
+ struct bpf_insn *patchlet;
+ struct bpf_insn chk_and_div[] = {
/* [R,W]x div 0 -> 0 */
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, 2),
- BPF_RAW_REG(*insn, insn->dst_reg, BPF_REG_AX),
+ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+ BPF_JNE | BPF_K, insn->src_reg,
+ 0, 2, 0),
+ BPF_ALU32_REG(BPF_XOR, insn->dst_reg, insn->dst_reg),
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
- BPF_ALU_REG(BPF_CLASS(insn->code), BPF_XOR, insn->dst_reg, insn->dst_reg),
+ *insn,
};
- struct bpf_insn mask_and_mod[] = {
- BPF_MOV_REG(BPF_CLASS(insn->code), BPF_REG_AX, insn->src_reg),
- BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, 1 + (is64 ? 0 : 1)),
- BPF_RAW_REG(*insn, insn->dst_reg, BPF_REG_AX),
+ struct bpf_insn chk_and_mod[] = {
+ /* [R,W]x mod 0 -> [R,W]x */
+ BPF_RAW_INSN((is64 ? BPF_JMP : BPF_JMP32) |
+ BPF_JEQ | BPF_K, insn->src_reg,
+ 0, 1 + (is64 ? 0 : 1), 0),
+ *insn,
BPF_JMP_IMM(BPF_JA, 0, 0, 1),
BPF_MOV32_REG(insn->dst_reg, insn->dst_reg),
};
- struct bpf_insn *patchlet;
- if (insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) ||
- insn->code == (BPF_ALU | BPF_DIV | BPF_X)) {
- patchlet = mask_and_div;
- cnt = ARRAY_SIZE(mask_and_div);
- } else {
- patchlet = mask_and_mod;
- cnt = ARRAY_SIZE(mask_and_mod) - (is64 ? 2 : 0);
- }
+ patchlet = isdiv ? chk_and_div : chk_and_mod;
+ cnt = isdiv ? ARRAY_SIZE(chk_and_div) :
+ ARRAY_SIZE(chk_and_mod) - (is64 ? 2 : 0);
new_prog = bpf_patch_insn_data(env, i + delta, patchlet, cnt);
if (!new_prog)
@@ -6288,7 +11744,9 @@
* the program array.
*/
prog->cb_access = 1;
- env->prog->aux->stack_depth = MAX_BPF_STACK;
+ if (!allow_tail_call_in_subprogs(env))
+ prog->aux->stack_depth = MAX_BPF_STACK;
+ prog->aux->max_pkt_offset = MAX_PACKET_OFF;
/* mark bpf_tail_call as different opcode to avoid
* conditional branch in the interpeter for every normal
@@ -6299,6 +11757,28 @@
insn->code = BPF_JMP | BPF_TAIL_CALL;
aux = &env->insn_aux_data[i + delta];
+ if (env->bpf_capable && !expect_blinding &&
+ prog->jit_requested &&
+ !bpf_map_key_poisoned(aux) &&
+ !bpf_map_ptr_poisoned(aux) &&
+ !bpf_map_ptr_unpriv(aux)) {
+ struct bpf_jit_poke_descriptor desc = {
+ .reason = BPF_POKE_REASON_TAIL_CALL,
+ .tail_call.map = BPF_MAP_PTR(aux->map_ptr_state),
+ .tail_call.key = bpf_map_key_immediate(aux),
+ .insn_idx = i + delta,
+ };
+
+ ret = bpf_jit_add_poke_descriptor(prog, &desc);
+ if (ret < 0) {
+ verbose(env, "adding tail call poke descriptor failed\n");
+ return ret;
+ }
+
+ insn->imm = ret + 1;
+ continue;
+ }
+
if (!bpf_map_ptr_unpriv(aux))
continue;
@@ -6313,7 +11793,7 @@
return -EINVAL;
}
- map_ptr = BPF_MAP_PTR(aux->map_state);
+ map_ptr = BPF_MAP_PTR(aux->map_ptr_state);
insn_buf[0] = BPF_JMP_IMM(BPF_JGE, BPF_REG_3,
map_ptr->max_entries, 2);
insn_buf[1] = BPF_ALU32_IMM(BPF_AND, BPF_REG_3,
@@ -6339,17 +11819,22 @@
if (prog->jit_requested && BITS_PER_LONG == 64 &&
(insn->imm == BPF_FUNC_map_lookup_elem ||
insn->imm == BPF_FUNC_map_update_elem ||
- insn->imm == BPF_FUNC_map_delete_elem)) {
+ insn->imm == BPF_FUNC_map_delete_elem ||
+ insn->imm == BPF_FUNC_map_push_elem ||
+ insn->imm == BPF_FUNC_map_pop_elem ||
+ insn->imm == BPF_FUNC_map_peek_elem)) {
aux = &env->insn_aux_data[i + delta];
if (bpf_map_ptr_poisoned(aux))
goto patch_call_imm;
- map_ptr = BPF_MAP_PTR(aux->map_state);
+ map_ptr = BPF_MAP_PTR(aux->map_ptr_state);
ops = map_ptr->ops;
if (insn->imm == BPF_FUNC_map_lookup_elem &&
ops->map_gen_lookup) {
cnt = ops->map_gen_lookup(map_ptr, insn_buf);
- if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) {
+ if (cnt == -EOPNOTSUPP)
+ goto patch_map_ops_generic;
+ if (cnt <= 0 || cnt >= ARRAY_SIZE(insn_buf)) {
verbose(env, "bpf verifier is misconfigured\n");
return -EINVAL;
}
@@ -6372,6 +11857,14 @@
BUILD_BUG_ON(!__same_type(ops->map_update_elem,
(int (*)(struct bpf_map *map, void *key, void *value,
u64 flags))NULL));
+ BUILD_BUG_ON(!__same_type(ops->map_push_elem,
+ (int (*)(struct bpf_map *map, void *value,
+ u64 flags))NULL));
+ BUILD_BUG_ON(!__same_type(ops->map_pop_elem,
+ (int (*)(struct bpf_map *map, void *value))NULL));
+ BUILD_BUG_ON(!__same_type(ops->map_peek_elem,
+ (int (*)(struct bpf_map *map, void *value))NULL));
+patch_map_ops_generic:
switch (insn->imm) {
case BPF_FUNC_map_lookup_elem:
insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
@@ -6385,9 +11878,45 @@
insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
__bpf_call_base;
continue;
+ case BPF_FUNC_map_push_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
+ __bpf_call_base;
+ continue;
+ case BPF_FUNC_map_pop_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
+ __bpf_call_base;
+ continue;
+ case BPF_FUNC_map_peek_elem:
+ insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
+ __bpf_call_base;
+ continue;
}
goto patch_call_imm;
+ }
+
+ if (prog->jit_requested && BITS_PER_LONG == 64 &&
+ insn->imm == BPF_FUNC_jiffies64) {
+ struct bpf_insn ld_jiffies_addr[2] = {
+ BPF_LD_IMM64(BPF_REG_0,
+ (unsigned long)&jiffies),
+ };
+
+ insn_buf[0] = ld_jiffies_addr[0];
+ insn_buf[1] = ld_jiffies_addr[1];
+ insn_buf[2] = BPF_LDX_MEM(BPF_DW, BPF_REG_0,
+ BPF_REG_0, 0);
+ cnt = 3;
+
+ new_prog = bpf_patch_insn_data(env, i + delta, insn_buf,
+ cnt);
+ if (!new_prog)
+ return -ENOMEM;
+
+ delta += cnt - 1;
+ env->prog = prog = new_prog;
+ insn = new_prog->insnsi + i + delta;
+ continue;
}
patch_call_imm:
@@ -6404,6 +11933,23 @@
insn->imm = fn->func - __bpf_call_base;
}
+ /* Since poke tab is now finalized, publish aux to tracker. */
+ for (i = 0; i < prog->aux->size_poke_tab; i++) {
+ map_ptr = prog->aux->poke_tab[i].tail_call.map;
+ if (!map_ptr->ops->map_poke_track ||
+ !map_ptr->ops->map_poke_untrack ||
+ !map_ptr->ops->map_poke_run) {
+ verbose(env, "bpf verifier is misconfigured\n");
+ return -EINVAL;
+ }
+
+ ret = map_ptr->ops->map_poke_track(map_ptr, prog->aux);
+ if (ret < 0) {
+ verbose(env, "tracking tail call prog failed\n");
+ return ret;
+ }
+ }
+
return 0;
}
@@ -6412,29 +11958,605 @@
struct bpf_verifier_state_list *sl, *sln;
int i;
+ sl = env->free_list;
+ while (sl) {
+ sln = sl->next;
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ sl = sln;
+ }
+ env->free_list = NULL;
+
if (!env->explored_states)
return;
- for (i = 0; i < env->prog->len; i++) {
+ for (i = 0; i < state_htab_size(env); i++) {
sl = env->explored_states[i];
- if (sl)
- while (sl != STATE_LIST_MARK) {
- sln = sl->next;
- free_verifier_state(&sl->state, false);
- kfree(sl);
- sl = sln;
- }
+ while (sl) {
+ sln = sl->next;
+ free_verifier_state(&sl->state, false);
+ kfree(sl);
+ sl = sln;
+ }
+ env->explored_states[i] = NULL;
}
-
- kfree(env->explored_states);
}
-int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
+static int do_check_common(struct bpf_verifier_env *env, int subprog)
{
+ bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
+ struct bpf_verifier_state *state;
+ struct bpf_reg_state *regs;
+ int ret, i;
+
+ env->prev_linfo = NULL;
+ env->pass_cnt++;
+
+ state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+ state->curframe = 0;
+ state->speculative = false;
+ state->branches = 1;
+ state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ if (!state->frame[0]) {
+ kfree(state);
+ return -ENOMEM;
+ }
+ env->cur_state = state;
+ init_func_state(env, state->frame[0],
+ BPF_MAIN_FUNC /* callsite */,
+ 0 /* frameno */,
+ subprog);
+
+ state->first_insn_idx = env->subprog_info[subprog].start;
+ state->last_insn_idx = -1;
+
+ regs = state->frame[state->curframe]->regs;
+ if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
+ ret = btf_prepare_func_args(env, subprog, regs);
+ if (ret)
+ goto out;
+ for (i = BPF_REG_1; i <= BPF_REG_5; i++) {
+ if (regs[i].type == PTR_TO_CTX)
+ mark_reg_known_zero(env, regs, i);
+ else if (regs[i].type == SCALAR_VALUE)
+ mark_reg_unknown(env, regs, i);
+ }
+ } else {
+ /* 1st arg to a function */
+ regs[BPF_REG_1].type = PTR_TO_CTX;
+ mark_reg_known_zero(env, regs, BPF_REG_1);
+ ret = btf_check_func_arg_match(env, subprog, regs);
+ if (ret == -EFAULT)
+ /* unlikely verifier bug. abort.
+ * ret == 0 and ret < 0 are sadly acceptable for
+ * main() function due to backward compatibility.
+ * Like socket filter program may be written as:
+ * int bpf_prog(struct pt_regs *ctx)
+ * and never dereference that ctx in the program.
+ * 'struct pt_regs' is a type mismatch for socket
+ * filter that should be using 'struct __sk_buff'.
+ */
+ goto out;
+ }
+
+ ret = do_check(env);
+out:
+ /* check for NULL is necessary, since cur_state can be freed inside
+ * do_check() under memory pressure.
+ */
+ if (env->cur_state) {
+ free_verifier_state(env->cur_state, true);
+ env->cur_state = NULL;
+ }
+ while (!pop_stack(env, NULL, NULL, false));
+ if (!ret && pop_log)
+ bpf_vlog_reset(&env->log, 0);
+ free_states(env);
+ return ret;
+}
+
+/* Verify all global functions in a BPF program one by one based on their BTF.
+ * All global functions must pass verification. Otherwise the whole program is rejected.
+ * Consider:
+ * int bar(int);
+ * int foo(int f)
+ * {
+ * return bar(f);
+ * }
+ * int bar(int b)
+ * {
+ * ...
+ * }
+ * foo() will be verified first for R1=any_scalar_value. During verification it
+ * will be assumed that bar() already verified successfully and call to bar()
+ * from foo() will be checked for type match only. Later bar() will be verified
+ * independently to check that it's safe for R1=any_scalar_value.
+ */
+static int do_check_subprogs(struct bpf_verifier_env *env)
+{
+ struct bpf_prog_aux *aux = env->prog->aux;
+ int i, ret;
+
+ if (!aux->func_info)
+ return 0;
+
+ for (i = 1; i < env->subprog_cnt; i++) {
+ if (aux->func_info_aux[i].linkage != BTF_FUNC_GLOBAL)
+ continue;
+ env->insn_idx = env->subprog_info[i].start;
+ WARN_ON_ONCE(env->insn_idx == 0);
+ ret = do_check_common(env, i);
+ if (ret) {
+ return ret;
+ } else if (env->log.level & BPF_LOG_LEVEL) {
+ verbose(env,
+ "Func#%d is safe for any args that match its prototype\n",
+ i);
+ }
+ }
+ return 0;
+}
+
+static int do_check_main(struct bpf_verifier_env *env)
+{
+ int ret;
+
+ env->insn_idx = 0;
+ ret = do_check_common(env, 0);
+ if (!ret)
+ env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
+ return ret;
+}
+
+
+static void print_verification_stats(struct bpf_verifier_env *env)
+{
+ int i;
+
+ if (env->log.level & BPF_LOG_STATS) {
+ verbose(env, "verification time %lld usec\n",
+ div_u64(env->verification_time, 1000));
+ verbose(env, "stack depth ");
+ for (i = 0; i < env->subprog_cnt; i++) {
+ u32 depth = env->subprog_info[i].stack_depth;
+
+ verbose(env, "%d", depth);
+ if (i + 1 < env->subprog_cnt)
+ verbose(env, "+");
+ }
+ verbose(env, "\n");
+ }
+ verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
+ "total_states %d peak_states %d mark_read %d\n",
+ env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
+ env->max_states_per_insn, env->total_states,
+ env->peak_states, env->longest_mark_read_walk);
+}
+
+static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
+{
+ const struct btf_type *t, *func_proto;
+ const struct bpf_struct_ops *st_ops;
+ const struct btf_member *member;
+ struct bpf_prog *prog = env->prog;
+ u32 btf_id, member_idx;
+ const char *mname;
+
+ if (!prog->gpl_compatible) {
+ verbose(env, "struct ops programs must have a GPL compatible license\n");
+ return -EINVAL;
+ }
+
+ btf_id = prog->aux->attach_btf_id;
+ st_ops = bpf_struct_ops_find(btf_id);
+ if (!st_ops) {
+ verbose(env, "attach_btf_id %u is not a supported struct\n",
+ btf_id);
+ return -ENOTSUPP;
+ }
+
+ t = st_ops->type;
+ member_idx = prog->expected_attach_type;
+ if (member_idx >= btf_type_vlen(t)) {
+ verbose(env, "attach to invalid member idx %u of struct %s\n",
+ member_idx, st_ops->name);
+ return -EINVAL;
+ }
+
+ member = &btf_type_member(t)[member_idx];
+ mname = btf_name_by_offset(btf_vmlinux, member->name_off);
+ func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type,
+ NULL);
+ if (!func_proto) {
+ verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
+ mname, member_idx, st_ops->name);
+ return -EINVAL;
+ }
+
+ if (st_ops->check_member) {
+ int err = st_ops->check_member(t, member);
+
+ if (err) {
+ verbose(env, "attach to unsupported member %s of struct %s\n",
+ mname, st_ops->name);
+ return err;
+ }
+ }
+
+ prog->aux->attach_func_proto = func_proto;
+ prog->aux->attach_func_name = mname;
+ env->ops = st_ops->verifier_ops;
+
+ return 0;
+}
+#define SECURITY_PREFIX "security_"
+
+static int check_attach_modify_return(unsigned long addr, const char *func_name)
+{
+ if (within_error_injection_list(addr) ||
+ !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
+ return 0;
+
+ return -EINVAL;
+}
+
+/* non exhaustive list of sleepable bpf_lsm_*() functions */
+BTF_SET_START(btf_sleepable_lsm_hooks)
+#ifdef CONFIG_BPF_LSM
+BTF_ID(func, bpf_lsm_bprm_committed_creds)
+#else
+BTF_ID_UNUSED
+#endif
+BTF_SET_END(btf_sleepable_lsm_hooks)
+
+static int check_sleepable_lsm_hook(u32 btf_id)
+{
+ return btf_id_set_contains(&btf_sleepable_lsm_hooks, btf_id);
+}
+
+/* list of non-sleepable functions that are otherwise on
+ * ALLOW_ERROR_INJECTION list
+ */
+BTF_SET_START(btf_non_sleepable_error_inject)
+/* Three functions below can be called from sleepable and non-sleepable context.
+ * Assume non-sleepable from bpf safety point of view.
+ */
+BTF_ID(func, __add_to_page_cache_locked)
+BTF_ID(func, should_fail_alloc_page)
+BTF_ID(func, should_failslab)
+BTF_SET_END(btf_non_sleepable_error_inject)
+
+static int check_non_sleepable_error_inject(u32 btf_id)
+{
+ return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
+}
+
+int bpf_check_attach_target(struct bpf_verifier_log *log,
+ const struct bpf_prog *prog,
+ const struct bpf_prog *tgt_prog,
+ u32 btf_id,
+ struct bpf_attach_target_info *tgt_info)
+{
+ bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
+ const char prefix[] = "btf_trace_";
+ int ret = 0, subprog = -1, i;
+ const struct btf_type *t;
+ bool conservative = true;
+ const char *tname;
+ struct btf *btf;
+ long addr = 0;
+
+ if (!btf_id) {
+ bpf_log(log, "Tracing programs must provide btf_id\n");
+ return -EINVAL;
+ }
+ btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux;
+ if (!btf) {
+ bpf_log(log,
+ "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n");
+ return -EINVAL;
+ }
+ t = btf_type_by_id(btf, btf_id);
+ if (!t) {
+ bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
+ return -EINVAL;
+ }
+ tname = btf_name_by_offset(btf, t->name_off);
+ if (!tname) {
+ bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
+ return -EINVAL;
+ }
+ if (tgt_prog) {
+ struct bpf_prog_aux *aux = tgt_prog->aux;
+
+ for (i = 0; i < aux->func_info_cnt; i++)
+ if (aux->func_info[i].type_id == btf_id) {
+ subprog = i;
+ break;
+ }
+ if (subprog == -1) {
+ bpf_log(log, "Subprog %s doesn't exist\n", tname);
+ return -EINVAL;
+ }
+ conservative = aux->func_info_aux[subprog].unreliable;
+ if (prog_extension) {
+ if (conservative) {
+ bpf_log(log,
+ "Cannot replace static functions\n");
+ return -EINVAL;
+ }
+ if (!prog->jit_requested) {
+ bpf_log(log,
+ "Extension programs should be JITed\n");
+ return -EINVAL;
+ }
+ }
+ if (!tgt_prog->jited) {
+ bpf_log(log, "Can attach to only JITed progs\n");
+ return -EINVAL;
+ }
+ if (tgt_prog->type == prog->type) {
+ /* Cannot fentry/fexit another fentry/fexit program.
+ * Cannot attach program extension to another extension.
+ * It's ok to attach fentry/fexit to extension program.
+ */
+ bpf_log(log, "Cannot recursively attach\n");
+ return -EINVAL;
+ }
+ if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
+ prog_extension &&
+ (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
+ tgt_prog->expected_attach_type == BPF_TRACE_FEXIT)) {
+ /* Program extensions can extend all program types
+ * except fentry/fexit. The reason is the following.
+ * The fentry/fexit programs are used for performance
+ * analysis, stats and can be attached to any program
+ * type except themselves. When extension program is
+ * replacing XDP function it is necessary to allow
+ * performance analysis of all functions. Both original
+ * XDP program and its program extension. Hence
+ * attaching fentry/fexit to BPF_PROG_TYPE_EXT is
+ * allowed. If extending of fentry/fexit was allowed it
+ * would be possible to create long call chain
+ * fentry->extension->fentry->extension beyond
+ * reasonable stack size. Hence extending fentry is not
+ * allowed.
+ */
+ bpf_log(log, "Cannot extend fentry/fexit\n");
+ return -EINVAL;
+ }
+ } else {
+ if (prog_extension) {
+ bpf_log(log, "Cannot replace kernel functions\n");
+ return -EINVAL;
+ }
+ }
+
+ switch (prog->expected_attach_type) {
+ case BPF_TRACE_RAW_TP:
+ if (tgt_prog) {
+ bpf_log(log,
+ "Only FENTRY/FEXIT progs are attachable to another BPF prog\n");
+ return -EINVAL;
+ }
+ if (!btf_type_is_typedef(t)) {
+ bpf_log(log, "attach_btf_id %u is not a typedef\n",
+ btf_id);
+ return -EINVAL;
+ }
+ if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
+ bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
+ btf_id, tname);
+ return -EINVAL;
+ }
+ tname += sizeof(prefix) - 1;
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_ptr(t))
+ /* should never happen in valid vmlinux build */
+ return -EINVAL;
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_func_proto(t))
+ /* should never happen in valid vmlinux build */
+ return -EINVAL;
+
+ break;
+ case BPF_TRACE_ITER:
+ if (!btf_type_is_func(t)) {
+ bpf_log(log, "attach_btf_id %u is not a function\n",
+ btf_id);
+ return -EINVAL;
+ }
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_func_proto(t))
+ return -EINVAL;
+ ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
+ if (ret)
+ return ret;
+ break;
+ default:
+ if (!prog_extension)
+ return -EINVAL;
+ fallthrough;
+ case BPF_MODIFY_RETURN:
+ case BPF_LSM_MAC:
+ case BPF_TRACE_FENTRY:
+ case BPF_TRACE_FEXIT:
+ if (!btf_type_is_func(t)) {
+ bpf_log(log, "attach_btf_id %u is not a function\n",
+ btf_id);
+ return -EINVAL;
+ }
+ if (prog_extension &&
+ btf_check_type_match(log, prog, btf, t))
+ return -EINVAL;
+ t = btf_type_by_id(btf, t->type);
+ if (!btf_type_is_func_proto(t))
+ return -EINVAL;
+
+ if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
+ (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
+ prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
+ return -EINVAL;
+
+ if (tgt_prog && conservative)
+ t = NULL;
+
+ ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
+ if (ret < 0)
+ return ret;
+
+ if (tgt_prog) {
+ if (subprog == 0)
+ addr = (long) tgt_prog->bpf_func;
+ else
+ addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
+ } else {
+ addr = kallsyms_lookup_name(tname);
+ if (!addr) {
+ bpf_log(log,
+ "The address of function %s cannot be found\n",
+ tname);
+ return -ENOENT;
+ }
+ }
+
+ if (prog->aux->sleepable) {
+ ret = -EINVAL;
+ switch (prog->type) {
+ case BPF_PROG_TYPE_TRACING:
+ /* fentry/fexit/fmod_ret progs can be sleepable only if they are
+ * attached to ALLOW_ERROR_INJECTION and are not in denylist.
+ */
+ if (!check_non_sleepable_error_inject(btf_id) &&
+ within_error_injection_list(addr))
+ ret = 0;
+ break;
+ case BPF_PROG_TYPE_LSM:
+ /* LSM progs check that they are attached to bpf_lsm_*() funcs.
+ * Only some of them are sleepable.
+ */
+ if (check_sleepable_lsm_hook(btf_id))
+ ret = 0;
+ break;
+ default:
+ break;
+ }
+ if (ret) {
+ bpf_log(log, "%s is not sleepable\n", tname);
+ return ret;
+ }
+ } else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
+ if (tgt_prog) {
+ bpf_log(log, "can't modify return codes of BPF programs\n");
+ return -EINVAL;
+ }
+ ret = check_attach_modify_return(addr, tname);
+ if (ret) {
+ bpf_log(log, "%s() is not modifiable\n", tname);
+ return ret;
+ }
+ }
+
+ break;
+ }
+ tgt_info->tgt_addr = addr;
+ tgt_info->tgt_name = tname;
+ tgt_info->tgt_type = t;
+ return 0;
+}
+
+static int check_attach_btf_id(struct bpf_verifier_env *env)
+{
+ struct bpf_prog *prog = env->prog;
+ struct bpf_prog *tgt_prog = prog->aux->dst_prog;
+ struct bpf_attach_target_info tgt_info = {};
+ u32 btf_id = prog->aux->attach_btf_id;
+ struct bpf_trampoline *tr;
+ int ret;
+ u64 key;
+
+ if (prog->aux->sleepable && prog->type != BPF_PROG_TYPE_TRACING &&
+ prog->type != BPF_PROG_TYPE_LSM) {
+ verbose(env, "Only fentry/fexit/fmod_ret and lsm programs can be sleepable\n");
+ return -EINVAL;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
+ return check_struct_ops_btf_id(env);
+
+ if (prog->type != BPF_PROG_TYPE_TRACING &&
+ prog->type != BPF_PROG_TYPE_LSM &&
+ prog->type != BPF_PROG_TYPE_EXT)
+ return 0;
+
+ ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
+ if (ret)
+ return ret;
+
+ if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
+ /* to make freplace equivalent to their targets, they need to
+ * inherit env->ops and expected_attach_type for the rest of the
+ * verification
+ */
+ env->ops = bpf_verifier_ops[tgt_prog->type];
+ prog->expected_attach_type = tgt_prog->expected_attach_type;
+ }
+
+ /* store info about the attachment target that will be used later */
+ prog->aux->attach_func_proto = tgt_info.tgt_type;
+ prog->aux->attach_func_name = tgt_info.tgt_name;
+
+ if (tgt_prog) {
+ prog->aux->saved_dst_prog_type = tgt_prog->type;
+ prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
+ }
+
+ if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
+ prog->aux->attach_btf_trace = true;
+ return 0;
+ } else if (prog->expected_attach_type == BPF_TRACE_ITER) {
+ if (!bpf_iter_prog_supported(prog))
+ return -EINVAL;
+ return 0;
+ }
+
+ if (prog->type == BPF_PROG_TYPE_LSM) {
+ ret = bpf_lsm_verify_prog(&env->log, prog);
+ if (ret < 0)
+ return ret;
+ }
+
+ key = bpf_trampoline_compute_key(tgt_prog, btf_id);
+ tr = bpf_trampoline_get(key, &tgt_info);
+ if (!tr)
+ return -ENOMEM;
+
+ prog->aux->dst_trampoline = tr;
+ return 0;
+}
+
+struct btf *bpf_get_btf_vmlinux(void)
+{
+ if (!btf_vmlinux && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
+ mutex_lock(&bpf_verifier_lock);
+ if (!btf_vmlinux)
+ btf_vmlinux = btf_parse_vmlinux();
+ mutex_unlock(&bpf_verifier_lock);
+ }
+ return btf_vmlinux;
+}
+
+int bpf_check(struct bpf_prog **prog, union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ u64 start_time = ktime_get_ns();
struct bpf_verifier_env *env;
struct bpf_verifier_log *log;
- int ret = -EINVAL;
+ int i, len, ret = -EINVAL;
+ bool is_priv;
/* no program is valid */
if (ARRAY_SIZE(bpf_verifier_ops) == 0)
@@ -6448,17 +12570,23 @@
return -ENOMEM;
log = &env->log;
+ len = (*prog)->len;
env->insn_aux_data =
- vzalloc(array_size(sizeof(struct bpf_insn_aux_data),
- (*prog)->len));
+ vzalloc(array_size(sizeof(struct bpf_insn_aux_data), len));
ret = -ENOMEM;
if (!env->insn_aux_data)
goto err_free_env;
+ for (i = 0; i < len; i++)
+ env->insn_aux_data[i].orig_idx = i;
env->prog = *prog;
env->ops = bpf_verifier_ops[env->prog->type];
+ is_priv = bpf_capable();
+
+ bpf_get_btf_vmlinux();
/* grab the mutex to protect few globals used by verifier */
- mutex_lock(&bpf_verifier_lock);
+ if (!is_priv)
+ mutex_lock(&bpf_verifier_lock);
if (attr->log_level || attr->log_buf || attr->log_size) {
/* user requested verbose verifier output
@@ -6468,58 +12596,93 @@
log->ubuf = (char __user *) (unsigned long) attr->log_buf;
log->len_total = attr->log_size;
- ret = -EINVAL;
/* log attributes have to be sane */
- if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 ||
- !log->level || !log->ubuf)
+ if (!bpf_verifier_log_attr_valid(log)) {
+ ret = -EINVAL;
goto err_unlock;
+ }
+ }
+
+ if (IS_ERR(btf_vmlinux)) {
+ /* Either gcc or pahole or kernel are broken. */
+ verbose(env, "in-kernel BTF is malformed\n");
+ ret = PTR_ERR(btf_vmlinux);
+ goto skip_full_check;
}
env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
env->strict_alignment = true;
-
if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
env->strict_alignment = false;
- ret = replace_map_fd_with_map_ptr(env);
- if (ret < 0)
- goto skip_full_check;
+ env->allow_ptr_leaks = bpf_allow_ptr_leaks();
+ env->allow_uninit_stack = bpf_allow_uninit_stack();
+ env->allow_ptr_to_map_access = bpf_allow_ptr_to_map_access();
+ env->bypass_spec_v1 = bpf_bypass_spec_v1();
+ env->bypass_spec_v4 = bpf_bypass_spec_v4();
+ env->bpf_capable = bpf_capable();
- if (bpf_prog_is_dev_bound(env->prog->aux)) {
- ret = bpf_prog_offload_verifier_prep(env);
- if (ret)
- goto skip_full_check;
- }
+ if (is_priv)
+ env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
- env->explored_states = kcalloc(env->prog->len,
+ env->explored_states = kvcalloc(state_htab_size(env),
sizeof(struct bpf_verifier_state_list *),
GFP_USER);
ret = -ENOMEM;
if (!env->explored_states)
goto skip_full_check;
- env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
+ ret = check_subprogs(env);
+ if (ret < 0)
+ goto skip_full_check;
+
+ ret = check_btf_info(env, attr, uattr);
+ if (ret < 0)
+ goto skip_full_check;
+
+ ret = check_attach_btf_id(env);
+ if (ret)
+ goto skip_full_check;
+
+ ret = resolve_pseudo_ldimm64(env);
+ if (ret < 0)
+ goto skip_full_check;
+
+ if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ ret = bpf_prog_offload_verifier_prep(env->prog);
+ if (ret)
+ goto skip_full_check;
+ }
ret = check_cfg(env);
if (ret < 0)
goto skip_full_check;
- ret = do_check(env);
- if (env->cur_state) {
- free_verifier_state(env->cur_state, true);
- env->cur_state = NULL;
- }
+ ret = do_check_subprogs(env);
+ ret = ret ?: do_check_main(env);
+
+ if (ret == 0 && bpf_prog_is_dev_bound(env->prog->aux))
+ ret = bpf_prog_offload_finalize(env);
skip_full_check:
- while (!pop_stack(env, NULL, NULL));
- free_states(env);
-
- if (ret == 0)
- sanitize_dead_code(env);
+ kvfree(env->explored_states);
if (ret == 0)
ret = check_max_stack_depth(env);
+
+ /* instruction rewrites happen after this point */
+ if (is_priv) {
+ if (ret == 0)
+ opt_hard_wire_dead_code_branches(env);
+ if (ret == 0)
+ ret = opt_remove_dead_code(env);
+ if (ret == 0)
+ ret = opt_remove_nops(env);
+ } else {
+ if (ret == 0)
+ sanitize_dead_code(env);
+ }
if (ret == 0)
/* program is valid, convert *(u32*)(ctx + off) accesses */
@@ -6528,8 +12691,20 @@
if (ret == 0)
ret = fixup_bpf_calls(env);
+ /* do 32-bit optimization after insn patching has done so those patched
+ * insns could be handled correctly.
+ */
+ if (ret == 0 && !bpf_prog_is_dev_bound(env->prog->aux)) {
+ ret = opt_subreg_zext_lo32_rnd_hi32(env, attr);
+ env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret
+ : false;
+ }
+
if (ret == 0)
ret = fixup_call_args(env);
+
+ env->verification_time = ktime_get_ns() - start_time;
+ print_verification_stats(env);
if (log->level && bpf_verifier_log_full(log))
ret = -ENOSPC;
@@ -6559,15 +12734,26 @@
convert_pseudo_ld_imm64(env);
}
+ if (ret == 0)
+ adjust_btf_func(env);
+
err_release_maps:
if (!env->prog->aux->used_maps)
/* if we didn't copy map pointers into bpf_prog_info, release
* 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:
- mutex_unlock(&bpf_verifier_lock);
+ if (!is_priv)
+ mutex_unlock(&bpf_verifier_lock);
vfree(env->insn_aux_data);
err_free_env:
kfree(env);
--
Gitblit v1.6.2