bpf: Hooks for sys_bind

[muen/linux.git] / kernel / bpf / verifier.c

/* 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.
 */
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>

#include "disasm.h"

static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
#define BPF_PROG_TYPE(_id, _name) \
        [_id] = & _name ## _verifier_ops,
#define BPF_MAP_TYPE(_id, _ops)
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
};

/* bpf_check() is a static code analyzer that walks eBPF program
 * instruction by instruction and updates register/stack state.
 * All paths of conditional branches are analyzed until 'bpf_exit' insn.
 *
 * The first pass is depth-first-search to check that the program is a DAG.
 * It rejects the following programs:
 * - larger than BPF_MAXINSNS insns
 * - if loop is present (detected via back-edge)
 * - unreachable insns exist (shouldn't be a forest. program = one function)
 * - out of bounds or malformed jumps
 * The second pass is all possible path descent from the 1st insn.
 * Since it's analyzing all pathes through the program, the length of the
 * analysis is limited to 64k insn, which may be hit even if total number of
 * insn is less then 4K, but there are too many branches that change stack/regs.
 * Number of 'branches to be analyzed' is limited to 1k
 *
 * On entry to each instruction, each register has a type, and the instruction
 * changes the types of the registers depending on instruction semantics.
 * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
 * copied to R1.
 *
 * All registers are 64-bit.
 * R0 - return register
 * R1-R5 argument passing registers
 * R6-R9 callee saved registers
 * R10 - frame pointer read-only
 *
 * At the start of BPF program the register R1 contains a pointer to bpf_context
 * and has type PTR_TO_CTX.
 *
 * Verifier tracks arithmetic operations on pointers in case:
 *    BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
 * 1st insn copies R10 (which has FRAME_PTR) type into R1
 * and 2nd arithmetic instruction is pattern matched to recognize
 * that it wants to construct a pointer to some element within stack.
 * So after 2nd insn, the register R1 has type PTR_TO_STACK
 * (and -20 constant is saved for further stack bounds checking).
 * Meaning that this reg is a pointer to stack plus known immediate constant.
 *
 * Most of the time the registers have SCALAR_VALUE type, which
 * means the register has some value, but it's not a valid pointer.
 * (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.
 *
 * 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.
 *
 * registers used to pass values to function calls are checked against
 * function argument constraints.
 *
 * ARG_PTR_TO_MAP_KEY is one of such argument constraints.
 * It means that the register type passed to this function must be
 * PTR_TO_STACK and it will be used inside the function as
 * 'pointer to map element key'
 *
 * For example the argument constraints for bpf_map_lookup_elem():
 *   .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL,
 *   .arg1_type = ARG_CONST_MAP_PTR,
 *   .arg2_type = ARG_PTR_TO_MAP_KEY,
 *
 * ret_type says that this function returns 'pointer to map elem value or null'
 * function expects 1st argument to be a const pointer to 'struct bpf_map' and
 * 2nd argument should be a pointer to stack, which will be used inside
 * the helper function as a pointer to map element key.
 *
 * On the kernel side the helper function looks like:
 * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
 * {
 *    struct bpf_map *map = (struct bpf_map *) (unsigned long) r1;
 *    void *key = (void *) (unsigned long) r2;
 *    void *value;
 *
 *    here kernel can access 'key' and 'map' pointers safely, knowing that
 *    [key, key + map->key_size) bytes are valid and were initialized on
 *    the stack of eBPF program.
 * }
 *
 * Corresponding eBPF program may look like:
 *    BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),  // after this insn R2 type is FRAME_PTR
 *    BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
 *    BPF_LD_MAP_FD(BPF_REG_1, map_fd),      // after this insn R1 type is CONST_PTR_TO_MAP
 *    BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
 * here verifier looks at prototype of map_lookup_elem() and sees:
 * .arg1_type == ARG_CONST_MAP_PTR and R1->type == CONST_PTR_TO_MAP, which is ok,
 * Now verifier knows that this map has key of R1->map_ptr->key_size bytes
 *
 * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
 * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
 * and were initialized prior to this call.
 * If it's ok, then verifier allows this BPF_CALL insn and looks at
 * .ret_type which is RET_PTR_TO_MAP_VALUE_OR_NULL, so it sets
 * R0->type = PTR_TO_MAP_VALUE_OR_NULL which means bpf_map_lookup_elem() function
 * returns ether pointer to map value or NULL.
 *
 * When type PTR_TO_MAP_VALUE_OR_NULL passes through 'if (reg != 0) goto +off'
 * insn, the register holding that pointer in the true branch changes state to
 * PTR_TO_MAP_VALUE and the same register changes state to CONST_IMM in the false
 * branch. See check_cond_jmp_op().
 *
 * 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.
 */

/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
        /* verifer state is 'st'
         * before processing instruction 'insn_idx'
         * and after processing instruction 'prev_insn_idx'
         */
        struct bpf_verifier_state st;
        int insn_idx;
        int prev_insn_idx;
        struct bpf_verifier_stack_elem *next;
};

#define BPF_COMPLEXITY_LIMIT_INSNS      131072
#define BPF_COMPLEXITY_LIMIT_STACK      1024

#define BPF_MAP_PTR_POISON ((void *)0xeB9F + POISON_POINTER_DELTA)

struct bpf_call_arg_meta {
        struct bpf_map *map_ptr;
        bool raw_mode;
        bool pkt_access;
        int regno;
        int access_size;
};

static DEFINE_MUTEX(bpf_verifier_lock);

void bpf_verifier_vlog(struct bpf_verifier_log *log, const char *fmt,
                       va_list args)
{
        unsigned int n;

        n = vscnprintf(log->kbuf, BPF_VERIFIER_TMP_LOG_SIZE, fmt, args);

        WARN_ONCE(n >= BPF_VERIFIER_TMP_LOG_SIZE - 1,
                  "verifier log line truncated - local buffer too short\n");

        n = min(log->len_total - log->len_used - 1, n);
        log->kbuf[n] = '\0';

        if (!copy_to_user(log->ubuf + log->len_used, log->kbuf, n + 1))
                log->len_used += n;
        else
                log->ubuf = NULL;
}

/* log_level controls verbosity level of eBPF verifier.
 * bpf_verifier_log_write() is used to dump the verification trace to the log,
 * so the user can figure out what's wrong with the program
 */
__printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
                                           const char *fmt, ...)
{
        va_list args;

        if (!bpf_verifier_log_needed(&env->log))
                return;

        va_start(args, fmt);
        bpf_verifier_vlog(&env->log, fmt, args);
        va_end(args);
}
EXPORT_SYMBOL_GPL(bpf_verifier_log_write);

__printf(2, 3) static void verbose(void *private_data, const char *fmt, ...)
{
        struct bpf_verifier_env *env = private_data;
        va_list args;

        if (!bpf_verifier_log_needed(&env->log))
                return;

        va_start(args, fmt);
        bpf_verifier_vlog(&env->log, fmt, args);
        va_end(args);
}

static bool type_is_pkt_pointer(enum bpf_reg_type type)
{
        return type == PTR_TO_PACKET ||
               type == PTR_TO_PACKET_META;
}

/* string representation of 'enum bpf_reg_type' */
static const char * const reg_type_str[] = {
        [NOT_INIT]              = "?",
        [SCALAR_VALUE]          = "inv",
        [PTR_TO_CTX]            = "ctx",
        [CONST_PTR_TO_MAP]      = "map_ptr",
        [PTR_TO_MAP_VALUE]      = "map_value",
        [PTR_TO_MAP_VALUE_OR_NULL] = "map_value_or_null",
        [PTR_TO_STACK]          = "fp",
        [PTR_TO_PACKET]         = "pkt",
        [PTR_TO_PACKET_META]    = "pkt_meta",
        [PTR_TO_PACKET_END]     = "pkt_end",
};

static void print_liveness(struct bpf_verifier_env *env,
                           enum bpf_reg_liveness live)
{
        if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
            verbose(env, "_");
        if (live & REG_LIVE_READ)
                verbose(env, "r");
        if (live & REG_LIVE_WRITTEN)
                verbose(env, "w");
}

static struct bpf_func_state *func(struct bpf_verifier_env *env,
                                   const struct bpf_reg_state *reg)
{
        struct bpf_verifier_state *cur = env->cur_state;

        return cur->frame[reg->frameno];
}

static void print_verifier_state(struct bpf_verifier_env *env,
                                 const struct bpf_func_state *state)
{
        const struct bpf_reg_state *reg;
        enum bpf_reg_type t;
        int i;

        if (state->frameno)
                verbose(env, " frame%d:", state->frameno);
        for (i = 0; i < MAX_BPF_REG; i++) {
                reg = &state->regs[i];
                t = reg->type;
                if (t == NOT_INIT)
                        continue;
                verbose(env, " R%d", i);
                print_liveness(env, reg->live);
                verbose(env, "=%s", reg_type_str[t]);
                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 {
                        verbose(env, "(id=%d", reg->id);
                        if (t != SCALAR_VALUE)
                                verbose(env, ",off=%d", reg->off);
                        if (type_is_pkt_pointer(t))
                                verbose(env, ",r=%d", reg->range);
                        else if (t == CONST_PTR_TO_MAP ||
                                 t == PTR_TO_MAP_VALUE ||
                                 t == PTR_TO_MAP_VALUE_OR_NULL)
                                verbose(env, ",ks=%d,vs=%d",
                                        reg->map_ptr->key_size,
                                        reg->map_ptr->value_size);
                        if (tnum_is_const(reg->var_off)) {
                                /* Typically an immediate SCALAR_VALUE, but
                                 * could be a pointer whose offset is too big
                                 * for reg->off
                                 */
                                verbose(env, ",imm=%llx", reg->var_off.value);
                        } else {
                                if (reg->smin_value != reg->umin_value &&
                                    reg->smin_value != S64_MIN)
                                        verbose(env, ",smin_value=%lld",
                                                (long long)reg->smin_value);
                                if (reg->smax_value != reg->umax_value &&
                                    reg->smax_value != S64_MAX)
                                        verbose(env, ",smax_value=%lld",
                                                (long long)reg->smax_value);
                                if (reg->umin_value != 0)
                                        verbose(env, ",umin_value=%llu",
                                                (unsigned long long)reg->umin_value);
                                if (reg->umax_value != U64_MAX)
                                        verbose(env, ",umax_value=%llu",
                                                (unsigned long long)reg->umax_value);
                                if (!tnum_is_unknown(reg->var_off)) {
                                        char tn_buf[48];

                                        tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
                                        verbose(env, ",var_off=%s", tn_buf);
                                }
                        }
                        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]);
                }
                if (state->stack[i].slot_type[0] == STACK_ZERO)
                        verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
        }
        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;
}

/* 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 bpf_verifier_state
 * which this function 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)
{
        u32 old_size = state->allocated_stack;
        struct bpf_stack_state *new_stack;
        int slot = size / BPF_REG_SIZE;

        if (size <= old_size || !size) {
                if (copy_old)
                        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 0;
}

static void free_func_state(struct bpf_func_state *state)
{
        if (!state)
                return;
        kfree(state->stack);
        kfree(state);
}

static void free_verifier_state(struct bpf_verifier_state *state,
                                bool free_self)
{
        int i;

        for (i = 0; i <= state->curframe; i++) {
                free_func_state(state->frame[i]);
                state->frame[i] = NULL;
        }
        if (free_self)
                kfree(state);
}

/* copy verifier state from src to dst growing dst stack space
 * when necessary to accommodate larger src stack
 */
static int copy_func_state(struct bpf_func_state *dst,
                           const struct bpf_func_state *src)
{
        int err;

        err = realloc_func_state(dst, src->allocated_stack, false);
        if (err)
                return err;
        memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
        return copy_stack_state(dst, src);
}

static int copy_verifier_state(struct bpf_verifier_state *dst_state,
                               const struct bpf_verifier_state *src)
{
        struct bpf_func_state *dst;
        int i, err;

        /* if dst has more stack frames then src frame, free them */
        for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
                free_func_state(dst_state->frame[i]);
                dst_state->frame[i] = NULL;
        }
        dst_state->curframe = src->curframe;
        dst_state->parent = src->parent;
        for (i = 0; i <= src->curframe; i++) {
                dst = dst_state->frame[i];
                if (!dst) {
                        dst = kzalloc(sizeof(*dst), GFP_KERNEL);
                        if (!dst)
                                return -ENOMEM;
                        dst_state->frame[i] = dst;
                }
                err = copy_func_state(dst, src->frame[i]);
                if (err)
                        return err;
        }
        return 0;
}

static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
                     int *insn_idx)
{
        struct bpf_verifier_state *cur = env->cur_state;
        struct bpf_verifier_stack_elem *elem, *head = env->head;
        int err;

        if (env->head == NULL)
                return -ENOENT;

        if (cur) {
                err = copy_verifier_state(cur, &head->st);
                if (err)
                        return err;
        }
        if (insn_idx)
                *insn_idx = head->insn_idx;
        if (prev_insn_idx)
                *prev_insn_idx = head->prev_insn_idx;
        elem = head->next;
        free_verifier_state(&head->st, false);
        kfree(head);
        env->head = elem;
        env->stack_size--;
        return 0;
}

static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
                                             int insn_idx, int prev_insn_idx)
{
        struct bpf_verifier_state *cur = env->cur_state;
        struct bpf_verifier_stack_elem *elem;
        int err;

        elem = kzalloc(sizeof(struct bpf_verifier_stack_elem), GFP_KERNEL);
        if (!elem)
                goto err;

        elem->insn_idx = insn_idx;
        elem->prev_insn_idx = prev_insn_idx;
        elem->next = env->head;
        env->head = elem;
        env->stack_size++;
        err = copy_verifier_state(&elem->st, cur);
        if (err)
                goto err;
        if (env->stack_size > BPF_COMPLEXITY_LIMIT_STACK) {
                verbose(env, "BPF program is too complex\n");
                goto err;
        }
        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));
        return NULL;
}

#define CALLER_SAVED_REGS 6
static const int caller_saved[CALLER_SAVED_REGS] = {
        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);

/* Mark the unknown part of a register (variable offset or scalar value) as
 * known to have the value @imm.
 */
static void __mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
        reg->id = 0;
        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 the 'variable offset' part of a register as zero.  This should be
 * used only on registers holding a pointer type.
 */
static void __mark_reg_known_zero(struct bpf_reg_state *reg)
{
        __mark_reg_known(reg, 0);
}

static void __mark_reg_const_zero(struct bpf_reg_state *reg)
{
        __mark_reg_known(reg, 0);
        reg->off = 0;
        reg->type = SCALAR_VALUE;
}

static void mark_reg_known_zero(struct bpf_verifier_env *env,
                                struct bpf_reg_state *regs, u32 regno)
{
        if (WARN_ON(regno >= MAX_BPF_REG)) {
                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);
                return;
        }
        __mark_reg_known_zero(regs + regno);
}

static bool reg_is_pkt_pointer(const struct bpf_reg_state *reg)
{
        return type_is_pkt_pointer(reg->type);
}

static bool reg_is_pkt_pointer_any(const struct bpf_reg_state *reg)
{
        return reg_is_pkt_pointer(reg) ||
               reg->type == PTR_TO_PACKET_END;
}

/* Unmodified PTR_TO_PACKET[_META,_END] register from ctx access. */
static bool reg_is_init_pkt_pointer(const struct bpf_reg_state *reg,
                                    enum bpf_reg_type which)
{
        /* The register can already have a range from prior markings.
         * This is fine as long as it hasn't been advanced from its
         * origin.
         */
        return reg->type == which &&
               reg->id == 0 &&
               reg->off == 0 &&
               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)
{
        /* min signed is max(sign bit) | min(other bits) */
        reg->smin_value = max_t(s64, reg->smin_value,
                                reg->var_off.value | (reg->var_off.mask & S64_MIN));
        /* max signed is min(sign bit) | max(other bits) */
        reg->smax_value = min_t(s64, reg->smax_value,
                                reg->var_off.value | (reg->var_off.mask & S64_MAX));
        reg->umin_value = max(reg->umin_value, reg->var_off.value);
        reg->umax_value = min(reg->umax_value,
                              reg->var_off.value | reg->var_off.mask);
}

/* Uses signed min/max values to inform unsigned, and vice-versa */
static void __reg_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->smin_value >= 0 || reg->smax_value < 0) {
                reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
                                                          reg->umin_value);
                reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
                                                          reg->umax_value);
                return;
        }
        /* Learn sign from unsigned bounds.  Signed bounds cross the sign
         * boundary, so we must be careful.
         */
        if ((s64)reg->umax_value >= 0) {
                /* Positive.  We can't learn anything from the smin, but smax
                 * is positive, hence safe.
                 */
                reg->smin_value = reg->umin_value;
                reg->smax_value = reg->umax_value = min_t(u64, reg->smax_value,
                                                          reg->umax_value);
        } else if ((s64)reg->umin_value < 0) {
                /* Negative.  We can't learn anything from the smax, but smin
                 * is negative, hence safe.
                 */
                reg->smin_value = reg->umin_value = max_t(u64, reg->smin_value,
                                                          reg->umin_value);
                reg->smax_value = reg->umax_value;
        }
}

/* 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));
}

/* 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;
}

/* Mark a register as having a completely unknown (scalar) value. */
static void __mark_reg_unknown(struct bpf_reg_state *reg)
{
        reg->type = SCALAR_VALUE;
        reg->id = 0;
        reg->off = 0;
        reg->var_off = tnum_unknown;
        reg->frameno = 0;
        __mark_reg_unbounded(reg);
}

static void mark_reg_unknown(struct bpf_verifier_env *env,
                             struct bpf_reg_state *regs, u32 regno)
{
        if (WARN_ON(regno >= MAX_BPF_REG)) {
                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);
                return;
        }
        __mark_reg_unknown(regs + regno);
}

static void __mark_reg_not_init(struct bpf_reg_state *reg)
{
        __mark_reg_unknown(reg);
        reg->type = NOT_INIT;
}

static void mark_reg_not_init(struct bpf_verifier_env *env,
                              struct bpf_reg_state *regs, u32 regno)
{
        if (WARN_ON(regno >= MAX_BPF_REG)) {
                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);
                return;
        }
        __mark_reg_not_init(regs + regno);
}

static void init_reg_state(struct bpf_verifier_env *env,
                           struct bpf_func_state *state)
{
        struct bpf_reg_state *regs = state->regs;
        int i;

        for (i = 0; i < MAX_BPF_REG; i++) {
                mark_reg_not_init(env, regs, i);
                regs[i].live = REG_LIVE_NONE;
        }

        /* 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)
static void init_func_state(struct bpf_verifier_env *env,
                            struct bpf_func_state *state,
                            int callsite, int frameno, int subprogno)
{
        state->callsite = callsite;
        state->frameno = frameno;
        state->subprogno = subprogno;
        init_reg_state(env, state);
}

enum reg_arg_type {
        SRC_OP,         /* register is used as source operand */
        DST_OP,         /* register is used as destination operand */
        DST_OP_NO_MARK  /* same as above, check only, don't mark */
};

static int cmp_subprogs(const void *a, const void *b)
{
        return *(int *)a - *(int *)b;
}

static int find_subprog(struct bpf_verifier_env *env, int off)
{
        u32 *p;

        p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
                    sizeof(env->subprog_starts[0]), cmp_subprogs);
        if (!p)
                return -ENOENT;
        return p - env->subprog_starts;

}

static int add_subprog(struct bpf_verifier_env *env, int off)
{
        int insn_cnt = env->prog->len;
        int ret;

        if (off >= insn_cnt || off < 0) {
                verbose(env, "call to invalid destination\n");
                return -EINVAL;
        }
        ret = find_subprog(env, off);
        if (ret >= 0)
                return 0;
        if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
                verbose(env, "too many subprograms\n");
                return -E2BIG;
        }
        env->subprog_starts[env->subprog_cnt++] = off;
        sort(env->subprog_starts, env->subprog_cnt,
             sizeof(env->subprog_starts[0]), cmp_subprogs, NULL);
        return 0;
}

static int check_subprogs(struct bpf_verifier_env *env)
{
        int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
        struct bpf_insn *insn = env->prog->insnsi;
        int insn_cnt = env->prog->len;

        /* determine subprog starts. The end is one before the next starts */
        for (i = 0; i < insn_cnt; i++) {
                if (insn[i].code != (BPF_JMP | BPF_CALL))
                        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");
                        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)
                        return ret;
        }

        if (env->log.level > 1)
                for (i = 0; i < env->subprog_cnt; i++)
                        verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);

        /* now check that all jumps are within the same subprog */
        subprog_start = 0;
        if (env->subprog_cnt == cur_subprog)
                subprog_end = insn_cnt;
        else
                subprog_end = env->subprog_starts[cur_subprog++];
        for (i = 0; i < insn_cnt; i++) {
                u8 code = insn[i].code;

                if (BPF_CLASS(code) != BPF_JMP)
                        goto next;
                if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
                        goto next;
                off = i + insn[i].off + 1;
                if (off < subprog_start || off >= subprog_end) {
                        verbose(env, "jump out of range from insn %d to %d\n", i, off);
                        return -EINVAL;
                }
next:
                if (i == subprog_end - 1) {
                        /* to avoid fall-through from one subprog into another
                         * the last insn of the subprog should be either exit
                         * or unconditional jump back
                         */
                        if (code != (BPF_JMP | BPF_EXIT) &&
                            code != (BPF_JMP | BPF_JA)) {
                                verbose(env, "last insn is not an exit or jmp\n");
                                return -EINVAL;
                        }
                        subprog_start = subprog_end;
                        if (env->subprog_cnt == cur_subprog)
                                subprog_end = insn_cnt;
                        else
                                subprog_end = env->subprog_starts[cur_subprog++];
                }
        }
        return 0;
}

static
struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
                                       const struct bpf_verifier_state *state,
                                       struct bpf_verifier_state *parent,
                                       u32 regno)
{
        struct bpf_verifier_state *tmp = NULL;

        /* 'parent' could be a state of caller and
         * 'state' could be a state of callee. In such case
         * parent->curframe < state->curframe
         * and it's ok for r1 - r5 registers
         *
         * 'parent' could be a callee's state after it bpf_exit-ed.
         * In such case parent->curframe > state->curframe
         * and it's ok for r0 only
         */
        if (parent->curframe == state->curframe ||
            (parent->curframe < state->curframe &&
             regno >= BPF_REG_1 && regno <= BPF_REG_5) ||
            (parent->curframe > state->curframe &&
               regno == BPF_REG_0))
                return parent;

        if (parent->curframe > state->curframe &&
            regno >= BPF_REG_6) {
                /* for callee saved regs we have to skip the whole chain
                 * of states that belong to callee and mark as LIVE_READ
                 * the registers before the call
                 */
                tmp = parent;
                while (tmp && tmp->curframe != state->curframe) {
                        tmp = tmp->parent;
                }
                if (!tmp)
                        goto bug;
                parent = tmp;
        } else {
                goto bug;
        }
        return parent;
bug:
        verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
        verbose(env, "regno %d parent frame %d current frame %d\n",
                regno, parent->curframe, state->curframe);
        return NULL;
}

static int mark_reg_read(struct bpf_verifier_env *env,
                         const struct bpf_verifier_state *state,
                         struct bpf_verifier_state *parent,
                         u32 regno)
{
        bool writes = parent == state->parent; /* Observe write marks */

        if (regno == BPF_REG_FP)
                /* We don't need to worry about FP liveness because it's read-only */
                return 0;

        while (parent) {
                /* if read wasn't screened by an earlier write ... */
                if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN)
                        break;
                parent = skip_callee(env, state, parent, regno);
                if (!parent)
                        return -EFAULT;
                /* ... then we depend on parent's value */
                parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ;
                state = parent;
                parent = state->parent;
                writes = true;
        }
        return 0;
}

static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
                         enum reg_arg_type t)
{
        struct bpf_verifier_state *vstate = env->cur_state;
        struct bpf_func_state *state = vstate->frame[vstate->curframe];
        struct bpf_reg_state *regs = state->regs;

        if (regno >= MAX_BPF_REG) {
                verbose(env, "R%d is invalid\n", regno);
                return -EINVAL;
        }

        if (t == SRC_OP) {
                /* check whether register used as source operand can be read */
                if (regs[regno].type == NOT_INIT) {
                        verbose(env, "R%d !read_ok\n", regno);
                        return -EACCES;
                }
                return mark_reg_read(env, vstate, vstate->parent, regno);
        } 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;
                if (t == DST_OP)
                        mark_reg_unknown(env, regs, regno);
        }
        return 0;
}

static bool is_spillable_regtype(enum bpf_reg_type type)
{
        switch (type) {
        case PTR_TO_MAP_VALUE:
        case PTR_TO_MAP_VALUE_OR_NULL:
        case PTR_TO_STACK:
        case PTR_TO_CTX:
        case PTR_TO_PACKET:
        case PTR_TO_PACKET_META:
        case PTR_TO_PACKET_END:
        case CONST_PTR_TO_MAP:
                return true;
        default:
                return false;
        }
}

/* Does this register contain a constant zero? */
static bool register_is_null(struct bpf_reg_state *reg)
{
        return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
}

/* check_stack_read/write 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)
{
        struct bpf_func_state *cur; /* state of the current function */
        int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
        enum bpf_reg_type type;

        err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
                                 true);
        if (err)
                return err;
        /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
         * so it's aligned access and [off, off + size) are within stack limits
         */
        if (!env->allow_ptr_leaks &&
            state->stack[spi].slot_type[0] == STACK_SPILL &&
            size != BPF_REG_SIZE) {
                verbose(env, "attempt to corrupt spilled pointer on stack\n");
                return -EACCES;
        }

        cur = env->cur_state->frame[env->cur_state->curframe];
        if (value_regno >= 0 &&
            is_spillable_regtype((type = cur->regs[value_regno].type))) {

                /* register containing pointer is being spilled into stack */
                if (size != BPF_REG_SIZE) {
                        verbose(env, "invalid size of register spill\n");
                        return -EACCES;
                }

                if (state != cur && type == PTR_TO_STACK) {
                        verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
                        return -EINVAL;
                }

                /* save register state */
                state->stack[spi].spilled_ptr = cur->regs[value_regno];
                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;
        } else {
                u8 type = STACK_MISC;

                /* regular write of data into stack */
                state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};

                /* only mark the slot as written if all 8 bytes were written
                 * otherwise read propagation may incorrectly stop too soon
                 * when stack slots are partially written.
                 * This heuristic means that read propagation will be
                 * conservative, since it will add reg_live_read marks
                 * to stack slots all the way to first state when programs
                 * writes+reads less than 8 bytes
                 */
                if (size == BPF_REG_SIZE)
                        state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;

                /* when we zero initialize stack slots mark them as such */
                if (value_regno >= 0 &&
                    register_is_null(&cur->regs[value_regno]))
                        type = STACK_ZERO;

                for (i = 0; i < size; i++)
                        state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
                                type;
        }
        return 0;
}

/* registers of every function are unique and mark_reg_read() propagates
 * the liveness in the following cases:
 * - from callee into caller for R1 - R5 that were used as arguments
 * - from caller into callee for R0 that used as result of the call
 * - from caller to the same caller skipping states of the callee for R6 - R9,
 *   since R6 - R9 are callee saved by implicit function prologue and
 *   caller's R6 != callee's R6, so when we propagate liveness up to
 *   parent states we need to skip callee states for R6 - R9.
 *
 * stack slot marking is different, since stacks of caller and callee are
 * accessible in both (since caller can pass a pointer to caller's stack to
 * callee which can pass it to another function), hence mark_stack_slot_read()
 * has to propagate the stack liveness to all parent states at given frame number.
 * Consider code:
 * f1() {
 *   ptr = fp - 8;
 *   *ptr = ctx;
 *   call f2 {
 *      .. = *ptr;
 *   }
 *   .. = *ptr;
 * }
 * First *ptr is reading from f1's stack and mark_stack_slot_read() has
 * to mark liveness at the f1's frame and not f2's frame.
 * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has
 * to propagate liveness to f2 states at f1's frame level and further into
 * f1 states at f1's frame level until write into that stack slot
 */
static void mark_stack_slot_read(struct bpf_verifier_env *env,
                                 const struct bpf_verifier_state *state,
                                 struct bpf_verifier_state *parent,
                                 int slot, int frameno)
{
        bool writes = parent == state->parent; /* Observe write marks */

        while (parent) {
                if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE)
                        /* since LIVE_WRITTEN mark is only done for full 8-byte
                         * write the read marks are conservative and parent
                         * state may not even have the stack allocated. In such case
                         * end the propagation, since the loop reached beginning
                         * of the function
                         */
                        break;
                /* if read wasn't screened by an earlier write ... */
                if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
                        break;
                /* ... then we depend on parent's value */
                parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
                state = parent;
                parent = state->parent;
                writes = true;
        }
}

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)
{
        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;
        u8 *stype;

        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;

        if (stype[0] == STACK_SPILL) {
                if (size != BPF_REG_SIZE) {
                        verbose(env, "invalid size of register spill\n");
                        return -EACCES;
                }
                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) {
                        /* restore register state from stack */
                        state->regs[value_regno] = reg_state->stack[spi].spilled_ptr;
                        /* 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;
                }
                mark_stack_slot_read(env, vstate, vstate->parent, spi,
                                     reg_state->frameno);
                return 0;
        } else {
                int zeros = 0;

                for (i = 0; i < size; i++) {
                        if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
                                continue;
                        if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
                                zeros++;
                                continue;
                        }
                        verbose(env, "invalid read from stack off %d+%d size %d\n",
                                off, i, size);
                        return -EACCES;
                }
                mark_stack_slot_read(env, vstate, vstate->parent, spi,
                                     reg_state->frameno);
                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;
                }
                return 0;
        }
}

/* 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)
{
        struct bpf_reg_state *regs = cur_regs(env);
        struct bpf_map *map = regs[regno].map_ptr;

        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",
                        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)
{
        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
         * 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)
                print_verifier_state(env, state);
        /* The minimum value is only important with signed
         * comparisons where we can't assume the floor of a
         * value is 0.  If we are using signed variables for our
         * index'es we need to make sure that whatever we use
         * will have a set floor within our range.
         */
        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;
        }
        err = __check_map_access(env, regno, reg->smin_value + off, size,
                                 zero_size_allowed);
        if (err) {
                verbose(env, "R%d min value is outside of the array range\n",
                        regno);
                return err;
        }

        /* If we haven't set a max value then we need to bail since we can't be
         * sure we won't do bad things.
         * 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",
                        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",
                        regno);
        return err;
}

#define MAX_PACKET_OFF 0xffff

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) {
        case BPF_PROG_TYPE_LWT_IN:
        case BPF_PROG_TYPE_LWT_OUT:
                /* dst_input() and dst_output() can't write for now */
                if (t == BPF_WRITE)
                        return false;
                /* fallthrough */
        case BPF_PROG_TYPE_SCHED_CLS:
        case BPF_PROG_TYPE_SCHED_ACT:
        case BPF_PROG_TYPE_XDP:
        case BPF_PROG_TYPE_LWT_XMIT:
        case BPF_PROG_TYPE_SK_SKB:
        case BPF_PROG_TYPE_SK_MSG:
                if (meta)
                        return meta->pkt_access;

                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 = &regs[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,
                               int size, bool zero_size_allowed)
{
        struct bpf_reg_state *regs = cur_regs(env);
        struct bpf_reg_state *reg = &regs[regno];
        int err;

        /* We may have added a variable offset to the packet pointer; but any
         * reg->range we have comes after that.  We are only checking the fixed
         * offset.
         */

        /* We don't allow negative numbers, because we aren't tracking enough
         * detail to prove they're safe.
         */
        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;
        }
        err = __check_packet_access(env, regno, off, size, zero_size_allowed);
        if (err) {
                verbose(env, "R%d offset is outside of the packet\n", regno);
                return err;
        }
        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)
{
        struct bpf_insn_access_aux info = {
                .reg_type = *reg_type,
        };

        if (env->ops->is_valid_access &&
            env->ops->is_valid_access(off, size, t, env->prog, &info)) {
                /* A non zero info.ctx_field_size indicates that this field is a
                 * candidate for later verifier transformation to load the whole
                 * field and then apply a mask when accessed with a narrower
                 * access than actual ctx access size. A zero info.ctx_field_size
                 * will only allow for whole field access and rejects any other
                 * type of narrower access.
                 */
                *reg_type = info.reg_type;

                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;
                return 0;
        }

        verbose(env, "invalid bpf_context access off=%d size=%d\n", off, size);
        return -EACCES;
}

static bool __is_pointer_value(bool allow_ptr_leaks,
                               const struct bpf_reg_state *reg)
{
        if (allow_ptr_leaks)
                return false;

        return reg->type != SCALAR_VALUE;
}

static bool is_pointer_value(struct bpf_verifier_env *env, int regno)
{
        return __is_pointer_value(env->allow_ptr_leaks, cur_regs(env) + regno);
}

static bool is_ctx_reg(struct bpf_verifier_env *env, int regno)
{
        const struct bpf_reg_state *reg = cur_regs(env) + regno;

        return reg->type == PTR_TO_CTX;
}

static bool is_pkt_reg(struct bpf_verifier_env *env, int regno)
{
        const struct bpf_reg_state *reg = cur_regs(env) + regno;

        return type_is_pkt_pointer(reg->type);
}

static int check_pkt_ptr_alignment(struct bpf_verifier_env *env,
                                   const struct bpf_reg_state *reg,
                                   int off, int size, bool strict)
{
        struct tnum reg_off;
        int ip_align;

        /* Byte size accesses are always allowed. */
        if (!strict || size == 1)
                return 0;

        /* For platforms that do not have a Kconfig enabling
         * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS the value of
         * NET_IP_ALIGN is universally set to '2'.  And on platforms
         * that do set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS, we get
         * to this code only in strict mode where we want to emulate
         * the NET_IP_ALIGN==2 checking.  Therefore use an
         * unconditional IP align value of '2'.
         */
        ip_align = 2;

        reg_off = tnum_add(reg->var_off, tnum_const(ip_align + reg->off + off));
        if (!tnum_is_aligned(reg_off, size)) {
                char tn_buf[48];

                tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
                verbose(env,
                        "misaligned packet access off %d+%s+%d+%d size %d\n",
                        ip_align, tn_buf, reg->off, off, size);
                return -EACCES;
        }

        return 0;
}

static int check_generic_ptr_alignment(struct bpf_verifier_env *env,
                                       const struct bpf_reg_state *reg,
                                       const char *pointer_desc,
                                       int off, int size, bool strict)
{
        struct tnum reg_off;

        /* Byte size accesses are always allowed. */
        if (!strict || size == 1)
                return 0;

        reg_off = tnum_add(reg->var_off, tnum_const(reg->off + off));
        if (!tnum_is_aligned(reg_off, size)) {
                char tn_buf[48];

                tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
                verbose(env, "misaligned %saccess off %s+%d+%d size %d\n",
                        pointer_desc, tn_buf, reg->off, off, size);
                return -EACCES;
        }

        return 0;
}

static int check_ptr_alignment(struct bpf_verifier_env *env,
                               const struct bpf_reg_state *reg, int off,
                               int size, bool strict_alignment_once)
{
        bool strict = env->strict_alignment || strict_alignment_once;
        const char *pointer_desc = "";

        switch (reg->type) {
        case PTR_TO_PACKET:
        case PTR_TO_PACKET_META:
                /* Special case, because of NET_IP_ALIGN. Given metadata sits
                 * right in front, treat it the very same way.
                 */
                return check_pkt_ptr_alignment(env, reg, off, size, strict);
        case PTR_TO_MAP_VALUE:
                pointer_desc = "value ";
                break;
        case PTR_TO_CTX:
                pointer_desc = "context ";
                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
                 * aligned.
                 */
                strict = true;
                break;
        default:
                break;
        }
        return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
                                           strict);
}

static int update_stack_depth(struct bpf_verifier_env *env,
                              const struct bpf_func_state *func,
                              int off)
{
        u16 stack = env->subprog_stack_depth[func->subprogno];

        if (stack >= -off)
                return 0;

        /* update known max for given subprogram */
        env->subprog_stack_depth[func->subprogno] = -off;
        return 0;
}

/* starting from main bpf function walk all instructions of the function
 * and recursively walk all callees that given function can call.
 * Ignore jump and exit insns.
 * Since recursion is prevented by check_cfg() this algorithm
 * only needs a local stack of MAX_CALL_FRAMES to remember callsites
 */
static int check_max_stack_depth(struct bpf_verifier_env *env)
{
        int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
        struct bpf_insn *insn = env->prog->insnsi;
        int insn_cnt = env->prog->len;
        int ret_insn[MAX_CALL_FRAMES];
        int ret_prog[MAX_CALL_FRAMES];

process_func:
        /* round up to 32-bytes, since this is granularity
         * of interpreter stack size
         */
        depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
        if (depth > MAX_BPF_STACK) {
                verbose(env, "combined stack size of %d calls is %d. Too large\n",
                        frame + 1, depth);
                return -EACCES;
        }
continue_func:
        if (env->subprog_cnt == subprog)
                subprog_end = insn_cnt;
        else
                subprog_end = env->subprog_starts[subprog];
        for (; i < subprog_end; i++) {
                if (insn[i].code != (BPF_JMP | BPF_CALL))
                        continue;
                if (insn[i].src_reg != BPF_PSEUDO_CALL)
                        continue;
                /* remember insn and function to return to */
                ret_insn[frame] = i + 1;
                ret_prog[frame] = subprog;

                /* find the callee */
                i = i + insn[i].imm + 1;
                subprog = find_subprog(env, i);
                if (subprog < 0) {
                        WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
                                  i);
                        return -EFAULT;
                }
                subprog++;
                frame++;
                if (frame >= MAX_CALL_FRAMES) {
                        WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
                        return -EFAULT;
                }
                goto process_func;
        }
        /* end of for() loop means the last insn of the 'subprog'
         * was reached. Doesn't matter whether it was JA or EXIT
         */
        if (frame == 0)
                return 0;
        depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
        frame--;
        i = ret_insn[frame];
        subprog = ret_prog[frame];
        goto continue_func;
}

#ifndef CONFIG_BPF_JIT_ALWAYS_ON
static int get_callee_stack_depth(struct bpf_verifier_env *env,
                                  const struct bpf_insn *insn, int idx)
{
        int start = idx + insn->imm + 1, subprog;

        subprog = find_subprog(env, start);
        if (subprog < 0) {
                WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
                          start);
                return -EFAULT;
        }
        subprog++;
        return env->subprog_stack_depth[subprog];
}
#endif

/* truncate register to smaller size (in bytes)
 * must be called with size < BPF_REG_SIZE
 */
static void coerce_reg_to_size(struct bpf_reg_state *reg, int size)
{
        u64 mask;

        /* clear high bits in bit representation */
        reg->var_off = tnum_cast(reg->var_off, size);

        /* fix arithmetic bounds */
        mask = ((u64)1 << (size * 8)) - 1;
        if ((reg->umin_value & ~mask) == (reg->umax_value & ~mask)) {
                reg->umin_value &= mask;
                reg->umax_value &= mask;
        } else {
                reg->umin_value = 0;
                reg->umax_value = mask;
        }
        reg->smin_value = reg->umin_value;
        reg->smax_value = reg->umax_value;
}

/* check whether memory at (regno + off) is accessible for t = (read | write)
 * if t==write, value_regno is a register which value is stored into memory
 * if t==read, value_regno is a register which will receive the value from memory
 * if t==write && value_regno==-1, some unknown value is stored into memory
 * if t==read && value_regno==-1, don't care what we read from memory
 */
static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regno,
                            int off, int bpf_size, enum bpf_access_type t,
                            int value_regno, bool strict_alignment_once)
{
        struct bpf_reg_state *regs = cur_regs(env);
        struct bpf_reg_state *reg = regs + regno;
        struct bpf_func_state *state;
        int size, err = 0;

        size = bpf_size_to_bytes(bpf_size);
        if (size < 0)
                return size;

        /* alignment checks will add in reg->off themselves */
        err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
        if (err)
                return err;

        /* for access checks, reg->off is just part of off */
        off += reg->off;

        if (reg->type == PTR_TO_MAP_VALUE) {
                if (t == BPF_WRITE && value_regno >= 0 &&
                    is_pointer_value(env, value_regno)) {
                        verbose(env, "R%d leaks addr into map\n", value_regno);
                        return -EACCES;
                }

                err = check_map_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_CTX) {
                enum bpf_reg_type reg_type = SCALAR_VALUE;

                if (t == BPF_WRITE && value_regno >= 0 &&
                    is_pointer_value(env, value_regno)) {
                        verbose(env, "R%d leaks addr into ctx\n", value_regno);
                        return -EACCES;
                }
                /* ctx accesses must be at a fixed offset, so that we can
                 * determine what type of data were returned.
                 */
                if (reg->off) {
                        verbose(env,
                                "dereference of modified ctx ptr R%d off=%d+%d, ctx+const is allowed, ctx+const+const is not\n",
                                regno, reg->off, off - reg->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,
                                "variable ctx access var_off=%s off=%d size=%d",
                                tn_buf, off, size);
                        return -EACCES;
                }
                err = check_ctx_access(env, insn_idx, off, size, t, &reg_type);
                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)
                                mark_reg_unknown(env, regs, value_regno);
                        else
                                mark_reg_known_zero(env, regs,
                                                    value_regno);
                        regs[value_regno].id = 0;
                        regs[value_regno].off = 0;
                        regs[value_regno].range = 0;
                        regs[value_regno].type = reg_type;
                }

        } else if (reg->type == PTR_TO_STACK) {
                /* stack accesses must be at a fixed offset, so that we can
                 * determine what type of data were returned.
                 * See check_stack_read().
                 */
                if (!tnum_is_const(reg->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",
                                tn_buf, off, size);
                        return -EACCES;
                }
                off += reg->var_off.value;
                if (off >= 0 || off < -MAX_BPF_STACK) {
                        verbose(env, "invalid stack off=%d size=%d\n", off,
                                size);
                        return -EACCES;
                }

                state = func(env, reg);
                err = update_stack_depth(env, state, off);
                if (err)
                        return err;

                if (t == BPF_WRITE)
                        err = check_stack_write(env, state, off, size,
                                                value_regno);
                else
                        err = check_stack_read(env, state, off, size,
                                               value_regno);
        } 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");
                        return -EACCES;
                }
                if (t == BPF_WRITE && value_regno >= 0 &&
                    is_pointer_value(env, value_regno)) {
                        verbose(env, "R%d leaks addr into packet\n",
                                value_regno);
                        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 {
                verbose(env, "R%d invalid mem access '%s'\n", regno,
                        reg_type_str[reg->type]);
                return -EACCES;
        }

        if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
            regs[value_regno].type == SCALAR_VALUE) {
                /* b/h/w load zero-extends, mark upper bits as known 0 */
                coerce_reg_to_size(&regs[value_regno], size);
        }
        return err;
}

static int check_xadd(struct bpf_verifier_env *env, int insn_idx, struct bpf_insn *insn)
{
        int err;

        if ((BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) ||
            insn->imm != 0) {
                verbose(env, "BPF_XADD uses reserved fields\n");
                return -EINVAL;
        }

        /* check src1 operand */
        err = check_reg_arg(env, insn->src_reg, SRC_OP);
        if (err)
                return err;

        /* check src2 operand */
        err = check_reg_arg(env, insn->dst_reg, SRC_OP);
        if (err)
                return err;

        if (is_pointer_value(env, insn->src_reg)) {
                verbose(env, "R%d leaks addr into mem\n", insn->src_reg);
                return -EACCES;
        }

        if (is_ctx_reg(env, insn->dst_reg) ||
            is_pkt_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");
                return -EACCES;
        }

        /* check whether atomic_add can read the memory */
        err = check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
                               BPF_SIZE(insn->code), BPF_READ, -1, true);
        if (err)
                return err;

        /* check whether atomic_add can write into the same memory */
        return check_mem_access(env, insn_idx, insn->dst_reg, insn->off,
                                BPF_SIZE(insn->code), BPF_WRITE, -1, true);
}

/* 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.
 */
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)
{
        struct bpf_reg_state *reg = cur_regs(env) + regno;
        struct bpf_func_state *state = func(env, reg);
        int off, i, slot, spi;

        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]);
                return -EACCES;
        }

        /* Only allow fixed-offset stack reads */
        if (!tnum_is_const(reg->var_off)) {
                char tn_buf[48];

                tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
                verbose(env, "invalid variable stack read R%d var_off=%s\n",
                        regno, tn_buf);
                return -EACCES;
        }
        off = reg->off + reg->var_off.value;
        if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
            access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
                verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
                        regno, off, access_size);
                return -EACCES;
        }

        if (meta && meta->raw_mode) {
                meta->access_size = access_size;
                meta->regno = regno;
                return 0;
        }

        for (i = 0; i < access_size; i++) {
                u8 *stype;

                slot = -(off + i) - 1;
                spi = slot / BPF_REG_SIZE;
                if (state->allocated_stack <= slot)
                        goto err;
                stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
                if (*stype == STACK_MISC)
                        goto mark;
                if (*stype == STACK_ZERO) {
                        /* helper can write anything into the stack */
                        *stype = STACK_MISC;
                        goto mark;
                }
err:
                verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
                        off, i, access_size);
                return -EACCES;
mark:
                /* reading any byte out of 8-byte 'spill_slot' will cause
                 * the whole slot to be marked as 'read'
                 */
                mark_stack_slot_read(env, env->cur_state, env->cur_state->parent,
                                     spi, state->frameno);
        }
        return update_stack_depth(env, state, off);
}

static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
                                   int access_size, bool zero_size_allowed,
                                   struct bpf_call_arg_meta *meta)
{
        struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];

        switch (reg->type) {
        case PTR_TO_PACKET:
        case PTR_TO_PACKET_META:
                return check_packet_access(env, regno, reg->off, access_size,
                                           zero_size_allowed);
        case PTR_TO_MAP_VALUE:
                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);
        }
}

static bool arg_type_is_mem_ptr(enum bpf_arg_type type)
{
        return type == ARG_PTR_TO_MEM ||
               type == ARG_PTR_TO_MEM_OR_NULL ||
               type == ARG_PTR_TO_UNINIT_MEM;
}

static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
        return type == ARG_CONST_SIZE ||
               type == ARG_CONST_SIZE_OR_ZERO;
}

static int check_func_arg(struct bpf_verifier_env *env, u32 regno,
                          enum bpf_arg_type arg_type,
                          struct bpf_call_arg_meta *meta)
{
        struct bpf_reg_state *regs = cur_regs(env), *reg = &regs[regno];
        enum bpf_reg_type expected_type, type = reg->type;
        int err = 0;

        if (arg_type == ARG_DONTCARE)
                return 0;

        err = check_reg_arg(env, regno, SRC_OP);
        if (err)
                return err;

        if (arg_type == ARG_ANYTHING) {
                if (is_pointer_value(env, regno)) {
                        verbose(env, "R%d leaks addr into helper function\n",
                                regno);
                        return -EACCES;
                }
                return 0;
        }

        if (type_is_pkt_pointer(type) &&
            !may_access_direct_pkt_data(env, meta, BPF_READ)) {
                verbose(env, "helper access to the packet is not allowed\n");
                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 != 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;
        } 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;
        }

        if (arg_type == ARG_CONST_MAP_PTR) {
                /* bpf_map_xxx(map_ptr) call: remember that map_ptr */
                meta->map_ptr = reg->map_ptr;
        } else if (arg_type == ARG_PTR_TO_MAP_KEY) {
                /* bpf_map_xxx(..., map_ptr, ..., key) call:
                 * check that [key, key + map->key_size) are within
                 * stack limits and initialized
                 */
                if (!meta->map_ptr) {
                        /* in function declaration map_ptr must come before
                         * map_key, so that it's verified and known before
                         * we have to check map_key here. Otherwise it means
                         * that kernel subsystem misconfigured verifier
                         */
                        verbose(env, "invalid map_ptr to access map->key\n");
                        return -EACCES;
                }
                if (type_is_pkt_pointer(type))
                        err = check_packet_access(env, regno, reg->off,
                                                  meta->map_ptr->key_size,
                                                  false);
                else
                        err = check_stack_boundary(env, regno,
                                                   meta->map_ptr->key_size,
                                                   false, NULL);
        } else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
                /* bpf_map_xxx(..., map_ptr, ..., value) call:
                 * check [value, value + map->value_size) validity
                 */
                if (!meta->map_ptr) {
                        /* kernel subsystem misconfigured verifier */
                        verbose(env, "invalid map_ptr to access map->value\n");
                        return -EACCES;
                }
                if (type_is_pkt_pointer(type))
                        err = check_packet_access(env, regno, reg->off,
                                                  meta->map_ptr->value_size,
                                                  false);
                else
                        err = check_stack_boundary(env, regno,
                                                   meta->map_ptr->value_size,
                                                   false, NULL);
        } else if (arg_type_is_mem_size(arg_type)) {
                bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);

                /* The register is SCALAR_VALUE; the access check
                 * happens using its boundaries.
                 */
                if (!tnum_is_const(reg->var_off))
                        /* For unprivileged variable accesses, disable raw
                         * mode so that the program is required to
                         * initialize all the memory that the helper could
                         * just partially fill up.
                         */
                        meta = NULL;

                if (reg->smin_value < 0) {
                        verbose(env, "R%d min value is negative, either use unsigned or 'var &= const'\n",
                                regno);
                        return -EACCES;
                }

                if (reg->umin_value == 0) {
                        err = check_helper_mem_access(env, regno - 1, 0,
                                                      zero_size_allowed,
                                                      meta);
                        if (err)
                                return err;
                }

                if (reg->umax_value >= BPF_MAX_VAR_SIZ) {
                        verbose(env, "R%d unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
                                regno);
                        return -EACCES;
                }
                err = check_helper_mem_access(env, regno - 1,
                                              reg->umax_value,
                                              zero_size_allowed, meta);
        }

        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 int check_map_func_compatibility(struct bpf_verifier_env *env,
                                        struct bpf_map *map, int func_id)
{
        if (!map)
                return 0;

        /* We need a two way check, first is from map perspective ... */
        switch (map->map_type) {
        case BPF_MAP_TYPE_PROG_ARRAY:
                if (func_id != BPF_FUNC_tail_call)
                        goto error;
                break;
        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)
                        goto error;
                break;
        case BPF_MAP_TYPE_STACK_TRACE:
                if (func_id != BPF_FUNC_get_stackid)
                        goto error;
                break;
        case BPF_MAP_TYPE_CGROUP_ARRAY:
                if (func_id != BPF_FUNC_skb_under_cgroup &&
                    func_id != BPF_FUNC_current_task_under_cgroup)
                        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)
                        goto error;
                break;
        /* Restrict bpf side of cpumap, open when use-cases appear */
        case BPF_MAP_TYPE_CPUMAP:
                if (func_id != BPF_FUNC_redirect_map)
                        goto error;
                break;
        case BPF_MAP_TYPE_ARRAY_OF_MAPS:
        case BPF_MAP_TYPE_HASH_OF_MAPS:
                if (func_id != BPF_FUNC_map_lookup_elem)
                        goto error;
                break;
        case BPF_MAP_TYPE_SOCKMAP:
                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)
                        goto error;
                break;
        default:
                break;
        }

        /* ... and second from the function itself. */
        switch (func_id) {
        case BPF_FUNC_tail_call:
                if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
                        goto error;
                if (env->subprog_cnt) {
                        verbose(env, "tail_calls are not allowed in 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:
                if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
                        goto error;
                break;
        case BPF_FUNC_get_stackid:
                if (map->map_type != BPF_MAP_TYPE_STACK_TRACE)
                        goto error;
                break;
        case BPF_FUNC_current_task_under_cgroup:
        case BPF_FUNC_skb_under_cgroup:
                if (map->map_type != BPF_MAP_TYPE_CGROUP_ARRAY)
                        goto error;
                break;
        case BPF_FUNC_redirect_map:
                if (map->map_type != BPF_MAP_TYPE_DEVMAP &&
                    map->map_type != BPF_MAP_TYPE_CPUMAP)
                        goto error;
                break;
        case BPF_FUNC_sk_redirect_map:
        case BPF_FUNC_msg_redirect_map:
                if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
                        goto error;
                break;
        case BPF_FUNC_sock_map_update:
                if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
                        goto error;
                break;
        default:
                break;
        }

        return 0;
error:
        verbose(env, "cannot pass map_type %d into func %s#%d\n",
                map->map_type, func_id_name(func_id), func_id);
        return -EINVAL;
}

static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
{
        int count = 0;

        if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
                count++;
        if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
                count++;
        if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
                count++;
        if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
                count++;
        if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
                count++;

        /* We only support one arg being in raw mode at the moment,
         * which is sufficient for the helper functions we have
         * right now.
         */
        return count <= 1;
}

static bool check_args_pair_invalid(enum bpf_arg_type arg_curr,
                                    enum bpf_arg_type arg_next)
{
        return (arg_type_is_mem_ptr(arg_curr) &&
                !arg_type_is_mem_size(arg_next)) ||
               (!arg_type_is_mem_ptr(arg_curr) &&
                arg_type_is_mem_size(arg_next));
}

static bool check_arg_pair_ok(const struct bpf_func_proto *fn)
{
        /* bpf_xxx(..., buf, len) call will access 'len'
         * bytes from memory 'buf'. Both arg types need
         * to be paired, so make sure there's no buggy
         * helper function specification.
         */
        if (arg_type_is_mem_size(fn->arg1_type) ||
            arg_type_is_mem_ptr(fn->arg5_type)  ||
            check_args_pair_invalid(fn->arg1_type, fn->arg2_type) ||
            check_args_pair_invalid(fn->arg2_type, fn->arg3_type) ||
            check_args_pair_invalid(fn->arg3_type, fn->arg4_type) ||
            check_args_pair_invalid(fn->arg4_type, fn->arg5_type))
                return false;

        return true;
}

static int check_func_proto(const struct bpf_func_proto *fn)
{
        return check_raw_mode_ok(fn) &&
               check_arg_pair_ok(fn) ? 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(&regs[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;
        int i;

        for (i = 0; i <= vstate->curframe; i++)
                __clear_all_pkt_pointers(env, vstate->frame[i]);
}

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_state *caller, *callee;
        int i, subprog, target_insn;

        if (state->curframe + 1 >= MAX_CALL_FRAMES) {
                verbose(env, "the call stack of %d frames is too deep\n",
                        state->curframe + 2);
                return -E2BIG;
        }

        target_insn = *insn_idx + insn->imm;
        subprog = find_subprog(env, target_insn + 1);
        if (subprog < 0) {
                verbose(env, "verifier bug. No program starts at insn %d\n",
                        target_insn + 1);
                return -EFAULT;
        }

        caller = state->frame[state->curframe];
        if (state->frame[state->curframe + 1]) {
                verbose(env, "verifier bug. Frame %d already allocated\n",
                        state->curframe + 1);
                return -EFAULT;
        }

        callee = kzalloc(sizeof(*callee), GFP_KERNEL);
        if (!callee)
                return -ENOMEM;
        state->frame[state->curframe + 1] = callee;

        /* callee cannot access r0, r6 - r9 for reading and has to write
         * into its own stack before reading from it.
         * callee can read/write into caller's stack
         */
        init_func_state(env, callee,
                        /* remember the callsite, it will be used by bpf_exit */
                        *insn_idx /* callsite */,
                        state->curframe + 1 /* frameno within this callchain */,
                        subprog + 1 /* subprog number within this prog */);

        /* copy r1 - r5 args that callee can access */
        for (i = BPF_REG_1; i <= BPF_REG_5; i++)
                callee->regs[i] = caller->regs[i];

        /* after the call regsiters 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);
        }

        /* only increment it after check_reg_arg() finished */
        state->curframe++;

        /* and go analyze first insn of the callee */
        *insn_idx = target_insn;

        if (env->log.level) {
                verbose(env, "caller:\n");
                print_verifier_state(env, caller);
                verbose(env, "callee:\n");
                print_verifier_state(env, callee);
        }
        return 0;
}

static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
        struct bpf_verifier_state *state = env->cur_state;
        struct bpf_func_state *caller, *callee;
        struct bpf_reg_state *r0;

        callee = state->frame[state->curframe];
        r0 = &callee->regs[BPF_REG_0];
        if (r0->type == PTR_TO_STACK) {
                /* technically it's ok to return caller's stack pointer
                 * (or caller's caller's pointer) back to the caller,
                 * since these pointers are valid. Only current stack
                 * pointer will be invalid as soon as function exits,
                 * but let's be conservative
                 */
                verbose(env, "cannot return stack pointer to the caller\n");
                return -EINVAL;
        }

        state->curframe--;
        caller = state->frame[state->curframe];
        /* return to the caller whatever r0 had in the callee */
        caller->regs[BPF_REG_0] = *r0;

        *insn_idx = callee->callsite + 1;
        if (env->log.level) {
                verbose(env, "returning from callee:\n");
                print_verifier_state(env, callee);
                verbose(env, "to caller at %d:\n", *insn_idx);
                print_verifier_state(env, caller);
        }
        /* clear everything in the callee */
        free_func_state(callee);
        state->frame[state->curframe + 1] = NULL;
        return 0;
}

static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
{
        const struct bpf_func_proto *fn = NULL;
        struct bpf_reg_state *regs;
        struct bpf_call_arg_meta meta;
        bool changes_data;
        int i, err;

        /* find function prototype */
        if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID) {
                verbose(env, "invalid func %s#%d\n", func_id_name(func_id),
                        func_id);
                return -EINVAL;
        }

        if (env->ops->get_func_proto)
                fn = env->ops->get_func_proto(func_id, env->prog);
        if (!fn) {
                verbose(env, "unknown func %s#%d\n", func_id_name(func_id),
                        func_id);
                return -EINVAL;
        }

        /* eBPF programs must be GPL compatible to use GPL-ed functions */
        if (!env->prog->gpl_compatible && fn->gpl_only) {
                verbose(env, "cannot call GPL only function from proprietary program\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) {
                verbose(env, "kernel subsystem misconfigured func %s#%d: r1 != ctx\n",
                        func_id_name(func_id), func_id);
                return -EINVAL;
        }

        memset(&meta, 0, sizeof(meta));
        meta.pkt_access = fn->pkt_access;

        err = check_func_proto(fn);
        if (err) {
                verbose(env, "kernel subsystem misconfigured func %s#%d\n",
                        func_id_name(func_id), func_id);
                return err;
        }

        /* 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;
        if (func_id == BPF_FUNC_tail_call) {
                if (meta.map_ptr == NULL) {
                        verbose(env, "verifier bug\n");
                        return -EINVAL;
                }
                env->insn_aux_data[insn_idx].map_ptr = meta.map_ptr;
        }
        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);
        if (err)
                return err;

        /* Mark slots with STACK_MISC in case of raw mode, stack offset
         * is inferred from register state.
         */
        for (i = 0; i < meta.access_size; i++) {
                err = check_mem_access(env, insn_idx, meta.regno, i, BPF_B,
                                       BPF_WRITE, -1, false);
                if (err)
                        return err;
        }

        regs = cur_regs(env);
        /* reset caller saved regs */
        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);
        }

        /* update return register (already marked as written above) */
        if (fn->ret_type == RET_INTEGER) {
                /* sets type to SCALAR_VALUE */
                mark_reg_unknown(env, regs, BPF_REG_0);
        } else if (fn->ret_type == RET_VOID) {
                regs[BPF_REG_0].type = NOT_INIT;
        } else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
                struct bpf_insn_aux_data *insn_aux;

                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);
                regs[BPF_REG_0].off = 0;
                /* remember map_ptr, so that check_map_access()
                 * can check 'value_size' boundary of memory access
                 * to map element returned from bpf_map_lookup_elem()
                 */
                if (meta.map_ptr == NULL) {
                        verbose(env,
                                "kernel subsystem misconfigured verifier\n");
                        return -EINVAL;
                }
                regs[BPF_REG_0].map_ptr = meta.map_ptr;
                regs[BPF_REG_0].id = ++env->id_gen;
                insn_aux = &env->insn_aux_data[insn_idx];
                if (!insn_aux->map_ptr)
                        insn_aux->map_ptr = meta.map_ptr;
                else if (insn_aux->map_ptr != meta.map_ptr)
                        insn_aux->map_ptr = BPF_MAP_PTR_POISON;
        } 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 = check_map_func_compatibility(env, meta.map_ptr, func_id);
        if (err)
                return err;

        if (changes_data)
                clear_all_pkt_pointers(env);
        return 0;
}

static bool signed_add_overflows(s64 a, s64 b)
{
        /* Do the add 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_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 check_reg_sane_offset(struct bpf_verifier_env *env,
                                  const struct bpf_reg_state *reg,
                                  enum bpf_reg_type type)
{
        bool known = tnum_is_const(reg->var_off);
        s64 val = reg->var_off.value;
        s64 smin = reg->smin_value;

        if (known && (val >= BPF_MAX_VAR_OFF || val <= -BPF_MAX_VAR_OFF)) {
                verbose(env, "math between %s pointer and %lld is not allowed\n",
                        reg_type_str[type], val);
                return false;
        }

        if (reg->off >= BPF_MAX_VAR_OFF || reg->off <= -BPF_MAX_VAR_OFF) {
                verbose(env, "%s pointer offset %d is not allowed\n",
                        reg_type_str[type], reg->off);
                return false;
        }

        if (smin == S64_MIN) {
                verbose(env, "math between %s pointer and register with unbounded min value is not allowed\n",
                        reg_type_str[type]);
                return false;
        }

        if (smin >= BPF_MAX_VAR_OFF || smin <= -BPF_MAX_VAR_OFF) {
                verbose(env, "value %lld makes %s pointer be out of bounds\n",
                        smin, reg_type_str[type]);
                return false;
        }

        return true;
}

/* Handles arithmetic on a pointer and a scalar: computes new min/max and var_off.
 * Caller should also handle BPF_MOV case separately.
 * If we return -EACCES, caller may want to try again treating pointer as a
 * scalar.  So we only emit a diagnostic if !env->allow_ptr_leaks.
 */
static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
                                   struct bpf_insn *insn,
                                   const struct bpf_reg_state *ptr_reg,
                                   const struct bpf_reg_state *off_reg)
{
        struct bpf_verifier_state *vstate = env->cur_state;
        struct bpf_func_state *state = vstate->frame[vstate->curframe];
        struct bpf_reg_state *regs = state->regs, *dst_reg;
        bool known = tnum_is_const(off_reg->var_off);
        s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
            smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
        u64 umin_val = off_reg->umin_value, umax_val = off_reg->umax_value,
            umin_ptr = ptr_reg->umin_value, umax_ptr = ptr_reg->umax_value;
        u8 opcode = BPF_OP(insn->code);
        u32 dst = insn->dst_reg;

        dst_reg = &regs[dst];

        if ((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;
        }

        if (BPF_CLASS(insn->code) != BPF_ALU64) {
                /* 32-bit ALU ops on pointers produce (meaningless) scalars */
                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);
                return -EACCES;
        }
        if (ptr_reg->type == CONST_PTR_TO_MAP) {
                verbose(env, "R%d pointer arithmetic on CONST_PTR_TO_MAP prohibited\n",
                        dst);
                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;
        }

        /* In case of 'scalar += pointer', dst_reg inherits pointer type and id.
         * The id may be overwritten later if we create a new variable offset.
         */
        dst_reg->type = ptr_reg->type;
        dst_reg->id = ptr_reg->id;

        if (!check_reg_sane_offset(env, off_reg, ptr_reg->type) ||
            !check_reg_sane_offset(env, ptr_reg, ptr_reg->type))
                return -EINVAL;

        switch (opcode) {
        case BPF_ADD:
                /* We can take a fixed offset as long as it doesn't overflow
                 * the s32 'off' field
                 */
                if (known && (ptr_reg->off + smin_val ==
                              (s64)(s32)(ptr_reg->off + smin_val))) {
                        /* pointer += K.  Accumulate it into fixed offset */
                        dst_reg->smin_value = smin_ptr;
                        dst_reg->smax_value = smax_ptr;
                        dst_reg->umin_value = umin_ptr;
                        dst_reg->umax_value = umax_ptr;
                        dst_reg->var_off = ptr_reg->var_off;
                        dst_reg->off = ptr_reg->off + smin_val;
                        dst_reg->range = ptr_reg->range;
                        break;
                }
                /* A new variable offset is created.  Note that off_reg->off
                 * == 0, since it's a scalar.
                 * dst_reg gets the pointer type and since some positive
                 * integer value was added to the pointer, give it a new 'id'
                 * if it's a PTR_TO_PACKET.
                 * this creates a new 'base' pointer, off_reg (variable) gets
                 * added into the variable offset, and we copy the fixed offset
                 * from ptr_reg.
                 */
                if (signed_add_overflows(smin_ptr, smin_val) ||
                    signed_add_overflows(smax_ptr, smax_val)) {
                        dst_reg->smin_value = S64_MIN;
                        dst_reg->smax_value = S64_MAX;
                } else {
                        dst_reg->smin_value = smin_ptr + smin_val;
                        dst_reg->smax_value = smax_ptr + smax_val;
                }
                if (umin_ptr + umin_val < umin_ptr ||
                    umax_ptr + umax_val < umax_ptr) {
                        dst_reg->umin_value = 0;
                        dst_reg->umax_value = U64_MAX;
                } else {
                        dst_reg->umin_value = umin_ptr + umin_val;
                        dst_reg->umax_value = umax_ptr + umax_val;
                }
                dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
                dst_reg->off = ptr_reg->off;
                if (reg_is_pkt_pointer(ptr_reg)) {
                        dst_reg->id = ++env->id_gen;
                        /* something was added to pkt_ptr, set range to zero */
                        dst_reg->range = 0;
                }
                break;
        case BPF_SUB:
                if (dst_reg == off_reg) {
                        /* scalar -= pointer.  Creates an unknown scalar */
                        verbose(env, "R%d tried to subtract pointer from scalar\n",
                                dst);
                        return -EACCES;
                }
                /* We don't allow subtraction from FP, because (according to
                 * test_verifier.c test "invalid fp arithmetic", JITs might not
                 * be able to deal with it.
                 */
                if (ptr_reg->type == PTR_TO_STACK) {
                        verbose(env, "R%d subtraction from stack pointer prohibited\n",
                                dst);
                        return -EACCES;
                }
                if (known && (ptr_reg->off - smin_val ==
                              (s64)(s32)(ptr_reg->off - smin_val))) {
                        /* pointer -= K.  Subtract it from fixed offset */
                        dst_reg->smin_value = smin_ptr;
                        dst_reg->smax_value = smax_ptr;
                        dst_reg->umin_value = umin_ptr;
                        dst_reg->umax_value = umax_ptr;
                        dst_reg->var_off = ptr_reg->var_off;
                        dst_reg->id = ptr_reg->id;
                        dst_reg->off = ptr_reg->off - smin_val;
                        dst_reg->range = ptr_reg->range;
                        break;
                }
                /* A new variable offset is created.  If the subtrahend is known
                 * nonnegative, then any reg->range we had before is still good.
                 */
                if (signed_sub_overflows(smin_ptr, smax_val) ||
                    signed_sub_overflows(smax_ptr, smin_val)) {
                        /* Overflow possible, we know nothing */
                        dst_reg->smin_value = S64_MIN;
                        dst_reg->smax_value = S64_MAX;
                } else {
                        dst_reg->smin_value = smin_ptr - smax_val;
                        dst_reg->smax_value = smax_ptr - smin_val;
                }
                if (umin_ptr < 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 = umin_ptr - umax_val;
                        dst_reg->umax_value = umax_ptr - umin_val;
                }
                dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
                dst_reg->off = ptr_reg->off;
                if (reg_is_pkt_pointer(ptr_reg)) {
                        dst_reg->id = ++env->id_gen;
                        /* something was added to pkt_ptr, set range to zero */
                        if (smin_val < 0)
                                dst_reg->range = 0;
                }
                break;
        case BPF_AND:
        case BPF_OR:
        case BPF_XOR:
                /* bitwise ops on pointers are troublesome, prohibit. */
                verbose(env, "R%d bitwise operator %s on pointer prohibited\n",
                        dst, bpf_alu_string[opcode >> 4]);
                return -EACCES;
        default:
                /* other operators (e.g. MUL,LSH) produce non-pointer results */
                verbose(env, "R%d pointer arithmetic with %s operator prohibited\n",
                        dst, bpf_alu_string[opcode >> 4]);
                return -EACCES;
        }

        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);
        return 0;
}

/* WARNING: This function does calculations on 64-bit values, but the actual
 * execution may occur on 32-bit values. Therefore, things like bitshifts
 * need extra checks in the 32-bit case.
 */
static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
                                      struct bpf_insn *insn,
                                      struct bpf_reg_state *dst_reg,
                                      struct bpf_reg_state src_reg)
{
        struct bpf_reg_state *regs = cur_regs(env);
        u8 opcode = BPF_OP(insn->code);
        bool src_known, dst_known;
        s64 smin_val, smax_val;
        u64 umin_val, umax_val;
        u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;

        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;
        }

        if (!src_known &&
            opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
                __mark_reg_unknown(dst_reg);
                return 0;
        }

        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;
                }
                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;
                }
                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;
                }
                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);
                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);
                break;
        case BPF_LSH:
                if (umax_val >= insn_bitness) {
                        /* Shifts greater than 31 or 63 are undefined.
                         * This includes shifts by a negative number.
                         */
                        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;
                }
                if (src_known)
                        dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
                else
                        dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val);
                /* We may learn something more from the var_off */
                __update_reg_bounds(dst_reg);
                break;
        case BPF_RSH:
                if (umax_val >= insn_bitness) {
                        /* Shifts greater than 31 or 63 are undefined.
                         * This includes shifts by a negative number.
                         */
                        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;
                if (src_known)
                        dst_reg->var_off = tnum_rshift(dst_reg->var_off,
                                                       umin_val);
                else
                        dst_reg->var_off = tnum_rshift(tnum_unknown, 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);
                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);
                coerce_reg_to_size(&src_reg, 4);
        }

        __reg_deduce_bounds(dst_reg);
        __reg_bound_offset(dst_reg);
        return 0;
}

/* Handles ALU ops other than BPF_END, BPF_NEG and BPF_MOV: computes new min/max
 * and var_off.
 */
static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
                                   struct bpf_insn *insn)
{
        struct bpf_verifier_state *vstate = env->cur_state;
        struct bpf_func_state *state = vstate->frame[vstate->curframe];
        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);

        dst_reg = &regs[insn->dst_reg];
        src_reg = NULL;
        if (dst_reg->type != SCALAR_VALUE)
                ptr_reg = dst_reg;
        if (BPF_SRC(insn->code) == BPF_X) {
                src_reg = &regs[insn->src_reg];
                if (src_reg->type != SCALAR_VALUE) {
                        if (dst_reg->type != SCALAR_VALUE) {
                                /* Combining two pointers by any ALU op yields
                                 * an arbitrary scalar. Disallow all math except
                                 * pointer subtraction
                                 */
                                if (opcode == BPF_SUB){
                                        mark_reg_unknown(env, regs, insn->dst_reg);
                                        return 0;
                                }
                                verbose(env, "R%d pointer %s pointer prohibited\n",
                                        insn->dst_reg,
                                        bpf_alu_string[opcode >> 4]);
                                return -EACCES;
                        } else {
                                /* scalar += pointer
                                 * This is legal, but we have to reverse our
                                 * src/dest handling in computing the range
                                 */
                                return adjust_ptr_min_max_vals(env, insn,
                                                               src_reg, dst_reg);
                        }
                } else if (ptr_reg) {
                        /* pointer += scalar */
                        return adjust_ptr_min_max_vals(env, insn,
                                                       dst_reg, src_reg);
                }
        } else {
                /* Pretend the src is a reg with a known value, since we only
                 * need to be able to read from this state.
                 */
                off_reg.type = SCALAR_VALUE;
                __mark_reg_known(&off_reg, insn->imm);
                src_reg = &off_reg;
                if (ptr_reg) /* pointer += K */
                        return adjust_ptr_min_max_vals(env, insn,
                                                       ptr_reg, src_reg);
        }

        /* Got here implies adding two SCALAR_VALUEs */
        if (WARN_ON_ONCE(ptr_reg)) {
                print_verifier_state(env, state);
                verbose(env, "verifier internal error: unexpected ptr_reg\n");
                return -EINVAL;
        }
        if (WARN_ON(!src_reg)) {
                print_verifier_state(env, state);
                verbose(env, "verifier internal error: no src_reg\n");
                return -EINVAL;
        }
        return adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
}

/* check validity of 32-bit and 64-bit arithmetic operations */
static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
        struct bpf_reg_state *regs = cur_regs(env);
        u8 opcode = BPF_OP(insn->code);
        int err;

        if (opcode == BPF_END || opcode == BPF_NEG) {
                if (opcode == BPF_NEG) {
                        if (BPF_SRC(insn->code) != 0 ||
                            insn->src_reg != BPF_REG_0 ||
                            insn->off != 0 || insn->imm != 0) {
                                verbose(env, "BPF_NEG uses reserved fields\n");
                                return -EINVAL;
                        }
                } else {
                        if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
                            (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
                            BPF_CLASS(insn->code) == BPF_ALU64) {
                                verbose(env, "BPF_END uses reserved fields\n");
                                return -EINVAL;
                        }
                }

                /* check src operand */
                err = check_reg_arg(env, insn->dst_reg, SRC_OP);
                if (err)
                        return err;

                if (is_pointer_value(env, insn->dst_reg)) {
                        verbose(env, "R%d pointer arithmetic prohibited\n",
                                insn->dst_reg);
                        return -EACCES;
                }

                /* check dest operand */
                err = check_reg_arg(env, insn->dst_reg, DST_OP);
                if (err)
                        return err;

        } else if (opcode == BPF_MOV) {

                if (BPF_SRC(insn->code) == BPF_X) {
                        if (insn->imm != 0 || insn->off != 0) {
                                verbose(env, "BPF_MOV uses reserved fields\n");
                                return -EINVAL;
                        }

                        /* check src operand */
                        err = check_reg_arg(env, insn->src_reg, SRC_OP);
                        if (err)
                                return err;
                } else {
                        if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
                                verbose(env, "BPF_MOV uses reserved fields\n");
                                return -EINVAL;
                        }
                }

                /* check dest operand */
                err = check_reg_arg(env, insn->dst_reg, DST_OP);
                if (err)
                        return err;

                if (BPF_SRC(insn->code) == BPF_X) {
                        if (BPF_CLASS(insn->code) == BPF_ALU64) {
                                /* case: R1 = R2
                                 * copy register state to dest reg
                                 */
                                regs[insn->dst_reg] = regs[insn->src_reg];
                                regs[insn->dst_reg].live |= REG_LIVE_WRITTEN;
                        } else {
                                /* R1 = (u32) R2 */
                                if (is_pointer_value(env, insn->src_reg)) {
                                        verbose(env,
                                                "R%d partial copy of pointer\n",
                                                insn->src_reg);
                                        return -EACCES;
                                }
                                mark_reg_unknown(env, regs, insn->dst_reg);
                                coerce_reg_to_size(&regs[insn->dst_reg], 4);
                        }
                } else {
                        /* case: R = imm
                         * remember the value we stored into this reg
                         */
                        regs[insn->dst_reg].type = SCALAR_VALUE;
                        if (BPF_CLASS(insn->code) == BPF_ALU64) {
                                __mark_reg_known(regs + insn->dst_reg,
                                                 insn->imm);
                        } else {
                                __mark_reg_known(regs + insn->dst_reg,
                                                 (u32)insn->imm);
                        }
                }

        } else if (opcode > BPF_END) {
                verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
                return -EINVAL;

        } else {        /* all other ALU ops: and, sub, xor, add, ... */

                if (BPF_SRC(insn->code) == BPF_X) {
                        if (insn->imm != 0 || insn->off != 0) {
                                verbose(env, "BPF_ALU uses reserved fields\n");
                                return -EINVAL;
                        }
                        /* check src1 operand */
                        err = check_reg_arg(env, insn->src_reg, SRC_OP);
                        if (err)
                                return err;
                } else {
                        if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
                                verbose(env, "BPF_ALU uses reserved fields\n");
                                return -EINVAL;
                        }
                }

                /* check src2 operand */
                err = check_reg_arg(env, insn->dst_reg, SRC_OP);
                if (err)
                        return err;

                if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
                    BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
                        verbose(env, "div by zero\n");
                        return -EINVAL;
                }