xref: /linux/kernel/bpf/verifier.c (revision 9b27cd0554c5883318256c32b2aaf060a3e20e0a)

// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016 Facebook
 * Copyright (c) 2018 Covalent IO, Inc. http://covalent.io
 */
#include <uapi/linux/btf.h>
#include <linux/bpf-cgroup.h>
#include <linux/count_zeros.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/bpf_verifier.h>
#include <linux/filter.h>
#include <net/netlink.h>
#include <linux/file.h>
#include <linux/vmalloc.h>
#include <linux/stringify.h>
#include <linux/bsearch.h>
#include <linux/sort.h>
#include <linux/perf_event.h>
#include <linux/ctype.h>
#include <linux/error-injection.h>
#include <linux/bpf_lsm.h>
#include <linux/security.h>
#include <linux/verification.h>
#include <linux/keyctl.h>
#include <linux/btf_ids.h>
#include <linux/poison.h>
#include <linux/module.h>
#include <linux/cpumask.h>
#include <linux/cnum.h>
#include <linux/gcd.h>
#include <linux/bpf_mem_alloc.h>
#include <net/xdp.h>
#include <linux/trace_events.h>
#include <linux/kallsyms.h>

#include "diagnostics.h"
#include "disasm.h"

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

enum bpf_features {
	BPF_FEAT_RDONLY_CAST_TO_VOID = 0,
	BPF_FEAT_STREAMS	     = 1,
	__MAX_BPF_FEAT,
};

struct bpf_mem_alloc bpf_global_percpu_ma;
static bool bpf_global_percpu_ma_set;

/* 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 paths 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, PTR_TO_SOCKET. These are
 * four pointer types recognized by check_mem_access() function.
 *
 * PTR_TO_MAP_VALUE means that this register is pointing to 'map element value'
 * and the range of [ptr, ptr + map's value_size) is accessible.
 *
 * 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 either 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.
 *
 * The following reference types represent a potential reference to a kernel
 * resource which, after first being allocated, must be checked and freed by
 * the BPF program:
 * - PTR_TO_SOCKET_OR_NULL, PTR_TO_SOCKET
 *
 * When the verifier sees a helper call return a reference type, it allocates a
 * pointer id for the reference and stores it in the current function state.
 * Similar to the way that PTR_TO_MAP_VALUE_OR_NULL is converted into
 * PTR_TO_MAP_VALUE, PTR_TO_SOCKET_OR_NULL becomes PTR_TO_SOCKET when the type
 * passes through a NULL-check conditional. For the branch wherein the state is
 * changed to CONST_IMM, the verifier releases the reference.
 *
 * For each helper function that allocates a reference, such as
 * bpf_sk_lookup_tcp(), there is a corresponding release function, such as
 * bpf_sk_release(). When a reference type passes into the release function,
 * the verifier also releases the reference. If any unchecked or unreleased
 * reference remains at the end of the program, the verifier rejects it.
 */

/* verifier_state + insn_idx are pushed to stack when branch is encountered */
struct bpf_verifier_stack_elem {
	/* verifier 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;
	/* length of verifier log at the time this state was pushed on stack */
	u32 log_pos;
	u64 diag_log_pos;
};

#define BPF_COMPLEXITY_LIMIT_JMP_SEQ	8192
#define BPF_COMPLEXITY_LIMIT_STATES	64

#define BPF_GLOBAL_PERCPU_MA_MAX_SIZE  512

#define BPF_PRIV_STACK_MIN_SIZE		64

static int acquire_reference(struct bpf_verifier_env *env, int insn_idx, int parent_id);
static int __release_reference_nomark(struct bpf_verifier_state *state, int id);
static int release_reference_nomark(struct bpf_verifier_env *env, int id);
static int release_reference(struct bpf_verifier_env *env, int id);
static void invalidate_non_owning_refs(struct bpf_verifier_env *env);
static void invalidate_rcu_protected_refs(struct bpf_verifier_env *env);
static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env);
static bool is_tracing_prog_type(enum bpf_prog_type type);
static int ref_set_non_owning(struct bpf_verifier_env *env,
			      struct bpf_reg_state *reg);
static bool is_trusted_reg(struct bpf_verifier_env *env, const struct bpf_reg_state *reg);
static inline bool in_sleepable_context(struct bpf_verifier_env *env);
static bool in_rcu_callback(struct bpf_verifier_env *env);
static const char *non_sleepable_context_description(struct bpf_verifier_env *env);
static void scalar32_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg);
static void scalar_min_max_add(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg);

static void bpf_map_ptr_store(struct bpf_insn_aux_data *aux,
			      struct bpf_map *map,
			      bool unpriv, bool poison)
{
	unpriv |= bpf_map_ptr_unpriv(aux);
	aux->map_ptr_state.unpriv = unpriv;
	aux->map_ptr_state.poison = poison;
	aux->map_ptr_state.map_ptr = map;
}

static void bpf_map_key_store(struct bpf_insn_aux_data *aux, u64 state)
{
	bool poisoned = bpf_map_key_poisoned(aux);

	aux->map_key_state = state | BPF_MAP_KEY_SEEN |
			     (poisoned ? BPF_MAP_KEY_POISON : 0ULL);
}

static void update_ref_obj(struct ref_obj_desc *ref_obj, struct bpf_reg_state *reg)
{
	ref_obj->id = reg->id;
	ref_obj->parent_id = reg->parent_id;
	ref_obj->cnt++;
}

static int validate_ref_obj(struct bpf_verifier_env *env, struct ref_obj_desc *ref_obj)
{
	if (ref_obj->cnt > 1) {
		verifier_bug(env, "function expects only one referenced object but got %d\n",
			     ref_obj->cnt);
		return -EFAULT;
	}

	return 0;
}

struct bpf_kfunc_meta {
	struct btf *btf;
	const struct btf_type *proto;
	const char *name;
	const u32 *flags;
	s32 id;
};

struct btf *btf_vmlinux;

typedef struct argno {
	int argno;
} argno_t;

static argno_t argno_from_reg(u32 regno)
{
	return (argno_t){ .argno = regno };
}

static argno_t argno_from_arg(u32 arg)
{
	return (argno_t){ .argno = -arg };
}

static int reg_from_argno(argno_t a)
{
	if (a.argno >= 0)
		return a.argno;
	if (a.argno >= -MAX_BPF_FUNC_REG_ARGS)
		return -a.argno;
	return -1;
}

static int arg_from_argno(argno_t a)
{
	if (a.argno < 0)
		return -a.argno;
	return -1;
}

static int arg_idx_from_argno(argno_t a)
{
	return arg_from_argno(a) - 1;
}

/* Normalize helper register numbers and kfunc argument numbers to ABI slots. */
static u32 arg_slot_from_argno(argno_t a)
{
	return abs(a.argno) - 1;
}

static const char *btf_type_name(const struct btf *btf, u32 id)
{
	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
}

static DEFINE_MUTEX(bpf_verifier_lock);
static DEFINE_MUTEX(btf_vmlinux_lock);
static DEFINE_MUTEX(bpf_percpu_ma_lock);

__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 void verbose_invalid_scalar(struct bpf_verifier_env *env,
				   struct bpf_reg_state *reg,
				   struct bpf_retval_range range, const char *ctx,
				   const char *reg_name)
{
	bool unknown = true;

	verbose(env, "%s the register %s has", ctx, reg_name);
	if (reg_smin(reg) > S64_MIN) {
		verbose(env, " smin=%lld", reg_smin(reg));
		unknown = false;
	}
	if (reg_smax(reg) < S64_MAX) {
		verbose(env, " smax=%lld", reg_smax(reg));
		unknown = false;
	}
	if (unknown)
		verbose(env, " unknown scalar value");
	verbose(env, " should have been in [%d, %d]\n", range.minval, range.maxval);
}

static bool reg_not_null(struct bpf_verifier_env *env, const struct bpf_reg_state *reg)
{
	enum bpf_reg_type type;

	type = reg->type;
	if (type_may_be_null(type))
		return false;

	/*
	 * The types below guarantee a non-NULL base, an unbounded offset can
	 * still wrap base + offset to zero.
	 */
	if (reg_smin(reg) <= -BPF_MAX_VAR_OFF || reg_smax(reg) >= BPF_MAX_VAR_OFF)
		return false;

	type = base_type(type);
	return type == PTR_TO_SOCKET ||
		type == PTR_TO_TCP_SOCK ||
		type == PTR_TO_XDP_SOCK ||
		type == PTR_TO_BUF ||
		type == PTR_TO_MAP_VALUE ||
		type == PTR_TO_MAP_KEY ||
		type == PTR_TO_SOCK_COMMON ||
		(type == PTR_TO_BTF_ID && is_trusted_reg(env, reg)) ||
		(type == PTR_TO_MEM && !(reg->type & PTR_UNTRUSTED)) ||
		type == CONST_PTR_TO_MAP;
}

static struct btf_record *reg_btf_record(const struct bpf_reg_state *reg)
{
	struct btf_record *rec = NULL;
	struct btf_struct_meta *meta;

	if (reg->type == PTR_TO_MAP_VALUE) {
		rec = reg->map_ptr->record;
	} else if (type_is_ptr_alloc_obj(reg->type)) {
		meta = btf_find_struct_meta(reg->btf, reg->btf_id);
		if (meta)
			rec = meta->record;
	}
	return rec;
}

bool bpf_subprog_is_global(const struct bpf_verifier_env *env, int subprog)
{
	struct bpf_func_info_aux *aux = env->prog->aux->func_info_aux;

	return aux && aux[subprog].linkage == BTF_FUNC_GLOBAL;
}

static const struct btf_type *subprog_ret_type(struct bpf_verifier_env *env, int subprog)
{
	const struct btf_type *func, *func_proto;
	const struct btf *btf = env->prog->aux->btf;
	u32 btf_id;

	if (!btf || !env->prog->aux->func_info)
		return NULL;

	btf_id = env->prog->aux->func_info[subprog].type_id;

	/* Both already validated by prepare_btf_func() at prog load. */
	func = btf_type_by_id(btf, btf_id);
	func_proto = btf_type_by_id(btf, func->type);

	return btf_type_skip_modifiers(btf, func_proto->type, NULL);
}

static bool subprog_returns_void(struct bpf_verifier_env *env, int subprog)
{
	const struct btf_type *type = subprog_ret_type(env, subprog);

	return type && btf_type_is_void(type);
}

static u32 ret_regs_cnt(u32 size)
{
	return size > 8 && size <= 16 ? 2 : 1;
}

/* Registers holding a function return value, in order. See ret_regs_cnt(). */
static const int ret_regs[] = { BPF_REG_0, BPF_REG_2 };

static int bpf_compute_subprog_ret_regs(struct bpf_verifier_env *env)
{
	const struct btf *btf = env->prog->aux->btf;
	const struct btf_type *type;
	int subprog;
	u32 size;

	if (!env->prog->jit_requested || bpf_prog_is_offloaded(env->prog->aux))
		return 0;

	/*
	 * Skip the main program: its return value is the program's exit code,
	 * read out of R0, so it never uses the register pair. An extension does
	 * have a real prototype for subprog 0, but btf_check_func_type_match()
	 * refuses to replace a function returning more than 8 bytes.
	 */
	for (subprog = 1; subprog < env->subprog_cnt; subprog++) {
		type = subprog_ret_type(env, subprog);
		if (!type || btf_type_is_void(type))
			continue;
		if (verifier_bug_if(IS_ERR(btf_resolve_size(btf, type, &size)), env,
				    "cannot size return type of subprog %d", subprog))
			return -EFAULT;
		if (ret_regs_cnt(size) > 1) {
			subprog_info(env, subprog)->ret_reg_pair = true;
			env->prog->jit_required = 1;
		}
	}

	return 0;
}

const char *bpf_subprog_name(const struct bpf_verifier_env *env, int subprog)
{
	struct bpf_func_info *info;

	if (!env->prog->aux->func_info)
		return "";

	info = &env->prog->aux->func_info[subprog];
	return btf_type_name(env->prog->aux->btf, info->type_id);
}

void bpf_mark_subprog_exc_cb(struct bpf_verifier_env *env, int subprog)
{
	struct bpf_subprog_info *info = subprog_info(env, subprog);

	info->is_cb = true;
	info->is_async_cb = true;
	info->is_exception_cb = true;
}

static bool subprog_is_exc_cb(struct bpf_verifier_env *env, int subprog)
{
	return subprog_info(env, subprog)->is_exception_cb;
}

static bool reg_may_point_to_spin_lock(const struct bpf_reg_state *reg)
{
	return btf_record_has_field(reg_btf_record(reg), BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK);
}

static bool type_is_rdonly_mem(u32 type)
{
	return type & MEM_RDONLY;
}

static bool is_acquire_function(enum bpf_func_id func_id,
				const struct bpf_map *map)
{
	enum bpf_map_type map_type = map ? map->map_type : BPF_MAP_TYPE_UNSPEC;

	if (func_id == BPF_FUNC_sk_lookup_tcp ||
	    func_id == BPF_FUNC_sk_lookup_udp ||
	    func_id == BPF_FUNC_skc_lookup_tcp ||
	    func_id == BPF_FUNC_ringbuf_reserve ||
	    func_id == BPF_FUNC_kptr_xchg)
		return true;

	if (func_id == BPF_FUNC_map_lookup_elem &&
	    (map_type == BPF_MAP_TYPE_SOCKMAP ||
	     map_type == BPF_MAP_TYPE_SOCKHASH))
		return true;

	return false;
}

static bool is_ptr_cast_function(enum bpf_func_id func_id)
{
	return func_id == BPF_FUNC_tcp_sock ||
		func_id == BPF_FUNC_sk_fullsock ||
		func_id == BPF_FUNC_skc_to_tcp_sock ||
		func_id == BPF_FUNC_skc_to_tcp6_sock ||
		func_id == BPF_FUNC_skc_to_udp6_sock ||
		func_id == BPF_FUNC_skc_to_mptcp_sock ||
		func_id == BPF_FUNC_skc_to_tcp_timewait_sock ||
		func_id == BPF_FUNC_skc_to_tcp_request_sock;
}

static bool is_sync_callback_calling_kfunc(u32 btf_id);
static bool is_async_callback_calling_kfunc(u32 btf_id);
static bool is_call_rcu_kfunc(u32 btf_id);
static bool is_callback_calling_kfunc(u32 btf_id);

static bool is_bpf_wq_set_callback_kfunc(u32 btf_id);
static bool is_task_work_add_kfunc(u32 func_id);

static bool is_sync_callback_calling_function(enum bpf_func_id func_id)
{
	return func_id == BPF_FUNC_for_each_map_elem ||
	       func_id == BPF_FUNC_find_vma ||
	       func_id == BPF_FUNC_loop ||
	       func_id == BPF_FUNC_user_ringbuf_drain;
}

static bool is_async_callback_calling_function(enum bpf_func_id func_id)
{
	return func_id == BPF_FUNC_timer_set_callback;
}

static bool is_callback_calling_function(enum bpf_func_id func_id)
{
	return is_sync_callback_calling_function(func_id) ||
	       is_async_callback_calling_function(func_id);
}

bool bpf_is_sync_callback_calling_insn(struct bpf_insn *insn)
{
	return (bpf_helper_call(insn) && is_sync_callback_calling_function(insn->imm)) ||
	       (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm));
}

bool bpf_is_async_callback_calling_insn(struct bpf_insn *insn)
{
	return (bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm)) ||
	       (bpf_pseudo_kfunc_call(insn) && is_async_callback_calling_kfunc(insn->imm));
}

static bool is_async_cb_sleepable(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	/* bpf_timer callbacks are never sleepable. */
	if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_timer_set_callback)
		return false;

	/* bpf_call_rcu and bpf_call_rcu_tasks_trace callbacks are never sleepable. */
	if (bpf_pseudo_kfunc_call(insn) && insn->off == 0 && is_call_rcu_kfunc(insn->imm))
		return false;

	/* bpf_wq and bpf_task_work callbacks are always sleepable. */
	if (bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
	    (is_bpf_wq_set_callback_kfunc(insn->imm) || is_task_work_add_kfunc(insn->imm)))
		return true;

	verifier_bug(env, "unhandled async callback in is_async_cb_sleepable");
	return false;
}

/* From here on the maps of the program count it as a sleepable user. */
static void mark_sleepable_async_cb(struct bpf_verifier_env *env)
{
	int i;

	if (bpf_prog_runs_sleepable(env->prog))
		return;

	env->prog->aux->sleepable_async_cb = true;
	for (i = 0; i < env->used_map_cnt; i++)
		atomic64_inc(&env->used_maps[i]->sleepable_refcnt);
}

bool bpf_is_may_goto_insn(struct bpf_insn *insn)
{
	return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO;
}

static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots)
{
	int allocated_slots = bpf_stack_nr_slots(state);

	/*
	 * We need to check that slots between [spi - nr_slots + 1, spi] are
	 * within [0, allocated_stack).
	 *
	 * Please note that the spi grows downwards. For example, a dynptr
	 * takes the size of two stack slots; the first slot will be at
	 * spi and the second slot will be at spi - 1.
	 */
	return spi - nr_slots + 1 >= 0 && spi < allocated_slots;
}

static int stack_slot_obj_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			          const char *obj_kind, int nr_slots)
{
	int off, spi;

	if (!tnum_is_const(reg->var_off)) {
		verbose(env, "%s has to be at a constant offset\n", obj_kind);
		return -EINVAL;
	}

	off = reg->var_off.value;
	if (off >= 0 || off % BPF_REG_SIZE) {
		verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off);
		return -EINVAL;
	}

	spi = bpf_get_spi(off);
	if (spi + 1 < nr_slots) {
		verbose(env, "cannot pass in %s at an offset=%d\n", obj_kind, off);
		return -EINVAL;
	}

	if (!is_spi_bounds_valid(bpf_func(env, reg), spi, nr_slots))
		return -ERANGE;
	return spi;
}

static int dynptr_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	return stack_slot_obj_get_spi(env, reg, "dynptr", BPF_DYNPTR_NR_SLOTS);
}

static int iter_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int nr_slots)
{
	return stack_slot_obj_get_spi(env, reg, "iter", nr_slots);
}

static int irq_flag_get_spi(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	return stack_slot_obj_get_spi(env, reg, "irq_flag", 1);
}

static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
{
	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
	case DYNPTR_TYPE_LOCAL:
		return BPF_DYNPTR_TYPE_LOCAL;
	case DYNPTR_TYPE_RINGBUF:
		return BPF_DYNPTR_TYPE_RINGBUF;
	case DYNPTR_TYPE_SKB:
		return BPF_DYNPTR_TYPE_SKB;
	case DYNPTR_TYPE_XDP:
		return BPF_DYNPTR_TYPE_XDP;
	case DYNPTR_TYPE_SKB_META:
		return BPF_DYNPTR_TYPE_SKB_META;
	case DYNPTR_TYPE_FILE:
		return BPF_DYNPTR_TYPE_FILE;
	default:
		return BPF_DYNPTR_TYPE_INVALID;
	}
}

static enum bpf_type_flag get_dynptr_type_flag(enum bpf_dynptr_type type)
{
	switch (type) {
	case BPF_DYNPTR_TYPE_LOCAL:
		return DYNPTR_TYPE_LOCAL;
	case BPF_DYNPTR_TYPE_RINGBUF:
		return DYNPTR_TYPE_RINGBUF;
	case BPF_DYNPTR_TYPE_SKB:
		return DYNPTR_TYPE_SKB;
	case BPF_DYNPTR_TYPE_XDP:
		return DYNPTR_TYPE_XDP;
	case BPF_DYNPTR_TYPE_SKB_META:
		return DYNPTR_TYPE_SKB_META;
	case BPF_DYNPTR_TYPE_FILE:
		return DYNPTR_TYPE_FILE;
	default:
		return 0;
	}
}

static bool dynptr_type_referenced(enum bpf_dynptr_type type)
{
	return type == BPF_DYNPTR_TYPE_RINGBUF || type == BPF_DYNPTR_TYPE_FILE;
}

static void __mark_dynptr_reg(struct bpf_reg_state *reg,
			      enum bpf_dynptr_type type,
			      bool first_slot, int id, int parent_id);

static void mark_dynptr_stack_regs(struct bpf_verifier_env *env,
				   struct bpf_reg_state *sreg1,
				   struct bpf_reg_state *sreg2,
				   enum bpf_dynptr_type type, int parent_id)
{
	int id = ++env->id_gen;

	__mark_dynptr_reg(sreg1, type, true, id, parent_id);
	__mark_dynptr_reg(sreg2, type, false, id, parent_id);
}

static void mark_dynptr_cb_reg(struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg,
			       enum bpf_dynptr_type type)
{
	__mark_dynptr_reg(reg, type, true, ++env->id_gen, 0);
}

static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env,
				        struct bpf_func_state *state, int spi);

static int destroy_dynptrs_in_stack_slots(struct bpf_verifier_env *env,
					  struct bpf_func_state *state,
					  int first_spi, int last_spi)
{
	int spi, err;

	for (spi = first_spi; spi <= last_spi; spi++) {
		err = destroy_if_dynptr_stack_slot(env, state, spi);
		if (err)
			return err;
	}

	return 0;
}

static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				   enum bpf_arg_type arg_type, int insn_idx,
				   struct ref_obj_desc *ref_obj, struct bpf_dynptr_desc *dynptr)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi, i, err, parent_id = 0;
	enum bpf_dynptr_type type;

	spi = dynptr_get_spi(env, reg);
	if (spi < 0)
		return spi;

	/* We cannot assume both spi and spi - 1 belong to the same dynptr,
	 * hence we need to destroy dynptrs in both slots,
	 * to ensure that for the following example:
	 *	[d1][d1][d2][d2]
	 * spi    3   2   1   0
	 * So marking spi = 2 should lead to destruction of both d1 and d2. In
	 * case they do belong to same dynptr, second call won't see slot_type
	 * as STACK_DYNPTR and will simply skip destruction.
	 */
	err = destroy_dynptrs_in_stack_slots(env, state, spi - 1, spi);
	if (err)
		return err;

	for (i = 0; i < BPF_REG_SIZE; i++) {
		bpf_stack_slot(state, spi)->slot_type[i] = STACK_DYNPTR;
		bpf_stack_slot(state, spi - 1)->slot_type[i] = STACK_DYNPTR;
	}

	type = arg_to_dynptr_type(arg_type);
	if (type == BPF_DYNPTR_TYPE_INVALID)
		return -EINVAL;

	if (dynptr->type == BPF_DYNPTR_TYPE_INVALID) { /* dynptr constructors */
		err = validate_ref_obj(env, ref_obj);
		if (err)
			return err;

		/* Track parent's id if the parent is a referenced object */
		parent_id = ref_obj->id;

		if (dynptr_type_referenced(type)) {
			int id;

			/*
			 * Create an intermediate reference that tracks the referenced
			 * object for the referenced dynptr. Freeing a referenced dynptr
			 * through helpers/kfuncs will invalidate all clones.
			 */
			id = acquire_reference(env, insn_idx, parent_id);
			if (id < 0)
				return id;

			parent_id = id;
		}
	} else { /* bpf_dynptr_clone() */
		parent_id = dynptr->parent_id;
	}

	mark_dynptr_stack_regs(env, &bpf_stack_slot(state, spi)->spilled_ptr,
			       &bpf_stack_slot(state, spi - 1)->spilled_ptr, type, parent_id);

	return 0;
}

static void invalidate_dynptr(struct bpf_verifier_env *env, struct bpf_stack_state *stack)
{
	int i;

	for (i = 0; i < BPF_REG_SIZE; i++) {
		stack[0].slot_type[i] = STACK_INVALID;
		stack[1].slot_type[i] = STACK_INVALID;
	}

	bpf_mark_reg_not_init(env, &stack[0].spilled_ptr);
	bpf_mark_reg_not_init(env, &stack[1].spilled_ptr);
}

static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi;

	spi = dynptr_get_spi(env, reg);
	if (spi < 0)
		return spi;

	/*
	 * For referenced dynptr, release the parent ref which cascades to
	 * all clones and derived slices. For non-referenced dynptr, only
	 * the dynptr and slices derived from it will be invalidated.
	 */
	reg = &bpf_stack_slot(state, spi)->spilled_ptr;
	return release_reference(env, dynptr_type_referenced(reg->dynptr.type)
				      ? reg->parent_id
				      : reg->id);
}

static void __mark_reg_unknown(const struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg);

static void mark_reg_invalid(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	if (!env->allow_ptr_leaks)
		bpf_mark_reg_not_init(env, reg);
	else
		__mark_reg_unknown(env, reg);
}

static int dynptr_ref_cnt(struct bpf_verifier_env *env, int v_parent_id)
{
	struct bpf_stack_state *stack;
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	int ref_cnt = 0;

	bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, stack, 1 << STACK_DYNPTR, ({
		if (!stack || stack->slot_type[0] != STACK_DYNPTR)
			continue;
		if (!stack->spilled_ptr.dynptr.first_slot)
			continue;
		if (stack->spilled_ptr.parent_id == v_parent_id)
			ref_cnt++;
	}));

	return ref_cnt;
}

static int destroy_if_dynptr_stack_slot(struct bpf_verifier_env *env,
				        struct bpf_func_state *state, int spi)
{
	struct bpf_stack_state *slot = bpf_stack_slot(state, spi);
	int err = 0;

	/* We always ensure that STACK_DYNPTR is never set partially,
	 * hence just checking for slot_type[0] is enough. This is
	 * different for STACK_SPILL, where it may be only set for
	 * 1 byte, so code has to use is_spilled_reg.
	 */
	if (slot->slot_type[0] != STACK_DYNPTR)
		return 0;

	/* Reposition spi to first slot */
	if (!slot->spilled_ptr.dynptr.first_slot) {
		spi = spi + 1;
		slot = bpf_stack_slot(state, spi);
	}

	/*
	 * A referenced dynptr can be overwritten only if there is at
	 * least one other dynptr sharing the same virtual ref parent,
	 * ensuring the reference can still be properly released.
	 */
	if (dynptr_type_referenced(slot->spilled_ptr.dynptr.type) &&
	    dynptr_ref_cnt(env, slot->spilled_ptr.parent_id) <= 1) {
		verbose(env, "cannot overwrite referenced dynptr\n");
		bpf_diag_res(
			env, env->insn_idx, "referenced dynptr overwrite",
			"This stack slot contains a dynptr that owns or protects a referenced resource. Overwriting the last dynptr for that resource would lose the verifier-tracked release path.",
			"Release or clone the dynptr so another live dynptr still tracks the referenced resource before overwriting this stack slot.");
		return -EINVAL;
	}

	/* Invalidate the dynptr and any derived slices */
	err = release_reference(env, slot->spilled_ptr.id);
	if (!err) {
		mark_stack_slot_scratched(env, spi);
		mark_stack_slot_scratched(env, spi - 1);
	}

	return err;
}

static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	int spi;

	if (reg->type == CONST_PTR_TO_DYNPTR)
		return false;

	spi = dynptr_get_spi(env, reg);

	/* -ERANGE (i.e. spi not falling into allocated stack slots) isn't an
	 * error because this just means the stack state hasn't been updated yet.
	 * We will do check_mem_access to check and update stack bounds later.
	 */
	if (spi < 0 && spi != -ERANGE)
		return false;

	/* We don't need to check if the stack slots are marked by previous
	 * dynptr initializations because we allow overwriting existing unreferenced
	 * STACK_DYNPTR slots, see mark_stack_slots_dynptr which calls
	 * destroy_if_dynptr_stack_slot to ensure dynptr objects at the slots we are
	 * touching are completely destructed before we reinitialize them for a new
	 * one. For referenced ones, destroy_if_dynptr_stack_slot returns an error early
	 * instead of delaying it until the end where the user will get "Unreleased
	 * reference" error.
	 */
	return true;
}

static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	struct bpf_stack_state *slot;
	int i, spi;

	/* This already represents first slot of initialized bpf_dynptr.
	 *
	 * CONST_PTR_TO_DYNPTR already has fixed and var_off as 0 due to
	 * check_func_arg_reg_off's logic, so we don't need to check its
	 * offset and alignment.
	 */
	if (reg->type == CONST_PTR_TO_DYNPTR)
		return true;

	spi = dynptr_get_spi(env, reg);
	if (spi < 0)
		return false;
	slot = bpf_stack_slot(state, spi);
	if (!slot->spilled_ptr.dynptr.first_slot)
		return false;

	for (i = 0; i < BPF_REG_SIZE; i++) {
		if (slot->slot_type[i] != STACK_DYNPTR ||
		    bpf_stack_slot(state, spi - 1)->slot_type[i] != STACK_DYNPTR)
			return false;
	}

	return true;
}

static enum bpf_dynptr_type dynptr_reg_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_func_state *state;
	int spi;

	if (reg->type == CONST_PTR_TO_DYNPTR)
		return reg->dynptr.type;

	spi = dynptr_get_spi(env, reg);
	if (spi < 0)
		return BPF_DYNPTR_TYPE_INVALID;
	state = bpf_func(env, reg);
	return bpf_stack_slot(state, spi)->spilled_ptr.dynptr.type;
}

static bool dynptr_write_changes_pkt_data(enum bpf_dynptr_type type)
{
	return type == BPF_DYNPTR_TYPE_SKB || type == BPF_DYNPTR_TYPE_SKB_META;
}

static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				    enum bpf_arg_type arg_type)
{
	/*
	 * ARG_PTR_TO_DYNPTR without a type flag takes any type of dynptr.
	 * Test the flags rather than the whole arg_type, which may carry
	 * unrelated ones such as PTR_MAYBE_NULL.
	 */
	if (!(arg_type & DYNPTR_TYPE_FLAG_MASK))
		return true;

	return dynptr_reg_type(env, reg) == arg_to_dynptr_type(arg_type);
}

static void __mark_reg_known_zero(struct bpf_reg_state *reg);

static bool in_rcu_cs(struct bpf_verifier_env *env);

static bool is_kfunc_rcu_protected(struct bpf_call_arg_meta *meta);

static int mark_stack_slots_iter(struct bpf_verifier_env *env,
				 struct bpf_call_arg_meta *meta,
				 struct bpf_reg_state *reg, int insn_idx,
				 struct btf *btf, u32 btf_id, int nr_slots)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi, i, j, id;

	spi = iter_get_spi(env, reg, nr_slots);
	if (spi < 0)
		return spi;

	id = acquire_reference(env, insn_idx, 0);
	if (id < 0)
		return id;

	for (i = 0; i < nr_slots; i++) {
		struct bpf_stack_state *slot = bpf_stack_slot(state, spi - i);
		struct bpf_reg_state *st = &slot->spilled_ptr;

		__mark_reg_known_zero(st);
		st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
		if (is_kfunc_rcu_protected(meta)) {
			if (in_rcu_cs(env))
				st->type |= MEM_RCU;
			else
				st->type |= PTR_UNTRUSTED;
		}
		st->id = i == 0 ? id : 0;
		st->iter.btf = btf;
		st->iter.btf_id = btf_id;
		st->iter.state = BPF_ITER_STATE_ACTIVE;
		st->iter.depth = 0;

		for (j = 0; j < BPF_REG_SIZE; j++)
			slot->slot_type[j] = STACK_ITER;

		mark_stack_slot_scratched(env, spi - i);
	}

	return 0;
}

static int unmark_stack_slots_iter(struct bpf_verifier_env *env,
				   struct bpf_reg_state *reg, int nr_slots)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi, i, j;

	spi = iter_get_spi(env, reg, nr_slots);
	if (spi < 0)
		return spi;

	for (i = 0; i < nr_slots; i++) {
		struct bpf_stack_state *slot = bpf_stack_slot(state, spi - i);
		struct bpf_reg_state *st = &slot->spilled_ptr;

		if (i == 0)
			WARN_ON_ONCE(release_reference(env, st->id));

		bpf_mark_reg_not_init(env, st);

		for (j = 0; j < BPF_REG_SIZE; j++)
			slot->slot_type[j] = STACK_INVALID;

		mark_stack_slot_scratched(env, spi - i);
	}

	return 0;
}

static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env,
				     struct bpf_reg_state *reg, int nr_slots)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi, i, j;

	/* For -ERANGE (i.e. spi not falling into allocated stack slots), we
	 * will do check_mem_access to check and update stack bounds later, so
	 * return true for that case.
	 */
	spi = iter_get_spi(env, reg, nr_slots);
	if (spi == -ERANGE)
		return true;
	if (spi < 0)
		return false;

	for (i = 0; i < nr_slots; i++) {
		struct bpf_stack_state *slot = bpf_stack_slot(state, spi - i);

		for (j = 0; j < BPF_REG_SIZE; j++)
			if (slot->slot_type[j] == STACK_ITER)
				return false;
	}

	return true;
}

static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				   struct btf *btf, u32 btf_id, int nr_slots)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int spi, i, j;

	spi = iter_get_spi(env, reg, nr_slots);
	if (spi < 0)
		return -EINVAL;

	for (i = 0; i < nr_slots; i++) {
		struct bpf_stack_state *slot = bpf_stack_slot(state, spi - i);
		struct bpf_reg_state *st = &slot->spilled_ptr;

		if (st->type & PTR_UNTRUSTED)
			return -EPROTO;
		/* only main (first) slot has id set */
		if (i == 0 && !st->id)
			return -EINVAL;
		if (i != 0 && st->id)
			return -EINVAL;
		if (st->iter.btf != btf || st->iter.btf_id != btf_id)
			return -EINVAL;

		for (j = 0; j < BPF_REG_SIZE; j++)
			if (slot->slot_type[j] != STACK_ITER)
				return -EINVAL;
	}

	return 0;
}

static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx);
static int release_irq_state(struct bpf_verifier_env *env, int id);

static int mark_stack_slot_irq_flag(struct bpf_verifier_env *env,
				     struct bpf_call_arg_meta *meta,
				     struct bpf_reg_state *reg, int insn_idx,
				     int kfunc_class)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	struct bpf_stack_state *slot;
	struct bpf_reg_state *st;
	int spi, i, id;

	spi = irq_flag_get_spi(env, reg);
	if (spi < 0)
		return spi;

	id = acquire_irq_state(env, insn_idx);
	if (id < 0)
		return id;

	slot = bpf_stack_slot(state, spi);
	st = &slot->spilled_ptr;

	__mark_reg_known_zero(st);
	st->type = PTR_TO_STACK; /* we don't have dedicated reg type */
	st->id = id;
	st->irq.kfunc_class = kfunc_class;

	for (i = 0; i < BPF_REG_SIZE; i++)
		slot->slot_type[i] = STACK_IRQ_FLAG;

	mark_stack_slot_scratched(env, spi);
	return 0;
}

static int unmark_stack_slot_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				      int kfunc_class)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	struct bpf_stack_state *slot;
	struct bpf_reg_state *st;
	int spi, i, err;

	spi = irq_flag_get_spi(env, reg);
	if (spi < 0)
		return spi;

	slot = bpf_stack_slot(state, spi);
	st = &slot->spilled_ptr;

	if (st->irq.kfunc_class != kfunc_class) {
		const char *flag_kfunc = st->irq.kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock";
		const char *used_kfunc = kfunc_class == IRQ_NATIVE_KFUNC ? "native" : "lock";
		const char *reason;

		verbose(env, "irq flag acquired by %s kfuncs cannot be restored with %s kfuncs\n",
			flag_kfunc, used_kfunc);
		reason = bpf_diag_fmt(env,
				      "This IRQ flag was saved by %s IRQ kfuncs, but the restore call "
			"belongs to the %s IRQ kfunc family. Save and restore operations "
			"must use the same family.",
			flag_kfunc, used_kfunc);
		bpf_diag_irq(env, env->insn_idx, "IRQ flag restore mismatch", reason,
			     "Restore the flag with the matching IRQ restore kfunc for the save "
			     "operation that created it.",
			     bpf_diag_irq_depth(env->cur_state));
		return -EINVAL;
	}

	err = release_irq_state(env, st->id);
	WARN_ON_ONCE(err && err != -EACCES);
	if (err) {
		int insn_idx = 0;

		for (int i = 0; i < env->cur_state->acquired_refs; i++) {
			if (env->cur_state->refs[i].id == env->cur_state->active_irq_id) {
				insn_idx = env->cur_state->refs[i].insn_idx;
				break;
			}
		}

		verbose(env, "cannot restore irq state out of order, expected id=%d acquired at insn_idx=%d\n",
			env->cur_state->active_irq_id, insn_idx);
		bpf_diag_irq(env, env->insn_idx, "IRQ flag restore out of order",
			     "IRQ-disabled regions must be restored in last-in, first-out order, "
			     "but this restore does not match the currently active IRQ flag.",
			     "Restore nested IRQ flags in the reverse order they were saved.",
			     bpf_diag_irq_depth(env->cur_state));
		return err;
	}

	bpf_mark_reg_not_init(env, st);

	for (i = 0; i < BPF_REG_SIZE; i++)
		slot->slot_type[i] = STACK_INVALID;

	mark_stack_slot_scratched(env, spi);
	return 0;
}

static bool is_irq_flag_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	struct bpf_stack_state *slot;
	int spi, i;

	/* For -ERANGE (i.e. spi not falling into allocated stack slots), we
	 * will do check_mem_access to check and update stack bounds later, so
	 * return true for that case.
	 */
	spi = irq_flag_get_spi(env, reg);
	if (spi == -ERANGE)
		return true;
	if (spi < 0)
		return false;

	slot = bpf_stack_slot(state, spi);

	for (i = 0; i < BPF_REG_SIZE; i++)
		if (slot->slot_type[i] == STACK_IRQ_FLAG)
			return false;
	return true;
}

static int is_irq_flag_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	struct bpf_stack_state *slot;
	struct bpf_reg_state *st;
	int spi, i;

	spi = irq_flag_get_spi(env, reg);
	if (spi < 0)
		return -EINVAL;

	slot = bpf_stack_slot(state, spi);
	st = &slot->spilled_ptr;

	if (!st->id)
		return -EINVAL;

	for (i = 0; i < BPF_REG_SIZE; i++)
		if (slot->slot_type[i] != STACK_IRQ_FLAG)
			return -EINVAL;
	return 0;
}

/* Check if given stack slot is "special":
 *   - spilled register state (STACK_SPILL);
 *   - dynptr state (STACK_DYNPTR);
 *   - iter state (STACK_ITER).
 *   - irq flag state (STACK_IRQ_FLAG)
 */
static bool is_stack_slot_special(const struct bpf_stack_state *stack)
{
	enum bpf_stack_slot_type type = stack->slot_type[BPF_REG_SIZE - 1];

	switch (type) {
	case STACK_SPILL:
	case STACK_DYNPTR:
	case STACK_ITER:
	case STACK_IRQ_FLAG:
		return true;
	case STACK_INVALID:
	case STACK_POISON:
	case STACK_MISC:
	case STACK_ZERO:
		return false;
	default:
		WARN_ONCE(1, "unknown stack slot type %d\n", type);
		return true;
	}
}

/* The reg state of a pointer or a bounded scalar was saved when
 * it was spilled to the stack.
 */

/*
 * Mark stack slot as STACK_MISC, unless it is already:
 * - STACK_INVALID, in which case they are equivalent.
 * - STACK_ZERO, in which case we preserve more precise STACK_ZERO.
 * - STACK_POISON, which truly forbids access to the slot.
 * Regardless of allow_ptr_leaks setting (i.e., privileged or unprivileged
 * mode), we won't promote STACK_INVALID to STACK_MISC. In privileged case it is
 * unnecessary as both are considered equivalent when loading data and pruning,
 * in case of unprivileged mode it will be incorrect to allow reads of invalid
 * slots.
 */
static void mark_stack_slot_misc(struct bpf_verifier_env *env, u8 *stype)
{
	if (*stype == STACK_ZERO)
		return;
	if (*stype == STACK_INVALID || *stype == STACK_POISON)
		return;
	*stype = STACK_MISC;
}

static void scrub_spilled_slot(u8 *stype)
{
	if (*stype != STACK_INVALID && *stype != STACK_POISON)
		*stype = STACK_MISC;
}

/* copy array src of length n * size bytes to dst. dst is reallocated if it's too
 * small to hold src. This is different from krealloc since we don't want to preserve
 * the contents of dst.
 *
 * Leaves dst untouched if src is NULL or length is zero. Returns NULL if memory could
 * not be allocated.
 */
static void *copy_array(void *dst, const void *src, size_t n, size_t size, gfp_t flags)
{
	size_t alloc_bytes;
	void *orig = dst;
	size_t bytes;

	if (ZERO_OR_NULL_PTR(src))
		goto out;

	if (unlikely(check_mul_overflow(n, size, &bytes)))
		return NULL;

	alloc_bytes = max(ksize(orig), kmalloc_size_roundup(bytes));
	dst = krealloc(orig, alloc_bytes, flags);
	if (!dst) {
		kfree(orig);
		return NULL;
	}

	memcpy(dst, src, bytes);
out:
	return dst ? dst : ZERO_SIZE_PTR;
}

/* resize an array from old_n items to new_n items. the array is reallocated if it's too
 * small to hold new_n items. new items are zeroed out if the array grows.
 *
 * Contrary to krealloc_array, does not free arr if new_n is zero.
 */
static void *realloc_array(void *arr, size_t old_n, size_t new_n, size_t size)
{
	size_t alloc_size;
	void *new_arr;

	if (!new_n || old_n == new_n)
		goto out;

	alloc_size = kmalloc_size_roundup(size_mul(new_n, size));
	new_arr = krealloc(arr, alloc_size, GFP_KERNEL_ACCOUNT);
	if (!new_arr) {
		kfree(arr);
		return NULL;
	}
	arr = new_arr;

	if (new_n > old_n)
		memset(arr + old_n * size, 0, (new_n - old_n) * size);

out:
	return arr ? arr : ZERO_SIZE_PTR;
}

static int copy_reference_state(struct bpf_verifier_state *dst, const struct bpf_verifier_state *src)
{
	dst->refs = copy_array(dst->refs, src->refs, src->acquired_refs,
			       sizeof(struct bpf_reference_state), GFP_KERNEL_ACCOUNT);
	if (!dst->refs)
		return -ENOMEM;

	dst->acquired_refs = src->acquired_refs;
	dst->active_locks = src->active_locks;
	dst->active_preempt_locks = src->active_preempt_locks;
	dst->active_rcu_locks = src->active_rcu_locks;
	dst->active_irq_id = src->active_irq_id;
	dst->active_lock_id = src->active_lock_id;
	dst->active_lock_ptr = src->active_lock_ptr;
	return 0;
}

static int copy_stack_state(struct bpf_func_state *dst, const struct bpf_func_state *src)
{
	size_t n = bpf_stack_nr_slots(src);

	dst->stack = copy_array(dst->stack, src->stack, n, sizeof(struct bpf_stack_state),
				GFP_KERNEL_ACCOUNT);
	if (!dst->stack)
		return -ENOMEM;

	dst->allocated_stack = src->allocated_stack;

	/* copy stack args state */
	n = src->out_stack_arg_cnt;
	if (n) {
		dst->stack_arg_regs = copy_array(dst->stack_arg_regs, src->stack_arg_regs, n,
						 sizeof(struct bpf_reg_state),
						 GFP_KERNEL_ACCOUNT);
		if (!dst->stack_arg_regs)
			return -ENOMEM;
	}

	dst->out_stack_arg_cnt = src->out_stack_arg_cnt;
	return 0;
}

static int resize_reference_state(struct bpf_verifier_state *state, size_t n)
{
	state->refs = realloc_array(state->refs, state->acquired_refs, n,
				    sizeof(struct bpf_reference_state));
	if (!state->refs)
		return -ENOMEM;

	state->acquired_refs = n;
	return 0;
}

/* Possibly update state->allocated_stack to be at least size bytes. Also
 * possibly update the function's high-water mark in its bpf_subprog_info.
 */
int bpf_grow_stack_state(struct bpf_verifier_env *env, struct bpf_func_state *state, int size)
{
	size_t old_n = bpf_stack_nr_slots(state), n;

	/* The stack size is always a multiple of BPF_REG_SIZE. */
	size = round_up(size, BPF_REG_SIZE);
	n = size / BPF_REG_SIZE;

	if (old_n >= n)
		return 0;

	state->stack = realloc_array(state->stack, old_n, n, sizeof(struct bpf_stack_state));
	if (!state->stack)
		return -ENOMEM;

	state->allocated_stack = size;

	/* update known max for given subprogram */
	if (env->subprog_info[state->subprogno].stack_depth < size)
		env->subprog_info[state->subprogno].stack_depth = size;

	return 0;
}

static int grow_stack_arg_slots(struct bpf_verifier_env *env,
				struct bpf_func_state *state, int cnt)
{
	size_t old_n = state->out_stack_arg_cnt;

	if (old_n >= cnt)
		return 0;

	state->stack_arg_regs = realloc_array(state->stack_arg_regs, old_n, cnt,
					      sizeof(struct bpf_reg_state));
	if (!state->stack_arg_regs)
		return -ENOMEM;

	state->out_stack_arg_cnt = cnt;
	return 0;
}

/* Acquire a pointer id from the env and update the state->refs to include
 * this new pointer reference.
 * On success, returns a valid pointer id to associate with the register
 * On failure, returns a negative errno.
 */
static struct bpf_reference_state *acquire_reference_state(struct bpf_verifier_env *env, int insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state;
	int new_ofs = state->acquired_refs;
	int err;

	err = resize_reference_state(state, state->acquired_refs + 1);
	if (err)
		return NULL;
	state->refs[new_ofs].insn_idx = insn_idx;

	return &state->refs[new_ofs];
}

static int acquire_reference(struct bpf_verifier_env *env, int insn_idx, int parent_id)
{
	struct bpf_reference_state *s;

	s = acquire_reference_state(env, insn_idx);
	if (!s)
		return -ENOMEM;
	s->type = REF_TYPE_PTR;
	s->id = ++env->id_gen;
	s->parent_id = parent_id;
	bpf_diag_record_ref_acquire(env, insn_idx, s->id);
	return s->id;
}

static int acquire_lock_state(struct bpf_verifier_env *env, int insn_idx, enum ref_state_type type,
			      int id, void *ptr)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_reference_state *s;

	s = acquire_reference_state(env, insn_idx);
	if (!s)
		return -ENOMEM;
	s->type = type;
	s->id = id;
	s->ptr = ptr;

	state->active_locks++;
	state->active_lock_id = id;
	state->active_lock_ptr = ptr;
	bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_LOCK, true,
				state->active_locks);
	return 0;
}

static int acquire_irq_state(struct bpf_verifier_env *env, int insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_reference_state *s;

	s = acquire_reference_state(env, insn_idx);
	if (!s)
		return -ENOMEM;
	s->type = REF_TYPE_IRQ;
	s->id = ++env->id_gen;

	state->active_irq_id = s->id;
	bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_IRQ, true,
				bpf_diag_irq_depth(state));
	return s->id;
}

static void release_reference_state(struct bpf_verifier_state *state, int idx)
{
	int last_idx;
	size_t rem;

	/* IRQ state requires the relative ordering of elements remaining the
	 * same, since it relies on the refs array to behave as a stack, so that
	 * it can detect out-of-order IRQ restore. Hence use memmove to shift
	 * the array instead of swapping the final element into the deleted idx.
	 */
	last_idx = state->acquired_refs - 1;
	rem = state->acquired_refs - idx - 1;
	if (last_idx && idx != last_idx)
		memmove(&state->refs[idx], &state->refs[idx + 1], sizeof(*state->refs) * rem);
	memset(&state->refs[last_idx], 0, sizeof(*state->refs));
	state->acquired_refs--;
	return;
}

static bool find_reference_state(struct bpf_verifier_state *state, int id)
{
	int i;

	for (i = 0; i < state->acquired_refs; i++) {
		if (state->refs[i].type != REF_TYPE_PTR)
			continue;
		if (state->refs[i].id == id)
			return true;
	}

	return false;
}

static bool reg_is_referenced(struct bpf_verifier_env *env, const struct bpf_reg_state *reg)
{
	return find_reference_state(env->cur_state, reg->id);
}

static int release_lock_state(struct bpf_verifier_env *env, int type, int id, void *ptr)
{
	struct bpf_verifier_state *state = env->cur_state;
	void *prev_ptr = NULL;
	u32 prev_id = 0;
	int i;

	for (i = 0; i < state->acquired_refs; i++) {
		if (state->refs[i].type == type && state->refs[i].id == id &&
		    state->refs[i].ptr == ptr) {
			release_reference_state(state, i);
			state->active_locks--;
			/* Reassign active lock (id, ptr). */
			state->active_lock_id = prev_id;
			state->active_lock_ptr = prev_ptr;
			bpf_diag_record_context(env, env->insn_idx, BPF_DIAG_CONTEXT_LOCK,
						false, state->active_locks);
			return 0;
		}
		if (state->refs[i].type & REF_TYPE_LOCK_MASK) {
			prev_id = state->refs[i].id;
			prev_ptr = state->refs[i].ptr;
		}
	}
	return -EINVAL;
}

static int release_irq_state(struct bpf_verifier_env *env, int id)
{
	struct bpf_verifier_state *state = env->cur_state;
	u32 prev_id = 0;
	int i;

	if (id != state->active_irq_id)
		return -EACCES;

	for (i = 0; i < state->acquired_refs; i++) {
		if (state->refs[i].type != REF_TYPE_IRQ)
			continue;
		if (state->refs[i].id == id) {
			release_reference_state(state, i);
			state->active_irq_id = prev_id;
			bpf_diag_record_context(env, env->insn_idx, BPF_DIAG_CONTEXT_IRQ,
						false, bpf_diag_irq_depth(state));
			return 0;
		} else {
			prev_id = state->refs[i].id;
		}
	}
	return -EINVAL;
}

static struct bpf_reference_state *find_lock_state(struct bpf_verifier_state *state, enum ref_state_type type,
						   int id, void *ptr)
{
	int i;

	for (i = 0; i < state->acquired_refs; i++) {
		struct bpf_reference_state *s = &state->refs[i];

		if (!(s->type & type))
			continue;

		if (s->id == id && s->ptr == ptr)
			return s;
	}
	return NULL;
}

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

void bpf_clear_jmp_history(struct bpf_verifier_state *state)
{
	kfree(state->jmp_history);
	state->jmp_history = NULL;
	state->jmp_history_cnt = 0;
}

void bpf_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;
	}
	kfree(state->refs);
	bpf_clear_jmp_history(state);
	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)
{
	memcpy(dst, src, offsetof(struct bpf_func_state, stack));
	/* Instruction accounting is path-local, not part of verifier state. */
	dst->insns_subtotal = 0;
	dst->loop_stack = copy_array(dst->loop_stack, src->loop_stack, src->loop_stack_cnt,
				     sizeof(*src->loop_stack), GFP_KERNEL_ACCOUNT);
	if (!dst->loop_stack)
		return -ENOMEM;
	return copy_stack_state(dst, src);
}

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

	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
					  src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
					  GFP_KERNEL_ACCOUNT);
	if (!dst_state->jmp_history)
		return -ENOMEM;
	dst_state->jmp_history_cnt = src->jmp_history_cnt;

	/* if dst has more stack frames then src frame, free them, this is also
	 * necessary in case of exceptional exits using bpf_throw.
	 */
	for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
		free_func_state(dst_state->frame[i]);
		dst_state->frame[i] = NULL;
	}
	err = copy_reference_state(dst_state, src);
	if (err)
		return err;
	dst_state->speculative = src->speculative;
	dst_state->in_sleepable = src->in_sleepable;
	dst_state->unwound = src->unwound;
	dst_state->curframe = src->curframe;
	dst_state->branches = src->branches;
	dst_state->parent = src->parent;
	dst_state->first_insn_idx = src->first_insn_idx;
	dst_state->last_insn_idx = src->last_insn_idx;
	dst_state->dfs_depth = src->dfs_depth;
	dst_state->callback_unroll_depth = src->callback_unroll_depth;
	dst_state->may_goto_depth = src->may_goto_depth;
	dst_state->equal_state = src->equal_state;
	for (i = 0; i <= src->curframe; i++) {
		dst = dst_state->frame[i];
		if (!dst) {
			dst = kzalloc_obj(*dst, GFP_KERNEL_ACCOUNT);
			if (!dst)
				return -ENOMEM;
			dst_state->frame[i] = dst;
		}
		err = copy_func_state(dst, src->frame[i]);
		if (err)
			return err;
	}
	return 0;
}

static u32 state_htab_size(struct bpf_verifier_env *env)
{
	return env->prog->len;
}

struct list_head *bpf_explored_state(struct bpf_verifier_env *env, int idx)
{
	struct bpf_verifier_state *cur = env->cur_state;
	struct bpf_func_state *state = cur->frame[cur->curframe];

	return &env->explored_states[(idx ^ state->callsite) % state_htab_size(env)];
}

static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_state *b)
{
	int fr;

	if (a->curframe != b->curframe)
		return false;

	for (fr = a->curframe; fr >= 0; fr--)
		if (a->frame[fr]->callsite != b->frame[fr]->callsite)
			return false;

	return true;
}

void bpf_free_backedges(struct bpf_scc_visit *visit)
{
	struct bpf_scc_backedge *backedge, *next;

	for (backedge = visit->backedges; backedge; backedge = next) {
		bpf_free_verifier_state(&backedge->state, false);
		next = backedge->next;
		kfree(backedge);
	}
	visit->backedges = NULL;
}

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

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

	if (cur) {
		err = bpf_copy_verifier_state(cur, &head->st);
		if (err)
			return err;
		bpf_diag_event_log_restore(env, head->diag_log_pos);
	}
	if (pop_log)
		bpf_vlog_reset(&env->log, head->log_pos);
	if (insn_idx)
		*insn_idx = head->insn_idx;
	if (prev_insn_idx)
		*prev_insn_idx = head->prev_insn_idx;
	elem = head->next;
	bpf_free_verifier_state(&head->st, false);
	kfree(head);
	env->head = elem;
	env->stack_size--;
	return 0;
}

static bool error_recoverable_with_nospec(int err)
{
	/* Should only return true for non-fatal errors that are allowed to
	 * occur during speculative verification. For these we can insert a
	 * nospec and the program might still be accepted. Do not include
	 * something like ENOMEM because it is likely to re-occur for the next
	 * architectural path once it has been recovered-from in all speculative
	 * paths.
	 */
	return err == -EPERM || err == -EACCES || err == -EINVAL;
}

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

	elem = kzalloc_obj(struct bpf_verifier_stack_elem, GFP_KERNEL_ACCOUNT);
	if (!elem)
		return ERR_PTR(-ENOMEM);

	elem->insn_idx = insn_idx;
	elem->prev_insn_idx = prev_insn_idx;
	elem->next = env->head;
	elem->log_pos = env->log.end_pos;
	elem->diag_log_pos = bpf_diag_event_log_save(env);
	env->head = elem;
	env->stack_size++;
	err = bpf_copy_verifier_state(&elem->st, cur);
	if (err)
		return ERR_PTR(-ENOMEM);
	elem->st.speculative |= speculative;
	if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
		verbose(env, "The sequence of %d jumps is too complex.\n",
			env->stack_size);
		return ERR_PTR(-E2BIG);
	}
	if (elem->st.parent) {
		++elem->st.parent->branches;
		/* WARN_ON(branches > 2) technically makes sense here,
		 * but
		 * 1. speculative states will bump 'branches' for non-branch
		 * instructions
		 * 2. is_state_visited() heuristics may decide not to create
		 * a new state for a sequence of branches and all such current
		 * and cloned states will be pointing to a single parent state
		 * which might have large 'branches' count.
		 */
	}
	return &elem->st;
}

static const char *reg_arg_name(struct bpf_verifier_env *env, argno_t argno)
{
	char *buf = env->tmp_arg_name;
	int len = sizeof(env->tmp_arg_name);
	int arg, regno = reg_from_argno(argno);

	if (regno >= 0) {
		snprintf(buf, len, "R%d", regno);
	} else {
		arg = arg_from_argno(argno);
		snprintf(buf, len, "*(R11-%u)", (arg - MAX_BPF_FUNC_REG_ARGS) * BPF_REG_SIZE);
	}

	return buf;
}

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 bpf_diag_record_caller_saved(struct bpf_verifier_env *env,
					 struct bpf_reg_state *regs)
{
	int i;

	for (i = 1; i < CALLER_SAVED_REGS; i++) {
		bpf_diag_record_scrub(env, &regs[caller_saved[i]],
				      BPF_DIAG_MOD_CALLER_SAVED);
	}
}

static void reg_step_reset(struct bpf_reg_state *reg)
{
	reg->base = 0;
	reg->step = 1;
}

static void scalar_step_add(struct bpf_reg_state *dst_reg,
			    const struct bpf_reg_state *a,
			    const struct bpf_reg_state *b)
{
	const struct bpf_reg_state *reg;
	s64 amount, tmp;

	if (tnum_is_const(b->var_off)) {
		reg = a;
		amount = (s64)b->var_off.value;
	} else if (tnum_is_const(a->var_off)) {
		reg = b;
		amount = (s64)a->var_off.value;
	} else {
		reg_step_reset(dst_reg);
		return;
	}

	/*
	 * Let x be a possible signed value of the register,
	 * d = amount, s = reg->step, and b = reg->base.
	 * Then x mod s = b, with s > 0 and 0 <= b < s.
	 * If the addition causes signed underflow, the resulting value
	 * is x + d + 2**64.
	 *
	 * Taking the result modulo s and substituting x mod s = b gives:
	 *   (x + d + 2**64) mod s = (b + d + (2**64 mod s)) mod s      (1)
	 * Keeping reg->step = s and updating reg->base to (b + d) mod s
	 * requires (1) to equal (b + d) mod s, which holds if and only
	 * if 2**64 mod s = 0.
	 * Signed overflow subtracts 2**64 and has the same requirement.
	 *
	 * Conservatively reset the stride if either wrap is possible.
	 */
	if (check_add_overflow(reg_smin(reg), amount, &tmp) ||
	    check_add_overflow(reg_smax(reg), amount, &tmp)) {
		reg_step_reset(dst_reg);
		return;
	}

	dst_reg->base = (reg->base + imod(amount, reg->step)) % reg->step;
	dst_reg->step = reg->step;
}

static void scalar_step_scale(struct bpf_reg_state *dst_reg, u64 amount)
{
	u16 step;
	s64 tmp;

	/*
	 * Using the same notation as scalar_step_add(), with d > 0,
	 * the scaled value satisfies (x * d) mod (s * d) = b * d.
	 * If the multiplication wraps, its signed result can be represented
	 * as x * d - n * 2**64 for some nonzero integer n.
	 *
	 * Taking the result modulo s * d gives:
	 *   (x * d - n * 2**64) mod (s * d) =
	 *   (b * d - (n * 2**64 mod (s * d))) mod (s * d)              (1)
	 * Updating dst_reg->base to b * d and dst_reg->step to s * d
	 * requires (1) to equal b * d, which holds if and only if
	 * n * 2**64 mod (s * d) = 0.
	 *
	 * Conservatively reset the stride if a wrap is possible.
	 */
	if (amount == 0 || check_mul_overflow(dst_reg->step, amount, &step) ||
	    check_mul_overflow(reg_smin(dst_reg), (s64)amount, &tmp) ||
	    check_mul_overflow(reg_smax(dst_reg), (s64)amount, &tmp)) {
		reg_step_reset(dst_reg);
		return;
	}
	/*
	 * The above established that `step = dst_reg->step * amount`
	 * does not overflow, therefore the base < step invariant holds
	 * after assignments below.
	 */
	dst_reg->base = dst_reg->base * amount;
	dst_reg->step = step;
}

/*
 * Let x be a possible signed value of the register,
 * s = reg->step, and b = reg->base.
 * Then x mod s = b, with s > 0 and 0 <= b < s.
 * Truncating to N bits and then zero- or sign-extending x
 * is equivalent to computing x + k * 2**N for some integer k.
 * For example, sign-extending the low 8 bits of x = 255 can
 * be expressed as 255 - 2**8 = -1.
 *
 * Taking the result modulo s and substituting x mod s = b gives:
 *   (x + k * 2**N) mod s = (b + (k * 2**N mod s)) mod s
 * Keeping reg->base = b and reg->step = s requires this to equal b,
 * which holds if and only if k * 2**N mod s = 0.
 * Continuing the example with s = 3 and b = 0, we have 255 mod 3 = 0,
 * but (-1) mod 3 = 2, so the original base and step no longer hold.
 *
 * Conservatively reset the stride unless all possible values fit in
 * the range where the conversion leaves them unchanged.
 * Call before updating the register's bounds. Requires 0 < bits < 64.
 */
static void reg_step_check_unsigned(struct bpf_reg_state *reg, u32 bits)
{
	if (reg_umax(reg) >= (1ULL << bits))
		reg_step_reset(reg);
}

/* This helper doesn't clear reg->id */
static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm)
{
	reg->var_off = tnum_const(imm);
	reg->r64 = cnum64_from_urange(imm, imm);
	reg->r32 = cnum32_from_urange((u32)imm, (u32)imm);
	reg_step_reset(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)
{
	/* Clear off and union(map_ptr, range) */
	memset(((u8 *)reg) + sizeof(reg->type), 0,
	       offsetof(struct bpf_reg_state, var_off) - sizeof(reg->type));
	reg->id = 0;
	reg->parent_id = 0;
	reg->map_uid = 0;
	___mark_reg_known(reg, imm);
}

void bpf_mark_reg_known_scalar(struct bpf_reg_state *reg, u64 imm)
{
	__mark_reg_known(reg, imm);
	reg->type = SCALAR_VALUE;
}

static void __mark_reg32_known(struct bpf_reg_state *reg, u64 imm)
{
	reg->var_off = tnum_const_subreg(reg->var_off, imm);
	reg->r32 = cnum32_from_urange((u32)imm, (u32)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(const struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	__mark_reg_known(reg, 0);
	reg->type = SCALAR_VALUE;
	/* all scalars are assumed imprecise initially (unless unprivileged,
	 * in which case everything is forced to be precise)
	 */
	reg->precise = !env->bpf_capable;
}

static void mark_reg_known_zero(struct bpf_verifier_env *env,
				struct bpf_reg_state *regs, u32 regno)
{
	__mark_reg_known_zero(regs + regno);
}

static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type,
			      bool first_slot, int id, int parent_id)
{
	/* reg->type has no meaning for STACK_DYNPTR, but when we set reg for
	 * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply
	 * set it unconditionally as it is ignored for STACK_DYNPTR anyway.
	 */
	__mark_reg_known_zero(reg);
	reg->type = CONST_PTR_TO_DYNPTR;
	/* Give each dynptr a unique id to uniquely associate slices to it. */
	reg->id = id;
	reg->parent_id = parent_id;
	reg->dynptr.type = type;
	reg->dynptr.first_slot = first_slot;
}

/*
 * Refine the return type of the bpf_map_lookup_elem() for special map types:
 * map-in-map, xskmap, sockmap and sockhash.
 */
static void refine_map_lookup_value(struct bpf_reg_state *reg)
{
	enum bpf_type_flag maybe_null = reg->type & PTR_MAYBE_NULL;
	const struct bpf_map *map = reg->map_ptr;

	if (map->inner_map_meta) {
		reg->type = CONST_PTR_TO_MAP | maybe_null;
		reg->map_ptr = map->inner_map_meta;
		/*
		 * transfer reg's id which is unique for every map_lookup_elem
		 * as UID of the inner map.
		 */
		reg->map_uid = reg->id;
	} else if (map->map_type == BPF_MAP_TYPE_XSKMAP) {
		reg->type = PTR_TO_XDP_SOCK | maybe_null;
		reg->map_uid = 0;
	} else if (map->map_type == BPF_MAP_TYPE_SOCKMAP ||
		   map->map_type == BPF_MAP_TYPE_SOCKHASH) {
		reg->type = PTR_TO_SOCKET | maybe_null;
		reg->map_uid = 0;
	}
}

static void mark_ptr_not_null_reg(struct bpf_reg_state *reg)
{
	reg->type &= ~PTR_MAYBE_NULL;
}

static void mark_reg_graph_node(struct bpf_reg_state *regs, u32 regno,
				struct btf_field_graph_root *ds_head)
{
	__mark_reg_known(&regs[regno], ds_head->node_offset);
	regs[regno].type = PTR_TO_BTF_ID | MEM_ALLOC;
	regs[regno].btf = ds_head->btf;
	regs[regno].btf_id = ds_head->value_btf_id;
}

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;
}

static bool reg_is_dynptr_slice_pkt(const struct bpf_reg_state *reg)
{
	return base_type(reg->type) == PTR_TO_MEM &&
	       (reg->type &
		(DYNPTR_TYPE_SKB | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META));
}

/* 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 &&
	       tnum_equals_const(reg->var_off, 0);
}

static void __mark_reg32_unbounded(struct bpf_reg_state *reg)
{
	reg->r32 = CNUM32_UNBOUNDED;
}

static void __mark_reg64_unbounded(struct bpf_reg_state *reg)
{
	reg->r64 = CNUM64_UNBOUNDED;
}

/* Reset the min/max bounds of a register */
static void __mark_reg_unbounded(struct bpf_reg_state *reg)
{
	__mark_reg64_unbounded(reg);
	__mark_reg32_unbounded(reg);
}

static void reset_reg64_and_tnum(struct bpf_reg_state *reg)
{
	__mark_reg64_unbounded(reg);
	reg->var_off = tnum_unknown;
}

static void reset_reg32_and_tnum(struct bpf_reg_state *reg)
{
	__mark_reg32_unbounded(reg);
	reg->var_off = tnum_unknown;
}

static struct cnum32 cnum32_from_tnum(struct tnum tnum)
{
	tnum = tnum_subreg(tnum);
	if ((tnum.mask & S32_MIN) || (tnum.value & S32_MIN))
		/* min signed is max(sign bit) | min(other bits) */
		/* max signed is min(sign bit) | max(other bits) */
		return cnum32_from_srange(tnum.value | (tnum.mask & S32_MIN),
					  tnum.value | (tnum.mask & S32_MAX));
	else
		return cnum32_from_urange(tnum.value, (tnum.value | tnum.mask));
}

static struct cnum64 cnum64_from_tnum(struct tnum tnum)
{
	if ((tnum.mask & S64_MIN) || (tnum.value & S64_MIN))
		/* min signed is max(sign bit) | min(other bits) */
		/* max signed is min(sign bit) | max(other bits) */
		return cnum64_from_srange(tnum.value | (tnum.mask & S64_MIN),
					  tnum.value | (tnum.mask & S64_MAX));
	else
		return cnum64_from_urange(tnum.value, (tnum.value | tnum.mask));
}

static void __update_reg32_bounds(struct bpf_reg_state *reg)
{
	cnum32_intersect_with(&reg->r32, cnum32_from_tnum(reg->var_off));
}

static void __update_reg64_bounds(struct bpf_reg_state *reg)
{
	u64 tnum_next, tmax;
	bool umin_in_tnum;

	cnum64_intersect_with(&reg->r64, cnum64_from_tnum(reg->var_off));

	/* Check if u64 and tnum overlap in a single value */
	tnum_next = tnum_step(reg->var_off, reg_umin(reg));
	umin_in_tnum = (reg_umin(reg) & ~reg->var_off.mask) == reg->var_off.value;
	tmax = reg->var_off.value | reg->var_off.mask;
	if (umin_in_tnum && tnum_next > reg_umax(reg)) {
		/* The u64 range and the tnum only overlap in umin.
		 * u64:  ---[xxxxxx]-----
		 * tnum: --xx----------x-
		 */
		___mark_reg_known(reg, reg_umin(reg));
	} else if (!umin_in_tnum && tnum_next == tmax) {
		/* The u64 range and the tnum only overlap in the maximum value
		 * represented by the tnum, called tmax.
		 * u64:  ---[xxxxxx]-----
		 * tnum: xx-----x--------
		 */
		___mark_reg_known(reg, tmax);
	} else if (!umin_in_tnum && tnum_next <= reg_umax(reg) &&
		   tnum_step(reg->var_off, tnum_next) > reg_umax(reg)) {
		/* The u64 range and the tnum only overlap in between umin
		 * (excluded) and umax.
		 * u64:  ---[xxxxxx]-----
		 * tnum: xx----x-------x-
		 */
		___mark_reg_known(reg, tnum_next);
	}
}

static void __update_reg_bounds(struct bpf_reg_state *reg)
{
	__update_reg32_bounds(reg);
	__update_reg64_bounds(reg);
}

static void deduce_bounds_32_from_64(struct bpf_reg_state *reg)
{
	cnum32_intersect_with(&reg->r32, cnum32_from_cnum64(reg->r64));
}

static void deduce_bounds_64_from_32(struct bpf_reg_state *reg)
{
	reg->r64 = cnum64_cnum32_intersect(reg->r64, reg->r32);
}

static void __reg_deduce_bounds(struct bpf_reg_state *reg)
{
	deduce_bounds_32_from_64(reg);
	deduce_bounds_64_from_32(reg);
}

/* Attempts to improve var_off based on unsigned min/max information */
static void __reg_bound_offset(struct bpf_reg_state *reg)
{
	struct tnum var64_off = tnum_intersect(reg->var_off,
					       tnum_range(reg_umin(reg),
							  reg_umax(reg)));
	struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off),
					       tnum_range(reg_u32_min(reg),
							  reg_u32_max(reg)));
	u32 trailing_zero_bits;
	u16 base = reg->base;
	u16 step = reg->step;

	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);

	if (base == 0)
		trailing_zero_bits = count_trailing_zeros(step);
	else
		trailing_zero_bits = min(count_trailing_zeros(base),
					 count_trailing_zeros(step));
	reg->var_off = tnum_and(reg->var_off, tnum_const(~0ULL << trailing_zero_bits));
}

static void __update_bounds_from_step(struct bpf_reg_state *reg)
{
	reg->r64 = cnum64_intersect_linear(reg->r64, reg->base, reg->step);
	deduce_bounds_32_from_64(reg);
}

static bool range_bounds_violation(struct bpf_reg_state *reg);

static void reg_bounds_sync(struct bpf_reg_state *reg)
{
	/* If the input reg_state is invalid, we can exit early */
	if (range_bounds_violation(reg))
		return;
	/* We might have learned new bounds from the var_off. */
	__update_reg_bounds(reg);
	/* We might have learned something about the sign bit. */
	__reg_deduce_bounds(reg);
	__reg_deduce_bounds(reg);
	/* We might have learned some bits from the bounds. */
	__reg_bound_offset(reg);
	/* Intersecting with the old var_off might have improved our bounds
	 * slightly, e.g. if umax was 0x7f...f and var_off was (0; 0xf...fc),
	 * then new var_off is (0; 0x7f...fc) which improves our umax.
	 */
	__update_reg_bounds(reg);
	/*
	 * Both tnum and base+step define a sequence of points,
	 * potentially w/o intersection, or intersecting after N
	 * tnum_step()'s, where N can be large. On the other hand,
	 * step+base *must* be in sync with r64 in order for
	 * array traversal logic starting at reg_smin() to be sound.
	 * Hence, place this as a final step in the reg_bounds_sync().
	 */
	__update_bounds_from_step(reg);
}

static bool const_tnum_range_mismatch(struct bpf_reg_state *reg)
{
	if (!tnum_is_const(reg->var_off))
		return false;

	return !cnum64_is_const(reg->r64) || reg->r64.base != reg->var_off.value;
}

static bool const_tnum_range_mismatch_32(struct bpf_reg_state *reg)
{
	if (!tnum_subreg_is_const(reg->var_off))
		return false;

	return !cnum32_is_const(reg->r32) || reg->r32.base != tnum_subreg(reg->var_off).value;
}

static bool range_bounds_violation(struct bpf_reg_state *reg)
{
	return cnum32_is_empty(reg->r32) || cnum64_is_empty(reg->r64);
}

static int reg_bounds_sanity_check(struct bpf_verifier_env *env,
				   struct bpf_reg_state *reg, const char *ctx)
{
	const char *msg;

	if (range_bounds_violation(reg)) {
		msg = "range bounds violation";
		goto out;
	}

	if (const_tnum_range_mismatch(reg)) {
		msg = "const tnum out of sync with range bounds";
		goto out;
	}

	if (const_tnum_range_mismatch_32(reg)) {
		msg = "const subreg tnum out of sync with range bounds";
		goto out;
	}

	if (reg->step == 0 || reg->base >= reg->step) {
		msg = "invalid base/step";
		goto out;
	}

	return 0;
out:
	verifier_bug(env, "REG INVARIANTS VIOLATION (%s): %s r64={.base=%#llx, .size=%#llx} "
		     "r32={.base=%#x, .size=%#x} var_off=(%#llx, %#llx) step=%u+%u",
		     ctx, msg,
		     reg->r64.base, reg->r64.size,
		     reg->r32.base, reg->r32.size,
		     reg->var_off.value, reg->var_off.mask,
		     reg->base, reg->step);
	if (env->test_reg_invariants)
		return -EFAULT;
	__mark_reg_unbounded(reg);
	reg_step_reset(reg);
	return 0;
}

/* Mark a register as having a completely unknown (scalar) value. */
void bpf_mark_reg_unknown_imprecise(struct bpf_reg_state *reg)
{
	memset(reg, 0, sizeof(*reg));
	reg->type = SCALAR_VALUE;
	reg->var_off = tnum_unknown;
	__mark_reg_unbounded(reg);
	reg_step_reset(reg);
}

/* Mark a register as having a completely unknown (scalar) value,
 * initialize .precise as true when not bpf capable.
 */
static void __mark_reg_unknown(const struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg)
{
	bpf_mark_reg_unknown_imprecise(reg);
	reg->precise = !env->bpf_capable;
}

static void mark_reg_unknown(struct bpf_verifier_env *env,
			     struct bpf_reg_state *regs, u32 regno)
{
	__mark_reg_unknown(env, regs + regno);
}

static int __mark_reg_s32_range(struct bpf_verifier_env *env,
				struct bpf_reg_state *regs,
				u32 regno,
				s32 s32_min,
				s32 s32_max)
{
	struct bpf_reg_state *reg = regs + regno;

	reg_set_srange32(reg,
			 max_t(s32, reg_s32_min(reg), s32_min),
			 min_t(s32, reg_s32_max(reg), s32_max));
	reg_set_srange64(reg,
			 max_t(s64, reg_smin(reg), s32_min),
			 min_t(s64, reg_smax(reg), s32_max));

	reg_bounds_sync(reg);

	return reg_bounds_sanity_check(env, reg, "s32_range");
}

void bpf_mark_reg_not_init(const struct bpf_verifier_env *env,
			   struct bpf_reg_state *reg)
{
	__mark_reg_unknown(env, reg);
	reg->type = NOT_INIT;
}

static int mark_btf_ld_reg(struct bpf_verifier_env *env,
			   struct bpf_reg_state *regs, u32 regno,
			   enum bpf_reg_type reg_type,
			   struct btf *btf, u32 btf_id,
			   enum bpf_type_flag flag)
{
	switch (reg_type) {
	case SCALAR_VALUE:
		mark_reg_unknown(env, regs, regno);
		return 0;
	case PTR_TO_BTF_ID:
		mark_reg_known_zero(env, regs, regno);
		regs[regno].type = PTR_TO_BTF_ID | flag;
		regs[regno].btf = btf;
		regs[regno].btf_id = btf_id;
		if (type_may_be_null(flag))
			regs[regno].id = ++env->id_gen;
		return 0;
	case PTR_TO_MEM:
		mark_reg_known_zero(env, regs, regno);
		regs[regno].type = PTR_TO_MEM | flag;
		regs[regno].mem_size = 0;
		return 0;
	default:
		verifier_bug(env, "unexpected reg_type %d in %s\n", reg_type, __func__);
		return -EFAULT;
	}
}

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++) {
		bpf_mark_reg_not_init(env, &regs[i]);
	}

	/* 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;
}

static struct bpf_retval_range retval_range(s32 minval, s32 maxval)
{
	/*
	 * return_32bit is set to false by default and set explicitly
	 * by the caller when necessary.
	 */
	return (struct bpf_retval_range){ minval, maxval, false };
}

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;
	bpf_diag_init_frame(env, state);
	state->subprogno = subprogno;
	state->callback_ret_range = retval_range(0, 0);
	init_reg_state(env, state);
	mark_verifier_state_scratched(env);
}

/* Similar to push_stack(), but for async callbacks */
static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
						int insn_idx, int prev_insn_idx,
						int subprog, bool is_sleepable)
{
	struct bpf_verifier_stack_elem *elem;
	struct bpf_func_state *frame;

	elem = kzalloc_obj(struct bpf_verifier_stack_elem, GFP_KERNEL_ACCOUNT);
	if (!elem)
		return ERR_PTR(-ENOMEM);

	elem->insn_idx = insn_idx;
	elem->prev_insn_idx = prev_insn_idx;
	elem->next = env->head;
	elem->log_pos = env->log.end_pos;
	elem->diag_log_pos = bpf_diag_event_log_save(env);
	env->head = elem;
	env->stack_size++;
	if (env->stack_size > BPF_COMPLEXITY_LIMIT_JMP_SEQ) {
		verbose(env,
			"The sequence of %d jumps is too complex for async cb.\n",
			env->stack_size);
		return ERR_PTR(-E2BIG);
	}
	/* Unlike push_stack() do not bpf_copy_verifier_state().
	 * The caller state doesn't matter.
	 * This is async callback. It starts in a fresh stack.
	 * Initialize it similar to do_check_common().
	 */
	elem->st.branches = 1;
	elem->st.in_sleepable = is_sleepable;
	frame = kzalloc_obj(*frame, GFP_KERNEL_ACCOUNT);
	if (!frame)
		return ERR_PTR(-ENOMEM);
	init_func_state(env, frame,
			BPF_MAIN_FUNC /* callsite */,
			0 /* frameno within this callchain */,
			subprog /* subprog number within this prog */);
	elem->st.frame[0] = frame;
	return &elem->st;
}

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

/* Find subprogram that contains instruction at 'off' */
struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off)
{
	struct bpf_subprog_info *vals = env->subprog_info;
	int l, r, m;

	if (off >= env->prog->len || off < 0 || env->subprog_cnt == 0)
		return NULL;

	l = 0;
	r = env->subprog_cnt - 1;
	while (l < r) {
		m = l + (r - l + 1) / 2;
		if (vals[m].start <= off)
			l = m;
		else
			r = m - 1;
	}
	return &vals[l];
}

/* Find subprogram that starts exactly at 'off' */
int bpf_find_subprog(struct bpf_verifier_env *env, int off)
{
	struct bpf_subprog_info *p;

	p = bpf_find_containing_subprog(env, off);
	if (!p || p->start != off)
		return -ENOENT;
	return p - env->subprog_info;
}

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 = bpf_find_subprog(env, off);
	if (ret >= 0)
		return ret;
	if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
		verbose(env, "too many subprograms\n");
		return -E2BIG;
	}
	/* determine subprog starts. The end is one before the next starts */
	env->subprog_info[env->subprog_cnt].exit_idx = U32_MAX;
	env->subprog_info[env->subprog_cnt++].start = off;
	sort(env->subprog_info, env->subprog_cnt,
	     sizeof(env->subprog_info[0]), cmp_subprogs, NULL);
	return env->subprog_cnt - 1;
}

static int bpf_find_exception_callback_insn_off(struct bpf_verifier_env *env)
{
	struct bpf_prog_aux *aux = env->prog->aux;
	struct btf *btf = aux->btf;
	const struct btf_type *t;
	u32 main_btf_id, id;
	const char *name;
	int ret, i;

	/* Non-zero func_info_cnt implies valid btf */
	if (!aux->func_info_cnt)
		return 0;
	main_btf_id = aux->func_info[0].type_id;

	t = btf_type_by_id(btf, main_btf_id);
	if (!t) {
		verbose(env, "invalid btf id for main subprog in func_info\n");
		return -EINVAL;
	}

	name = btf_find_decl_tag_value(btf, t, -1, "exception_callback:");
	if (IS_ERR(name)) {
		ret = PTR_ERR(name);
		/* If there is no tag present, there is no exception callback */
		if (ret == -ENOENT)
			ret = 0;
		else if (ret == -EEXIST)
			verbose(env, "multiple exception callback tags for main subprog\n");
		return ret;
	}

	ret = btf_find_by_name_kind(btf, name, BTF_KIND_FUNC);
	if (ret < 0) {
		verbose(env, "exception callback '%s' could not be found in BTF\n", name);
		return ret;
	}
	id = ret;
	t = btf_type_by_id(btf, id);
	if (btf_func_linkage(t) != BTF_FUNC_GLOBAL) {
		verbose(env, "exception callback '%s' must have global linkage\n", name);
		return -EINVAL;
	}
	ret = 0;
	for (i = 0; i < aux->func_info_cnt; i++) {
		if (aux->func_info[i].type_id != id)
			continue;
		ret = aux->func_info[i].insn_off;
		/* Further func_info and subprog checks will also happen
		 * later, so assume this is the right insn_off for now.
		 */
		if (!ret) {
			verbose(env, "invalid exception callback insn_off in func_info: 0\n");
			ret = -EINVAL;
		}
	}
	if (!ret) {
		verbose(env, "exception callback type id not found in func_info\n");
		ret = -EINVAL;
	}
	return ret;
}

#define MAX_KFUNC_BTFS	256

struct bpf_kfunc_btf {
	struct btf *btf;
	struct module *module;
	u16 offset;
};

struct bpf_kfunc_btf_tab {
	struct bpf_kfunc_btf descs[MAX_KFUNC_BTFS];
	u32 nr_descs;
};

static int kfunc_desc_cmp_by_id_off(const void *a, const void *b)
{
	const struct bpf_kfunc_desc *d0 = a;
	const struct bpf_kfunc_desc *d1 = b;

	/* func_id is not greater than BTF_MAX_TYPE */
	return d0->func_id - d1->func_id ?: d0->offset - d1->offset;
}

static int kfunc_btf_cmp_by_off(const void *a, const void *b)
{
	const struct bpf_kfunc_btf *d0 = a;
	const struct bpf_kfunc_btf *d1 = b;

	return d0->offset - d1->offset;
}

static struct bpf_kfunc_desc *
find_kfunc_desc(const struct bpf_prog *prog, u32 func_id, u16 offset)
{
	struct bpf_kfunc_desc desc = {
		.func_id = func_id,
		.offset = offset,
	};
	struct bpf_kfunc_desc_tab *tab;

	tab = prog->aux->kfunc_tab;
	return bsearch(&desc, tab->descs, tab->nr_base_descs,
		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off);
}

int bpf_get_kfunc_addr(const struct bpf_prog *prog, u32 func_id,
		       u16 desc_idx, u8 **func_addr)
{
	struct bpf_kfunc_desc_tab *tab;
	const struct bpf_kfunc_desc *desc;

	tab = prog->aux->kfunc_tab;
	if (desc_idx >= tab->nr_descs)
		return -EFAULT;
	desc = &tab->descs[desc_idx];
	if (desc->func_id != func_id)
		return -EFAULT;

	*func_addr = (u8 *)desc->addr;
	return 0;
}

#define BPF_FD_SLOT_BTF	1UL

static void fd_slot_set_map(struct bpf_fd_array *slot, struct bpf_map *map)
{
	slot->val = (unsigned long)map;
}

static void fd_slot_set_btf(struct bpf_fd_array *slot, struct btf *btf)
{
	slot->val = (unsigned long)btf | BPF_FD_SLOT_BTF;
}

static struct bpf_map *fd_slot_map(struct bpf_fd_array slot)
{
	if (slot.val & BPF_FD_SLOT_BTF)
		return NULL;
	return (struct bpf_map *)slot.val;
}

static struct btf *fd_slot_btf(struct bpf_fd_array slot)
{
	if (!(slot.val & BPF_FD_SLOT_BTF))
		return NULL;
	return (struct btf *)(slot.val & ~BPF_FD_SLOT_BTF);
}

static struct btf *
fd_array_get_btf_continuous(struct bpf_verifier_env *env, u32 idx)
{
	struct btf *btf;

	if (idx >= env->fd_array_cnt) {
		verbose(env, "kfunc fd_idx %u out of bounds, fd_array_cnt %u\n",
			idx, env->fd_array_cnt);
		return ERR_PTR(-EINVAL);
	}
	btf = fd_slot_btf(env->fd_array[idx]);
	if (!btf) {
		verbose(env, "kfunc fd_idx %u is not a module BTF\n", idx);
		return ERR_PTR(-EINVAL);
	}
	btf_get(btf);
	return btf;
}

static struct btf *
fd_array_get_btf_sparse(struct bpf_verifier_env *env, u32 idx)
{
	struct btf *btf;
	int btf_fd;

	if (copy_from_bpfptr_offset(&btf_fd, env->fd_array_raw,
				    (size_t)idx * sizeof(btf_fd), sizeof(btf_fd)))
		return ERR_PTR(-EFAULT);
	btf = btf_get_by_fd(btf_fd);
	if (IS_ERR(btf)) {
		verbose(env, "invalid module BTF fd specified\n");
		return btf;
	}
	return btf;
}

static struct btf *fd_array_get_btf(struct bpf_verifier_env *env, u32 idx)
{
	if (env->signature) {
		verbose(env, "signed program cannot bind any BTF\n");
		return ERR_PTR(-EACCES);
	}
	if (env->fd_array)
		return fd_array_get_btf_continuous(env, idx);
	if (!bpfptr_is_null(env->fd_array_raw))
		return fd_array_get_btf_sparse(env, idx);

	verbose(env, "kfunc offset > 0 without fd_array is invalid\n");
	return ERR_PTR(-EPROTO);
}

static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
					 s16 offset)
{
	struct bpf_kfunc_btf kf_btf = { .offset = offset };
	struct bpf_kfunc_btf_tab *tab;
	struct bpf_kfunc_btf *b;
	struct module *mod;
	struct btf *btf;

	tab = env->prog->aux->kfunc_btf_tab;
	b = bsearch(&kf_btf, tab->descs, tab->nr_descs,
		    sizeof(tab->descs[0]), kfunc_btf_cmp_by_off);
	if (!b) {
		if (tab->nr_descs == MAX_KFUNC_BTFS) {
			verbose(env, "too many different module BTFs\n");
			return ERR_PTR(-E2BIG);
		}

		btf = fd_array_get_btf(env, offset);
		if (IS_ERR(btf))
			return btf;
		if (!btf_is_module(btf)) {
			verbose(env, "BTF fd for kfunc is not a module BTF\n");
			btf_put(btf);
			return ERR_PTR(-EINVAL);
		}

		mod = btf_try_get_module(btf);
		if (!mod) {
			btf_put(btf);
			return ERR_PTR(-ENXIO);
		}

		b = &tab->descs[tab->nr_descs++];
		b->btf = btf;
		b->module = mod;
		b->offset = offset;

		/* sort() reorders entries by value, so b may no longer point
		 * to the right entry after this
		 */
		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
		     kfunc_btf_cmp_by_off, NULL);
	} else {
		btf = b->btf;
	}

	return btf;
}

void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab)
{
	if (!tab)
		return;

	while (tab->nr_descs--) {
		module_put(tab->descs[tab->nr_descs].module);
		btf_put(tab->descs[tab->nr_descs].btf);
	}
	kfree(tab);
}

static struct btf *find_kfunc_desc_btf(struct bpf_verifier_env *env, s16 offset)
{
	if (offset) {
		if (offset < 0) {
			/* In the future, this can be allowed to increase limit
			 * of fd index into fd_array, interpreted as u16.
			 */
			verbose(env, "negative offset disallowed for kernel module function call\n");
			return ERR_PTR(-EINVAL);
		}

		return __find_kfunc_desc_btf(env, offset);
	}
	return btf_vmlinux ?: ERR_PTR(-ENOENT);
}

static struct btf *find_kfunc_desc_btf_cached(struct bpf_verifier_env *env, s16 offset)
{
	struct bpf_kfunc_btf kf_btf = { .offset = offset };
	struct bpf_kfunc_btf_tab *tab;
	struct bpf_kfunc_btf *b;

	if (!offset)
		return btf_vmlinux ?: ERR_PTR(-ENOENT);
	if (offset < 0)
		return ERR_PTR(-EINVAL);

	tab = env->prog->aux->kfunc_btf_tab;
	if (!tab)
		return ERR_PTR(-ENOENT);

	b = bsearch(&kf_btf, tab->descs, tab->nr_descs,
		    sizeof(tab->descs[0]), kfunc_btf_cmp_by_off);
	return b ? b->btf : ERR_PTR(-ENOENT);
}

#define KF_IMPL_SUFFIX "_impl"

static const struct btf_type *find_kfunc_impl_proto(struct bpf_verifier_log *log,
						    struct btf *btf,
						    const char *func_name)
{
	const struct btf_type *func;
	char buf[KSYM_NAME_LEN];
	s32 impl_id;
	int len;

	len = snprintf(buf, sizeof(buf), "%s%s", func_name, KF_IMPL_SUFFIX);
	if (len < 0 || len >= sizeof(buf)) {
		bpf_log(log, "function name %s%s is too long\n",
			func_name, KF_IMPL_SUFFIX);
		return NULL;
	}

	impl_id = btf_find_by_name_kind(btf, buf, BTF_KIND_FUNC);
	if (impl_id <= 0) {
		bpf_log(log, "cannot find function %s in BTF\n", buf);
		return NULL;
	}

	func = btf_type_by_id(btf, impl_id);

	return btf_type_by_id(btf, func->type);
}

static int fetch_kfunc_meta(struct bpf_verifier_env *env,
			    s32 func_id,
			    s16 offset,
			    struct bpf_kfunc_meta *kfunc)
{
	const struct btf_type *func, *func_proto;
	const char *func_name;
	u32 *kfunc_flags;
	struct btf *btf;

	if (func_id <= 0) {
		verbose(env, "invalid kernel function btf_id %d\n", func_id);
		return -EINVAL;
	}

	btf = find_kfunc_desc_btf(env, offset);
	if (IS_ERR(btf)) {
		verbose(env, "failed to find BTF for kernel function\n");
		return PTR_ERR(btf);
	}

	/*
	 * Note that kfunc_flags may be NULL at this point, which
	 * means that we couldn't find func_id in any relevant
	 * kfunc_id_set. This most likely indicates an invalid kfunc
	 * call.  However we don't fail with an error here,
	 * and let the caller decide what to do with NULL kfunc->flags.
	 */
	kfunc_flags = btf_kfunc_flags(btf, func_id, env->prog);

	func = btf_type_by_id(btf, func_id);
	if (!func || !btf_type_is_func(func)) {
		verbose(env, "kernel btf_id %d is not a function\n", func_id);
		return -EINVAL;
	}

	func_name = btf_name_by_offset(btf, func->name_off);

	/*
	 * An actual prototype of a kfunc with KF_IMPLICIT_ARGS flag
	 * can be found through the counterpart _impl kfunc.
	 */
	if (kfunc_flags && (*kfunc_flags & KF_IMPLICIT_ARGS))
		func_proto = find_kfunc_impl_proto(&env->log, btf, func_name);
	else
		func_proto = btf_type_by_id(btf, func->type);

	if (!func_proto || !btf_type_is_func_proto(func_proto)) {
		verbose(env, "kernel function btf_id %d does not have a valid func_proto\n",
			func_id);
		return -EINVAL;
	}

	memset(kfunc, 0, sizeof(*kfunc));
	kfunc->btf = btf;
	kfunc->id = func_id;
	kfunc->name = func_name;
	kfunc->proto = func_proto;
	kfunc->flags = kfunc_flags;

	return 0;
}

static int gen_kfunc_arg_proto(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
			       const struct btf_func_model *fm, struct bpf_func_proto *proto);

int bpf_add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, u16 offset)
{
	struct bpf_call_arg_meta meta;
	struct bpf_kfunc_btf_tab *btf_tab;
	struct btf_func_model func_model;
	struct bpf_kfunc_desc_tab *tab;
	struct bpf_prog_aux *prog_aux;
	struct bpf_kfunc_meta kfunc;
	struct bpf_kfunc_desc *desc;
	unsigned long addr;
	int err;

	prog_aux = env->prog->aux;
	tab = prog_aux->kfunc_tab;
	btf_tab = prog_aux->kfunc_btf_tab;
	if (!tab) {
		if (!btf_vmlinux) {
			verbose(env, "calling kernel function is not supported without CONFIG_DEBUG_INFO_BTF\n");
			return -ENOTSUPP;
		}

		if (!env->prog->jit_requested) {
			verbose(env, "JIT is required for calling kernel function\n");
			return -ENOTSUPP;
		}

		if (!bpf_jit_supports_kfunc_call()) {
			verbose(env, "JIT does not support calling kernel function\n");
			return -ENOTSUPP;
		}

		if (!env->prog->gpl_compatible) {
			verbose(env, "cannot call kernel function from non-GPL compatible program\n");
			return -EINVAL;
		}

		tab = kzalloc_obj(*tab, GFP_KERNEL_ACCOUNT);
		if (!tab)
			return -ENOMEM;
		prog_aux->kfunc_tab = tab;
	}

	env->prog->jit_required = 1;

	/* func_id == 0 is always invalid, but instead of returning an error, be
	 * conservative and wait until the code elimination pass before returning
	 * error, so that invalid calls that get pruned out can be in BPF programs
	 * loaded from userspace.  It is also required that offset be untouched
	 * for such calls.
	 */
	if (!func_id && !offset)
		return 0;

	if (!btf_tab && offset) {
		btf_tab = kzalloc_obj(*btf_tab, GFP_KERNEL_ACCOUNT);
		if (!btf_tab)
			return -ENOMEM;
		prog_aux->kfunc_btf_tab = btf_tab;
	}

	if (find_kfunc_desc(env->prog, func_id, offset))
		return 0;

	if (tab->nr_base_descs == MAX_KFUNC_DESCS) {
		verbose(env, "too many different kernel function calls\n");
		return -E2BIG;
	}
	if (tab->nr_descs != tab->nr_base_descs) {
		verifier_bug(env, "unexpected specialized func desc found (%d descs, %d base descs)",
			     tab->nr_descs, tab->nr_base_descs);
		return -EFAULT;
	}

	err = fetch_kfunc_meta(env, func_id, offset, &kfunc);
	if (err)
		return err;

	addr = kallsyms_lookup_name(kfunc.name);
	if (!addr) {
		verbose(env, "cannot find address for kernel function %s\n", kfunc.name);
		return -EINVAL;
	}

	if (bpf_dev_bound_kfunc_id(func_id)) {
		err = bpf_dev_bound_kfunc_check(&env->log, prog_aux);
		if (err)
			return err;
	}

	err = btf_distill_func_proto(&env->log, kfunc.btf, kfunc.proto, kfunc.name, &func_model);
	if (err)
		return err;
	if (func_model.ret_size > 8) {
		if (kfunc.flags && (*kfunc.flags & KF_FASTCALL)) {
			verbose(env, "kfunc %s with >8-byte return is not supported with KF_FASTCALL\n",
				kfunc.name);
			return -EOPNOTSUPP;
		}
		if (!bpf_jit_supports_kfunc_ret_reg_pair()) {
			verbose(env, "kfunc %s with >8-byte return is not supported by JIT\n",
				kfunc.name);
			return -EOPNOTSUPP;
		}
	}

	memset(&meta, 0, sizeof(meta));
	meta.btf = kfunc.btf;
	meta.func_id = kfunc.id;
	meta.func_proto = kfunc.proto;
	meta.func_name = kfunc.name;
	meta.kfunc_flags = kfunc.flags ? *kfunc.flags : 0;

	tab = krealloc(tab, struct_size(tab, descs, tab->nr_descs + 1), GFP_KERNEL_ACCOUNT);
	if (!tab)
		return -ENOMEM;
	prog_aux->kfunc_tab = tab;

	desc = &tab->descs[tab->nr_descs];
	memset(desc, 0, sizeof(*desc));

	err = gen_kfunc_arg_proto(env, &meta, &func_model, &desc->proto);
	if (err)
		return err;

	desc->func_id = func_id;
	desc->offset = offset;
	desc->addr = addr;
	desc->func_model = func_model;
	tab->nr_descs++;
	tab->nr_base_descs++;
	sort(tab->descs, tab->nr_base_descs, sizeof(tab->descs[0]),
	     kfunc_desc_cmp_by_id_off, NULL);
	return 0;
}

static int add_subprogs(struct bpf_verifier_env *env)
{
	struct bpf_subprog_info *subprog = env->subprog_info;
	int i, ret, insn_cnt = env->prog->len, ex_cb_insn;
	struct bpf_insn *insn = env->prog->insnsi;
	const char *operation, *suggestion;

	/* Add entry function. */
	ret = add_subprog(env, 0);
	if (ret)
		return ret;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (!bpf_pseudo_func(insn) && !bpf_pseudo_call(insn))
			continue;

		if (!env->bpf_capable) {
			if (bpf_pseudo_func(insn)) {
				operation = "BPF function reference";
				suggestion = "Load this program with the required capability, or avoid BPF function references in unprivileged programs.";
			} else {
				operation = "BPF-to-BPF function call";
				suggestion = "Load this program with the required capability, or avoid BPF-to-BPF function calls in unprivileged programs.";
			}
			verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
			bpf_diag_policy(
				env, i, operation,
				"loading or calling other BPF functions requires CAP_BPF or CAP_SYS_ADMIN",
				suggestion);
			return -EPERM;
		}

		ret = add_subprog(env, i + insn->imm + 1);
		if (ret < 0)
			return ret;
	}

	/*
	 * func_info describes all functions of the program. Those that are
	 * referenced only from data, e.g. from a table of functions to be
	 * called via callx, are not seen by the loop above. They are possible
	 * callees that have to be known upfront as well.
	 */
	if (env->bpf_capable) {
		struct bpf_prog_aux *aux = env->prog->aux;

		for (i = 1; i < aux->func_info_cnt; i++) {
			ret = add_subprog(env, aux->func_info[i].insn_off);
			if (ret < 0)
				return ret;
		}
	}

	ret = bpf_find_exception_callback_insn_off(env);
	if (ret < 0)
		return ret;
	ex_cb_insn = ret;

	/* If ex_cb_insn > 0, this means that the main program has a subprog
	 * marked using BTF decl tag to serve as the exception callback.
	 */
	if (ex_cb_insn) {
		ret = add_subprog(env, ex_cb_insn);
		if (ret < 0)
			return ret;
		for (i = 1; i < env->subprog_cnt; i++) {
			if (env->subprog_info[i].start != ex_cb_insn)
				continue;
			env->exception_callback_subprog = i;
			bpf_mark_subprog_exc_cb(env, i);
			break;
		}
	}

	/* Add a fake 'exit' subprog which could simplify subprog iteration
	 * logic. 'subprog_cnt' should not be increased.
	 */
	subprog[env->subprog_cnt].start = insn_cnt;

	if (env->log.level & BPF_LOG_LEVEL2)
		for (i = 0; i < env->subprog_cnt; i++)
			verbose(env, "func#%d @%d\n", i, subprog[i].start);

	return 0;
}

static int add_kfuncs(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int i, ret, insn_cnt = env->prog->len;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (!bpf_pseudo_kfunc_call(insn))
			continue;

		if (!env->bpf_capable) {
			verbose(env, "loading/calling other bpf or kernel functions are allowed for CAP_BPF and CAP_SYS_ADMIN\n");
			bpf_diag_policy(
				env, i, "kernel function call",
				"calling kernel functions requires CAP_BPF or CAP_SYS_ADMIN",
				"Load this program with the required capability, or avoid kernel function calls in unprivileged programs.");
			return -EPERM;
		}

		ret = bpf_add_kfunc_call(env, insn->imm, insn->off);
		if (ret < 0)
			return ret;
	}

	return 0;
}

static void find_subprog_properties(struct bpf_verifier_env *env)
{
	struct bpf_subprog_info *subprog = env->subprog_info;
	struct bpf_insn *insn = env->prog->insnsi;
	int cur_subprog;

	for (cur_subprog = 0; cur_subprog < env->subprog_cnt; cur_subprog++) {
		int i;

		for (i = subprog[cur_subprog].start;
		     i < subprog[cur_subprog + 1].start; i++) {
			u8 code = insn[i].code;

			if (code == (BPF_JMP | BPF_CALL) &&
			    insn[i].src_reg == 0 &&
			    insn[i].imm == BPF_FUNC_tail_call) {
				subprog[cur_subprog].has_tail_call = true;
				subprog[cur_subprog].tail_call_reachable = true;
			}
			if (BPF_CLASS(code) == BPF_LD &&
			    (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
				subprog[cur_subprog].has_ld_abs = true;
			if (bpf_is_callx(&insn[i]))
				env->has_callx = true;
		}
	}
}

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

	/* now check that all jumps are within the same subprog */
	subprog_start = subprog[cur_subprog].start;
	subprog_end = subprog[cur_subprog + 1].start;
	for (i = 0; i < insn_cnt; i++) {
		u8 code = insn[i].code;

		if (BPF_CLASS(code) != BPF_JMP && BPF_CLASS(code) != BPF_JMP32)
			goto next;
		if (BPF_OP(code) == BPF_CALL)
			goto next;
		if (BPF_OP(code) == BPF_EXIT) {
			subprog[cur_subprog].exit_idx = i;
			goto next;
		}
		if (insn_is_gotox(&insn[i]))
			goto next;
		off = i + bpf_jmp_offset(&insn[i]) + 1;
		if (off < subprog_start || off >= subprog_end) {
			verbose(env, "jump out of range from insn %d to %d\n", i, off);
			bpf_diag_program_structure(
				env, i, "jump out of range",
				"Keep branch targets within the same subprogram, or use an explicit subprogram call.",
				"Instruction %d jumps to instruction %d, but subprogram %d only contains instructions %d through %d. "
				"A branch target must stay inside the same subprogram.",
				i, off, cur_subprog, subprog_start, subprog_end - 1);
			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 or bpf_throw call.
			 */
			if (code != (BPF_JMP | BPF_EXIT) &&
			    code != (BPF_JMP32 | BPF_JA) &&
			    code != (BPF_JMP | BPF_JA) &&
			    !insn_is_gotox(&insn[i])) {
				verbose(env, "last insn is not an exit or jmp\n");
				bpf_diag_program_structure(
					env, i, "subprogram can fall through",
					"End each subprogram with an exit or an explicit jump that keeps control flow inside the subprogram.",
					"Subprogram %d reaches its last instruction %d without an exit or jump, so control could continue into the next subprogram.",
					cur_subprog, i);
				return -EINVAL;
			}
			subprog_start = subprog_end;
			cur_subprog++;
			if (cur_subprog < env->subprog_cnt)
				subprog_end = subprog[cur_subprog + 1].start;
		}
	}
	return 0;
}

/*
 * The callee of callx is known to the main verification pass only, which
 * records the 'caller' -> 'callee' edge of the call graph for the checks
 * that follow it: absence of recursion and the maximum stack depth.
 */
static int record_callx_edge(struct bpf_verifier_env *env, int caller, int callee)
{
	u32 cnt = env->subprog_cnt;

	if (!env->callx_edges) {
		env->callx_edges = kvcalloc(BITS_TO_LONGS(cnt * cnt), sizeof(long),
					    GFP_KERNEL_ACCOUNT);
		if (!env->callx_edges)
			return -ENOMEM;
	}
	__set_bit(caller * cnt + callee, env->callx_edges);
	return 0;
}

/*
 * Return the first subprog with the number >= 'from' that 'caller' calls
 * via callx, or -1 when there is none.
 */
static int next_callx_callee(struct bpf_verifier_env *env, int caller, int from)
{
	u32 cnt = env->subprog_cnt;
	unsigned long bit, end = (caller + 1) * cnt;

	if (!env->callx_edges || from >= cnt)
		return -1;
	bit = find_next_bit(env->callx_edges, end, caller * cnt + from);
	return bit < end ? bit - caller * cnt : -1;
}

/*
 * 'call foo; unwind_goto pad' goes to the pad when foo left with unwind_exit.
 * JITs don't emit a branch for it. unwind_exit finds the pad by its return
 * address. So unwind_goto has to follow the call and nothing may jump to it.
 */
static int check_unwind_insns(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	bool seen = false;
	int i;

	for (i = 0; i < env->prog->len; i++, insn++) {
		if (bpf_is_unwind_exit(insn)) {
			bpf_find_containing_subprog(env, i)->can_unwind = true;
			seen = true;
		}
		if (!bpf_is_unwind_goto(insn))
			continue;
		seen = true;
		if (!i || !(bpf_pseudo_call(insn - 1) || bpf_is_callx(insn - 1))) {
			verbose(env, "unwind_goto at insn %d doesn't follow a call of a subprog\n",
				i);
			return -EINVAL;
		}
		if (bpf_is_jump_target(env, i)) {
			verbose(env, "jump to unwind_goto at insn %d\n", i);
			return -EINVAL;
		}
	}
	if (!seen)
		return 0;
	if (!bpf_jit_supports_unwind() || bpf_prog_is_offloaded(env->prog->aux)) {
		verbose(env, "JIT does not support unwinding\n");
		return -ENOTSUPP;
	}
	env->prog->jit_required = 1;
	env->prog->aux->can_unwind = env->subprog_info[0].can_unwind;
	return 0;
}

/*
 * Sort subprogs in topological order so that leaf subprogs come first and
 * their callers come later. This is a DFS post-order traversal of the call
 * graph. Scan only reachable instructions (those in the computed postorder) of
 * the current subprog to discover callees (direct subprogs and sync
 * callbacks).
 *
 * The callees of callx are not known before the main verification pass.
 * When callx is used the sort is repeated after it with the recorded callx
 * edges added to the call graph to reject recursion through indirect calls.
 */
static int sort_subprogs_topo(struct bpf_verifier_env *env)
{
	struct bpf_subprog_info *si = env->subprog_info;
	int *insn_postorder = env->cfg.insn_postorder;
	struct bpf_insn *insn = env->prog->insnsi;
	int cnt = env->subprog_cnt;
	int *dfs_stack = NULL;
	int top = 0, order = 0;
	int i, ret = 0;
	u8 *color = NULL;

	color = kvzalloc_objs(*color, cnt, GFP_KERNEL_ACCOUNT);
	dfs_stack = kvmalloc_objs(*dfs_stack, cnt, GFP_KERNEL_ACCOUNT);
	if (!color || !dfs_stack) {
		ret = -ENOMEM;
		goto out;
	}

	/*
	 * DFS post-order traversal.
	 * Color values: 0 = unvisited, 1 = on stack, 2 = done.
	 */
	for (i = 0; i < cnt; i++) {
		if (color[i])
			continue;
		color[i] = 1;
		dfs_stack[top++] = i;

		while (top > 0) {
			int cur = dfs_stack[top - 1];
			int po_start = si[cur].postorder_start;
			int po_end = si[cur + 1].postorder_start;
			bool pushed = false;
			int j;

			for (j = po_start; j < po_end; j++) {
				int idx = insn_postorder[j];
				int callee;

				if (bpf_is_callx(&insn[idx])) {
					/* find a callee that is not explored yet */
					callee = -1;
					do {
						callee = next_callx_callee(env, cur, callee + 1);
					} while (callee >= 0 && color[callee] == 2);
					if (callee < 0)
						continue;
				} else if (bpf_pseudo_call(&insn[idx]) || bpf_pseudo_func(&insn[idx])) {
					callee = bpf_find_subprog(env, idx + insn[idx].imm + 1);
					if (callee < 0) {
						ret = -EFAULT;
						goto out;
					}
				} else {
					continue;
				}
				if (color[callee] == 2)
					continue;
				if (color[callee] == 1) {
					if (bpf_pseudo_func(&insn[idx]))
						continue;
					verbose(env, "recursive call from %s() to %s()\n",
						bpf_subprog_name(env, cur),
						bpf_subprog_name(env, callee));
					bpf_diag_program_structure(
						env, idx, "recursive subprogram call",
						"Rewrite the recursion as an explicit bounded loop, or split the logic so subprogram calls do not form a cycle.",
						"This bpf2bpf call would make the subprogram call graph recursive. "
						"The verifier requires a finite, acyclic call graph so it can bound stack depth and analysis.");
					ret = -EINVAL;
					goto out;
				}
				color[callee] = 1;
				dfs_stack[top++] = callee;
				pushed = true;
				break;
			}

			if (!pushed) {
				color[cur] = 2;
				env->subprog_topo_order[order++] = cur;
				top--;
			}
		}
	}

	if (env->log.level & BPF_LOG_LEVEL2)
		for (i = 0; i < cnt; i++)
			verbose(env, "topo_order[%d] = %s\n",
				i, bpf_subprog_name(env, env->subprog_topo_order[i]));
out:
	kvfree(dfs_stack);
	kvfree(color);
	return ret;
}

static void mark_stack_slots_scratched(struct bpf_verifier_env *env,
				       int spi, int nr_slots)
{
	int i;

	for (i = 0; i < nr_slots; i++)
		mark_stack_slot_scratched(env, spi - i);
}

static int __check_reg_arg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno,
			   enum bpf_reg_arg_type t)
{
	struct bpf_reg_state *reg;

	mark_reg_scratched(env, regno);

	reg = &regs[regno];
	if (t == SRC_OP) {
		/* check whether register used as source operand can be read */
		if (reg->type == NOT_INIT) {
			verbose(env, "R%d !read_ok\n", regno);
			bpf_diag_unreadable_reg(env, env->insn_idx, regno);
			return -EACCES;
		}
		/* We don't need to worry about FP liveness because it's read-only */
		if (regno == BPF_REG_FP)
			return 0;

		return 0;
	} 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;
		}
		if (t == DST_OP)
			mark_reg_unknown(env, regs, regno);
	}
	return 0;
}

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

	return __check_reg_arg(env, state->regs, regno, t);
}

static void mark_indirect_target(struct bpf_verifier_env *env, int idx)
{
	env->insn_aux_data[idx].indirect_target = true;
}

static void mark_non_stack_access(struct bpf_verifier_env *env, int idx)
{
	env->insn_aux_data[idx].non_stack_access = true;
}

/* Layout of one packed linked register in the jump history, see linked_regs_pack() */
#define LR_FRAMENO_BITS	4
#define LR_INDEX_BITS	11
#define LR_FRAMENO_MASK	((1u << LR_FRAMENO_BITS) - 1)
#define LR_IS_REG	BIT(LR_FRAMENO_BITS)
#define LR_INDEX_OFF	(LR_FRAMENO_BITS + 1)
#define LR_INDEX_MASK	((1u << LR_INDEX_BITS) - 1)
#define LINKED_REGS_MAX	BPF_LINKED_REGS_MAX

static_assert(MAX_CALL_FRAMES <= (1 << LR_FRAMENO_BITS));
static_assert(MAX_BPF_REG <= (1 << LR_INDEX_BITS));
static_assert(MAX_BPF_STACK_SLOTS <= (1 << LR_INDEX_BITS));
static_assert(LR_INDEX_OFF + LR_INDEX_BITS <= 16);

struct linked_reg {
	u8 frameno;
	union {
		u16 spi;
		u16 regno;
	};
	bool is_reg;
};

struct linked_regs {
	int cnt;
	struct linked_reg entries[LINKED_REGS_MAX];
};

static struct linked_reg *linked_regs_push(struct linked_regs *s)
{
	if (s->cnt < LINKED_REGS_MAX)
		return &s->entries[s->cnt++];

	return NULL;
}

/*
 * Pack linked registers for a jump history entry, one u16 each:
 * - 4 bits frameno
 * - 1 bit  is_reg
 * - 11 bits register or stack slot index
 */
static void linked_regs_pack(const struct linked_regs *s, u16 *packed)
{
	int i;

	for (i = 0; i < s->cnt; ++i) {
		const struct linked_reg *e = &s->entries[i];

		packed[i] = e->frameno | (e->is_reg ? LR_IS_REG : 0) | (e->spi << LR_INDEX_OFF);
	}
}

static void linked_regs_unpack(const struct bpf_jmp_history_entry *hist, struct linked_regs *s)
{
	int i;

	s->cnt = hist->linked_regs_cnt;
	for (i = 0; i < s->cnt; ++i) {
		struct linked_reg *e = &s->entries[i];
		u16 packed = hist->linked_regs[i];

		e->frameno = packed & LR_FRAMENO_MASK;
		e->is_reg  = packed & LR_IS_REG;
		e->spi     = (packed >> LR_INDEX_OFF) & LR_INDEX_MASK;
	}
}

const char *bpf_disasm_kfunc_name(void *data, const struct bpf_insn *insn)
{
	const struct btf_type *func;
	struct btf *desc_btf;

	if (insn->src_reg != BPF_PSEUDO_KFUNC_CALL)
		return NULL;

	desc_btf = find_kfunc_desc_btf_cached(data, insn->off);
	if (IS_ERR(desc_btf))
		return "<error>";

	func = btf_type_by_id(desc_btf, insn->imm);
	if (!func || !btf_type_is_func(func))
		return "<error>";
	return btf_name_by_offset(desc_btf, func->name_off);
}

void bpf_verbose_insn(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	const struct bpf_insn_cbs cbs = {
		.cb_call	= bpf_disasm_kfunc_name,
		.cb_print	= verbose,
		.private_data	= env,
	};

	print_bpf_insn(&cbs, insn, env->allow_ptr_leaks);
}

/* If any register R in hist->linked_regs is marked as precise in bt,
 * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs.
 */
void bpf_bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist)
{
	struct linked_regs linked_regs;
	bool some_precise = false;
	int i;

	if (!hist || !hist->linked_regs_cnt)
		return;

	linked_regs_unpack(hist, &linked_regs);
	for (i = 0; i < linked_regs.cnt; ++i) {
		struct linked_reg *e = &linked_regs.entries[i];

		if ((e->is_reg && bt_is_frame_reg_set(bt, e->frameno, e->regno)) ||
		    (!e->is_reg && bt_is_frame_slot_set(bt, e->frameno, e->spi))) {
			some_precise = true;
			break;
		}
	}

	if (!some_precise)
		return;

	for (i = 0; i < linked_regs.cnt; ++i) {
		struct linked_reg *e = &linked_regs.entries[i];

		if (e->is_reg)
			bpf_bt_set_frame_reg(bt, e->frameno, e->regno);
		else
			bpf_bt_set_frame_slot(bt, e->frameno, e->spi);
	}
}

int mark_chain_precision(struct bpf_verifier_env *env, int regno)
{
	return bpf_mark_chain_precision(env, env->cur_state, regno, NULL);
}

/* mark_chain_precision_batch() assumes that env->bt is set in the caller to
 * desired reg and stack masks across all relevant frames
 */
static int mark_chain_precision_batch(struct bpf_verifier_env *env,
				      struct bpf_verifier_state *starting_state)
{
	return bpf_mark_chain_precision(env, starting_state, -1, NULL);
}

/* check if register is a constant scalar value */
static bool is_reg_const(struct bpf_reg_state *reg, bool subreg32)
{
	return reg->type == SCALAR_VALUE &&
	       tnum_is_const(subreg32 ? tnum_subreg(reg->var_off) : reg->var_off);
}

/* assuming is_reg_const() is true, return constant value of a register */
static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32)
{
	return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value;
}

static bool is_pointer_regtype(enum bpf_reg_type type)
{
	return type != SCALAR_VALUE && type != NOT_INIT;
}

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

	return is_pointer_regtype(reg->type);
}

static void clear_scalar_id(struct bpf_reg_state *reg)
{
	reg->id = 0;
	reg->delta = 0;
}

static void assign_scalar_id_before_mov(struct bpf_verifier_env *env,
					struct bpf_reg_state *src_reg)
{
	if (src_reg->type != SCALAR_VALUE)
		return;
	/*
	 * The verifier is processing rX = rY insn and
	 * rY->id has special linked register already.
	 * Cleared it, since multiple rX += const are not supported.
	 */
	if (src_reg->id & BPF_ADD_CONST)
		clear_scalar_id(src_reg);
	/*
	 * Ensure that src_reg has a valid ID that will be copied to
	 * dst_reg and then will be used by sync_linked_regs() to
	 * propagate min/max range.
	 */
	if (!src_reg->id && !tnum_is_const(src_reg->var_off))
		src_reg->id = ++env->id_gen;
}

static void save_register_state(struct bpf_verifier_env *env,
				struct bpf_func_state *state,
				int spi, struct bpf_reg_state *reg,
				int size)
{
	struct bpf_stack_state *slot = bpf_stack_slot(state, spi);
	int i;

	bpf_diag_mod_begin(env, &slot->spilled_ptr, reg, BPF_DIAG_MOD_SPILL);
	slot->spilled_ptr = *reg;

	for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--)
		slot->slot_type[i - 1] = STACK_SPILL;

	/* size < 8 bytes spill */
	for (; i; i--)
		mark_stack_slot_misc(env, &slot->slot_type[i - 1]);

	bpf_diag_mod_end(env);
}

static bool is_bpf_st_mem(struct bpf_insn *insn)
{
	return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM;
}

static int get_reg_width(struct bpf_reg_state *reg)
{
	return fls64(reg_umax(reg));
}

/* See comment for mark_fastcall_pattern_for_call() */
static void check_fastcall_stack_contract(struct bpf_verifier_env *env,
					  struct bpf_func_state *state, int insn_idx, int off)
{
	struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno];
	struct bpf_insn_aux_data *aux = env->insn_aux_data;
	int i;

	if (subprog->fastcall_stack_off <= off || aux[insn_idx].fastcall_pattern)
		return;
	/* access to the region [max_stack_depth .. fastcall_stack_off)
	 * from something that is not a part of the fastcall pattern,
	 * disable fastcall rewrites for current subprogram by setting
	 * fastcall_stack_off to a value smaller than any possible offset.
	 */
	subprog->fastcall_stack_off = S16_MIN;
	/* reset fastcall aux flags within subprogram,
	 * happens at most once per subprogram
	 */
	for (i = subprog->start; i < (subprog + 1)->start; ++i) {
		aux[i].fastcall_spills_num = 0;
		aux[i].fastcall_pattern = 0;
	}
}

static void scrub_special_slot(struct bpf_func_state *state, int spi)
{
	struct bpf_stack_state *slot = bpf_stack_slot(state, spi);
	int i;

	/* regular write of data into stack destroys any spilled ptr */
	slot->spilled_ptr.type = NOT_INIT;
	/* Mark slots as STACK_MISC if they belonged to spilled ptr/dynptr/iter. */
	if (is_stack_slot_special(slot))
		for (i = 0; i < BPF_REG_SIZE; i++)
			scrub_spilled_slot(&slot->slot_type[i]);
}

/* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
 * stack boundary and alignment are checked in check_mem_access()
 */
static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
				       /* stack frame we're writing to */
				       struct bpf_func_state *state,
				       int off, int size, int value_regno,
				       int insn_idx)
{
	struct bpf_func_state *cur; /* state of the current function */
	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
	struct bpf_reg_state *reg = NULL;
	int insn_flags = INSN_F_STACK_ACCESS;
	int hist_spi = spi, hist_frame = state->frameno;
	struct bpf_stack_state *ss = bpf_stack_slot(state, spi);

	/*
	 * caller checked that off % size == 0 and -env->stack_limit <= off < 0,
	 * so it's aligned access and [off, off + size) are within stack limits
	 */
	if (!env->allow_ptr_leaks &&
	    bpf_is_spilled_reg(ss) &&
	    !bpf_is_spilled_scalar_reg(ss) &&
	    size != BPF_REG_SIZE) {
		const char *reason;

		verbose(env, "attempt to corrupt spilled pointer on stack\n");
		reason = bpf_diag_fmt(env,
				      "This store writes %d bytes at stack offset %d into a stack slot that currently holds a spilled pointer. "
			"Partial writes to spilled pointers are rejected because they can corrupt pointer metadata and leak kernel pointers.",
			size, off);
		bpf_diag_memory(
			env, insn_idx, "stack spill corruption", reason,
			"Write the full 8-byte spilled pointer slot, or use a separate stack slot for scalar data before overwriting only part of it.");
		return -EACCES;
	}

	cur = env->cur_state->frame[env->cur_state->curframe];
	if (value_regno >= 0)
		reg = &cur->regs[value_regno];
	if (!env->bypass_spec_v4) {
		bool sanitize = reg && is_pointer_regtype(reg->type);

		for (i = 0; i < size; i++) {
			u8 type = ss->slot_type[(slot - i) %
							      BPF_REG_SIZE];

			if (type != STACK_MISC && type != STACK_ZERO) {
				sanitize = true;
				break;
			}
		}

		if (sanitize)
			env->insn_aux_data[insn_idx].nospec_result = true;
	}

	err = destroy_if_dynptr_stack_slot(env, state, spi);
	if (err)
		return err;

	mark_stack_slot_scratched(env, spi);
	if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) {
		bool reg_value_fits;

		reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size;
		/* Make sure that reg had an ID to build a relation on spill. */
		if (reg_value_fits)
			assign_scalar_id_before_mov(env, reg);
		save_register_state(env, state, spi, reg, size);
		/* Break the relation on a narrowing spill. */
		if (!reg_value_fits)
			clear_scalar_id(&ss->spilled_ptr);
	} else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) &&
		   env->bpf_capable) {
		struct bpf_reg_state *tmp_reg = &env->fake_reg[0];

		memset(tmp_reg, 0, sizeof(*tmp_reg));
		__mark_reg_known(tmp_reg, insn->imm);
		tmp_reg->type = SCALAR_VALUE;
		save_register_state(env, state, spi, tmp_reg, size);
	} else if (reg && is_pointer_regtype(reg->type)) {
		/* register containing pointer is being spilled into stack */
		if (size != BPF_REG_SIZE) {
			verbose_linfo(env, insn_idx, "; ");
			verbose(env, "invalid size of register spill\n");
			return -EACCES;
		}
		if (state != cur && reg->type == PTR_TO_STACK) {
			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
			return -EINVAL;
		}
		save_register_state(env, state, spi, reg, size);
	} else {
		u8 type = STACK_MISC;

		if (bpf_is_spilled_reg(ss))
			bpf_diag_record_scrub(env, &ss->spilled_ptr,
					      BPF_DIAG_MOD_WRITE);
		scrub_special_slot(state, spi);

		/* when we zero initialize stack slots mark them as such */
		if ((reg && bpf_register_is_null(reg)) ||
		    (!reg && is_bpf_st_mem(insn) && insn->imm == 0)) {
			/* STACK_ZERO case happened because register spill
			 * wasn't properly aligned at the stack slot boundary,
			 * so it's not a register spill anymore; force
			 * originating register to be precise to make
			 * STACK_ZERO correct for subsequent states
			 */
			err = mark_chain_precision(env, value_regno);
			if (err)
				return err;
			type = STACK_ZERO;
		}

		/* Mark slots affected by this stack write. */
		for (i = 0; i < size; i++)
			ss->slot_type[(slot - i) % BPF_REG_SIZE] = type;
		insn_flags = 0; /* not a register spill */
	}

	if (insn_flags)
		return bpf_push_jmp_history(env, env->cur_state, insn_flags,
					    hist_spi, hist_frame, NULL, 0);
	return 0;
}

/* Write the stack: 'stack[ptr_reg + off] = value_regno'. 'ptr_reg' is
 * known to contain a variable offset.
 * This function checks whether the write is permitted and conservatively
 * tracks the effects of the write, considering that each stack slot in the
 * dynamic range is potentially written to.
 *
 * 'value_regno' can be -1, meaning that an unknown value is being written to
 * the stack.
 *
 * Spilled pointers in range are not marked as written because we don't know
 * what's going to be actually written. This means that read propagation for
 * future reads cannot be terminated by this write.
 *
 * For privileged programs, uninitialized stack slots are considered
 * initialized by this write (even though we don't know exactly what offsets
 * are going to be written to). The idea is that we don't want the verifier to
 * reject future reads that access slots written to through variable offsets.
 */
static int check_stack_write_var_off(struct bpf_verifier_env *env,
				     /* func where register points to */
				     struct bpf_func_state *state,
				     struct bpf_reg_state *ptr_reg, int off, int size,
				     int value_regno, int insn_idx)
{
	struct bpf_func_state *cur; /* state of the current function */
	int min_off, max_off;
	int i, err;
	struct bpf_reg_state *value_reg = NULL;
	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
	bool writing_zero = false;
	/* set if the fact that we're writing a zero is used to let any
	 * stack slots remain STACK_ZERO
	 */
	bool zero_used = false;

	cur = env->cur_state->frame[env->cur_state->curframe];
	min_off = reg_smin(ptr_reg) + off;
	max_off = reg_smax(ptr_reg) + off + size;
	if (value_regno >= 0)
		value_reg = &cur->regs[value_regno];
	if ((value_reg && bpf_register_is_null(value_reg)) ||
	    (!value_reg && is_bpf_st_mem(insn) && insn->imm == 0))
		writing_zero = true;

	err = destroy_dynptrs_in_stack_slots(env, state, bpf_get_spi(max_off - 1),
					     bpf_get_spi(min_off));
	if (err)
		return err;

	/* Variable offset writes destroy any spilled pointers in range. */
	for (i = min_off; i < max_off; i++) {
		struct bpf_stack_state *ss;
		u8 new_type, *stype;
		int slot, spi;

		slot = -i - 1;
		spi = slot / BPF_REG_SIZE;
		ss = bpf_stack_slot(state, spi);
		stype = &ss->slot_type[slot % BPF_REG_SIZE];
		mark_stack_slot_scratched(env, spi);

		if (!env->allow_ptr_leaks && *stype != STACK_MISC && *stype != STACK_ZERO) {
			/* Reject the write if range we may write to has not
			 * been initialized beforehand. If we didn't reject
			 * here, the ptr status would be erased below (even
			 * though not all slots are actually overwritten),
			 * possibly opening the door to leaks.
			 *
			 * We do however catch STACK_INVALID case below, and
			 * only allow reading possibly uninitialized memory
			 * later for CAP_PERFMON, as the write may not happen to
			 * that slot.
			 */
			verbose(env, "spilled ptr in range of var-offset stack write; insn %d, ptr off: %d",
				insn_idx, i);
			return -EINVAL;
		}

		/* If writing_zero and the spi slot contains a spill of value 0,
		 * maintain the spill type.
		 */
		if (writing_zero && *stype == STACK_SPILL && bpf_is_spilled_scalar_reg(ss)) {
			struct bpf_reg_state *spill_reg = &ss->spilled_ptr;

			if (tnum_is_const(spill_reg->var_off) && spill_reg->var_off.value == 0) {
				zero_used = true;
				continue;
			}
		}

		/*
		 * Scrub slots if variable-offset stack write goes over spilled pointers.
		 * Otherwise bpf_is_spilled_reg() may == true && spilled_ptr.type == NOT_INIT
		 * and valid program is rejected by check_stack_read_fixed_off()
		 * with obscure "invalid size of register fill" message.
		 */
		scrub_special_slot(state, spi);

		/* Update the slot type. */
		new_type = STACK_MISC;
		if (writing_zero && *stype == STACK_ZERO) {
			new_type = STACK_ZERO;
			zero_used = true;
		}
		/* If the slot is STACK_INVALID, we check whether it's OK to
		 * pretend that it will be initialized by this write. The slot
		 * might not actually be written to, and so if we mark it as
		 * initialized future reads might leak uninitialized memory.
		 * For privileged programs, we will accept such reads to slots
		 * that may or may not be written because, if we're reject
		 * them, the error would be too confusing.
		 * Conservatively, treat STACK_POISON in a similar way.
		 */
		if ((*stype == STACK_INVALID || *stype == STACK_POISON) &&
		    !env->allow_uninit_stack) {
			verbose(env, "uninit stack in range of var-offset write prohibited for !root; insn %d, off: %d",
					insn_idx, i);
			return -EINVAL;
		}
		*stype = new_type;
	}
	if (zero_used) {
		/* backtracking doesn't work for STACK_ZERO yet. */
		err = mark_chain_precision(env, value_regno);
		if (err)
			return err;
	}
	bpf_diag_record_scrub_stack(env, state, min_off, max_off,
				    BPF_DIAG_MOD_VAR_WRITE);
	return 0;
}

/* When register 'dst_regno' is assigned some values from stack[min_off,
 * max_off), we set the register's type according to the types of the
 * respective stack slots. If all the stack values are known to be zeros, then
 * so is the destination reg. Otherwise, the register is considered to be
 * SCALAR. This function does not deal with register filling; the caller must
 * ensure that all spilled registers in the stack range have been marked as
 * read.
 *
 * STACK_SPILL bytes backed by spilled scalar const zeroes are also considered
 * zero bytes. In that case, mark the contributing stack slots precise so
 * pruning cannot reuse a zero-spill state for a later non-zero spill state.
 *
 * Returns an error if precision backtracking fails.
 */
static int mark_reg_stack_read(struct bpf_verifier_env *env,
			       /* func where src register points to */
			       struct bpf_func_state *ptr_state,
			       int min_off, int max_off, int dst_regno)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	int i, slot, spi;
	u8 *stype;
	int zeros = 0, zero_spills = 0;

	for (i = min_off; i < max_off; i++) {
		slot = -i - 1;
		spi = slot / BPF_REG_SIZE;
		mark_stack_slot_scratched(env, spi);
		stype = bpf_stack_slot(ptr_state, spi)->slot_type;
		if (stype[slot % BPF_REG_SIZE] == STACK_ZERO) {
			zeros++;
			continue;
		}
		if (stype[slot % BPF_REG_SIZE] == STACK_SPILL &&
		    bpf_register_is_null(&bpf_stack_slot(ptr_state, spi)->spilled_ptr)) {
			zero_spills++;
			zeros++;
			continue;
		}
		break;
	}
	if (zeros == max_off - min_off) {
		/* Any access_size read into register is zero extended,
		 * so the whole register == const_zero.
		 */
		__mark_reg_const_zero(env, &state->regs[dst_regno]);
		if (zero_spills) {
			for (i = min_off; i < max_off; i++) {
				slot = -i - 1;
				spi = slot / BPF_REG_SIZE;
				stype = bpf_stack_slot(ptr_state, spi)->slot_type;
				if (stype[slot % BPF_REG_SIZE] == STACK_SPILL)
					bpf_bt_set_frame_slot(&env->bt, ptr_state->frameno, spi);
			}
			return mark_chain_precision_batch(env, env->cur_state);
		}
	} else {
		/* have read misc data from the stack */
		mark_reg_unknown(env, state->regs, dst_regno);
	}

	return 0;
}

static void bpf_diag_stack_read_invalid(struct bpf_verifier_env *env, int off, int i, int size,
					enum bpf_stack_slot_type type)
{
	const char *problem, *reason, *suggestion, *kind;

	if (type == STACK_INVALID) {
		reason = bpf_diag_fmt(
			env, "This rejected read uses %d bytes at stack offset %d, but byte %d in that range is uninitialized on this path. "
			"Programs loaded with CAP_PERFMON can be allowed to read uninitialized stack bytes, but this program is being rejected without that allowance.",
			size, off, i);
		bpf_diag_memory(
			env, env->insn_idx, "uninitialized stack read", reason,
			"Initialize every byte in the stack range before reading it, adjust the offset and size so the read covers only initialized bytes, "
			"or load with CAP_PERFMON if uninitialized stack reads are intended.");
		return;
	}

	switch (type) {
	case STACK_DYNPTR:
		kind = "dynptr";
		suggestion = "Use dynptr helpers or kfuncs to access the object represented by the dynptr instead of reading the dynptr state directly.";
		break;
	case STACK_ITER:
		kind = "iterator";
		suggestion = "Use iterator kfuncs to advance or destroy the iterator instead of reading its state directly.";
		break;
	case STACK_IRQ_FLAG:
		kind = "IRQ flag";
		suggestion = "Pass the saved IRQ flag to the matching restore kfunc instead of reading its state directly.";
		break;
	default:
		return;
	}

	problem = bpf_diag_fmt(env, "direct read of %s stack state", kind);
	reason = bpf_diag_fmt(
		env, "This rejected read uses %d bytes at stack offset %d, but byte %d in that range belongs to verifier-managed %s state. "
		"This state has an opaque representation that BPF programs cannot read directly.",
		size, off, i, kind);
	bpf_diag_memory(env, env->insn_idx, problem, reason, suggestion);
}

/* Read the stack at 'off' and put the results into the register indicated by
 * 'dst_regno'. It handles reg filling if the addressed stack slot is a
 * spilled reg.
 *
 * 'dst_regno' can be -1, meaning that the read value is not going to a
 * register.
 *
 * The access is assumed to be within the current stack bounds.
 */
static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
				      /* func where src register points to */
				      struct bpf_func_state *reg_state,
				      int off, int size, int dst_regno)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
	struct bpf_reg_state *reg;
	u8 *stype, type;
	int err;
	int insn_flags = INSN_F_STACK_ACCESS;
	int hist_spi = spi, hist_frame = reg_state->frameno;
	struct bpf_stack_state *ss = bpf_stack_slot(reg_state, spi);

	stype = ss->slot_type;
	reg = &ss->spilled_ptr;

	mark_stack_slot_scratched(env, spi);

	/*
	 * Refine the in-progress load record's origin to the source stack slot.
	 */
	if (dst_regno >= 0)
		bpf_diag_mod_begin(env, &state->regs[dst_regno], reg, BPF_DIAG_MOD_WRITE);

	if (bpf_is_spilled_reg(ss)) {
		u8 spill_size = bpf_spill_size(ss);

		if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) {
			if (reg->type != SCALAR_VALUE) {
				verbose_linfo(env, env->insn_idx, "; ");
				verbose(env, "invalid size of register fill\n");
				return -EACCES;
			}

			if (size <= spill_size &&
			    bpf_stack_narrow_access_ok(off, size, spill_size)) {
				if (dst_regno < 0)
					return 0;

				if (env->bpf_capable && size == 4 && spill_size == 4 &&
				    get_reg_width(reg) <= 32)
					/* Ensure stack slot has an ID to build a relation
					 * with the destination register on fill.
					 */
					assign_scalar_id_before_mov(env, reg);
				state->regs[dst_regno] = *reg;

				/* Break the relation on a narrowing fill.
				 * coerce_reg_to_size will adjust the boundaries.
				 */
				if (get_reg_width(reg) > size * BITS_PER_BYTE)
					clear_scalar_id(&state->regs[dst_regno]);
			} else {
				int spill_cnt = 0, zero_cnt = 0;

				for (i = 0; i < size; i++) {
					type = stype[(slot - i) % BPF_REG_SIZE];
					if (type == STACK_SPILL) {
						spill_cnt++;
						continue;
					}
					if (type == STACK_MISC)
						continue;
					if (type == STACK_ZERO) {
						zero_cnt++;
						continue;
					}
					if (type == STACK_INVALID && env->allow_uninit_stack)
						continue;
					if (type == STACK_POISON) {
						verbose(env, "reading from stack off %d+%d size %d, slot poisoned by dead code elimination\n",
							off, i, size);
					} else {
						verbose(env, "invalid read from stack off %d+%d size %d\n",
							off, i, size);
						bpf_diag_stack_read_invalid(env, off, i, size, type);
					}
					return -EACCES;
				}

				if (dst_regno < 0)
					return 0;

				if (spill_cnt == size &&
				    tnum_is_const(reg->var_off) && reg->var_off.value == 0) {
					__mark_reg_const_zero(env, &state->regs[dst_regno]);
					/* this IS register fill, so keep insn_flags */
				} else if (zero_cnt == size) {
					/* similarly to mark_reg_stack_read(), preserve zeroes */
					__mark_reg_const_zero(env, &state->regs[dst_regno]);
					insn_flags = 0; /* not restoring original register state */
				} else {
					err = mark_reg_stack_read(env, reg_state, off, off + size,
								  dst_regno);
					if (err)
						return err;
					insn_flags = 0; /* not restoring original register state */
				}
			}
		} else if (dst_regno >= 0) {
			/* restore register state from stack */
			if (env->bpf_capable)
				/* Ensure stack slot has an ID to build a relation
				 * with the destination register on fill.
				 */
				assign_scalar_id_before_mov(env, reg);
			state->regs[dst_regno] = *reg;
			/* mark reg as written since spilled pointer state likely
			 * has its liveness marks cleared by is_state_visited()
			 * which resets stack/reg liveness for state transitions
			 */
		} else if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
			/* If dst_regno==-1, the caller is asking us whether
			 * it is acceptable to use this value as a SCALAR_VALUE
			 * (e.g. for XADD).
			 * We must not allow unprivileged callers to do that
			 * with spilled pointers.
			 */
			verbose(env, "leaking pointer from stack off %d\n",
				off);
			return -EACCES;
		}
	} else {
		for (i = 0; i < size; i++) {
			type = stype[(slot - i) % BPF_REG_SIZE];
			if (type == STACK_MISC)
				continue;
			if (type == STACK_ZERO)
				continue;
			if (type == STACK_INVALID && env->allow_uninit_stack)
				continue;
			if (type == STACK_POISON) {
				verbose(env, "reading from stack off %d+%d size %d, slot poisoned by dead code elimination\n",
					off, i, size);
			} else {
				verbose(env, "invalid read from stack off %d+%d size %d\n",
					off, i, size);
				bpf_diag_stack_read_invalid(env, off, i, size, type);
			}
			return -EACCES;
		}
		if (dst_regno >= 0) {
			err = mark_reg_stack_read(env, reg_state, off, off + size, dst_regno);
			if (err)
				return err;
		}
		insn_flags = 0; /* we are not restoring spilled register */
	}
	if (insn_flags)
		return bpf_push_jmp_history(env, env->cur_state, insn_flags,
					    hist_spi, hist_frame, NULL, 0);
	return 0;
}

enum bpf_access_src {
	ACCESS_DIRECT = 1,  /* the access is performed by an instruction */
	ACCESS_HELPER = 2,  /* the access is performed by a helper */
};

static int check_stack_range_initialized(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
					 argno_t argno, int off, int access_size,
					 bool zero_size_allowed,
					 enum bpf_access_type type,
					 struct bpf_call_arg_meta *meta);

static struct bpf_reg_state *reg_state(struct bpf_verifier_env *env, int regno)
{
	return cur_regs(env) + regno;
}

/* Read the stack at 'reg + off' and put the result into the register
 * 'dst_regno'.
 * 'off' includes the pointer register's fixed offset(i.e. 'reg->off'),
 * but not its variable offset.
 * 'size' is assumed to be <= reg size and the access is assumed to be aligned.
 *
 * As opposed to check_stack_read_fixed_off, this function doesn't deal with
 * filling registers (i.e. reads of spilled register cannot be detected when
 * the offset is not fixed). We conservatively mark 'dst_regno' as containing
 * SCALAR_VALUE. That's why we assert that the 'reg' has a variable
 * offset; for a fixed offset check_stack_read_fixed_off should be used
 * instead.
 */
static int check_stack_read_var_off(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				    argno_t ptr_argno, int off, int size, int dst_regno)
{
	struct bpf_func_state *ptr_state = bpf_func(env, reg);
	int err;
	int min_off, max_off;

	/* Note that we pass a NULL meta, so raw access will not be permitted.
	 */
	err = check_stack_range_initialized(env, reg, ptr_argno, off, size,
					    false, BPF_READ, NULL);
	if (err)
		return err;

	min_off = reg_smin(reg) + off;
	max_off = reg_smax(reg) + off;
	err = mark_reg_stack_read(env, ptr_state, min_off, max_off + size,
				  dst_regno);
	if (err)
		return err;
	return 0;
}

/* check_stack_read dispatches to check_stack_read_fixed_off or
 * check_stack_read_var_off.
 *
 * The caller must ensure that the offset falls within the allocated stack
 * bounds.
 *
 * 'dst_regno' is a register which will receive the value from the stack. It
 * can be -1, meaning that the read value is not going to a register.
 */
static int check_stack_read(struct bpf_verifier_env *env,
			    struct bpf_reg_state *reg, argno_t ptr_argno, int off, int size,
			    int dst_regno)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int err;
	/* Some accesses are only permitted with a static offset. */
	bool var_off = !tnum_is_const(reg->var_off);

	/* The offset is required to be static when reads don't go to a
	 * register, in order to not leak pointers (see
	 * check_stack_read_fixed_off).
	 */
	if (dst_regno < 0 && var_off) {
		const char *reason;
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "variable offset stack pointer cannot be passed into helper function; var_off=%s off=%d size=%d\n",
			tn_buf, off, size);
		reason = bpf_diag_fmt(
			env, "The instruction would access the stack through variable offset %s plus fixed offset %d and size %d. "
			"This stack access requires a constant stack offset and a precise initialized range.",
			tn_buf, off, size);
		bpf_diag_memory(
			env, env->insn_idx, "variable-offset stack access", reason,
			"Use a fixed stack offset for the instruction, selecting the target stack slot on separate control-flow paths if necessary.");
		return -EACCES;
	}
	/* Variable offset is prohibited for unprivileged mode for simplicity
	 * since it requires corresponding support in Spectre masking for stack
	 * ALU. See also retrieve_ptr_limit(). The check in
	 * check_stack_access_for_ptr_arithmetic() called by
	 * adjust_ptr_min_max_vals() prevents users from creating stack pointers
	 * with variable offsets, therefore no check is required here. Further,
	 * just checking it here would be insufficient as speculative stack
	 * writes could still lead to unsafe speculative behaviour.
	 */
	if (!var_off) {
		off += reg->var_off.value;
		err = check_stack_read_fixed_off(env, state, off, size,
						 dst_regno);
	} else {
		/* Variable offset stack reads need more conservative handling
		 * than fixed offset ones. Note that dst_regno >= 0 on this
		 * branch.
		 */
		err = check_stack_read_var_off(env, reg, ptr_argno, off, size,
					       dst_regno);
	}
	return err;
}

/* check_stack_write dispatches to check_stack_write_fixed_off or
 * check_stack_write_var_off.
 *
 * 'reg' is the register used as a pointer into the stack.
 * 'value_regno' is the register whose value we're writing to the stack. It can
 * be -1, meaning that we're not writing from a register.
 *
 * The caller must ensure that the offset falls within the maximum stack size.
 */
static int check_stack_write(struct bpf_verifier_env *env,
			     struct bpf_reg_state *reg, int off, int size,
			     int value_regno, int insn_idx)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int err;

	if (tnum_is_const(reg->var_off)) {
		off += reg->var_off.value;
		err = check_stack_write_fixed_off(env, state, off, size,
						  value_regno, insn_idx);
	} else {
		/* Variable offset stack reads need more conservative handling
		 * than fixed offset ones.
		 */
		err = check_stack_write_var_off(env, state,
						reg, off, size,
						value_regno, insn_idx);
	}
	return err;
}

/*
 * Write a value to the outgoing stack arg area.
 * off is a negative offset from r11 (e.g. -8 for arg6, -16 for arg7).
 */
static int check_stack_arg_write(struct bpf_verifier_env *env, struct bpf_func_state *state,
				 int off, struct bpf_reg_state *value_reg)
{
	int max_stack_arg_regs = MAX_BPF_FUNC_ARGS - MAX_BPF_FUNC_REG_ARGS;
	struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno];
	int spi = -off / BPF_REG_SIZE - 1;
	struct bpf_reg_state *arg;
	int err;

	if (spi >= max_stack_arg_regs) {
		verbose(env, "stack arg write offset %d exceeds max %d stack args\n",
			off, max_stack_arg_regs);
		return -EINVAL;
	}

	err = grow_stack_arg_slots(env, state, spi + 1);
	if (err)
		return err;

	/* Track the max outgoing stack arg slot count. */
	if (spi + 1 > subprog->max_out_stack_arg_cnt)
		subprog->max_out_stack_arg_cnt = spi + 1;

	arg = &state->stack_arg_regs[spi];
	bpf_diag_mod_begin(env, arg, value_reg, BPF_DIAG_MOD_WRITE);

	if (value_reg) {
		state->stack_arg_regs[spi] = *value_reg;
	} else {
		/* BPF_ST: store immediate, treat as scalar */
		arg->type = SCALAR_VALUE;
		__mark_reg_known(arg, env->prog->insnsi[env->insn_idx].imm);
	}
	bpf_diag_mod_end(env);
	state->no_stack_arg_load = true;
	return bpf_push_jmp_history(env, env->cur_state,
				    INSN_F_STACK_ARG_ACCESS, spi, 0, NULL, 0);
}

/*
 * Read a value from the incoming stack arg area.
 * off is a positive offset from r11 (e.g. +8 for arg6, +16 for arg7).
 */
static int check_stack_arg_read(struct bpf_verifier_env *env, struct bpf_func_state *state,
				int off, int dst_regno)
{
	struct bpf_subprog_info *subprog = &env->subprog_info[state->subprogno];
	struct bpf_verifier_state *vstate = env->cur_state;
	int spi = off / BPF_REG_SIZE - 1;
	struct bpf_func_state *caller, *cur;
	struct bpf_reg_state *arg;

	if (state->no_stack_arg_load) {
		verbose(env, "r11 load must be before any r11 store or call insn\n");
		return -EINVAL;
	}

	if (spi + 1 > bpf_in_stack_arg_cnt(subprog)) {
		verbose(env, "invalid read from stack arg off %d depth %d\n",
			off, bpf_in_stack_arg_cnt(subprog) * BPF_REG_SIZE);
		return -EACCES;
	}

	caller = vstate->frame[vstate->curframe - 1];
	arg = &caller->stack_arg_regs[spi];
	cur = vstate->frame[vstate->curframe];
	bpf_diag_mod_begin(env, &cur->regs[dst_regno], arg, BPF_DIAG_MOD_WRITE);
	cur->regs[dst_regno] = *arg;
	bpf_diag_mod_end(env);
	return bpf_push_jmp_history(env, env->cur_state,
				    INSN_F_STACK_ARG_ACCESS, spi, 0, NULL, 0);
}

static int mark_stack_arg_precision(struct bpf_verifier_env *env, int arg_idx)
{
	struct bpf_func_state *caller = cur_func(env);
	int spi = arg_idx - MAX_BPF_FUNC_REG_ARGS;

	bt_set_frame_stack_arg_slot(&env->bt, caller->frameno, spi);
	return mark_chain_precision_batch(env, env->cur_state);
}

static int mark_arg_precision(struct bpf_verifier_env *env, argno_t argno)
{
	int regno = reg_from_argno(argno);

	if (regno >= 0)
		return mark_chain_precision(env, regno);
	return mark_stack_arg_precision(env, arg_idx_from_argno(argno));
}

static int check_outgoing_stack_args(struct bpf_verifier_env *env, struct bpf_func_state *caller,
				     int nargs, const char *callee_name, const struct btf *btf,
				     const struct btf_param *args)
{
	int i, spi;

	for (i = MAX_BPF_FUNC_REG_ARGS; i < nargs; i++) {
		spi = i - MAX_BPF_FUNC_REG_ARGS;
		if (spi >= caller->out_stack_arg_cnt ||
		    caller->stack_arg_regs[spi].type == NOT_INIT) {
			const char *arg_name = NULL;

			if (args && args[i].name_off)
				arg_name = btf_name_by_offset(btf, args[i].name_off);
			verbose(env, "callee expects %d args, stack arg%d is not initialized\n",
				nargs, spi + 1);
			bpf_diag_stack_arg_uninit(env, env->insn_idx, nargs, spi,
						  callee_name, arg_name);
			return -EFAULT;
		}
	}

	return 0;
}

static struct bpf_reg_state *get_func_arg_reg(struct bpf_func_state *caller,
					      struct bpf_reg_state *regs, int arg)
{
	if (arg < MAX_BPF_FUNC_REG_ARGS)
		return &regs[arg + 1];

	return &caller->stack_arg_regs[arg - MAX_BPF_FUNC_REG_ARGS];
}

static int check_map_access_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				 int off, int size, enum bpf_access_type type)
{
	struct bpf_map *map = reg->map_ptr;
	u32 cap = bpf_map_flags_to_cap(map);

	if (type == BPF_WRITE && !(cap & BPF_MAP_CAN_WRITE)) {
		verbose(env, "write into map forbidden, value_size=%d off=%lld size=%d\n",
			map->value_size, reg_smin(reg) + off, size);
		return -EACCES;
	}

	if (type == BPF_READ && !(cap & BPF_MAP_CAN_READ)) {
		verbose(env, "read from map forbidden, value_size=%d off=%lld size=%d\n",
			map->value_size, reg_smin(reg) + off, size);
		return -EACCES;
	}

	return 0;
}

/* check read/write into memory region (e.g., map value, ringbuf sample, etc) */
static int __check_mem_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
			      int off, int size, u32 mem_size,
			      bool zero_size_allowed)
{
	bool size_ok = size > 0 || (size == 0 && zero_size_allowed);

	if (off >= 0 && size_ok && (u64)off + size <= mem_size)
		return 0;

	switch (reg->type) {
	case PTR_TO_MAP_KEY:
		verbose(env, "invalid access to map key, key_size=%d off=%d size=%d\n",
			mem_size, off, size);
		break;
	case PTR_TO_MAP_VALUE:
		verbose(env, "invalid access to map value, value_size=%d off=%d size=%d\n",
			mem_size, off, size);
		break;
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
	case PTR_TO_PACKET_END:
		verbose(env, "invalid access to packet, off=%d size=%d, %s(id=%d,off=%d,r=%d)\n",
			off, size, reg_arg_name(env, argno), reg->id, off, mem_size);
		break;
	case PTR_TO_CTX:
		verbose(env, "invalid access to context, ctx_size=%d off=%d size=%d\n",
			mem_size, off, size);
		break;
	case PTR_TO_MEM:
	default:
		verbose(env, "invalid access to memory, mem_size=%u off=%d size=%d\n",
			mem_size, off, size);
	}

	return -EACCES;
}

/* check read/write into a memory region with possible variable offset */
static int check_mem_region_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
				   int off, int size, u32 mem_size,
				   bool zero_size_allowed)
{
	const char *proof = "";
	const char *start;
	s64 max_start, max_end;
	int err;

	/* We may have adjusted the register pointing to memory region, so we
	 * need to try adding each of min_value and max_value to off
	 * to make sure our theoretical access will be safe.
	 *
	 * 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(reg) < 0 &&
	    (reg_smin(reg) == S64_MIN ||
	     (off + reg_smin(reg) != (s64)(s32)(off + reg_smin(reg))) ||
	      reg_smin(reg) + off < 0)) {
		verbose(env, "%s min value is negative, either use unsigned index or do a if (index >=0) check.\n",
			reg_arg_name(env, argno));
		err = -EACCES;
		if (bpf_diag_enabled(env)) {
			start = bpf_diag_fmt_s64_sum(env, reg_smin(reg), off);
			proof = bpf_diag_fmt(
				env, "the minimal bound for a memory access is a negative value: %s",
				start);
		}
		goto report_error;
	}

	err = __check_mem_access(env, reg, argno, reg_smin(reg) + off, size,
				 mem_size, zero_size_allowed);
	if (err) {
		verbose(env, "%s min value is outside of the allowed memory range\n",
			reg_arg_name(env, argno));
		if (bpf_diag_enabled(env)) {
			start = bpf_diag_fmt_s64_sum(env, reg_smin(reg), off);
			proof = bpf_diag_fmt(
				env, "the minimal bound for a memory access is %s and is outside of the object of size %u",
				start, mem_size);
		}
		goto report_error;
	}

	/* 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(reg) + off could overflow, treat that as unbounded too.
	 */
	if (reg_umax(reg) >= BPF_MAX_VAR_OFF) {
		verbose(env, "%s unbounded memory access, make sure to bounds check any such access\n",
			reg_arg_name(env, argno));
		err = -EACCES;
		if (bpf_diag_enabled(env))
			proof = bpf_diag_fmt(
				env, "the maximal bound for a memory access is %llu and exceeds maximum allowed offset of %u",
				reg_umax(reg), BPF_MAX_VAR_OFF);
		goto report_error;
	}

	err = __check_mem_access(env, reg, argno, reg_umax(reg) + off, size,
				 mem_size, zero_size_allowed);
	if (err) {
		verbose(env, "%s max value is outside of the allowed memory range\n",
			reg_arg_name(env, argno));
		if (bpf_diag_enabled(env)) {
			max_start = (s64)reg_umax(reg) + off;
			max_end = max_start + size;
			proof = bpf_diag_fmt(
				env, "the maximal bound for a memory access is %lld: start %lld + access_size %d, beyond object_size %u",
				max_end, max_start, size, mem_size);
		}
		goto report_error;
	}

	return 0;

report_error:
	bpf_diag_mem_bounds(env, env->insn_idx, reg_from_argno(argno),
			    reg_arg_name(env, argno), reg_type_str(env, reg->type), proof,
			    off, size, mem_size, reg);
	return err;
}

static int __check_ptr_off_reg(struct bpf_verifier_env *env,
			       const struct bpf_reg_state *reg, argno_t argno,
			       bool fixed_off_ok)
{
	/* Access to this pointer-typed register or passing it to a helper
	 * is only allowed in its original, unmodified form.
	 */

	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "variable %s access var_off=%s disallowed\n",
			reg_type_str(env, reg->type), tn_buf);
		return -EACCES;
	}

	if (reg_smin(reg) < 0) {
		verbose(env, "negative offset %s ptr %s off=%lld disallowed\n",
			reg_type_str(env, reg->type), reg_arg_name(env, argno), reg->var_off.value);
		return -EACCES;
	}

	if (!fixed_off_ok && reg->var_off.value != 0) {
		verbose(env, "dereference of modified %s ptr %s off=%lld disallowed\n",
			reg_type_str(env, reg->type), reg_arg_name(env, argno), reg->var_off.value);
		bpf_diag_invalid_deref(env, env->insn_idx, reg_from_argno(argno),
				       reg_arg_name(env, argno), reg,
					      BPF_DIAG_DEREF_MODIFIED_PTR, reg->var_off.value);
		return -EACCES;
	}

	return 0;
}

static int check_ptr_off_reg(struct bpf_verifier_env *env,
		             const struct bpf_reg_state *reg, int regno)
{
	return __check_ptr_off_reg(env, reg, argno_from_reg(regno), false);
}

static int map_kptr_match_type(struct bpf_verifier_env *env,
			       struct btf_field *kptr_field,
			       struct bpf_reg_state *reg, u32 regno)
{
	const char *targ_name = btf_type_name(kptr_field->kptr.btf, kptr_field->kptr.btf_id);
	int perm_flags;
	const char *reg_name = "";

	if (base_type(reg->type) != PTR_TO_BTF_ID)
		goto bad_type;

	if (btf_is_kernel(reg->btf)) {
		perm_flags = PTR_MAYBE_NULL | PTR_TRUSTED | MEM_RCU;

		/* Only unreferenced case accepts untrusted pointers */
		if (kptr_field->type == BPF_KPTR_UNREF)
			perm_flags |= PTR_UNTRUSTED;
	} else {
		perm_flags = PTR_MAYBE_NULL | MEM_ALLOC;
		if (kptr_field->type == BPF_KPTR_PERCPU)
			perm_flags |= MEM_PERCPU;
	}

	if (type_flag(reg->type) & ~perm_flags)
		goto bad_type;

	/*
	 * A BPF_KPTR_PERCPU field is read back as MEM_PERCPU, so the value
	 * stored in it must carry the same flag.
	 */
	if ((kptr_field->type == BPF_KPTR_PERCPU) != !!(reg->type & MEM_PERCPU))
		goto bad_type;

	/* We need to verify reg->type and reg->btf, before accessing reg->btf */
	reg_name = btf_type_name(reg->btf, reg->btf_id);

	/* For ref_ptr case, release function check should ensure we get one
	 * referenced PTR_TO_BTF_ID, and that its fixed offset is 0. For the
	 * normal store of unreferenced kptr, we must ensure var_off is zero.
	 * Since ref_ptr cannot be accessed directly by BPF insns, check for
	 * reg->id is not needed here.
	 */
	if (__check_ptr_off_reg(env, reg, argno_from_reg(regno), true))
		return -EACCES;

	/* A full type match is needed, as BTF can be vmlinux, module or prog BTF, and
	 * we also need to take into account the reg->var_off.
	 *
	 * We want to support cases like:
	 *
	 * struct foo {
	 *         struct bar br;
	 *         struct baz bz;
	 * };
	 *
	 * struct foo *v;
	 * v = func();	      // PTR_TO_BTF_ID
	 * val->foo = v;      // reg->var_off is zero, btf and btf_id match type
	 * val->bar = &v->br; // reg->var_off is still zero, but we need to retry with
	 *                    // first member type of struct after comparison fails
	 * val->baz = &v->bz; // reg->var_off is non-zero, so struct needs to be walked
	 *                    // to match type
	 *
	 * In the kptr_ref case, check_func_arg_reg_off already ensures reg->var_off
	 * is zero. We must also ensure that btf_struct_ids_match does not walk
	 * the struct to match type against first member of struct, i.e. reject
	 * second case from above. Hence, when type is BPF_KPTR_REF, we set
	 * strict mode to true for type match.
	 */
	if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->var_off.value,
				  kptr_field->kptr.btf, kptr_field->kptr.btf_id,
				  kptr_field->type != BPF_KPTR_UNREF,
				  !type_is_alloc(reg->type)))
		goto bad_type;
	return 0;
bad_type:
	verbose(env, "invalid kptr access, R%d type=%s%s ", regno,
		reg_type_str(env, reg->type), reg_name);
	verbose(env, "expected=%s%s", reg_type_str(env, PTR_TO_BTF_ID), targ_name);
	if (kptr_field->type == BPF_KPTR_UNREF)
		verbose(env, " or %s%s\n", reg_type_str(env, PTR_TO_BTF_ID | PTR_UNTRUSTED),
			targ_name);
	else
		verbose(env, "\n");
	return -EINVAL;
}

static bool in_sleepable(struct bpf_verifier_env *env)
{
	return env->cur_state->in_sleepable;
}

/* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock()
 * can dereference RCU protected pointers and result is PTR_TRUSTED.
 */
static bool in_rcu_cs(struct bpf_verifier_env *env)
{
	return env->cur_state->active_rcu_locks ||
	       env->cur_state->active_preempt_locks ||
	       env->cur_state->active_locks ||
	       env->cur_state->active_irq_id ||
	       !in_sleepable(env);
}

/* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */
BTF_SET_START(rcu_protected_types)
#ifdef CONFIG_NET
BTF_ID(struct, prog_test_ref_kfunc)
#endif
#ifdef CONFIG_CGROUPS
BTF_ID(struct, cgroup)
#endif
#ifdef CONFIG_BPF_JIT
BTF_ID(struct, bpf_cpumask)
#endif
BTF_ID(struct, task_struct)
#ifdef CONFIG_BPF_CRYPTO
BTF_ID(struct, bpf_crypto_ctx)
#endif
#ifdef CONFIG_INET
BTF_ID(struct, bpf_ksock)
#endif
BTF_SET_END(rcu_protected_types)

static bool rcu_protected_object(const struct btf *btf, u32 btf_id)
{
	if (!btf_is_kernel(btf))
		return true;
	return btf_id_set_contains(&rcu_protected_types, btf_id);
}

static struct btf_record *kptr_pointee_btf_record(struct btf_field *kptr_field)
{
	struct btf_struct_meta *meta;

	if (btf_is_kernel(kptr_field->kptr.btf))
		return NULL;

	meta = btf_find_struct_meta(kptr_field->kptr.btf,
				    kptr_field->kptr.btf_id);

	return meta ? meta->record : NULL;
}

static bool rcu_safe_kptr(const struct btf_field *field)
{
	const struct btf_field_kptr *kptr = &field->kptr;

	return field->type == BPF_KPTR_PERCPU ||
	       (field->type == BPF_KPTR_REF && rcu_protected_object(kptr->btf, kptr->btf_id));
}

static u32 btf_ld_kptr_type(struct bpf_verifier_env *env, struct btf_field *kptr_field)
{
	struct btf_record *rec;
	u32 ret;

	ret = PTR_MAYBE_NULL;
	if (rcu_safe_kptr(kptr_field) && in_rcu_cs(env)) {
		ret |= MEM_RCU;
		if (kptr_field->type == BPF_KPTR_PERCPU)
			ret |= MEM_PERCPU;
		else if (!btf_is_kernel(kptr_field->kptr.btf))
			ret |= MEM_ALLOC;

		rec = kptr_pointee_btf_record(kptr_field);
		if (rec && btf_record_has_field(rec, BPF_GRAPH_NODE))
			ret |= NON_OWN_REF;
	} else {
		ret |= PTR_UNTRUSTED;
	}

	return ret;
}

static int mark_uptr_ld_reg(struct bpf_verifier_env *env, u32 regno,
			    struct btf_field *field)
{
	struct bpf_reg_state *reg;
	const struct btf_type *t;

	t = btf_type_by_id(field->kptr.btf, field->kptr.btf_id);
	mark_reg_known_zero(env, cur_regs(env), regno);
	reg = reg_state(env, regno);
	reg->type = PTR_TO_MEM | PTR_MAYBE_NULL;
	reg->mem_size = t->size;
	reg->id = ++env->id_gen;

	return 0;
}

static int check_map_kptr_access(struct bpf_verifier_env *env,
				 int value_regno, int insn_idx,
				 struct btf_field *kptr_field)
{
	struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
	int class = BPF_CLASS(insn->code);
	struct bpf_reg_state *val_reg;
	int ret;

	/* Things we already checked for in check_map_access and caller:
	 *  - Reject cases where variable offset may touch kptr
	 *  - size of access (must be BPF_DW)
	 *  - tnum_is_const(reg->var_off)
	 *  - kptr_field->offset == off + reg->var_off.value
	 */
	/* Only BPF_[LDX,STX,ST] | BPF_MEM | BPF_DW is supported */
	if (BPF_MODE(insn->code) != BPF_MEM) {
		verbose(env, "kptr in map can only be accessed using BPF_MEM instruction mode\n");
		return -EACCES;
	}

	/* We only allow loading referenced kptr, since it will be marked as
	 * untrusted, similar to unreferenced kptr.
	 */
	if (class != BPF_LDX &&
	    (kptr_field->type == BPF_KPTR_REF || kptr_field->type == BPF_KPTR_PERCPU)) {
		verbose(env, "store to referenced kptr disallowed\n");
		return -EACCES;
	}
	if (class != BPF_LDX && kptr_field->type == BPF_UPTR) {
		verbose(env, "store to uptr disallowed\n");
		return -EACCES;
	}

	if (class == BPF_LDX) {
		if (kptr_field->type == BPF_UPTR)
			return mark_uptr_ld_reg(env, value_regno, kptr_field);

		/* We can simply mark the value_regno receiving the pointer
		 * value from map as PTR_TO_BTF_ID, with the correct type.
		 */
		ret = mark_btf_ld_reg(env, cur_regs(env), value_regno, PTR_TO_BTF_ID,
				      kptr_field->kptr.btf, kptr_field->kptr.btf_id,
				      btf_ld_kptr_type(env, kptr_field));
		if (ret < 0)
			return ret;
	} else if (class == BPF_STX) {
		val_reg = reg_state(env, value_regno);
		if (bpf_register_is_null(val_reg)) {
			/*
			 * This store is valid only because the scalar is known to be
			 * zero. Mark it precise so another scalar cannot be pruned
			 * against this state.
			 */
			return mark_chain_precision(env, value_regno);
		}
		if (map_kptr_match_type(env, kptr_field, val_reg, value_regno))
			return -EACCES;
	} else if (class == BPF_ST) {
		if (insn->imm) {
			verbose(env, "BPF_ST imm must be 0 when storing to kptr at off=%u\n",
				kptr_field->offset);
			return -EACCES;
		}
	} else {
		verbose(env, "kptr in map can only be accessed using BPF_LDX/BPF_STX/BPF_ST\n");
		return -EACCES;
	}
	return 0;
}

/*
 * Return the size of the memory region accessible from a pointer to map value.
 * For INSN_ARRAY maps whole bpf_insn_array->ips array is accessible.
 */
static u32 map_mem_size(const struct bpf_map *map)
{
	if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY)
		return map->max_entries * sizeof(long);

	return map->value_size;
}

/* check read/write into a map element with possible variable offset */
static int check_map_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
			    int off, int size, bool zero_size_allowed,
			    enum bpf_access_src src)
{
	struct bpf_map *map = reg->map_ptr;
	u32 mem_size = map_mem_size(map);
	struct btf_record *rec;
	int err, i;

	err = check_mem_region_access(env, reg, argno, off, size, mem_size, zero_size_allowed);
	if (err)
		return err;

	if (IS_ERR_OR_NULL(map->record))
		return 0;
	rec = map->record;
	for (i = 0; i < rec->cnt; i++) {
		struct btf_field *field = &rec->fields[i];
		u32 p = field->offset;

		/* If any part of a field  can be touched by load/store, reject
		 * this program. To check that [x1, x2) overlaps with [y1, y2),
		 * it is sufficient to check x1 < y2 && y1 < x2.
		 */
		if (reg_smin(reg) + off < p + field->size &&
		    p < reg_umax(reg) + off + size) {
			switch (field->type) {
			case BPF_KPTR_UNREF:
			case BPF_KPTR_REF:
			case BPF_KPTR_PERCPU:
			case BPF_UPTR:
				if (src != ACCESS_DIRECT) {
					verbose(env, "%s cannot be accessed indirectly by helper\n",
						btf_field_type_name(field->type));
					return -EACCES;
				}
				if (!tnum_is_const(reg->var_off)) {
					verbose(env, "%s access cannot have variable offset\n",
						btf_field_type_name(field->type));
					return -EACCES;
				}
				if (p != off + reg->var_off.value) {
					verbose(env, "%s access misaligned expected=%u off=%llu\n",
						btf_field_type_name(field->type),
						p, off + reg->var_off.value);
					return -EACCES;
				}
				if (size != bpf_size_to_bytes(BPF_DW)) {
					verbose(env, "%s access size must be BPF_DW\n",
						btf_field_type_name(field->type));
					return -EACCES;
				}
				break;
			default:
				verbose(env, "%s cannot be accessed directly by load/store\n",
					btf_field_type_name(field->type));
				return -EACCES;
			}
		}
	}
	return 0;
}

static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
			       const struct bpf_call_arg_meta *meta,
			       enum bpf_access_type t)
{
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);

	switch (prog_type) {
	/* Program types only with direct read access go here! */
	case BPF_PROG_TYPE_LWT_IN:
	case BPF_PROG_TYPE_LWT_OUT:
	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
	case BPF_PROG_TYPE_SK_REUSEPORT:
	case BPF_PROG_TYPE_FLOW_DISSECTOR:
	case BPF_PROG_TYPE_CGROUP_SKB:
		if (t == BPF_WRITE)
			return false;
		fallthrough;

	/* Program types with direct read + write access go here! */
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
	case BPF_PROG_TYPE_XDP:
	case BPF_PROG_TYPE_LWT_XMIT:
	case BPF_PROG_TYPE_SK_SKB:
	case BPF_PROG_TYPE_SK_MSG:
		if (meta && !meta->btf && meta->func_id)
			return meta->fn->pkt_access;

		if (t == BPF_WRITE)
			env->seen_direct_write = true;
		return true;

	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
		if (t == BPF_WRITE)
			env->seen_direct_write = true;

		return true;

	default:
		return false;
	}
}

static int check_packet_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno, int off,
			       int size, bool zero_size_allowed)
{
	int err;

	if (reg->range < 0) {
		verbose(env, "%s offset is outside of the packet\n", reg_arg_name(env, argno));
		return -EINVAL;
	}

	err = check_mem_region_access(env, reg, argno, off, size, reg->range, zero_size_allowed);
	if (err)
		return err;

	/* __check_mem_access has made sure "off + size - 1" is within u16.
	 * reg_umax(reg) can't be bigger than MAX_PACKET_OFF which is 0xffff,
	 * otherwise find_good_pkt_pointers would have refused to set range info
	 * that __check_mem_access would have rejected this pkt access.
	 * Therefore, "off + reg_umax(reg) + size - 1" won't overflow u32.
	 */
	env->prog->aux->max_pkt_offset =
		max_t(u32, env->prog->aux->max_pkt_offset,
		      off + reg_umax(reg) + size - 1);

	return 0;
}

static bool is_var_ctx_off_allowed(struct bpf_prog *prog)
{
	return resolve_prog_type(prog) == BPF_PROG_TYPE_SYSCALL;
}

/* 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, struct bpf_insn_access_aux *info)
{
	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.
		 */
		if (base_type(info->reg_type) == PTR_TO_BTF_ID) {
			if (info->ref_id &&
			    !find_reference_state(env->cur_state, info->ref_id)) {
				verbose(env, "invalid bpf_context access off=%d. Reference may already be released\n",
					off);
				return -EACCES;
			}
		} else {
			env->insn_aux_data[insn_idx].ctx_field_size = info->ctx_field_size;
		}
		/* remember the offset of last byte accessed in ctx */
		if (env->prog->aux->max_ctx_offset < off + size)
			env->prog->aux->max_ctx_offset = off + size;
		return 0;
	}

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

static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, struct bpf_reg_state *reg, argno_t argno,
			    int off, int access_size, enum bpf_access_type t,
			    struct bpf_insn_access_aux *info)
{
	/*
	 * Program types that don't rewrite ctx accesses can safely
	 * dereference ctx pointers with fixed offsets.
	 */
	bool var_off_ok = is_var_ctx_off_allowed(env->prog);
	bool fixed_off_ok = !env->ops->convert_ctx_access;
	int err;

	if (var_off_ok)
		err = check_mem_region_access(env, reg, argno, off, access_size, U16_MAX, false);
	else
		err = __check_ptr_off_reg(env, reg, argno, fixed_off_ok);
	if (err)
		return err;
	off += reg_umax(reg);

	err = __check_ctx_access(env, insn_idx, off, access_size, t, info);
	if (err)
		verbose_linfo(env, insn_idx, "; ");
	return err;
}

static int check_flow_keys_access(struct bpf_verifier_env *env,
				  struct bpf_reg_state *reg, argno_t argno,
				  int off, int size)
{
	/* Only a constant offset is allowed here; fold it into off. */
	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "%s invalid variable offset to flow keys: off=%d, var_off=%s\n",
			reg_arg_name(env, argno), off, tn_buf);
		return -EACCES;
	}
	off += reg->var_off.value;

	if (size < 0 || off < 0 ||
	    (u64)off + size > sizeof(struct bpf_flow_keys)) {
		verbose(env, "invalid access to flow keys off=%d size=%d\n",
			off, size);
		return -EACCES;
	}
	return 0;
}

static int check_sock_access(struct bpf_verifier_env *env, int insn_idx,
			     struct bpf_reg_state *reg, argno_t argno, int off, int size,
			     enum bpf_access_type t)
{
	struct bpf_insn_access_aux info = {};
	bool valid;

	if (reg_smin(reg) < 0) {
		verbose(env, "%s min value is negative, either use unsigned index or do a if (index >=0) check.\n",
			reg_arg_name(env, argno));
		return -EACCES;
	}

	switch (reg->type) {
	case PTR_TO_SOCK_COMMON:
		valid = bpf_sock_common_is_valid_access(off, size, t, &info);
		break;
	case PTR_TO_SOCKET:
		valid = bpf_sock_is_valid_access(off, size, t, &info);
		break;
	case PTR_TO_TCP_SOCK:
		valid = bpf_tcp_sock_is_valid_access(off, size, t, &info);
		break;
	case PTR_TO_XDP_SOCK:
		valid = bpf_xdp_sock_is_valid_access(off, size, t, &info);
		break;
	default:
		valid = false;
	}

	if (valid) {
		env->insn_aux_data[insn_idx].ctx_field_size =
			info.ctx_field_size;
		return 0;
	}

	verbose(env, "%s invalid %s access off=%d size=%d\n",
		reg_arg_name(env, argno), reg_type_str(env, reg->type), off, size);

	return -EACCES;
}

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

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

	return reg->type == PTR_TO_CTX;
}

static bool is_sk_reg(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = reg_state(env, regno);

	return type_is_sk_pointer(reg->type);
}

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

	return type_is_pkt_pointer(reg->type);
}

static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = reg_state(env, regno);

	/* Separate to is_ctx_reg() since we still want to allow BPF_ST here. */
	return reg->type == PTR_TO_FLOW_KEYS;
}

static bool is_arena_reg(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = reg_state(env, regno);

	return reg->type == PTR_TO_ARENA;
}

/*
 * There are no address spaces in Rust, addresses of arena are plain numbers.
 * When the program is loaded with BPF_F_ARENA_SCALAR and has an arena a load or
 * a store through a number is an access to arena at the low 32 bits of it,
 * like the access through PTR_TO_ARENA is. The register stays a number.
 */
static bool is_arena_scalar(struct bpf_verifier_env *env, int regno)
{
	const struct bpf_reg_state *reg = reg_state(env, regno);

	return reg->type == SCALAR_VALUE && env->arena_scalar && env->prog->aux->arena;
}

static bool is_load_acq_unsafe(struct bpf_verifier_env *env, int regno,
			       struct bpf_insn *insn)
{
	const struct bpf_reg_state *reg = reg_state(env, regno);

	/*
	 * A BPF_LOAD_ACQ is not rewritten to a BPF_PROBE_MEM load by the
	 * verifier, unlike a regular BPF_LDX. The JIT would emit a plain load
	 * with no exception table entry, so a fault (e.g. NULL deref) crashes
	 * the kernel instead of being handled. Reject the source pointer types
	 * that would have needed that protection, the remaining ones stay
	 * allowed.
	 */
	return insn->imm == BPF_LOAD_ACQ && bpf_may_fault_on_deref(reg->type);
}

/* Return false if @regno contains a pointer whose type isn't supported for
 * atomic instruction @insn.
 */
static bool atomic_ptr_type_ok(struct bpf_verifier_env *env, int regno,
			       struct bpf_insn *insn)
{
	if (is_ctx_reg(env, regno))
		return false;
	if (is_pkt_reg(env, regno))
		return false;
	if (is_flow_key_reg(env, regno))
		return false;
	if (is_sk_reg(env, regno))
		return false;
	if (is_arena_reg(env, regno) || is_arena_scalar(env, regno))
		return bpf_jit_supports_insn(insn, true);
	if (is_load_acq_unsafe(env, regno, insn))
		return false;
	return true;
}

static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
#ifdef CONFIG_NET
	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
	[PTR_TO_SOCK_COMMON] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
	[PTR_TO_TCP_SOCK] = &btf_sock_ids[BTF_SOCK_TYPE_TCP],
#endif
	[CONST_PTR_TO_MAP] = btf_bpf_map_id,
};

static bool is_trusted_reg_type(struct bpf_verifier_env *env,
				const struct bpf_reg_state *reg,
				enum bpf_reg_type type)
{
	/* A referenced register is always trusted. */
	if (reg_is_referenced(env, reg))
		return true;

	/* Types listed in the reg2btf_ids are always trusted */
	if (reg2btf_ids[base_type(type)] &&
	    !bpf_type_has_unsafe_modifiers(type))
		return true;

	/* If a register is not referenced, it is trusted if it has the
	 * MEM_ALLOC or PTR_TRUSTED type modifiers, and no others. Some of the
	 * other type modifiers may be safe, but we elect to take an opt-in
	 * approach here as some (e.g. PTR_UNTRUSTED and PTR_MAYBE_NULL) are
	 * not.
	 *
	 * Eventually, we should make PTR_TRUSTED the single source of truth
	 * for whether a register is trusted.
	 */
	return type_flag(type) & BPF_REG_TRUSTED_MODIFIERS &&
	       !bpf_type_has_unsafe_modifiers(type);
}

static bool is_trusted_reg(struct bpf_verifier_env *env,
			   const struct bpf_reg_state *reg)
{
	return is_trusted_reg_type(env, reg, reg->type);
}

static bool is_rcu_reg(const struct bpf_reg_state *reg)
{
	return reg->type & MEM_RCU;
}

static void clear_trusted_flags(enum bpf_type_flag *flag)
{
	*flag &= ~(BPF_REG_TRUSTED_MODIFIERS | MEM_RCU);
}

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 + 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 size %d\n",
			ip_align, tn_buf, 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(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 size %d\n",
			pointer_desc, tn_buf, 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_FLOW_KEYS:
		pointer_desc = "flow keys ";
		break;
	case PTR_TO_MAP_KEY:
		pointer_desc = "key ";
		break;
	case PTR_TO_MAP_VALUE:
		pointer_desc = "value ";
		if (reg->map_ptr->map_type == BPF_MAP_TYPE_INSN_ARRAY)
			strict = true;
		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_fixed_off()
		 * and check_stack_read_fixed_off() relies on stack accesses being
		 * aligned.
		 */
		strict = true;
		break;
	case PTR_TO_SOCKET:
		pointer_desc = "sock ";
		break;
	case PTR_TO_SOCK_COMMON:
		pointer_desc = "sock_common ";
		break;
	case PTR_TO_TCP_SOCK:
		pointer_desc = "tcp_sock ";
		break;
	case PTR_TO_XDP_SOCK:
		pointer_desc = "xdp_sock ";
		break;
	case PTR_TO_ARENA:
		return 0;
	default:
		break;
	}
	return check_generic_ptr_alignment(env, reg, pointer_desc, off, size,
					   strict);
}

static enum priv_stack_mode bpf_enable_priv_stack(struct bpf_prog *prog)
{
	if (!bpf_jit_supports_private_stack())
		return NO_PRIV_STACK;

	/* bpf_prog_check_recur() checks all prog types that use bpf trampoline
	 * while kprobe/tp/perf_event/raw_tp don't use trampoline hence checked
	 * explicitly.
	 */
	switch (prog->type) {
	case BPF_PROG_TYPE_KPROBE:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_PERF_EVENT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
		return PRIV_STACK_ADAPTIVE;
	case BPF_PROG_TYPE_TRACING:
	case BPF_PROG_TYPE_LSM:
	case BPF_PROG_TYPE_STRUCT_OPS:
		if (prog->aux->priv_stack_requested || bpf_prog_check_recur(prog))
			return PRIV_STACK_ADAPTIVE;
		fallthrough;
	default:
		break;
	}

	return NO_PRIV_STACK;
}

static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth)
{
	if (env->prog->jit_requested)
		return round_up(stack_depth, 16);

	/* round up to 32-bytes, since this is granularity
	 * of interpreter stack size
	 */
	return round_up(max_t(u32, stack_depth, 1), 32);
}

/* temporary state used for call frame depth calculation */
struct bpf_subprog_call_depth_info {
	int ret_insn; /* caller instruction where we return to. */
	int caller; /* caller subprogram idx */
	int frame; /* # of consecutive static call stack frames on top of stack */
	int callx_insn; /* callx instruction whose callees are being walked */
	int callx_next; /* next callee of callx_insn to walk */
	bool via_callx; /* the subprogram is entered via callx */
};

/* 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.
 */
static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx,
					 struct bpf_subprog_call_depth_info *dinfo,
					 bool priv_stack_supported)
{
	struct bpf_subprog_info *subprog = env->subprog_info;
	struct bpf_insn *insn = env->prog->insnsi;
	int depth = 0, frame = 0, i, subprog_end, subprog_depth;
	bool tail_call_reachable = false;
	int total;
	int tmp;

	/* no caller idx */
	dinfo[idx].caller = -1;
	dinfo[idx].via_callx = false;

	i = subprog[idx].start;
	if (!priv_stack_supported)
		subprog[idx].priv_stack_mode = NO_PRIV_STACK;
process_func:
	dinfo[idx].callx_insn = -1;
	if (subprog[idx].has_ld_abs) {
		for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) {
			if (subprog[tmp].is_cb) {
				verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n");
				return -EINVAL;
			}
		}
	}

	/* protect against potential stack overflow that might happen when
	 * bpf2bpf calls get combined with tailcalls. Limit the caller's stack
	 * depth for such case down to 256 so that the worst case scenario
	 * would result in 8k stack size (32 which is tailcall limit * 256 =
	 * 8k).
	 *
	 * To get the idea what might happen, see an example:
	 * func1 -> sub rsp, 128
	 *  subfunc1 -> sub rsp, 256
	 *  tailcall1 -> add rsp, 256
	 *   func2 -> sub rsp, 192 (total stack size = 128 + 192 = 320)
	 *   subfunc2 -> sub rsp, 64
	 *   subfunc22 -> sub rsp, 128
	 *   tailcall2 -> add rsp, 128
	 *    func3 -> sub rsp, 32 (total stack size 128 + 192 + 64 + 32 = 416)
	 *
	 * tailcall will unwind the current stack frame but it will not get rid
	 * of caller's stack as shown on the example above.
	 */
	if (idx && subprog[idx].has_tail_call && depth >= 256) {
		verbose(env,
			"tail_calls are not allowed when call stack of previous frames is %d bytes. Too large\n",
			depth);
		return -EACCES;
	}

	subprog_depth = round_up_stack_depth(env, subprog[idx].stack_depth);
	if (IS_ENABLED(CONFIG_X86_64) && subprog[idx].stack_arg_cnt) {
		/* x86-64 uses R9 for both private stack frame pointer and arg6. */
		subprog[idx].priv_stack_mode = NO_PRIV_STACK;
	} else if (priv_stack_supported) {
		/* Request private stack support only if the subprog stack
		 * depth is no less than BPF_PRIV_STACK_MIN_SIZE. This is to
		 * avoid jit penalty if the stack usage is small.
		 */
		if (subprog[idx].priv_stack_mode == PRIV_STACK_UNKNOWN &&
		    subprog_depth >= BPF_PRIV_STACK_MIN_SIZE)
			subprog[idx].priv_stack_mode = PRIV_STACK_ADAPTIVE;
	}

	if (subprog[idx].priv_stack_mode == PRIV_STACK_ADAPTIVE) {
		if (subprog_depth > env->max_stack_depth)
			env->max_stack_depth = subprog_depth;
		if (subprog_depth > env->stack_limit) {
			verbose(env, "stack size of subprog %d is %d. Too large\n",
				idx, subprog_depth);
			return -EACCES;
		}
	} else {
		depth += subprog_depth;
		if (depth > env->max_stack_depth)
			env->max_stack_depth = depth;
		if (depth > env->stack_limit) {
			total = 0;
			for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller)
				total++;

			verbose(env, "combined stack size of %d calls is %d. Too large\n",
				total, depth);
			return -EACCES;
		}
	}
continue_func:
	subprog_end = subprog[idx + 1].start;
	for (; i < subprog_end; i++) {
		int next_insn, sidx;

		if (bpf_pseudo_kfunc_call(insn + i) && !insn[i].off &&
		    bpf_is_throw_kfunc(insn + i)) {
			bool err = false;

			for (tmp = idx; tmp >= 0 && !err; tmp = dinfo[tmp].caller) {
				if (subprog[tmp].is_cb) {
					err = true;
					break;
				}
			}
			if (!err)
				continue;
			verbose(env,
				"bpf_throw kfunc (insn %d) cannot be called from callback subprog %d\n",
				i, idx);
			return -EINVAL;
		}

		if (bpf_is_callx(insn + i) || bpf_calls_callback(env, i)) {
			/*
			 * Walk the callees and the callbacks recorded by
			 * the main verification pass one by one, returning to
			 * this insn after each.
			 */
			if (dinfo[idx].callx_insn != i) {
				dinfo[idx].callx_insn = i;
				dinfo[idx].callx_next = 0;
			}
			sidx = next_callx_callee(env, idx, dinfo[idx].callx_next);
			if (sidx < 0)
				continue;
			dinfo[idx].callx_next = sidx + 1;
			dinfo[idx].ret_insn = i;
			next_insn = subprog[sidx].start;
		} else if (bpf_pseudo_call(insn + i) || bpf_pseudo_func(insn + i)) {
			/* find the callee */
			next_insn = i + insn[i].imm + 1;
			sidx = bpf_find_subprog(env, next_insn);
			if (verifier_bug_if(sidx < 0, env, "callee not found at insn %d", next_insn))
				return -EFAULT;
			if (subprog[sidx].is_async_cb) {
				/* async callbacks don't increase bpf prog stack size unless called directly */
				if (!bpf_pseudo_call(insn + i))
					continue;
				if (subprog[sidx].is_exception_cb) {
					verbose(env, "insn %d cannot call exception cb directly", i);
					return -EINVAL;
				}
			}
			/* remember insn to return to */
			dinfo[idx].ret_insn = i + 1;
		} else {
			continue;
		}

		/*
		 * sort_subprogs_topo() tolerates cycles in the call graph that
		 * go through the address of a function being taken, since it
		 * doesn't know what it is taken for. Such cycle is a recursion
		 * unless it's an async callback, which are skipped above.
		 * The main verification pass limits the depth of the recursion,
		 * but it doesn't follow calls of global functions.
		 */
		for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) {
			if (tmp != sidx)
				continue;
			verbose(env, "recursive call from %s() to %s()\n",
				bpf_subprog_name(env, idx), bpf_subprog_name(env, sidx));
			bpf_diag_program_structure(
				env, i, "recursive subprogram call",
				"Rewrite the recursion as an explicit bounded loop, or split the logic so subprogram calls do not form a cycle.",
				"This call or callback would make the subprogram call graph recursive. "
				"The verifier requires a finite, acyclic call graph so it can bound stack depth and analysis.");
			return -EINVAL;
		}

		/* store caller info for after we return from callee */
		dinfo[idx].frame = frame;

		/* push caller idx into callee's dinfo */
		dinfo[sidx].caller = idx;
		dinfo[sidx].via_callx = bpf_is_callx(insn + i);

		i = next_insn;

		idx = sidx;
		if (!priv_stack_supported)
			subprog[idx].priv_stack_mode = NO_PRIV_STACK;

		/* sync tail_call_reachable with callee state on entry */
		tail_call_reachable = subprog[idx].has_tail_call;

		frame = bpf_subprog_is_global(env, idx) ? 0 : frame + 1;
		if (frame >= MAX_CALL_FRAMES) {
			verbose(env, "the call stack of %d frames is too deep !\n",
				frame);
			return -E2BIG;
		}
		goto process_func;
	}
	/* if tail call got detected across bpf2bpf calls then mark each of the
	 * currently present subprog frames as tail call reachable subprogs;
	 * this info will be utilized by JIT so that we will be preserving the
	 * tail call counter throughout bpf2bpf calls combined with tailcalls
	 */
	if (tail_call_reachable) {
		for (tmp = idx; tmp >= 0; tmp = dinfo[tmp].caller) {
			if (subprog[tmp].is_cb) {
				verbose(env, "cannot tail call within callback\n");
				return -EINVAL;
			}
			if (subprog[tmp].stack_arg_cnt) {
				verbose(env, "tail_calls are not allowed in programs with stack args\n");
				return -EINVAL;
			}
			/*
			 * JITs pass tail call counter in a register that is
			 * not available when the callee is called via callx.
			 */
			if (dinfo[tmp].via_callx) {
				verbose(env, "tail_calls are not allowed in functions called via callx\n");
				return -EINVAL;
			}
			subprog[tmp].tail_call_reachable = true;
		}
	} else if (!idx && subprog[0].has_tail_call && subprog[0].stack_arg_cnt) {
		verbose(env, "tail_calls are not allowed in programs with stack args\n");
		return -EINVAL;
	}

	if (subprog[0].tail_call_reachable)
		env->prog->aux->tail_call_reachable = true;

	/* end of for() loop means the last insn of the 'subprog'
	 * was reached. Doesn't matter whether it was JA or EXIT
	 */
	if (frame == 0 && dinfo[idx].caller < 0)
		return 0;
	if (subprog[idx].priv_stack_mode != PRIV_STACK_ADAPTIVE)
		depth -= round_up_stack_depth(env, subprog[idx].stack_depth);

	/* pop caller idx from callee */
	idx = dinfo[idx].caller;

	/* retrieve caller state from its frame */
	frame = dinfo[idx].frame;
	i = dinfo[idx].ret_insn;

	/* reset tail_call_reachable to the parent's actual state */
	tail_call_reachable = subprog[idx].tail_call_reachable;

	goto continue_func;
}

static int check_max_stack_depth(struct bpf_verifier_env *env)
{
	enum priv_stack_mode priv_stack_mode = PRIV_STACK_UNKNOWN;
	struct bpf_subprog_call_depth_info *dinfo;
	struct bpf_subprog_info *si = env->subprog_info;
	bool priv_stack_supported;
	int ret;

	dinfo = kvzalloc_objs(*dinfo, env->subprog_cnt, GFP_KERNEL_ACCOUNT);
	if (!dinfo)
		return -ENOMEM;

	for (int i = 0; i < env->subprog_cnt; i++) {
		if (si[i].has_tail_call) {
			priv_stack_mode = NO_PRIV_STACK;
			break;
		}
	}

	if (priv_stack_mode == PRIV_STACK_UNKNOWN)
		priv_stack_mode = bpf_enable_priv_stack(env->prog);

	/* All async_cb subprogs use normal kernel stack. If a particular
	 * subprog appears in both main prog and async_cb subtree, that
	 * subprog will use normal kernel stack to avoid potential nesting.
	 * The reverse subprog traversal ensures when main prog subtree is
	 * checked, the subprogs appearing in async_cb subtrees are already
	 * marked as using normal kernel stack, so stack size checking can
	 * be done properly.
	 */
	for (int i = env->subprog_cnt - 1; i >= 0; i--) {
		if (!i || si[i].is_async_cb) {
			priv_stack_supported = !i && priv_stack_mode == PRIV_STACK_ADAPTIVE;
			ret = check_max_stack_depth_subprog(env, i, dinfo,
					priv_stack_supported);
			if (ret < 0) {
				kvfree(dinfo);
				return ret;
			}
		}
	}

	for (int i = 0; i < env->subprog_cnt; i++) {
		if (si[i].priv_stack_mode == PRIV_STACK_ADAPTIVE) {
			env->prog->aux->jits_use_priv_stack = true;
			break;
		}
	}

	kvfree(dinfo);

	return 0;
}

static int __check_buffer_access(struct bpf_verifier_env *env,
				 const char *buf_info,
				 const struct bpf_reg_state *reg,
				 argno_t argno, int off, int size,
				 u32 *access_end)
{
	s64 start;

	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env,
			"%s invalid variable buffer offset: off=%d, var_off=%s\n",
			reg_arg_name(env, argno), off, tn_buf);
		return -EACCES;
	}

	start = (s64)reg->var_off.value + off;
	if (start < 0) {
		verbose(env,
			"%s invalid negative %s buffer offset: off=%d, var_off=%lld\n",
			reg_arg_name(env, argno), buf_info, off, (s64)reg->var_off.value);
		return -EACCES;
	}

	*access_end = start + size;
	return 0;
}

static int check_tp_buffer_access(struct bpf_verifier_env *env,
				  const struct bpf_reg_state *reg,
				  argno_t argno, int off, int size)
{
	u32 access_end;
	int err;

	err = __check_buffer_access(env, "tracepoint", reg, argno, off, size, &access_end);
	if (err)
		return err;

	env->prog->aux->max_tp_access = max(access_end, env->prog->aux->max_tp_access);

	return 0;
}

static int check_buffer_access(struct bpf_verifier_env *env,
			       const struct bpf_reg_state *reg,
			       argno_t argno, int off, int size,
			       bool zero_size_allowed,
			       u32 *max_access, bool write)
{
	const char *buf_info = type_is_rdonly_mem(reg->type) ? "rdonly" : "rdwr";
	struct bpf_prog_aux *aux = env->prog->aux;
	u32 access_end;
	int err;

	err = __check_buffer_access(env, buf_info, reg, argno, off, size, &access_end);
	if (err)
		return err;

	*max_access = max(access_end, *max_access);
	if (write && size) {
		if (!aux->max_rdwr_write || access_end - size < aux->min_rdwr_write)
			aux->min_rdwr_write = access_end - size;
		aux->max_rdwr_write = max(access_end, aux->max_rdwr_write);
	}

	return 0;
}

/* BPF architecture zero extends alu32 ops into 64-bit registesr */
static void zext_32_to_64(struct bpf_reg_state *reg)
{
	reg_step_check_unsigned(reg, 32);
	reg->var_off = tnum_subreg(reg->var_off);
	reg_set_urange64(reg, reg_u32_min(reg), reg_u32_max(reg));
}

/* 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 = (1ULL << (size * 8)) - 1;

	reg_step_check_unsigned(reg, size * 8);

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

	/* fix arithmetic bounds */
	if ((reg_umin(reg) & ~mask) == (reg_umax(reg) & ~mask))
		reg_set_urange64(reg, reg_umin(reg) & mask, reg_umax(reg) & mask);
	else
		reg_set_urange64(reg, 0, mask);

	/* If size is smaller than 32bit register the 32bit register
	 * values are also truncated so we push 64-bit bounds into
	 * 32-bit bounds. Above were truncated < 32-bits already.
	 */
	if (size < 4)
		__mark_reg32_unbounded(reg);

	reg_bounds_sync(reg);
}

static void set_sext64_default_val(struct bpf_reg_state *reg, int size)
{
	if (size == 1) {
		reg_set_srange64(reg, S8_MIN, S8_MAX);
		reg_set_srange32(reg, S8_MIN, S8_MAX);
	} else if (size == 2) {
		reg_set_srange64(reg, S16_MIN, S16_MAX);
		reg_set_srange32(reg, S16_MIN, S16_MAX);
	} else {
		/* size == 4 */
		reg_set_srange64(reg, S32_MIN, S32_MAX);
		reg_set_srange32(reg, S32_MIN, S32_MAX);
	}
	reg->var_off = tnum_unknown;
}

static void coerce_reg_to_size_sx(struct bpf_reg_state *reg, int size)
{
	s64 init_s64_max, init_s64_min, s64_max, s64_min, u64_cval;
	u64 top_smax_value, top_smin_value;
	u64 num_bits = size * 8;
	s64 limit = 1LL << (num_bits - 1);

	/* If every value fits the signed N-bit range sign extension is a noop. */
	if (reg_smin(reg) >= -limit && reg_smax(reg) < limit)
		return;

	/* See commen at reg_step_check_unsigned(). */
	reg_step_reset(reg);

	if (tnum_is_const(reg->var_off)) {
		u64_cval = reg->var_off.value;
		if (size == 1)
			reg->var_off = tnum_const((s8)u64_cval);
		else if (size == 2)
			reg->var_off = tnum_const((s16)u64_cval);
		else
			/* size == 4 */
			reg->var_off = tnum_const((s32)u64_cval);

		u64_cval = reg->var_off.value;
		reg->r64 = cnum64_from_urange(u64_cval, u64_cval);
		reg->r32 = cnum32_from_urange((u32)u64_cval, (u32)u64_cval);
		return;
	}

	top_smax_value = ((u64)reg_smax(reg) >> num_bits) << num_bits;
	top_smin_value = ((u64)reg_smin(reg) >> num_bits) << num_bits;

	if (top_smax_value != top_smin_value)
		goto out;

	/* find the s64_min and s64_min after sign extension */
	if (size == 1) {
		init_s64_max = (s8)reg_smax(reg);
		init_s64_min = (s8)reg_smin(reg);
	} else if (size == 2) {
		init_s64_max = (s16)reg_smax(reg);
		init_s64_min = (s16)reg_smin(reg);
	} else {
		init_s64_max = (s32)reg_smax(reg);
		init_s64_min = (s32)reg_smin(reg);
	}

	s64_max = max(init_s64_max, init_s64_min);
	s64_min = min(init_s64_max, init_s64_min);

	/* both of s64_max/s64_min positive or negative */
	if ((s64_max >= 0) == (s64_min >= 0)) {
		reg_set_srange64(reg, s64_min, s64_max);
		reg_set_srange32(reg, s64_min, s64_max);
		reg->var_off = tnum_range(s64_min, s64_max);
		return;
	}

out:
	set_sext64_default_val(reg, size);
}

static void set_sext32_default_val(struct bpf_reg_state *reg, int size)
{
	if (size == 1)
		reg_set_srange32(reg, S8_MIN, S8_MAX);
	else
		/* size == 2 */
		reg_set_srange32(reg, S16_MIN, S16_MAX);
	reg->var_off = tnum_subreg(tnum_unknown);
}

static void coerce_subreg_to_size_sx(struct bpf_reg_state *reg, int size)
{
	s32 init_s32_max, init_s32_min, s32_max, s32_min, u32_val;
	u32 top_smax_value, top_smin_value;
	u32 num_bits = size * 8;

	/*
	 * If value fits the non-negative half of the signed N-bit range,
	 * sign extension is a noop.
	 */
	if (reg_umax(reg) < (1ULL << (num_bits - 1)))
		return;

	/* See comment at reg_step_check_unsigned(). */
	reg_step_reset(reg);

	if (tnum_is_const(reg->var_off)) {
		u32_val = reg->var_off.value;
		if (size == 1)
			reg->var_off = tnum_const((s8)u32_val);
		else
			reg->var_off = tnum_const((s16)u32_val);

		u32_val = reg->var_off.value;
		reg_set_srange32(reg, u32_val, u32_val);
		return;
	}

	top_smax_value = ((u32)reg_s32_max(reg) >> num_bits) << num_bits;
	top_smin_value = ((u32)reg_s32_min(reg) >> num_bits) << num_bits;

	if (top_smax_value != top_smin_value)
		goto out;

	/* find the s32_min and s32_min after sign extension */
	if (size == 1) {
		init_s32_max = (s8)reg_s32_max(reg);
		init_s32_min = (s8)reg_s32_min(reg);
	} else {
		/* size == 2 */
		init_s32_max = (s16)reg_s32_max(reg);
		init_s32_min = (s16)reg_s32_min(reg);
	}
	s32_max = max(init_s32_max, init_s32_min);
	s32_min = min(init_s32_max, init_s32_min);

	if ((s32_min >= 0) == (s32_max >= 0)) {
		reg_set_srange32(reg, s32_min, s32_max);
		reg->var_off = tnum_subreg(tnum_range(s32_min, s32_max));
		return;
	}

out:
	set_sext32_default_val(reg, size);
}

bool bpf_map_is_rdonly(const struct bpf_map *map)
{
	/* A map is considered read-only if the following condition are true:
	 *
	 * 1) BPF program side cannot change any of the map content. The
	 *    BPF_F_RDONLY_PROG flag is throughout the lifetime of a map
	 *    and was set at map creation time.
	 * 2) The map value(s) have been initialized from user space by a
	 *    loader and then "frozen", such that no new map update/delete
	 *    operations from syscall side are possible for the rest of
	 *    the map's lifetime from that point onwards.
	 * 3) Any parallel/pending map update/delete operations from syscall
	 *    side have been completed. Only after that point, it's safe to
	 *    assume that map value(s) are immutable.
	 */
	return (map->map_flags & BPF_F_RDONLY_PROG) &&
	       READ_ONCE(map->frozen) &&
	       !bpf_map_write_active(map);
}

int bpf_map_direct_read(struct bpf_map *map, int off, int size, u64 *val,
			bool is_ldsx)
{
	void *ptr;
	u64 addr;
	int err;

	if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY || map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY)
		return -EINVAL;
	err = map->ops->map_direct_value_addr(map, &addr, off);
	if (err)
		return err;
	ptr = (void *)(long)addr + off;

	switch (size) {
	case sizeof(u8):
		*val = is_ldsx ? (s64)*(s8 *)ptr : (u64)*(u8 *)ptr;
		break;
	case sizeof(u16):
		*val = is_ldsx ? (s64)*(s16 *)ptr : (u64)*(u16 *)ptr;
		break;
	case sizeof(u32):
		*val = is_ldsx ? (s64)*(s32 *)ptr : (u64)*(u32 *)ptr;
		break;
	case sizeof(u64):
		*val = *(u64 *)ptr;
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

static int cmp_func_ptrs(const void *_a, const void *_b)
{
	const struct bpf_func_ptr *a = _a, *b = _b;

	if (a->map != b->map)
		return a->map < b->map ? -1 : 1;
	if (a->map_off != b->map_off)
		return a->map_off < b->map_off ? -1 : 1;
	return 0;
}

/* Find the first pointer to a function at or after 'off' in the value of 'map' */
static u32 func_ptr_lower_bound(struct bpf_verifier_env *env, const struct bpf_map *map, u64 off)
{
	u32 l = 0, r = env->func_ptr_cnt, m;
	struct bpf_func_ptr *p;

	while (l < r) {
		m = l + (r - l) / 2;
		p = &env->func_ptrs[m];
		if (p->map < map || (p->map == map && p->map_off < off))
			l = m + 1;
		else
			r = m;
	}
	return l;
}

/*
 * Return pointers to functions that overlap with 'size' bytes at offset 'off'
 * of the value of 'map' and their number in 'cnt'.
 */
struct bpf_func_ptr *bpf_map_range_func_ptrs(struct bpf_verifier_env *env,
					     const struct bpf_map *map,
					     u64 off, u64 size, u32 *cnt)
{
	u32 first, last;

	*cnt = 0;
	if (!env->func_ptr_cnt || !size)
		return NULL;

	/* a pointer that starts up to 7 bytes before 'off' overlaps too */
	first = func_ptr_lower_bound(env, map, off >= sizeof(u64) ? off - sizeof(u64) + 1 : 0);
	last = func_ptr_lower_bound(env, map, off + size);
	if (first >= last)
		return NULL;

	*cnt = last - first;
	return &env->func_ptrs[first];
}

/* Return all pointers to functions in the value of 'map' */
struct bpf_func_ptr *bpf_map_func_ptrs(struct bpf_verifier_env *env,
				       const struct bpf_map *map, u32 *cnt)
{
	return bpf_map_range_func_ptrs(env, map, 0, (u64)map->value_size, cnt);
}

/* instructions [off, off + len) replaced the instruction at 'off' */
void bpf_adjust_func_ptrs(struct bpf_verifier_env *env, u32 off, u32 len)
{
	struct bpf_func_ptr *p;
	u32 i;

	if (len <= 1)
		return;

	for (i = 0; i < env->func_ptr_cnt; i++) {
		p = &env->func_ptrs[i];
		if (p->xlated_off <= off || p->xlated_off == BPF_FUNC_PTR_DELETED)
			continue;
		p->xlated_off += len - 1;
	}
}

/*
 * Instructions [off, off + len) are about to be removed. It's called before
 * the starts of subprogs are adjusted. A subprog is gone when all of its
 * instructions are. Otherwise, e.g. when its first instruction is a nop,
 * it starts where the removed instructions did.
 */
void bpf_adjust_func_ptrs_after_remove(struct bpf_verifier_env *env, u32 off, u32 len)
{
	struct bpf_func_ptr *p;
	int subprog;
	u32 i;

	for (i = 0; i < env->func_ptr_cnt; i++) {
		p = &env->func_ptrs[i];
		if (p->xlated_off < off || p->xlated_off == BPF_FUNC_PTR_DELETED)
			continue;
		if (p->xlated_off >= off + len) {
			p->xlated_off -= len;
			continue;
		}
		subprog = bpf_find_subprog(env, p->xlated_off);
		if (subprog > 0 && env->subprog_info[subprog + 1].start > off + len)
			p->xlated_off = off;
		else
			p->xlated_off = BPF_FUNC_PTR_DELETED;
	}
}

#define BTF_TYPE_SAFE_RCU(__type)  __PASTE(__type, __safe_rcu)
#define BTF_TYPE_SAFE_RCU_OR_NULL(__type)  __PASTE(__type, __safe_rcu_or_null)
#define BTF_TYPE_SAFE_TRUSTED(__type)  __PASTE(__type, __safe_trusted)
#define BTF_TYPE_SAFE_TRUSTED_OR_NULL(__type)  __PASTE(__type, __safe_trusted_or_null)

/*
 * Allow list few fields as RCU trusted or full trusted.
 * This logic doesn't allow mix tagging and will be removed once GCC supports
 * btf_type_tag.
 */

/* RCU trusted: these fields are trusted in RCU CS and never NULL */
BTF_TYPE_SAFE_RCU(struct task_struct) {
	const cpumask_t *cpus_ptr;
	struct css_set __rcu *cgroups;
	struct task_struct __rcu *real_parent;
	struct task_struct *group_leader;
};

BTF_TYPE_SAFE_RCU(struct cgroup) {
	/* cgrp->kn is always accessible as documented in kernel/cgroup/cgroup.c */
	struct kernfs_node *kn;
};

BTF_TYPE_SAFE_RCU(struct css_set) {
	struct cgroup *dfl_cgrp;
};

BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state) {
	struct cgroup *cgroup;
};

/* RCU trusted: these fields are trusted in RCU CS and can be NULL */
BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct) {
	struct file __rcu *exe_file;
#ifdef CONFIG_MEMCG
	struct task_struct __rcu *owner;
#endif
};

/* skb->sk, req->sk are not RCU protected, but we mark them as such
 * because bpf prog accessible sockets are SOCK_RCU_FREE.
 */
BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff) {
	struct sock *sk;
};

BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock) {
	struct sock *sk;
};

/* full trusted: these fields are trusted even outside of RCU CS and never NULL */
BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta) {
	struct seq_file *seq;
};

BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task) {
	struct bpf_iter_meta *meta;
	struct task_struct *task;
};

BTF_TYPE_SAFE_TRUSTED(struct linux_binprm) {
	struct file *file;
};

BTF_TYPE_SAFE_TRUSTED(struct file) {
	struct inode *f_inode;
};

/*
 * The pointer fields in the sched_ext ops argument containers are pinned by the
 * callers for the duration of the ops calls and are never NULL.
 */
BTF_TYPE_SAFE_TRUSTED(struct scx_init_task_args) {
#ifdef CONFIG_EXT_GROUP_SCHED
	struct cgroup *cgroup;
#endif
};

BTF_TYPE_SAFE_TRUSTED(struct scx_cpu_release_args) {
	struct task_struct *task;
};

BTF_TYPE_SAFE_TRUSTED(struct scx_sub_attach_args) {
	struct sched_ext_ops *ops;
};

BTF_TYPE_SAFE_TRUSTED(struct scx_sub_detach_args) {
	struct sched_ext_ops *ops;
};

BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry) {
	struct inode *d_inode;
};

BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct linux_binprm) {
	struct mm_struct *mm;
};

BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket) {
	struct sock *sk;
};

BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct) {
	struct mm_struct *vm_mm;
	struct file *vm_file;
};

static bool type_is_rcu(struct bpf_verifier_env *env,
			struct bpf_reg_state *reg,
			const char *field_name, u32 btf_id)
{
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct task_struct));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct css_set));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU(struct cgroup_subsys_state));

	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu");
}

static bool type_is_rcu_or_null(struct bpf_verifier_env *env,
				struct bpf_reg_state *reg,
				const char *field_name, u32 btf_id)
{
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct mm_struct));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct sk_buff));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_RCU_OR_NULL(struct request_sock));

	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_rcu_or_null");
}

static bool type_is_trusted(struct bpf_verifier_env *env,
			    struct bpf_reg_state *reg,
			    const char *field_name, u32 btf_id)
{
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter_meta));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct bpf_iter__task));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct linux_binprm));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct file));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct scx_init_task_args));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct scx_cpu_release_args));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct scx_sub_attach_args));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED(struct scx_sub_detach_args));

	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id, "__safe_trusted");
}

static bool type_is_trusted_or_null(struct bpf_verifier_env *env,
				    struct bpf_reg_state *reg,
				    const char *field_name, u32 btf_id)
{
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct socket));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct dentry));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct linux_binprm));
	BTF_TYPE_EMIT(BTF_TYPE_SAFE_TRUSTED_OR_NULL(struct vm_area_struct));

	return btf_nested_type_is_trusted(&env->log, reg, field_name, btf_id,
					  "__safe_trusted_or_null");
}

/*
 * The member holds the kernel address of arena memory, which the rewritten
 * load turns into an arena pointer, see arena_member_fixup(). NULL needs no
 * tracking, PTR_TO_ARENA covers it.
 */
static int check_arena_member_load(struct bpf_verifier_env *env, struct bpf_reg_state *regs,
				   int value_regno, enum bpf_type_flag flag, const char *tname,
				   const char *field_name)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[env->insn_idx];
	struct bpf_insn *insn;

	/* a helper reading the member as bytes needs no rewrite */
	if (value_regno < 0)
		return 0;
	if (!env->prog->aux->arena) {
		verbose(env,
			"arena pointer member %s of struct %s requires a program with an associated arena\n",
			field_name, tname);
		return -EINVAL;
	}
	/* only a plain load or an acquire load is rewritten */
	insn = &env->prog->insnsi[env->insn_idx];
	if (BPF_CLASS(insn->code) != BPF_LDX &&
	    !(insn->code == (BPF_STX | BPF_ATOMIC | BPF_DW) && insn->imm == BPF_LOAD_ACQ)) {
		verbose(env,
			"arena pointer member %s of struct %s can only be read with a plain or an acquire load\n",
			field_name, tname);
		return -EACCES;
	}

	aux->arena_member = true;
	if (flag & PTR_MAYBE_NULL)
		aux->arena_member_nullable = true;
	mark_reg_unknown(env, regs, value_regno);
	regs[value_regno].type = PTR_TO_ARENA;
	return 0;
}

static int check_ptr_to_btf_access(struct bpf_verifier_env *env,
				   struct bpf_reg_state *regs, struct bpf_reg_state *reg,
				   argno_t argno, int off, int size,
				   enum bpf_access_type atype,
				   int value_regno)
{
	const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
	const char *tname = btf_name_by_offset(reg->btf, t->name_off);
	const char *field_name = NULL;
	enum bpf_type_flag flag = 0;
	u32 btf_id = 0;
	s64 min_off;
	int ret;

	if (!env->allow_ptr_leaks) {
		verbose(env,
			"'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
			tname);
		return -EPERM;
	}
	if (!env->prog->gpl_compatible && btf_is_kernel(reg->btf)) {
		verbose(env,
			"Cannot access kernel 'struct %s' from non-GPL compatible program\n",
			tname);
		return -EINVAL;
	}

	if (check_add_overflow(reg_smin(reg), off, &min_off)) {
		verbose(env,
			"%s is ptr_%s access, offset computation overflows: register's minimal offset is %lld, instruction offset is %d\n",
			reg_arg_name(env, argno), tname, reg_smin(reg), off);
		return -EACCES;
	}

	if (min_off < 0) {
		verbose(env,
			"%s is ptr_%s invalid negative access: off=%lld\n",
			reg_arg_name(env, argno), tname, min_off);
		return -EACCES;
	}

	if (reg->type & MEM_USER) {
		verbose(env,
			"%s is ptr_%s access user memory\n",
			reg_arg_name(env, argno), tname);
		return -EACCES;
	}

	if (reg->type & MEM_PERCPU) {
		verbose(env,
			"%s is ptr_%s access percpu memory\n",
			reg_arg_name(env, argno), tname);
		return -EACCES;
	}

	if (atype != BPF_READ && bpf_may_fault_on_deref(reg->type)) {
		verbose(env, "only read is supported\n");
		return -EACCES;
	}

	if (env->ops->btf_struct_access && !type_is_alloc(reg->type) && atype == BPF_WRITE) {
		if (!tnum_is_const(reg->var_off)) {
			char tn_buf[48];

			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
			verbose(env,
				"%s is ptr_%s invalid variable offset: off=%d, var_off=%s\n",
				reg_arg_name(env, argno), tname, off, tn_buf);
			return -EACCES;
		}

		off += reg->var_off.value;

		if (!btf_is_kernel(reg->btf)) {
			verifier_bug(env, "reg->btf must be kernel btf");
			return -EFAULT;
		}
		ret = env->ops->btf_struct_access(&env->log, reg, off, size);
		if (ret < 0)
			verbose(env,
				"%s cannot write into ptr_%s at off=%d size=%d\n",
				reg_arg_name(env, argno), tname, off, size);
	} else {
		/* Writes are permitted with default btf_struct_access for
		 * program allocated objects (which always have id > 0).
		 */
		if (atype != BPF_READ && !type_is_ptr_alloc_obj(reg->type)) {
			verbose(env, "only read is supported\n");
			return -EACCES;
		}

		/*
		 * A fault-prone allocated object may still be read through a
		 * BPF_PROBE_MEM load after its lifetime protection ends. Writes
		 * through such pointers were rejected above.
		 */
		if (type_is_alloc(reg->type) && !bpf_may_fault_on_deref(reg->type) &&
		    !type_is_non_owning_ref(reg->type) &&
		    !(reg->type & MEM_RCU) && !reg_is_referenced(env, reg)) {
			verifier_bug(env, "allocated object must have a referenced id");
			return -EFAULT;
		}

		ret = btf_struct_access(&env->log, reg, off, size, atype, &btf_id, &flag, &field_name);
	}

	if (ret < 0)
		return ret;

	if (ret == PTR_TO_ARENA)
		return check_arena_member_load(env, regs, value_regno, flag, tname, field_name);

	if (ret != PTR_TO_BTF_ID) {
		/* just mark; */

	} else if (type_flag(reg->type) & PTR_UNTRUSTED) {
		/* If this is an untrusted pointer, all pointers formed by walking it
		 * also inherit the untrusted flag.
		 */
		flag = PTR_UNTRUSTED;

	} else if (is_trusted_reg(env, reg) || is_rcu_reg(reg)) {
		/* By default any pointer obtained from walking a trusted pointer is no
		 * longer trusted, unless the field being accessed has explicitly been
		 * marked as inheriting its parent's state of trust (either full or RCU).
		 * For example:
		 * 'cgroups' pointer is untrusted if task->cgroups dereference
		 * happened in a sleepable program outside of bpf_rcu_read_lock()
		 * section. In a non-sleepable program it's trusted while in RCU CS (aka MEM_RCU).
		 * Note bpf_rcu_read_unlock() converts MEM_RCU pointers to PTR_UNTRUSTED.
		 *
		 * A regular RCU-protected pointer with __rcu tag can also be deemed
		 * trusted if we are in an RCU CS. Such pointer can be NULL.
		 */
		if (type_is_trusted(env, reg, field_name, btf_id)) {
			flag |= PTR_TRUSTED;
		} else if (type_is_trusted_or_null(env, reg, field_name, btf_id)) {
			flag |= PTR_TRUSTED | PTR_MAYBE_NULL;
		} else if (in_rcu_cs(env) && !type_may_be_null(reg->type)) {
			if (type_is_rcu(env, reg, field_name, btf_id)) {
				/* ignore __rcu tag and mark it MEM_RCU */
				flag |= MEM_RCU;
			} else if (flag & MEM_RCU ||
				   type_is_rcu_or_null(env, reg, field_name, btf_id)) {
				/* __rcu tagged pointers can be NULL */
				flag |= MEM_RCU | PTR_MAYBE_NULL;

				/* We always trust them */
				if (type_is_rcu_or_null(env, reg, field_name, btf_id) &&
				    flag & PTR_UNTRUSTED)
					flag &= ~PTR_UNTRUSTED;
			} else if (flag & (MEM_PERCPU | MEM_USER)) {
				/* keep as-is */
			} else {
				/* walking unknown pointers yields old deprecated PTR_TO_BTF_ID */
				clear_trusted_flags(&flag);
			}
		} else {
			/*
			 * If not in RCU CS or MEM_RCU pointer can be NULL then
			 * aggressively mark as untrusted otherwise such
			 * pointers will be plain PTR_TO_BTF_ID without flags
			 * and will be allowed to be passed into helpers for
			 * compat reasons.
			 */
			flag = PTR_UNTRUSTED;
		}
	} else {
		/* Old compat. Deprecated */
		clear_trusted_flags(&flag);
	}

	/*
	 * A __nullable member only matters where NULL would otherwise be
	 * assumed away, which is anywhere but on a plain or an untrusted
	 * pointer: those are probed on a dereference, which tolerates NULL, and
	 * the BTF_TYPE_SAFE_*_OR_NULL lists never applied to them either. A
	 * per-CPU pointer counts, per_cpu_ptr() does not check for NULL.
	 */
	if (bpf_may_fault_on_deref(PTR_TO_BTF_ID | (flag & ~PTR_MAYBE_NULL)))
		flag &= ~PTR_MAYBE_NULL;

	if (atype == BPF_READ && value_regno >= 0) {
		ret = mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id, flag);
		if (ret < 0)
			return ret;
	}

	return 0;
}

static int check_ptr_to_map_access(struct bpf_verifier_env *env,
				   struct bpf_reg_state *regs, struct bpf_reg_state *reg,
				   argno_t argno, int off, int size,
				   enum bpf_access_type atype,
				   int value_regno)
{
	struct bpf_map *map = reg->map_ptr;
	struct bpf_reg_state map_reg;
	enum bpf_type_flag flag = 0;
	const struct btf_type *t;
	const char *tname;
	u32 btf_id;
	int ret;

	if (!btf_vmlinux) {
		verbose(env, "map_ptr access not supported without CONFIG_DEBUG_INFO_BTF\n");
		return -ENOTSUPP;
	}

	if (!map->ops->map_btf_id || !*map->ops->map_btf_id) {
		verbose(env, "map_ptr access not supported for map type %d\n",
			map->map_type);
		return -ENOTSUPP;
	}

	t = btf_type_by_id(btf_vmlinux, *map->ops->map_btf_id);
	tname = btf_name_by_offset(btf_vmlinux, t->name_off);

	if (!env->allow_ptr_leaks) {
		verbose(env,
			"'struct %s' access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
			tname);
		return -EPERM;
	}

	if (off < 0) {
		verbose(env, "%s is %s invalid negative access: off=%d\n",
			reg_arg_name(env, argno), tname, off);
		return -EACCES;
	}

	if (atype != BPF_READ) {
		verbose(env, "only read from %s is supported\n", tname);
		return -EACCES;
	}

	/* Simulate access to a PTR_TO_BTF_ID */
	memset(&map_reg, 0, sizeof(map_reg));
	ret = mark_btf_ld_reg(env, &map_reg, 0, PTR_TO_BTF_ID,
			      btf_vmlinux, *map->ops->map_btf_id, 0);
	if (ret < 0)
		return ret;
	ret = btf_struct_access(&env->log, &map_reg, off, size, atype, &btf_id, &flag, NULL);
	if (ret < 0)
		return ret;

	if (value_regno >= 0) {
		ret = mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id, flag);
		if (ret < 0)
			return ret;
	}

	return 0;
}

/*
 * Check that the stack access at the given offset is within bounds. The
 * maximum valid offset is -1.
 *
 * The minimum valid offset is -env->stack_limit for writes, and
 * -state->allocated_stack for reads.
 */
static int check_stack_slot_within_bounds(struct bpf_verifier_env *env,
                                          s64 off,
                                          struct bpf_func_state *state,
                                          enum bpf_access_type t)
{
	int min_valid_off;

	if (t == BPF_WRITE || env->allow_uninit_stack)
		min_valid_off = -(int)env->stack_limit;
	else
		min_valid_off = -state->allocated_stack;

	if (off < min_valid_off || off > -1)
		return -EACCES;
	return 0;
}

/* Check that the stack access at 'regno + off' falls within the maximum stack
 * bounds.
 *
 * 'off' includes `regno->offset`, but not its dynamic part (if any).
 */
static int check_stack_access_within_bounds(
		struct bpf_verifier_env *env, struct bpf_reg_state *reg,
		argno_t argno, int off, int access_size,
		enum bpf_access_type type)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	s64 min_off, max_off;
	int err;
	char *err_extra;

	if (type == BPF_READ)
		err_extra = " read from";
	else
		err_extra = " write to";

	if (tnum_is_const(reg->var_off)) {
		min_off = (s64)reg->var_off.value + off;
		max_off = min_off + access_size;
	} else {
		if (reg_smax(reg) >= BPF_MAX_VAR_OFF ||
		    reg_smin(reg) <= -BPF_MAX_VAR_OFF) {
			verbose(env, "invalid unbounded variable-offset%s stack %s\n",
				err_extra, reg_arg_name(env, argno));
			return -EACCES;
		}
		min_off = reg_smin(reg) + off;
		max_off = reg_smax(reg) + off + access_size;
	}

	err = check_stack_slot_within_bounds(env, min_off, state, type);
	if (!err && max_off > 0)
		err = -EINVAL; /* out of stack access into non-negative offsets */
	if (!err && access_size < 0)
		/* access_size should not be negative (or overflow an int); others checks
		 * along the way should have prevented such an access.
		 */
		err = -EFAULT; /* invalid negative access size; integer overflow? */

	if (err) {
		if (tnum_is_const(reg->var_off)) {
			verbose(env, "invalid%s stack %s off=%lld size=%d\n",
				err_extra, reg_arg_name(env, argno), min_off, access_size);
		} else {
			char tn_buf[48];

			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
			verbose(env, "invalid variable-offset%s stack %s var_off=%s off=%d size=%d\n",
				err_extra, reg_arg_name(env, argno), tn_buf, off, access_size);
		}
		return err;
	}

	/*
	 * Every stack access passes through here, including buffers passed to
	 * helpers and kfuncs and accesses into a caller's frame, so check the
	 * fastcall contract of the frame that owns the slots once for all of
	 * them. Zero-sized accesses touch no stack and keep the rewrite enabled.
	 */
	if (access_size)
		check_fastcall_stack_contract(env, state, env->insn_idx, min_off);

	/* Note that there is no stack access with offset zero, so the needed stack
	 * size is -min_off, not -min_off+1.
	 */
	return bpf_grow_stack_state(env, state, -min_off /* size */);
}

static bool get_func_retval_range(struct bpf_prog *prog,
				  struct bpf_retval_range *range)
{
	if (prog->type == BPF_PROG_TYPE_LSM &&
		prog->expected_attach_type == BPF_LSM_MAC &&
		!bpf_lsm_get_retval_range(prog, range)) {
		return true;
	}
	return false;
}

static void add_scalar_to_reg(struct bpf_reg_state *dst_reg, s64 val)
{
	struct bpf_reg_state fake_reg;

	if (!val)
		return;

	fake_reg.type = SCALAR_VALUE;
	__mark_reg_known(&fake_reg, val);

	scalar_step_add(dst_reg, dst_reg, &fake_reg);
	scalar32_min_max_add(dst_reg, &fake_reg);
	scalar_min_max_add(dst_reg, &fake_reg);
	dst_reg->var_off = tnum_add(dst_reg->var_off, fake_reg.var_off);

	reg_bounds_sync(dst_reg);
}

/* there is no support for callx in the interpreter */
static int require_callx_jit(struct bpf_verifier_env *env)
{
	if (!env->prog->jit_requested) {
		verbose(env, "JIT is required to use callx\n");
		return -EOPNOTSUPP;
	}
	if (!bpf_jit_supports_callx()) {
		verbose(env, "JIT doesn't support callx\n");
		return -EOPNOTSUPP;
	}
	env->prog->jit_required = true;
	return 0;
}

static void mark_reg_func_ptr(struct bpf_verifier_env *env, struct bpf_reg_state *regs,
			      int regno, int subprog)
{
	mark_reg_known_zero(env, regs, regno);
	regs[regno].type = PTR_TO_FUNC;
	regs[regno].subprogno = subprog;
}

/* a read from a table of functions branches into that many states at most */
#define BPF_MAX_FUNC_PTR_TARGETS 64
/* and that many pointers at most are next to what is read at variable offset */
#define BPF_MAX_FUNC_PTR_RANGE 4096

/* Count up to 'limit' offsets in [min_off, max_off] that the read is possible at */
static u32 count_read_offsets(struct tnum offs, u64 min_off, u64 max_off, u32 limit)
{
	u64 o = min_off, next;
	u32 cnt = 0;

	if (!tnum_in(offs, tnum_const(o))) {
		next = tnum_step(offs, o);
		if (next <= o)
			return 0;
		o = next;
	}
	while (o <= max_off && cnt < limit) {
		cnt++;
		next = tnum_step(offs, o);
		if (next <= o)
			break;
		o = next;
	}
	return cnt;
}

/*
 * A read from a frozen read-only map that has pointers to functions, see
 * resolve_func_ptrs(). The bounds and var_off of the offset tell where the read
 * is possible at, e.g. var_off is the stride of the elements of an array.
 * A read of exactly one pointer yields PTR_TO_FUNC. When the offset is variable
 * and only pointers can be read, which is how an element of a table of
 * functions is loaded, the verification continues with each of them. Other
 * reads that overlap with a pointer are rejected, because their result is not
 * known until the program is jitted.
 *
 * Return -ENOENT if there are no pointers to functions in the bytes that are read.
 */
static int check_func_ptr_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int off,
			       int size, int value_regno)
{
	u64 min_off = reg_umin(reg) + off, max_off = reg_umax(reg) + off;
	struct tnum offs = tnum_add(reg->var_off, tnum_const(off));
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_map *map = reg->map_ptr;
	struct bpf_verifier_state *branch;
	int subprog, targets[BPF_MAX_FUNC_PTR_TARGETS];
	struct bpf_func_ptr *ptrs;
	u32 i, cnt, n = 0;
	u64 o, lo, hi;
	int err;

	ptrs = bpf_map_range_func_ptrs(env, map, min_off, max_off - min_off + size, &cnt);
	if (!ptrs)
		return -ENOENT;
	if (cnt > BPF_MAX_FUNC_PTR_RANGE)
		goto overlap;

	for (i = 0; i < cnt; i++) {
		/* the offsets at which the read overlaps with the pointer */
		lo = ptrs[i].map_off >= size ? ptrs[i].map_off - size + 1 : 0;
		lo = max(lo, min_off);
		hi = min(ptrs[i].map_off + sizeof(u64) - 1, max_off);
		for (o = lo; o <= hi; o++) {
			if (!tnum_in(offs, tnum_const(o)))
				continue;
			if (o != ptrs[i].map_off || size != sizeof(u64) || value_regno < 0)
				goto overlap;
			if (n == BPF_MAX_FUNC_PTR_TARGETS) {
				verbose(env, "read from map '%s' may yield more than %d pointers to functions\n",
					map->name, BPF_MAX_FUNC_PTR_TARGETS);
				return -E2BIG;
			}
			subprog = bpf_find_subprog(env, ptrs[i].xlated_off);
			if (verifier_bug_if(subprog <= 0, env,
					    "no function at insn %u for map '%s' offset %u",
					    ptrs[i].xlated_off, map->name, ptrs[i].map_off))
				return -EFAULT;
			targets[n++] = subprog;
		}
	}
	/* pointers are next to what is read, e.g. the data of an array of vtables */
	if (!n)
		return -ENOENT;
	/* either every offset that the read is possible at is a pointer or none */
	if (count_read_offsets(offs, min_off, max_off, n + 1) != n)
		goto overlap;

	/* the map has the offset of the function until the program is jitted */
	err = require_callx_jit(env);
	if (err)
		return err;

	for (i = 0; i < n - 1; i++) {
		branch = push_stack(env, env->insn_idx + 1, env->insn_idx,
				    env->cur_state->speculative);
		if (IS_ERR(branch))
			return PTR_ERR(branch);
		mark_reg_func_ptr(env, branch->frame[branch->curframe]->regs, value_regno,
				  targets[i]);
	}
	mark_reg_func_ptr(env, regs, value_regno, targets[n - 1]);
	return 0;

overlap:
	verbose(env, "read of %d bytes at offset [%llu,%llu] of map '%s' overlaps with a pointer to a function\n",
		size, min_off, max_off, map->name);
	return -EACCES;
}

static int check_map_mem_read(struct bpf_verifier_env *env, struct bpf_reg_state *reg, int off,
			      int bpf_size, int value_regno, bool is_ldsx)
{
	struct bpf_reg_state *regs = cur_regs(env);
	int size = bpf_size_to_bytes(bpf_size);
	struct bpf_map *map = reg->map_ptr;
	int err;

	switch (map->map_type) {
	case BPF_MAP_TYPE_INSN_ARRAY:
		if (bpf_size != BPF_DW) {
			verbose(env, "Invalid read of %d bytes from insn_array\n", size);
			return -EACCES;
		}
		regs[value_regno] = *reg;
		add_scalar_to_reg(&regs[value_regno], off);
		regs[value_regno].type = PTR_TO_INSN;
		return 0;
	case BPF_MAP_TYPE_PERCPU_ARRAY:
		goto reg_unknown;
	default:
		break;
	}

	if (env->func_ptr_cnt) {
		err = check_func_ptr_read(env, reg, off, size, value_regno);
		if (err != -ENOENT)
			return err;
	}

	/* If map is read-only, track its contents as scalars. */
	if (tnum_is_const(reg->var_off) &&
	    bpf_map_is_rdonly(map) &&
	    map->ops->map_direct_value_addr) {
		int map_off = off + reg->var_off.value;
		u64 val = 0;

		err = bpf_map_direct_read(map, map_off, size, &val, is_ldsx);
		if (err)
			return err;

		regs[value_regno].type = SCALAR_VALUE;
		__mark_reg_known(&regs[value_regno], val);
		return 0;
	}

reg_unknown:
	mark_reg_unknown(env, regs, value_regno);
	return 0;
}

/* 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, struct bpf_reg_state *reg, argno_t argno,
			    int off, int bpf_size, enum bpf_access_type t,
			    int value_regno, bool strict_alignment_once, bool is_ldsx)
{
	struct bpf_reg_state *regs = cur_regs(env);
	enum bpf_reg_type ptr_type = reg->type;
	int size, err = 0;

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

	err = check_ptr_alignment(env, reg, off, size, strict_alignment_once);
	if (err)
		return err;

	if (reg->type == PTR_TO_MAP_KEY) {
		if (t == BPF_WRITE) {
			verbose(env, "write to change key %s not allowed\n",
				reg_arg_name(env, argno));
			return -EACCES;
		}

		err = check_mem_region_access(env, reg, argno, off, size,
					      reg->map_ptr->key_size, false);
		if (err)
			return err;
		if (value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else if (reg->type == PTR_TO_MAP_VALUE) {
		struct btf_field *kptr_field = NULL;

		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_type(env, reg, off, size, t);
		if (err)
			return err;
		err = check_map_access(env, reg, argno, off, size, false, ACCESS_DIRECT);
		if (err)
			return err;
		if (tnum_is_const(reg->var_off))
			kptr_field = btf_record_find(reg->map_ptr->record,
						     off + reg->var_off.value, BPF_KPTR | BPF_UPTR);
		if (kptr_field) {
			err = check_map_kptr_access(env, value_regno, insn_idx, kptr_field);
		} else if (t == BPF_READ && value_regno >= 0) {
			err = check_map_mem_read(env, reg, off, bpf_size, value_regno, is_ldsx);
		}
	} else if (base_type(reg->type) == PTR_TO_MEM) {
		bool rdonly_mem = type_is_rdonly_mem(reg->type);
		bool rdonly_untrusted = rdonly_mem && (reg->type & PTR_UNTRUSTED);

		if (type_may_be_null(reg->type)) {
			verbose(env, "%s invalid mem access '%s'\n", reg_arg_name(env, argno),
				reg_type_str(env, reg->type));
			bpf_diag_invalid_deref(env, insn_idx, reg_from_argno(argno),
					       reg_arg_name(env, argno), reg,
						      BPF_DIAG_DEREF_NULLABLE_PTR, 0);
			return -EACCES;
		}

		if (t == BPF_WRITE && rdonly_mem) {
			verbose(env, "%s cannot write into %s\n",
				reg_arg_name(env, argno), reg_type_str(env, reg->type));
			return -EACCES;
		}

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

		if (rdonly_untrusted && !env->allow_ptr_leaks) {
			verbose(env, "%s access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
				reg_type_str(env, reg->type));
			bpf_diag_policy(env, insn_idx, "read from untrusted read-only memory",
					"the access requires CAP_PERFMON",
					"Load the program with CAP_PERFMON, or avoid dereferencing untrusted pointers.");
			return -EPERM;
		}

		/*
		 * Accesses to untrusted PTR_TO_MEM are done through probe
		 * instructions, hence no need to check bounds in that case.
		 */
		if (!rdonly_untrusted)
			err = check_mem_region_access(env, reg, argno, off, size,
						      reg->mem_size, false);
		if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
			mark_reg_unknown(env, regs, value_regno);
	} else if (reg->type == PTR_TO_CTX) {
		struct bpf_insn_access_aux info = {
			.reg_type = SCALAR_VALUE,
			.is_ldsx = is_ldsx,
			.log = &env->log,
		};
		struct bpf_retval_range range;

		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;
		}

		err = check_ctx_access(env, insn_idx, reg, argno, off, size, t, &info);
		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 (info.reg_type == SCALAR_VALUE) {
				if (info.is_retval && get_func_retval_range(env->prog, &range)) {
					mark_reg_unknown(env, regs, value_regno);
					err = __mark_reg_s32_range(env, regs, value_regno,
								   range.minval, range.maxval);
					if (err)
						return err;
				} else {
					mark_reg_unknown(env, regs, value_regno);
				}
			} else {
				mark_reg_known_zero(env, regs,
						    value_regno);
				if (base_type(info.reg_type) == PTR_TO_BTF_ID) {
					regs[value_regno].btf = info.btf;
					regs[value_regno].btf_id = info.btf_id;
					regs[value_regno].id = info.ref_id;
				} else if (base_type(info.reg_type) == PTR_TO_MEM) {
					regs[value_regno].mem_size = info.mem_size;
				}
				if (type_may_be_null(info.reg_type) && !regs[value_regno].id)
					regs[value_regno].id = ++env->id_gen;
			}
			regs[value_regno].type = info.reg_type;
		}

	} else if (reg->type == PTR_TO_STACK) {
		/* Basic bounds checks. */
		err = check_stack_access_within_bounds(env, reg, argno, off, size, t);
		if (err)
			return err;

		if (t == BPF_READ)
			err = check_stack_read(env, reg, argno, off, size,
					       value_regno);
		else
			err = check_stack_write(env, reg, off, size,
						value_regno, insn_idx);
	} else if (reg_is_pkt_pointer(reg)) {
		if (t == BPF_WRITE && !may_access_direct_pkt_data(env, NULL, t)) {
			verbose(env, "cannot write into packet\n");
			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, reg, argno, off, size, false);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else if (reg->type == PTR_TO_FLOW_KEYS) {
		if (t == BPF_WRITE && value_regno >= 0 &&
		    is_pointer_value(env, value_regno)) {
			verbose(env, "R%d leaks addr into flow keys\n",
				value_regno);
			return -EACCES;
		}

		err = check_flow_keys_access(env, reg, argno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else if (type_is_sk_pointer(reg->type)) {
		if (t == BPF_WRITE) {
			verbose(env, "%s cannot write into %s\n",
				reg_arg_name(env, argno), reg_type_str(env, reg->type));
			return -EACCES;
		}
		err = check_sock_access(env, insn_idx, reg, argno, off, size, t);
		if (!err && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else if (reg->type == PTR_TO_TP_BUFFER) {
		err = check_tp_buffer_access(env, reg, argno, off, size);
		if (!err && t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else if (base_type(reg->type) == PTR_TO_BTF_ID &&
		   !type_may_be_null(reg->type)) {
		err = check_ptr_to_btf_access(env, regs, reg, argno, off, size, t,
					      value_regno);
	} else if (reg->type == CONST_PTR_TO_MAP) {
		err = check_ptr_to_map_access(env, regs, reg, argno, off, size, t,
					      value_regno);
	} else if (base_type(reg->type) == PTR_TO_BUF &&
		   !type_may_be_null(reg->type)) {
		bool rdonly_mem = type_is_rdonly_mem(reg->type);
		u32 *max_access;

		if (rdonly_mem) {
			if (t == BPF_WRITE) {
				verbose(env, "%s cannot write into %s\n",
					reg_arg_name(env, argno), reg_type_str(env, reg->type));
				return -EACCES;
			}
			max_access = &env->prog->aux->max_rdonly_access;
		} else {
			max_access = &env->prog->aux->max_rdwr_access;
		}

		err = check_buffer_access(env, reg, argno, off, size, false,
					  max_access, t == BPF_WRITE);

		if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ))
			mark_reg_unknown(env, regs, value_regno);
	} else if (reg->type == PTR_TO_ARENA) {
		if (t == BPF_READ && value_regno >= 0)
			mark_reg_unknown(env, regs, value_regno);
	} else {
		enum bpf_diag_invalid_deref_kind kind = BPF_DIAG_DEREF_INVALID_PTR;

		verbose(env, "%s invalid mem access '%s'\n", reg_arg_name(env, argno),
			reg_type_str(env, reg->type));
		if (reg->type == SCALAR_VALUE)
			kind = BPF_DIAG_DEREF_SCALAR;
		else if (type_may_be_null(reg->type))
			kind = BPF_DIAG_DEREF_NULLABLE_PTR;
		bpf_diag_invalid_deref(env, insn_idx, reg_from_argno(argno),
				       reg_arg_name(env, argno), reg, kind, 0);
		return -EACCES;
	}

	if (!err && size < BPF_REG_SIZE && value_regno >= 0 && t == BPF_READ &&
	    regs[value_regno].type == SCALAR_VALUE) {
		if (!is_ldsx) {
			/* b/h/w load zero-extends, mark upper bits as known 0 */
			coerce_reg_to_size(&regs[value_regno], size);
		} else {
			/*
			 * Sign-extension can change the register value relative
			 * to a scalar it is linked with by id (e.g. a zero-
			 * extending fill of the same spilled stack slot), thus
			 * drop the shared id in that case.
			 */
			bool no_sext = reg_umax(&regs[value_regno]) <
					(1ULL << (size * BITS_PER_BYTE - 1));

			coerce_reg_to_size_sx(&regs[value_regno], size);
			if (!no_sext)
				clear_scalar_id(&regs[value_regno]);
		}
	}

	if (!err && bpf_is_mem_insn(&env->prog->insnsi[insn_idx]) && ptr_type != PTR_TO_STACK)
		mark_non_stack_access(env, insn_idx);

	return err;
}

static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type,
			     bool allow_trust_mismatch);

/*
 * Returns the register to check the access of the current insn with.
 * For a number in a program with an arena that is 'arena'.
 */
static struct bpf_reg_state *mem_access_reg(struct bpf_verifier_env *env, int regno,
					    struct bpf_reg_state *arena)
{
	if (!is_arena_scalar(env, regno))
		return cur_regs(env) + regno;

	memset(arena, 0, sizeof(*arena));
	arena->type = PTR_TO_ARENA;
	env->insn_aux_data[env->insn_idx].arena_scalar = true;
	return arena;
}

static int check_load_mem(struct bpf_verifier_env *env, struct bpf_insn *insn,
			  bool strict_alignment_once, bool is_ldsx,
			  bool allow_trust_mismatch, const char *ctx)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state arena, *src_reg;
	enum bpf_reg_type src_reg_type;
	int err;

	/* Handle stack arg read */
	if (is_stack_arg_ldx(insn)) {
		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
		if (err)
			return err;
		return check_stack_arg_read(env, state, insn->off, insn->dst_reg);
	}

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

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

	src_reg = mem_access_reg(env, insn->src_reg, &arena);
	src_reg_type = src_reg->type;

	/*
	 * check_stack_read_fixed_off() may refine the modification's origin to
	 * the source stack slot.
	 */
	bpf_diag_mod_begin(env, &regs[insn->dst_reg], NULL, BPF_DIAG_MOD_WRITE);
	err = check_mem_access(env, env->insn_idx, src_reg, argno_from_reg(insn->src_reg),
			       insn->off, BPF_SIZE(insn->code), BPF_READ, insn->dst_reg,
			       strict_alignment_once, is_ldsx);
	/*
	 * Paths through a kernel struct pointer and through other pointers
	 * may share the insn, see save_aux_ptr_type(). Record a load that did
	 * not produce an arena pointer from an __arena member, the only load
	 * through a kernel struct pointer that does, next to the one
	 * check_arena_member_load() records, so that arena_member_fixup() can
	 * tell when the paths disagree.
	 */
	if (!err && !(base_type(src_reg_type) == PTR_TO_BTF_ID &&
		      regs[insn->dst_reg].type == PTR_TO_ARENA))
		env->insn_aux_data[env->insn_idx].non_arena_load = true;
	err = err ?: save_aux_ptr_type(env, src_reg_type,
				       allow_trust_mismatch);
	err = err ?: reg_bounds_sanity_check(env, &regs[insn->dst_reg], ctx);
	if (!err)
		bpf_diag_mod_end(env);

	return err;
}

static int check_store_reg(struct bpf_verifier_env *env, struct bpf_insn *insn,
			   bool strict_alignment_once)
{
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state arena, *dst_reg;
	enum bpf_reg_type dst_reg_type;
	int err;

	/* Handle stack arg write */
	if (is_stack_arg_stx(insn)) {
		err = check_reg_arg(env, insn->src_reg, SRC_OP);
		if (err)
			return err;
		return check_stack_arg_write(env, state, insn->off, regs + insn->src_reg);
	}

	/* 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;

	dst_reg = mem_access_reg(env, insn->dst_reg, &arena);
	dst_reg_type = dst_reg->type;

	/* Check if (dst_reg + off) is writeable. */
	err = check_mem_access(env, env->insn_idx, dst_reg, argno_from_reg(insn->dst_reg),
			       insn->off, BPF_SIZE(insn->code), BPF_WRITE, insn->src_reg,
			       strict_alignment_once, false);
	err = err ?: save_aux_ptr_type(env, dst_reg_type, false);

	return err;
}

static int check_atomic_rmw(struct bpf_verifier_env *env,
			    struct bpf_insn *insn)
{
	struct bpf_reg_state arena, *dst_reg;
	int load_reg;
	int err;

	if (BPF_SIZE(insn->code) != BPF_W && BPF_SIZE(insn->code) != BPF_DW) {
		verbose(env, "invalid atomic operand size\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 (insn->imm == BPF_CMPXCHG) {
		/* Check comparison of R0 with memory location */
		const u32 aux_reg = BPF_REG_0;

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

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

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

	if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) {
		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
			insn->dst_reg,
			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
		return -EACCES;
	}

	/* load_reg may be dst_reg. Look at dst_reg before it's marked as unknown. */
	dst_reg = mem_access_reg(env, insn->dst_reg, &arena);

	load_reg = bpf_atomic_load_reg(insn);
	if (load_reg >= 0) {
		/* check and record load of old value */
		err = check_reg_arg(env, load_reg, DST_OP);
		if (err)
			return err;
	}

	/* Check whether we can read the memory, with second call for fetch
	 * case to simulate the register fill.
	 */
	err = check_mem_access(env, env->insn_idx, dst_reg, argno_from_reg(insn->dst_reg), insn->off,
			       BPF_SIZE(insn->code), BPF_READ, -1, true, false);
	if (!err && load_reg >= 0) {
		bpf_diag_mod_begin(env, cur_regs(env) + load_reg, NULL, BPF_DIAG_MOD_WRITE);
		err = check_mem_access(env, env->insn_idx, dst_reg, argno_from_reg(insn->dst_reg),
				       insn->off, BPF_SIZE(insn->code),
				       BPF_READ, load_reg, true, false);
		if (!err)
			bpf_diag_mod_end(env);
	}
	if (err)
		return err;

	err = save_aux_ptr_type(env, dst_reg->type, false);
	if (err)
		return err;
	/* Check whether we can write into the same memory. */
	err = check_mem_access(env, env->insn_idx, dst_reg, argno_from_reg(insn->dst_reg), insn->off,
			       BPF_SIZE(insn->code), BPF_WRITE, -1, true, false);
	if (err)
		return err;
	return 0;
}

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

	err = check_reg_arg(env, insn->src_reg, SRC_OP);
	if (err)
		return err;

	if (!atomic_ptr_type_ok(env, insn->src_reg, insn)) {
		verbose(env, "BPF_ATOMIC loads from R%d %s is not allowed\n",
			insn->src_reg,
			reg_type_str(env, reg_state(env, insn->src_reg)->type));
		return -EACCES;
	}

	return check_load_mem(env, insn, true, false, false, "atomic_load");
}

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

	err = check_store_reg(env, insn, true);
	if (err)
		return err;

	if (!atomic_ptr_type_ok(env, insn->dst_reg, insn)) {
		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
			insn->dst_reg,
			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
		return -EACCES;
	}

	return 0;
}

static int check_atomic(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	switch (insn->imm) {
	case BPF_ADD:
	case BPF_ADD | BPF_FETCH:
	case BPF_AND:
	case BPF_AND | BPF_FETCH:
	case BPF_OR:
	case BPF_OR | BPF_FETCH:
	case BPF_XOR:
	case BPF_XOR | BPF_FETCH:
	case BPF_XCHG:
	case BPF_CMPXCHG:
		return check_atomic_rmw(env, insn);
	case BPF_LOAD_ACQ:
		if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) {
			verbose(env,
				"64-bit load-acquires are only supported on 64-bit arches\n");
			return -EOPNOTSUPP;
		}
		return check_atomic_load(env, insn);
	case BPF_STORE_REL:
		if (BPF_SIZE(insn->code) == BPF_DW && BITS_PER_LONG != 64) {
			verbose(env,
				"64-bit store-releases are only supported on 64-bit arches\n");
			return -EOPNOTSUPP;
		}
		return check_atomic_store(env, insn);
	default:
		verbose(env, "BPF_ATOMIC uses invalid atomic opcode %02x\n",
			insn->imm);
		return -EINVAL;
	}
}

/* When register 'regno' is used to read the stack (either directly or through
 * a helper function) make sure that it's within stack boundary and, depending
 * on the access type and privileges, that all elements of the stack are
 * initialized.
 *
 * All registers that have been spilled on the stack in the slots within the
 * read offsets are marked as read.
 */
static int check_stack_range_initialized(
		struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno, int off,
		int access_size, bool zero_size_allowed,
		enum bpf_access_type type, struct bpf_call_arg_meta *meta)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	int err, min_off, max_off, i, j, slot, spi;
	/* Some accesses can write anything into the stack, others are
	 * read-only.
	 */
	bool clobber = type == BPF_WRITE;
	/*
	 * Negative access_size signals global subprog arg check where
	 * STACK_POISON slots are acceptable. static stack liveness
	 * might have determined that subprog doesn't read them,
	 * but BTF based global subprog validation isn't accurate enough.
	 */
	bool allow_poison = access_size < 0 || clobber;
	u32 arg_slot = arg_slot_from_argno(argno);
	bool uninit = clobber && meta && arg_slot < MAX_BPF_FUNC_ARGS &&
		      (meta->arg_raw_mem.mask & BIT(arg_slot));
	bool raw_mode = uninit && env->allow_uninit_stack &&
			!(meta->arg_raw_mem.var_size_mask & BIT(arg_slot));

	access_size = abs(access_size);

	if (access_size == 0 && !zero_size_allowed) {
		verbose(env, "invalid zero-sized read\n");
		return -EACCES;
	}

	err = check_stack_access_within_bounds(env, reg, argno, off, access_size, type);
	if (err)
		return err;

	if (tnum_is_const(reg->var_off)) {
		min_off = max_off = reg->var_off.value + off;
	} else {
		/* Variable offset is prohibited for unprivileged mode for
		 * simplicity since it requires corresponding support in
		 * Spectre masking for stack ALU.
		 * See also retrieve_ptr_limit().
		 */
		if (!env->bypass_spec_v1) {
			char tn_buf[48];

			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
			verbose(env, "%s variable offset stack access prohibited for !root, var_off=%s\n",
				reg_arg_name(env, argno), tn_buf);
			return -EACCES;
		}
		/*
		 * The call may touch any byte in the possible range, but does not
		 * definitely initialize all of it. Fall back to ordinary stack checks.
		 */
		raw_mode = false;

		min_off = reg_smin(reg) + off;
		max_off = reg_smax(reg) + off;
	}

	/* Unprivileged outputs retain each byte's initialization state. */
	if (raw_mode) {
		meta->arg_raw_mem.size[arg_slot] = access_size;
		return 0;
	}

	for (i = min_off; i < max_off + access_size; i++) {
		struct bpf_stack_state *ss;
		u8 *stype;

		slot = -i - 1;
		spi = slot / BPF_REG_SIZE;
		if (state->allocated_stack <= slot) {
			verbose(env, "allocated_stack too small\n");
			return -EFAULT;
		}

		ss = bpf_stack_slot(state, spi);
		stype = &ss->slot_type[slot % BPF_REG_SIZE];
		if (*stype == STACK_MISC)
			goto mark;
		if ((*stype == STACK_ZERO) ||
		    (*stype == STACK_INVALID && (uninit || env->allow_uninit_stack))) {
			if (clobber && (*stype != STACK_INVALID || env->allow_uninit_stack)) {
				/* helper can write anything into the stack */
				*stype = STACK_MISC;
			}
			goto mark;
		}

		/*
		 * Only the bytes marked STACK_SPILL hold the spilled register.
		 * The rest of a narrowly spilled slot keeps its previous type
		 * and must be initialized on its own.
		 */
		if (*stype == STACK_SPILL &&
		    (ss->spilled_ptr.type == SCALAR_VALUE ||
		     env->allow_ptr_leaks)) {
			if (clobber) {
				__mark_reg_unknown(env, &ss->spilled_ptr);
				for (j = 0; j < BPF_REG_SIZE; j++)
					scrub_spilled_slot(&ss->slot_type[j]);
			}
			goto mark;
		}

		if (*stype == STACK_POISON) {
			if (allow_poison) {
				if (uninit && env->allow_uninit_stack)
					*stype = STACK_MISC;
				goto mark;
			}
			verbose(env, "reading from stack %s off %d+%d size %d, slot poisoned by dead code elimination\n",
				reg_arg_name(env, argno), min_off, i - min_off, access_size);
		} else if (tnum_is_const(reg->var_off)) {
			verbose(env, "invalid read from stack %s off %d+%d size %d\n",
				reg_arg_name(env, argno), min_off, i - min_off, access_size);
		} else {
			char tn_buf[48];

			tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
			verbose(env, "invalid read from stack %s var_off %s+%d size %d\n",
				reg_arg_name(env, argno), tn_buf, i - min_off, access_size);
		}
		return -EACCES;
mark:
		;
	}
	return 0;
}

static int check_helper_mem_access(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				   argno_t argno, int access_size,
				   enum bpf_access_type access_type, bool zero_size_allowed,
				   struct bpf_call_arg_meta *meta, bool *known_memory)
{
	struct bpf_reg_state *regs = cur_regs(env);
	u32 *max_access;

	if (known_memory)
		*known_memory = true;

	switch (base_type(reg->type)) {
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
		if (!may_access_direct_pkt_data(env, meta, access_type)) {
			verbose(env, "function access to the packet is not allowed\n");
			return -EACCES;
		}
		return check_packet_access(env, reg, argno, 0, access_size,
					   zero_size_allowed);
	case PTR_TO_MAP_KEY:
		if (access_type == BPF_WRITE) {
			verbose(env, "%s cannot write into %s\n",
				reg_arg_name(env, argno), reg_type_str(env, reg->type));
			return -EACCES;
		}
		return check_mem_region_access(env, reg, argno, 0, access_size,
					       reg->map_ptr->key_size, false);
	case PTR_TO_MAP_VALUE:
		if (check_map_access_type(env, reg, 0, access_size, access_type))
			return -EACCES;
		return check_map_access(env, reg, argno, 0, access_size,
					zero_size_allowed, ACCESS_HELPER);
	case PTR_TO_MEM:
		if (type_is_rdonly_mem(reg->type)) {
			if (access_type == BPF_WRITE) {
				verbose(env, "%s cannot write into %s\n",
					reg_arg_name(env, argno), reg_type_str(env, reg->type));
				return -EACCES;
			}
		}
		return check_mem_region_access(env, reg, argno, 0,
					       access_size, reg->mem_size,
					       zero_size_allowed);
	case PTR_TO_BUF:
		if (type_is_rdonly_mem(reg->type)) {
			if (access_type == BPF_WRITE) {
				verbose(env, "%s cannot write into %s\n",
					reg_arg_name(env, argno), reg_type_str(env, reg->type));
				return -EACCES;
			}

			max_access = &env->prog->aux->max_rdonly_access;
		} else {
			max_access = &env->prog->aux->max_rdwr_access;
		}
		return check_buffer_access(env, reg, argno, 0,
					   access_size, zero_size_allowed,
					   max_access, access_type == BPF_WRITE);
	case PTR_TO_STACK:
		return check_stack_range_initialized(
				env, reg,
				argno, 0, access_size,
				zero_size_allowed, access_type, meta);
	case PTR_TO_BTF_ID:
		return check_ptr_to_btf_access(env, regs, reg, argno, 0,
					       access_size, access_type, -1);
	case PTR_TO_CTX:
		/* Only permit reading or writing syscall context using helper calls. */
		if (is_var_ctx_off_allowed(env->prog)) {
			int err = check_mem_region_access(env, reg, argno, 0, access_size, U16_MAX,
							  zero_size_allowed);
			if (err)
				return err;
			if (env->prog->aux->max_ctx_offset < reg_umax(reg) + access_size)
				env->prog->aux->max_ctx_offset = reg_umax(reg) + access_size;
			return 0;
		}
		fallthrough;
	default: /* scalar_value or invalid ptr */
		/* Allow zero-byte read from NULL, regardless of pointer type */
		if (zero_size_allowed && access_size == 0 &&
		    bpf_register_is_null(reg))
			return 0;
		if (known_memory && base_type(reg->type) != PTR_TO_CTX)
			*known_memory = false;

		verbose(env, "%s type=%s ", reg_arg_name(env, argno),
			reg_type_str(env, reg->type));
		verbose(env, "expected=%s\n", reg_type_str(env, PTR_TO_STACK));
		return -EACCES;
	}
}

enum bpf_mem_size_failure {
	BPF_MEM_SIZE_FAIL_NONE,
	BPF_MEM_SIZE_FAIL_MEMORY,
	BPF_MEM_SIZE_FAIL_SIZE,
};

/* verify arguments to helpers or kfuncs consisting of a pointer and an access
 * size.
 *
 * @mem_reg contains the pointer, @size_reg contains the access size.
 */
static int check_mem_size_reg(struct bpf_verifier_env *env,
			      struct bpf_reg_state *mem_reg,
			      struct bpf_reg_state *size_reg, argno_t mem_argno,
			      argno_t size_argno, u32 access_type,
			      bool zero_size_allowed,
			      struct bpf_call_arg_meta *meta,
			      enum bpf_mem_size_failure *failure)
{
	int err = 0;

	if (failure)
		*failure = BPF_MEM_SIZE_FAIL_NONE;

	/* This is used to refine r0 return value bounds for helpers
	 * that enforce this value as an upper bound on return values.
	 * See do_refine_retval_range() for helpers that can refine
	 * the return value. C type of helper is u32 so we pull register
	 * bound from umax_value however, if negative verifier errors
	 * out. Only upper bounds can be learned because retval is an
	 * int type and negative retvals are allowed.
	 */
	meta->msize_max_value = reg_umax(size_reg);

	/*
	 * Check variable ranges byte by byte instead of using raw mode. Keep the
	 * MEM_UNINIT annotation so invalid bytes are accepted without marking them
	 * initialized when the caller cannot read uninitialized stack memory.
	 */
	if (!tnum_is_const(size_reg->var_off))
		meta->arg_raw_mem.var_size_mask |= BIT(arg_slot_from_argno(mem_argno));

	if (reg_smin(size_reg) < 0) {
		verbose(env, "%s min value is negative, either use unsigned or 'var &= const'\n",
			reg_arg_name(env, size_argno));
		err = -EACCES;
		goto size_error;
	}

	if (reg_umin(size_reg) == 0 && !zero_size_allowed) {
		verbose(env, "%s invalid zero-sized read: u64=[%lld,%lld]\n",
			reg_arg_name(env, size_argno), reg_umin(size_reg), reg_umax(size_reg));
		err = -EACCES;
		goto size_error;
	}

	if (reg_umax(size_reg) >= BPF_MAX_VAR_SIZ) {
		verbose(env, "%s unbounded memory access, use 'var &= const' or 'if (var < const)'\n",
			reg_arg_name(env, size_argno));
		err = -EACCES;
		goto size_error;
	}

	if (access_type & BPF_READ)
		err = check_helper_mem_access(env, mem_reg, mem_argno, reg_umax(size_reg),
					      BPF_READ, zero_size_allowed, meta, NULL);
	if (!err && access_type & BPF_WRITE)
		err = check_helper_mem_access(env, mem_reg, mem_argno, reg_umax(size_reg),
					      BPF_WRITE, zero_size_allowed, meta, NULL);
	if (err && failure)
		*failure = BPF_MEM_SIZE_FAIL_MEMORY;

	if (!err)
		err = mark_arg_precision(env, size_argno);

	return err;

size_error:
	if (failure)
		*failure = BPF_MEM_SIZE_FAIL_SIZE;
	return err;
}

static bool is_subprog(const struct bpf_call_arg_meta *meta)
{
	return meta->btf && !meta->func_id;
}

static int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			 argno_t argno, u32 mem_size, enum bpf_access_type access_type,
			 struct bpf_call_arg_meta *meta, bool *known_memory)
{
	int size, err = 0;

	if (bpf_register_is_null(reg))
		return mark_arg_precision(env, argno);
	if (known_memory)
		*known_memory = true;

	if (mem_size > S32_MAX) {
		verbose(env, "%s memory size %u is too large\n",
			reg_arg_name(env, argno), mem_size);
		return -EACCES;
	}

	/*
	 * Only a global subprog may read poisoned stack slots:
	 * its static stack liveness proved the callee body skips them.
	 */
	size = (is_subprog(meta) &&
		base_type(reg->type) == PTR_TO_STACK) ? -(int)mem_size : mem_size;

	if (access_type & BPF_READ)
		err = check_helper_mem_access(env, reg, argno, size, BPF_READ, true, meta,
					      known_memory);
	if (!err && (access_type & BPF_WRITE))
		err = check_helper_mem_access(env, reg, argno, size, BPF_WRITE, true, meta,
					      known_memory);

	return err;
}

static int process_const_alloc_mem_size(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
					argno_t argno, struct ret_mem_desc *ret_mem)
{
	int regno = reg_from_argno(argno);
	int err;

	if (ret_mem->found) {
		verifier_bug(env, "only one allocation size argument permitted");
		return -EFAULT;
	}

	if (!tnum_is_const(reg->var_off)) {
		verbose(env, "%s is not a const\n", reg_arg_name(env, argno));
		return -EINVAL;
	}

	if (reg->var_off.value > U32_MAX) {
		verbose(env, "%s allocation size exceeds u32 max\n", reg_arg_name(env, argno));
		return -EINVAL;
	}

	if (regno >= 0)
		err = mark_chain_precision(env, regno);
	else
		err = mark_stack_arg_precision(env, arg_idx_from_argno(argno));
	if (err)
		return err;

	ret_mem->size = reg->var_off.value;
	ret_mem->found = true;

	return 0;
}

static int process_const_arg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			     argno_t argno, struct bpf_call_arg_meta *meta)
{
	int regno = reg_from_argno(argno);
	int err;

	if (meta->arg_constant.found) {
		verifier_bug(env, "only one constant argument permitted");
		return -EFAULT;
	}

	if (!tnum_is_const(reg->var_off)) {
		verbose(env, "%s must be a known constant\n", reg_arg_name(env, argno));
		return -EINVAL;
	}

	if (regno >= 0)
		err = mark_chain_precision(env, regno);
	else
		err = mark_stack_arg_precision(env, arg_idx_from_argno(argno));
	if (err < 0)
		return err;

	meta->arg_constant.found = true;
	meta->arg_constant.value = reg->var_off.value;

	return 0;
}

enum {
	PROCESS_SPIN_LOCK = (1 << 0),
	PROCESS_RES_LOCK  = (1 << 1),
	PROCESS_LOCK_IRQ  = (1 << 2),
};

/* Implementation details:
 * bpf_map_lookup returns PTR_TO_MAP_VALUE_OR_NULL.
 * bpf_obj_new returns PTR_TO_BTF_ID | MEM_ALLOC | PTR_MAYBE_NULL.
 * Two bpf_map_lookups (even with the same key) will have different reg->id.
 * Two separate bpf_obj_new will also have different reg->id.
 * For traditional PTR_TO_MAP_VALUE or PTR_TO_BTF_ID | MEM_ALLOC, the verifier
 * clears reg->id after value_or_null->value transition, since the verifier only
 * cares about the range of access to valid map value pointer and doesn't care
 * about actual address of the map element.
 * For maps with 'struct bpf_spin_lock' inside map value the verifier keeps
 * reg->id > 0 after value_or_null->value transition. By doing so
 * two bpf_map_lookups will be considered two different pointers that
 * point to different bpf_spin_locks. Likewise for pointers to allocated objects
 * returned from bpf_obj_new.
 * The verifier allows taking only one bpf_spin_lock at a time to avoid
 * dead-locks.
 * Since only one bpf_spin_lock is allowed the checks are simpler than
 * reg_is_refcounted() logic. The verifier needs to remember only
 * one spin_lock instead of array of acquired_refs.
 * env->cur_state->active_locks remembers which map value element or allocated
 * object got locked and clears it after bpf_spin_unlock.
 */
static int process_spin_lock(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno, int flags)
{
	bool is_lock = flags & PROCESS_SPIN_LOCK, is_res_lock = flags & PROCESS_RES_LOCK;
	const char *lock_str = is_res_lock ? "bpf_res_spin" : "bpf_spin";
	struct bpf_verifier_state *cur = env->cur_state;
	struct bpf_reference_state *lock;
	bool is_const = tnum_is_const(reg->var_off);
	bool is_irq = flags & PROCESS_LOCK_IRQ;
	u64 val = reg->var_off.value;
	struct bpf_map *map = NULL;
	struct btf *btf = NULL;
	struct btf_record *rec;
	u32 spin_lock_off;
	int err;

	if (!is_const) {
		verbose(env,
			"%s doesn't have constant offset. %s_lock has to be at the constant offset\n",
			reg_arg_name(env, argno), lock_str);
		return -EINVAL;
	}
	if (reg->type == PTR_TO_MAP_VALUE) {
		map = reg->map_ptr;
		if (!map->btf) {
			verbose(env,
				"map '%s' has to have BTF in order to use %s_lock\n",
				map->name, lock_str);
			return -EINVAL;
		}
	} else {
		btf = reg->btf;
	}

	rec = reg_btf_record(reg);
	if (!btf_record_has_field(rec, is_res_lock ? BPF_RES_SPIN_LOCK : BPF_SPIN_LOCK)) {
		verbose(env, "%s '%s' has no valid %s_lock\n", map ? "map" : "local",
			map ? map->name : "kptr", lock_str);
		return -EINVAL;
	}
	spin_lock_off = is_res_lock ? rec->res_spin_lock_off : rec->spin_lock_off;
	if (spin_lock_off != val) {
		verbose(env, "off %lld doesn't point to 'struct %s_lock' that is at %d\n",
			val, lock_str, spin_lock_off);
		return -EINVAL;
	}
	if (is_lock) {
		void *ptr;
		int type;

		if (map)
			ptr = map;
		else
			ptr = btf;

		if (!is_res_lock && cur->active_locks) {
			lock = find_lock_state(cur, REF_TYPE_LOCK, 0, NULL);
			if (lock) {
				verbose(env,
					"Locking two bpf_spin_locks are not allowed\n");
				bpf_diag_lock(
					env, env->insn_idx, "nested spin lock",
					"This path already holds a bpf_spin_lock. The verifier allows only one regular BPF spin lock at a time.",
					"Unlock the current bpf_spin_lock before taking another one.", lock);
				return -EINVAL;
			}
		} else if (is_res_lock && cur->active_locks) {
			lock = find_lock_state(cur, REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ,
					       reg->id, ptr);
			if (lock) {
				verbose(env, "Acquiring the same lock again, AA deadlock detected\n");
				bpf_diag_lock(
					env, env->insn_idx, "recursive resource spin lock",
					"This path already holds the same resource spin lock. Taking it again would deadlock.",
					"Avoid reacquiring the same resource spin lock before it is unlocked.", lock);
				return -EINVAL;
			}
		}

		if (is_res_lock && is_irq)
			type = REF_TYPE_RES_LOCK_IRQ;
		else if (is_res_lock)
			type = REF_TYPE_RES_LOCK;
		else
			type = REF_TYPE_LOCK;
		err = acquire_lock_state(env, env->insn_idx, type, reg->id, ptr);
		if (err < 0) {
			verbose(env, "Failed to acquire lock state\n");
			return err;
		}
	} else {
		void *ptr;
		int type;

		if (map)
			ptr = map;
		else
			ptr = btf;

		if (!cur->active_locks) {
			verbose(env, "%s_unlock without taking a lock\n", lock_str);
			bpf_diag_res(
				env, env->insn_idx, "unlock without lock",
				"This unlock operation has no matching active lock on the current path.",
				"Take the matching lock before this unlock, or remove the unmatched unlock path.");
			return -EINVAL;
		}

		if (is_res_lock && is_irq)
			type = REF_TYPE_RES_LOCK_IRQ;
		else if (is_res_lock)
			type = REF_TYPE_RES_LOCK;
		else
			type = REF_TYPE_LOCK;

		lock = find_lock_state(cur, type, reg->id, ptr);
		if (!lock) {
			verbose(env, "%s_unlock of different lock\n", lock_str);
			lock = find_lock_state(cur, REF_TYPE_LOCK_MASK, cur->active_lock_id,
					       cur->active_lock_ptr);
			bpf_diag_lock(
				env, env->insn_idx, "unlock of a different lock",
				"This unlock does not match any active lock with the same tracked identity on the current path.",
				"Unlock the same lock object that was most recently acquired.", lock);
			return -EINVAL;
		}
		if (reg->id != cur->active_lock_id || ptr != cur->active_lock_ptr) {
			verbose(env, "%s_unlock cannot be out of order\n", lock_str);
			lock = find_lock_state(cur, REF_TYPE_LOCK_MASK, cur->active_lock_id,
					       cur->active_lock_ptr);
			bpf_diag_lock(
				env, env->insn_idx, "unlock out of order",
				"Locks must be released in last-in, first-out order, but this unlock does not match the currently active lock.",
				"Release nested locks in the reverse order they were acquired.", lock);
			return -EINVAL;
		}
		if (release_lock_state(env, type, reg->id, ptr)) {
			verbose(env, "%s_unlock of different lock\n", lock_str);
			bpf_diag_lock(
				env, env->insn_idx, "unlock of a different lock",
				"The verifier could not release a lock state matching this unlock operation.",
				"Pass the same lock object and lock kind that were used for the matching lock operation.",
				lock);
			return -EINVAL;
		}
		/*
		 * Invalidate non-owning refs before RCU demotion clears their
		 * NON_OWN_REF flag.
		 */
		invalidate_non_owning_refs(env);

		if (!in_rcu_cs(env))
			invalidate_rcu_protected_refs(env);
	}
	return 0;
}

/* Check if @regno is a pointer to a specific field in a map value */
static int check_map_field_pointer(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
				   enum btf_field_type field_type,
				   struct bpf_map_desc *map_desc)
{
	bool is_const = tnum_is_const(reg->var_off);
	struct bpf_map *map = reg->map_ptr;
	u64 val = reg->var_off.value;
	const char *struct_name = btf_field_type_name(field_type);
	int field_off = -1;

	if (!is_const) {
		verbose(env,
			"%s doesn't have constant offset. %s has to be at the constant offset\n",
			reg_arg_name(env, argno), struct_name);
		return -EINVAL;
	}
	if (!map->btf) {
		verbose(env, "map '%s' has to have BTF in order to use %s\n", map->name,
			struct_name);
		return -EINVAL;
	}
	if (!btf_record_has_field(map->record, field_type)) {
		verbose(env, "map '%s' has no valid %s\n", map->name, struct_name);
		return -EINVAL;
	}
	switch (field_type) {
	case BPF_TIMER:
		field_off = map->record->timer_off;
		break;
	case BPF_TASK_WORK:
		field_off = map->record->task_work_off;
		break;
	case BPF_RCU_HEAD:
		field_off = map->record->rcu_head_off;
		break;
	case BPF_WORKQUEUE:
		field_off = map->record->wq_off;
		break;
	default:
		verifier_bug(env, "unsupported BTF field type: %s\n", struct_name);
		return -EINVAL;
	}
	if (field_off != val) {
		verbose(env, "off %lld doesn't point to 'struct %s' that is at %d\n",
			val, struct_name, field_off);
		return -EINVAL;
	}
	if (map_desc->ptr) {
		verifier_bug(env, "Two map pointers in a %s helper", struct_name);
		return -EFAULT;
	}
	map_desc->uid = reg->map_uid;
	map_desc->ptr = map;
	return 0;
}

static int process_timer_func(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
			      struct bpf_map_desc *map)
{
	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
		verbose(env, "bpf_timer cannot be used for PREEMPT_RT.\n");
		return -EOPNOTSUPP;
	}
	return check_map_field_pointer(env, reg, argno, BPF_TIMER, map);
}

static int process_kptr_func(struct bpf_verifier_env *env, int regno,
			     struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *reg = reg_state(env, regno);
	struct btf_field *kptr_field;
	struct bpf_map *map_ptr;
	struct btf_record *rec;
	u32 kptr_off;

	if (type_is_ptr_alloc_obj(reg->type)) {
		rec = reg_btf_record(reg);
	} else { /* PTR_TO_MAP_VALUE */
		map_ptr = reg->map_ptr;
		if (!map_ptr->btf) {
			verbose(env, "map '%s' has to have BTF in order to use bpf_kptr_xchg\n",
				map_ptr->name);
			return -EINVAL;
		}
		rec = map_ptr->record;
		meta->map.ptr = map_ptr;
	}

	if (!tnum_is_const(reg->var_off)) {
		verbose(env,
			"R%d doesn't have constant offset. kptr has to be at the constant offset\n",
			regno);
		return -EINVAL;
	}

	if (!btf_record_has_field(rec, BPF_KPTR)) {
		verbose(env, "R%d has no valid kptr\n", regno);
		return -EINVAL;
	}

	kptr_off = reg->var_off.value;
	kptr_field = btf_record_find(rec, kptr_off, BPF_KPTR);
	if (!kptr_field) {
		verbose(env, "off=%d doesn't point to kptr\n", kptr_off);
		return -EACCES;
	}
	if (kptr_field->type != BPF_KPTR_REF && kptr_field->type != BPF_KPTR_PERCPU) {
		verbose(env, "off=%d kptr isn't referenced kptr\n", kptr_off);
		return -EACCES;
	}
	meta->kptr_field = kptr_field;
	return 0;
}

static void bpf_diag_call_arg(struct bpf_verifier_env *env, u32 insn_idx, argno_t argno,
			      const char *call_name, const char *reason, const char *suggestion);
__printf(6, 7) static void bpf_diag_call_arg_fmt(struct bpf_verifier_env *env, u32 insn_idx,
						 argno_t argno, const char *call_name,
						 const char *suggestion, const char *fmt, ...);

/*
 * Validate dynptr arguments for helper, kfunc and subprog.
 *
 * @meta carries the dynptr and referenced-object state. The dynptr is populated
 * when the argument is tagged with MEM_UNINIT (i.e., the dynptr argument that
 * will be constructed) and consumed when the argument is expected to be an
 * initialized dynptr. The reference tracks the parent object (e.g., file or skb
 * in qdisc program) when constructing a dynptr.
 *
 * There are two register types representing a bpf_dynptr, one is PTR_TO_STACK
 * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR.
 *
 * In both cases we deal with the first 8 bytes, but need to mark the next 8
 * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of
 * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object.
 *
 * Mutability of bpf_dynptr is at two levels: the dynptr and the memory the
 * dynptr points to. At the first level, the verifier will make sure a
 * CONST_PTR_TO_DYNPTR cannot be reinitialized or destroyed. The mutability of
 * a dynptr's view (i.e., start and offset) is not tracked as there is not such
 * use case. The second level is tracked using the upper bit of bpf_dynptr->size
 * and checked dynamically during runtime.
 */
static int process_dynptr_func(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			       argno_t argno, int insn_idx, enum bpf_arg_type arg_type,
			       struct bpf_call_arg_meta *meta)
{
	int spi, err = 0;

	/*  MEM_UNINIT - Points to memory that is an appropriate candidate for
	 *		 constructing a mutable bpf_dynptr object.
	 *
	 *		 Currently, this is only possible with PTR_TO_STACK
	 *		 pointing to a region of at least 16 bytes which doesn't
	 *		 contain an existing bpf_dynptr.
	 *
	 *  OBJ_RELEASE - Points to a initialized bpf_dynptr that will be
	 *		  destroyed.
	 *
	 *  None       - Points to a initialized dynptr that cannot be
	 *		 reinitialized or destroyed. However, the view of the
	 *		 dynptr and the memory it points to may be mutated.
	 */
	if (arg_type & MEM_UNINIT) {
		int i;

		if (!is_dynptr_reg_valid_uninit(env, reg)) {
			verbose(env, "Dynptr has to be an uninitialized dynptr\n");
			bpf_diag_res(
				env, insn_idx, "dynptr is already initialized",
				"This function constructs a dynptr and requires an uninitialized dynptr stack slot, but the selected slot already holds dynptr state.",
				"Use a fresh stack dynptr slot, or release/destroy the existing dynptr before reusing the slot.");
			return -EINVAL;
		}

		/* we write BPF_DW bits (8 bytes) at a time */
		for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
			err = check_mem_access(env, insn_idx, reg, argno,
					       i, BPF_DW, BPF_WRITE, -1, false, false);
			if (err)
				return err;
		}

		err = mark_stack_slots_dynptr(env, reg, arg_type, insn_idx,
					      &meta->ref_obj, &meta->dynptr);
	} else /* OBJ_RELEASE and None case from above */ {
		/* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */
		if (reg->type == CONST_PTR_TO_DYNPTR && (arg_type & OBJ_RELEASE)) {
			verbose(env, "CONST_PTR_TO_DYNPTR cannot be released\n");
			bpf_diag_res(
				env, insn_idx, "const dynptr release",
				"This release operation was given a const dynptr. Const dynptr values are verifier-provided views and cannot be released by the program.",
				"Release only mutable dynptrs that the program initialized or reserved.");
			return -EINVAL;
		}

		if (!is_dynptr_reg_valid_init(env, reg)) {
			verbose(env, "Expected an initialized dynptr as %s\n",
				reg_arg_name(env, argno));
			bpf_diag_res(
				env, insn_idx, "uninitialized dynptr use",
				"This operation requires an initialized dynptr, but the stack slot does not currently hold a valid dynptr on this path.",
				"Initialize the dynptr on every path before this call, and avoid overwriting or releasing it before this use.");
			return -EINVAL;
		}

		/* Fold modifiers (in this case, OBJ_RELEASE) when checking expected type */
		if (!is_dynptr_type_expected(env, reg, arg_type & ~OBJ_RELEASE)) {
			enum bpf_dynptr_type expected_type = arg_to_dynptr_type(arg_type);
			enum bpf_dynptr_type actual_type = dynptr_reg_type(env, reg);

			verbose(env, "Expected a dynptr of type %s as %s\n",
				dynptr_type_str(expected_type), reg_arg_name(env, argno));
			bpf_diag_call_arg_fmt(
				env, insn_idx, argno, meta->func_name,
				"Use a dynptr constructor that matches this operation, or call an operation that accepts the dynptr's current type.",
				"the dynptr is initialized with backing object type %s, but this operation expects dynptr type %s",
				dynptr_type_str(actual_type), dynptr_type_str(expected_type));
			return -EINVAL;
		}

		if (reg->type != CONST_PTR_TO_DYNPTR) {
			struct bpf_func_state *state = bpf_func(env, reg);

			spi = dynptr_get_spi(env, reg);
			if (spi < 0)
				return spi;

			mark_stack_slots_scratched(env, spi, BPF_DYNPTR_NR_SLOTS);

			reg = &bpf_stack_slot(state, spi)->spilled_ptr;
		}

		meta->dynptr.type = reg->dynptr.type;
		meta->dynptr.id = reg->id;
		meta->dynptr.parent_id = reg->parent_id;
	}
	return err;
}

static bool is_iter_kfunc(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY);
}

static bool is_iter_new_kfunc(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_ITER_NEW;
}

static bool is_iter_destroy_kfunc(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_ITER_DESTROY;
}

static bool is_kfunc_arg_iter(struct bpf_call_arg_meta *meta, int arg_idx,
			      const struct btf_param *arg)
{
	/* btf_check_iter_kfuncs() guarantees that first argument of any iter
	 * kfunc is iter state pointer
	 */
	if (is_iter_kfunc(meta))
		return arg_idx == 0;

	/* iter passed as an argument to a generic kfunc */
	return btf_param_match_suffix(meta->btf, arg, "__iter");
}

static int process_iter_arg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			    u32 arg, argno_t argno, int insn_idx,
			    struct bpf_call_arg_meta *meta)
{
	struct bpf_func_state *state = bpf_func(env, reg);
	const struct btf_type *t;
	int spi, err, i, nr_slots, btf_id;

	if (reg->type != PTR_TO_STACK) {
		verbose(env, "%s expected pointer to an iterator on stack\n",
			reg_arg_name(env, argno));
		bpf_diag_call_arg_fmt(
			env, insn_idx, argno, meta->func_name,
			"Pass the address of a stack iterator object for iterator new, next, and destroy calls.",
			"iterator state must live in verifier-tracked stack memory, but %s is %s",
			reg_arg_name(env, argno), bpf_diag_reg_type_plain(env, reg->type));
		return -EINVAL;
	}

	/* For iter_{new,next,destroy} functions, btf_check_iter_kfuncs()
	 * ensures struct convention, so we wouldn't need to do any BTF
	 * validation here. But given iter state can be passed as a parameter
	 * to any kfunc, if arg has "__iter" suffix, we need to be a bit more
	 * conservative here.
	 */
	btf_id = btf_check_iter_arg(meta->btf, meta->func_proto, arg);
	if (btf_id < 0) {
		verbose(env, "expected valid iter pointer as %s\n",
			reg_arg_name(env, argno));
		bpf_diag_call_arg(
			env, insn_idx, argno, meta->func_name,
			"the function expects a recognized iterator state pointer, but this argument does not match a valid iterator type",
			"Pass the exact iterator state type expected by this function.");
		return -EINVAL;
	}
	t = btf_type_by_id(meta->btf, btf_id);
	nr_slots = t->size / BPF_REG_SIZE;

	if (is_iter_new_kfunc(meta)) {
		/* bpf_iter_<type>_new() expects pointer to uninit iter state */
		if (!is_iter_reg_valid_uninit(env, reg, nr_slots)) {
			verbose(env, "expected uninitialized iter_%s as %s\n",
				iter_type_str(meta->btf, btf_id), reg_arg_name(env, argno));
			bpf_diag_res(
				env, insn_idx, "iterator is already initialized",
				"Iterator creation requires an uninitialized iterator stack object, but this stack range already contains iterator state.",
				"Use a fresh iterator stack slot, or destroy the existing iterator before reusing the slot.");
			return -EINVAL;
		}

		for (i = 0; i < nr_slots * 8; i += BPF_REG_SIZE) {
			err = check_mem_access(env, insn_idx, reg, argno,
					       i, BPF_DW, BPF_WRITE, -1, false, false);
			if (err)
				return err;
		}

		err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots);
		if (err)
			return err;
	} else {
		/* iter_next() or iter_destroy(), as well as any kfunc
		 * accepting iter argument, expect initialized iter state
		 */
		err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots);
		switch (err) {
		case 0:
			break;
		case -EINVAL:
			verbose(env, "expected an initialized iter_%s as %s\n",
				iter_type_str(meta->btf, btf_id), reg_arg_name(env, argno));
			bpf_diag_res(
				env, insn_idx, "uninitialized iterator use",
				"This iterator operation requires an initialized iterator state object, but the stack range does not contain a live iterator on this path.",
				"Call the matching iterator new kfunc on every path before calling next or destroy, and do not destroy the iterator before this use.");
			return err;
		case -EPROTO:
			verbose(env, "expected an RCU CS when using %s\n", meta->func_name);
			bpf_diag_ctx_required(
				env, insn_idx, meta->func_name, BPF_DIAG_CONTEXT_RCU,
				"Wrap iterator use in bpf_rcu_read_lock() and bpf_rcu_read_unlock(), keeping all exit paths balanced.");
			return err;
		default:
			return err;
		}

		spi = iter_get_spi(env, reg, nr_slots);
		if (spi < 0)
			return spi;

		mark_stack_slots_scratched(env, spi, nr_slots);

		/* remember meta->iter info for process_iter_next_call() */
		meta->iter.spi = spi;
		meta->iter.frameno = reg->frameno;
		update_ref_obj(&meta->ref_obj, &bpf_stack_slot(state, spi)->spilled_ptr);

		if (is_iter_destroy_kfunc(meta)) {
			err = unmark_stack_slots_iter(env, reg, nr_slots);
			if (err)
				return err;
		}
	}

	return 0;
}

/* Look for a previous loop entry at insn_idx: nearest parent state
 * stopped at insn_idx with callsites matching those in cur->frame.
 */
static struct bpf_verifier_state *find_prev_entry(struct bpf_verifier_env *env,
						  struct bpf_verifier_state *cur,
						  int insn_idx)
{
	struct bpf_verifier_state_list *sl;
	struct bpf_verifier_state *st;
	struct list_head *pos, *head;

	/* Explored states are pushed in stack order, most recent states come first */
	head = bpf_explored_state(env, insn_idx);
	list_for_each(pos, head) {
		sl = container_of(pos, struct bpf_verifier_state_list, node);
		/* If st->branches != 0 state is a part of current DFS verification path,
		 * hence cur & st for a loop.
		 */
		st = &sl->state;
		if (st->insn_idx == insn_idx && st->branches && same_callsites(st, cur) &&
		    st->dfs_depth < cur->dfs_depth)
			return st;
	}

	return NULL;
}

/*
 * Check if scalar registers are exact for the purpose of not widening.
 * More lenient than regs_exact()
 */
static bool scalars_exact_for_widen(const struct bpf_reg_state *rold,
				    const struct bpf_reg_state *rcur)
{
	return !memcmp(rold, rcur, offsetof(struct bpf_reg_state, id));
}

static void maybe_widen_reg(struct bpf_verifier_env *env,
			    struct bpf_reg_state *rold, struct bpf_reg_state *rcur)
{
	if (rold->type != SCALAR_VALUE)
		return;
	if (rold->type != rcur->type)
		return;
	if (rold->precise || rcur->precise || scalars_exact_for_widen(rold, rcur))
		return;
	__mark_reg_unknown(env, rcur);
}

static int widen_imprecise_scalars(struct bpf_verifier_env *env,
				   struct bpf_verifier_state *old,
				   struct bpf_verifier_state *cur)
{
	struct bpf_func_state *fold, *fcur;
	int i, fr, num_slots;

	for (fr = old->curframe; fr >= 0; fr--) {
		fold = old->frame[fr];
		fcur = cur->frame[fr];

		for (i = 0; i < MAX_BPF_REG; i++)
			maybe_widen_reg(env,
					&fold->regs[i],
					&fcur->regs[i]);

		num_slots = min(bpf_stack_nr_slots(fold), bpf_stack_nr_slots(fcur));
		for (i = 0; i < num_slots; i++) {
			struct bpf_stack_state *old_ss = bpf_stack_slot(fold, i);
			struct bpf_stack_state *cur_ss = bpf_stack_slot(fcur, i);

			if (!bpf_is_spilled_reg(old_ss) || !bpf_is_spilled_reg(cur_ss))
				continue;

			maybe_widen_reg(env, &old_ss->spilled_ptr, &cur_ss->spilled_ptr);
		}
	}
	return 0;
}

static struct bpf_reg_state *get_iter_from_state(struct bpf_verifier_state *cur_st,
						 struct bpf_call_arg_meta *meta)
{
	int iter_frameno = meta->iter.frameno;
	int iter_spi = meta->iter.spi;

	return &bpf_stack_slot(cur_st->frame[iter_frameno], iter_spi)->spilled_ptr;
}

/* process_iter_next_call() is called when verifier gets to iterator's next
 * "method" (e.g., bpf_iter_num_next() for numbers iterator) call. We'll refer
 * to it as just "iter_next()" in comments below.
 *
 * BPF verifier relies on a crucial contract for any iter_next()
 * implementation: it should *eventually* return NULL, and once that happens
 * it should keep returning NULL. That is, once iterator exhausts elements to
 * iterate, it should never reset or spuriously return new elements.
 *
 * With the assumption of such contract, process_iter_next_call() simulates
 * a fork in the verifier state to validate loop logic correctness and safety
 * without having to simulate infinite amount of iterations.
 *
 * In current state, we first assume that iter_next() returned NULL and
 * iterator state is set to DRAINED (BPF_ITER_STATE_DRAINED). In such
 * conditions we should not form an infinite loop and should eventually reach
 * exit.
 *
 * Besides that, we also fork current state and enqueue it for later
 * verification. In a forked state we keep iterator state as ACTIVE
 * (BPF_ITER_STATE_ACTIVE) and assume non-NULL return from iter_next(). We
 * also bump iteration depth to prevent erroneous infinite loop detection
 * later on (see iter_active_depths_differ() comment for details). In this
 * state we assume that we'll eventually loop back to another iter_next()
 * calls (it could be in exactly same location or in some other instruction,
 * it doesn't matter, we don't make any unnecessary assumptions about this,
 * everything revolves around iterator state in a stack slot, not which
 * instruction is calling iter_next()). When that happens, we either will come
 * to iter_next() with equivalent state and can conclude that next iteration
 * will proceed in exactly the same way as we just verified, so it's safe to
 * assume that loop converges. If not, we'll go on another iteration
 * simulation with a different input state, until all possible starting states
 * are validated or we reach maximum number of instructions limit.
 *
 * This way, we will either exhaustively discover all possible input states
 * that iterator loop can start with and eventually will converge, or we'll
 * effectively regress into bounded loop simulation logic and either reach
 * maximum number of instructions if loop is not provably convergent, or there
 * is some statically known limit on number of iterations (e.g., if there is
 * an explicit `if n > 100 then break;` statement somewhere in the loop).
 *
 * Iteration convergence logic in is_state_visited() relies on exact
 * states comparison, which ignores read and precision marks.
 * This is necessary because read and precision marks are not finalized
 * while in the loop. Exact comparison might preclude convergence for
 * simple programs like below:
 *
 *     i = 0;
 *     while(iter_next(&it))
 *       i++;
 *
 * At each iteration step i++ would produce a new distinct state and
 * eventually instruction processing limit would be reached.
 *
 * To avoid such behavior speculatively forget (widen) range for
 * imprecise scalar registers, if those registers were not precise at the
 * end of the previous iteration and do not match exactly.
 *
 * This is a conservative heuristic that allows to verify wide range of programs,
 * however it precludes verification of programs that conjure an
 * imprecise value on the first loop iteration and use it as precise on a second.
 * For example, the following safe program would fail to verify:
 *
 *     struct bpf_num_iter it;
 *     int arr[10];
 *     int i = 0, a = 0;
 *     bpf_iter_num_new(&it, 0, 10);
 *     while (bpf_iter_num_next(&it)) {
 *       if (a == 0) {
 *         a = 1;
 *         i = 7; // Because i changed verifier would forget
 *                // it's range on second loop entry.
 *       } else {
 *         arr[i] = 42; // This would fail to verify.
 *       }
 *     }
 *     bpf_iter_num_destroy(&it);
 */
static int process_iter_next_call(struct bpf_verifier_env *env, int insn_idx,
				  struct bpf_call_arg_meta *meta)
{
	struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st;
	struct bpf_func_state *cur_fr = cur_st->frame[cur_st->curframe], *queued_fr;
	struct bpf_reg_state *cur_iter, *queued_iter;

	BTF_TYPE_EMIT(struct bpf_iter);

	cur_iter = get_iter_from_state(cur_st, meta);

	if (cur_iter->iter.state != BPF_ITER_STATE_ACTIVE &&
	    cur_iter->iter.state != BPF_ITER_STATE_DRAINED) {
		verifier_bug(env, "unexpected iterator state %d (%s)",
			     cur_iter->iter.state, iter_state_str(cur_iter->iter.state));
		return -EFAULT;
	}

	if (cur_iter->iter.state == BPF_ITER_STATE_ACTIVE) {
		/* Because iter_next() call is a checkpoint is_state_visitied()
		 * should guarantee parent state with same call sites and insn_idx.
		 */
		if (!cur_st->parent || cur_st->parent->insn_idx != insn_idx ||
		    !same_callsites(cur_st->parent, cur_st)) {
			verifier_bug(env, "bad parent state for iter next call");
			return -EFAULT;
		}
		/* Note cur_st->parent in the call below, it is necessary to skip
		 * checkpoint created for cur_st by is_state_visited()
		 * right at this instruction.
		 */
		prev_st = find_prev_entry(env, cur_st->parent, insn_idx);
		/* branch out active iter state */
		queued_st = push_stack(env, insn_idx + 1, insn_idx, false);
		if (IS_ERR(queued_st))
			return PTR_ERR(queued_st);

		queued_iter = get_iter_from_state(queued_st, meta);
		queued_iter->iter.state = BPF_ITER_STATE_ACTIVE;
		queued_iter->iter.depth++;
		if (prev_st)
			widen_imprecise_scalars(env, prev_st, queued_st);

		queued_fr = queued_st->frame[queued_st->curframe];
		mark_ptr_not_null_reg(&queued_fr->regs[BPF_REG_0]);
	}

	/* switch to DRAINED state, but keep the depth unchanged */
	/* mark current iter state as drained and assume returned NULL */
	cur_iter->iter.state = BPF_ITER_STATE_DRAINED;
	__mark_reg_const_zero(env, &cur_fr->regs[BPF_REG_0]);

	return 0;
}

static bool arg_type_is_mem_size(enum bpf_arg_type type)
{
	return type == ARG_MEM_SIZE || type == ARG_MEM_SIZE_OR_ZERO;
}

static bool arg_type_is_raw_mem(enum bpf_arg_type type)
{
	/*
	 * A map value output buffer (e.g. bpf_map_pop_elem) is also a raw
	 * (uninitialized) memory argument, and like ARG_PTR_TO_MEM it may be
	 * passed as a PTR_TO_STACK that reaches check_stack_range_initialized().
	 */
	return (base_type(type) == ARG_PTR_TO_MEM ||
		base_type(type) == ARG_PTR_TO_MAP_VALUE) &&
	       type & MEM_UNINIT;
}

static bool arg_type_is_release(enum bpf_arg_type type)
{
	return type & OBJ_RELEASE;
}

static bool arg_type_is_dynptr(enum bpf_arg_type type)
{
	return base_type(type) == ARG_PTR_TO_DYNPTR;
}

/*
 * An argument that only ever takes a scalar, so a zero register passed to it
 * is a value rather than a NULL pointer.
 */
static bool arg_type_is_scalar(enum bpf_arg_type type)
{
	switch (base_type(type)) {
	case ARG_SCALAR:
	case ARG_CONST_SCALAR:
	case ARG_MEM_SIZE:
	case ARG_MEM_SIZE_OR_ZERO:
	case ARG_CONST_MEM_SIZE:
	case ARG_CONST_ALLOC_SIZE_OR_ZERO:
		return true;
	default:
		return false;
	}
}

/*
 * A helper has no BTF and a nonzero function ID. A kfunc has both, while a
 * BPF subprogram has BTF and a zero function ID.
 */
static bool is_helper(const struct bpf_call_arg_meta *meta)
{
	return !meta->btf && meta->func_id;
}

static bool is_helper_call(const struct bpf_call_arg_meta *meta, enum bpf_func_id func_id)
{
	return is_helper(meta) && meta->func_id == func_id;
}

static bool is_kfunc(const struct bpf_call_arg_meta *meta)
{
	return meta->btf && meta->func_id;
}

static bool is_kfunc_call(const struct bpf_call_arg_meta *meta, u32 btf_id)
{
	return is_kfunc(meta) && meta->func_id == btf_id;
}

static int resolve_map_arg_type(struct bpf_verifier_env *env,
				const struct bpf_call_arg_meta *meta,
				enum bpf_arg_type *arg_type)
{
	if (!meta->map.ptr) {
		/* kernel subsystem misconfigured verifier */
		verifier_bug(env, "invalid map_ptr to access map->type");
		return -EFAULT;
	}

	switch (meta->map.ptr->map_type) {
	case BPF_MAP_TYPE_SOCKMAP:
	case BPF_MAP_TYPE_SOCKHASH:
		if (*arg_type == ARG_PTR_TO_MAP_VALUE) {
			*arg_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON;
		} else {
			verbose(env, "invalid arg_type for sockmap/sockhash\n");
			return -EINVAL;
		}
		break;
	case BPF_MAP_TYPE_BLOOM_FILTER:
		if (is_helper_call(meta, BPF_FUNC_map_peek_elem))
			*arg_type = ARG_PTR_TO_MAP_VALUE;
		break;
	default:
		break;
	}
	return 0;
}

static int resolve_func_arg_type(struct bpf_verifier_env *env,
				 struct bpf_reg_state *reg, u32 arg, argno_t argno,
				 struct bpf_call_arg_meta *meta,
				 enum bpf_arg_type *arg_type, u32 *arg_size);
static int process_arg_ptr_to_btf_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				     argno_t argno, enum bpf_arg_type arg_type,
				     const struct btf *arg_btf, u32 arg_btf_id,
				     struct bpf_call_arg_meta *meta, int insn_idx);
static bool is_kfunc_arg_nonown_allowed(const struct btf *btf,
					const struct btf_param *arg);
static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
					  const struct btf_param *arg,
					  const char *name);
static bool is_bpf_cast_to_kern_ctx_kfunc(const struct bpf_call_arg_meta *meta);
static bool is_bpf_dynptr_clone_kfunc(const struct bpf_call_arg_meta *meta);
static bool is_bpf_iter_css_task_new_kfunc(const struct bpf_call_arg_meta *meta);
static bool is_kfunc_dynptr_write(struct bpf_call_arg_meta *meta);
static bool is_bpf_obj_drop_kfunc(u32 func_id);
static bool is_bpf_percpu_obj_drop_kfunc(u32 func_id);
static bool is_bpf_rbtree_add_kfunc(u32 func_id);
static int get_bpf_res_spin_lock_kfunc_flags(const struct bpf_call_arg_meta *meta);
static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env);
static int process_irq_flag(struct bpf_verifier_env *env,
			    struct bpf_reg_state *reg, argno_t argno,
			    struct bpf_call_arg_meta *meta);
static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env,
					   struct bpf_reg_state *reg,
					   argno_t argno,
					   struct bpf_call_arg_meta *meta);
static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env,
					     struct bpf_reg_state *reg,
					     argno_t argno,
					     struct bpf_call_arg_meta *meta);
static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env,
					   struct bpf_reg_state *reg,
					   argno_t argno,
					   struct bpf_call_arg_meta *meta);
static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
					     struct bpf_reg_state *reg,
					     argno_t argno,
					     struct bpf_call_arg_meta *meta);
static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env);

struct bpf_reg_types {
	const enum bpf_reg_type types[10];
	u32 *btf_id;
};

static const struct bpf_reg_types sock_types = {
	.types = {
		PTR_TO_SOCK_COMMON,
		PTR_TO_SOCKET,
		PTR_TO_TCP_SOCK,
		PTR_TO_XDP_SOCK,
	},
};

#ifdef CONFIG_NET
static const struct bpf_reg_types btf_id_sock_common_types = {
	.types = {
		PTR_TO_SOCK_COMMON,
		PTR_TO_SOCKET,
		PTR_TO_TCP_SOCK,
		PTR_TO_XDP_SOCK,
		PTR_TO_BTF_ID,
		PTR_TO_BTF_ID | PTR_TRUSTED,
	},
	.btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON],
};
#endif

static const struct bpf_reg_types mem_types = {
	.types = {
		PTR_TO_STACK,
		PTR_TO_PACKET,
		PTR_TO_PACKET_META,
		PTR_TO_MAP_KEY,
		PTR_TO_MAP_VALUE,
		PTR_TO_MEM,
		PTR_TO_MEM | MEM_RINGBUF,
		PTR_TO_BUF,
		PTR_TO_BTF_ID | PTR_TRUSTED,
		PTR_TO_CTX,
	},
};

static const struct bpf_reg_types map_value_or_alloc_obj_types = {
	.types = {
		PTR_TO_MAP_VALUE,
		PTR_TO_BTF_ID | MEM_ALLOC,
	}
};

static const struct bpf_reg_types fullsock_types = { .types = { PTR_TO_SOCKET } };
static const struct bpf_reg_types scalar_types = { .types = { SCALAR_VALUE } };
static const struct bpf_reg_types context_types = { .types = { PTR_TO_CTX } };
static const struct bpf_reg_types ringbuf_mem_types = { .types = { PTR_TO_MEM | MEM_RINGBUF } };
static const struct bpf_reg_types const_map_ptr_types = { .types = { CONST_PTR_TO_MAP } };
static const struct bpf_reg_types btf_ptr_types = {
	.types = {
		PTR_TO_BTF_ID,
		PTR_TO_BTF_ID | PTR_TRUSTED,
		PTR_TO_BTF_ID | MEM_RCU,
	},
};
static const struct bpf_reg_types percpu_btf_ptr_types = {
	.types = {
		PTR_TO_BTF_ID | MEM_PERCPU,
		PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU,
		PTR_TO_BTF_ID | MEM_PERCPU | PTR_TRUSTED,
	}
};
static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } };
static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types map_value_types = { .types = { PTR_TO_MAP_VALUE } };
static const struct bpf_reg_types arena_types = {
	.types = {
		PTR_TO_ARENA,
		SCALAR_VALUE,
	}
};
static const struct bpf_reg_types ctx_out_types = {
	.types = { PTR_TO_MEM | MEM_RDONLY | PTR_TRUSTED },
};

static const struct bpf_reg_types alloc_obj_drop_types = {
	.types = {
		PTR_TO_BTF_ID | MEM_ALLOC,
		PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU,
	}
};

static const struct bpf_reg_types alloc_obj_types = {
	.types = {
		PTR_TO_BTF_ID | MEM_ALLOC,
		PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU,
		PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF,
		PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU,
	}
};

static const struct bpf_reg_types kptr_xchg_dest_types = {
	.types = {
		PTR_TO_MAP_VALUE,
		PTR_TO_BTF_ID | MEM_ALLOC,
		PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF,
		PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU,
	}
};
static const struct bpf_reg_types dynptr_types = {
	.types = {
		PTR_TO_STACK,
		CONST_PTR_TO_DYNPTR,
	}
};

static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
	[ARG_PTR_TO_MAP_KEY]		= &mem_types,
	[ARG_PTR_TO_MAP_VALUE]		= &mem_types,
	[ARG_MEM_SIZE]			= &scalar_types,
	[ARG_MEM_SIZE_OR_ZERO]		= &scalar_types,
	[ARG_CONST_ALLOC_SIZE_OR_ZERO]	= &scalar_types,
	[ARG_SCALAR]			= &scalar_types,
	[ARG_CONST_MAP_PTR]		= &const_map_ptr_types,
	[ARG_PTR_TO_CTX]		= &context_types,
	[ARG_PTR_TO_SOCK_COMMON]	= &sock_types,
#ifdef CONFIG_NET
	[ARG_PTR_TO_BTF_ID_SOCK_COMMON]	= &btf_id_sock_common_types,
#endif
	[ARG_PTR_TO_SOCKET]		= &fullsock_types,
	[ARG_PTR_TO_BTF_ID]		= &btf_ptr_types,
	[ARG_PTR_TO_SPIN_LOCK]		= &map_value_or_alloc_obj_types,
	[ARG_PTR_TO_MEM]		= &mem_types,
	[ARG_PTR_TO_RINGBUF_MEM]	= &ringbuf_mem_types,
	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
	[ARG_PTR_TO_FUNC]		= &func_ptr_types,
	[ARG_PTR_TO_STACK]		= &stack_ptr_types,
	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
	[ARG_PTR_TO_TIMER]		= &map_value_types,
	[ARG_KPTR_XCHG_DEST]		= &kptr_xchg_dest_types,
	[ARG_PTR_TO_DYNPTR]		= &dynptr_types,
	[ARG_CONST_SCALAR]		= &scalar_types,
	[ARG_CONST_MEM_SIZE]		= &scalar_types,
	[ARG_PTR_TO_ALLOC_BTF_ID]	= &alloc_obj_drop_types,
	[ARG_PTR_TO_REFCOUNTED_KPTR]	= &alloc_obj_types,
	[ARG_PTR_TO_ITER]		= &stack_ptr_types,
	[ARG_PTR_TO_LIST_HEAD]		= &map_value_or_alloc_obj_types,
	[ARG_PTR_TO_LIST_NODE]		= &alloc_obj_types,
	[ARG_PTR_TO_RB_ROOT]		= &map_value_or_alloc_obj_types,
	[ARG_PTR_TO_RB_NODE]		= &alloc_obj_types,
	[ARG_PTR_TO_RES_SPIN_LOCK]	= &map_value_or_alloc_obj_types,
	[ARG_PTR_TO_WORKQUEUE]		= &map_value_types,
	[ARG_PTR_TO_TASK_WORK]		= &map_value_types,
	[ARG_PTR_TO_RCU_HEAD]		= &map_value_types,
	[ARG_PTR_TO_IRQ_FLAG]		= &stack_ptr_types,
	[ARG_PTR_TO_ARENA]		= &arena_types,
	[ARG_PTR_TO_CTX_OUT]		= &ctx_out_types,
};

static void bpf_diag_call_arg(struct bpf_verifier_env *env, u32 insn_idx, argno_t argno,
			      const char *call_name, const char *reason,
			      const char *suggestion)
{
	int arg = arg_from_argno(argno);
	int regno = reg_from_argno(argno);
	int stack_slot = -1;

	if (arg < 0 && regno >= BPF_REG_1 && regno <= BPF_REG_5)
		arg = regno;
	if (arg > MAX_BPF_FUNC_REG_ARGS)
		stack_slot = arg - MAX_BPF_FUNC_REG_ARGS - 1;

	bpf_diag_call_type(env, insn_idx, arg, regno, stack_slot,
			   call_name && *call_name ? call_name : "call",
			   reg_arg_name(env, argno), reason, suggestion);
}

static const char *bpf_diag_arg_name(struct bpf_verifier_env *env, argno_t argno)
{
	return bpf_diag_fmt(env, "%s", reg_arg_name(env, argno));
}

__printf(6, 7) static void bpf_diag_call_arg_fmt(struct bpf_verifier_env *env, u32 insn_idx,
						 argno_t argno, const char *call_name,
						 const char *suggestion, const char *fmt, ...)
{
	const char *reason;
	va_list args;

	va_start(args, fmt);
	reason = bpf_diag_vfmt(env, fmt, args);
	va_end(args);

	bpf_diag_call_arg(env, insn_idx, argno, call_name, reason, suggestion);
}

static int check_func_arg_nullability(struct bpf_verifier_env *env,
				      struct bpf_reg_state *reg, u32 arg, argno_t argno,
				      enum bpf_arg_type arg_type,
				      struct bpf_call_arg_meta *meta, int insn_idx)
{
	const char *expected_type = "pointer";

	if (arg_type_is_scalar(arg_type) || type_may_be_null(arg_type) ||
	    (!bpf_register_is_null(reg) && !type_may_be_null(reg->type)))
		return 0;

	if (meta->btf) {
		u32 arg_btf_id;

		arg_btf_id = btf_params(meta->func_proto)[arg].type;
		expected_type = bpf_diag_fmt(env, "value of type %s",
					     bpf_diag_fmt_btf_type(env, meta->btf, arg_btf_id));
	}

	verbose(env, "Possibly NULL pointer passed to trusted %s\n",
		reg_arg_name(env, argno));
	bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
			      "Add a NULL check and make the call only on the non-NULL path.",
			      "the pointer may be NULL, but this call requires a non-NULL %s",
			      expected_type);
	return -EACCES;
}

static int check_func_arg_release(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				  u32 arg, argno_t argno, enum bpf_arg_type arg_type,
				  struct bpf_call_arg_meta *meta, int insn_idx)
{
	const char *expected_type = "pointer";

	if (!arg_type_is_release(arg_type))
		return 0;

	if (arg_type_is_dynptr(arg_type) || reg_is_referenced(env, reg) ||
	    bpf_register_is_null(reg))
		return 0;

	verbose(env, "release function %s expects referenced PTR_TO_BTF_ID passed to %s\n",
		meta->func_name, reg_arg_name(env, argno));

	if (is_kfunc(meta)) {
		const struct btf_param *btf_arg;
		const struct btf_type *t;
		u32 ref_id;

		btf_arg = &btf_params(meta->func_proto)[arg];
		ref_id = btf_arg->type;
		t = btf_type_skip_modifiers(meta->btf, btf_arg->type, NULL);
		if (btf_type_is_ptr(t))
			btf_type_skip_modifiers(meta->btf, t->type, &ref_id);
		expected_type = bpf_diag_fmt(env, "value of type %s",
					     bpf_diag_fmt_btf_type(env, meta->btf, ref_id));
	}

	bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
			      bpf_diag_fmt(env, "Pass the resource-owning %s returned by the matching acquire call, or avoid the release function after ownership has already been transferred or released.",
					   expected_type),
			      "release functions require a value that owns a live resource returned by a matching acquire function");
	return -EINVAL;
}

static const char *bpf_diag_expected_reg_types(struct bpf_verifier_env *env,
					       const enum bpf_reg_type *types, int count)
{
	size_t len = 0, size = 1;
	char *buf;
	int i;

	for (i = 0; i < count; i++)
		size += strlen(reg_type_str(env, types[i])) + (i ? 2 : 0);

	buf = bpf_diag_fmt_buf(env, size);
	if (!buf)
		return "";

	for (i = 0; i < count; i++)
		len += scnprintf(buf + len, size - len, "%s%s", i ? ", " : "",
				 reg_type_str(env, types[i]));
	return buf;
}

static int check_reg_type(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
			  enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta)
{
	enum bpf_reg_type expected, type = reg->type;
	const struct bpf_reg_types *compatible;
	const char *actual, *accepted;
	int i, j;

	compatible = compatible_reg_types[base_type(arg_type)];
	if (!compatible) {
		verifier_bug(env, "unsupported arg type %d", arg_type);
		return -EFAULT;
	}
	if (is_kfunc(meta) && base_type(arg_type) == ARG_PTR_TO_BTF_ID &&
	    (base_type(type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(type)]))
		goto found;

	/* ARG_PTR_TO_MEM + RDONLY is compatible with PTR_TO_MEM and PTR_TO_MEM + RDONLY,
	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM and NOT with PTR_TO_MEM + RDONLY
	 *
	 * Same for MAYBE_NULL:
	 *
	 * ARG_PTR_TO_MEM + MAYBE_NULL is compatible with PTR_TO_MEM and PTR_TO_MEM + MAYBE_NULL,
	 * but ARG_PTR_TO_MEM is compatible only with PTR_TO_MEM but NOT with PTR_TO_MEM + MAYBE_NULL
	 *
	 * ARG_PTR_TO_MEM is compatible with PTR_TO_MEM that is tagged with a dynptr type.
	 *
	 * Therefore we fold these flags depending on the arg_type before comparison.
	 */
	if (arg_type & MEM_RDONLY)
		type &= ~MEM_RDONLY;
	if (arg_type & PTR_MAYBE_NULL)
		type &= ~PTR_MAYBE_NULL;
	if (base_type(arg_type) == ARG_PTR_TO_MEM)
		type &= ~DYNPTR_TYPE_FLAG_MASK;
	/* Allow allocated memory for BTF-defined ARG_PTR_TO_MEM but not helpers. */
	if (!is_helper(meta) && base_type(arg_type) == ARG_PTR_TO_MEM &&
	    type_is_ptr_alloc_obj(type))
		type = PTR_TO_MEM;

	/* Local kptr types are allowed as the source argument of bpf_kptr_xchg */
	if (is_helper_call(meta, BPF_FUNC_kptr_xchg) && type_is_alloc(type) &&
	    reg_from_argno(argno) == BPF_REG_2) {
		type &= ~MEM_ALLOC;
		type &= ~MEM_PERCPU;
	}

	for (i = 0; i < ARRAY_SIZE(compatible->types); i++) {
		expected = compatible->types[i];
		if (expected == NOT_INIT)
			break;

		if (type == expected)
			goto found;
	}

	verbose(env, "%s type=%s expected=", reg_arg_name(env, argno), reg_type_str(env, reg->type));
	for (j = 0; j + 1 < i; j++)
		verbose(env, "%s, ", reg_type_str(env, compatible->types[j]));
	verbose(env, "%s\n", reg_type_str(env, compatible->types[j]));
	actual = bpf_diag_fmt(env, "%s", reg_type_str(env, reg->type));
	accepted = bpf_diag_expected_reg_types(env, compatible->types, i);
	bpf_diag_call_arg_fmt(env, env->insn_idx, argno, meta->func_name,
			      bpf_diag_fmt(env, "Pass %s.", bpf_diag_arg_type_plain(arg_type)),
			      "it has type %s, but this argument accepts %s",
			      actual, accepted);
	return -EACCES;

found:
	return 0;
}

static struct btf_field *
reg_find_field_offset(const struct bpf_reg_state *reg, s32 off, u32 fields)
{
	struct btf_field *field;
	struct btf_record *rec;

	rec = reg_btf_record(reg);
	if (!rec)
		return NULL;

	field = btf_record_find(rec, off, fields);
	if (!field)
		return NULL;

	return field;
}

static int check_func_arg_reg_off(struct bpf_verifier_env *env,
				  const struct bpf_reg_state *reg, argno_t argno,
				  enum bpf_arg_type arg_type)
{
	u32 type = reg->type;

	/* When referenced register is passed to release function, its fixed
	 * offset must be 0.
	 *
	 * We will check arg_type_is_release reg has id when storing
	 * meta->release_regno.
	 */
	if (arg_type_is_release(arg_type)) {
		/* ARG_PTR_TO_DYNPTR with OBJ_RELEASE is a bit special, as it
		 * may not directly point to the object being released, but to
		 * dynptr pointing to such object, which might be at some offset
		 * on the stack. In that case, we simply to fallback to the
		 * default handling.
		 */
		if (arg_type_is_dynptr(arg_type) && type == PTR_TO_STACK)
			return 0;

		/* Doing check_ptr_off_reg check for the offset will catch this
		 * because fixed_off_ok is false, but checking here allows us
		 * to give the user a better error message.
		 */
		if (!tnum_is_const(reg->var_off) || reg->var_off.value != 0) {
			verbose(env, "%s must have zero offset when passed to release func or trusted arg to kfunc\n",
				reg_arg_name(env, argno));
			return -EINVAL;
		}
	}

	switch (type) {
	/* Pointer types where both fixed and variable offset is explicitly allowed: */
	case PTR_TO_STACK:
	case PTR_TO_PACKET:
	case PTR_TO_PACKET_META:
	case PTR_TO_MAP_KEY:
	case PTR_TO_MAP_VALUE:
	case PTR_TO_MEM:
	case PTR_TO_MEM | MEM_RDONLY:
	case PTR_TO_MEM | MEM_RINGBUF:
	case PTR_TO_BUF:
	case PTR_TO_BUF | MEM_RDONLY:
	case PTR_TO_ARENA:
	case SCALAR_VALUE:
		return 0;
	/* All the rest must be rejected, except PTR_TO_BTF_ID which allows
	 * fixed offset.
	 */
	case PTR_TO_BTF_ID:
	case PTR_TO_BTF_ID | MEM_ALLOC:
	case PTR_TO_BTF_ID | PTR_TRUSTED:
	case PTR_TO_BTF_ID | MEM_RCU:
	case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF:
	case PTR_TO_BTF_ID | MEM_ALLOC | NON_OWN_REF | MEM_RCU:
		/* When referenced PTR_TO_BTF_ID is passed to release function,
		 * its fixed offset must be 0. bpf_refcount_acquire() returns the
		 * pointer it was given while incrementing the refcount at the
		 * refcount field offset, so it needs a zero offset too. In the
		 * other cases, fixed offset can be non-zero. var_off always must
		 * be 0 for PTR_TO_BTF_ID, hence we still need to do checks
		 * instead of returning.
		 */
		return __check_ptr_off_reg(env, reg, argno,
					   base_type(arg_type) != ARG_PTR_TO_REFCOUNTED_KPTR);
	case PTR_TO_CTX:
		/*
		 * Allow fixed and variable offsets for syscall context, but
		 * only when the argument is passed as memory, not ctx,
		 * otherwise we may get modified ctx in tail called programs and
		 * global subprogs (that may act as extension prog hooks).
		 */
		if (base_type(arg_type) != ARG_PTR_TO_CTX && is_var_ctx_off_allowed(env->prog))
			return 0;
		fallthrough;
	default:
		return __check_ptr_off_reg(env, reg, argno, false);
	}
}

static int check_arg_const_str(struct bpf_verifier_env *env,
			       struct bpf_reg_state *reg, argno_t argno)
{
	struct bpf_map *map = reg->map_ptr;
	int err;
	int map_off;
	u64 map_addr;
	char *str_ptr;
	u32 cnt;

	if (reg->type != PTR_TO_MAP_VALUE)
		return -EINVAL;

	if (map->map_type == BPF_MAP_TYPE_INSN_ARRAY) {
		verbose(env, "%s points to insn_array map which cannot be used as const string\n",
			reg_arg_name(env, argno));
		return -EACCES;
	}

	if (map->map_type == BPF_MAP_TYPE_PERCPU_ARRAY) {
		verbose(env, "%s points to percpu_array map which cannot be used as const string\n",
			reg_arg_name(env, argno));
		return -EACCES;
	}

	if (!bpf_map_is_rdonly(map)) {
		verbose(env, "%s does not point to a readonly map'\n", reg_arg_name(env, argno));
		return -EACCES;
	}

	if (!tnum_is_const(reg->var_off)) {
		verbose(env, "%s is not a constant address'\n", reg_arg_name(env, argno));
		return -EACCES;
	}

	if (!map->ops->map_direct_value_addr) {
		verbose(env, "no direct value access support for this map type\n");
		return -EACCES;
	}

	err = check_map_access(env, reg, argno, 0,
			       map->value_size - reg->var_off.value, false,
			       ACCESS_HELPER);
	if (err)
		return err;

	map_off = reg->var_off.value;
	err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
	if (err) {
		verbose(env, "direct value access on string failed\n");
		return err;
	}

	str_ptr = (char *)(long)(map_addr);
	if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
		verbose(env, "string is not zero-terminated\n");
		return -EINVAL;
	}
	/* the bytes of a pointer to a function are not known until the program is jitted */
	if (bpf_map_range_func_ptrs(env, map, map_off, strlen(str_ptr + map_off) + 1, &cnt)) {
		verbose(env, "string overlaps with a pointer to a function\n");
		return -EACCES;
	}
	return 0;
}

/* Returns constant key value in `value` if possible, else negative error */
static int get_constant_map_key(struct bpf_verifier_env *env,
				struct bpf_reg_state *key,
				u32 key_size,
				s64 *value)
{
	struct bpf_func_state *state = bpf_func(env, key);
	struct bpf_stack_state *ss;
	struct bpf_reg_state *reg;
	int slot, spi, off;
	int spill_size = 0;
	int zero_size = 0;
	int stack_off;
	int i, err;
	u8 *stype;

	if (!env->bpf_capable)
		return -EOPNOTSUPP;
	if (key->type != PTR_TO_STACK)
		return -EOPNOTSUPP;
	if (!tnum_is_const(key->var_off))
		return -EOPNOTSUPP;

	stack_off = key->var_off.value;
	slot = -stack_off - 1;
	spi = slot / BPF_REG_SIZE;
	off = slot % BPF_REG_SIZE;
	ss = bpf_stack_slot(state, spi);
	stype = ss->slot_type;

	/* First handle precisely tracked STACK_ZERO */
	for (i = off; i >= 0 && stype[i] == STACK_ZERO; i--)
		zero_size++;
	if (zero_size >= key_size) {
		*value = 0;
		return 0;
	}

	/* Check that stack contains a scalar spill of expected size */
	if (!bpf_is_spilled_scalar_reg(ss))
		return -EOPNOTSUPP;
	for (i = off; i >= 0 && stype[i] == STACK_SPILL; i--)
		spill_size++;
	if (spill_size != key_size)
		return -EOPNOTSUPP;

	reg = &ss->spilled_ptr;
	if (!tnum_is_const(reg->var_off))
		/* Stack value not statically known */
		return -EOPNOTSUPP;

	/* We are relying on a constant value. So mark as precise
	 * to prevent pruning on it.
	 */
	bpf_bt_set_frame_slot(&env->bt, key->frameno, spi);
	err = mark_chain_precision_batch(env, env->cur_state);
	if (err < 0)
		return err;

	*value = reg->var_off.value;
	return 0;
}

static bool can_elide_value_nullness(const struct bpf_map *map);

static int process_map_ptr_arg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
			       argno_t argno, struct bpf_call_arg_meta *meta)
{
	/* Use map_uid (which is unique id of inner map) to reject:
	 * inner_map1 = bpf_map_lookup_elem(outer_map, key1)
	 * inner_map2 = bpf_map_lookup_elem(outer_map, key2)
	 * if (inner_map1 && inner_map2) {
	 *     timer = bpf_map_lookup_elem(inner_map1);
	 *     if (timer)
	 *         // mismatch would have been allowed
	 *         bpf_timer_init(timer, inner_map2);
	 * }
	 *
	 * Comparing map_ptr is enough to distinguish normal and outer maps.
	 */
	if (meta->map.ptr &&
	    (meta->map.ptr != reg->map_ptr || meta->map.uid != reg->map_uid)) {
		argno_t obj_argno = argno_from_reg(reg_from_argno(argno) - 1);
		struct btf_record *rec = meta->map.ptr->record;
		const char *obj_name = "workqueue";

		if (rec->timer_off >= 0)
			obj_name = "timer";
		else if (rec->task_work_off >= 0)
			obj_name = "bpf_task_work";
		else if (rec->rcu_head_off >= 0)
			obj_name = "bpf_rcu_head";

		verbose(env, "%s pointer in %s map_uid=%d ",
			obj_name, reg_arg_name(env, obj_argno), meta->map.uid);
		verbose(env, "doesn't match map pointer in %s map_uid=%d\n",
			reg_arg_name(env, argno), reg->map_uid);
		return -EINVAL;
	}

	meta->map.ptr = reg->map_ptr;
	meta->map.uid = reg->map_uid;
	return 0;
}

/*
 * MEM_WRITE alone denotes an input/output buffer. MEM_UNINIT marks an output
 * whose incoming contents are not read.
 */
static enum bpf_access_type func_arg_access_type(enum bpf_arg_type arg_type)
{
	if (!(arg_type & MEM_WRITE))
		return BPF_READ;
	if (arg_type & MEM_UNINIT)
		return BPF_WRITE;
	return BPF_READ | BPF_WRITE;
}

static int check_func_arg(struct bpf_verifier_env *env, u32 arg, u32 slot, u32 prev_slot,
			  struct bpf_call_arg_meta *meta,
			  int insn_idx)
{
	const struct btf_param *btf_arg = is_kfunc(meta) ?
					  &btf_params(meta->func_proto)[arg] : NULL;
	const struct bpf_func_proto *fn = meta->fn;
	struct bpf_func_state *caller = cur_func(env);
	struct bpf_reg_state *regs = cur_regs(env);
	argno_t argno = argno_from_arg(slot + 1);
	struct bpf_reg_state *reg = get_func_arg_reg(caller, regs, slot);
	enum bpf_arg_type arg_type = fn->arg_type[arg];
	int regno = reg_from_argno(argno);
	u32 arg_size = arg_type & MEM_FIXED_SIZE ? fn->arg_size[arg] : 0;
	u32 key_size;
	int err = 0;

	if (arg_type == ARG_PTR_TO_PROG_AUX) {
		cur_aux(env)->arg_prog = regno;
		return 0;
	}

	if (arg_type == ARG_IGNORE)
		return 0;

	if (regno >= 0) {
		err = check_reg_arg(env, regno, SRC_OP);
		if (err)
			return err;
	}

	/* Preserve the legacy helper behavior for privileged pointer leaks. */
	if (arg_type == ARG_ANYTHING) {
		if (__is_pointer_value(env->allow_ptr_leaks, reg)) {
			verbose(env, "%s leaks addr into helper function\n",
				reg_arg_name(env, argno));
			return -EACCES;
		}
		return 0;
	}

	err = resolve_func_arg_type(env, reg, arg, argno, meta, &arg_type, &arg_size);
	if (err)
		return err;

	/*
	 * A slice of a packet is packet data under another name. A helper which
	 * may reallocate the packet must not go on reading from the old one.
	 */
	if (is_helper(meta) && reg_is_dynptr_slice_pkt(reg) &&
	    bpf_helper_changes_pkt_data(meta->func_id)) {
		verbose(env, "function access to the packet is not allowed\n");
		return -EACCES;
	}

	if (arg_type_is_raw_mem(arg_type))
		meta->arg_raw_mem.mask |= BIT(slot);

	if (bpf_register_is_null(reg) && type_may_be_null(arg_type)) {
		err = mark_arg_precision(env, argno);
		if (err)
			return err;
		return 0;
	}

	err = check_func_arg_nullability(env, reg, arg, argno, arg_type, meta, insn_idx);
	if (err)
		return err;

	err = check_reg_type(env, reg, argno, arg_type, meta);
	if (err)
		return err;

	err = check_func_arg_reg_off(env, reg, argno, arg_type);
	if (err)
		return err;

	err = check_func_arg_release(env, reg, arg, argno, arg_type, meta, insn_idx);
	if (err)
		return err;

	if (reg_is_referenced(env, reg))
		update_ref_obj(&meta->ref_obj, reg);

	switch (base_type(arg_type)) {
	case ARG_CONST_SCALAR:
		err = process_const_arg(env, reg, argno, meta);
		if (err < 0) {
			if (err == -EINVAL)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
						      "Pass a compile-time constant or a value the verifier can prove is constant at this call.",
						      "the function requires this scalar argument to be a verifier-known constant, but %s is variable on this path",
						      reg_arg_name(env, argno));
			return err;
		}
		break;
	case ARG_SCALAR:
		break;
	case ARG_CONST_MAP_PTR:
		/* bpf_map_xxx(map_ptr) call: remember that map_ptr */
		err = process_map_ptr_arg(env, reg, argno, meta);
		if (err)
			return err;
		break;
	case 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
			 */
			verifier_bug(env, "invalid map_ptr to access map->key");
			return -EFAULT;
		}
		key_size = meta->map.ptr->key_size;
		err = check_helper_mem_access(env, reg, argno, key_size, BPF_READ, false, meta,
					      NULL);
		if (err)
			return err;
		if (can_elide_value_nullness(meta->map.ptr)) {
			err = get_constant_map_key(env, reg, key_size, &meta->const_map_key);
			if (err < 0) {
				meta->const_map_key = -1;
				if (err == -EOPNOTSUPP)
					err = 0;
				else
					return err;
			}
		}
		break;
	case ARG_PTR_TO_MAP_VALUE:
		if (type_may_be_null(arg_type) && bpf_register_is_null(reg))
			return 0;

		/* bpf_map_xxx(..., map_ptr, ..., value) call:
		 * check [value, value + map->value_size) validity
		 */
		if (!meta->map.ptr) {
			/* kernel subsystem misconfigured verifier */
			verifier_bug(env, "invalid map_ptr to access map->value");
			return -EFAULT;
		}

		err = check_helper_mem_access(env, reg, argno, meta->map.ptr->value_size,
					      arg_type & MEM_WRITE ? BPF_WRITE : BPF_READ,
					      false, meta, NULL);
		break;
	case ARG_PTR_TO_BTF_ID:
	case ARG_PTR_TO_BTF_ID_SOCK_COMMON:
	{
		const u32 *arg_btf_id = fn->arg_btf_id[arg];
		const struct btf *arg_btf = is_kfunc(meta) ? meta->btf : btf_vmlinux;
		enum bpf_reg_type reg_type;

		if (!meta->btf) {
			const struct bpf_reg_types *compatible;

			if (base_type(reg->type) != PTR_TO_BTF_ID)
				break;

			if (is_helper_call(meta, BPF_FUNC_kptr_xchg))
				return map_kptr_match_type(env, meta->kptr_field, reg, regno) ?
				       -EACCES : 0;

			if (!arg_btf_id) {
				compatible = compatible_reg_types[base_type(arg_type)];
				if (!compatible->btf_id) {
					verifier_bug(env, "missing arg compatible BTF ID");
					return -EFAULT;
				}
				arg_btf_id = compatible->btf_id;
			}
			if (arg_btf_id == BPF_PTR_POISON) {
				verbose(env, "verifier internal error:");
				verbose(env, "%s has non-overwritten BPF_PTR_POISON type\n",
					reg_arg_name(env, argno));
				return -EACCES;
			}
		}

		reg_type = reg->type & ~(arg_type & PTR_MAYBE_NULL);
		if ((arg_type & PTR_TRUSTED) &&
		    (!is_trusted_reg_type(env, reg, reg_type) ||
		     bpf_type_has_unsafe_modifiers(reg_type))) {
			if (!(arg_type & MEM_RCU)) {
				const char *actual_type, *arg_name, *expected_type;

				expected_type = bpf_diag_fmt_btf_type(env, arg_btf, *arg_btf_id);
				verbose(env, "%s must be referenced or trusted\n",
					reg_arg_name(env, argno));
				arg_name = reg_arg_name(env, argno);
				actual_type = bpf_diag_reg_type_plain(env, reg->type);
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
						      "Pass a pointer acquired from a verifier-tracked source, or call this function only inside the required protection if it accepts RCU pointers.",
						      "the function requires a trusted or resource-owning pointer to %s, but %s is %s",
						      expected_type, arg_name, actual_type);
				return -EINVAL;
			}
			if (!is_rcu_reg(reg)) {
				const char *actual_type, *arg_name, *expected_type;

				expected_type = bpf_diag_fmt_btf_type(env, arg_btf, *arg_btf_id);
				verbose(env, "%s must be a rcu pointer\n",
					reg_arg_name(env, argno));
				arg_name = reg_arg_name(env, argno);
				actual_type = bpf_diag_reg_type_plain(env, reg->type);
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
						      "Use this function with a pointer that is valid in an RCU read lock region.",
						      "the function requires an RCU-protected pointer to %s, but %s is %s",
						      expected_type, arg_name, actual_type);
				return -EINVAL;
			}
		}

		err = process_arg_ptr_to_btf_id(env, reg, argno, arg_type, arg_btf,
						*arg_btf_id, meta, insn_idx);
		if (err < 0)
			return err;
		break;
	}
	case ARG_PTR_TO_PERCPU_BTF_ID:
		if (!reg->btf_id) {
			verbose(env, "Helper has invalid btf_id in %s\n", reg_arg_name(env, argno));
			return -EACCES;
		}
		meta->ret_btf = reg->btf;
		meta->ret_btf_id = reg->btf_id;
		break;
	case ARG_PTR_TO_SPIN_LOCK:
		if (in_rbtree_lock_required_cb(env)) {
			verbose(env, "can't spin_{lock,unlock} in rbtree cb\n");
			return -EACCES;
		}
		if (is_helper_call(meta, BPF_FUNC_spin_lock)) {
			err = process_spin_lock(env, reg, argno, PROCESS_SPIN_LOCK);
			if (err)
				return err;
		} else if (is_helper_call(meta, BPF_FUNC_spin_unlock)) {
			err = process_spin_lock(env, reg, argno, 0);
			if (err)
				return err;
		} else {
			verifier_bug(env, "spin lock arg on unexpected helper");
			return -EFAULT;
		}
		break;
	case ARG_PTR_TO_TIMER:
		err = process_timer_func(env, reg, argno, &meta->map);
		if (err)
			return err;
		break;
	case ARG_PTR_TO_CTX:
		if (is_bpf_cast_to_kern_ctx_kfunc(meta)) {
			err = get_kern_ctx_btf_id(&env->log, resolve_prog_type(env->prog));
			if (err < 0)
				return -EINVAL;
			meta->ret_btf_id = err;
		}
		break;
	case ARG_PTR_TO_ARENA:
		break;
	case ARG_PTR_TO_ALLOC_BTF_ID:
		if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC)) {
			if (!is_bpf_obj_drop_kfunc(meta->func_id)) {
				verbose(env, "%s expected for bpf_obj_drop()\n",
					reg_arg_name(env, argno));
				return -EINVAL;
			}
		} else if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC | MEM_PERCPU)) {
			if (!is_bpf_percpu_obj_drop_kfunc(meta->func_id)) {
				verbose(env, "%s expected for bpf_percpu_obj_drop()\n",
					reg_arg_name(env, argno));
				return -EINVAL;
			}
		}
		if (!reg_is_referenced(env, reg)) {
			verbose(env, "allocated object must be referenced\n");
			bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					      "Pass the owned object pointer before it is released or transferred.",
					      "the allocated object pointer in %s must still carry verifier-tracked ownership, but this pointer no longer owns a live resource",
					      reg_arg_name(env, argno));
			return -EINVAL;
		}
		if (meta->btf == btf_vmlinux) {
			meta->arg_btf = reg->btf;
			meta->arg_btf_id = reg->btf_id;
		}
		break;
	case ARG_PTR_TO_FUNC:
		meta->subprogno = reg->subprogno;
		break;
	case ARG_PTR_TO_MEM:
	{
		enum bpf_access_type access_type;
		bool known_memory;

		/* The access to this pointer is only checked when we hit the
		 * next is_mem_size argument below.
		 */
		if (!(arg_type & MEM_FIXED_SIZE))
			break;

		access_type = func_arg_access_type(arg_type);

		err = check_mem_reg(env, reg, argno, arg_size, access_type, meta, &known_memory);
		if (err < 0) {
			if (known_memory)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					"Pass memory with at least the required number of accessible bytes and suitable read or write access.",
					"the function expects %u bytes of memory, but the verifier cannot prove that %s provides a range of that size with the required read or write access",
					arg_size,
					bpf_diag_reg_type_plain(env, reg->type));
			else
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					"Pass stack, map, context, or other verifier-known memory of the expected type and size, not an integer cast to a pointer.",
					"the function expects %u bytes of memory, but it is %s and not verifier-known memory",
					arg_size,
					bpf_diag_reg_type_plain(env, reg->type));
			return err;
		}
		/*
		 * PTR_TO_PACKET gets passed as PTR_TO_MEM, preventing us from adjusting
		 * bounds tracking information.
		 */
		if (is_subprog(meta) && meta->subprog_may_change_pkt &&
		    (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg))) {
			verbose(env,
				"cannot pass packet pointer %s to %s(): function may change packet data\n",
				reg_arg_name(env, argno), meta->func_name);
			return -EINVAL;
		}
		if (arg_type & MEM_ALIGNED)
			err = check_ptr_alignment(env, reg, 0, arg_size, true);
		break;
	}
	case ARG_CONST_MEM_SIZE:
		err = process_const_arg(env, reg, argno, meta);
		if (err < 0) {
			if (err == -EINVAL)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
						      "Pass a compile-time constant or a value the verifier can prove is constant at this call.",
						      "the function requires this memory size to be a verifier-known constant, but %s is variable on this path",
						      reg_arg_name(env, argno));
			return err;
		}
		fallthrough;
	case ARG_MEM_SIZE:
	case ARG_MEM_SIZE_OR_ZERO:
	{
		struct bpf_reg_state *buff_reg = get_func_arg_reg(caller, regs, prev_slot);
		argno_t buff_argno = argno_from_arg(prev_slot + 1);
		enum bpf_mem_size_failure failure;
		const char *buff_arg, *size_arg;
		bool zero_size_allowed;
		u32 access_type;

		if (meta->btf && bpf_register_is_null(buff_reg))
			break;

		access_type = func_arg_access_type(fn->arg_type[arg - 1]);

		zero_size_allowed = meta->btf || base_type(arg_type) == ARG_MEM_SIZE_OR_ZERO;

		err = check_mem_size_reg(env, buff_reg, reg, buff_argno, argno,
					 access_type, zero_size_allowed, meta, &failure);
		if (!err)
			break;

		buff_arg = bpf_diag_arg_name(env, buff_argno);
		size_arg = bpf_diag_arg_name(env, argno);
		verbose(env, "%s and ", reg_arg_name(env, buff_argno));
		verbose(env, "%s memory, len pair leads to invalid memory access\n",
			reg_arg_name(env, argno));
		if (failure == BPF_MEM_SIZE_FAIL_MEMORY) {
			bpf_diag_call_arg_fmt(env, insn_idx, buff_argno, meta->func_name,
					      "Pass a stack, map, context, or other verifier-known memory pointer, and keep the paired length within that object.",
					      "it is the memory pointer in a memory/length pair with %s, but %s does not provide a verifier-accessible range of the requested length",
					      size_arg, buff_arg);
		} else if (failure == BPF_MEM_SIZE_FAIL_SIZE) {
			if (reg_smin(reg) < 0)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					"Constrain the memory size to a non-negative value smaller than BPF_MAX_VAR_SIZ before this call.",
					"the memory size in %s may be negative because its signed minimum is %lld",
					size_arg, reg_smin(reg));
			else if (!zero_size_allowed && reg_umin(reg) == 0)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					"Ensure the memory size is non-zero before this call.",
					"the memory size in %s may be zero, but the function requires a non-zero size",
					size_arg);
			else
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
					"Constrain the memory size to a non-negative value smaller than BPF_MAX_VAR_SIZ before this call.",
					"the memory size in %s may reach %llu bytes, but variable memory accesses must stay below %u bytes",
					size_arg, reg_umax(reg), BPF_MAX_VAR_SIZ);
		}
		break;
	}
	case ARG_PTR_TO_DYNPTR: {
		if (is_bpf_dynptr_clone_kfunc(meta) &&
		    (arg_type & MEM_UNINIT)) {
			enum bpf_dynptr_type parent_type = meta->dynptr.type;

			if (parent_type == BPF_DYNPTR_TYPE_INVALID) {
				verifier_bug(env, "no dynptr type for parent of clone");
				return -EFAULT;
			}

			arg_type |= (unsigned int)get_dynptr_type_flag(parent_type);
		}

		err = process_dynptr_func(env, reg, argno, insn_idx, arg_type, meta);
		if (err)
			return err;
		if (!arg && is_kfunc_dynptr_write(meta))
			meta->dynptr_write_type = meta->dynptr.type;
		break;
	}
	case ARG_PTR_TO_ITER:
		if (is_bpf_iter_css_task_new_kfunc(meta) &&
		    !check_css_task_iter_allowlist(env)) {
			verbose(env, "css_task_iter is only allowed in bpf_lsm, bpf_iter and sleepable progs\n");
			return -EINVAL;
		}
		err = process_iter_arg(env, reg, arg, argno, insn_idx, meta);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_LIST_HEAD:
		if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) &&
		    !reg_is_referenced(env, reg)) {
			verbose(env, "allocated object must be referenced\n");
			return -EINVAL;
		}
		err = process_kf_arg_ptr_to_list_head(env, reg, argno, meta);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_RB_ROOT:
		if (reg->type == (PTR_TO_BTF_ID | MEM_ALLOC) &&
		    !reg_is_referenced(env, reg)) {
			verbose(env, "allocated object must be referenced\n");
			return -EINVAL;
		}
		err = process_kf_arg_ptr_to_rbtree_root(env, reg, argno, meta);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_LIST_NODE:
		if (!(is_kfunc_arg_nonown_allowed(meta->btf, btf_arg) &&
		      type_is_non_owning_ref(reg->type) && !reg_is_referenced(env, reg))) {
			if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
				verbose(env, "%s expected pointer to allocated object\n",
					reg_arg_name(env, argno));
				return -EINVAL;
			}
			if (!reg_is_referenced(env, reg)) {
				verbose(env, "allocated object must be referenced\n");
				return -EINVAL;
			}
		}
		err = process_kf_arg_ptr_to_list_node(env, reg, argno, meta);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_RB_NODE:
		if (is_bpf_rbtree_add_kfunc(meta->func_id)) {
			if (reg->type != (PTR_TO_BTF_ID | MEM_ALLOC)) {
				verbose(env, "%s expected pointer to allocated object\n",
					reg_arg_name(env, argno));
				return -EINVAL;
			}
			if (!reg_is_referenced(env, reg)) {
				verbose(env, "allocated object must be referenced\n");
				return -EINVAL;
			}
		} else {
			if (!type_is_non_owning_ref(reg->type) &&
			    !reg_is_referenced(env, reg)) {
				verbose(env, "%s can only take non-owning or refcounted bpf_rb_node pointer\n",
					meta->func_name);
				return -EINVAL;
			}
			if (in_rbtree_lock_required_cb(env)) {
				verbose(env, "%s not allowed in rbtree cb\n", meta->func_name);
				return -EINVAL;
			}
		}
		err = process_kf_arg_ptr_to_rbtree_node(env, reg, argno, meta);
		if (err < 0)
			return err;
		break;
	case ARG_CONST_ALLOC_SIZE_OR_ZERO:
		if (meta->btf && is_kfunc_arg_scalar_with_name(meta->btf, btf_arg,
							       "rdonly_buf_size"))
			meta->r0_rdonly = true;
		err = process_const_alloc_mem_size(env, reg, argno, &meta->ret_mem);
		if (err < 0) {
			if (meta->btf && err == -EINVAL)
				bpf_diag_call_arg_fmt(env, insn_idx, argno, meta->func_name,
						      "Pass a verifier-known constant size for this function's buffer argument.",
						      "the function uses this argument as a return-buffer size, but %s is invalid or variable on this path",
						      reg_arg_name(env, argno));
			return err;
		}
		break;
	case ARG_PTR_TO_REFCOUNTED_KPTR:
	{
		struct btf_record *rec;

		if (!type_is_non_owning_ref(reg->type) && reg_is_referenced(env, reg))
			meta->arg_owning_ref = true;

		rec = reg_btf_record(reg);
		if (!rec) {
			verifier_bug(env, "Couldn't find btf_record");
			return -EFAULT;
		}

		if (rec->refcount_off < 0) {
			verbose(env, "%s doesn't point to a type with bpf_refcount field\n",
				reg_arg_name(env, argno));
			return -EINVAL;
		}

		meta->arg_btf = reg->btf;
		meta->arg_btf_id = reg->btf_id;
		break;
	}
	case ARG_PTR_TO_CONST_STR:
	{
		err = check_arg_const_str(env, reg, argno);
		if (err)
			return err;
		break;
	}
	case ARG_PTR_TO_WORKQUEUE:
		err = check_map_field_pointer(env, reg, argno, BPF_WORKQUEUE, &meta->map);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_TASK_WORK:
		err = check_map_field_pointer(env, reg, argno, BPF_TASK_WORK, &meta->map);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_RCU_HEAD:
		err = check_map_field_pointer(env, reg, argno, BPF_RCU_HEAD, &meta->map);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_IRQ_FLAG:
		err = process_irq_flag(env, reg, argno, meta);
		if (err < 0)
			return err;
		break;
	case ARG_PTR_TO_CTX_OUT:
		if (reg->mem_size != arg_size) {
			verbose(env, "%s expected %u bytes of ctx-provided memory, got %u\n",
				reg_arg_name(env, argno), arg_size, reg->mem_size);
			return -EINVAL;
		}
		break;
	case ARG_PTR_TO_RES_SPIN_LOCK:
	{
		int flags;

		if (in_rbtree_lock_required_cb(env)) {
			verbose(env, "can't res_spin_{lock,unlock} in rbtree cb\n");
			return -EACCES;
		}

		flags = get_bpf_res_spin_lock_kfunc_flags(meta);
		if (!flags)
			return -EFAULT;
		err = process_spin_lock(env, reg, argno, flags);
		if (err < 0)
			return err;
		break;
	}
	case ARG_KPTR_XCHG_DEST:
		err = process_kptr_func(env, regno, meta);
		if (err)
			return err;
		break;
	}

	return err;
}

/*
 * The slots a parameter takes, from its BTF type. This has to agree with
 * btf_func_model_arg_slots(), which answers the same from the size the
 * func model recorded, or the verifier would check an argument at a slot
 * the JIT does not place it at.
 */
static u32 btf_arg_slots(const struct btf_type *t)
{
	if (btf_type_is_int(t) || btf_type_is_struct(t))
		return (t->size + BPF_REG_SIZE - 1) / BPF_REG_SIZE;
	return 1;
}

static u32 btf_proto_slots(const struct btf *btf, const struct btf_type *func_proto)
{
	const struct btf_param *args = btf_params(func_proto);
	u32 i, nargs = btf_type_vlen(func_proto), slots_used = 0;

	for (i = 0; i < nargs; i++)
		slots_used += btf_arg_slots(btf_type_skip_modifiers(btf, args[i].type, NULL));

	return slots_used;
}

/* The argument slot @slot holds an eightbyte of a by-value argument. */
static int check_arg_extra_slot(struct bpf_verifier_env *env, struct bpf_func_state *caller,
				u32 slot, struct bpf_call_arg_meta *meta)
{
	struct bpf_reg_state *reg = get_func_arg_reg(caller, cur_regs(env), slot);
	argno_t argno = argno_from_arg(slot + 1);
	int regno = reg_from_argno(argno);
	int err;

	if (regno >= 0) {
		err = check_reg_arg(env, regno, SRC_OP);
		if (err)
			return err;
	}

	return check_reg_type(env, reg, argno, ARG_SCALAR, meta);
}

static int check_func_args(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
			   int insn_idx)
{
	u32 slot = 0, prev_slot = 0, proto_slots, nslots;
	struct bpf_func_state *caller = cur_func(env);
	const struct btf_param *args = NULL;
	u32 arg, nargs = MAX_BPF_FUNC_REG_ARGS;
	int err;

	if (meta->btf) {
		args = btf_params(meta->func_proto);
		nargs = btf_type_vlen(meta->func_proto);
	}

	/*
	 * A by-value argument of more than one eightbyte takes a slot per
	 * eightbyte, so the slots a call occupies are no longer its parameter
	 * count. Only a proto whose parameters take a slot each can name the
	 * argument a stack slot belongs to.
	 */
	proto_slots = meta->btf ? btf_proto_slots(meta->btf, meta->func_proto) : nargs;

	if (proto_slots > MAX_BPF_FUNC_REG_ARGS) {
		err = check_outgoing_stack_args(env, caller, proto_slots, meta->func_name,
						meta->btf, proto_slots == nargs ? args : NULL);
		if (err)
			return err;
	}

	for (arg = 0; arg < nargs; arg++, prev_slot = slot, slot += nslots) {
		const struct btf_type *t;
		u32 k;

		nslots = 1;
		if (args) {
			t = btf_type_skip_modifiers(meta->btf, args[arg].type, NULL);
			nslots = btf_arg_slots(t);
		}

		if (meta->fn->arg_type[arg] == ARG_UNUSED)
			break;
		err = check_func_arg(env, arg, slot, prev_slot, meta, insn_idx);
		if (err)
			return err;

		/*
		 * check_func_arg() took the first slot. A parameter of more
		 * than one eightbyte is always a scalar, so every slot it
		 * takes beyond the first holds one too.
		 */
		for (k = 1; k < nslots; k++) {
			err = check_arg_extra_slot(env, caller, slot + k, meta);
			if (err)
				return err;
		}
	}

	return 0;
}

static int mark_raw_stack(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
			  int insn_idx)
{
	struct bpf_func_state *caller = cur_func(env);
	u32 slot;
	int i, err;

	/*
	 * Validate every argument before initializing outputs: an input argument
	 * may alias an output buffer. Use the normal stack-write checks to discard
	 * stale spills and preserve the rules for special stack objects.
	 */
	for (slot = 0; slot < MAX_BPF_FUNC_ARGS; slot++) {
		struct bpf_reg_state *reg;
		argno_t argno = argno_from_arg(slot + 1);

		if (!meta->arg_raw_mem.size[slot])
			continue;
		reg = get_func_arg_reg(caller, cur_regs(env), slot);

		for (i = 0; i < meta->arg_raw_mem.size[slot]; i++) {
			err = check_mem_access(env, insn_idx, reg, argno, i, BPF_B,
					       BPF_WRITE, -1, false, false);
			if (err)
				return err;
		}
	}

	return 0;
}

static bool may_update_sockmap(struct bpf_verifier_env *env, int func_id)
{
	enum bpf_attach_type eatype = env->prog->expected_attach_type;
	enum bpf_prog_type type = resolve_prog_type(env->prog);

	if (func_id != BPF_FUNC_map_update_elem &&
	    func_id != BPF_FUNC_map_delete_elem)
		return false;

	/* It's not possible to get access to a locked struct sock in these
	 * contexts, so updating is safe.
	 */
	switch (type) {
	case BPF_PROG_TYPE_TRACING:
		if (eatype == BPF_TRACE_ITER)
			return true;
		break;
	case BPF_PROG_TYPE_SOCK_OPS:
		/* map_update allowed only via dedicated helpers with event type checks */
		if (func_id == BPF_FUNC_map_delete_elem)
			return true;
		break;
	case BPF_PROG_TYPE_SK_REUSEPORT:
	case BPF_PROG_TYPE_SK_LOOKUP:
		return true;
	default:
		break;
	}

	verbose(env, "cannot update sockmap in this context\n");
	return false;
}

bool bpf_allow_tail_call_in_subprogs(struct bpf_verifier_env *env)
{
	return env->prog->jit_requested &&
	       bpf_jit_supports_subprog_tailcalls();
}

/*
 * Is rcu_read_lock_held() true at run time? Unlike for in_rcu_cs(), disabled
 * preemption or interrupts will not do.
 */
static bool has_rcu_read_lock(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *state = env->cur_state;

	if (state->active_rcu_locks || in_rcu_callback(env))
		return true;
	if (in_sleepable(env))
		return false;
	return !env->no_rcu_read_lock || state->frame[0]->in_async_callback_fn;
}

/* May the map be used outside of an RCU read side critical section? */
static bool map_needs_no_rcu(const struct bpf_map *map)
{
	switch (map->map_type) {
	case BPF_MAP_TYPE_HASH:
	case BPF_MAP_TYPE_RHASH:
	case BPF_MAP_TYPE_LRU_HASH:
	case BPF_MAP_TYPE_ARRAY:
	case BPF_MAP_TYPE_PERCPU_HASH:
	case BPF_MAP_TYPE_PERCPU_ARRAY:
	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
	case BPF_MAP_TYPE_LPM_TRIE:
	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
	case BPF_MAP_TYPE_HASH_OF_MAPS:
	case BPF_MAP_TYPE_RINGBUF:
	case BPF_MAP_TYPE_USER_RINGBUF:
	case BPF_MAP_TYPE_INODE_STORAGE:
	case BPF_MAP_TYPE_SK_STORAGE:
	case BPF_MAP_TYPE_TASK_STORAGE:
	case BPF_MAP_TYPE_CGRP_STORAGE:
	case BPF_MAP_TYPE_QUEUE:
	case BPF_MAP_TYPE_STACK:
	case BPF_MAP_TYPE_ARENA:
	case BPF_MAP_TYPE_INSN_ARRAY:
	case BPF_MAP_TYPE_PROG_ARRAY:
	case BPF_MAP_TYPE_BLOOM_FILTER:
		return true;
	default:
		return false;
	}
}

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

	/*
	 * check_map_prog_compatibility() asks the program.  That misses the
	 * sleepable callback of another program, and an inner map.  They may
	 * use any map under the RCU read lock.  Disabled preemption or
	 * interrupts will not do: the maps ask for rcu_read_lock_held().
	 */
	if (!has_rcu_read_lock(env) && !map_needs_no_rcu(map)) {
		verbose(env, "map '%s' needs bpf_rcu_read_lock() in sleepable context\n",
			map->name);
		return -EINVAL;
	}

	/* 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_skb_output &&
		    func_id != BPF_FUNC_perf_event_read_value &&
		    func_id != BPF_FUNC_xdp_output)
			goto error;
		break;
	case BPF_MAP_TYPE_RINGBUF:
		if (func_id != BPF_FUNC_ringbuf_output &&
		    func_id != BPF_FUNC_ringbuf_reserve &&
		    func_id != BPF_FUNC_ringbuf_query &&
		    func_id != BPF_FUNC_ringbuf_reserve_dynptr &&
		    func_id != BPF_FUNC_ringbuf_submit_dynptr &&
		    func_id != BPF_FUNC_ringbuf_discard_dynptr)
			goto error;
		break;
	case BPF_MAP_TYPE_USER_RINGBUF:
		if (func_id != BPF_FUNC_user_ringbuf_drain)
			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;
	case BPF_MAP_TYPE_CGROUP_STORAGE:
	case BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE:
		if (func_id != BPF_FUNC_get_local_storage)
			goto error;
		break;
	case BPF_MAP_TYPE_DEVMAP:
	case BPF_MAP_TYPE_DEVMAP_HASH:
		if (func_id != BPF_FUNC_redirect_map &&
		    func_id != BPF_FUNC_map_lookup_elem)
			goto error;
		break;
	/* Restrict bpf side of cpumap and xskmap, open when use-cases
	 * appear.
	 */
	case BPF_MAP_TYPE_CPUMAP:
		if (func_id != BPF_FUNC_redirect_map)
			goto error;
		break;
	case BPF_MAP_TYPE_XSKMAP:
		if (func_id != BPF_FUNC_redirect_map &&
		    func_id != BPF_FUNC_map_lookup_elem)
			goto error;
		break;
	case BPF_MAP_TYPE_ARRAY_OF_MAPS:
	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_msg_redirect_map &&
		    func_id != BPF_FUNC_sk_select_reuseport &&
		    func_id != BPF_FUNC_map_lookup_elem &&
		    !may_update_sockmap(env, func_id))
			goto error;
		break;
	case BPF_MAP_TYPE_SOCKHASH:
		if (func_id != BPF_FUNC_sk_redirect_hash &&
		    func_id != BPF_FUNC_sock_hash_update &&
		    func_id != BPF_FUNC_msg_redirect_hash &&
		    func_id != BPF_FUNC_sk_select_reuseport &&
		    func_id != BPF_FUNC_map_lookup_elem &&
		    !may_update_sockmap(env, func_id))
			goto error;
		break;
	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
		if (func_id != BPF_FUNC_sk_select_reuseport)
			goto error;
		break;
	case BPF_MAP_TYPE_QUEUE:
	case BPF_MAP_TYPE_STACK:
		if (func_id != BPF_FUNC_map_peek_elem &&
		    func_id != BPF_FUNC_map_pop_elem &&
		    func_id != BPF_FUNC_map_push_elem)
			goto error;
		break;
	case BPF_MAP_TYPE_SK_STORAGE:
		if (func_id != BPF_FUNC_sk_storage_get &&
		    func_id != BPF_FUNC_sk_storage_delete &&
		    func_id != BPF_FUNC_kptr_xchg)
			goto error;
		break;
	case BPF_MAP_TYPE_INODE_STORAGE:
		if (func_id != BPF_FUNC_inode_storage_get &&
		    func_id != BPF_FUNC_inode_storage_delete &&
		    func_id != BPF_FUNC_kptr_xchg)
			goto error;
		break;
	case BPF_MAP_TYPE_TASK_STORAGE:
		if (func_id != BPF_FUNC_task_storage_get &&
		    func_id != BPF_FUNC_task_storage_delete &&
		    func_id != BPF_FUNC_kptr_xchg)
			goto error;
		break;
	case BPF_MAP_TYPE_CGRP_STORAGE:
		if (func_id != BPF_FUNC_cgrp_storage_get &&
		    func_id != BPF_FUNC_cgrp_storage_delete &&
		    func_id != BPF_FUNC_kptr_xchg)
			goto error;
		break;
	case BPF_MAP_TYPE_BLOOM_FILTER:
		if (func_id != BPF_FUNC_map_peek_elem &&
		    func_id != BPF_FUNC_map_push_elem)
			goto error;
		break;
	case BPF_MAP_TYPE_INSN_ARRAY:
		goto error;
	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 > 1 && !bpf_allow_tail_call_in_subprogs(env)) {
			verbose(env, "mixing of tail_calls and bpf-to-bpf calls is not supported\n");
			return -EINVAL;
		}
		break;
	case BPF_FUNC_perf_event_read:
	case BPF_FUNC_perf_event_output:
	case BPF_FUNC_perf_event_read_value:
	case BPF_FUNC_skb_output:
	case BPF_FUNC_xdp_output:
		if (map->map_type != BPF_MAP_TYPE_PERF_EVENT_ARRAY)
			goto error;
		break;
	case BPF_FUNC_ringbuf_output:
	case BPF_FUNC_ringbuf_reserve:
	case BPF_FUNC_ringbuf_query:
	case BPF_FUNC_ringbuf_reserve_dynptr:
	case BPF_FUNC_ringbuf_submit_dynptr:
	case BPF_FUNC_ringbuf_discard_dynptr:
		if (map->map_type != BPF_MAP_TYPE_RINGBUF)
			goto error;
		break;
	case BPF_FUNC_user_ringbuf_drain:
		if (map->map_type != BPF_MAP_TYPE_USER_RINGBUF)
			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_DEVMAP_HASH &&
		    map->map_type != BPF_MAP_TYPE_CPUMAP &&
		    map->map_type != BPF_MAP_TYPE_XSKMAP)
			goto error;
		break;
	case BPF_FUNC_sk_redirect_map:
	case BPF_FUNC_msg_redirect_map:
	case BPF_FUNC_sock_map_update:
		if (map->map_type != BPF_MAP_TYPE_SOCKMAP)
			goto error;
		break;
	case BPF_FUNC_sk_redirect_hash:
	case BPF_FUNC_msg_redirect_hash:
	case BPF_FUNC_sock_hash_update:
		if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
			goto error;
		break;
	case BPF_FUNC_get_local_storage:
		if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE &&
		    map->map_type != BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE)
			goto error;
		break;
	case BPF_FUNC_sk_select_reuseport:
		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY &&
		    map->map_type != BPF_MAP_TYPE_SOCKMAP &&
		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
			goto error;
		break;
	case BPF_FUNC_map_pop_elem:
		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
		    map->map_type != BPF_MAP_TYPE_STACK)
			goto error;
		break;
	case BPF_FUNC_map_peek_elem:
	case BPF_FUNC_map_push_elem:
		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
		    map->map_type != BPF_MAP_TYPE_STACK &&
		    map->map_type != BPF_MAP_TYPE_BLOOM_FILTER)
			goto error;
		break;
	case BPF_FUNC_map_lookup_percpu_elem:
		if (map->map_type != BPF_MAP_TYPE_PERCPU_ARRAY &&
		    map->map_type != BPF_MAP_TYPE_PERCPU_HASH &&
		    map->map_type != BPF_MAP_TYPE_LRU_PERCPU_HASH)
			goto error;
		break;
	case BPF_FUNC_sk_storage_get:
	case BPF_FUNC_sk_storage_delete:
		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
			goto error;
		break;
	case BPF_FUNC_inode_storage_get:
	case BPF_FUNC_inode_storage_delete:
		if (map->map_type != BPF_MAP_TYPE_INODE_STORAGE)
			goto error;
		break;
	case BPF_FUNC_task_storage_get:
	case BPF_FUNC_task_storage_delete:
		if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE)
			goto error;
		break;
	case BPF_FUNC_cgrp_storage_get:
	case BPF_FUNC_cgrp_storage_delete:
		if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE)
			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_args_pair_invalid(const struct bpf_func_proto *fn, int arg)
{
	bool is_fixed = fn->arg_type[arg] & MEM_FIXED_SIZE;
	bool has_size = fn->arg_size[arg] != 0;
	bool is_next_size = false;

	if (arg + 1 < ARRAY_SIZE(fn->arg_type))
		is_next_size = arg_type_is_mem_size(fn->arg_type[arg + 1]);

	if (base_type(fn->arg_type[arg]) != ARG_PTR_TO_MEM)
		return is_next_size;

	return has_size == is_next_size || is_next_size == is_fixed;
}

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) ||
	    check_args_pair_invalid(fn, 0) ||
	    check_args_pair_invalid(fn, 1) ||
	    check_args_pair_invalid(fn, 2) ||
	    check_args_pair_invalid(fn, 3) ||
	    check_args_pair_invalid(fn, 4))
		return false;

	return true;
}

static bool check_btf_id_ok(const struct bpf_func_proto *fn)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
		if (fn->arg_type[i] == ARG_UNUSED)
			break;
		if (base_type(fn->arg_type[i]) == ARG_PTR_TO_BTF_ID)
			return !!fn->arg_btf_id[i];
		if (base_type(fn->arg_type[i]) == ARG_PTR_TO_SPIN_LOCK)
			return fn->arg_btf_id[i] == BPF_PTR_POISON;
		if (base_type(fn->arg_type[i]) != ARG_PTR_TO_BTF_ID && fn->arg_btf_id[i] &&
		    /* arg_btf_id and arg_size are in a union. */
		    (base_type(fn->arg_type[i]) != ARG_PTR_TO_MEM ||
		     !(fn->arg_type[i] & MEM_FIXED_SIZE)))
			return false;
	}

	return true;
}

static bool check_mem_arg_rw_flag_ok(const struct bpf_func_proto *fn)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
		enum bpf_arg_type arg_type = fn->arg_type[i];

		if (arg_type == ARG_UNUSED)
			break;
		if (base_type(arg_type) != ARG_PTR_TO_MEM)
			continue;
		if (!(arg_type & (MEM_WRITE | MEM_RDONLY)))
			return false;
	}

	return true;
}

static bool check_proto_release_reg(const struct bpf_func_proto *fn, struct bpf_call_arg_meta *meta)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++) {
		enum bpf_arg_type arg_type = fn->arg_type[i];

		if (arg_type == ARG_UNUSED)
			break;
		if (arg_type_is_release(arg_type)) {
			if (meta->release_regno)
				return false;
			meta->release_regno = i + 1;
		}
	}

	return true;
}

static bool check_arg_prog_aux(struct bpf_verifier_env *env,
			       const struct bpf_func_proto *proto)
{
	bool seen = false;
	argno_t argno;
	u32 i;

	for (i = 0; i < ARRAY_SIZE(proto->arg_type); i++) {
		if (proto->arg_type[i] == ARG_UNUSED)
			break;
		if (proto->arg_type[i] != ARG_PTR_TO_PROG_AUX)
			continue;

		if (seen) {
			verifier_bug(env, "Only 1 prog->aux argument supported");
			return false;
		}

		argno = argno_from_arg(i + 1);
		if (reg_from_argno(argno) < 0) {
			verbose(env, "%s prog->aux cannot be a stack argument\n",
				reg_arg_name(env, argno));
			return false;
		}

		seen = true;
	}

	return true;
}

static int check_func_proto(struct bpf_verifier_env *env, const struct bpf_func_proto *fn,
			    struct bpf_call_arg_meta *meta)
{
	return check_arg_prog_aux(env, fn) &&
	       check_arg_pair_ok(fn) &&
	       check_mem_arg_rw_flag_ok(fn) &&
	       check_proto_release_reg(fn, meta) &&
	       check_btf_id_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.
 *
 * This also applies to dynptr slices belonging to skb and xdp dynptrs,
 * since these slices point to packet data.
 */
static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
{
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;

	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
		if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg)) {
			bpf_diag_record_scrub(env, reg, BPF_DIAG_MOD_PKT_DATA_CHANGE);
			mark_reg_invalid(env, reg);
		}
	}));
}

static bool holds_pkt_pointers(struct bpf_verifier_env *env)
{
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	bool ret = false;

	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
		if (reg_is_pkt_pointer_any(reg) || reg_is_dynptr_slice_pkt(reg))
			ret = true;
	}));

	return ret;
}

enum {
	AT_PKT_END = -1,
	BEYOND_PKT_END = -2,
};

static void mark_pkt_end(struct bpf_verifier_state *vstate, int regn, bool range_open)
{
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *reg = &state->regs[regn];

	if (reg->type != PTR_TO_PACKET)
		/* PTR_TO_PACKET_META is not supported yet */
		return;

	/* The 'reg' is pkt > pkt_end or pkt >= pkt_end.
	 * How far beyond pkt_end it goes is unknown.
	 * if (!range_open) it's the case of pkt >= pkt_end
	 * if (range_open) it's the case of pkt > pkt_end
	 * hence this pointer is at least 1 byte bigger than pkt_end
	 */
	if (range_open)
		reg->range = BEYOND_PKT_END;
	else
		reg->range = AT_PKT_END;
}

static int __release_reference_nomark(struct bpf_verifier_state *state, int id)
{
	int i;

	for (i = 0; i < state->acquired_refs; i++) {
		if (state->refs[i].type != REF_TYPE_PTR)
			continue;
		if (state->refs[i].id == id) {
			release_reference_state(state, i);
			return 0;
		}
	}
	return -EINVAL;
}

static int release_reference_nomark(struct bpf_verifier_env *env, int id)
{
	int err;

	err = __release_reference_nomark(env->cur_state, id);
	if (!err)
		bpf_diag_record_ref_release(env, env->insn_idx, id);
	return err;
}

static int idstack_push(struct bpf_idmap *idmap, u32 id)
{
	int i;

	if (!id)
		return 0;

	for (i = 0; i < idmap->cnt; i++)
		if (idmap->map[i].old == id)
			return 0;

	if (WARN_ON_ONCE(idmap->cnt >= BPF_ID_MAP_SIZE))
		return -EFAULT;

	idmap->map[idmap->cnt++].old = id;
	return 0;
}

static int idstack_pop(struct bpf_idmap *idmap)
{
	if (!idmap->cnt)
		return 0;

	return idmap->map[--idmap->cnt].old;
}

/* Release id and objects derived from it iteratively in a DFS manner */
static int release_reference(struct bpf_verifier_env *env, int id)
{
	u32 mask = (1 << STACK_SPILL) | (1 << STACK_DYNPTR);
	struct bpf_verifier_state *vstate = env->cur_state;
	struct bpf_idmap *idstack = &env->idmap_scratch;
	struct bpf_stack_state *stack;
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	int i, err;

	idstack->cnt = 0;
	err = idstack_push(idstack, id);
	if (err)
		return err;

	if (find_reference_state(vstate, id)) {
		err = release_reference_nomark(env, id);
		WARN_ON_ONCE(err);
	}

	while ((id = idstack_pop(idstack))) {
		/*
		 * Child references are inaccessible after parent is released,
		 * any child references that exist at this point are a leak.
		 */
		for (i = 0; i < vstate->acquired_refs; i++) {
			if (vstate->refs[i].type != REF_TYPE_PTR)
				continue;
			if (vstate->refs[i].parent_id != id)
				continue;
			verbose(env, "Leaking reference id=%d alloc_insn=%d. Release it first.\n",
				vstate->refs[i].id, vstate->refs[i].insn_idx);
			return -EINVAL;
		}

		bpf_for_each_reg_in_vstate_mask(vstate, state, reg, stack, mask, ({
			if (reg->id != id && reg->parent_id != id)
				continue;

			/* Free objects derived from the current object */
			if (reg->parent_id == id) {
				err = idstack_push(idstack, reg->id);
				if (err)
					return err;
			}

			/*
			 * A dynptr occupies two stack slots that invalidate_dynptr()
			 * clears together. Record both scrubs before invalidating it.
			 */
			if (stack && stack->slot_type[BPF_REG_SIZE - 1] == STACK_DYNPTR) {
				struct bpf_stack_state *dyn_stack = stack;

				if (reg->dynptr.first_slot)
					dyn_stack--;
				bpf_diag_record_scrub(env, &dyn_stack[0].spilled_ptr,
						      BPF_DIAG_MOD_REF_RELEASE);
				bpf_diag_record_scrub(env, &dyn_stack[1].spilled_ptr,
						      BPF_DIAG_MOD_REF_RELEASE);
				invalidate_dynptr(env, dyn_stack);
				continue;
			}
			bpf_diag_record_scrub(env, reg, BPF_DIAG_MOD_REF_RELEASE);
			if (!stack || stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL)
				mark_reg_invalid(env, reg);
		}));
	}

	return 0;
}

static void invalidate_non_owning_refs(struct bpf_verifier_env *env)
{
	struct bpf_func_state *unused;
	struct bpf_reg_state *reg;

	bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({
		if (type_is_non_owning_ref(reg->type)) {
			bpf_diag_record_scrub(env, reg, BPF_DIAG_MOD_NON_OWN_REF);
			mark_reg_invalid(env, reg);
		}
	}));
}

static void invalidate_rcu_protected_refs(struct bpf_verifier_env *env)
{
	struct bpf_stack_state *stack;
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER);

	bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, stack, clear_mask, ({
		if (reg->type & MEM_RCU) {
			bpf_diag_mod_begin(env, reg, NULL, BPF_DIAG_MOD_WRITE);
			reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL | NON_OWN_REF);
			reg->type |= PTR_UNTRUSTED;
			bpf_diag_mod_end(env);
		}
	}));
}

static int ref_convert_alloc_rcu_protected(struct bpf_verifier_env *env, u32 id)
{
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	int err;

	err = release_reference_nomark(env, id);
	if (err)
		return err;

	bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({
		if (reg->id != id)
			continue;
		if ((reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU)) {
			bpf_diag_mod_begin(env, reg, NULL, BPF_DIAG_MOD_WRITE);
			if (!type_may_be_null(reg->type))
				reg->id = 0;
			reg->type &= ~MEM_ALLOC;
			reg->type |= MEM_RCU;
			bpf_diag_mod_end(env);
		}
	}));

	return err;
}

static void clear_caller_saved_regs(struct bpf_verifier_env *env,
				    struct bpf_reg_state *regs)
{
	int i;

	bpf_diag_record_caller_saved(env, regs);

	/* after the call registers r0 - r5 were scratched */
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		bpf_mark_reg_not_init(env, &regs[caller_saved[i]]);
		__check_reg_arg(env, regs, caller_saved[i], DST_OP_NO_MARK);
	}
}

static void invalidate_outgoing_stack_args(struct bpf_verifier_env *env,
					   struct bpf_func_state *state)
{
	int i, nslots = state->out_stack_arg_cnt;

	for (i = 0; i < nslots; i++) {
		bpf_diag_record_scrub(env, &state->stack_arg_regs[i], BPF_DIAG_MOD_CALLER_SAVED);
		bpf_mark_reg_not_init(env, &state->stack_arg_regs[i]);
	}
}

typedef int (*set_callee_state_fn)(struct bpf_verifier_env *env,
				   struct bpf_func_state *caller,
				   struct bpf_func_state *callee,
				   int insn_idx);

static int set_callee_state(struct bpf_verifier_env *env,
			    struct bpf_func_state *caller,
			    struct bpf_func_state *callee, int insn_idx);

static int setup_func_entry(struct bpf_verifier_env *env, int subprog, int callsite,
			    set_callee_state_fn set_callee_state_cb,
			    struct bpf_verifier_state *state)
{
	struct bpf_func_state *caller, *callee;
	int err;

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

	if (state->frame[state->curframe + 1]) {
		verifier_bug(env, "Frame %d already allocated", state->curframe + 1);
		return -EFAULT;
	}

	caller = state->frame[state->curframe];
	callee = kzalloc_obj(*callee, GFP_KERNEL_ACCOUNT);
	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 */
			callsite,
			state->curframe + 1 /* frameno within this callchain */,
			subprog /* subprog number within this prog */);
	err = set_callee_state_cb(env, caller, callee, callsite);
	if (err)
		goto err_out;

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

	return 0;

err_out:
	free_func_state(callee);
	state->frame[state->curframe + 1] = NULL;
	return err;
}

static void gen_subprog_arg_proto(const struct bpf_subprog_info *sub, const struct btf *btf,
				  const struct btf_type *func_proto, struct bpf_func_proto *proto)
{
	const struct btf_param *args = btf_params(func_proto);
	u32 arg, slot = 0;

	memset(proto, 0, sizeof(*proto));
	for (arg = 0; arg < btf_type_vlen(func_proto); arg++) {
		enum bpf_arg_type arg_type = sub->args[slot].arg_type;
		const struct btf_type *t;

		if (arg_type & PTR_UNTRUSTED) {
			/*
			 * An __arg_untrusted argument accepts any caller value. The
			 * callee treats it as read-only and uses probe-read instructions
			 * to protect against invalid memory access.
			 */
			arg_type = ARG_IGNORE;
		} else if (base_type(arg_type) == ARG_PTR_TO_ARENA) {
			arg_type |= PTR_MAYBE_NULL;
		} else if (base_type(arg_type) == ARG_PTR_TO_MEM) {
			proto->arg_size[arg] = sub->args[slot].mem_size;
			arg_type |= MEM_FIXED_SIZE | MEM_WRITE;
		} else if (base_type(arg_type) == ARG_PTR_TO_BTF_ID) {
			proto->arg_btf_id[arg] = &sub->args[slot].btf_id;
		}
		proto->arg_type[arg] = arg_type;
		t = btf_type_skip_modifiers(btf, args[arg].type, NULL);
		slot += btf_arg_slots(t);
	}
}

static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, struct btf *btf)
{
	struct bpf_subprog_info *sub = subprog_info(env, subprog);
	struct bpf_func_state *caller = cur_func(env);
	const struct btf_type *func, *func_proto;
	struct bpf_call_arg_meta meta;
	struct bpf_func_proto *fn;
	int ret, err;
	u32 i;

	memset(&meta, 0, sizeof(meta));
	meta.btf = btf;
	meta.subprog_may_change_pkt = sub->changes_pkt_data;
	meta.func_name = bpf_subprog_name(env, subprog);

	ret = btf_prepare_func_args(env, subprog);
	if (ret) {
		if (bpf_in_stack_arg_cnt(sub) > 0) {
			err = check_outgoing_stack_args(env, caller, sub->arg_slot_cnt,
							bpf_subprog_name(env, subprog),
							NULL, NULL);
			if (err)
				return err;
		}
		return ret;
	}

	func = btf_type_by_id(btf, env->prog->aux->func_info[subprog].type_id);
	func_proto = btf_type_by_id(btf, func->type);

	fn = &env->bpf_subprog_scratch;
	gen_subprog_arg_proto(sub, btf, func_proto, fn);
	meta.fn = fn;
	meta.func_proto = func_proto;

	/*
	 * Check if all register arguments declared in BTF are initialized.
	 * If they aren't the BTF is unreliable.
	 */
	if (!bpf_subprog_is_global(env, subprog)) {
		for (i = 0; i < min_t(u32, sub->arg_slot_cnt, MAX_BPF_FUNC_REG_ARGS); i++)
			if (caller->regs[BPF_REG_1 + i].type == NOT_INIT)
				return -EINVAL;
	}
	return check_func_args(env, &meta, env->insn_idx);
}

/*
 * Check that call-site argument states match a subprog's BTF signature.
 *
 * Returns:
 * EFAULT - there is a verifier bug. Abort verification.
 * Other errors - there is a type mismatch or BTF is not available.
 * 0 - BTF matches with what bpf_reg_state expects.
 */
static int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog)
{
	struct bpf_prog *prog = env->prog;
	struct btf *btf = prog->aux->btf;
	u32 btf_id;
	int err;

	if (!prog->aux->func_info)
		return -EINVAL;

	btf_id = prog->aux->func_info[subprog].type_id;
	if (!btf_id)
		return -EFAULT;

	if (prog->aux->func_info_aux[subprog].unreliable)
		return -EINVAL;

	err = btf_check_func_arg_match(env, subprog, btf);
	/* Compiler optimizations can remove arguments from static functions
	 * or mismatched type can be passed into a global function.
	 * In such cases mark the function as unreliable from BTF point of view.
	 */
	if (err)
		prog->aux->func_info_aux[subprog].unreliable = true;
	return err;
}

static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
			      int insn_idx, int subprog,
			      set_callee_state_fn set_callee_state_cb)
{
	struct bpf_verifier_state *state = env->cur_state, *callback_state;
	struct bpf_func_state *caller, *callee;
	int err;

	caller = state->frame[state->curframe];
	err = btf_check_subprog_call(env, subprog);
	if (err == -EFAULT)
		return err;

	/* set_callee_state is used for direct subprog calls, but we are
	 * interested in validating only BPF helpers that can call subprogs as
	 * callbacks
	 */
	env->subprog_info[subprog].is_cb = true;
	if (bpf_pseudo_kfunc_call(insn) &&
	    !is_callback_calling_kfunc(insn->imm)) {
		verifier_bug(env, "kfunc %s#%d not marked as callback-calling",
			     func_id_name(insn->imm), insn->imm);
		return -EFAULT;
	} else if (!bpf_pseudo_kfunc_call(insn) &&
		   !is_callback_calling_function(insn->imm)) { /* helper */
		verifier_bug(env, "helper %s#%d not marked as callback-calling",
			     func_id_name(insn->imm), insn->imm);
		return -EFAULT;
	}

	if (bpf_is_async_callback_calling_insn(insn)) {
		struct bpf_verifier_state *async_cb;

		/* there is no real recursion here. timer and workqueue callbacks are async */
		env->subprog_info[subprog].is_async_cb = true;
		async_cb = push_async_cb(env, env->subprog_info[subprog].start,
					 insn_idx, subprog,
					 is_async_cb_sleepable(env, insn));
		if (IS_ERR(async_cb))
			return PTR_ERR(async_cb);
		if (is_async_cb_sleepable(env, insn))
			mark_sleepable_async_cb(env);
		callee = async_cb->frame[0];
		callee->async_entry_cnt = state->frame[0]->async_entry_cnt + 1;

		/* Convert bpf_timer_set_callback() args into timer callback args */
		err = set_callee_state_cb(env, caller, callee, insn_idx);
		if (err)
			return err;

		return 0;
	}

	/*
	 * The address of the callback might be taken in another function or
	 * read from a map, see check_func_ptr_read(). Like with callx it's
	 * known here what is called.
	 */
	err = record_callx_edge(env, caller->subprogno, subprog);
	if (err)
		return err;

	/* for callback functions enqueue entry to callback and
	 * proceed with next instruction within current frame.
	 */
	callback_state = push_stack(env, env->subprog_info[subprog].start, insn_idx, false);
	if (IS_ERR(callback_state))
		return PTR_ERR(callback_state);

	err = setup_func_entry(env, subprog, insn_idx, set_callee_state_cb,
			       callback_state);
	if (err)
		return err;

	callback_state->callback_unroll_depth++;
	callback_state->frame[callback_state->curframe - 1]->callback_depth++;
	caller->callback_depth = 0;
	return 0;
}

static int process_bpf_exit_full(struct bpf_verifier_env *env,
				 bool *do_print_state, bool exception_exit);

/*
 * Call of a static subprog. The callee is verified in the context of
 * the caller, hence set up a new frame and continue from the first
 * instruction of the callee.
 */
static int check_static_func_call(struct bpf_verifier_env *env, int subprog,
				  int *insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_subprog_info *caller_info;
	u16 callee_incoming, stack_arg_cnt;
	struct bpf_func_state *caller;
	int err;

	caller = state->frame[state->curframe];

	/*
	 * Track caller's total stack arg count (incoming + max outgoing).
	 * This is needed so the JIT knows how much stack arg space to allocate.
	 */
	caller_info = &env->subprog_info[caller->subprogno];
	callee_incoming = bpf_in_stack_arg_cnt(&env->subprog_info[subprog]);
	stack_arg_cnt = bpf_in_stack_arg_cnt(caller_info) + callee_incoming;
	if (stack_arg_cnt > caller_info->stack_arg_cnt)
		caller_info->stack_arg_cnt = stack_arg_cnt;

	/*
	 * For regular function entry setup new frame and continue
	 * from that frame.
	 */
	err = setup_func_entry(env, subprog, *insn_idx, set_callee_state, state);
	if (err)
		return err;

	bpf_diag_record_scrub(env, &caller->regs[BPF_REG_0], BPF_DIAG_MOD_CALLER_SAVED);
	clear_caller_saved_regs(env, caller->regs);

	/* and go analyze first insn of the callee */
	*insn_idx = env->subprog_info[subprog].start - 1;

	if (env->log.level & BPF_LOG_LEVEL) {
		verbose(env, "caller:\n");
		print_verifier_state(env, state, caller->frameno, true);
		verbose(env, "callee:\n");
		print_verifier_state(env, state, state->curframe, true);
	}

	return 0;
}

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;
	int err, subprog, target_insn;
	u32 i, nregs;

	target_insn = *insn_idx + insn->imm + 1;
	subprog = bpf_find_subprog(env, target_insn);
	if (verifier_bug_if(subprog < 0, env, "target of func call at insn %d is not a program",
			    target_insn))
		return -EFAULT;

	caller = state->frame[state->curframe];
	err = btf_check_subprog_call(env, subprog);
	if (err == -EFAULT)
		return err;
	if (bpf_subprog_is_global(env, subprog)) {
		struct bpf_func_info_aux *sub_aux = subprog_aux(env, subprog);
		const char *sub_name = bpf_subprog_name(env, subprog);
		const char *operation;
		bool returns_void;

		if (env->cur_state->active_locks) {
			verbose(env, "global function calls are not allowed while holding a lock,\n"
				     "use static function instead\n");
			operation = bpf_diag_fmt(env, "global function %s()", sub_name);
			bpf_diag_ctx_active(env, *insn_idx, operation, BPF_DIAG_CONTEXT_LOCK,
					    "Release the lock before calling the global function, or use a static function instead.");
			return -EINVAL;
		}

		if (env->subprog_info[subprog].might_sleep && !in_sleepable_context(env)) {
			const char *suggestion;

			verbose(env, "sleepable global function %s() called in %s\n",
				sub_name, non_sleepable_context_description(env));
			if (in_sleepable(env))
				suggestion = "Move the call outside the critical section, or use a non-sleepable function.";
			else
				suggestion = "Mark the program sleepable if the program type allows it, or use a non-sleepable function.";
			operation = bpf_diag_fmt(env, "sleepable global function %s()", sub_name);
			bpf_diag_ctx_forbidden(env, *insn_idx, operation, suggestion);
			return -EINVAL;
		}

		if (err) {
			verbose(env, "Caller passes invalid args into func#%d ('%s')\n",
				subprog, sub_name);
			return err;
		}

		if (env->log.level & BPF_LOG_LEVEL)
			verbose(env, "Func#%d ('%s') is global and assumed valid.\n",
				subprog, sub_name);
		if (in_sleepable_context(env))
			sub_aux->called[BPF_FUNC_CTX_SLEEPABLE] = true;
		else if (has_rcu_read_lock(env))
			sub_aux->called[BPF_FUNC_CTX_NON_SLEEPABLE] = true;
		else
			sub_aux->called[BPF_FUNC_CTX_NO_RCU_LOCK] = true;
		returns_void = subprog_returns_void(env, subprog);
		if (env->subprog_info[subprog].changes_pkt_data)
			clear_all_pkt_pointers(env);
		if (returns_void)
			bpf_diag_record_scrub(env, &caller->regs[BPF_REG_0], BPF_DIAG_MOD_CALLER_SAVED);
		else
			bpf_diag_mod_begin(env, &caller->regs[BPF_REG_0], NULL, BPF_DIAG_MOD_WRITE);
		clear_caller_saved_regs(env, caller->regs);
		invalidate_outgoing_stack_args(env, cur_func(env));
		/*
		 * What the callers of a global function hold is not known
		 * while it is verified.
		 */
		if (!env->subprog_info[subprog].changes_pkt_data &&
		    (state->frame[0]->subprogno || holds_pkt_pointers(env)))
			sub_aux->called_with_pkt_ptrs = true;

		/*
		 * A non-void global function returns a 64-bit SCALAR_VALUE in
		 * R0, or a >8 byte SCALAR_VALUE in the R0:R2 register pair.
		 */
		if (!returns_void) {
			nregs = bpf_ret_reg_pair(env, subprog) ? 2 : 1;
			mark_reg_unknown(env, caller->regs, ret_regs[0]);
			bpf_diag_mod_end(env);
			for (i = 1; i < nregs; i++) {
				bpf_diag_mod_begin(env, &caller->regs[ret_regs[i]], NULL,
						   BPF_DIAG_MOD_WRITE);
				mark_reg_unknown(env, caller->regs, ret_regs[i]);
				bpf_diag_mod_end(env);
			}
		}

		if (env->subprog_info[subprog].can_unwind) {
			struct bpf_verifier_state *branch;

			if (!bpf_is_unwind_goto(insn + 1)) {
				verbose(env, "no unwind_goto after the call of %s()\n", sub_name);
				return -EINVAL;
			}
			branch = push_stack(env, *insn_idx + 1, *insn_idx, false);
			if (IS_ERR(branch))
				return PTR_ERR(branch);
			branch->unwound = true;
		}

		if (env->subprog_info[subprog].might_throw) {
			struct bpf_verifier_state *branch;

			branch = push_stack(env, *insn_idx + 1, *insn_idx, false);
			if (IS_ERR(branch)) {
				verbose(env, "failed to push state for global subprog exception path\n");
				return PTR_ERR(branch);
			}
			return process_bpf_exit_full(env, NULL, true);
		}

		/* continue with next insn after call */
		return 0;
	}

	return check_static_func_call(env, subprog, insn_idx);
}

/*
 * callx dst_reg: call a bpf subprog whose address is in dst_reg.
 *
 * The address of a subprog is either loaded into a register by ld_imm64 with
 * src_reg == BPF_PSEUDO_FUNC, or it is read from a frozen read-only map, see
 * resolve_func_ptrs(). Both are possible for static subprogs only. Hence all
 * possible callees of callx are discovered by add_subprogs() and are reachable
 * in the control flow graph before the main verification pass begins.
 * PTR_TO_FUNC register identifies the callee, so from here on callx is verified
 * as a direct call of that static subprog.
 */
static int check_func_callx(struct bpf_verifier_env *env, struct bpf_insn *insn,
			    int *insn_idx)
{
	struct bpf_func_state *caller = cur_func(env);
	struct bpf_reg_state *reg;
	const char *reason;
	int err, subprog;

	err = check_reg_arg(env, insn->dst_reg, SRC_OP);
	if (err)
		return err;

	reg = reg_state(env, insn->dst_reg);
	if (reg->type != PTR_TO_FUNC) {
		verbose(env, "R%d has type %s, expected func\n", insn->dst_reg,
			reg_type_str(env, reg->type));
		reason = bpf_diag_fmt(
			env, "R%d holds %s, but callx can only call through the address of a static BPF function.",
			insn->dst_reg, bpf_diag_reg_type_plain(env, reg->type));
		bpf_diag_register_type(
			env, *insn_idx, insn->dst_reg, "indirect call through a non-function pointer", reason,
			"Load the address of a static BPF function into the register before callx.");
		return -EACCES;
	}

	/*
	 * Arithmetic on PTR_TO_FUNC is allowed, but only unmodified address
	 * of a subprog can be called.
	 */
	err = check_ptr_off_reg(env, reg, insn->dst_reg);
	if (err)
		return err;

	/* the callx is valid, but only a JIT can execute it */
	err = require_callx_jit(env);
	if (err)
		return err;

	/* PTR_TO_FUNC is a pointer to a static subprog */
	subprog = reg->subprogno;
	err = btf_check_subprog_call(env, subprog);
	if (err == -EFAULT)
		return err;

	err = record_callx_edge(env, caller->subprogno, subprog);
	if (err)
		return err;

	return check_static_func_call(env, subprog, insn_idx);
}

int map_set_for_each_callback_args(struct bpf_verifier_env *env,
				   struct bpf_func_state *caller,
				   struct bpf_func_state *callee)
{
	/* bpf_for_each_map_elem(struct bpf_map *map, void *callback_fn,
	 *      void *callback_ctx, u64 flags);
	 * callback_fn(struct bpf_map *map, void *key, void *value,
	 *      void *callback_ctx);
	 */
	callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];

	callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
	callee->regs[BPF_REG_2].map_ptr = caller->regs[BPF_REG_1].map_ptr;
	callee->regs[BPF_REG_2].map_uid = caller->regs[BPF_REG_1].map_uid;

	callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
	callee->regs[BPF_REG_3].map_ptr = caller->regs[BPF_REG_1].map_ptr;
	callee->regs[BPF_REG_3].map_uid = caller->regs[BPF_REG_1].map_uid;
	callee->regs[BPF_REG_3].id = ++env->id_gen;

	/* pointer to stack or null */
	callee->regs[BPF_REG_4] = caller->regs[BPF_REG_3];

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	return 0;
}

static int set_callee_state(struct bpf_verifier_env *env,
			    struct bpf_func_state *caller,
			    struct bpf_func_state *callee, int insn_idx)
{
	int i;

	/* copy r1 - r5 args that callee can access.  The copy includes parent
	 * pointers, which connects us up to the liveness chain
	 */
	for (i = BPF_REG_1; i <= BPF_REG_5; i++)
		callee->regs[i] = caller->regs[i];
	return 0;
}

static int set_map_elem_callback_state(struct bpf_verifier_env *env,
				       struct bpf_func_state *caller,
				       struct bpf_func_state *callee,
				       int insn_idx)
{
	struct bpf_insn_aux_data *insn_aux = &env->insn_aux_data[insn_idx];
	struct bpf_map *map;
	int err;

	/* valid map_ptr and poison value does not matter */
	map = insn_aux->map_ptr_state.map_ptr;
	if (!map->ops->map_set_for_each_callback_args ||
	    !map->ops->map_for_each_callback) {
		verbose(env, "callback function not allowed for map\n");
		return -ENOTSUPP;
	}

	err = map->ops->map_set_for_each_callback_args(env, caller, callee);
	if (err)
		return err;

	switch (map->map_type) {
	case BPF_MAP_TYPE_HASH:
	case BPF_MAP_TYPE_PERCPU_HASH:
	case BPF_MAP_TYPE_LRU_HASH:
	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
	case BPF_MAP_TYPE_RHASH:
		/* Hash tables run the callback under rcu_read_lock(). */
		callee->in_rcu_callback_fn = true;
		break;
	default:
		break;
	}

	callee->in_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 1);
	return 0;
}

static int set_loop_callback_state(struct bpf_verifier_env *env,
				   struct bpf_func_state *caller,
				   struct bpf_func_state *callee,
				   int insn_idx)
{
	/* bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx,
	 *	    u64 flags);
	 * callback_fn(u64 index, void *callback_ctx);
	 */
	callee->regs[BPF_REG_1].type = SCALAR_VALUE;
	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);

	callee->in_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 1);
	return 0;
}

static int set_timer_callback_state(struct bpf_verifier_env *env,
				    struct bpf_func_state *caller,
				    struct bpf_func_state *callee,
				    int insn_idx)
{
	struct bpf_map *map_ptr = caller->regs[BPF_REG_1].map_ptr;
	u32 map_uid = caller->regs[BPF_REG_1].map_uid;

	/* bpf_timer_set_callback(struct bpf_timer *timer, void *callback_fn);
	 * callback_fn(struct bpf_map *map, void *key, void *value);
	 */
	callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP;
	__mark_reg_known_zero(&callee->regs[BPF_REG_1]);
	callee->regs[BPF_REG_1].map_ptr = map_ptr;
	callee->regs[BPF_REG_1].map_uid = map_uid;

	callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
	callee->regs[BPF_REG_2].map_ptr = map_ptr;
	callee->regs[BPF_REG_2].map_uid = map_uid;

	callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
	callee->regs[BPF_REG_3].map_ptr = map_ptr;
	callee->regs[BPF_REG_3].map_uid = map_uid;
	callee->regs[BPF_REG_3].id = ++env->id_gen;

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	callee->in_async_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 0);
	return 0;
}

static int set_find_vma_callback_state(struct bpf_verifier_env *env,
				       struct bpf_func_state *caller,
				       struct bpf_func_state *callee,
				       int insn_idx)
{
	/* bpf_find_vma(struct task_struct *task, u64 addr,
	 *               void *callback_fn, void *callback_ctx, u64 flags)
	 * (callback_fn)(struct task_struct *task,
	 *               struct vm_area_struct *vma, void *callback_ctx);
	 */
	callee->regs[BPF_REG_1] = caller->regs[BPF_REG_1];

	callee->regs[BPF_REG_2].type = PTR_TO_BTF_ID;
	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
	callee->regs[BPF_REG_2].btf =  btf_vmlinux;
	callee->regs[BPF_REG_2].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];

	/* pointer to stack or null */
	callee->regs[BPF_REG_3] = caller->regs[BPF_REG_4];

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	callee->in_callback_fn = true;
	/* bpf_find_vma() runs the callback under mmap_lock and RCU. */
	callee->in_rcu_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 1);
	return 0;
}

static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env,
					   struct bpf_func_state *caller,
					   struct bpf_func_state *callee,
					   int insn_idx)
{
	/* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void
	 *			  callback_ctx, u64 flags);
	 * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx);
	 */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_0]);
	mark_dynptr_cb_reg(env, &callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL);
	callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3];

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);

	callee->in_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 1);
	return 0;
}

static int set_rbtree_add_callback_state(struct bpf_verifier_env *env,
					 struct bpf_func_state *caller,
					 struct bpf_func_state *callee,
					 int insn_idx)
{
	/* void bpf_rbtree_add_impl(struct bpf_rb_root *root, struct bpf_rb_node *node,
	 *                     bool (less)(struct bpf_rb_node *a, const struct bpf_rb_node *b));
	 *
	 * 'struct bpf_rb_node *node' arg to bpf_rbtree_add_impl is the same PTR_TO_BTF_ID w/ offset
	 * that 'less' callback args will be receiving. However, 'node' arg was release_reference'd
	 * by this point, so look at 'root'
	 */
	struct btf_field *field;

	field = reg_find_field_offset(&caller->regs[BPF_REG_1],
				      caller->regs[BPF_REG_1].var_off.value,
				      BPF_RB_ROOT);
	if (!field || !field->graph_root.value_btf_id)
		return -EFAULT;

	mark_reg_graph_node(callee->regs, BPF_REG_1, &field->graph_root);
	ref_set_non_owning(env, &callee->regs[BPF_REG_1]);
	mark_reg_graph_node(callee->regs, BPF_REG_2, &field->graph_root);
	ref_set_non_owning(env, &callee->regs[BPF_REG_2]);

	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_3]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	callee->in_callback_fn = true;
	callee->callback_ret_range = retval_range(0, 1);
	return 0;
}

static int set_task_work_schedule_callback_state(struct bpf_verifier_env *env,
						 struct bpf_func_state *caller,
						 struct bpf_func_state *callee,
						 int insn_idx)
{
	struct bpf_map *map_ptr = caller->regs[BPF_REG_3].map_ptr;
	u32 map_uid = caller->regs[BPF_REG_3].map_uid;

	/*
	 * callback_fn(struct bpf_map *map, void *key, void *value);
	 */
	callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP;
	__mark_reg_known_zero(&callee->regs[BPF_REG_1]);
	callee->regs[BPF_REG_1].map_ptr = map_ptr;
	callee->regs[BPF_REG_1].map_uid = map_uid;

	callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
	callee->regs[BPF_REG_2].map_ptr = map_ptr;
	callee->regs[BPF_REG_2].map_uid = map_uid;

	callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
	callee->regs[BPF_REG_3].map_ptr = map_ptr;
	callee->regs[BPF_REG_3].map_uid = map_uid;
	callee->regs[BPF_REG_3].id = ++env->id_gen;

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	callee->in_async_callback_fn = true;
	callee->callback_ret_range = retval_range(S32_MIN, S32_MAX);
	return 0;
}

static int set_rcu_callback_state(struct bpf_verifier_env *env,
				  struct bpf_func_state *caller,
				  struct bpf_func_state *callee,
				  int insn_idx)
{
	struct bpf_map *map_ptr = caller->regs[BPF_REG_2].map_ptr;
	u32 map_uid = caller->regs[BPF_REG_2].map_uid;

	/*
	 * callback_fn(struct bpf_map *map, void *key, void *value);
	 */
	callee->regs[BPF_REG_1].type = CONST_PTR_TO_MAP;
	__mark_reg_known_zero(&callee->regs[BPF_REG_1]);
	callee->regs[BPF_REG_1].map_ptr = map_ptr;
	callee->regs[BPF_REG_1].map_uid = map_uid;

	callee->regs[BPF_REG_2].type = PTR_TO_MAP_KEY;
	__mark_reg_known_zero(&callee->regs[BPF_REG_2]);
	callee->regs[BPF_REG_2].map_ptr = map_ptr;
	callee->regs[BPF_REG_2].map_uid = map_uid;

	callee->regs[BPF_REG_3].type = PTR_TO_MAP_VALUE;
	__mark_reg_known_zero(&callee->regs[BPF_REG_3]);
	callee->regs[BPF_REG_3].map_ptr = map_ptr;
	callee->regs[BPF_REG_3].map_uid = map_uid;

	/* unused */
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_4]);
	bpf_mark_reg_not_init(env, &callee->regs[BPF_REG_5]);
	callee->in_async_callback_fn = true;
	callee->callback_ret_range = retval_range(S32_MIN, S32_MAX);
	return 0;
}

static bool is_rbtree_lock_required_kfunc(u32 btf_id);

static void account_processed_insn(struct bpf_verifier_env *env)
{
	struct bpf_func_state *frame = cur_func(env);

	env->insn_processed++;
	frame->insns_subtotal++;
	env->subprog_info[frame->subprogno].insns_self++;
}

static void account_processed_insns(struct bpf_verifier_env *env,
				    struct bpf_func_state *callee,
				    struct bpf_func_state *caller)
{
	u32 insns;

	if (!callee)
		return;

	insns = callee->insns_subtotal;

	env->subprog_info[callee->subprogno].insns_total += insns;
	if (caller)
		caller->insns_subtotal += insns;
	callee->insns_subtotal = 0;
}

static void account_current_path(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *state = env->cur_state;
	int frame;

	for (frame = state->curframe; frame >= 0; frame--)
		account_processed_insns(env, state->frame[frame],
					frame ? state->frame[frame - 1] : NULL);
}

/*
 * Are we currently verifying the callback for an rbtree kfunc that must
 * be called with a lock held, or one of that callback's subprogs? If so,
 * no need to complain about an unreleased lock.
 */
static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_insn *insn = env->prog->insnsi;
	struct bpf_func_state *callee;
	int kfunc_btf_id;
	u32 frame;

	for (frame = state->curframe; frame; frame--) {
		callee = state->frame[frame];
		if (!callee->in_callback_fn)
			continue;

		kfunc_btf_id = insn[callee->callsite].imm;
		if (is_rbtree_lock_required_kfunc(kfunc_btf_id))
			return true;
	}

	return false;
}

static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
{
	if (range.return_32bit)
		return range.minval <= reg_s32_min(reg) && reg_s32_max(reg) <= range.maxval;
	else
		return range.minval <= reg_smin(reg) && reg_smax(reg) <= range.maxval;
}

static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
{
	struct bpf_verifier_state *state = env->cur_state, *prev_st;
	struct bpf_func_state *caller, *callee;
	struct bpf_reg_state *r0;
	bool in_callback_fn;
	u32 i, nregs;
	int err;

	callee = state->frame[state->curframe];
	r0 = &callee->regs[BPF_REG_0];
	nregs = bpf_ret_reg_pair(env, callee->subprogno) ? 2 : 1;
	for (i = 0; i < nregs; i++) {
		if (callee->regs[ret_regs[i]].type != PTR_TO_STACK)
			continue;
		/* 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;
	}

	caller = state->frame[state->curframe - 1];
	if (bpf_is_unwind_exit(&env->prog->insnsi[*insn_idx])) {
		/* the helper or the kfunc that called it doesn't expect that */
		if (callee->in_callback_fn) {
			verbose(env, "callback cannot unwind\n");
			return -EINVAL;
		}
		if (!bpf_is_unwind_goto(&env->prog->insnsi[callee->callsite + 1])) {
			verbose(env, "unwind_exit, but no unwind_goto after the call at insn %d\n",
				callee->callsite);
			return -EINVAL;
		}
		state->unwound = true;
	}
	if (callee->in_callback_fn) {
		if (r0->type != SCALAR_VALUE) {
			verbose(env, "R0 not a scalar value\n");
			return -EACCES;
		}

		/* we are going to rely on register's precise value */
		err = mark_chain_precision(env, BPF_REG_0);
		if (err)
			return err;

		/* enforce R0 return value range, and bpf_callback_t returns 64bit */
		if (!retval_range_within(callee->callback_ret_range, r0)) {
			verbose_invalid_scalar(env, r0, callee->callback_ret_range,
					       "At callback return", "R0");
			return -EINVAL;
		}
		if (!bpf_calls_callback(env, callee->callsite)) {
			verifier_bug(env, "in callback at %d, callsite %d !calls_callback",
				     *insn_idx, callee->callsite);
			return -EFAULT;
		}
	} else {
		/*
		 * return to the caller whatever the callee had in the
		 * return register(s)
		 */
		for (i = 0; i < nregs; i++) {
			u32 regno = ret_regs[i];

			bpf_diag_mod_begin(env, &caller->regs[regno], &callee->regs[regno],
					   BPF_DIAG_MOD_WRITE);
			caller->regs[regno] = callee->regs[regno];
			bpf_diag_mod_end(env);
		}
	}

	/* Invalidate callee-local dynptrs and their slices before the frame goes away. */
	err = destroy_dynptrs_in_stack_slots(env, callee, 0,
					     callee->allocated_stack / BPF_REG_SIZE - 1);
	if (err)
		return err;

	/* for callbacks like bpf_loop or bpf_for_each_map_elem go back to callsite,
	 * there function call logic would reschedule callback visit. If iteration
	 * converges is_state_visited() would prune that visit eventually.
	 */
	in_callback_fn = callee->in_callback_fn;
	if (in_callback_fn)
		*insn_idx = callee->callsite;
	else
		*insn_idx = callee->callsite + 1;

	if (env->log.level & BPF_LOG_LEVEL) {
		verbose(env, "returning from callee:\n");
		print_verifier_state(env, state, callee->frameno, true);
		verbose(env, "to caller at %d:\n", *insn_idx);
		print_verifier_state(env, state, caller->frameno, true);
	}
	account_processed_insns(env, callee, caller);
	/* clear everything in the callee. In case of exceptional exits using
	 * bpf_throw, this will be done by copy_verifier_state for extra frames. */
	free_func_state(callee);
	state->frame[state->curframe--] = NULL;
	invalidate_outgoing_stack_args(env, caller);

	/* for callbacks widen imprecise scalars to make programs like below verify:
	 *
	 *   struct ctx { int i; }
	 *   void cb(int idx, struct ctx *ctx) { ctx->i++; ... }
	 *   ...
	 *   struct ctx = { .i = 0; }
	 *   bpf_loop(100, cb, &ctx, 0);
	 *
	 * This is similar to what is done in process_iter_next_call() for open
	 * coded iterators.
	 */
	prev_st = in_callback_fn ? find_prev_entry(env, state, *insn_idx) : NULL;
	if (prev_st) {
		err = widen_imprecise_scalars(env, prev_st, state);
		if (err)
			return err;
	}
	return 0;
}

static int do_refine_retval_range(struct bpf_verifier_env *env,
				  struct bpf_reg_state *regs, int ret_type,
				  int func_id,
				  struct bpf_call_arg_meta *meta)
{
	struct bpf_retval_range range;
	struct bpf_reg_state *ret_reg = &regs[BPF_REG_0];
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);

	if (ret_type != RET_INTEGER)
		return 0;

	switch (func_id) {
	case BPF_FUNC_get_stack:
	case BPF_FUNC_get_task_stack:
	case BPF_FUNC_probe_read_str:
	case BPF_FUNC_probe_read_kernel_str:
	case BPF_FUNC_probe_read_user_str:
		reg_set_srange64(ret_reg, -MAX_ERRNO, meta->msize_max_value);
		reg_set_srange32(ret_reg, -MAX_ERRNO, meta->msize_max_value);
		reg_bounds_sync(ret_reg);
		break;
	case BPF_FUNC_get_smp_processor_id:
		reg_set_urange64(ret_reg, 0, nr_cpu_ids - 1);
		reg_set_urange32(ret_reg, 0, nr_cpu_ids - 1);
		reg_bounds_sync(ret_reg);
		break;
	case BPF_FUNC_get_retval:
		/*
		 * bpf_get_retval may see arbitrary value passed by bpf_prog_run_array_cg for
		 * CGROUP_GETSOCKOPT type.
		 */
		if (prog_type == BPF_PROG_TYPE_CGROUP_SOCKOPT &&
		    env->prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT)
			break;

		if (prog_type == BPF_PROG_TYPE_LSM &&
		    env->prog->expected_attach_type == BPF_LSM_CGROUP) {
			if (!env->prog->aux->attach_func_proto->type)
				break;
			bpf_lsm_get_retval_range(env->prog, &range);
		} else {
			range.minval = -MAX_ERRNO;
			range.maxval = 0;
		}

		reg_set_srange64(ret_reg, range.minval, range.maxval);
		reg_set_srange32(ret_reg, range.minval, range.maxval);
		reg_bounds_sync(ret_reg);
		break;
	}

	return reg_bounds_sanity_check(env, ret_reg, "retval");
}

static int
record_func_map(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
		int func_id, int insn_idx)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
	struct bpf_map *map = meta->map.ptr;

	if (func_id != BPF_FUNC_tail_call &&
	    func_id != BPF_FUNC_map_lookup_elem &&
	    func_id != BPF_FUNC_map_update_elem &&
	    func_id != BPF_FUNC_map_delete_elem &&
	    func_id != BPF_FUNC_map_push_elem &&
	    func_id != BPF_FUNC_map_pop_elem &&
	    func_id != BPF_FUNC_map_peek_elem &&
	    func_id != BPF_FUNC_for_each_map_elem &&
	    func_id != BPF_FUNC_redirect_map &&
	    func_id != BPF_FUNC_map_lookup_percpu_elem)
		return 0;

	if (map == NULL) {
		verifier_bug(env, "expected map for helper call");
		return -EFAULT;
	}

	/* In case of read-only, some additional restrictions
	 * need to be applied in order to prevent altering the
	 * state of the map from program side.
	 */
	if ((map->map_flags & BPF_F_RDONLY_PROG) &&
	    (func_id == BPF_FUNC_map_delete_elem ||
	     func_id == BPF_FUNC_map_update_elem ||
	     func_id == BPF_FUNC_map_push_elem ||
	     func_id == BPF_FUNC_map_pop_elem)) {
		verbose(env, "write into map forbidden\n");
		return -EACCES;
	}

	if (!aux->map_ptr_state.map_ptr)
		bpf_map_ptr_store(aux, meta->map.ptr,
				  !meta->map.ptr->bypass_spec_v1, false);
	else if (aux->map_ptr_state.map_ptr != meta->map.ptr)
		bpf_map_ptr_store(aux, meta->map.ptr,
				  !meta->map.ptr->bypass_spec_v1, true);
	return 0;
}

static int
record_func_key(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
		int func_id, int insn_idx)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
	struct bpf_reg_state *reg;
	struct bpf_map *map = meta->map.ptr;
	u64 val, max;
	int err;

	if (func_id != BPF_FUNC_tail_call)
		return 0;
	if (!map || map->map_type != BPF_MAP_TYPE_PROG_ARRAY) {
		verbose(env, "expected prog array map for tail call");
		return -EINVAL;
	}

	reg = reg_state(env, BPF_REG_3);
	val = reg->var_off.value;
	max = map->max_entries;

	if (!(is_reg_const(reg, false) && val < max)) {
		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
		return 0;
	}

	err = mark_chain_precision(env, BPF_REG_3);
	if (err)
		return err;
	if (bpf_map_key_unseen(aux))
		bpf_map_key_store(aux, val);
	else if (!bpf_map_key_poisoned(aux) &&
		  bpf_map_key_immediate(aux) != val)
		bpf_map_key_store(aux, BPF_MAP_KEY_POISON);
	return 0;
}

static int check_reference_leak(struct bpf_verifier_env *env, bool exception_exit)
{
	struct bpf_verifier_state *state = env->cur_state;
	enum bpf_prog_type type = resolve_prog_type(env->prog);
	struct bpf_reg_state *reg = reg_state(env, BPF_REG_0);
	bool refs_lingering = false;
	int i;

	if (!exception_exit && cur_func(env)->frameno)
		return 0;

	for (i = 0; i < state->acquired_refs; i++) {
		if (state->refs[i].type != REF_TYPE_PTR)
			continue;
		/* Allow struct_ops programs to return a referenced kptr back to
		 * kernel. Type checks are performed later in check_return_code.
		 */
		if (type == BPF_PROG_TYPE_STRUCT_OPS && !exception_exit &&
		    reg->id == state->refs[i].id)
			continue;
		verbose(env, "Unreleased reference id=%d alloc_insn=%d\n",
			state->refs[i].id, state->refs[i].insn_idx);
		bpf_diag_leak(env, state->refs[i].id, state->refs[i].insn_idx, env->insn_idx);
		refs_lingering = true;
	}
	return refs_lingering ? -EINVAL : 0;
}

static int check_resource_leak(struct bpf_verifier_env *env, bool exception_exit, bool check_lock, const char *prefix)
{
	int err;

	if (check_lock && env->cur_state->active_locks) {
		verbose(env, "%s cannot be used inside bpf_spin_lock-ed region\n", prefix);
		bpf_diag_ctx_active(env, env->insn_idx, prefix, BPF_DIAG_CONTEXT_LOCK,
				    "Release the BPF spin lock before this operation on every path.");
		return -EINVAL;
	}

	err = check_reference_leak(env, exception_exit);
	if (err) {
		verbose(env, "%s would lead to reference leak\n", prefix);
		return err;
	}

	if (check_lock && env->cur_state->active_irq_id) {
		verbose(env, "%s cannot be used inside bpf_local_irq_save-ed region\n", prefix);
		bpf_diag_ctx_active(env, env->insn_idx, prefix, BPF_DIAG_CONTEXT_IRQ,
				    "Restore the saved IRQ state before this operation on every path.");
		return -EINVAL;
	}

	if (check_lock && env->cur_state->active_rcu_locks) {
		verbose(env, "%s cannot be used inside bpf_rcu_read_lock-ed region\n", prefix);
		bpf_diag_ctx_active(env, env->insn_idx, prefix, BPF_DIAG_CONTEXT_RCU,
				    "Call bpf_rcu_read_unlock() before this operation on every path.");
		return -EINVAL;
	}

	if (check_lock && env->cur_state->active_preempt_locks) {
		verbose(env, "%s cannot be used inside bpf_preempt_disable-ed region\n", prefix);
		bpf_diag_ctx_active(
			env, env->insn_idx, prefix, BPF_DIAG_CONTEXT_PREEMPT,
			"Call bpf_preempt_enable() before this operation on every path.");
		return -EINVAL;
	}

	return 0;
}

static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
				   struct bpf_reg_state *regs)
{
	struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
	struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
	struct bpf_map *fmt_map = fmt_reg->map_ptr;
	struct bpf_bprintf_data data = {};
	int err, fmt_map_off, num_args;
	u64 fmt_addr;
	char *fmt;

	/* data must be an array of u64 */
	if (data_len_reg->var_off.value % 8)
		return -EINVAL;
	num_args = data_len_reg->var_off.value / 8;

	/* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const
	 * and map_direct_value_addr is set.
	 */
	fmt_map_off = fmt_reg->var_off.value;
	err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
						  fmt_map_off);
	if (err) {
		verbose(env, "failed to retrieve map value address\n");
		return -EFAULT;
	}
	fmt = (char *)(long)fmt_addr + fmt_map_off;

	/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
	 * can focus on validating the format specifiers.
	 */
	err = bpf_bprintf_prepare(fmt, UINT_MAX, NULL, num_args, &data);
	if (err < 0)
		verbose(env, "Invalid format string\n");

	return err;
}

static int check_get_func_ip(struct bpf_verifier_env *env)
{
	enum bpf_prog_type type = resolve_prog_type(env->prog);
	int func_id = BPF_FUNC_get_func_ip;

	if (type == BPF_PROG_TYPE_TRACING) {
		if (!bpf_prog_has_trampoline(env->prog)) {
			verbose(env, "func %s#%d supported only for fentry/fexit/fsession/fmod_ret programs\n",
				func_id_name(func_id), func_id);
			return -ENOTSUPP;
		}
		return 0;
	} else if (type == BPF_PROG_TYPE_KPROBE) {
		return 0;
	}

	verbose(env, "func %s#%d not supported for program type %d\n",
		func_id_name(func_id), func_id, type);
	return -ENOTSUPP;
}

static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env)
{
	return &env->insn_aux_data[env->insn_idx];
}

/* Returns 1 if R4 is a known zero, 0 if it is not, a negative errno on error. */
static int loop_flag_is_zero(struct bpf_verifier_env *env)
{
	struct bpf_reg_state *reg = reg_state(env, BPF_REG_4);
	int err;

	if (!bpf_register_is_null(reg))
		return 0;

	err = mark_chain_precision(env, BPF_REG_4);
	if (err)
		return err;
	return 1;
}

static int update_loop_inline_state(struct bpf_verifier_env *env, u32 subprogno)
{
	struct bpf_loop_inline_state *state = &cur_aux(env)->loop_inline_state;
	int flag_is_zero;

	if (!state->initialized) {
		flag_is_zero = loop_flag_is_zero(env);
		if (flag_is_zero < 0)
			return flag_is_zero;
		state->initialized = 1;
		state->fit_for_inline = flag_is_zero;
		state->callback_subprogno = subprogno;
		return 0;
	}

	if (!state->fit_for_inline)
		return 0;

	flag_is_zero = loop_flag_is_zero(env);
	if (flag_is_zero < 0)
		return flag_is_zero;
	state->fit_for_inline = (flag_is_zero &&
				 state->callback_subprogno == subprogno);
	return 0;
}

/* Returns whether or not the given map can potentially elide
 * lookup return value nullness check. This is possible if the key
 * is statically known.
 */
static bool can_elide_value_nullness(const struct bpf_map *map)
{
	if (map->map_flags & BPF_F_INNER_MAP)
		return false;

	switch (map->map_type) {
	case BPF_MAP_TYPE_ARRAY:
	case BPF_MAP_TYPE_PERCPU_ARRAY:
		return true;
	default:
		return false;
	}
}

int bpf_get_helper_proto(struct bpf_verifier_env *env, int func_id,
			 const struct bpf_func_proto **ptr)
{
	if (func_id < 0 || func_id >= __BPF_FUNC_MAX_ID)
		return -ERANGE;

	if (!env->ops->get_func_proto)
		return -EINVAL;

	*ptr = env->ops->get_func_proto(func_id, env->prog);
	return *ptr && (*ptr)->func ? 0 : -EINVAL;
}

/* Is any frame on the current path a callback that runs under RCU? */
static bool in_rcu_callback(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *state = env->cur_state;
	int i;

	for (i = 0; i <= state->curframe; i++)
		if (state->frame[i]->in_rcu_callback_fn)
			return true;
	return false;
}

/* Check if we're in a sleepable context. */
static inline bool in_sleepable_context(struct bpf_verifier_env *env)
{
	return !in_rcu_cs(env) && !in_rcu_callback(env);
}

static const char *non_sleepable_context_description(struct bpf_verifier_env *env)
{
	if (in_sleepable(env)) {
		if (env->cur_state->active_rcu_locks)
			return "rcu_read_lock region";
		if (env->cur_state->active_preempt_locks)
			return "non-preemptible region";
		if (env->cur_state->active_irq_id)
			return "IRQ-disabled region";
		if (env->cur_state->active_locks)
			return "lock region";
		return "callback running under rcu_read_lock";
	}
	return "non-sleepable prog";
}

static int release_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
		       bool convert_rcu, bool release_dynptr)
{
	int err = -EINVAL;

	if (bpf_register_is_null(reg))
		return 0;

	if (release_dynptr)
		err = unmark_stack_slots_dynptr(env, reg);
	else if (convert_rcu)
		err = ref_convert_alloc_rcu_protected(env, reg->id);
	else if (reg_is_referenced(env, reg))
		err = release_reference(env, reg->id);

	return err;
}

static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
			     int *insn_idx_p)
{
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
	bool returns_cpu_specific_alloc_ptr = false;
	const struct bpf_func_proto *fn = NULL;
	enum bpf_return_type ret_type;
	enum bpf_type_flag ret_flag;
	struct bpf_reg_state *regs;
	struct bpf_call_arg_meta meta;
	const char *operation;
	int insn_idx = *insn_idx_p;
	bool changes_data;
	int i, err, func_id;

	/* find function prototype */
	func_id = insn->imm;
	err = bpf_get_helper_proto(env, insn->imm, &fn);
	if (err == -ERANGE) {
		verbose(env, "invalid func %s#%d\n", func_id_name(func_id), func_id);
		return -EINVAL;
	}

	if (err) {
		verbose(env, "program of this type cannot use helper %s#%d\n",
			func_id_name(func_id), func_id);
		operation = bpf_diag_fmt(env, "helper %s#%d", func_id_name(func_id), func_id);
		bpf_diag_policy(
			env, insn_idx, operation, "this program type does not allow the helper",
			"Use a helper allowed for this program type, or move the logic to a compatible program type.");
		return err;
	}

	/* eBPF programs must be GPL compatible to use GPL-ed functions */
	if (!env->prog->gpl_compatible && fn->gpl_only) {
		verbose(env, "cannot call GPL-restricted function from non-GPL compatible program\n");
		operation = bpf_diag_fmt(env, "helper %s#%d", func_id_name(func_id), func_id);
		bpf_diag_policy(
			env, insn_idx, operation,
			"this helper is restricted to GPL-compatible programs",
			"Use a GPL-compatible license, or replace the helper with one that is available to non-GPL programs.");
		return -EINVAL;
	}

	if (fn->allowed && !fn->allowed(env->prog)) {
		verbose(env, "helper call is not allowed in probe\n");
		operation = bpf_diag_fmt(env, "helper %s#%d", func_id_name(func_id), func_id);
		bpf_diag_policy(
			env, insn_idx, operation,
			"the helper-specific policy callback rejected this program",
			"Use the helper only from an allowed attach point or program configuration.");
		return -EINVAL;
	}

	/* With LD_ABS/IND some JITs save/restore skb from r1. */
	changes_data = bpf_helper_changes_pkt_data(func_id);
	if (changes_data && fn->arg1_type != ARG_PTR_TO_CTX) {
		verifier_bug(env, "func %s#%d: r1 != ctx", func_id_name(func_id), func_id);
		return -EFAULT;
	}

	memset(&meta, 0, sizeof(meta));

	err = check_func_proto(env, fn, &meta);
	if (err) {
		verifier_bug(env, "incorrect func proto %s#%d", func_id_name(func_id), func_id);
		return err;
	}

	if (fn->might_sleep && !in_sleepable_context(env)) {
		const char *suggestion;

		verbose(env, "sleepable helper %s#%d in %s\n", func_id_name(func_id), func_id,
			non_sleepable_context_description(env));
		if (in_sleepable(env))
			suggestion = "Move the helper call outside the critical section, or use a non-sleepable helper.";
		else
			suggestion = "Mark the program sleepable if the program type allows it, or use a non-sleepable helper.";
		operation = bpf_diag_fmt(env, "sleepable helper %s#%d",
					 func_id_name(func_id), func_id);
		bpf_diag_ctx_forbidden(env, insn_idx, operation, suggestion);
		return -EINVAL;
	}

	/* Track non-sleepable context for helpers. */
	if (!in_sleepable_context(env))
		env->insn_aux_data[insn_idx].non_sleepable = true;

	meta.func_id = func_id;
	meta.func_name = func_id_name(func_id);
	meta.fn = fn;
	err = check_func_args(env, &meta, insn_idx);
	if (err)
		return err;

	err = record_func_map(env, &meta, func_id, insn_idx);
	if (err)
		return err;

	err = record_func_key(env, &meta, func_id, insn_idx);
	if (err)
		return err;

	regs = cur_regs(env);

	err = mark_raw_stack(env, &meta, insn_idx);
	if (err)
		return err;

	if (meta.release_regno) {
		struct bpf_reg_state *reg = &regs[meta.release_regno];
		bool convert_rcu = (func_id == BPF_FUNC_kptr_xchg) && in_rcu_cs(env) &&
				   (reg->type & MEM_ALLOC) && (reg->type & MEM_PERCPU);

		err = release_reg(env, reg, convert_rcu, !!meta.dynptr.id);
		if (err)
			return err;
	}

	switch (func_id) {
	case BPF_FUNC_tail_call:
		err = check_resource_leak(env, false, true, "tail_call");
		if (err)
			return err;
		break;
	case BPF_FUNC_get_local_storage:
		/* check that flags argument in get_local_storage(map, flags) is 0,
		 * this is required because get_local_storage() can't return an error.
		 */
		if (!bpf_register_is_null(&regs[BPF_REG_2])) {
			verbose(env, "get_local_storage() doesn't support non-zero flags\n");
			return -EINVAL;
		}
		err = mark_chain_precision(env, BPF_REG_2);
		if (err)
			return err;
		break;
	case BPF_FUNC_for_each_map_elem:
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_map_elem_callback_state);
		break;
	case BPF_FUNC_timer_set_callback:
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_timer_callback_state);
		break;
	case BPF_FUNC_find_vma:
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_find_vma_callback_state);
		break;
	case BPF_FUNC_snprintf:
		err = check_bpf_snprintf_call(env, regs);
		break;
	case BPF_FUNC_loop:
		err = update_loop_inline_state(env, meta.subprogno);
		if (err)
			return err;
		/* Verifier relies on R1 value to determine if bpf_loop() iteration
		 * is finished, thus mark it precise.
		 */
		err = mark_chain_precision(env, BPF_REG_1);
		if (err)
			return err;
		if (cur_func(env)->callback_depth < reg_umax(&regs[BPF_REG_1])) {
			err = push_callback_call(env, insn, insn_idx, meta.subprogno,
						 set_loop_callback_state);
		} else {
			cur_func(env)->callback_depth = 0;
			if (env->log.level & BPF_LOG_LEVEL2)
				verbose(env, "frame%d bpf_loop iteration limit reached\n",
					env->cur_state->curframe);
		}
		break;
	case BPF_FUNC_dynptr_from_mem:
		if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
			verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n",
				reg_type_str(env, regs[BPF_REG_1].type));
			return -EACCES;
		}
		break;
	case BPF_FUNC_set_retval:
	{
		struct bpf_retval_range range = {
			.minval = -MAX_ERRNO,
			.maxval = 0,
			.return_32bit = true
		};
		struct bpf_reg_state *r1 = &regs[BPF_REG_1];

		if (r1->type != SCALAR_VALUE) {
			verbose(env, "R1 is not a scalar\n");
			return -EINVAL;
		}

		/* CGROUP_GETSOCKOPT is allowed to return arbitrary value */
		if (prog_type == BPF_PROG_TYPE_CGROUP_SOCKOPT &&
		    env->prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT)
			break;

		if (prog_type == BPF_PROG_TYPE_LSM &&
		    env->prog->expected_attach_type == BPF_LSM_CGROUP) {
			if (!env->prog->aux->attach_func_proto->type) {
				/* Make sure programs that attach to void
				 * hooks don't try to modify return value.
				 */
				verbose(env, "BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
				return -EINVAL;
			}
			bpf_lsm_get_retval_range(env->prog, &range);
		}

		err = mark_chain_precision(env, BPF_REG_1);
		if (err)
			return err;

		if (!retval_range_within(range, r1)) {
			verbose_invalid_scalar(env, r1, range, "At bpf_set_retval", "R1");
			return -EINVAL;
		}

		break;
	}
	case BPF_FUNC_dynptr_write:
	{
		enum bpf_dynptr_type dynptr_type = meta.dynptr.type;

		if (dynptr_type == BPF_DYNPTR_TYPE_INVALID)
			return -EFAULT;

		if (dynptr_write_changes_pkt_data(dynptr_type))
			/* this will trigger clear_all_pkt_pointers(), which will
			 * invalidate all dynptr slices associated with the skb
			 */
			changes_data = true;

		break;
	}
	case BPF_FUNC_per_cpu_ptr:
	case BPF_FUNC_this_cpu_ptr:
	{
		struct bpf_reg_state *reg = &regs[BPF_REG_1];
		const struct btf_type *type;

		if (reg->type & MEM_RCU) {
			type = btf_type_by_id(reg->btf, reg->btf_id);
			if (!type || !btf_type_is_struct(type)) {
				verbose(env, "Helper has invalid btf/btf_id in R1\n");
				return -EFAULT;
			}
			returns_cpu_specific_alloc_ptr = true;
			env->insn_aux_data[insn_idx].call_with_percpu_alloc_ptr = true;
		}
		break;
	}
	case BPF_FUNC_user_ringbuf_drain:
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_user_ringbuf_callback_state);
		break;
	}

	if (err)
		return err;

	/* reset caller saved regs */
	bpf_diag_record_caller_saved(env, regs);
	bpf_diag_mod_begin(env, &regs[BPF_REG_0], NULL, BPF_DIAG_MOD_WRITE);
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		bpf_mark_reg_not_init(env, &regs[caller_saved[i]]);
		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
	}
	invalidate_outgoing_stack_args(env, cur_func(env));

	/* update return register (already marked as written above) */
	ret_type = fn->ret_type;
	ret_flag = type_flag(ret_type);

	switch (base_type(ret_type)) {
	case RET_INTEGER:
		/* sets type to SCALAR_VALUE */
		mark_reg_unknown(env, regs, BPF_REG_0);
		break;
	case RET_VOID:
		regs[BPF_REG_0].type = NOT_INIT;
		break;
	case RET_PTR_TO_MAP_VALUE:
		/* There is no offset yet applied, variable or fixed */
		mark_reg_known_zero(env, regs, BPF_REG_0);
		/* remember map_ptr, so that check_map_access()
		 * can check 'value_size' boundary of memory access
		 * to map element returned from bpf_map_lookup_elem()
		 */
		if (meta.map.ptr == NULL) {
			verifier_bug(env, "unexpected null map_ptr");
			return -EFAULT;
		}

		if (func_id == BPF_FUNC_map_lookup_elem &&
		    can_elide_value_nullness(meta.map.ptr) &&
		    meta.const_map_key >= 0 &&
		    meta.const_map_key < meta.map.ptr->max_entries)
			ret_flag &= ~PTR_MAYBE_NULL;

		regs[BPF_REG_0].map_ptr = meta.map.ptr;
		regs[BPF_REG_0].map_uid = meta.map.uid;
		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE | ret_flag;
		if (type_may_be_null(ret_flag) ||
		    btf_record_has_field(meta.map.ptr->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) {
			regs[BPF_REG_0].id = ++env->id_gen;
		}
		/* requires regs[BPF_REG_0].id to be set because of the map-in-map case */
		refine_map_lookup_value(&regs[BPF_REG_0]);
		break;
	case RET_PTR_TO_SOCKET:
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_SOCKET | ret_flag;
		break;
	case RET_PTR_TO_SOCK_COMMON:
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON | ret_flag;
		break;
	case RET_PTR_TO_TCP_SOCK:
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK | ret_flag;
		break;
	case RET_PTR_TO_MEM:
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
		regs[BPF_REG_0].mem_size = meta.ret_mem.size;
		break;
	case RET_PTR_TO_MEM_OR_BTF_ID:
	{
		const struct btf_type *t;

		mark_reg_known_zero(env, regs, BPF_REG_0);
		t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL);
		if (!btf_type_is_struct(t)) {
			u32 tsize;
			const struct btf_type *ret;
			const char *tname;

			/* resolve the type size of ksym. */
			ret = btf_resolve_size(meta.ret_btf, t, &tsize);
			if (IS_ERR(ret)) {
				tname = btf_name_by_offset(meta.ret_btf, t->name_off);
				verbose(env, "unable to resolve the size of type '%s': %ld\n",
					tname, PTR_ERR(ret));
				return -EINVAL;
			}
			regs[BPF_REG_0].type = PTR_TO_MEM | ret_flag;
			regs[BPF_REG_0].mem_size = tsize;
		} else {
			if (returns_cpu_specific_alloc_ptr) {
				regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC | MEM_RCU;
			} else {
				/* MEM_RDONLY may be carried from ret_flag, but it
				 * doesn't apply on PTR_TO_BTF_ID. Fold it, otherwise
				 * it will confuse the check of PTR_TO_BTF_ID in
				 * check_mem_access().
				 */
				ret_flag &= ~MEM_RDONLY;
				regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
			}

			regs[BPF_REG_0].btf = meta.ret_btf;
			regs[BPF_REG_0].btf_id = meta.ret_btf_id;
		}
		break;
	}
	case RET_PTR_TO_BTF_ID:
	{
		struct btf *ret_btf;
		int ret_btf_id;

		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_BTF_ID | ret_flag;
		if (func_id == BPF_FUNC_kptr_xchg) {
			ret_btf = meta.kptr_field->kptr.btf;
			ret_btf_id = meta.kptr_field->kptr.btf_id;
			if (!btf_is_kernel(ret_btf)) {
				regs[BPF_REG_0].type |= MEM_ALLOC;
				if (meta.kptr_field->type == BPF_KPTR_PERCPU)
					regs[BPF_REG_0].type |= MEM_PERCPU;
			}
		} else {
			if (fn->ret_btf_id == BPF_PTR_POISON) {
				verifier_bug(env, "func %s has non-overwritten BPF_PTR_POISON return type",
					     func_id_name(func_id));
				return -EFAULT;
			}
			ret_btf = btf_vmlinux;
			ret_btf_id = *fn->ret_btf_id;
		}
		if (ret_btf_id == 0) {
			verbose(env, "invalid return type %u of func %s#%d\n",
				base_type(ret_type), func_id_name(func_id),
				func_id);
			return -EINVAL;
		}
		regs[BPF_REG_0].btf = ret_btf;
		regs[BPF_REG_0].btf_id = ret_btf_id;
		break;
	}
	default:
		verbose(env, "unknown return type %u of func %s#%d\n",
			base_type(ret_type), func_id_name(func_id), func_id);
		return -EINVAL;
	}

	if (type_may_be_null(regs[BPF_REG_0].type) && !regs[BPF_REG_0].id)
		regs[BPF_REG_0].id = ++env->id_gen;

	if (is_ptr_cast_function(func_id) &&
	    find_reference_state(env->cur_state, meta.ref_obj.id)) {
		struct bpf_verifier_state *branch;
		struct bpf_reg_state *r0;

		err = validate_ref_obj(env, &meta.ref_obj);
		if (err)
			return err;

		bpf_diag_mod_end(env);

		/*
		 * In order for a release of any of the original or cast pointers
		 * to invalidate all other pointers, reuse the same reference id for
		 * the cast result.
		 * This reference id can't be used for nullness propagation,
		 * as cast might return NULL for a non-NULL input.
		 * Hence, explore the NULL case as a separate branch.
		 */
		branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
		if (IS_ERR(branch))
			return PTR_ERR(branch);

		r0 = &branch->frame[branch->curframe]->regs[BPF_REG_0];
		__mark_reg_known_zero(r0);
		r0->type = SCALAR_VALUE;

		bpf_diag_mod_begin(env, &regs[BPF_REG_0], NULL, BPF_DIAG_MOD_WRITE);
		regs[BPF_REG_0].type &= ~PTR_MAYBE_NULL;
		regs[BPF_REG_0].id = meta.ref_obj.id;
	} else if (is_acquire_function(func_id, meta.map.ptr)) {
		int id = acquire_reference(env, insn_idx, 0);

		if (id < 0)
			return id;

		regs[BPF_REG_0].id = id;
	}

	if (func_id == BPF_FUNC_dynptr_data)
		regs[BPF_REG_0].parent_id = meta.dynptr.id;

	err = do_refine_retval_range(env, regs, fn->ret_type, func_id, &meta);
	if (err)
		return err;

	bpf_diag_mod_end(env);

	err = check_map_func_compatibility(env, meta.map.ptr, func_id);
	if (err)
		return err;

	if ((func_id == BPF_FUNC_get_stack ||
	     func_id == BPF_FUNC_get_task_stack) &&
	    !env->prog->has_callchain_buf) {
		const char *err_str;

#ifdef CONFIG_PERF_EVENTS
		err = get_callchain_buffers(sysctl_perf_event_max_stack);
		err_str = "cannot get callchain buffer for func %s#%d\n";
#else
		err = -ENOTSUPP;
		err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n";
#endif
		if (err) {
			verbose(env, err_str, func_id_name(func_id), func_id);
			return err;
		}

		env->prog->has_callchain_buf = true;
	}

	if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
		env->prog->call_get_stack = true;

	if (func_id == BPF_FUNC_get_func_ip) {
		if (check_get_func_ip(env))
			return -ENOTSUPP;
		env->prog->call_get_func_ip = true;
	}

	if (func_id == BPF_FUNC_tail_call) {
		if (env->cur_state->curframe) {
			struct bpf_verifier_state *branch;

			/*
			 * A taken tail call is modeled as a return from the current
			 * frame. A callback frame cannot be left that way because
			 * prepare_func_exit() would apply its return contract to the
			 * unknown R0 synthesized below. Stack-depth validation rejects
			 * this construct anyway.
			 */
			if (cur_func(env)->in_callback_fn) {
				verbose(env, "cannot tail call within callback\n");
				return -EINVAL;
			}
			mark_reg_scratched(env, BPF_REG_0);
			branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
			if (IS_ERR(branch))
				return PTR_ERR(branch);
			clear_all_pkt_pointers(env);
			mark_reg_unknown(env, regs, BPF_REG_0);
			err = prepare_func_exit(env, &env->insn_idx);
			if (err)
				return err;
			env->insn_idx--;
		} else {
			changes_data = false;
		}
	}

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

/*
 * Mark the register(s) holding a @size byte kfunc return value as unknown
 * scalars and return how many registers that took. Both halves of a register
 * pair are treated the same way.
 *
 * R0 is written in the diagnostic modification scope the caller opened before
 * the caller-saved scrub, since R0 gets no scrub record of its own and that
 * scope is what carries its pre-call value into the history. A scope tracks a
 * single register and does not nest, so close it before recording the rest of
 * the return value. A value that fits in R0 leaves the caller's scope open for
 * the caller to close, so a later write to R0 still lands in it.
 */
static u32 mark_kfunc_ret_regs(struct bpf_verifier_env *env,
			       struct bpf_reg_state *regs, u32 size)
{
	u32 i, nregs = ret_regs_cnt(size);

	mark_reg_unknown(env, regs, ret_regs[0]);
	if (nregs == 1)
		return nregs;

	bpf_diag_mod_end(env);
	for (i = 1; i < nregs; i++) {
		bpf_diag_mod_begin(env, &regs[ret_regs[i]], NULL, BPF_DIAG_MOD_WRITE);
		mark_reg_unknown(env, regs, ret_regs[i]);
		bpf_diag_mod_end(env);
	}

	return nregs;
}

static bool is_kfunc_acquire(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_ACQUIRE;
}

static bool is_kfunc_release(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_RELEASE;
}

static bool is_kfunc_destructive(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_DESTRUCTIVE;
}

static bool is_kfunc_perfmon(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_PERFMON;
}

static bool is_kfunc_rcu(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_RCU;
}

static bool is_kfunc_rcu_protected(struct bpf_call_arg_meta *meta)
{
	return meta->kfunc_flags & KF_RCU_PROTECTED;
}

static bool is_kfunc_arg_mem_size(const struct btf *btf,
				  const struct btf_param *arg)
{
	const struct btf_type *t;

	t = btf_type_skip_modifiers(btf, arg->type, NULL);
	if (!btf_type_is_scalar(t))
		return false;

	return btf_param_match_suffix(btf, arg, "__sz");
}

static bool is_kfunc_arg_const_mem_size(const struct btf *btf,
					const struct btf_param *arg)
{
	const struct btf_type *t;

	t = btf_type_skip_modifiers(btf, arg->type, NULL);
	if (!btf_type_is_scalar(t))
		return false;

	return btf_param_match_suffix(btf, arg, "__szk");
}

static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__k");
}

static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__ign");
}

static bool is_kfunc_arg_map(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__map");
}

static bool is_kfunc_arg_const_map(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__const_map");
}

static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__alloc");
}

static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__uninit");
}

static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__refcounted_kptr");
}

static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__nullable") ||
	       btf_param_match_suffix(btf, arg, "__arena");
}

static bool is_kfunc_arg_nonown_allowed(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__nonown_allowed");
}

static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__str");
}

static bool is_kfunc_arg_irq_flag(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__irq_flag");
}

static bool is_kfunc_arg_ctx_out(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__ctx_out");
}

static bool is_kfunc_arg_arena(const struct btf *btf, const struct btf_param *arg)
{
	return btf_param_match_suffix(btf, arg, "__arena__nullable") ||
	       btf_param_match_suffix(btf, arg, "__arena");
}

static bool is_kfunc_arg_scalar_with_name(const struct btf *btf,
					  const struct btf_param *arg,
					  const char *name)
{
	int len, target_len = strlen(name);
	const char *param_name;

	param_name = btf_name_by_offset(btf, arg->name_off);
	if (str_is_empty(param_name))
		return false;
	len = strlen(param_name);
	if (len != target_len)
		return false;
	if (strcmp(param_name, name))
		return false;

	return true;
}

enum {
	KF_ARG_DYNPTR_ID,
	KF_ARG_LIST_HEAD_ID,
	KF_ARG_LIST_NODE_ID,
	KF_ARG_RB_ROOT_ID,
	KF_ARG_RB_NODE_ID,
	KF_ARG_WORKQUEUE_ID,
	KF_ARG_RES_SPIN_LOCK_ID,
	KF_ARG_TASK_WORK_ID,
	KF_ARG_PROG_AUX_ID,
	KF_ARG_TIMER_ID,
	KF_ARG_RCU_HEAD_ID
};

BTF_ID_LIST(kf_arg_btf_ids)
BTF_ID(struct, bpf_dynptr)
BTF_ID(struct, bpf_list_head)
BTF_ID(struct, bpf_list_node)
BTF_ID(struct, bpf_rb_root)
BTF_ID(struct, bpf_rb_node)
BTF_ID(struct, bpf_wq)
BTF_ID(struct, bpf_res_spin_lock)
BTF_ID(struct, bpf_task_work)
BTF_ID(struct, bpf_prog_aux)
BTF_ID(struct, bpf_timer)
BTF_ID(struct, bpf_rcu_head)

static bool __is_kfunc_ptr_arg_type(const struct btf *btf,
				    const struct btf_param *arg, int type)
{
	const struct btf_type *t;
	u32 res_id;

	t = btf_type_skip_modifiers(btf, arg->type, NULL);
	if (!t)
		return false;
	if (!btf_type_is_ptr(t))
		return false;
	t = btf_type_skip_modifiers(btf, t->type, &res_id);
	if (!t)
		return false;
	return btf_types_are_same(btf, res_id, btf_vmlinux, kf_arg_btf_ids[type]);
}

static bool is_kfunc_arg_dynptr(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_DYNPTR_ID);
}

static bool is_kfunc_arg_list_head(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_HEAD_ID);
}

static bool is_kfunc_arg_list_node(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_LIST_NODE_ID);
}

static bool is_kfunc_arg_rbtree_root(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_ROOT_ID);
}

static bool is_kfunc_arg_rbtree_node(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RB_NODE_ID);
}

static bool is_kfunc_arg_timer(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_TIMER_ID);
}

static bool is_kfunc_arg_wq(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_WORKQUEUE_ID);
}

static bool is_kfunc_arg_task_work(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_TASK_WORK_ID);
}

static bool is_kfunc_arg_rcu_head(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RCU_HEAD_ID);
}

static bool is_kfunc_arg_res_spin_lock(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_RES_SPIN_LOCK_ID);
}

static bool is_rbtree_node_type(const struct btf_type *t)
{
	return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_RB_NODE_ID]);
}

static bool is_list_node_type(const struct btf_type *t)
{
	return t == btf_type_by_id(btf_vmlinux, kf_arg_btf_ids[KF_ARG_LIST_NODE_ID]);
}

static bool is_kfunc_arg_callback(struct bpf_verifier_env *env, const struct btf *btf,
				  const struct btf_param *arg)
{
	const struct btf_type *t;

	t = btf_type_resolve_func_ptr(btf, arg->type, NULL);
	if (!t)
		return false;

	return true;
}

static bool is_kfunc_arg_prog_aux(const struct btf *btf, const struct btf_param *arg)
{
	return __is_kfunc_ptr_arg_type(btf, arg, KF_ARG_PROG_AUX_ID);
}

/*
 * A kfunc with KF_IMPLICIT_ARGS has two prototypes in BTF:
 *   - the _impl prototype with full arg list (meta->func_proto)
 *   - the BPF API prototype w/o implicit args (func->type in BTF)
 * To determine whether an argument is implicit, we compare its position
 * against the number of arguments in the prototype w/o implicit args.
 */
static bool is_kfunc_arg_implicit(const struct bpf_call_arg_meta *meta, u32 arg_idx)
{
	const struct btf_type *func, *func_proto;
	u32 argn;

	if (!(meta->kfunc_flags & KF_IMPLICIT_ARGS))
		return false;

	func = btf_type_by_id(meta->btf, meta->func_id);
	func_proto = btf_type_by_id(meta->btf, func->type);
	argn = btf_type_vlen(func_proto);

	return argn <= arg_idx;
}

#define BTF_MEMBER_MAX_DEPTH	4
#define BTF_MEMBER_PATH_LEN	64

struct btf_member_path {
	const struct btf_member *member[BTF_MEMBER_MAX_DEPTH];
	bool in_array[BTF_MEMBER_MAX_DEPTH];
	const struct btf_type *bad_type;
	int depth;
	bool too_deep;
};

static bool btf_member_kind_allowed(const struct btf *btf, const struct btf_type *t,
				    u32 member_kinds)
{
	if ((member_kinds & BTF_MEMBER_SCALAR) && btf_type_is_scalar(t))
		return true;
	if ((member_kinds & BTF_MEMBER_ARENA_PTR) && btf_type_is_arena_ptr(btf, t))
		return true;
	return false;
}

/*
 * Returns true if every member of struct @t is of a kind listed in
 * @member_kinds, 4 levels of nesting allowed. An array member counts as its
 * element type.
 */
static bool btf_struct_member_walk(struct bpf_verifier_env *env, const struct btf *btf,
				   const struct btf_type *t, u32 member_kinds, int rec,
				   struct btf_member_path *path)
{
	const struct btf_type *member_type;
	const struct btf_member *member;
	bool in_array;
	u32 i;

	if (!btf_type_is_struct(t))
		return false;

	for_each_member(i, t, member) {
		const struct btf_array *array;

		in_array = false;
		member_type = btf_type_skip_modifiers(btf, member->type, NULL);
		/*
		 * Every element of an array is laid out in the value being
		 * returned, so an array counts as its element type however many
		 * dimensions deep that is.
		 */
		while (btf_type_is_array(member_type)) {
			array = btf_array(member_type);
			if (!array->nelems) {
				member_type = NULL;
				goto bad_member;
			}
			member_type = btf_type_skip_modifiers(btf, array->type, NULL);
			in_array = true;
		}
		if (btf_type_is_struct(member_type)) {
			if (rec >= BTF_MEMBER_MAX_DEPTH - 1) {
				verbose(env, "max struct nesting depth exceeded\n");
				if (path)
					path->too_deep = true;
				return false;
			}
			if (!btf_struct_member_walk(env, btf, member_type, member_kinds,
						    rec + 1, path))
				goto bad_path;
			continue;
		}
		if (!btf_member_kind_allowed(btf, member_type, member_kinds))
			goto bad_member;
	}
	return true;

bad_member:
	if (path) {
		path->depth = rec + 1;
		path->bad_type = member_type;
	}
bad_path:
	if (path && path->depth) {
		path->member[rec] = member;
		path->in_array[rec] = in_array;
	}
	return false;
}

bool btf_struct_is_composed_of(struct bpf_verifier_env *env,
			       const struct btf *btf,
			       const struct btf_type *t, u32 member_kinds)
{
	return btf_struct_member_walk(env, btf, t, member_kinds, 0, NULL);
}

static bool btf_type_is_scalar_struct(struct bpf_verifier_env *env,
				      const struct btf *btf,
				      const struct btf_type *t)
{
	return btf_struct_is_composed_of(env, btf, t, BTF_MEMBER_SCALAR);
}

static int resolve_func_arg_type(struct bpf_verifier_env *env,
				 struct bpf_reg_state *reg, u32 arg, argno_t argno,
				 struct bpf_call_arg_meta *meta,
				 enum bpf_arg_type *arg_type, u32 *arg_size)
{
	const struct btf_param *args;
	const struct btf_type *ref_t, *resolve_ret;
	const struct btf *btf;
	const char *ref_tname;
	u32 ref_id;

	if (base_type(*arg_type) == ARG_PTR_TO_MAP_VALUE)
		return resolve_map_arg_type(env, meta, arg_type);

	if (base_type(*arg_type) != ARG_PTR_TO_BTF_ID)
		return 0;

	if (!is_kfunc(meta) || arg_type_is_release(*arg_type) ||
	    base_type(reg->type) == PTR_TO_BTF_ID ||
	    reg2btf_ids[base_type(reg->type)])
		return 0;

	args = btf_params(meta->func_proto);
	ref_id = *meta->fn->arg_btf_id[arg];
	btf = is_kfunc_arg_map(meta->btf, &args[arg]) ? btf_vmlinux : meta->btf;
	ref_t = btf_type_skip_modifiers(btf, ref_id, &ref_id);
	ref_tname = btf_name_by_offset(btf, ref_t->name_off);

	if (!btf_type_is_scalar_struct(env, btf, ref_t))
		return 0;

	resolve_ret = btf_resolve_size(btf, ref_t, arg_size);
	if (IS_ERR(resolve_ret)) {
		verbose(env, "%s reference type('%s %s') size cannot be determined: %ld\n",
			reg_arg_name(env, argno), btf_type_str(ref_t), ref_tname,
			PTR_ERR(resolve_ret));
		return -EINVAL;
	}
	*arg_type = ARG_PTR_TO_MEM | MEM_FIXED_SIZE | MEM_WRITE |
		    (*arg_type & (PTR_MAYBE_NULL | MEM_UNINIT));

	return 0;
}

static void btf_member_path_str(const struct btf *btf, const struct btf_member_path *path,
				char *buf, size_t buf_sz)
{
	size_t len = 0;
	int i;

	buf[0] = '\0';
	for (i = 0; i < path->depth; i++) {
		const char *name = btf_name_by_offset(btf, path->member[i]->name_off);

		/* An anonymous struct or union has no name to spell. */
		if (!name || !name[0])
			continue;
		len += scnprintf(buf + len, buf_sz - len, "%s%s", len ? "." : "", name);
		if (path->in_array[i])
			len += scnprintf(buf + len, buf_sz - len, "[]");
	}
}

enum special_kfunc_type {
	KF_bpf_obj_new_impl,
	KF_bpf_obj_new,
	KF_bpf_obj_drop_impl,
	KF_bpf_obj_drop,
	KF_bpf_refcount_acquire_impl,
	KF_bpf_refcount_acquire,
	KF_bpf_list_push_front_impl,
	KF_bpf_list_push_front,
	KF_bpf_list_push_back_impl,
	KF_bpf_list_push_back,
	KF_bpf_list_add,
	KF_bpf_list_pop_front,
	KF_bpf_list_pop_back,
	KF_bpf_list_del,
	KF_bpf_list_front,
	KF_bpf_list_back,
	KF_bpf_list_is_first,
	KF_bpf_list_is_last,
	KF_bpf_list_empty,
	KF_bpf_cast_to_kern_ctx,
	KF_bpf_rdonly_cast,
	KF_bpf_rcu_read_lock,
	KF_bpf_rcu_read_unlock,
	KF_bpf_rbtree_remove,
	KF_bpf_rbtree_add_impl,
	KF_bpf_rbtree_add,
	KF_bpf_rbtree_first,
	KF_bpf_rbtree_root,
	KF_bpf_rbtree_left,
	KF_bpf_rbtree_right,
	KF_bpf_dynptr_from_skb,
	KF_bpf_dynptr_from_xdp,
	KF_bpf_dynptr_from_skb_meta,
	KF_bpf_xdp_pull_data,
	KF_bpf_dynptr_slice,
	KF_bpf_dynptr_slice_rdwr,
	KF_bpf_dynptr_clone,
	KF_bpf_percpu_obj_new_impl,
	KF_bpf_percpu_obj_new,
	KF_bpf_percpu_obj_drop_impl,
	KF_bpf_percpu_obj_drop,
	KF_bpf_throw,
	KF_bpf_wq_set_callback,
	KF_bpf_preempt_disable,
	KF_bpf_preempt_enable,
	KF_bpf_iter_css_task_new,
	KF_bpf_session_cookie,
	KF_bpf_get_kmem_cache,
	KF_bpf_local_irq_save,
	KF_bpf_local_irq_restore,
	KF_bpf_iter_num_new,
	KF_bpf_iter_num_next,
	KF_bpf_iter_num_destroy,
	KF_bpf_set_dentry_xattr,
	KF_bpf_remove_dentry_xattr,
	KF_bpf_res_spin_lock,
	KF_bpf_res_spin_unlock,
	KF_bpf_res_spin_lock_irqsave,
	KF_bpf_res_spin_unlock_irqrestore,
	KF_bpf_dynptr_from_file,
	KF_bpf_dynptr_file_discard,
	KF___bpf_trap,
	KF_bpf_task_work_schedule_signal,
	KF_bpf_task_work_schedule_resume,
	KF_bpf_call_rcu,
	KF_bpf_call_rcu_tasks_trace,
	KF_bpf_arena_alloc_pages,
	KF_bpf_arena_free_pages,
	KF_bpf_session_is_return,
};

BTF_ID_LIST(special_kfunc_list)
BTF_ID(func, bpf_obj_new_impl)
BTF_ID(func, bpf_obj_new)
BTF_ID(func, bpf_obj_drop_impl)
BTF_ID(func, bpf_obj_drop)
BTF_ID(func, bpf_refcount_acquire_impl)
BTF_ID(func, bpf_refcount_acquire)
BTF_ID(func, bpf_list_push_front_impl)
BTF_ID(func, bpf_list_push_front)
BTF_ID(func, bpf_list_push_back_impl)
BTF_ID(func, bpf_list_push_back)
BTF_ID(func, bpf_list_add)
BTF_ID(func, bpf_list_pop_front)
BTF_ID(func, bpf_list_pop_back)
BTF_ID(func, bpf_list_del)
BTF_ID(func, bpf_list_front)
BTF_ID(func, bpf_list_back)
BTF_ID(func, bpf_list_is_first)
BTF_ID(func, bpf_list_is_last)
BTF_ID(func, bpf_list_empty)
BTF_ID(func, bpf_cast_to_kern_ctx)
BTF_ID(func, bpf_rdonly_cast)
BTF_ID(func, bpf_rcu_read_lock)
BTF_ID(func, bpf_rcu_read_unlock)
BTF_ID(func, bpf_rbtree_remove)
BTF_ID(func, bpf_rbtree_add_impl)
BTF_ID(func, bpf_rbtree_add)
BTF_ID(func, bpf_rbtree_first)
BTF_ID(func, bpf_rbtree_root)
BTF_ID(func, bpf_rbtree_left)
BTF_ID(func, bpf_rbtree_right)
#ifdef CONFIG_NET
BTF_ID(func, bpf_dynptr_from_skb)
BTF_ID(func, bpf_dynptr_from_xdp)
BTF_ID(func, bpf_dynptr_from_skb_meta)
BTF_ID(func, bpf_xdp_pull_data)
#else
BTF_ID_UNUSED
BTF_ID_UNUSED
BTF_ID_UNUSED
BTF_ID_UNUSED
#endif
BTF_ID(func, bpf_dynptr_slice)
BTF_ID(func, bpf_dynptr_slice_rdwr)
BTF_ID(func, bpf_dynptr_clone)
BTF_ID(func, bpf_percpu_obj_new_impl)
BTF_ID(func, bpf_percpu_obj_new)
BTF_ID(func, bpf_percpu_obj_drop_impl)
BTF_ID(func, bpf_percpu_obj_drop)
BTF_ID(func, bpf_throw)
BTF_ID(func, bpf_wq_set_callback)
BTF_ID(func, bpf_preempt_disable)
BTF_ID(func, bpf_preempt_enable)
#ifdef CONFIG_CGROUPS
BTF_ID(func, bpf_iter_css_task_new)
#else
BTF_ID_UNUSED
#endif
#ifdef CONFIG_BPF_EVENTS
BTF_ID(func, bpf_session_cookie)
#else
BTF_ID_UNUSED
#endif
BTF_ID(func, bpf_get_kmem_cache)
BTF_ID(func, bpf_local_irq_save)
BTF_ID(func, bpf_local_irq_restore)
BTF_ID(func, bpf_iter_num_new)
BTF_ID(func, bpf_iter_num_next)
BTF_ID(func, bpf_iter_num_destroy)
#ifdef CONFIG_BPF_LSM
BTF_ID(func, bpf_set_dentry_xattr)
BTF_ID(func, bpf_remove_dentry_xattr)
#else
BTF_ID_UNUSED
BTF_ID_UNUSED
#endif
BTF_ID(func, bpf_res_spin_lock)
BTF_ID(func, bpf_res_spin_unlock)
BTF_ID(func, bpf_res_spin_lock_irqsave)
BTF_ID(func, bpf_res_spin_unlock_irqrestore)
BTF_ID(func, bpf_dynptr_from_file)
BTF_ID(func, bpf_dynptr_file_discard)
BTF_ID(func, __bpf_trap)
BTF_ID(func, bpf_task_work_schedule_signal)
BTF_ID(func, bpf_task_work_schedule_resume)
BTF_ID(func, bpf_call_rcu)
BTF_ID(func, bpf_call_rcu_tasks_trace)
#if defined(CONFIG_MMU) && defined(CONFIG_64BIT)
BTF_ID(func, bpf_arena_alloc_pages)
BTF_ID(func, bpf_arena_free_pages)
#else
BTF_ID_UNUSED
BTF_ID_UNUSED
#endif
#ifdef CONFIG_BPF_EVENTS
BTF_ID(func, bpf_session_is_return)
#else
BTF_ID_UNUSED
#endif

static bool is_bpf_cast_to_kern_ctx_kfunc(const struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_cast_to_kern_ctx]);
}

static bool is_bpf_dynptr_clone_kfunc(const struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_clone]);
}

static bool is_bpf_iter_css_task_new_kfunc(const struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_iter_css_task_new]);
}

static bool is_bpf_obj_new_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_obj_new] ||
	       func_id == special_kfunc_list[KF_bpf_obj_new_impl];
}

static bool is_bpf_percpu_obj_new_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_percpu_obj_new] ||
	       func_id == special_kfunc_list[KF_bpf_percpu_obj_new_impl];
}

static bool is_bpf_obj_drop_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_obj_drop] ||
	       func_id == special_kfunc_list[KF_bpf_obj_drop_impl];
}

static bool is_bpf_percpu_obj_drop_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_percpu_obj_drop] ||
	       func_id == special_kfunc_list[KF_bpf_percpu_obj_drop_impl];
}

static bool is_bpf_refcount_acquire_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_refcount_acquire] ||
	       func_id == special_kfunc_list[KF_bpf_refcount_acquire_impl];
}

static bool is_bpf_list_push_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_list_push_front] ||
	       func_id == special_kfunc_list[KF_bpf_list_push_front_impl] ||
	       func_id == special_kfunc_list[KF_bpf_list_push_back] ||
	       func_id == special_kfunc_list[KF_bpf_list_push_back_impl] ||
	       func_id == special_kfunc_list[KF_bpf_list_add];
}

static bool is_bpf_rbtree_add_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_rbtree_add] ||
	       func_id == special_kfunc_list[KF_bpf_rbtree_add_impl];
}

static bool is_call_rcu_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_call_rcu] ||
	       func_id == special_kfunc_list[KF_bpf_call_rcu_tasks_trace];
}

static bool is_task_work_add_kfunc(u32 func_id)
{
	return func_id == special_kfunc_list[KF_bpf_task_work_schedule_signal] ||
	       func_id == special_kfunc_list[KF_bpf_task_work_schedule_resume];
}

static bool is_kfunc_ret_null(struct bpf_call_arg_meta *meta)
{
	if (is_bpf_refcount_acquire_kfunc(meta->func_id) && meta->arg_owning_ref)
		return false;

	return meta->kfunc_flags & KF_RET_NULL;
}

static bool is_kfunc_bpf_rcu_read_lock(struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_rcu_read_lock]);
}

static bool is_kfunc_bpf_rcu_read_unlock(struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_rcu_read_unlock]);
}

static bool is_kfunc_bpf_preempt_disable(struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_preempt_disable]);
}

static bool is_kfunc_bpf_preempt_enable(struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_preempt_enable]);
}

/* These write to what their first argument, a dynptr, points to */
BTF_SET_START(dynptr_write_kfuncs)
BTF_ID(func, bpf_dynptr_copy)
BTF_ID(func, bpf_dynptr_memset)
#ifdef CONFIG_BPF_EVENTS
BTF_ID(func, bpf_probe_read_user_dynptr)
BTF_ID(func, bpf_probe_read_kernel_dynptr)
BTF_ID(func, bpf_probe_read_user_str_dynptr)
BTF_ID(func, bpf_probe_read_kernel_str_dynptr)
BTF_ID(func, bpf_copy_from_user_dynptr)
BTF_ID(func, bpf_copy_from_user_str_dynptr)
BTF_ID(func, bpf_copy_from_user_task_dynptr)
BTF_ID(func, bpf_copy_from_user_task_str_dynptr)
#endif
BTF_SET_END(dynptr_write_kfuncs)

static bool is_kfunc_dynptr_write(struct bpf_call_arg_meta *meta)
{
	return meta->btf == btf_vmlinux &&
	       btf_id_set_contains(&dynptr_write_kfuncs, meta->func_id);
}

/*
 * A write through the dynptr of an skb may reallocate its head. Before the
 * arguments are checked nobody knows what kind of dynptr it is.
 */
bool bpf_is_kfunc_pkt_changing(struct bpf_call_arg_meta *meta)
{
	return is_kfunc_call(meta, special_kfunc_list[KF_bpf_xdp_pull_data]) ||
	       is_kfunc_dynptr_write(meta);
}

static u32 kfunc_abi_slots(const struct btf_func_model *fm)
{
	const struct bpf_jit_arg_abi *abi = bpf_jit_arg_abi();
	u8 pos_of_slot[MAX_BPF_FUNC_ARG_SLOTS];
	u32 i, nslots, slots = 0;

	for (i = 0; i < fm->nr_args; i++)
		slots += btf_func_model_arg_slots(fm, i);

	if (!abi)
		return slots;

	nslots = bpf_jit_place_args(abi, fm, pos_of_slot);
	for (i = 0; i < nslots; i++)
		if (pos_of_slot[i] + 1 > slots)
			slots = pos_of_slot[i] + 1;

	return slots;
}

static u32 __btf_func_arg_align(const struct btf *btf, const struct btf_type *t, int rec)
{
	const struct btf_member *member;
	const struct btf_type *mt;
	u32 align, i;

	while (btf_type_is_array(t))
		t = btf_type_skip_modifiers(btf, btf_array(t)->type, NULL);

	if (btf_type_is_int(t))
		return t->size > BPF_REG_SIZE ? t->size : BPF_REG_SIZE;
	if (!btf_type_is_struct(t))
		return BPF_REG_SIZE;
	if (rec >= BTF_MEMBER_MAX_DEPTH)
		return 0;

	for_each_member(i, t, member) {
		mt = btf_type_skip_modifiers(btf, member->type, NULL);
		align = __btf_func_arg_align(btf, mt, rec + 1);
		if (!align)
			return 0;
		if (align > BPF_REG_SIZE)
			return 2 * BPF_REG_SIZE;
	}
	return BPF_REG_SIZE;
}

u32 btf_func_arg_align(const struct btf *btf, const struct btf_type *t)
{
	return __btf_func_arg_align(btf, t, 0);
}

static int
get_kfunc_arg_type(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
		   const struct btf_param *args, int arg, int nargs, u32 slot,
		   struct bpf_func_proto *proto)
{
	const struct btf_type *t, *ref_t = NULL, *resolve_ret;
	const u32 *ref_id_ptr = NULL;
	argno_t argno = argno_from_arg(slot + 1);
	const char *ref_tname = NULL;
	u32 ref_id, type_size;
	int arg_type;

	proto->arg_btf_id[arg] = NULL;

	if (is_kfunc_arg_prog_aux(meta->btf, &args[arg]))
		return ARG_PTR_TO_PROG_AUX;

	if (is_kfunc_arg_ignore(meta->btf, &args[arg]) || is_kfunc_arg_implicit(meta, arg))
		return ARG_IGNORE;

	t = btf_type_skip_modifiers(meta->btf, args[arg].type, NULL);

	/* Scalar arguments are classified from their BTF suffix/name alone. */
	if (btf_type_is_scalar(t)) {
		if (is_kfunc_arg_constant(meta->btf, &args[arg]))
			return ARG_CONST_SCALAR;
		if (is_kfunc_arg_const_mem_size(meta->btf, &args[arg]))
			return ARG_CONST_MEM_SIZE;
		if (is_kfunc_arg_mem_size(meta->btf, &args[arg]))
			return ARG_MEM_SIZE;
		if (is_kfunc_arg_scalar_with_name(meta->btf, &args[arg], "rdonly_buf_size") ||
		    is_kfunc_arg_scalar_with_name(meta->btf, &args[arg], "rdwr_buf_size"))
			return ARG_CONST_ALLOC_SIZE_OR_ZERO;
		return ARG_SCALAR;
	}

	if (btf_type_is_struct(t)) {
		if (!t->size || t->size > 2 * BPF_REG_SIZE) {
			verbose(env,
				"%s type %s has size %u, only 1 to %d bytes "
				"can be passed by value\n",
				reg_arg_name(env, argno), btf_type_str(t), t->size,
				2 * BPF_REG_SIZE);
			return -EINVAL;
		}
		if (!btf_type_is_scalar_struct(env, meta->btf, t)) {
			verbose(env, "%s type %s is not composed of scalars\n",
				reg_arg_name(env, argno), btf_type_str(t));
			return -EINVAL;
		}
		return ARG_SCALAR;
	}

	if (!btf_type_is_ptr(t)) {
		verbose(env, "Unrecognized %s type %s\n",
			reg_arg_name(env, argno), btf_type_str(t));
		return -EINVAL;
	}
	/* Keep a pointer to the BTF field containing the resolved referent ID. */
	ref_id_ptr = &t->type;
	ref_t = btf_type_skip_modifiers(meta->btf, *ref_id_ptr, &ref_id);
	while (*ref_id_ptr != ref_id)
		ref_id_ptr = &btf_type_by_id(meta->btf, *ref_id_ptr)->type;
	ref_tname = btf_name_by_offset(meta->btf, ref_t->name_off);

	/* In this function, we verify the kfunc's BTF as per the argument type,
	 * leaving the rest of the verification with respect to the register
	 * type to our caller. When a set of conditions hold in the BTF type of
	 * arguments, we resolve it to a known bpf_arg_type.
	 */
	if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_cast_to_kern_ctx]) ||
	    is_kfunc_call(meta, special_kfunc_list[KF_bpf_session_is_return]) ||
	    is_kfunc_call(meta, special_kfunc_list[KF_bpf_session_cookie]))
		arg_type = ARG_PTR_TO_CTX;
	else if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), arg))
		arg_type = ARG_PTR_TO_CTX;
	else if (is_kfunc_arg_alloc_obj(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_ALLOC_BTF_ID;
	else if (is_kfunc_arg_refcounted_kptr(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_REFCOUNTED_KPTR;
	else if (is_kfunc_arg_dynptr(meta->btf, &args[arg])) {
		arg_type = ARG_PTR_TO_DYNPTR;

		if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_from_skb]))
			arg_type |= DYNPTR_TYPE_SKB;
		else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_from_xdp]))
			arg_type |= DYNPTR_TYPE_XDP;
		else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_from_skb_meta]))
			arg_type |= DYNPTR_TYPE_SKB_META;
		else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_from_file]) ||
			 is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_file_discard]))
			/* OBJ_RELEASE for the latter comes from KF_RELEASE below */
			arg_type |= DYNPTR_TYPE_FILE;
	} else if (is_kfunc_arg_iter(meta, arg, &args[arg]))
		arg_type = ARG_PTR_TO_ITER;
	else if (is_kfunc_arg_list_head(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_LIST_HEAD;
	else if (is_kfunc_arg_list_node(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_LIST_NODE;
	else if (is_kfunc_arg_rbtree_root(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_RB_ROOT;
	else if (is_kfunc_arg_rbtree_node(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_RB_NODE;
	else if (is_kfunc_arg_const_str(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_CONST_STR;
	else if (is_kfunc_arg_const_map(meta->btf, &args[arg]))
		arg_type = ARG_CONST_MAP_PTR;
	else if (is_kfunc_arg_map(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_BTF_ID;
	else if (is_kfunc_arg_wq(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_WORKQUEUE;
	else if (is_kfunc_arg_timer(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_TIMER;
	else if (is_kfunc_arg_task_work(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_TASK_WORK;
	else if (is_kfunc_arg_rcu_head(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_RCU_HEAD;
	else if (is_kfunc_arg_irq_flag(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_IRQ_FLAG;
	else if (is_kfunc_arg_res_spin_lock(meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_RES_SPIN_LOCK;
	else if (is_kfunc_arg_ctx_out(meta->btf, &args[arg])) {
		if (!btf_type_is_scalar(ref_t)) {
			verbose(env, "%s __ctx_out argument must point to a scalar\n",
				reg_arg_name(env, argno));
			return -EINVAL;
		}
		resolve_ret = btf_resolve_size(meta->btf, ref_t, &type_size);
		if (IS_ERR(resolve_ret)) {
			verbose(env,
				"%s reference type('%s %s') size cannot be determined: %ld\n",
				reg_arg_name(env, argno), btf_type_str(ref_t),
				ref_tname, PTR_ERR(resolve_ret));
			return -EINVAL;
		}
		proto->arg_size[arg] = type_size;
		arg_type = ARG_PTR_TO_CTX_OUT | MEM_FIXED_SIZE;
	} else if (is_kfunc_arg_callback(env, meta->btf, &args[arg]))
		arg_type = ARG_PTR_TO_FUNC;
	else if (is_kfunc_arg_arena(meta->btf, &args[arg])) {
		if (!bpf_jit_supports_arena_args()) {
			verbose(env, "JIT does not support kfunc %s() with arena pointer arguments\n",
				meta->func_name);
			return -ENOTSUPP;
		}
		if (!env->prog->aux->arena) {
			verbose(env,
				"%s arena pointer requires a program with an associated arena\n",
				reg_arg_name(env, argno));
			return -EINVAL;
		}
		if (reg_from_argno(argno) < 0) {
			verbose(env, "%s arena pointer cannot be a stack argument\n",
				reg_arg_name(env, argno));
			return -EINVAL;
		}
		/*
		 * Both suffixes accept a constant zero. The function model determines
		 * whether the JIT rebases it to the arena base or preserves NULL.
		 * The common nullable path below records that verifier property.
		 */
		arg_type = ARG_PTR_TO_ARENA;
	} else if (arg + 1 < nargs &&
		 (is_kfunc_arg_mem_size(meta->btf, &args[arg + 1]) ||
		  is_kfunc_arg_const_mem_size(meta->btf, &args[arg + 1]))) {
		if (!btf_type_is_void(ref_t) && !btf_type_is_scalar(ref_t) &&
		    !btf_type_is_scalar_struct(env, meta->btf, ref_t)) {
			verbose(env, "%s pointer type %s %s must point to void, scalar, or struct with scalar\n",
				reg_arg_name(env, argno), btf_type_str(ref_t), ref_tname);
			return -EINVAL;
		}
		arg_type = ARG_PTR_TO_MEM | MEM_WRITE;
	} else if (btf_type_is_struct(ref_t))
		/* A pointer to a struct without a size argument is classified as ARG_PTR_TO_BTF_ID */
		arg_type = ARG_PTR_TO_BTF_ID;
	else {
		/*
		 * Otherwise this is a fixed-size memory buffer supported by
		 * check_helper_mem_access(): a pointer to a scalar or a struct of
		 * scalars. The access size is derived from the pointed-to BTF type.
		 */
		if (!btf_type_is_scalar(ref_t) &&
		    !btf_type_is_scalar_struct(env, meta->btf, ref_t)) {
			verbose(env, "%s pointer type %s %s must point to scalar, or struct with scalar\n",
				reg_arg_name(env, argno), btf_type_str(ref_t), ref_tname);
			return -EINVAL;
		}
		resolve_ret = btf_resolve_size(meta->btf, ref_t, &type_size);
		if (IS_ERR(resolve_ret)) {
			verbose(env,
				"%s reference type('%s %s') size cannot be determined: %ld\n",
				reg_arg_name(env, argno), btf_type_str(ref_t),
				ref_tname, PTR_ERR(resolve_ret));
			return -EINVAL;
		}
		proto->arg_size[arg] = type_size;
		arg_type = ARG_PTR_TO_MEM | MEM_FIXED_SIZE | MEM_WRITE;
	}

	if (is_kfunc_arg_uninit(meta->btf, &args[arg]))
		arg_type |= MEM_UNINIT;

	if (is_kfunc_arg_nullable(meta->btf, &args[arg]))
		arg_type |= PTR_MAYBE_NULL;

	/*
	 * Only the first argument of a KF_RELEASE kfunc releases anything, and
	 * bpf_fetch_kfunc_arg_meta() only ever records BPF_REG_1 for it.
	 */
	if (is_kfunc_release(meta) && arg == 0)
		arg_type |= OBJ_RELEASE;

	if (base_type(arg_type) == ARG_PTR_TO_BTF_ID) {
		if (is_kfunc_arg_map(meta->btf, &args[arg]))
			proto->arg_btf_id[arg] = reg2btf_ids[CONST_PTR_TO_MAP];
		else
			proto->arg_btf_id[arg] = ref_id_ptr;

		arg_type |= PTR_TRUSTED;

		/*
		 * A KF_RCU kfunc accepts an RCU-protected pointer where it would
		 * otherwise demand a referenced or trusted one. Other argument kinds
		 * have their own provenance requirements and must not inherit MEM_RCU.
		 */
		if (is_kfunc_rcu(meta))
			arg_type |= MEM_RCU;
	}

	return arg_type;
}

static int gen_kfunc_arg_proto(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
			       const struct btf_func_model *fm, struct bpf_func_proto *proto)
{
	const struct bpf_jit_arg_abi *abi;
	const struct btf *btf = meta->btf;
	const struct btf_param *args;
	const struct btf_type *t;
	u32 i, nargs, slots_used;
	int arg_type;

	args = (const struct btf_param *)(meta->func_proto + 1);
	nargs = btf_type_vlen(meta->func_proto);
	if (nargs > MAX_BPF_FUNC_ARGS) {
		verbose(env, "Function %s has %d > %d args\n", meta->func_name,
			nargs, MAX_BPF_FUNC_ARGS);
		return -EINVAL;
	}

	for (i = 0, slots_used = 0; i < nargs; i++) {
		u32 nslots = btf_func_model_arg_slots(fm, i);

		if (nslots > 1) {
			t = btf_type_skip_modifiers(btf, args[i].type, NULL);
			if (!btf_func_arg_align(btf, t)) {
				verbose(env,
					"Function %s arg#%d type %s nests structs more than "
					"%d levels deep\n",
					meta->func_name, i, btf_type_str(t),
					BTF_MEMBER_MAX_DEPTH);
				return -EINVAL;
			}
		}
		slots_used += nslots;
	}

	if (slots_used > MAX_BPF_FUNC_ARGS) {
		verbose(env, "Function %s needs %d > %d argument slots\n", meta->func_name,
			slots_used, MAX_BPF_FUNC_ARGS);
		return -EINVAL;
	}

	abi = bpf_jit_arg_abi();

	for (i = 0, slots_used = 0; i < nargs; i++) {
		u32 nslots = btf_func_model_arg_slots(fm, i);

		if (!abi && nslots > 1) {
			t = btf_type_skip_modifiers(btf, args[i].type, NULL);
			verbose(env,
				"Function %s arg#%d type %s cannot be passed at "
				"argument slot %d on this architecture\n",
				meta->func_name, i, btf_type_str(t), slots_used);
			return -EINVAL;
		}
		slots_used += nslots;

		arg_type = get_kfunc_arg_type(env, meta, args, i, nargs,
					      slots_used - nslots, proto);
		if (arg_type < 0)
			return arg_type;

		proto->arg_type[i] = arg_type;
	}

	if (slots_used > MAX_BPF_FUNC_REG_ARGS && !bpf_jit_supports_stack_args()) {
		verbose(env, "JIT does not support kfunc %s() with %d argument slots\n",
			meta->func_name, slots_used);
		return -ENOTSUPP;
	}

	return check_arg_prog_aux(env, proto) ? 0 : -EINVAL;
}

static int process_arg_ptr_to_btf_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
				     argno_t argno, enum bpf_arg_type arg_type,
				     const struct btf *arg_btf, u32 arg_btf_id,
				     struct bpf_call_arg_meta *meta, int insn_idx)
{
	bool taking_projection, struct_same, strict_type_match = false;
	const struct btf_type *arg_t, *reg_t;
	const char *arg_tname, *reg_tname;
	const struct btf *reg_btf;
	u32 reg_btf_id;

	if (base_type(reg->type) == PTR_TO_BTF_ID) {
		reg_btf = reg->btf;
		reg_btf_id = reg->btf_id;
	} else {
		reg_btf = btf_vmlinux;
		reg_btf_id = *reg2btf_ids[base_type(reg->type)];
	}

	/*
	 * Enforce strict type matching for arguments that release a reference,
	 * or are no-cast aliases. We do _not_ enforce strict matching by default,
	 * as we want to enable BPF programs to pass types that are bitwise
	 * equivalent without forcing them to explicitly cast with something
	 * like bpf_cast_to_kern_ctx().
	 *
	 * For example, say we had a type like the following:
	 *
	 * struct bpf_cpumask {
	 *	cpumask_t cpumask;
	 *	refcount_t usage;
	 * };
	 *
	 * Note that as specified in <linux/cpumask.h>, cpumask_t is typedef'ed
	 * to a struct cpumask, so it would be safe to pass a struct
	 * bpf_cpumask * to a kfunc expecting a struct cpumask *.
	 *
	 * The philosophy here is similar to how we allow scalars of different
	 * types to be passed to kfuncs as long as the size is the same. The
	 * only difference here is that we're simply allowing
	 * btf_struct_ids_match() to walk the struct at the 0th offset, and
	 * resolve types.
	 */
	if ((arg_type_is_release(arg_type) && !is_helper_call(meta, BPF_FUNC_sk_release)) ||
	    (is_kfunc(meta) && btf_type_ids_nocast_alias(&env->log, reg_btf, reg_btf_id,
						    arg_btf, arg_btf_id)))
		strict_type_match = true;

	arg_t = btf_type_skip_modifiers(arg_btf, arg_btf_id, &arg_btf_id);
	arg_tname = btf_name_by_offset(arg_btf, arg_t->name_off);
	reg_t = btf_type_skip_modifiers(reg_btf, reg_btf_id, &reg_btf_id);
	reg_tname = btf_name_by_offset(reg_btf, reg_t->name_off);

	struct_same = btf_struct_ids_match(&env->log, reg_btf, reg_btf_id,
					  reg->var_off.value, arg_btf, arg_btf_id,
					  strict_type_match, !type_is_alloc(reg->type));

	/* If kfunc is accepting a projection type (ie. __sk_buff), it cannot
	 * actually use it -- it must cast to the underlying type. So we allow
	 * caller to pass in the underlying type.
	 */
	taking_projection = is_kfunc(meta) && btf_is_projection_of(arg_tname, reg_tname);
	if (!taking_projection && !struct_same) {
		verbose(env, "%s %s expected pointer to %s %s but %s has a pointer to %s %s\n",
			meta->func_name, reg_arg_name(env, argno),
			btf_type_str(arg_t), arg_tname,
			reg_arg_name(env, argno), btf_type_str(reg_t), reg_tname);
		return -EINVAL;
	}
	return 0;
}

static int process_irq_flag(struct bpf_verifier_env *env, struct bpf_reg_state *reg, argno_t argno,
			     struct bpf_call_arg_meta *meta)
{
	int err, spi, kfunc_class = IRQ_NATIVE_KFUNC;
	bool irq_save;

	if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_local_irq_save]) ||
	    is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) {
		irq_save = true;
		if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_lock_irqsave]))
			kfunc_class = IRQ_LOCK_KFUNC;
	} else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_local_irq_restore]) ||
		   is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore])) {
		irq_save = false;
		if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]))
			kfunc_class = IRQ_LOCK_KFUNC;
	} else {
		verifier_bug(env, "unknown irq flags kfunc");
		return -EFAULT;
	}

	if (irq_save) {
		if (!is_irq_flag_reg_valid_uninit(env, reg)) {
			verbose(env, "expected uninitialized irq flag as %s\n",
				reg_arg_name(env, argno));
			bpf_diag_res(env, env->insn_idx, "IRQ flag is already initialized",
				     "Saving IRQ state requires an uninitialized stack slot for "
				     "the IRQ flag, but this slot already contains tracked IRQ "
				     "flag state.",
				     "Use a fresh stack slot for this save operation, or restore "
				     "the existing IRQ flag before reusing the slot.");
			return -EINVAL;
		}

		err = check_mem_access(env, env->insn_idx, reg, argno, 0, BPF_DW,
				       BPF_WRITE, -1, false, false);
		if (err)
			return err;

		err = mark_stack_slot_irq_flag(env, meta, reg, env->insn_idx, kfunc_class);
		if (err)
			return err;
	} else {
		err = is_irq_flag_reg_valid_init(env, reg);
		if (err) {
			verbose(env, "expected an initialized irq flag as %s\n",
				reg_arg_name(env, argno));
			bpf_diag_res(env, env->insn_idx, "uninitialized IRQ flag restore",
				     "Restoring IRQ state requires a stack slot that was "
				     "initialized by a matching IRQ save operation on this path.",
				     "Pass the same stack slot that was previously initialized by "
				     "the matching IRQ save kfunc.");
			return err;
		}

		spi = irq_flag_get_spi(env, reg);
		if (spi < 0)
			return spi;

		mark_stack_slots_scratched(env, spi, 1);

		err = unmark_stack_slot_irq_flag(env, reg, kfunc_class);
		if (err)
			return err;

		if (!in_rcu_cs(env))
			invalidate_rcu_protected_refs(env);
	}
	return 0;
}

static int ref_set_non_owning(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct btf_record *rec = reg_btf_record(reg);

	if (!env->cur_state->active_locks) {
		verifier_bug(env, "%s w/o active lock", __func__);
		return -EFAULT;
	}

	if (type_flag(reg->type) & NON_OWN_REF) {
		verifier_bug(env, "NON_OWN_REF already set");
		return -EFAULT;
	}

	reg->type |= NON_OWN_REF;
	if (rec->refcount_off >= 0)
		reg->type |= MEM_RCU;

	return 0;
}

static void ref_convert_owning_non_owning(struct bpf_verifier_env *env, u32 id)
{
	struct bpf_func_state *unused;
	struct bpf_reg_state *reg;
	int err;

	err = release_reference_nomark(env, id);
	WARN_ON_ONCE(err);

	bpf_for_each_reg_in_vstate(env->cur_state, unused, reg, ({
		if (reg->id == id) {
			reg->id = 0;
			ref_set_non_owning(env, reg);
		}
	}));

	return;
}

/* Implementation details:
 *
 * Each register points to some region of memory, which we define as an
 * allocation. Each allocation may embed a bpf_spin_lock which protects any
 * special BPF objects (bpf_list_head, bpf_rb_root, etc.) part of the same
 * allocation. The lock and the data it protects are colocated in the same
 * memory region.
 *
 * Hence, everytime a register holds a pointer value pointing to such
 * allocation, the verifier preserves a unique reg->id for it.
 *
 * The verifier remembers the lock 'ptr' and the lock 'id' whenever
 * bpf_spin_lock is called.
 *
 * To enable this, lock state in the verifier captures two values:
 *	active_lock.ptr = Register's type specific pointer
 *	active_lock.id  = A unique ID for each register pointer value
 *
 * Currently, PTR_TO_MAP_VALUE and PTR_TO_BTF_ID | MEM_ALLOC are the two
 * supported register types.
 *
 * The active_lock.ptr in case of map values is the reg->map_ptr, and in case of
 * allocated objects is the reg->btf pointer.
 *
 * The active_lock.id is non-unique for maps supporting direct_value_addr, as we
 * can establish the provenance of the map value statically for each distinct
 * lookup into such maps. They always contain a single map value hence unique
 * IDs for each pseudo load pessimizes the algorithm and rejects valid programs.
 *
 * So, in case of global variables, they use array maps with max_entries = 1,
 * hence their active_lock.ptr becomes map_ptr and id = 0 (since they all point
 * into the same map value as max_entries is 1, as described above).
 *
 * In case of inner map lookups, the inner map pointer has same map_ptr as the
 * outer map pointer (in verifier context), but each lookup into an inner map
 * assigns a fresh reg->id to the lookup, so while lookups into distinct inner
 * maps from the same outer map share the same map_ptr as active_lock.ptr, they
 * will get different reg->id assigned to each lookup, hence different
 * active_lock.id.
 *
 * In case of allocated objects, active_lock.ptr is the reg->btf, and the
 * reg->id is a unique ID preserved after the NULL pointer check on the pointer
 * returned from bpf_obj_new. Each allocation receives a new reg->id.
 */
static int check_reg_allocation_locked(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
{
	struct bpf_reference_state *s;
	void *ptr;
	u32 id;

	switch ((int)reg->type) {
	case PTR_TO_MAP_VALUE:
		ptr = reg->map_ptr;
		break;
	case PTR_TO_BTF_ID | MEM_ALLOC:
		ptr = reg->btf;
		break;
	default:
		verifier_bug(env, "unknown reg type for lock check");
		return -EFAULT;
	}
	id = reg->id;

	if (!env->cur_state->active_locks)
		return -EINVAL;
	s = find_lock_state(env->cur_state, REF_TYPE_LOCK_MASK, id, ptr);
	if (!s) {
		verbose(env, "held lock and object are not in the same allocation\n");
		return -EINVAL;
	}
	return 0;
}

static bool is_bpf_list_api_kfunc(u32 btf_id)
{
	return is_bpf_list_push_kfunc(btf_id) ||
	       btf_id == special_kfunc_list[KF_bpf_list_pop_front] ||
	       btf_id == special_kfunc_list[KF_bpf_list_pop_back] ||
	       btf_id == special_kfunc_list[KF_bpf_list_del] ||
	       btf_id == special_kfunc_list[KF_bpf_list_front] ||
	       btf_id == special_kfunc_list[KF_bpf_list_back] ||
	       btf_id == special_kfunc_list[KF_bpf_list_is_first] ||
	       btf_id == special_kfunc_list[KF_bpf_list_is_last] ||
	       btf_id == special_kfunc_list[KF_bpf_list_empty];
}

static bool is_bpf_rbtree_api_kfunc(u32 btf_id)
{
	return is_bpf_rbtree_add_kfunc(btf_id) ||
	       btf_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
	       btf_id == special_kfunc_list[KF_bpf_rbtree_first] ||
	       btf_id == special_kfunc_list[KF_bpf_rbtree_root] ||
	       btf_id == special_kfunc_list[KF_bpf_rbtree_left] ||
	       btf_id == special_kfunc_list[KF_bpf_rbtree_right];
}

static int get_bpf_res_spin_lock_kfunc_flags(const struct bpf_call_arg_meta *meta)
{
	int flags = PROCESS_RES_LOCK;

	if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_lock]) ||
	    is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_lock_irqsave]))
		flags |= PROCESS_SPIN_LOCK;
	else if (!is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_unlock]) &&
		 !is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]))
		return 0;
	if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_lock_irqsave]) ||
	    is_kfunc_call(meta, special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore]))
		flags |= PROCESS_LOCK_IRQ;
	return flags;
}

static bool kfunc_spin_allowed(struct bpf_verifier_env *env, s32 func_id, s16 offset)
{
	struct bpf_kfunc_meta kfunc;
	int err;

	err = fetch_kfunc_meta(env, func_id, offset, &kfunc);
	if (err || !kfunc.flags)
		return false;

	return *kfunc.flags & KF_SPINLOCK_SAFE;
}

/*
 * True if insn calls a helper/kfunc that requires one of its arguments to
 * be a stack pointer with a constant offset.
 */
bool bpf_needs_fixed_stack_off(struct bpf_verifier_env *env, int insn_idx)
{
	const struct bpf_insn *insn = &env->prog->insnsi[insn_idx];
	const struct bpf_func_proto *fn;
	struct bpf_kfunc_desc *desc;
	u32 *flags, btf_id;
	int i;

	if (bpf_helper_call(insn)) {
		if (bpf_get_helper_proto(env, insn->imm, &fn) < 0)
			return false;
	} else if (bpf_pseudo_kfunc_call(insn)) {
		desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
		if (!desc)
			return false;
		fn = &desc->proto;
	} else {
		return false;
	}

	/* Both initialized and uninitialized stack dynptrs need a fixed offset. */
	for (i = 0; i < ARRAY_SIZE(fn->arg_type); i++)
		if (arg_type_is_dynptr(fn->arg_type[i]))
			return true;

	/* vmlinux kfuncs only */
	if (!bpf_pseudo_kfunc_call(insn) || insn->off != 0)
		return false;
	btf_id = insn->imm;

	flags = btf_kfunc_flags(btf_vmlinux, btf_id, env->prog);
	if (flags && (*flags & (KF_ITER_NEW | KF_ITER_NEXT | KF_ITER_DESTROY)))
		return true;

	if (btf_id == special_kfunc_list[KF_bpf_res_spin_lock] ||
	    btf_id == special_kfunc_list[KF_bpf_res_spin_unlock] ||
	    btf_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave] ||
	    btf_id == special_kfunc_list[KF_bpf_res_spin_unlock_irqrestore] ||
	    btf_id == special_kfunc_list[KF_bpf_local_irq_save] ||
	    btf_id == special_kfunc_list[KF_bpf_local_irq_restore])
		return true;

	return false;
}

static bool is_sync_callback_calling_kfunc(u32 btf_id)
{
	return is_bpf_rbtree_add_kfunc(btf_id);
}

static bool is_async_callback_calling_kfunc(u32 btf_id)
{
	return is_bpf_wq_set_callback_kfunc(btf_id) ||
	       is_task_work_add_kfunc(btf_id) ||
	       is_call_rcu_kfunc(btf_id);
}

bool bpf_is_throw_kfunc(struct bpf_insn *insn)
{
	return bpf_pseudo_kfunc_call(insn) && insn->off == 0 &&
	       insn->imm == special_kfunc_list[KF_bpf_throw];
}

static bool is_bpf_wq_set_callback_kfunc(u32 btf_id)
{
	return btf_id == special_kfunc_list[KF_bpf_wq_set_callback];
}

static bool is_callback_calling_kfunc(u32 btf_id)
{
	return is_sync_callback_calling_kfunc(btf_id) ||
	       is_async_callback_calling_kfunc(btf_id);
}

static bool is_rbtree_lock_required_kfunc(u32 btf_id)
{
	return is_bpf_rbtree_api_kfunc(btf_id);
}

static bool check_kfunc_is_graph_root_api(struct bpf_verifier_env *env,
					  enum btf_field_type head_field_type,
					  u32 kfunc_btf_id)
{
	bool ret;

	switch (head_field_type) {
	case BPF_LIST_HEAD:
		ret = is_bpf_list_api_kfunc(kfunc_btf_id);
		break;
	case BPF_RB_ROOT:
		ret = is_bpf_rbtree_api_kfunc(kfunc_btf_id);
		break;
	default:
		verbose(env, "verifier internal error: unexpected graph root argument type %s\n",
			btf_field_type_name(head_field_type));
		return false;
	}

	if (!ret)
		verbose(env, "verifier internal error: %s head arg for unknown kfunc\n",
			btf_field_type_name(head_field_type));
	return ret;
}

static bool check_kfunc_is_graph_node_api(struct bpf_verifier_env *env,
					  enum btf_field_type node_field_type,
					  u32 kfunc_btf_id)
{
	bool ret;

	switch (node_field_type) {
	case BPF_LIST_NODE:
		ret = is_bpf_list_push_kfunc(kfunc_btf_id) ||
		      kfunc_btf_id == special_kfunc_list[KF_bpf_list_del] ||
		      kfunc_btf_id == special_kfunc_list[KF_bpf_list_is_first] ||
		      kfunc_btf_id == special_kfunc_list[KF_bpf_list_is_last];
		break;
	case BPF_RB_NODE:
		ret = (is_bpf_rbtree_add_kfunc(kfunc_btf_id) ||
		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_remove] ||
		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_left] ||
		       kfunc_btf_id == special_kfunc_list[KF_bpf_rbtree_right]);
		break;
	default:
		verbose(env, "verifier internal error: unexpected graph node argument type %s\n",
			btf_field_type_name(node_field_type));
		return false;
	}

	if (!ret)
		verbose(env, "verifier internal error: %s node arg for unknown kfunc\n",
			btf_field_type_name(node_field_type));
	return ret;
}

static int
__process_kf_arg_ptr_to_graph_root(struct bpf_verifier_env *env,
				   struct bpf_reg_state *reg, argno_t argno,
				   struct bpf_call_arg_meta *meta,
				   enum btf_field_type head_field_type,
				   struct btf_field **head_field)
{
	const char *head_type_name;
	struct btf_field *field;
	struct btf_record *rec;
	u32 head_off;

	if (meta->btf != btf_vmlinux) {
		verifier_bug(env, "unexpected btf mismatch in kfunc call");
		return -EFAULT;
	}

	if (!check_kfunc_is_graph_root_api(env, head_field_type, meta->func_id))
		return -EFAULT;

	head_type_name = btf_field_type_name(head_field_type);
	if (!tnum_is_const(reg->var_off)) {
		verbose(env,
			"%s doesn't have constant offset. %s has to be at the constant offset\n",
			reg_arg_name(env, argno), head_type_name);
		return -EINVAL;
	}

	rec = reg_btf_record(reg);
	head_off = reg->var_off.value;
	field = btf_record_find(rec, head_off, head_field_type);
	if (!field) {
		verbose(env, "%s not found at offset=%u\n", head_type_name, head_off);
		return -EINVAL;
	}

	/* All functions require bpf_list_head to be protected using a bpf_spin_lock */
	if (check_reg_allocation_locked(env, reg)) {
		verbose(env, "bpf_spin_lock at off=%d must be held for %s\n",
			rec->spin_lock_off, head_type_name);
		return -EINVAL;
	}

	if (*head_field) {
		verifier_bug(env, "repeating %s arg", head_type_name);
		return -EFAULT;
	}
	*head_field = field;
	return 0;
}

static int process_kf_arg_ptr_to_list_head(struct bpf_verifier_env *env,
					   struct bpf_reg_state *reg, argno_t argno,
					   struct bpf_call_arg_meta *meta)
{
	return __process_kf_arg_ptr_to_graph_root(env, reg, argno, meta, BPF_LIST_HEAD,
							  &meta->arg_list_head.field);
}

static int process_kf_arg_ptr_to_rbtree_root(struct bpf_verifier_env *env,
					     struct bpf_reg_state *reg, argno_t argno,
					     struct bpf_call_arg_meta *meta)
{
	return __process_kf_arg_ptr_to_graph_root(env, reg, argno, meta, BPF_RB_ROOT,
							  &meta->arg_rbtree_root.field);
}

static int
__process_kf_arg_ptr_to_graph_node(struct bpf_verifier_env *env,
				   struct bpf_reg_state *reg, argno_t argno,
				   struct bpf_call_arg_meta *meta,
				   enum btf_field_type head_field_type,
				   enum btf_field_type node_field_type,
				   struct btf_field **node_field)
{
	const char *node_type_name;
	const struct btf_type *et, *t;
	struct btf_field *field;
	u32 node_off;

	if (meta->btf != btf_vmlinux) {
		verifier_bug(env, "unexpected btf mismatch in kfunc call");
		return -EFAULT;
	}

	if (!check_kfunc_is_graph_node_api(env, node_field_type, meta->func_id))
		return -EFAULT;

	node_type_name = btf_field_type_name(node_field_type);
	if (!tnum_is_const(reg->var_off)) {
		verbose(env,
			"%s doesn't have constant offset. %s has to be at the constant offset\n",
			reg_arg_name(env, argno), node_type_name);
		return -EINVAL;
	}

	node_off = reg->var_off.value;
	field = reg_find_field_offset(reg, node_off, node_field_type);
	if (!field) {
		verbose(env, "%s not found at offset=%u\n", node_type_name, node_off);
		return -EINVAL;
	}

	field = *node_field;

	et = btf_type_by_id(field->graph_root.btf, field->graph_root.value_btf_id);
	t = btf_type_by_id(reg->btf, reg->btf_id);
	if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, 0, field->graph_root.btf,
				  field->graph_root.value_btf_id, true,
				  !type_is_alloc(reg->type))) {
		verbose(env, "operation on %s expects arg#1 %s at offset=%d "
			"in struct %s, but arg is at offset=%d in struct %s\n",
			btf_field_type_name(head_field_type),
			btf_field_type_name(node_field_type),
			field->graph_root.node_offset,
			btf_name_by_offset(field->graph_root.btf, et->name_off),
			node_off, btf_name_by_offset(reg->btf, t->name_off));
		return -EINVAL;
	}
	meta->arg_btf = reg->btf;
	meta->arg_btf_id = reg->btf_id;

	if (node_off != field->graph_root.node_offset) {
		verbose(env, "arg#1 offset=%d, but expected %s at offset=%d in struct %s\n",
			node_off, btf_field_type_name(node_field_type),
			field->graph_root.node_offset,
			btf_name_by_offset(field->graph_root.btf, et->name_off));
		return -EINVAL;
	}

	return 0;
}

static int process_kf_arg_ptr_to_list_node(struct bpf_verifier_env *env,
					   struct bpf_reg_state *reg, argno_t argno,
					   struct bpf_call_arg_meta *meta)
{
	return __process_kf_arg_ptr_to_graph_node(env, reg, argno, meta,
						  BPF_LIST_HEAD, BPF_LIST_NODE,
						  &meta->arg_list_head.field);
}

static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env,
					     struct bpf_reg_state *reg, argno_t argno,
					     struct bpf_call_arg_meta *meta)
{
	return __process_kf_arg_ptr_to_graph_node(env, reg, argno, meta,
						  BPF_RB_ROOT, BPF_RB_NODE,
						  &meta->arg_rbtree_root.field);
}

/*
 * css_task iter allowlist is needed to avoid dead locking on css_set_lock.
 * LSM hooks and iters (both sleepable and non-sleepable) are safe.
 * Any sleepable progs are also safe since bpf_check_attach_target() enforce
 * them can only be attached to some specific hook points.
 */
static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env)
{
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);

	switch (prog_type) {
	case BPF_PROG_TYPE_LSM:
		return true;
	case BPF_PROG_TYPE_TRACING:
		if (env->prog->expected_attach_type == BPF_TRACE_ITER)
			return true;
		fallthrough;
	default:
		return in_sleepable(env);
	}
}

int bpf_fetch_kfunc_arg_meta(struct bpf_verifier_env *env,
			     s32 func_id,
			     s16 offset,
			     struct bpf_call_arg_meta *meta)
{
	struct bpf_kfunc_meta kfunc;
	int err;

	memset(meta, 0, sizeof(*meta));

	err = fetch_kfunc_meta(env, func_id, offset, &kfunc);
	if (err)
		return err;

	meta->btf = kfunc.btf;
	meta->func_id = kfunc.id;
	meta->func_proto = kfunc.proto;
	meta->func_name = kfunc.name;

	if (!kfunc.flags || !btf_kfunc_is_allowed(kfunc.btf, kfunc.id, env->prog))
		return -EACCES;

	meta->kfunc_flags = *kfunc.flags;

	/* Only support release referenced argument passed by register */
	if (is_kfunc_release(meta))
		meta->release_regno = BPF_REG_1;

	return 0;
}

/*
 * Describe a helper's stack access through argument @arg (0-based, R1-R5).
 * must_write means the verifier destroys prior state throughout size bytes.
 * In other words, must_write follows the verifier's model of the
 * function's behaviour, which is safe to use for is_state_visited() pruning.
 */
struct arg_access_info
bpf_helper_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn,
			      int arg, int insn_idx)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
	struct arg_access_info info = {
		.size = U32_MAX,
		.may_read = true,
		.may_write = true,
	};
	const struct bpf_func_proto *fn;
	enum bpf_access_type access_type;
	enum bpf_arg_type at;
	bool exact_size = true;
	u64 size = U32_MAX;

	if (bpf_get_helper_proto(env, insn->imm, &fn) < 0)
		return info;

	at = fn->arg_type[arg];
	access_type = func_arg_access_type(at);

	switch (base_type(at)) {
	case ARG_PTR_TO_MAP_KEY:
	case ARG_PTR_TO_MAP_VALUE: {
		bool is_key = base_type(at) == ARG_PTR_TO_MAP_KEY;
		u64 val;
		int i, map_reg;

		for (i = 0; i < arg; i++) {
			if (base_type(fn->arg_type[i]) == ARG_CONST_MAP_PTR)
				break;
		}
		if (i >= arg)
			goto scan_all_maps;

		map_reg = BPF_REG_1 + i;

		if (!(aux->const_reg_map_mask & BIT(map_reg)))
			goto scan_all_maps;

		i = aux->const_reg_vals[map_reg];
		if (i < env->used_map_cnt) {
			/* Bloom-filter peek reads the value buffer. */
			if (!is_key && insn->imm == BPF_FUNC_map_peek_elem &&
			    env->used_maps[i]->map_type == BPF_MAP_TYPE_BLOOM_FILTER)
				access_type = BPF_READ;
			size = is_key ? env->used_maps[i]->key_size
				      : env->used_maps[i]->value_size;
			goto out;
		}
scan_all_maps:
		/*
		 * Map pointer is not known at this call site (e.g. different
		 * maps on merged paths).  Conservatively return the largest
		 * key_size or value_size across all maps used by the program.
		 * This is only an upper bound, so it cannot establish a definite
		 * write. Map-dependent argument types can also turn an output
		 * into an input, so conservatively retain a read dependency.
		 */
		exact_size = false;
		access_type |= BPF_READ;
		val = 0;
		for (i = 0; i < env->used_map_cnt; i++) {
			struct bpf_map *map = env->used_maps[i];
			u32 sz = is_key ? map->key_size : map->value_size;

			if (sz > val)
				val = sz;
			if (map->inner_map_meta) {
				sz = is_key ? map->inner_map_meta->key_size
					    : map->inner_map_meta->value_size;
				if (sz > val)
					val = sz;
			}
		}
		if (!val)
			return info;
		size = val;
		goto out;
	}
	case ARG_PTR_TO_MEM:
		if (at & MEM_FIXED_SIZE) {
			size = fn->arg_size[arg];
			goto out;
		}
		if (arg + 1 < ARRAY_SIZE(fn->arg_type) &&
		    arg_type_is_mem_size(fn->arg_type[arg + 1])) {
			int size_reg = BPF_REG_1 + arg + 1;

			if (aux->const_reg_mask & BIT(size_reg)) {
				size = aux->const_reg_vals[size_reg];
				goto out;
			}
		}
		/* Preserve access directions even when the extent is unknown. */
		goto out;
	case ARG_PTR_TO_DYNPTR:
		size = BPF_DYNPTR_SIZE;
		break;
	case ARG_PTR_TO_STACK:
		/*
		 * Only used by bpf_calls_callback() helpers. The helper itself
		 * doesn't access stack. The callback subprog does and it's
		 * analyzed separately.
		 */
		return (struct arg_access_info) {};
	default:
		return info;
	}
out:
	info.size = min_t(u64, size, U32_MAX);
	info.may_read = !!(access_type & BPF_READ);
	info.may_write = !!(access_type & BPF_WRITE);
	info.must_write = info.may_write && exact_size && info.size != U32_MAX;
	/* Generic unprivileged outputs retain prior initialization state. */
	if (!env->allow_uninit_stack && arg_type_is_raw_mem(at)) {
		info.may_read = true;
		info.must_write = false;
	}
	return info;
}

/*
 * Describe a kfunc's stack access through argument slot @arg (0-based).
 * As for helpers, must_write describes destruction of prior verifier state,
 * rather than a guarantee that the callee writes every byte at runtime.
 */
struct arg_access_info
bpf_kfunc_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn,
			     int arg, int insn_idx)
{
	struct bpf_insn_aux_data *aux = &env->insn_aux_data[insn_idx];
	struct arg_access_info info = {
		.size = U32_MAX,
		.may_read = true,
		.may_write = true,
	};
	struct bpf_call_arg_meta meta;
	const struct btf_param *args;
	const struct btf_type *t, *ref_t;
	const struct btf *btf;
	u32 i, slot, nargs, type_size;
	u64 size;

	if (bpf_fetch_kfunc_arg_meta(env, insn->imm, insn->off, &meta) < 0)
		return info;

	btf = meta.btf;
	args = btf_params(meta.func_proto);
	nargs = btf_type_vlen(meta.func_proto);

	/*
	 * @arg is an argument slot and a 16-byte parameter takes two of them,
	 * so walk the parameters to find the one that starts at this slot. A
	 * slot holding the upper eightbyte of such a parameter belongs to no
	 * pointer, and neither does a slot past the last parameter.
	 */
	for (i = 0, slot = 0; i < nargs && slot < arg; i++)
		slot += btf_arg_slots(btf_type_skip_modifiers(btf, args[i].type, NULL));
	if (i >= nargs || slot != arg)
		return (struct arg_access_info) {};

	t = btf_type_skip_modifiers(btf, args[i].type, NULL);
	if (!btf_type_is_ptr(t))
		return (struct arg_access_info) {};

	/* dynptr: fixed 16-byte on-stack representation */
	if (is_kfunc_arg_dynptr(btf, &args[i])) {
		size = BPF_DYNPTR_SIZE;
		goto out;
	}

	/* ptr + __sz/__szk pair: the size follows the pointer */
	if (i + 1 < nargs &&
	    (btf_param_match_suffix(btf, &args[i + 1], "__sz") ||
	     btf_param_match_suffix(btf, &args[i + 1], "__szk"))) {
		int size_reg = BPF_REG_1 + arg + 1;

		if (size_reg <= MAX_BPF_FUNC_REG_ARGS &&
		    (aux->const_reg_mask & BIT(size_reg))) {
			size = aux->const_reg_vals[size_reg];
			goto out;
		}
		/* Unknown size: the read may extend anywhere up to the frame top. */
		return info;
	}

	/* fixed-size pointed-to type: resolve via BTF */
	ref_t = btf_type_skip_modifiers(btf, t->type, NULL);
	if (!IS_ERR(btf_resolve_size(btf, ref_t, &type_size))) {
		size = type_size;
		goto out;
	}

	return info;
out:
	info.size = min_t(u64, size, U32_MAX);
	/* KF_ITER_NEW kfuncs initialize the iterator state at arg 0 */
	if (arg == 0 && meta.kfunc_flags & KF_ITER_NEW)
		info.may_read = false;
	if (is_kfunc_arg_uninit(btf, &args[i]) &&
	    (is_kfunc_arg_dynptr(btf, &args[i]) || env->allow_uninit_stack))
		info.may_read = false;
	info.must_write = !info.may_read && info.size != U32_MAX;
	return info;
}

/*
 * Called before dead code elimination, some subprograms may be genuinely unreachable.
 * Suppress diagnostics so callers can use a conservative result on error.
 * The main pass would report errors for reachable subprograms.
 */
static bool try_btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
{
	struct bpf_prog *prog = env->prog;
	u32 log_level = env->log.level;
	int err;

	if (!prog->aux->func_info || !prog->aux->func_info[subprog].type_id)
		return false;

	env->log.level = 0;
	err = btf_prepare_func_args(env, subprog);
	env->log.level = log_level;
	return !err;
}

/* Prepare argument metadata for liveness; the main program is handled separately. */
static void prepare_subprog_args(struct bpf_verifier_env *env)
{
	int i;

	for (i = 1; i < env->subprog_cnt; i++) {
		if (!try_btf_prepare_func_args(env, i) && bpf_subprog_is_global(env, i))
			/* Keep all argument registers live if the prototype is unavailable. */
			env->subprog_info[i].arg_slot_cnt = MAX_BPF_FUNC_REG_ARGS;
	}
}

/*
 * Derive stack effects for a global subprog's argument slot @arg (0-based)
 * from its declared type, matching the main pass's argument checks.
 */
struct arg_access_info
bpf_global_subprog_stack_access_bytes(struct bpf_verifier_env *env, struct bpf_insn *insn,
				      int arg, int insn_idx)
{
	struct arg_access_info info = {
		.size = U32_MAX,
		.may_read = true,
		.may_write = true,
	};
	struct bpf_subprog_info *sub;
	int callee;

	callee = bpf_find_subprog(env, insn_idx + insn->imm + 1);
	if (callee < 0)
		return info;
	sub = subprog_info(env, callee);
	if (!try_btf_prepare_func_args(env, callee))
		return info;

	switch (base_type(sub->args[arg].arg_type)) {
	case ARG_UNUSED:	/* Not an argument slot. */
	case ARG_SCALAR:	/* A scalar, the callee can't dereference it. */
		return (struct arg_access_info) {};
	case ARG_PTR_TO_BTF_ID:
		/*
		 * Trusted arguments cannot be stack pointers.
		 * Untrusted arguments use ARG_IGNORE:
		 * probe reads need no caller stack state, writes are prohibited.
		 */
		return (struct arg_access_info) {};
	case ARG_PTR_TO_MEM:
		/* mem_size is zero for untrusted pointers of unknown size. */
		if (sub->args[arg].mem_size) {
			info.size = sub->args[arg].mem_size;
			info.must_write = true;
		}
		return info;
	case ARG_PTR_TO_DYNPTR:
		/* The callee may adjust the view, but cannot reinitialize the dynptr. */
		info.size = BPF_DYNPTR_SIZE;
		return info;
	default:
		return info;
	}
}

/* check special kfuncs and return:
 *  1  - not fall-through to 'else' branch, continue verification
 *  0  - fall-through to 'else' branch
 * < 0 - not fall-through to 'else' branch, return error
 */
static int check_special_kfunc(struct bpf_verifier_env *env, struct bpf_call_arg_meta *meta,
			       struct bpf_reg_state *regs, struct bpf_insn_aux_data *insn_aux,
			       const struct btf_type *ptr_type, struct btf *desc_btf)
{
	const struct btf_type *ret_t;
	int err = 0;

	if (meta->btf != btf_vmlinux)
		return 0;

	if (is_bpf_obj_new_kfunc(meta->func_id) || is_bpf_percpu_obj_new_kfunc(meta->func_id)) {
		struct btf_struct_meta *struct_meta;
		struct btf *ret_btf;
		u32 ret_btf_id;

		if (is_bpf_obj_new_kfunc(meta->func_id) && !bpf_global_ma_set)
			return -ENOMEM;

		if (((u64)(u32)meta->arg_constant.value) != meta->arg_constant.value) {
			verbose(env, "local type ID argument must be in range [0, U32_MAX]\n");
			return -EINVAL;
		}

		ret_btf = env->prog->aux->btf;
		ret_btf_id = meta->arg_constant.value;

		/* This may be NULL due to user not supplying a BTF */
		if (!ret_btf) {
			verbose(env, "bpf_obj_new/bpf_percpu_obj_new requires prog BTF\n");
			return -EINVAL;
		}

		ret_t = btf_type_by_id(ret_btf, ret_btf_id);
		if (!ret_t || !__btf_type_is_struct(ret_t)) {
			verbose(env, "bpf_obj_new/bpf_percpu_obj_new type ID argument must be of a struct\n");
			return -EINVAL;
		}

		if (is_bpf_percpu_obj_new_kfunc(meta->func_id)) {
			if (ret_t->size > BPF_GLOBAL_PERCPU_MA_MAX_SIZE) {
				verbose(env, "bpf_percpu_obj_new type size (%d) is greater than %d\n",
					ret_t->size, BPF_GLOBAL_PERCPU_MA_MAX_SIZE);
				return -EINVAL;
			}

			if (!bpf_global_percpu_ma_set) {
				mutex_lock(&bpf_percpu_ma_lock);
				if (!bpf_global_percpu_ma_set) {
					/* Charge memory allocated with bpf_global_percpu_ma to
					 * root memcg. The obj_cgroup for root memcg is NULL.
					 */
					err = bpf_mem_alloc_percpu_init(&bpf_global_percpu_ma, NULL);
					if (!err)
						bpf_global_percpu_ma_set = true;
				}
				mutex_unlock(&bpf_percpu_ma_lock);
				if (err)
					return err;
			}

			mutex_lock(&bpf_percpu_ma_lock);
			err = bpf_mem_alloc_percpu_unit_init(&bpf_global_percpu_ma, ret_t->size);
			mutex_unlock(&bpf_percpu_ma_lock);
			if (err)
				return err;
		}

		struct_meta = btf_find_struct_meta(ret_btf, ret_btf_id);
		if (is_bpf_percpu_obj_new_kfunc(meta->func_id)) {
			if (!btf_type_is_scalar_struct(env, ret_btf, ret_t)) {
				verbose(env, "bpf_percpu_obj_new type ID argument must be of a struct of scalars\n");
				return -EINVAL;
			}

			if (struct_meta) {
				verbose(env, "bpf_percpu_obj_new type ID argument must not contain special fields\n");
				return -EINVAL;
			}
		}

		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
		regs[BPF_REG_0].btf = ret_btf;
		regs[BPF_REG_0].btf_id = ret_btf_id;
		if (is_bpf_percpu_obj_new_kfunc(meta->func_id))
			regs[BPF_REG_0].type |= MEM_PERCPU;

		insn_aux->obj_new_size = ret_t->size;
		insn_aux->kptr_struct_meta = struct_meta;
	} else if (is_bpf_refcount_acquire_kfunc(meta->func_id)) {
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_BTF_ID | MEM_ALLOC;
		regs[BPF_REG_0].btf = meta->arg_btf;
		regs[BPF_REG_0].btf_id = meta->arg_btf_id;

		insn_aux->kptr_struct_meta =
			btf_find_struct_meta(meta->arg_btf,
					     meta->arg_btf_id);
	} else if (is_list_node_type(ptr_type)) {
		struct btf_field *field = meta->arg_list_head.field;

		mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
	} else if (is_rbtree_node_type(ptr_type)) {
		struct btf_field *field = meta->arg_rbtree_root.field;

		mark_reg_graph_node(regs, BPF_REG_0, &field->graph_root);
	} else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_cast_to_kern_ctx])) {
		mark_reg_known_zero(env, regs, BPF_REG_0);
		regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_TRUSTED;
		regs[BPF_REG_0].btf = desc_btf;
		regs[BPF_REG_0].btf_id = meta->ret_btf_id;
	} else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_rdonly_cast])) {
		ret_t = btf_type_by_id(desc_btf, meta->arg_constant.value);
		if (!ret_t) {
			verbose(env, "Unknown type ID %lld passed to kfunc bpf_rdonly_cast\n",
				meta->arg_constant.value);
			return -EINVAL;
		} else if (btf_type_is_struct(ret_t)) {
			mark_reg_known_zero(env, regs, BPF_REG_0);
			regs[BPF_REG_0].type = PTR_TO_BTF_ID | PTR_UNTRUSTED;
			regs[BPF_REG_0].btf = desc_btf;
			regs[BPF_REG_0].btf_id = meta->arg_constant.value;
		} else if (btf_type_is_void(ret_t)) {
			mark_reg_known_zero(env, regs, BPF_REG_0);
			regs[BPF_REG_0].type = PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED;
			regs[BPF_REG_0].mem_size = 0;
		} else {
			verbose(env,
				"kfunc bpf_rdonly_cast type ID argument must be of a struct or void\n");
			return -EINVAL;
		}
	} else if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_slice]) ||
		   is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_slice_rdwr])) {
		enum bpf_type_flag type_flag = get_dynptr_type_flag(meta->dynptr.type);

		mark_reg_known_zero(env, regs, BPF_REG_0);

		if (!meta->arg_constant.found) {
			verifier_bug(env, "bpf_dynptr_slice(_rdwr) no constant size");
			return -EFAULT;
		}

		regs[BPF_REG_0].mem_size = meta->arg_constant.value;

		/* PTR_MAYBE_NULL will be added when is_kfunc_ret_null is checked */
		regs[BPF_REG_0].type = PTR_TO_MEM | type_flag;

		if (is_kfunc_call(meta, special_kfunc_list[KF_bpf_dynptr_slice])) {
			regs[BPF_REG_0].type |= MEM_RDONLY;
		} else {
			/* this will set env->seen_direct_write to true */
			if (!may_access_direct_pkt_data(env, NULL, BPF_WRITE)) {
				verbose(env, "the prog does not allow writes to packet data\n");
				return -EINVAL;
			}
		}

		if (!meta->dynptr.id) {
			verifier_bug(env, "no dynptr id");
			return -EFAULT;
		}
		regs[BPF_REG_0].parent_id = meta->dynptr.id;
	} else {
		return 0;
	}

	return 1;
}

static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name);

static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
			    int *insn_idx_p)
{
	bool sleepable, rcu_lock, rcu_unlock, preempt_disable, preempt_enable;
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
	struct bpf_reg_state *regs = cur_regs(env);
	const char *func_name, *ptr_type_name;
	const struct btf_type *t, *ptr_type;
	struct bpf_call_arg_meta meta;
	struct bpf_insn_aux_data *insn_aux;
	const char *operation;
	int err, insn_idx = *insn_idx_p;
	u32 i, proto_slots, ptr_type_id, ret_nregs = 1;
	struct bpf_kfunc_desc *desc;
	struct btf *desc_btf;
	int id;

	/* skip for now, but return error when we find this in fixup_kfunc_call */
	if (!insn->imm)
		return 0;

	err = bpf_fetch_kfunc_arg_meta(env, insn->imm, insn->off, &meta);
	if (err == -EACCES && meta.func_name) {
		verbose(env, "calling kernel function %s is not allowed\n", meta.func_name);
		operation = bpf_diag_fmt(env, "kfunc %s", meta.func_name);
		bpf_diag_policy(
			env, insn_idx, operation, "this program cannot call the kfunc",
			"Use a kfunc allowed for this program type and attach point, or change the program context.");
	}
	if (err)
		return err;
	desc_btf = meta.btf;
	func_name = meta.func_name;
	insn_aux = &env->insn_aux_data[insn_idx];

	desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
	if (!desc) {
		verifier_bug(env, "kfunc descriptor not found for func_id %u", insn->imm);
		return -EFAULT;
	}
	meta.fn = &desc->proto;

	insn_aux->is_iter_next = bpf_is_iter_next_kfunc(&meta);

	if (!insn->off &&
	    (insn->imm == special_kfunc_list[KF_bpf_res_spin_lock] ||
	     insn->imm == special_kfunc_list[KF_bpf_res_spin_lock_irqsave])) {
		struct bpf_verifier_state *branch;
		struct bpf_reg_state *regs;

		branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
		if (IS_ERR(branch)) {
			verbose(env, "failed to push state for failed lock acquisition\n");
			return PTR_ERR(branch);
		}

		regs = branch->frame[branch->curframe]->regs;

		/* Clear r0-r5 registers in forked state */
		for (i = 0; i < CALLER_SAVED_REGS; i++)
			bpf_mark_reg_not_init(env, &regs[caller_saved[i]]);

		mark_reg_unknown(env, regs, BPF_REG_0);
		err = __mark_reg_s32_range(env, regs, BPF_REG_0, -MAX_ERRNO, -1);
		if (err) {
			verbose(env, "failed to mark s32 range for retval in forked state for lock\n");
			return err;
		}
	} else if (!insn->off && insn->imm == special_kfunc_list[KF___bpf_trap]) {
		verbose(env, "unexpected __bpf_trap() due to uninitialized variable?\n");
		return -EFAULT;
	}

	if (is_kfunc_destructive(&meta) && !capable(CAP_SYS_BOOT)) {
		verbose(env, "destructive kfunc calls require CAP_SYS_BOOT capability\n");
		operation = bpf_diag_fmt(env, "destructive kfunc %s", meta.func_name);
		bpf_diag_policy(
			env, insn_idx, operation, "destructive kfuncs require CAP_SYS_BOOT",
			"Load the program with CAP_SYS_BOOT, or avoid destructive kfuncs.");
		return -EACCES;
	}

	if (is_kfunc_perfmon(&meta) && !env->allow_ptr_leaks) {
		verbose(env, "%s is allowed only to CAP_PERFMON and CAP_SYS_ADMIN\n",
			func_name);
		operation = bpf_diag_fmt(env, "kfunc %s", func_name);
		bpf_diag_policy(env, insn_idx, operation, "the kfunc requires CAP_PERFMON",
				"Load the program with CAP_PERFMON, or avoid the kfunc.");
		return -EPERM;
	}

	sleepable = bpf_is_kfunc_sleepable(&meta);
	if (sleepable && !in_sleepable_context(env)) {
		const char *suggestion;

		if (in_sleepable(env)) {
			verbose(env, "kernel func %s is sleepable within %s\n",
				func_name, non_sleepable_context_description(env));
			suggestion = "Move the kfunc call outside the critical section, or use a non-sleepable kfunc.";
		} else {
			verbose(env, "program must be sleepable to call sleepable kfunc %s\n",
				func_name);
			suggestion = "Mark the program sleepable if the program type allows it, or use a non-sleepable kfunc.";
		}
		operation = bpf_diag_fmt(env, "sleepable kfunc %s", func_name);
		bpf_diag_ctx_forbidden(env, insn_idx, operation, suggestion);
		return -EACCES;
	}

	/* Track non-sleepable context for kfuncs, same as for helpers. */
	if (!in_sleepable_context(env))
		insn_aux->non_sleepable = true;

	/* Check the arguments */
	err = check_func_args(env, &meta, insn_idx);
	if (err < 0)
		return err;

	err = mark_raw_stack(env, &meta, insn_idx);
	if (err)
		return err;

	if ((is_bpf_obj_drop_kfunc(meta.func_id) ||
	     is_bpf_percpu_obj_drop_kfunc(meta.func_id)) && (is_tracing_prog_type(prog_type) ||
	     /* is_tracing_prog_type() for now doesn't cover non-iterator tracing progs. */
	     (prog_type == BPF_PROG_TYPE_TRACING && env->prog->expected_attach_type != BPF_TRACE_ITER
	      && !env->prog->sleepable))) {
		struct btf_struct_meta *struct_meta;

		struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id);
		if (struct_meta && btf_record_has_nmi_unsafe_fields(struct_meta->record)) {
			verbose(env, "%s cannot be used in tracing programs on types with NMI unsafe fields\n",
				func_name);
			return -EINVAL;
		}
	}

	if (is_bpf_rbtree_add_kfunc(meta.func_id)) {
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_rbtree_add_callback_state);
		if (err) {
			verbose(env, "kfunc %s#%d failed callback verification\n",
				func_name, meta.func_id);
			return err;
		}
	}

	if (is_bpf_wq_set_callback_kfunc(meta.func_id)) {
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_timer_callback_state);
		if (err) {
			verbose(env, "kfunc %s#%d failed callback verification\n",
				func_name, meta.func_id);
			return err;
		}
	}

	if (is_task_work_add_kfunc(meta.func_id)) {
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_task_work_schedule_callback_state);
		if (err) {
			verbose(env, "kfunc %s#%d failed callback verification\n",
				func_name, meta.func_id);
			return err;
		}
	}

	if (is_call_rcu_kfunc(meta.func_id)) {
		err = push_callback_call(env, insn, insn_idx, meta.subprogno,
					 set_rcu_callback_state);
		if (err) {
			verbose(env, "kfunc %s#%d failed callback verification\n",
				func_name, meta.func_id);
			return err;
		}
	}

	rcu_lock = is_kfunc_bpf_rcu_read_lock(&meta);
	rcu_unlock = is_kfunc_bpf_rcu_read_unlock(&meta);

	preempt_disable = is_kfunc_bpf_preempt_disable(&meta);
	preempt_enable = is_kfunc_bpf_preempt_enable(&meta);

	if (rcu_lock) {
		env->cur_state->active_rcu_locks++;
		bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_RCU, true,
					env->cur_state->active_rcu_locks);
	} else if (rcu_unlock) {
		if (env->cur_state->active_rcu_locks == 0) {
			verbose(env, "unmatched rcu read unlock (kernel function %s)\n", func_name);
			bpf_diag_ctx_underflow(
				env, insn_idx, func_name, BPF_DIAG_CONTEXT_RCU,
				"Remove the extra bpf_rcu_read_unlock() call, or ensure this path first enters an RCU read lock region.");
			return -EINVAL;
		}
		env->cur_state->active_rcu_locks--;
		bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_RCU, false,
					env->cur_state->active_rcu_locks);
		if (!in_rcu_cs(env))
			invalidate_rcu_protected_refs(env);
	} else if (preempt_disable) {
		env->cur_state->active_preempt_locks++;
		bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_PREEMPT, true,
					env->cur_state->active_preempt_locks);
	} else if (preempt_enable) {
		if (env->cur_state->active_preempt_locks == 0) {
			verbose(env, "unmatched attempt to enable preemption (kernel function %s)\n", func_name);
			bpf_diag_ctx_underflow(
				env, insn_idx, func_name, BPF_DIAG_CONTEXT_PREEMPT,
				"Remove the extra bpf_preempt_enable() call, or ensure this path first disables preemption.");
			return -EINVAL;
		}
		env->cur_state->active_preempt_locks--;
		bpf_diag_record_context(env, insn_idx, BPF_DIAG_CONTEXT_PREEMPT, false,
					env->cur_state->active_preempt_locks);
		if (!in_rcu_cs(env))
			invalidate_rcu_protected_refs(env);
	}

	if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) {
		verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n");
		return -EACCES;
	}

	if (is_kfunc_rcu_protected(&meta) && !in_rcu_cs(env)) {
		verbose(env, "kernel func %s requires RCU critical section protection\n", func_name);
		bpf_diag_ctx_required(
			env, insn_idx, func_name, BPF_DIAG_CONTEXT_RCU,
			"Call this kfunc between bpf_rcu_read_lock() and bpf_rcu_read_unlock(), keeping all exit paths balanced.");
		return -EACCES;
	}

	/* In case of release function, we get register number of refcounted
	 * PTR_TO_BTF_ID in bpf_kfunc_arg_meta, do the release now.
	 */
	if (meta.release_regno) {
		err = release_reg(env, &regs[meta.release_regno], false, !!meta.dynptr.id);
		if (err)
			return err;
	}

	if (is_bpf_list_push_kfunc(meta.func_id) || is_bpf_rbtree_add_kfunc(meta.func_id)) {
		id = regs[BPF_REG_2].id;
		insn_aux->insert_off = regs[BPF_REG_2].var_off.value;
		insn_aux->kptr_struct_meta = btf_find_struct_meta(meta.arg_btf, meta.arg_btf_id);
		ref_convert_owning_non_owning(env, id);
	}

	if (meta.func_id == special_kfunc_list[KF_bpf_throw]) {
		if (!bpf_jit_supports_exceptions()) {
			verbose(env, "JIT does not support calling kfunc %s#%d\n",
				func_name, meta.func_id);
			return -ENOTSUPP;
		}
		env->seen_exception = true;

		/* In the case of the default callback, the cookie value passed
		 * to bpf_throw becomes the return value of the program.
		 */
		if (!env->exception_callback_subprog) {
			err = check_return_code(env, BPF_REG_1, "R1");
			if (err < 0)
				return err;
		}
	}

	bpf_diag_record_caller_saved(env, regs);
	bpf_diag_mod_begin(env, &regs[BPF_REG_0], NULL, BPF_DIAG_MOD_WRITE);
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		u32 regno = caller_saved[i];

		bpf_mark_reg_not_init(env, &regs[regno]);
	}
	invalidate_outgoing_stack_args(env, cur_func(env));

	/* Check return type */
	t = btf_type_skip_modifiers(desc_btf, meta.func_proto->type, NULL);

	if (is_kfunc_acquire(&meta) && !btf_type_is_struct_ptr(meta.btf, t)) {
		if (meta.btf != btf_vmlinux ||
		    (!is_bpf_obj_new_kfunc(meta.func_id) &&
		     !is_bpf_percpu_obj_new_kfunc(meta.func_id) &&
		     !is_bpf_refcount_acquire_kfunc(meta.func_id))) {
			verbose(env, "acquire kernel function does not return PTR_TO_BTF_ID\n");
			return -EINVAL;
		}
	}

	if (btf_type_is_scalar(t)) {
		ret_nregs = mark_kfunc_ret_regs(env, regs, t->size);
		if (meta.btf == btf_vmlinux && (meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock] ||
		    meta.func_id == special_kfunc_list[KF_bpf_res_spin_lock_irqsave]))
			__mark_reg_const_zero(env, &regs[BPF_REG_0]);
	} else if (btf_type_is_struct(t)) {
		struct btf_member_path path = {};
		const char *member_note = "";

		/*
		 * The returned struct comes back as raw register bits modeled
		 * as an unknown scalar, so a pointer member would be laundered
		 * into a scalar and escape provenance and reference tracking.
		 * Only scalars and arena pointers are allowed; see
		 * btf_validate_return_type() in btf.c for why an arena pointer
		 * is safe here.
		 */
		if (!btf_struct_member_walk(env, desc_btf, t,
					    BTF_MEMBER_SCALAR | BTF_MEMBER_ARENA_PTR, 0, &path)) {
			verbose(env,
				"kernel function %s returns %s %s that is not composed of scalars or arena pointers\n",
				func_name, btf_type_str(t),
				btf_name_by_offset(desc_btf, t->name_off));
			if (path.too_deep) {
				member_note = bpf_diag_fmt(
					env, " It nests structs more than %d levels deep.",
					BTF_MEMBER_MAX_DEPTH);
			} else if (path.depth) {
				char bad_name[BTF_MEMBER_PATH_LEN];

				btf_member_path_str(desc_btf, &path, bad_name, sizeof(bad_name));
				if (!path.bad_type) {
					verbose(env, "member '%s' is a zero-length array\n",
						bad_name);
					member_note = bpf_diag_fmt(
						env, " Its member '%s' is a zero-length array.",
						bad_name);
				} else {
					verbose(env, "member '%s' has type %s\n", bad_name,
						btf_type_str(path.bad_type));
					member_note = bpf_diag_fmt(
						env,
						" Its member '%s' is %s, not a scalar or an arena pointer.",
						bad_name, btf_type_str(path.bad_type));
				}
			}
			bpf_diag_program_structure(
				env, insn_idx, "unsupported kernel function return type",
				"Call a kernel function that returns only scalars or arena pointers by value.",
				"%s() returns %s %s by value.%s "
				"Only kfuncs returning scalar values or arena pointers, or "
				"structures composed of scalar values or arena pointers are "
				"supported.",
				func_name, btf_type_str(t),
				btf_name_by_offset(desc_btf, t->name_off), member_note);
			return -EINVAL;
		}
		ret_nregs = mark_kfunc_ret_regs(env, regs, t->size);
	} else if (btf_type_is_ptr(t)) {
		ptr_type = btf_type_skip_modifiers(desc_btf, t->type, &ptr_type_id);
		err = check_special_kfunc(env, &meta, regs, insn_aux, ptr_type, desc_btf);
		if (err) {
			if (err < 0)
				return err;
		} else if (btf_type_is_void(ptr_type)) {
			/* kfunc returning 'void *' is equivalent to returning scalar */
			mark_reg_unknown(env, regs, BPF_REG_0);
		} else if (!__btf_type_is_struct(ptr_type)) {
			if (!meta.ret_mem.found) {
				__u32 sz;

				if (!IS_ERR(btf_resolve_size(desc_btf, ptr_type, &sz))) {
					meta.ret_mem.found = true;
					meta.ret_mem.size = sz;
					meta.r0_rdonly = true;
				}

				if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie])
					meta.r0_rdonly = false;
			}
			if (!meta.ret_mem.found) {
				ptr_type_name = btf_name_by_offset(desc_btf,
								   ptr_type->name_off);
				verbose(env,
					"kernel function %s returns pointer type %s %s is not supported\n",
					func_name,
					btf_type_str(ptr_type),
					ptr_type_name);
				return -EINVAL;
			}

			mark_reg_known_zero(env, regs, BPF_REG_0);
			regs[BPF_REG_0].type = PTR_TO_MEM;
			regs[BPF_REG_0].mem_size = meta.ret_mem.size;

			if (meta.r0_rdonly)
				regs[BPF_REG_0].type |= MEM_RDONLY;

			/* Ensures we don't access the memory after a release_reference() */
			if (meta.ref_obj.id) {
				err = validate_ref_obj(env, &meta.ref_obj);
				if (err)
					return err;
				regs[BPF_REG_0].parent_id = meta.ref_obj.id;
			}

			if (is_kfunc_rcu_protected(&meta))
				regs[BPF_REG_0].type |= MEM_RCU;
		} else {
			enum bpf_reg_type type = PTR_TO_BTF_ID;

			if (meta.func_id == special_kfunc_list[KF_bpf_get_kmem_cache])
				type |= PTR_UNTRUSTED;
			else if (is_kfunc_rcu_protected(&meta) ||
				 (bpf_is_iter_next_kfunc(&meta) &&
				  (get_iter_from_state(env->cur_state, &meta)
					   ->type & MEM_RCU))) {
				/*
				 * If the iterator's constructor (the _new
				 * function e.g., bpf_iter_task_new) has been
				 * annotated with BPF kfunc flag
				 * KF_RCU_PROTECTED and was called within a RCU
				 * read-side critical section, also propagate
				 * the MEM_RCU flag to the pointer returned from
				 * the iterator's next function (e.g.,
				 * bpf_iter_task_next).
				 */
				type |= MEM_RCU;
			} else {
				/*
				 * Any PTR_TO_BTF_ID that is returned from a BPF
				 * kfunc should by default be treated as
				 * implicitly trusted.
				 */
				type |= PTR_TRUSTED;
			}

			mark_reg_known_zero(env, regs, BPF_REG_0);
			regs[BPF_REG_0].btf = desc_btf;
			regs[BPF_REG_0].type = type;
			regs[BPF_REG_0].btf_id = ptr_type_id;
		}

		if (is_kfunc_ret_null(&meta)) {
			regs[BPF_REG_0].type |= PTR_MAYBE_NULL;
			/* For mark_ptr_or_null_reg, see 93c230e3f5bd6 */
			regs[BPF_REG_0].id = ++env->id_gen;
		}
		if (is_kfunc_acquire(&meta)) {
			id = acquire_reference(env, insn_idx, 0);
			if (id < 0)
				return id;
			regs[BPF_REG_0].id = id;
		} else if (is_rbtree_node_type(ptr_type) || is_list_node_type(ptr_type)) {
			ref_set_non_owning(env, &regs[BPF_REG_0]);
		}

		if (reg_may_point_to_spin_lock(&regs[BPF_REG_0]) && !regs[BPF_REG_0].id)
			regs[BPF_REG_0].id = ++env->id_gen;
	} else if (btf_type_is_void(t)) {
		if (meta.btf == btf_vmlinux) {
			if (is_bpf_obj_drop_kfunc(meta.func_id) ||
			    is_bpf_percpu_obj_drop_kfunc(meta.func_id)) {
				insn_aux->kptr_struct_meta =
					btf_find_struct_meta(meta.arg_btf,
							     meta.arg_btf_id);
			}
		}
	}

	if (is_kfunc_dynptr_write(&meta) ?
	    dynptr_write_changes_pkt_data(meta.dynptr_write_type) :
	    bpf_is_kfunc_pkt_changing(&meta))
		clear_all_pkt_pointers(env);

	/*
	 * These kfuncs write to the head of the skb in place if what they write
	 * to is linear. Like a direct write that takes bpf_unclone_prologue().
	 */
	if (is_kfunc_dynptr_write(&meta) &&
	    dynptr_write_changes_pkt_data(meta.dynptr_write_type))
		may_access_direct_pkt_data(env, NULL, BPF_WRITE);

	proto_slots = kfunc_abi_slots(&desc->func_model);
	if (proto_slots > MAX_BPF_FUNC_REG_ARGS) {
		struct bpf_func_state *caller = cur_func(env);
		struct bpf_subprog_info *caller_info = &env->subprog_info[caller->subprogno];
		u16 out_stack_arg_cnt = proto_slots - MAX_BPF_FUNC_REG_ARGS;
		u16 stack_arg_cnt = bpf_in_stack_arg_cnt(caller_info) + out_stack_arg_cnt;

		if (stack_arg_cnt > caller_info->stack_arg_cnt)
			caller_info->stack_arg_cnt = stack_arg_cnt;
	}

	/*
	 * Record R0 before process_iter_next_call() snapshots the alternate
	 * iterator path's diagnostic position.
	 */
	if (ret_nregs == 1)
		bpf_diag_mod_end(env);

	if (bpf_is_iter_next_kfunc(&meta)) {
		err = process_iter_next_call(env, insn_idx, &meta);
		if (err)
			return err;
	}

	if (meta.func_id == special_kfunc_list[KF_bpf_session_cookie])
		env->prog->call_session_cookie = true;

	if (bpf_is_throw_kfunc(insn))
		return process_bpf_exit_full(env, NULL, true);

	return 0;
}

static bool check_reg_sane_offset_scalar(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(reg);

	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(env, type), val);
		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(env, 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(env, type));
		return false;
	}

	return true;
}

static bool check_reg_sane_offset_ptr(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(reg);

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

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

	return true;
}

enum {
	REASON_BOUNDS	= -1,
	REASON_TYPE	= -2,
	REASON_PATHS	= -3,
	REASON_LIMIT	= -4,
	REASON_STACK	= -5,
};

static int retrieve_ptr_limit(const struct bpf_verifier_env *env,
			      const struct bpf_reg_state *ptr_reg,
			      u32 *alu_limit, bool mask_to_left)
{
	u32 max = 0, ptr_limit = 0;

	switch (ptr_reg->type) {
	case PTR_TO_STACK:
		/* Offset 0 is out-of-bounds, but acceptable start for the
		 * left direction, see BPF_REG_FP. Also, unknown scalar
		 * offset where we would need to deal with min/max bounds is
		 * currently prohibited for unprivileged.
		 */
		max = env->stack_limit + mask_to_left;
		ptr_limit = -ptr_reg->var_off.value;
		break;
	case PTR_TO_MAP_VALUE:
		max = ptr_reg->map_ptr->value_size;
		ptr_limit = mask_to_left ? reg_smin(ptr_reg) : reg_umax(ptr_reg);
		break;
	default:
		return REASON_TYPE;
	}

	if (ptr_limit >= max)
		return REASON_LIMIT;
	*alu_limit = ptr_limit;
	return 0;
}

static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
				    const struct bpf_insn *insn)
{
	return env->bypass_spec_v1 ||
		BPF_SRC(insn->code) == BPF_K ||
		cur_aux(env)->nospec;
}

static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
				       u32 alu_state, u32 alu_limit)
{
	/* If we arrived here from different branches with different
	 * state or limits to sanitize, then this won't work.
	 */
	if (aux->alu_state &&
	    (aux->alu_state != alu_state ||
	     aux->alu_limit != alu_limit))
		return REASON_PATHS;

	/* Corresponding fixup done in do_misc_fixups(). */
	aux->alu_state = alu_state;
	aux->alu_limit = alu_limit;
	return 0;
}

static int sanitize_val_alu(struct bpf_verifier_env *env,
			    struct bpf_insn *insn)
{
	struct bpf_insn_aux_data *aux = cur_aux(env);

	if (can_skip_alu_sanitation(env, insn))
		return 0;

	return update_alu_sanitation_state(aux, BPF_ALU_NON_POINTER, 0);
}

static bool sanitize_needed(u8 opcode)
{
	return opcode == BPF_ADD || opcode == BPF_SUB;
}

struct bpf_sanitize_info {
	struct bpf_insn_aux_data aux;
	bool mask_to_left;
};

static int sanitize_speculative_path(struct bpf_verifier_env *env,
				     const struct bpf_insn *insn,
				     u32 next_idx, u32 curr_idx)
{
	struct bpf_verifier_state *branch;
	struct bpf_reg_state *regs;

	branch = push_stack(env, next_idx, curr_idx, true);
	if (!IS_ERR(branch) && insn) {
		regs = branch->frame[branch->curframe]->regs;
		if (BPF_SRC(insn->code) == BPF_K) {
			mark_reg_unknown(env, regs, insn->dst_reg);
		} else if (BPF_SRC(insn->code) == BPF_X) {
			mark_reg_unknown(env, regs, insn->dst_reg);
			mark_reg_unknown(env, regs, insn->src_reg);
		}
	}
	return PTR_ERR_OR_ZERO(branch);
}

static int sanitize_ptr_alu(struct bpf_verifier_env *env,
			    struct bpf_insn *insn,
			    const struct bpf_reg_state *ptr_reg,
			    const struct bpf_reg_state *off_reg,
			    struct bpf_reg_state *dst_reg,
			    struct bpf_sanitize_info *info,
			    const bool commit_window)
{
	struct bpf_insn_aux_data *aux = commit_window ? cur_aux(env) : &info->aux;
	struct bpf_verifier_state *vstate = env->cur_state;
	bool off_is_imm = tnum_is_const(off_reg->var_off);
	bool off_is_neg = reg_smin(off_reg) < 0;
	bool ptr_is_dst_reg = ptr_reg == dst_reg;
	u8 opcode = BPF_OP(insn->code);
	u32 alu_state, alu_limit;
	struct bpf_reg_state tmp;
	int err;

	if (can_skip_alu_sanitation(env, insn))
		return 0;

	/* We already marked aux for masking from non-speculative
	 * paths, thus we got here in the first place. We only care
	 * to explore bad access from here.
	 */
	if (vstate->speculative)
		goto do_sim;

	if (!commit_window) {
		if (!tnum_is_const(off_reg->var_off) &&
		    (reg_smin(off_reg) < 0) != (reg_smax(off_reg) < 0))
			return REASON_BOUNDS;

		info->mask_to_left = (opcode == BPF_ADD &&  off_is_neg) ||
				     (opcode == BPF_SUB && !off_is_neg);
	}

	err = retrieve_ptr_limit(env, ptr_reg, &alu_limit, info->mask_to_left);
	if (err < 0)
		return err;

	if (commit_window) {
		/* In commit phase we narrow the masking window based on
		 * the observed pointer move after the simulated operation.
		 */
		alu_state = info->aux.alu_state;
		alu_limit = abs(info->aux.alu_limit - alu_limit);
	} else {
		alu_state  = off_is_neg ? BPF_ALU_NEG_VALUE : 0;
		alu_state |= off_is_imm ? BPF_ALU_IMMEDIATE : 0;
		alu_state |= ptr_is_dst_reg ?
			     BPF_ALU_SANITIZE_SRC : BPF_ALU_SANITIZE_DST;

		/* Limit pruning on unknown scalars to enable deep search for
		 * potential masking differences from other program paths.
		 */
		if (!off_is_imm)
			env->explore_alu_limits = true;
	}

	err = update_alu_sanitation_state(aux, alu_state, alu_limit);
	if (err < 0)
		return err;
do_sim:
	/* If we're in commit phase, we're done here given we already
	 * pushed the truncated dst_reg into the speculative verification
	 * stack.
	 *
	 * Also, when register is a known constant, we rewrite register-based
	 * operation to immediate-based, and thus do not need masking (and as
	 * a consequence, do not need to simulate the zero-truncation either).
	 */
	if (commit_window || off_is_imm)
		return 0;

	/* Simulate and find potential out-of-bounds access under
	 * speculative execution from truncation as a result of
	 * masking when off was not within expected range. If off
	 * sits in dst, then we temporarily need to move ptr there
	 * to simulate dst (== 0) +/-= ptr. Needed, for example,
	 * for cases where we use K-based arithmetic in one direction
	 * and truncated reg-based in the other in order to explore
	 * bad access.
	 */
	if (!ptr_is_dst_reg) {
		tmp = *dst_reg;
		*dst_reg = *ptr_reg;
	}
	err = sanitize_speculative_path(env, NULL, env->insn_idx + 1, env->insn_idx);
	if (err < 0)
		return REASON_STACK;
	if (!ptr_is_dst_reg)
		*dst_reg = tmp;
	return 0;
}

static void sanitize_mark_insn_seen(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *vstate = env->cur_state;

	/* If we simulate paths under speculation, we don't update the
	 * insn as 'seen' such that when we verify unreachable paths in
	 * the non-speculative domain, sanitize_dead_code() can still
	 * rewrite/sanitize them.
	 */
	if (!vstate->speculative)
		env->insn_aux_data[env->insn_idx].seen = env->pass_cnt;
}

static int sanitize_err(struct bpf_verifier_env *env, const struct bpf_insn *insn, int reason)
{
	static const char *err = "pointer arithmetic with it prohibited for !root";
	const char *op = BPF_OP(insn->code) == BPF_ADD ? "add" : "sub";
	u32 dst = insn->dst_reg, src = insn->src_reg;
	struct bpf_reg_state *regs = cur_regs(env);

	switch (reason) {
	case REASON_BOUNDS:
		verbose(env, "R%d has unknown scalar with mixed signed bounds, %s\n",
			regs[src].type == SCALAR_VALUE ? src : dst, err);
		break;
	case REASON_TYPE:
		verbose(env, "R%d has pointer with unsupported alu operation, %s\n",
			regs[src].type == SCALAR_VALUE ? dst : src, err);
		break;
	case REASON_PATHS:
		verbose(env, "R%d tried to %s from different maps, paths or scalars, %s\n",
			dst, op, err);
		break;
	case REASON_LIMIT:
		verbose(env, "R%d tried to %s beyond pointer bounds, %s\n",
			dst, op, err);
		break;
	case REASON_STACK:
		verbose(env, "R%d could not be pushed for speculative verification, %s\n",
			dst, err);
		return -ENOMEM;
	default:
		verifier_bug(env, "unknown reason (%d)", reason);
		break;
	}

	return -EACCES;
}

/* check that stack access falls within stack limits and that 'reg' doesn't
 * have a variable offset.
 *
 * Variable offset is prohibited for unprivileged mode for simplicity since it
 * requires corresponding support in Spectre masking for stack ALU.  See also
 * retrieve_ptr_limit().
 */
static int check_stack_access_for_ptr_arithmetic(
				struct bpf_verifier_env *env,
				int regno,
				const struct bpf_reg_state *reg,
				int off)
{
	if (!tnum_is_const(reg->var_off)) {
		char tn_buf[48];

		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
		verbose(env, "R%d variable stack access prohibited for !root, var_off=%s off=%d\n",
			regno, tn_buf, off);
		return -EACCES;
	}

	if (off >= 0 || off < -(int)env->stack_limit) {
		verbose(env, "R%d stack pointer arithmetic goes out of range, "
			"prohibited for !root; off=%d\n", regno, off);
		return -EACCES;
	}

	return 0;
}

static int sanitize_check_bounds(struct bpf_verifier_env *env,
				 const struct bpf_insn *insn,
				 struct bpf_reg_state *dst_reg)
{
	u32 dst = insn->dst_reg;

	/* For unprivileged we require that resulting offset must be in bounds
	 * in order to be able to sanitize access later on.
	 */
	if (env->bypass_spec_v1)
		return 0;

	switch (dst_reg->type) {
	case PTR_TO_STACK:
		if (check_stack_access_for_ptr_arithmetic(env, dst, dst_reg,
							  dst_reg->var_off.value))
			return -EACCES;
		break;
	case PTR_TO_MAP_VALUE:
		if (check_map_access(env, dst_reg, argno_from_reg(dst), 0, 1, false, ACCESS_HELPER)) {
			verbose(env, "R%d pointer arithmetic of map value goes out of range, "
				"prohibited for !root\n", dst);
			return -EACCES;
		}
		break;
	default:
		return -EOPNOTSUPP;
	}

	return 0;
}

static void scalar_step_mul(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg)
{
	if (tnum_is_const(src_reg->var_off))
		scalar_step_scale(dst_reg, src_reg->var_off.value);
	else
		reg_step_reset(dst_reg);
}

static void scalar_step_lsh(struct bpf_reg_state *dst_reg, struct bpf_reg_state *src_reg)
{
	u64 amount = src_reg->var_off.value;

	if (tnum_is_const(src_reg->var_off) && amount < 64)
		scalar_step_scale(dst_reg, 1ULL << amount);
	else
		reg_step_reset(dst_reg);
}

/* 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,
				   u32 ptr_regno, 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 = reg_smin(off_reg), smax_val = reg_smax(off_reg);
	u64 umin_val = reg_umin(off_reg), umax_val = reg_umax(off_reg);
	struct bpf_sanitize_info info = {};
	u8 opcode = BPF_OP(insn->code);
	u32 dst = insn->dst_reg;
	const char *reason;
	int ret, bounds_ret;
	bool to_scalar;

	dst_reg = &regs[dst];
	/*
	 * Only += and -= keep a pointer. Any other op makes a number of it,
	 * which is fine when the program may see values of pointers anyway.
	 */
	to_scalar = opcode != BPF_ADD && opcode != BPF_SUB && env->allow_ptr_leaks;

	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(env, dst_reg);
		return 0;
	}

	if (BPF_CLASS(insn->code) != BPF_ALU64 && !to_scalar) {
		/* 32-bit ALU ops on pointers produce (meaningless) scalars */
		if (opcode == BPF_SUB && env->allow_ptr_leaks) {
			__mark_reg_unknown(env, dst_reg);
			return 0;
		}

		verbose(env,
			"R%d 32-bit pointer arithmetic prohibited\n",
			dst);
		reason = bpf_diag_fmt(
			env, "R%d holds %s. 32-bit ALU operations on pointers discard pointer tracking, so the verifier cannot keep the result as a safe pointer.",
			ptr_regno, bpf_diag_reg_type_plain(env, ptr_reg->type));
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "32-bit pointer arithmetic", reason,
			"Use a 64-bit ALU instruction with an allowed, bounded scalar offset.");
		return -EACCES;
	}

	if (ptr_reg->type & PTR_MAYBE_NULL) {
		verbose(env, "R%d pointer arithmetic on %s prohibited, null-check it first\n",
			dst, reg_type_str(env, ptr_reg->type));
		reason = bpf_diag_fmt(
			env, "R%d may be NULL (%s). Pointer arithmetic is allowed only after the program proves the pointer is non-NULL on this path.",
			ptr_regno, reg_type_str(env, ptr_reg->type));
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "pointer arithmetic before NULL check", reason,
			"Make sure that a NULL check precedes any arithmetic performed on the pointer.");
		return -EACCES;
	}

	switch (base_type(ptr_reg->type)) {
	case PTR_TO_CTX:
	case PTR_TO_MAP_VALUE:
	case PTR_TO_MAP_KEY:
	case PTR_TO_STACK:
	case PTR_TO_PACKET_META:
	case PTR_TO_PACKET:
	case PTR_TO_TP_BUFFER:
	case PTR_TO_BTF_ID:
	case PTR_TO_MEM:
	case PTR_TO_BUF:
	case PTR_TO_FUNC:
	case CONST_PTR_TO_DYNPTR:
		break;
	case PTR_TO_FLOW_KEYS:
		if (known)
			break;
		fallthrough;
	case CONST_PTR_TO_MAP:
		/* smin_val represents the known value */
		if (known && smin_val == 0 && opcode == BPF_ADD)
			break;
		fallthrough;
	default:
		verbose(env, "R%d pointer arithmetic on %s prohibited\n",
			dst, reg_type_str(env, ptr_reg->type));
		reason = bpf_diag_fmt(
			env, "R%d holds %s. This pointer kind does not allow offset arithmetic.",
			ptr_regno, bpf_diag_reg_type_plain(env, ptr_reg->type));
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "pointer arithmetic is not allowed", reason,
			"Do not change this pointer's offset; use it only in operations accepted for its kind.");
		return -EACCES;
	}

	if (to_scalar) {
		__mark_reg_unknown(env, dst_reg);
		return 0;
	}

	/* For 'scalar += pointer', dst_reg inherits the complete pointer
	 * register state. Individual fields may be adjusted later by pointer
	 * arithmetic. Callers guarantee that below does not overwrite off_reg.
	 */
	if (dst_reg != ptr_reg)
		*dst_reg = *ptr_reg;

	/*
	 * Accesses to untrusted PTR_TO_MEM are done through probe
	 * instructions, hence no need to track offsets.
	 */
	if (base_type(ptr_reg->type) == PTR_TO_MEM && (ptr_reg->type & PTR_UNTRUSTED))
		return 0;

	if (!check_reg_sane_offset_scalar(env, off_reg, ptr_reg->type)) {
		reason = bpf_diag_fmt(
			env, "The scalar offset used with R%d is unbounded or outside the verifier's safe pointer-offset range [-%u, %u].",
			ptr_regno, BPF_MAX_VAR_OFF, BPF_MAX_VAR_OFF);
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "pointer offset is not safe", reason,
			"Clamp or bounds-check the scalar offset before applying it to the pointer.");
		return -EINVAL;
	}
	if (!check_reg_sane_offset_ptr(env, ptr_reg, ptr_reg->type)) {
		reason = bpf_diag_fmt(
			env, "R%d already has an offset outside the verifier's safe range [-%u, %u] for %s.",
			ptr_regno, BPF_MAX_VAR_OFF, BPF_MAX_VAR_OFF,
			bpf_diag_reg_type_plain(env, ptr_reg->type));
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "pointer offset is not safe", reason,
			"Keep the base pointer within the verifier's allowed offset range before applying more arithmetic.");
		return -EINVAL;
	}

	if (sanitize_needed(opcode)) {
		ret = sanitize_ptr_alu(env, insn, ptr_reg, off_reg, dst_reg,
				       &info, false);
		if (ret < 0)
			return sanitize_err(env, insn, ret);
	}

	/*
	 * Pointer types do not carry 32-bit bounds at the moment. Blank r32
	 * only after sanitize_ptr_alu() may have snapshotted dst_reg into a
	 * speculative path: otherwise reg_bounds_sanity_check() might hit some
	 * constraints violations.
	 */
	__mark_reg32_unbounded(dst_reg);

	switch (opcode) {
	case BPF_ADD:
		/*
		 * 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.
		 */
		scalar_step_add(dst_reg, ptr_reg, off_reg);
		dst_reg->r64 = cnum64_add(ptr_reg->r64, off_reg->r64);
		dst_reg->var_off = tnum_add(ptr_reg->var_off, off_reg->var_off);
		dst_reg->raw = ptr_reg->raw;
		if (reg_is_pkt_pointer(ptr_reg)) {
			if (!known)
				dst_reg->id = ++env->id_gen;
			/*
			 * Clear range for unknown addends since we can't know
			 * where the pkt pointer ended up. Also clear AT_PKT_END /
			 * BEYOND_PKT_END from prior comparison as any pointer
			 * arithmetic invalidates them.
			 */
			if (!known || dst_reg->range < 0)
				memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
		}
		break;
	case BPF_SUB:
		if (dst_reg != ptr_reg) {
			/* scalar -= pointer.  Creates an unknown scalar */
			verbose(env, "R%d tried to subtract pointer from scalar\n",
				dst);
			reason = bpf_diag_fmt(
				env, "This operation subtracts pointer register R%d from scalar register R%d. "
				"The verifier only tracks pointer-minus-scalar arithmetic for allowed pointer types.",
				ptr_regno, dst);
			bpf_diag_register_type(
				env, env->insn_idx, ptr_regno, "pointer subtracted from scalar", reason,
				"Keep the pointer as the base; only add or subtract bounded scalars when permitted.");
			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);
			reason = bpf_diag_fmt(
				env, "R%d is a stack pointer. The verifier does not allow BPF_SUB to move stack pointers.",
				ptr_regno);
			bpf_diag_register_type(
				env, env->insn_idx, ptr_regno, "subtraction from stack pointer", reason,
				"Use addition from R10 to form stack addresses within the tracked stack frame.");
			return -EACCES;
		}
		dst_reg->r64 = cnum64_add(ptr_reg->r64, cnum64_negate(off_reg->r64));
		dst_reg->var_off = tnum_sub(ptr_reg->var_off, off_reg->var_off);
		dst_reg->raw = ptr_reg->raw;
		if (reg_is_pkt_pointer(ptr_reg)) {
			if (!known)
				dst_reg->id = ++env->id_gen;
			/*
			 * Clear range if the subtrahend may be negative since
			 * pkt pointer could move past its bounds. A positive
			 * subtrahend moves it backwards keeping positive range
			 * intact. Also clear AT_PKT_END / BEYOND_PKT_END from
			 * prior comparison as arithmetic invalidates them.
			 */
			if ((!known && smin_val < 0) || dst_reg->range < 0)
				memset(&dst_reg->raw, 0, sizeof(dst_reg->raw));
		}
		reg_step_reset(dst_reg);
		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]);
		reason = bpf_diag_fmt(
			env, "R%d holds %s. Bitwise operator %s would destroy the pointer value the verifier is tracking.",
			ptr_regno, bpf_diag_reg_type_plain(env, ptr_reg->type),
			bpf_alu_string[opcode >> 4]);
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "bitwise operation on pointer", reason,
			"Do bitwise operations on scalar values, not on pointer-valued registers.");
		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]);
		reason = bpf_diag_fmt(
			env, "R%d holds %s. Operator %s is not one of the limited pointer arithmetic operations the verifier can track.",
			ptr_regno, bpf_diag_reg_type_plain(env, ptr_reg->type),
			bpf_alu_string[opcode >> 4]);
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "invalid pointer arithmetic operator", reason,
			"Use only verifier-supported addition or subtraction with a bounded scalar offset, or perform this operation on a scalar value.");
		return -EACCES;
	}

	if (!check_reg_sane_offset_ptr(env, dst_reg, ptr_reg->type)) {
		reason = bpf_diag_fmt(
			env, "After this arithmetic, R%d would be outside the verifier's safe offset range [-%u, %u] for %s.",
			dst, BPF_MAX_VAR_OFF, BPF_MAX_VAR_OFF,
			bpf_diag_reg_type_plain(env, ptr_reg->type));
		bpf_diag_register_type(
			env, env->insn_idx, ptr_regno, "pointer offset is not safe", reason,
			"Tighten the scalar bounds before the arithmetic so the resulting pointer remains within the allowed range.");
		return -EINVAL;
	}
	/*
	 * A packet pointer that keeps its id or range is checked against a
	 * range set from the checked pointer's umax, so var_off must not tighten
	 * its umax. r32 must still match var_off for reg_bounds_sanity_check().
	 */
	if (reg_is_pkt_pointer(dst_reg) && (known || dst_reg->range > 0))
		__update_reg32_bounds(dst_reg);
	else
		reg_bounds_sync(dst_reg);
	bounds_ret = sanitize_check_bounds(env, insn, dst_reg);
	if (bounds_ret == -EACCES)
		return bounds_ret;
	if (sanitize_needed(opcode)) {
		ret = sanitize_ptr_alu(env, insn, dst_reg, off_reg, dst_reg,
				       &info, true);
		if (verifier_bug_if(!can_skip_alu_sanitation(env, insn)
				    && !env->cur_state->speculative
				    && bounds_ret
				    && !ret,
				    env, "Pointer type unsupported by sanitize_check_bounds() not rejected by retrieve_ptr_limit() as required")) {
			return -EFAULT;
		}
		if (ret < 0)
			return sanitize_err(env, insn, ret);
	}

	return 0;
}

static void scalar32_min_max_add(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	dst_reg->r32 = cnum32_add(dst_reg->r32, src_reg->r32);
}

static void scalar_min_max_add(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	dst_reg->r64 = cnum64_add(dst_reg->r64, src_reg->r64);
}

static void scalar32_min_max_sub(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	dst_reg->r32 = cnum32_add(dst_reg->r32, cnum32_negate(src_reg->r32));
}

static void scalar_min_max_sub(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	dst_reg->r64 = cnum64_add(dst_reg->r64, cnum64_negate(src_reg->r64));
}

static void scalar32_min_max_mul(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	s32 smin = reg_s32_min(dst_reg);
	s32 smax = reg_s32_max(dst_reg);
	u32 umin = reg_u32_min(dst_reg);
	u32 umax = reg_u32_max(dst_reg);
	s32 tmp_prod[4];

	if (check_mul_overflow(umax, reg_u32_max(src_reg), &umax) ||
	    check_mul_overflow(umin, reg_u32_min(src_reg), &umin)) {
		/* Overflow possible, we know nothing */
		umin = 0;
		umax = U32_MAX;
	}
	if (check_mul_overflow(smin, reg_s32_min(src_reg), &tmp_prod[0]) ||
	    check_mul_overflow(smin, reg_s32_max(src_reg), &tmp_prod[1]) ||
	    check_mul_overflow(smax, reg_s32_min(src_reg), &tmp_prod[2]) ||
	    check_mul_overflow(smax, reg_s32_max(src_reg), &tmp_prod[3])) {
		/* Overflow possible, we know nothing */
		smin = S32_MIN;
		smax = S32_MAX;
	} else {
		smin = min_array(tmp_prod, 4);
		smax = max_array(tmp_prod, 4);
	}

	dst_reg->r32 = cnum32_intersect(cnum32_from_urange(umin, umax),
					cnum32_from_srange(smin, smax));
}

static void scalar_min_max_mul(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	s64 smin = reg_smin(dst_reg);
	s64 smax = reg_smax(dst_reg);
	u64 umin = reg_umin(dst_reg);
	u64 umax = reg_umax(dst_reg);
	s64 tmp_prod[4];

	if (check_mul_overflow(umax, reg_umax(src_reg), &umax) ||
	    check_mul_overflow(umin, reg_umin(src_reg), &umin)) {
		/* Overflow possible, we know nothing */
		umin = 0;
		umax = U64_MAX;
	}
	if (check_mul_overflow(smin, reg_smin(src_reg), &tmp_prod[0]) ||
	    check_mul_overflow(smin, reg_smax(src_reg), &tmp_prod[1]) ||
	    check_mul_overflow(smax, reg_smin(src_reg), &tmp_prod[2]) ||
	    check_mul_overflow(smax, reg_smax(src_reg), &tmp_prod[3])) {
		/* Overflow possible, we know nothing */
		smin = S64_MIN;
		smax = S64_MAX;
	} else {
		smin = min_array(tmp_prod, 4);
		smax = max_array(tmp_prod, 4);
	}

	dst_reg->r64 = cnum64_intersect(cnum64_from_urange(umin, umax),
					cnum64_from_srange(smin, smax));
}

static void scalar32_min_max_udiv(struct bpf_reg_state *dst_reg,
				  struct bpf_reg_state *src_reg)
{
	u32 src_val = reg_u32_min(src_reg); /* non-zero, const divisor */

	reg_set_urange32(dst_reg, reg_u32_min(dst_reg) / src_val,
			 reg_u32_max(dst_reg) / src_val);

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg64_and_tnum(dst_reg);
}

static void scalar_min_max_udiv(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	u64 src_val = reg_umin(src_reg); /* non-zero, const divisor */

	reg_set_urange64(dst_reg, div64_u64(reg_umin(dst_reg), src_val),
			 div64_u64(reg_umax(dst_reg), src_val));

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg32_and_tnum(dst_reg);
}

static void scalar32_min_max_sdiv(struct bpf_reg_state *dst_reg,
				  struct bpf_reg_state *src_reg)
{
	s32 smin = reg_s32_min(dst_reg);
	s32 smax = reg_s32_max(dst_reg);
	s32 src_val = reg_s32_min(src_reg); /* non-zero, const divisor */
	s32 res1, res2;

	/* BPF div specification: S32_MIN / -1 = S32_MIN */
	if (smin == S32_MIN && src_val == -1) {
		/*
		 * If the dividend range contains more than just S32_MIN,
		 * we cannot precisely track the result, so it becomes unbounded.
		 * e.g., [S32_MIN, S32_MIN+10]/(-1),
		 *     = {S32_MIN} U [-(S32_MIN+10), -(S32_MIN+1)]
		 *     = {S32_MIN} U [S32_MAX-9, S32_MAX] = [S32_MIN, S32_MAX]
		 * Otherwise (if dividend is exactly S32_MIN), result remains S32_MIN.
		 */
		if (smax != S32_MIN) {
			smin = S32_MIN;
			smax = S32_MAX;
		}
		goto reset;
	}

	res1 = smin / src_val;
	res2 = smax / src_val;
	smin = min(res1, res2);
	smax = max(res1, res2);

reset:
	reg_set_srange32(dst_reg, smin, smax);
	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg64_and_tnum(dst_reg);
}

static void scalar_min_max_sdiv(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	s64 smin = reg_smin(dst_reg);
	s64 smax = reg_smax(dst_reg);
	s64 src_val = reg_smin(src_reg); /* non-zero, const divisor */
	s64 res1, res2;

	/* BPF div specification: S64_MIN / -1 = S64_MIN */
	if (smin == S64_MIN && src_val == -1) {
		/*
		 * If the dividend range contains more than just S64_MIN,
		 * we cannot precisely track the result, so it becomes unbounded.
		 * e.g., [S64_MIN, S64_MIN+10]/(-1),
		 *     = {S64_MIN} U [-(S64_MIN+10), -(S64_MIN+1)]
		 *     = {S64_MIN} U [S64_MAX-9, S64_MAX] = [S64_MIN, S64_MAX]
		 * Otherwise (if dividend is exactly S64_MIN), result remains S64_MIN.
		 */
		if (smax != S64_MIN) {
			smin = S64_MIN;
			smax = S64_MAX;
		}
		goto reset;
	}

	res1 = div64_s64(smin, src_val);
	res2 = div64_s64(smax, src_val);
	smin = min(res1, res2);
	smax = max(res1, res2);

reset:
	reg_set_srange64(dst_reg, smin, smax);
	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg32_and_tnum(dst_reg);
}

static void scalar32_min_max_umod(struct bpf_reg_state *dst_reg,
				  struct bpf_reg_state *src_reg)
{
	u32 src_val = reg_u32_min(src_reg); /* non-zero, const divisor */
	u32 res_max = src_val - 1;

	/*
	 * If dst_umax <= res_max, the result remains unchanged.
	 * e.g., [2, 5] % 10 = [2, 5].
	 */
	if (reg_u32_max(dst_reg) <= res_max)
		return;

	reg_set_urange32(dst_reg, 0, min(reg_u32_max(dst_reg), res_max));

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg64_and_tnum(dst_reg);
}

static void scalar_min_max_umod(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	u64 src_val = reg_umin(src_reg); /* non-zero, const divisor */
	u64 res_max = src_val - 1;

	/*
	 * If dst_umax <= res_max, the result remains unchanged.
	 * e.g., [2, 5] % 10 = [2, 5].
	 */
	if (reg_umax(dst_reg) <= res_max)
		return;

	reg_set_urange64(dst_reg, 0, min(reg_umax(dst_reg), res_max));

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg32_and_tnum(dst_reg);
}

static void scalar32_min_max_smod(struct bpf_reg_state *dst_reg,
				  struct bpf_reg_state *src_reg)
{
	s32 src_val = reg_s32_min(src_reg); /* non-zero, const divisor */

	/*
	 * Safe absolute value calculation:
	 * If src_val == S32_MIN (-2147483648), src_abs becomes 2147483648.
	 * Here use unsigned integer to avoid overflow.
	 */
	u32 src_abs = (src_val > 0) ? (u32)src_val : -(u32)src_val;

	/*
	 * Calculate the maximum possible absolute value of the result.
	 * Even if src_abs is 2147483648 (S32_MIN), subtracting 1 gives
	 * 2147483647 (S32_MAX), which fits perfectly in s32.
	 */
	s32 res_max_abs = src_abs - 1;

	/*
	 * If the dividend is already within the result range,
	 * the result remains unchanged. e.g., [-2, 5] % 10 = [-2, 5].
	 */
	if (reg_s32_min(dst_reg) >= -res_max_abs && reg_s32_max(dst_reg) <= res_max_abs)
		return;

	/* General case: result has the same sign as the dividend. */
	if (reg_s32_min(dst_reg) >= 0) {
		reg_set_srange32(dst_reg, 0, min(reg_s32_max(dst_reg), res_max_abs));
	} else if (reg_s32_max(dst_reg) <= 0) {
		reg_set_srange32(dst_reg, max(reg_s32_min(dst_reg), -res_max_abs), 0);
	} else {
		reg_set_srange32(dst_reg, -res_max_abs, res_max_abs);
	}

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg64_and_tnum(dst_reg);
}

static void scalar_min_max_smod(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	s64 src_val = reg_smin(src_reg); /* non-zero, const divisor */

	/*
	 * Safe absolute value calculation:
	 * If src_val == S64_MIN (-2^63), src_abs becomes 2^63.
	 * Here use unsigned integer to avoid overflow.
	 */
	u64 src_abs = (src_val > 0) ? (u64)src_val : -(u64)src_val;

	/*
	 * Calculate the maximum possible absolute value of the result.
	 * Even if src_abs is 2^63 (S64_MIN), subtracting 1 gives
	 * 2^63 - 1 (S64_MAX), which fits perfectly in s64.
	 */
	s64 res_max_abs = src_abs - 1;

	/*
	 * If the dividend is already within the result range,
	 * the result remains unchanged. e.g., [-2, 5] % 10 = [-2, 5].
	 */
	if (reg_smin(dst_reg) >= -res_max_abs && reg_smax(dst_reg) <= res_max_abs)
		return;

	/* General case: result has the same sign as the dividend. */
	if (reg_smin(dst_reg) >= 0) {
		reg_set_srange64(dst_reg, 0, min(reg_smax(dst_reg), res_max_abs));
	} else if (reg_smax(dst_reg) <= 0) {
		reg_set_srange64(dst_reg, max(reg_smin(dst_reg), -res_max_abs), 0);
	} else {
		reg_set_srange64(dst_reg, -res_max_abs, res_max_abs);
	}

	/* Reset other ranges/tnum to unbounded/unknown. */
	reset_reg32_and_tnum(dst_reg);
}

static void scalar32_min_max_and(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_subreg_is_const(src_reg->var_off);
	bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
	struct tnum var32_off = tnum_subreg(dst_reg->var_off);
	u32 umax_val = reg_u32_max(src_reg);

	if (src_known && dst_known) {
		__mark_reg32_known(dst_reg, var32_off.value);
		return;
	}

	/* We get our minimum from the var_off, since that's inherently
	 * bitwise.  Our maximum is the minimum of the operands' maxima.
	 */
	reg_set_urange32(dst_reg,
			 var32_off.value,
			 min(reg_u32_max(dst_reg), umax_val));
}

static void scalar_min_max_and(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_is_const(src_reg->var_off);
	bool dst_known = tnum_is_const(dst_reg->var_off);
	u64 umax_val = reg_umax(src_reg);

	if (src_known && dst_known) {
		__mark_reg_known(dst_reg, dst_reg->var_off.value);
		return;
	}

	/* We get our minimum from the var_off, since that's inherently
	 * bitwise.  Our maximum is the minimum of the operands' maxima.
	 */
	reg_set_urange64(dst_reg,
			 dst_reg->var_off.value,
			 min(reg_umax(dst_reg), umax_val));

	/* We may learn something more from the var_off */
	__update_reg_bounds(dst_reg);
}

static void scalar32_min_max_or(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_subreg_is_const(src_reg->var_off);
	bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
	struct tnum var32_off = tnum_subreg(dst_reg->var_off);
	u32 umin_val = reg_u32_min(src_reg);

	if (src_known && dst_known) {
		__mark_reg32_known(dst_reg, var32_off.value);
		return;
	}

	/* We get our maximum from the var_off, and our minimum is the
	 * maximum of the operands' minima
	 */
	reg_set_urange32(dst_reg,
			 max(reg_u32_min(dst_reg), umin_val),
			 var32_off.value | var32_off.mask);
}

static void scalar_min_max_or(struct bpf_reg_state *dst_reg,
			      struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_is_const(src_reg->var_off);
	bool dst_known = tnum_is_const(dst_reg->var_off);
	u64 umin_val = reg_umin(src_reg);

	if (src_known && dst_known) {
		__mark_reg_known(dst_reg, dst_reg->var_off.value);
		return;
	}

	/* We get our maximum from the var_off, and our minimum is the
	 * maximum of the operands' minima
	 */
	reg_set_urange64(dst_reg,
			 max(reg_umin(dst_reg), umin_val),
			 dst_reg->var_off.value | dst_reg->var_off.mask);

	/* We may learn something more from the var_off */
	__update_reg_bounds(dst_reg);
}

static void scalar32_min_max_xor(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_subreg_is_const(src_reg->var_off);
	bool dst_known = tnum_subreg_is_const(dst_reg->var_off);
	struct tnum var32_off = tnum_subreg(dst_reg->var_off);

	if (src_known && dst_known) {
		__mark_reg32_known(dst_reg, var32_off.value);
		return;
	}

	/* We get both minimum and maximum from the var32_off. */
	reg_set_urange32(dst_reg, var32_off.value, var32_off.value | var32_off.mask);
}

static void scalar_min_max_xor(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	bool src_known = tnum_is_const(src_reg->var_off);
	bool dst_known = tnum_is_const(dst_reg->var_off);

	if (src_known && dst_known) {
		/* dst_reg->var_off.value has been updated earlier */
		__mark_reg_known(dst_reg, dst_reg->var_off.value);
		return;
	}

	/* We get both minimum and maximum from the var_off. */
	reg_set_urange64(dst_reg,
			 dst_reg->var_off.value,
			 dst_reg->var_off.value | dst_reg->var_off.mask);
}

static void __scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
				   u64 umin_val, u64 umax_val)
{
	/* If we might shift our top bit out, then we know nothing */
	if (umax_val > 31 || reg_u32_max(dst_reg) > 1ULL << (31 - umax_val))
		reg_set_urange32(dst_reg, 0, U32_MAX);
	else
		/* We lose all sign bit information (except what we can pick
		 * up from var_off)
		 */
		reg_set_urange32(dst_reg, reg_u32_min(dst_reg) << umin_val,
				 reg_u32_max(dst_reg) << umax_val);
}

static void scalar32_min_max_lsh(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	u32 umax_val = reg_u32_max(src_reg);
	u32 umin_val = reg_u32_min(src_reg);
	/* u32 alu operation will zext upper bits */
	struct tnum subreg = tnum_subreg(dst_reg->var_off);

	__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);
	dst_reg->var_off = tnum_subreg(tnum_lshift(subreg, umin_val));
	/* Not required but being careful mark reg64 bounds as unknown so
	 * that we are forced to pick them up from tnum and zext later and
	 * if some path skips this step we are still safe.
	 */
	__mark_reg64_unbounded(dst_reg);
	__update_reg32_bounds(dst_reg);
}

static void __scalar64_min_max_lsh(struct bpf_reg_state *dst_reg,
				   u64 umin_val, u64 umax_val)
{
	struct cnum64 u, s;

	/* Special case <<32 because it is a common compiler pattern to sign
	 * extend subreg by doing <<32 s>>32. smin/smax assignments are correct
	 * because s32 bounds don't flip sign when shifting to the left by
	 * 32bits.
	 */
	if (umin_val == 32 && umax_val == 32)
		s = cnum64_from_srange((s64)reg_s32_min(dst_reg) << 32,
				       (s64)reg_s32_max(dst_reg) << 32);
	else
		s = CNUM64_UNBOUNDED;

	/* If we might shift our top bit out, then we know nothing */
	if (reg_umax(dst_reg) > 1ULL << (63 - umax_val))
		u = CNUM64_UNBOUNDED;
	else
		u = cnum64_from_urange(reg_umin(dst_reg) << umin_val,
				       reg_umax(dst_reg) << umax_val);

	dst_reg->r64 = cnum64_intersect(u, s);
}

static void scalar_min_max_lsh(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	u64 umax_val = reg_umax(src_reg);
	u64 umin_val = reg_umin(src_reg);

	/* scalar64 calc uses 32bit unshifted bounds so must be called first */
	__scalar64_min_max_lsh(dst_reg, umin_val, umax_val);
	__scalar32_min_max_lsh(dst_reg, umin_val, umax_val);

	dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val);
	/* We may learn something more from the var_off */
	__update_reg_bounds(dst_reg);
}

static void scalar32_min_max_rsh(struct bpf_reg_state *dst_reg,
				 struct bpf_reg_state *src_reg)
{
	struct tnum subreg = tnum_subreg(dst_reg->var_off);
	u32 umax_val = reg_u32_max(src_reg);
	u32 umin_val = reg_u32_min(src_reg);

	/* 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 bounds 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->var_off = tnum_rshift(subreg, umin_val);
	reg_set_urange32(dst_reg, reg_u32_min(dst_reg) >> umax_val,
			 reg_u32_max(dst_reg) >> umin_val);

	__mark_reg64_unbounded(dst_reg);
	__update_reg32_bounds(dst_reg);
}

static void scalar_min_max_rsh(struct bpf_reg_state *dst_reg,
			       struct bpf_reg_state *src_reg)
{
	u64 umax_val = reg_umax(src_reg);
	u64 umin_val = reg_umin(src_reg);

	/* 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 bounds 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->var_off = tnum_rshift(dst_reg->var_off, umin_val);
	reg_set_urange64(dst_reg, reg_umin(dst_reg) >> umax_val,
			 reg_umax(dst_reg) >> umin_val);

	/* Its not easy to operate on alu32 bounds here because it depends
	 * on bits being shifted in. Take easy way out and mark unbounded
	 * so we can recalculate later from tnum.
	 */
	__mark_reg32_unbounded(dst_reg);
	__update_reg_bounds(dst_reg);
}

static void scalar32_min_max_arsh(struct bpf_reg_state *dst_reg,
				  struct bpf_reg_state *src_reg)
{
	u64 umin_val = reg_u32_min(src_reg);

	/* Upon reaching here, src_known is true and
	 * umax_val is equal to umin_val.
	 * Blow away the dst_reg umin_value/umax_value and rely on
	 * dst_reg var_off to refine the result.
	 */
	reg_set_srange32(dst_reg,
			 (u32)(((s32)reg_s32_min(dst_reg)) >> umin_val),
			 (u32)(((s32)reg_s32_max(dst_reg)) >> umin_val));

	dst_reg->var_off = tnum_arshift(tnum_subreg(dst_reg->var_off), umin_val, 32);

	__mark_reg64_unbounded(dst_reg);
	__update_reg32_bounds(dst_reg);
}

static void scalar_min_max_arsh(struct bpf_reg_state *dst_reg,
				struct bpf_reg_state *src_reg)
{
	u64 umin_val = reg_umin(src_reg);

	/* Upon reaching here, src_known is true and umax_val is equal
	 * to umin_val.
	 */
	reg_set_srange64(dst_reg, reg_smin(dst_reg) >> umin_val,
			 reg_smax(dst_reg) >> umin_val);

	dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val, 64);

	/* Its not easy to operate on alu32 bounds here because it depends
	 * on bits being shifted in from upper 32-bits. Take easy way out
	 * and mark unbounded so we can recalculate later from tnum.
	 */
	__mark_reg32_unbounded(dst_reg);
	__update_reg_bounds(dst_reg);
}

static void scalar_byte_swap(struct bpf_reg_state *dst_reg, struct bpf_insn *insn)
{
	/*
	 * Byte swap operation - update var_off using tnum_bswap.
	 * Three cases:
	 * 1. bswap(16|32|64): opcode=0xd7 (BPF_END | BPF_ALU64 | BPF_TO_LE)
	 *    unconditional swap
	 * 2. to_le(16|32|64): opcode=0xd4 (BPF_END | BPF_ALU | BPF_TO_LE)
	 *    swap on big-endian, truncation or no-op on little-endian
	 * 3. to_be(16|32|64): opcode=0xdc (BPF_END | BPF_ALU | BPF_TO_BE)
	 *    swap on little-endian, truncation or no-op on big-endian
	 */

	bool alu64 = BPF_CLASS(insn->code) == BPF_ALU64;
	bool to_le = BPF_SRC(insn->code) == BPF_TO_LE;
	bool is_big_endian;
#ifdef CONFIG_CPU_BIG_ENDIAN
	is_big_endian = true;
#else
	is_big_endian = false;
#endif
	/* Apply bswap if alu64 or switch between big-endian and little-endian machines */
	bool need_bswap = alu64 || (to_le == is_big_endian);

	/*
	 * If the register is mutated, manually reset its scalar ID to break
	 * any existing ties and avoid incorrect bounds propagation.
	 */
	if (need_bswap || insn->imm == 16 || insn->imm == 32)
		clear_scalar_id(dst_reg);

	if (need_bswap) {
		if (insn->imm == 16)
			dst_reg->var_off = tnum_bswap16(dst_reg->var_off);
		else if (insn->imm == 32)
			dst_reg->var_off = tnum_bswap32(dst_reg->var_off);
		else if (insn->imm == 64)
			dst_reg->var_off = tnum_bswap64(dst_reg->var_off);
		/*
		 * Byteswap scrambles the range, so we must reset bounds.
		 * Bounds will be re-derived from the new tnum later.
		 */
		__mark_reg_unbounded(dst_reg);
		reg_step_reset(dst_reg);
	}
	/* For bswap16/32, truncate dst register to match the swapped size */
	if (insn->imm == 16 || insn->imm == 32)
		coerce_reg_to_size(dst_reg, insn->imm / 8);
}

static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn,
					     const struct bpf_reg_state *src_reg)
{
	bool src_is_const = false;
	u64 insn_bitness = (BPF_CLASS(insn->code) == BPF_ALU64) ? 64 : 32;

	if (insn_bitness == 32) {
		if (tnum_subreg_is_const(src_reg->var_off)
		    && reg_s32_min(src_reg) == reg_s32_max(src_reg)
		    && reg_u32_min(src_reg) == reg_u32_max(src_reg))
			src_is_const = true;
	} else {
		if (tnum_is_const(src_reg->var_off)
		    && reg_smin(src_reg) == reg_smax(src_reg)
		    && reg_umin(src_reg) == reg_umax(src_reg))
			src_is_const = true;
	}

	switch (BPF_OP(insn->code)) {
	case BPF_ADD:
	case BPF_SUB:
	case BPF_NEG:
	case BPF_AND:
	case BPF_XOR:
	case BPF_OR:
	case BPF_MUL:
	case BPF_END:
		return true;

	/*
	 * Division and modulo operators range is only safe to compute when the
	 * divisor is a constant.
	 */
	case BPF_DIV:
	case BPF_MOD:
		return src_is_const;

	/* Shift operators range is only computable if shift dimension operand
	 * is a constant. Shifts greater than 31 or 63 are undefined. This
	 * includes shifts by a negative number.
	 */
	case BPF_LSH:
	case BPF_RSH:
	case BPF_ARSH:
		return (src_is_const && reg_umax(src_reg) < insn_bitness);
	default:
		return false;
	}
}

static int maybe_fork_scalars(struct bpf_verifier_env *env, struct bpf_insn *insn,
			      struct bpf_reg_state *dst_reg)
{
	struct bpf_verifier_state *branch;
	struct bpf_reg_state *regs;
	bool alu32;

	if (reg_smin(dst_reg) == -1 && reg_smax(dst_reg) == 0)
		alu32 = false;
	else if (reg_s32_min(dst_reg) == -1 && reg_s32_max(dst_reg) == 0)
		alu32 = true;
	else
		return 0;

	branch = push_stack(env, env->insn_idx, env->insn_idx, false);
	if (IS_ERR(branch))
		return PTR_ERR(branch);

	regs = branch->frame[branch->curframe]->regs;
	if (alu32) {
		__mark_reg32_known(&regs[insn->dst_reg], 0);
		__mark_reg32_known(dst_reg, -1ull);
	} else {
		__mark_reg_known(&regs[insn->dst_reg], 0);
		__mark_reg_known(dst_reg, -1ull);
	}
	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)
{
	u8 opcode = BPF_OP(insn->code);
	s16 off = insn->off;
	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
	int ret;

	if (!is_safe_to_compute_dst_reg_range(insn, &src_reg)) {
		__mark_reg_unknown(env, dst_reg);
		return 0;
	}

	if (sanitize_needed(opcode)) {
		ret = sanitize_val_alu(env, insn);
		if (ret < 0)
			return sanitize_err(env, insn, ret);
	}

	/* Calculate sign/unsigned bounds and tnum for alu32 and alu64 bit ops.
	 * There are two classes of instructions: The first class we track both
	 * alu32 and alu64 sign/unsigned bounds independently this provides the
	 * greatest amount of precision when alu operations are mixed with jmp32
	 * operations. These operations are BPF_ADD, BPF_SUB, BPF_MUL, BPF_ADD,
	 * and BPF_OR. This is possible because these ops have fairly easy to
	 * understand and calculate behavior in both 32-bit and 64-bit alu ops.
	 * See alu32 verifier tests for examples. The second class of
	 * operations, BPF_LSH, BPF_RSH, and BPF_ARSH, however are not so easy
	 * with regards to tracking sign/unsigned bounds because the bits may
	 * cross subreg boundaries in the alu64 case. When this happens we mark
	 * the reg unbounded in the subreg bound space and use the resulting
	 * tnum to calculate an approximation of the sign/unsigned bounds.
	 */
	switch (opcode) {
	case BPF_ADD:
		scalar_step_add(dst_reg, dst_reg, &src_reg);
		scalar32_min_max_add(dst_reg, &src_reg);
		scalar_min_max_add(dst_reg, &src_reg);
		dst_reg->var_off = tnum_add(dst_reg->var_off, src_reg.var_off);
		break;
	case BPF_SUB:
		scalar32_min_max_sub(dst_reg, &src_reg);
		scalar_min_max_sub(dst_reg, &src_reg);
		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
		reg_step_reset(dst_reg);
		break;
	case BPF_NEG:
		env->fake_reg[0] = *dst_reg;
		__mark_reg_known(dst_reg, 0);
		scalar32_min_max_sub(dst_reg, &env->fake_reg[0]);
		scalar_min_max_sub(dst_reg, &env->fake_reg[0]);
		dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off);
		reg_step_reset(dst_reg);
		break;
	case BPF_MUL:
		scalar_step_mul(dst_reg, &src_reg);
		dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
		scalar32_min_max_mul(dst_reg, &src_reg);
		scalar_min_max_mul(dst_reg, &src_reg);
		break;
	case BPF_DIV:
		/* BPF div specification: x / 0 = 0 */
		if ((alu32 && reg_u32_min(&src_reg) == 0) || (!alu32 && reg_umin(&src_reg) == 0)) {
			___mark_reg_known(dst_reg, 0);
			break;
		}
		if (alu32)
			if (off == 1)
				scalar32_min_max_sdiv(dst_reg, &src_reg);
			else
				scalar32_min_max_udiv(dst_reg, &src_reg);
		else
			if (off == 1)
				scalar_min_max_sdiv(dst_reg, &src_reg);
			else
				scalar_min_max_udiv(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_MOD:
		/* BPF mod specification: x % 0 = x */
		if ((alu32 && reg_u32_min(&src_reg) == 0) || (!alu32 && reg_umin(&src_reg) == 0))
			break;
		if (alu32)
			if (off == 1)
				scalar32_min_max_smod(dst_reg, &src_reg);
			else
				scalar32_min_max_umod(dst_reg, &src_reg);
		else
			if (off == 1)
				scalar_min_max_smod(dst_reg, &src_reg);
			else
				scalar_min_max_umod(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_AND:
		if (tnum_is_const(src_reg.var_off)) {
			ret = maybe_fork_scalars(env, insn, dst_reg);
			if (ret)
				return ret;
		}
		dst_reg->var_off = tnum_and(dst_reg->var_off, src_reg.var_off);
		scalar32_min_max_and(dst_reg, &src_reg);
		scalar_min_max_and(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_OR:
		if (tnum_is_const(src_reg.var_off)) {
			ret = maybe_fork_scalars(env, insn, dst_reg);
			if (ret)
				return ret;
		}
		dst_reg->var_off = tnum_or(dst_reg->var_off, src_reg.var_off);
		scalar32_min_max_or(dst_reg, &src_reg);
		scalar_min_max_or(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_XOR:
		dst_reg->var_off = tnum_xor(dst_reg->var_off, src_reg.var_off);
		scalar32_min_max_xor(dst_reg, &src_reg);
		scalar_min_max_xor(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_LSH:
		scalar_step_lsh(dst_reg, &src_reg);
		if (alu32)
			scalar32_min_max_lsh(dst_reg, &src_reg);
		else
			scalar_min_max_lsh(dst_reg, &src_reg);
		break;
	case BPF_RSH:
		if (alu32)
			scalar32_min_max_rsh(dst_reg, &src_reg);
		else
			scalar_min_max_rsh(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_ARSH:
		if (alu32)
			scalar32_min_max_arsh(dst_reg, &src_reg);
		else
			scalar_min_max_arsh(dst_reg, &src_reg);
		reg_step_reset(dst_reg);
		break;
	case BPF_END:
		scalar_byte_swap(dst_reg, insn);
		reg_step_reset(dst_reg);
		break;
	default:
		break;
	}

	/*
	 * ALU32 ops are zero extended into 64bit register.
	 *
	 * BPF_END is already handled inside the helper (truncation),
	 * so skip zext here to avoid unexpected zero extension.
	 * e.g., le64: opcode=(BPF_END|BPF_ALU|BPF_TO_LE), imm=0x40
	 * This is a 64bit byte swap operation with alu32==true,
	 * but we should not zero extend the result.
	 */
	if (alu32 && opcode != BPF_END)
		zext_32_to_64(dst_reg);
	reg_bounds_sync(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};
	bool alu32 = (BPF_CLASS(insn->code) != BPF_ALU64);
	struct bpf_insn_aux_data *aux = cur_aux(env);
	u8 opcode = BPF_OP(insn->code);
	int err;

	dst_reg = &regs[insn->dst_reg];
	if (BPF_SRC(insn->code) == BPF_X)
		src_reg = &regs[insn->src_reg];
	else
		src_reg = NULL;

	/* Case where at least one operand is an arena. */
	if (dst_reg->type == PTR_TO_ARENA || (src_reg && src_reg->type == PTR_TO_ARENA)) {

		if (dst_reg->type != PTR_TO_ARENA)
			*dst_reg = *src_reg;

		if (BPF_CLASS(insn->code) == BPF_ALU64) {
			/*
			 * Only arena pointers set needs_zext, but doing so
			 * modifies the instruction at fixup time to an ALU32
			 * and makes it unsuitable for 64-bit scalar args. We
			 * prevent zext from being set if the instruction has
			 * been previously called with non-arena registers.
			 */
			if (aux->prevent_zext) {
				verbose(env, "same insn cannot be used with and without arena pointer\n");
				return -EINVAL;
			}

			/*
			 * 32-bit operations zero upper bits automatically.
			 * 64-bit operations need to be converted to 32.
			 */
			aux->needs_zext = true;
			aux->zext_dst = true;
		}

		/* Any arithmetic operations are allowed on arena pointers */
		return 0;
	}

	/* Prevent the instruction from being used with arena pointers (see above). */
	if (env->prog->aux->arena && BPF_CLASS(insn->code) == BPF_ALU64) {
		if (aux->needs_zext) {
			verbose(env, "same insn cannot be used with and without arena pointer\n");
			return -EINVAL;
		}

		aux->prevent_zext = true;
	}

	if (dst_reg->type != SCALAR_VALUE)
		ptr_reg = dst_reg;

	if (BPF_SRC(insn->code) == BPF_X) {
		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 && env->allow_ptr_leaks) {
					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
				 */
				err = mark_chain_precision(env, insn->dst_reg);
				if (err)
					return err;
				off_reg = *dst_reg;
				return adjust_ptr_min_max_vals(env, insn, insn->src_reg, src_reg,
							       &off_reg);
			}
		} else if (ptr_reg) {
			/* pointer += scalar */
			err = mark_chain_precision(env, insn->src_reg);
			if (err)
				return err;
			return adjust_ptr_min_max_vals(env, insn, insn->dst_reg, dst_reg, src_reg);
		} else if (dst_reg->precise) {
			/* if dst_reg is precise, src_reg should be precise as well */
			err = mark_chain_precision(env, insn->src_reg);
			if (err)
				return err;
		}
	} else {
		/* Pretend the src is a reg with a known value, since we only
		 * 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, insn->dst_reg, ptr_reg, src_reg);
	}

	/* Got here implies adding two SCALAR_VALUEs */
	if (WARN_ON_ONCE(ptr_reg)) {
		print_verifier_state(env, vstate, vstate->curframe, true);
		verbose(env, "verifier internal error: unexpected ptr_reg\n");
		return -EFAULT;
	}
	if (WARN_ON(!src_reg)) {
		print_verifier_state(env, vstate, vstate->curframe, true);
		verbose(env, "verifier internal error: no src_reg\n");
		return -EFAULT;
	}
	/*
	 * For alu32 linked register tracking, we need to check dst_reg's
	 * umax_value before the ALU operation. After adjust_scalar_min_max_vals(),
	 * alu32 ops will have zero-extended the result, making umax_value <= U32_MAX.
	 */
	u64 dst_umax = reg_umax(dst_reg);

	err = adjust_scalar_min_max_vals(env, insn, dst_reg, *src_reg);
	if (err)
		return err;
	/*
	 * Compilers can generate the code
	 * r1 = r2
	 * r1 += 0x1
	 * if r2 < 1000 goto ...
	 * use r1 in memory access
	 * So remember constant delta between r2 and r1 and update r1 after
	 * 'if' condition.
	 */
	if (env->bpf_capable &&
	    (BPF_OP(insn->code) == BPF_ADD || BPF_OP(insn->code) == BPF_SUB) &&
	    dst_reg->id && is_reg_const(src_reg, alu32) &&
	    !(BPF_SRC(insn->code) == BPF_X && insn->src_reg == insn->dst_reg)) {
		u64 val = reg_const_value(src_reg, alu32);
		s32 off;

		if (!alu32 && ((s64)val < S32_MIN || (s64)val > S32_MAX))
			goto clear_id;

		if (alu32 && (dst_umax > U32_MAX))
			goto clear_id;

		off = (s32)val;

		if (BPF_OP(insn->code) == BPF_SUB) {
			/* Negating S32_MIN would overflow */
			if (off == S32_MIN)
				goto clear_id;
			off = -off;
		}

		if (dst_reg->id & BPF_ADD_CONST) {
			/*
			 * If the register already went through rX += val
			 * we cannot accumulate another val into rx->off.
			 */
clear_id:
			clear_scalar_id(dst_reg);
		} else {
			if (alu32)
				dst_reg->id |= BPF_ADD_CONST32;
			else
				dst_reg->id |= BPF_ADD_CONST64;
			dst_reg->delta = off;
		}
	} else {
		/*
		 * Make sure ID is cleared otherwise dst_reg min/max could be
		 * incorrectly propagated into other registers by sync_linked_regs()
		 */
		clear_scalar_id(dst_reg);
	}
	return 0;
}

/*
 * Many checks done by this function are quite conservative.
 * This is because main verification pass does not maintain
 * enough information to track object identities for some
 * of the interesting types, e.g. PTR_TO_MEM.
 */
bool bpf_same_memory_origin(const struct bpf_reg_state *reg_a,
			    const struct bpf_reg_state *reg_b)
{
	if (reg_a == reg_b)
		return true;
	/* Require matching flags and base types. */
	if (reg_a->type != reg_b->type)
		return false;
	/* NULL can't be compared to some base+offset pointer. */
	if (type_may_be_null(reg_a->type))
		return false;

	switch (base_type(reg_a->type)) {
	case PTR_TO_STACK:
		return reg_a->frameno == reg_b->frameno;
	case PTR_TO_MAP_VALUE:
		if (reg_a->map_ptr != reg_b->map_ptr || reg_a->map_uid != reg_b->map_uid)
			return false;
		if (reg_a->id && reg_a->id == reg_b->id)
			return true;
		/*
		 * A plain single-element array has one stable value address,
		 * but not when BPF_F_INNER_MAP is set, see arraymap.c:array_map_meta_equal().
		 */
		if (reg_a->map_ptr->map_type == BPF_MAP_TYPE_ARRAY &&
		    reg_a->map_ptr->max_entries == 1 &&
		    !(reg_a->map_ptr->map_flags & BPF_F_INNER_MAP))
			return true;
		/*
		 * The rules above can be simplified / relaxed if:
		 * - fresh IDs would always be assigned for map-value lookups;
		 * - direct map value loads would always have and ID of zero.
		 */
		return false;
	case PTR_TO_MEM:
	case PTR_TO_BUF:
		return reg_a->id && reg_a->id == reg_b->id;

	default:
		return false;
	}
}

int bpf_set_reg_range(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
		      struct cnum64 r64, struct cnum32 r32, u16 base, u16 step)
{
	reg->r64 = r64;
	reg->r32 = r32;
	reg->step = step;
	reg->base = base;
	reg->var_off = tnum_unknown;
	reg_bounds_sync(reg); /* this should infer the tnum alignment */
	return reg_bounds_sanity_check(env, reg, "bpf_set_reg_range");
}

/*
 * Checks if pointer and packet metadata matches between two registers.
 * For use with bpf_reg_union().
 */
bool bpf_reg_union_compatible(const struct bpf_reg_state *a, const struct bpf_reg_state *b)
{
	if (a->type != b->type)
		return false;
	if (a->type == SCALAR_VALUE)
		return true;
	return !memcmp(a, b, offsetof(struct bpf_reg_state, var_off)) &&
	       a->id == b->id && a->parent_id == b->parent_id && a->map_uid == b->map_uid;
}

/*
 * Extends acc's scalar range to include src's scalar range.
 * Caller must ensure that other kinds of metadata is compatible.
 * Caller must clear acc's scalar ID.
 */
int bpf_reg_union(struct bpf_verifier_env *env, struct bpf_reg_state *acc,
		  const struct bpf_reg_state *src)
{
	u16 base, step;

	if (!bpf_reg_union_compatible(acc, src)) {
		verifier_bug(env, "union of incompatible registers");
		return -EFAULT;
	}
	acc->r64 = cnum64_union(acc->r64, src->r64);
	acc->r32 = cnum32_union(acc->r32, src->r32);
	acc->var_off = tnum_union(acc->var_off, src->var_off);

	/* Retain a common congruence if the bases agree modulo the gcd. */
	step = gcd(acc->step, src->step);
	base = acc->base % step;
	if (base != src->base % step) {
		reg_step_reset(acc);
	} else {
		acc->base = base;
		acc->step = step;
	}
	reg_bounds_sync(acc);
	return reg_bounds_sanity_check(env, acc, "bpf_reg_union");
}

/* 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;

	bpf_diag_mod_begin(env, &regs[insn->dst_reg], NULL, BPF_DIAG_MOD_WRITE);

	if (opcode == BPF_END || opcode == BPF_NEG) {
		/* 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 */
		if (regs[insn->dst_reg].type == SCALAR_VALUE) {
			err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
			err = err ?: adjust_scalar_min_max_vals(env, insn,
							 &regs[insn->dst_reg],
							 regs[insn->dst_reg]);
		} else {
			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->off == BPF_ADDR_SPACE_CAST) {
				if (!env->prog->aux->arena) {
					verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n");
					return -EINVAL;
				}
			}

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

		/* check dest operand, mark as required later */
		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
		if (err)
			return err;

		if (BPF_SRC(insn->code) == BPF_X) {
			struct bpf_reg_state *src_reg = regs + insn->src_reg;
			struct bpf_reg_state *dst_reg = regs + insn->dst_reg;

			if (BPF_CLASS(insn->code) == BPF_ALU64) {
				if (insn->imm) {
					/* off == BPF_ADDR_SPACE_CAST */
					mark_reg_unknown(env, regs, insn->dst_reg);
					if (insn->imm == 1) /* cast from as(1) to as(0) */
						dst_reg->type = PTR_TO_ARENA;
				} else if (insn->off == 0) {
					/* case: R1 = R2
					 * copy register state to dest reg
					 */
					assign_scalar_id_before_mov(env, src_reg);
					*dst_reg = *src_reg;
				} else {
					/* case: R1 = (s8, s16 s32)R2 */
					if (is_pointer_value(env, insn->src_reg)) {
						verbose(env,
							"R%d sign-extension part of pointer\n",
							insn->src_reg);
						return -EACCES;
					} else if (src_reg->type == SCALAR_VALUE) {
						bool no_sext;

						no_sext = reg_umax(src_reg) < (1ULL << (insn->off - 1));
						if (no_sext)
							assign_scalar_id_before_mov(env, src_reg);
						*dst_reg = *src_reg;
						if (!no_sext)
							clear_scalar_id(dst_reg);
						coerce_reg_to_size_sx(dst_reg, insn->off >> 3);
					} else {
						mark_reg_unknown(env, regs, insn->dst_reg);
					}
				}
			} 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;
				} else if (src_reg->type == SCALAR_VALUE) {
					if (insn->off == 0) {
						bool is_src_reg_u32 = get_reg_width(src_reg) <= 32;

						if (is_src_reg_u32)
							assign_scalar_id_before_mov(env, src_reg);
						*dst_reg = *src_reg;
						/* Make sure ID is cleared if src_reg is not in u32
						 * range otherwise dst_reg min/max could be incorrectly
						 * propagated into src_reg by sync_linked_regs()
						 */
						if (!is_src_reg_u32)
							clear_scalar_id(dst_reg);
					} else {
						/* case: W1 = (s8, s16)W2 */
						bool no_sext = reg_umax(src_reg) < (1ULL << (insn->off - 1));

						if (no_sext)
							assign_scalar_id_before_mov(env, src_reg);
						*dst_reg = *src_reg;
						if (!no_sext)
							clear_scalar_id(dst_reg);
						coerce_subreg_to_size_sx(dst_reg, insn->off >> 3);
					}
				} else {
					mark_reg_unknown(env, regs,
							 insn->dst_reg);
				}
				zext_32_to_64(dst_reg);
				reg_bounds_sync(dst_reg);
			}
		} else {
			/* case: R = imm
			 * remember the value we stored into this reg
			 */
			/* clear any state __mark_reg_known doesn't set */
			mark_reg_unknown(env, regs, insn->dst_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 {	/* all other ALU ops: and, sub, xor, add, ... */

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

		if ((opcode == BPF_LSH || opcode == BPF_RSH ||
		     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
			int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;

			if (insn->imm < 0 || insn->imm >= size) {
				verbose(env, "invalid shift %d\n", insn->imm);
				return -EINVAL;
			}
		}

		/* check dest operand */
		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
		err = err ?: adjust_reg_min_max_vals(env, insn);
		if (err)
			return err;
	}

	err = reg_bounds_sanity_check(env, &regs[insn->dst_reg], "alu");
	if (err)
		return err;

	bpf_diag_mod_end(env);
	return 0;
}

static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
				   struct bpf_reg_state *dst_reg,
				   enum bpf_reg_type type,
				   bool range_right_open)
{
	struct bpf_func_state *state;
	struct bpf_reg_state *reg;
	int new_range;

	if (reg_umax(dst_reg) == 0 && range_right_open)
		/* This doesn't give us any range */
		return;

	if (reg_umax(dst_reg) > MAX_PACKET_OFF)
		/* Risk of overflow.  For instance, ptr + (1<<63) may be less
		 * than pkt_end, but that's because it's also less than pkt.
		 */
		return;

	new_range = reg_umax(dst_reg);
	if (range_right_open)
		new_range++;

	/* Examples for register markings:
	 *
	 * pkt_data in dst register:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (r2 > pkt_end) goto <handle exception>
	 *   <access okay>
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (r2 < pkt_end) goto <access okay>
	 *   <handle exception>
	 *
	 *   Where:
	 *     r2 == dst_reg, pkt_end == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * pkt_data in src register:
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (pkt_end >= r2) goto <access okay>
	 *   <handle exception>
	 *
	 *   r2 = r3;
	 *   r2 += 8;
	 *   if (pkt_end <= r2) goto <handle exception>
	 *   <access okay>
	 *
	 *   Where:
	 *     pkt_end == dst_reg, r2 == src_reg
	 *     r2=pkt(id=n,off=8,r=0)
	 *     r3=pkt(id=n,off=0,r=0)
	 *
	 * Find register r3 and mark its range as r3=pkt(id=n,off=0,r=8)
	 * or r3=pkt(id=n,off=0,r=8-1), so that range of bytes [r3, r3 + 8)
	 * and [r3, r3 + 8-1) respectively is safe to access depending on
	 * the check.
	 */

	/* If our ids match, then we must have the same max_value.  And we
	 * don't care about the other reg's fixed offset, since if it's too big
	 * the range won't allow anything.
	 * reg_umax(dst_reg) is known < MAX_PACKET_OFF, therefore it fits in a u16.
	 */
	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
		if (reg->type == type && reg->id == dst_reg->id)
			/* keep the maximum range already checked */
			reg->range = max(reg->range, new_range);
	}));
}

static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
				u8 opcode, bool is_jmp32);
/*
 * Learn more information about live branches by simulating refinement on both branches.
 * regs_refine_cond_op() is sound, so producing ill-formed register bounds for the branch means
 * that branch is dead.
 */
static int simulate_both_branches_taken(struct bpf_verifier_env *env, u8 opcode, bool is_jmp32)
{
	/* Fallthrough (FALSE) branch */
	regs_refine_cond_op(&env->false_reg1, &env->false_reg2, bpf_rev_opcode(opcode), is_jmp32);
	reg_bounds_sync(&env->false_reg1);
	reg_bounds_sync(&env->false_reg2);
	/*
	 * If there is a range bounds violation in *any* of the abstract values in either
	 * reg_states in the FALSE branch (i.e. reg1, reg2), the FALSE branch must be dead. Only
	 * TRUE branch will be taken.
	 */
	if (range_bounds_violation(&env->false_reg1) || range_bounds_violation(&env->false_reg2))
		return 1;

	/* Jump (TRUE) branch */
	regs_refine_cond_op(&env->true_reg1, &env->true_reg2, opcode, is_jmp32);
	reg_bounds_sync(&env->true_reg1);
	reg_bounds_sync(&env->true_reg2);
	/*
	 * If there is a range bounds violation in *any* of the abstract values in either
	 * reg_states in the TRUE branch (i.e. true_reg1, true_reg2), the TRUE branch must be dead.
	 * Only FALSE branch will be taken.
	 */
	if (range_bounds_violation(&env->true_reg1) || range_bounds_violation(&env->true_reg2))
		return 0;

	/* Both branches are possible, we can't determine which one will be taken. */
	return -1;
}

/*
 * <reg1> <op> <reg2>, currently assuming reg2 is a constant
 */
static int is_scalar_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *reg1,
				  struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32)
{
	struct tnum t1 = is_jmp32 ? tnum_subreg(reg1->var_off) : reg1->var_off;
	struct tnum t2 = is_jmp32 ? tnum_subreg(reg2->var_off) : reg2->var_off;
	u64 umin1 = is_jmp32 ? (u64)reg_u32_min(reg1) : reg_umin(reg1);
	u64 umax1 = is_jmp32 ? (u64)reg_u32_max(reg1) : reg_umax(reg1);
	s64 smin1 = is_jmp32 ? (s64)reg_s32_min(reg1) : reg_smin(reg1);
	s64 smax1 = is_jmp32 ? (s64)reg_s32_max(reg1) : reg_smax(reg1);
	u64 umin2 = is_jmp32 ? (u64)reg_u32_min(reg2) : reg_umin(reg2);
	u64 umax2 = is_jmp32 ? (u64)reg_u32_max(reg2) : reg_umax(reg2);
	s64 smin2 = is_jmp32 ? (s64)reg_s32_min(reg2) : reg_smin(reg2);
	s64 smax2 = is_jmp32 ? (s64)reg_s32_max(reg2) : reg_smax(reg2);

	if (reg1 == reg2) {
		switch (opcode) {
		case BPF_JGE:
		case BPF_JLE:
		case BPF_JSGE:
		case BPF_JSLE:
		case BPF_JEQ:
			return 1;
		case BPF_JGT:
		case BPF_JLT:
		case BPF_JSGT:
		case BPF_JSLT:
		case BPF_JNE:
			return 0;
		case BPF_JSET:
			if (tnum_is_const(t1))
				return t1.value != 0;
			else
				return (smin1 <= 0 && smax1 >= 0) ? -1 : 1;
		default:
			return -1;
		}
	}

	switch (opcode) {
	case BPF_JEQ:
		/* constants, umin/umax and smin/smax checks would be
		 * redundant in this case because they all should match
		 */
		if (tnum_is_const(t1) && tnum_is_const(t2))
			return t1.value == t2.value;
		if (!tnum_overlap(t1, t2))
			return 0;
		/* non-overlapping ranges */
		if (umin1 > umax2 || umax1 < umin2)
			return 0;
		if (smin1 > smax2 || smax1 < smin2)
			return 0;
		if (!is_jmp32) {
			/* if 64-bit ranges are inconclusive, see if we can
			 * utilize 32-bit subrange knowledge to eliminate
			 * branches that can't be taken a priori
			 */
			if (reg_u32_min(reg1) > reg_u32_max(reg2) ||
			    reg_u32_max(reg1) < reg_u32_min(reg2))
				return 0;
			if (reg_s32_min(reg1) > reg_s32_max(reg2) ||
			    reg_s32_max(reg1) < reg_s32_min(reg2))
				return 0;
		}
		break;
	case BPF_JNE:
		/* constants, umin/umax and smin/smax checks would be
		 * redundant in this case because they all should match
		 */
		if (tnum_is_const(t1) && tnum_is_const(t2))
			return t1.value != t2.value;
		if (!tnum_overlap(t1, t2))
			return 1;
		/* non-overlapping ranges */
		if (umin1 > umax2 || umax1 < umin2)
			return 1;
		if (smin1 > smax2 || smax1 < smin2)
			return 1;
		if (!is_jmp32) {
			/* if 64-bit ranges are inconclusive, see if we can
			 * utilize 32-bit subrange knowledge to eliminate
			 * branches that can't be taken a priori
			 */
			if (reg_u32_min(reg1) > reg_u32_max(reg2) ||
			    reg_u32_max(reg1) < reg_u32_min(reg2))
				return 1;
			if (reg_s32_min(reg1) > reg_s32_max(reg2) ||
			    reg_s32_max(reg1) < reg_s32_min(reg2))
				return 1;
		}
		break;
	case BPF_JSET:
		if (!is_reg_const(reg2, is_jmp32)) {
			swap(reg1, reg2);
			swap(t1, t2);
		}
		if (!is_reg_const(reg2, is_jmp32))
			return -1;
		if ((~t1.mask & t1.value) & t2.value)
			return 1;
		if (!((t1.mask | t1.value) & t2.value))
			return 0;
		break;
	case BPF_JGT:
		if (umin1 > umax2)
			return 1;
		else if (umax1 <= umin2)
			return 0;
		break;
	case BPF_JSGT:
		if (smin1 > smax2)
			return 1;
		else if (smax1 <= smin2)
			return 0;
		break;
	case BPF_JLT:
		if (umax1 < umin2)
			return 1;
		else if (umin1 >= umax2)
			return 0;
		break;
	case BPF_JSLT:
		if (smax1 < smin2)
			return 1;
		else if (smin1 >= smax2)
			return 0;
		break;
	case BPF_JGE:
		if (umin1 >= umax2)
			return 1;
		else if (umax1 < umin2)
			return 0;
		break;
	case BPF_JSGE:
		if (smin1 >= smax2)
			return 1;
		else if (smax1 < smin2)
			return 0;
		break;
	case BPF_JLE:
		if (umax1 <= umin2)
			return 1;
		else if (umin1 > umax2)
			return 0;
		break;
	case BPF_JSLE:
		if (smax1 <= smin2)
			return 1;
		else if (smin1 > smax2)
			return 0;
		break;
	}

	return simulate_both_branches_taken(env, opcode, is_jmp32);
}

int bpf_flip_opcode(u32 opcode)
{
	/* How can we transform "a <op> b" into "b <op> a"? */
	static const u8 opcode_flip[16] = {
		/* these stay the same */
		[BPF_JEQ  >> 4] = BPF_JEQ,
		[BPF_JNE  >> 4] = BPF_JNE,
		[BPF_JSET >> 4] = BPF_JSET,
		/* these swap "lesser" and "greater" (L and G in the opcodes) */
		[BPF_JGE  >> 4] = BPF_JLE,
		[BPF_JGT  >> 4] = BPF_JLT,
		[BPF_JLE  >> 4] = BPF_JGE,
		[BPF_JLT  >> 4] = BPF_JGT,
		[BPF_JSGE >> 4] = BPF_JSLE,
		[BPF_JSGT >> 4] = BPF_JSLT,
		[BPF_JSLE >> 4] = BPF_JSGE,
		[BPF_JSLT >> 4] = BPF_JSGT
	};
	return opcode_flip[opcode >> 4];
}

static int is_pkt_ptr_branch_taken(struct bpf_reg_state *dst_reg,
				   struct bpf_reg_state *src_reg,
				   u8 opcode)
{
	struct bpf_reg_state *pkt;

	if (src_reg->type == PTR_TO_PACKET_END) {
		pkt = dst_reg;
	} else if (dst_reg->type == PTR_TO_PACKET_END) {
		pkt = src_reg;
		opcode = bpf_flip_opcode(opcode);
	} else {
		return -1;
	}

	if (pkt->range >= 0)
		return -1;

	switch (opcode) {
	case BPF_JLE:
		/* pkt <= pkt_end */
		fallthrough;
	case BPF_JGT:
		/* pkt > pkt_end */
		if (pkt->range == BEYOND_PKT_END)
			/* pkt has at last one extra byte beyond pkt_end */
			return opcode == BPF_JGT;
		break;
	case BPF_JLT:
		/* pkt < pkt_end */
		fallthrough;
	case BPF_JGE:
		/* pkt >= pkt_end */
		if (pkt->range == BEYOND_PKT_END || pkt->range == AT_PKT_END)
			return opcode == BPF_JGE;
		break;
	}
	return -1;
}

/* compute branch direction of the expression "if (<reg1> opcode <reg2>) goto target;"
 * and return:
 *  1 - branch will be taken and "goto target" will be executed
 *  0 - branch will not be taken and fall-through to next insn
 * -1 - unknown. Example: "if (reg1 < 5)" is unknown when register value
 *      range [0,10]
 */
static int is_branch_taken(struct bpf_verifier_env *env, struct bpf_reg_state *reg1,
			   struct bpf_reg_state *reg2, u8 opcode, bool is_jmp32)
{
	if (reg_is_pkt_pointer_any(reg1) && reg_is_pkt_pointer_any(reg2) && !is_jmp32)
		return is_pkt_ptr_branch_taken(reg1, reg2, opcode);

	if (__is_pointer_value(false, reg1) || __is_pointer_value(false, reg2)) {
		u64 val;

		/*
		 * The low 32 bits of a valid pointer may well be zero, hence
		 * nothing below applies to a 32-bit comparison.
		 */
		if (is_jmp32)
			return -1;

		/* arrange that reg2 is a scalar, and reg1 is a pointer */
		if (!is_reg_const(reg2, is_jmp32)) {
			opcode = bpf_flip_opcode(opcode);
			swap(reg1, reg2);
		}
		/* and ensure that reg2 is a constant */
		if (!is_reg_const(reg2, is_jmp32))
			return -1;

		if (!reg_not_null(env, reg1))
			return -1;

		/* If pointer is valid tests against zero will fail so we can
		 * use this to direct branch taken.
		 */
		val = reg_const_value(reg2, is_jmp32);
		if (val != 0)
			return -1;

		switch (opcode) {
		case BPF_JEQ:
			return 0;
		case BPF_JNE:
			return 1;
		default:
			return -1;
		}
	}

	/* now deal with two scalars, but not necessarily constants */
	return is_scalar_branch_taken(env, reg1, reg2, opcode, is_jmp32);
}

/* Opcode that corresponds to a *false* branch condition.
 * E.g., if r1 < r2, then reverse (false) condition is r1 >= r2
 */
u8 bpf_rev_opcode(u8 opcode)
{
	switch (opcode) {
	case BPF_JEQ:		return BPF_JNE;
	case BPF_JNE:		return BPF_JEQ;
	/* JSET doesn't have it's reverse opcode in BPF, so add
	 * BPF_X flag to denote the reverse of that operation
	 */
	case BPF_JSET:		return BPF_JSET | BPF_X;
	case BPF_JSET | BPF_X:	return BPF_JSET;
	case BPF_JGE:		return BPF_JLT;
	case BPF_JGT:		return BPF_JLE;
	case BPF_JLE:		return BPF_JGT;
	case BPF_JLT:		return BPF_JGE;
	case BPF_JSGE:		return BPF_JSLT;
	case BPF_JSGT:		return BPF_JSLE;
	case BPF_JSLE:		return BPF_JSGT;
	case BPF_JSLT:		return BPF_JSGE;
	default:		return 0;
	}
}

/* Refine range knowledge for <reg1> <op> <reg>2 conditional operation. */
static void regs_refine_cond_op(struct bpf_reg_state *reg1, struct bpf_reg_state *reg2,
				u8 opcode, bool is_jmp32)
{
	struct tnum t;
	u64 val;

	/* In case of GE/GT/SGE/JST, reuse LE/LT/SLE/SLT logic from below */
	switch (opcode) {
	case BPF_JGE:
	case BPF_JGT:
	case BPF_JSGE:
	case BPF_JSGT:
		opcode = bpf_flip_opcode(opcode);
		swap(reg1, reg2);
		break;
	default:
		break;
	}

	switch (opcode) {
	case BPF_JEQ:
		if (is_jmp32) {
			reg1->r32 = cnum32_intersect(reg1->r32, reg2->r32);
			reg2->r32 = reg1->r32;

			t = tnum_intersect(tnum_subreg(reg1->var_off), tnum_subreg(reg2->var_off));
			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
			reg2->var_off = tnum_with_subreg(reg2->var_off, t);
		} else {
			reg1->r64 = cnum64_intersect(reg1->r64, reg2->r64);
			reg2->r64 = reg1->r64;

			reg1->var_off = tnum_intersect(reg1->var_off, reg2->var_off);
			reg2->var_off = reg1->var_off;
		}
		break;
	case BPF_JNE:
		if (!is_reg_const(reg2, is_jmp32))
			swap(reg1, reg2);
		if (!is_reg_const(reg2, is_jmp32))
			break;

		/* try to recompute the bound of reg1 if reg2 is a const and
		 * is exactly the edge of reg1.
		 */
		val = reg_const_value(reg2, is_jmp32);
		if (is_jmp32) {
			/* Complement of the range [val, val] as cnum32. */
			cnum32_intersect_with(&reg1->r32, (struct cnum32){ val + 1, U32_MAX - 1 });
		} else {
			/* Complement of the range [val, val] as cnum64. */
			cnum64_intersect_with(&reg1->r64, (struct cnum64){ val + 1, U64_MAX - 1 });
		}
		break;
	case BPF_JSET:
		if (!is_reg_const(reg2, is_jmp32))
			swap(reg1, reg2);
		if (!is_reg_const(reg2, is_jmp32))
			break;
		val = reg_const_value(reg2, is_jmp32);
		/* BPF_JSET (i.e., TRUE branch, *not* BPF_JSET | BPF_X)
		 * requires single bit to learn something useful. E.g., if we
		 * know that `r1 & 0x3` is true, then which bits (0, 1, or both)
		 * are actually set? We can learn something definite only if
		 * it's a single-bit value to begin with.
		 *
		 * BPF_JSET | BPF_X (i.e., negation of BPF_JSET) doesn't have
		 * this restriction. I.e., !(r1 & 0x3) means neither bit 0 nor
		 * bit 1 is set, which we can readily use in adjustments.
		 */
		if (hweight64(val) != 1)
			break;
		if (is_jmp32) {
			t = tnum_or(tnum_subreg(reg1->var_off), tnum_const(val));
			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
		} else {
			reg1->var_off = tnum_or(reg1->var_off, tnum_const(val));
		}
		break;
	case BPF_JSET | BPF_X: /* reverse of BPF_JSET, see bpf_rev_opcode() */
		if (!is_reg_const(reg2, is_jmp32))
			swap(reg1, reg2);
		if (!is_reg_const(reg2, is_jmp32))
			break;
		val = reg_const_value(reg2, is_jmp32);
		/* Forget the ranges before narrowing tnums, to avoid invariant
		 * violations if we're on a dead branch.
		 */
		__mark_reg_unbounded(reg1);
		reg_step_reset(reg1);
		if (is_jmp32) {
			t = tnum_and(tnum_subreg(reg1->var_off), tnum_const(~val));
			reg1->var_off = tnum_with_subreg(reg1->var_off, t);
		} else {
			reg1->var_off = tnum_and(reg1->var_off, tnum_const(~val));
		}
		break;
	case BPF_JLE:
		if (is_jmp32) {
			cnum32_intersect_with_urange(&reg1->r32, 0, reg_u32_max(reg2));
			cnum32_intersect_with_urange(&reg2->r32, reg_u32_min(reg1), U32_MAX);
		} else {
			cnum64_intersect_with_urange(&reg1->r64, 0, reg_umax(reg2));
			cnum64_intersect_with_urange(&reg2->r64, reg_umin(reg1), U64_MAX);
		}
		break;
	case BPF_JLT:
		if (is_jmp32) {
			cnum32_intersect_with_urange(&reg1->r32, 0, reg_u32_max(reg2) - 1);
			cnum32_intersect_with_urange(&reg2->r32, reg_u32_min(reg1) + 1, U32_MAX);
		} else {
			cnum64_intersect_with_urange(&reg1->r64, 0, reg_umax(reg2) - 1);
			cnum64_intersect_with_urange(&reg2->r64, reg_umin(reg1) + 1, U64_MAX);
		}
		break;
	case BPF_JSLE:
		if (is_jmp32) {
			cnum32_intersect_with_srange(&reg1->r32, S32_MIN, reg_s32_max(reg2));
			cnum32_intersect_with_srange(&reg2->r32, reg_s32_min(reg1), S32_MAX);
		} else {
			cnum64_intersect_with_srange(&reg1->r64, S64_MIN, reg_smax(reg2));
			cnum64_intersect_with_srange(&reg2->r64, reg_smin(reg1), S64_MAX);
		}
		break;
	case BPF_JSLT:
		if (is_jmp32) {
			cnum32_intersect_with_srange(&reg1->r32, S32_MIN, reg_s32_max(reg2) - 1);
			cnum32_intersect_with_srange(&reg2->r32, reg_s32_min(reg1) + 1, S32_MAX);
		} else {
			cnum64_intersect_with_srange(&reg1->r64, S64_MIN, reg_smax(reg2) - 1);
			cnum64_intersect_with_srange(&reg2->r64, reg_smin(reg1) + 1, S64_MAX);
		}
		break;
	default:
		return;
	}
}

/* Check for invariant violations on the registers for both branches of a condition */
static int regs_bounds_sanity_check_branches(struct bpf_verifier_env *env)
{
	int err;

	err = reg_bounds_sanity_check(env, &env->true_reg1, "true_reg1");
	err = err ?: reg_bounds_sanity_check(env, &env->true_reg2, "true_reg2");
	err = err ?: reg_bounds_sanity_check(env, &env->false_reg1, "false_reg1");
	err = err ?: reg_bounds_sanity_check(env, &env->false_reg2, "false_reg2");
	return err;
}

static void mark_ptr_or_null_reg(struct bpf_func_state *state,
				 struct bpf_reg_state *reg, u32 id,
				 bool is_null)
{
	if (type_may_be_null(reg->type) && reg->id == id &&
	    (is_rcu_reg(reg) || !WARN_ON_ONCE(!reg->id))) {
		/* Old offset should have been known-zero, because we don't
		 * allow pointer arithmetic on pointers that might be NULL.
		 * If we see this happening, don't convert the register.
		 *
		 * But in some cases, some helpers that return local kptrs
		 * advance offset for the returned pointer. In those cases,
		 * it is fine to expect to see reg->var_off.
		 */
		if (!(type_is_ptr_alloc_obj(reg->type) || type_is_non_owning_ref(reg->type)) &&
		    WARN_ON_ONCE(!tnum_equals_const(reg->var_off, 0)))
			return;
		if (is_null) {
			/* We don't need id from this point
			 * onwards anymore, thus we should better reset it,
			 * so that state pruning has chances to take effect.
			 */
			__mark_reg_known_zero(reg);
			reg->type = SCALAR_VALUE;

			return;
		}

		mark_ptr_not_null_reg(reg);

		/*
		 * reg->id is preserved for object relationship tracking
		 * and spin_lock lock state tracking
		 */
	}
}

/* The logic is similar to find_good_pkt_pointers(), both could eventually
 * be folded together at some point.
 */
static void mark_ptr_or_null_regs(struct bpf_verifier_state *vstate, u32 regno,
				  bool is_null)
{
	struct bpf_func_state *state = vstate->frame[vstate->curframe];
	struct bpf_reg_state *regs = state->regs, *reg;
	u32 id = regs[regno].id;

	if (is_null && find_reference_state(vstate, id))
		/* regs[regno] is in the " == NULL" branch.
		 * No one could have freed the reference state before
		 * doing the NULL check.
		 */
		WARN_ON_ONCE(__release_reference_nomark(vstate, id));

	bpf_for_each_reg_in_vstate(vstate, state, reg, ({
		mark_ptr_or_null_reg(state, reg, id, is_null);
	}));
}

static bool try_match_pkt_pointers(const struct bpf_insn *insn,
				   struct bpf_reg_state *dst_reg,
				   struct bpf_reg_state *src_reg,
				   struct bpf_verifier_state *this_branch,
				   struct bpf_verifier_state *other_branch)
{
	if (BPF_SRC(insn->code) != BPF_X)
		return false;

	/* Pointers are always 64-bit. */
	if (BPF_CLASS(insn->code) == BPF_JMP32)
		return false;

	switch (BPF_OP(insn->code)) {
	case BPF_JGT:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' > pkt_end, pkt_meta' > pkt_data */
			find_good_pkt_pointers(this_branch, dst_reg,
					       dst_reg->type, false);
			mark_pkt_end(other_branch, insn->dst_reg, true);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end > pkt_data', pkt_data > pkt_meta' */
			find_good_pkt_pointers(other_branch, src_reg,
					       src_reg->type, true);
			mark_pkt_end(this_branch, insn->src_reg, false);
		} else {
			return false;
		}
		break;
	case BPF_JLT:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' < pkt_end, pkt_meta' < pkt_data */
			find_good_pkt_pointers(other_branch, dst_reg,
					       dst_reg->type, true);
			mark_pkt_end(this_branch, insn->dst_reg, false);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end < pkt_data', pkt_data > pkt_meta' */
			find_good_pkt_pointers(this_branch, src_reg,
					       src_reg->type, false);
			mark_pkt_end(other_branch, insn->src_reg, true);
		} else {
			return false;
		}
		break;
	case BPF_JGE:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' >= pkt_end, pkt_meta' >= pkt_data */
			find_good_pkt_pointers(this_branch, dst_reg,
					       dst_reg->type, true);
			mark_pkt_end(other_branch, insn->dst_reg, false);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end >= pkt_data', pkt_data >= pkt_meta' */
			find_good_pkt_pointers(other_branch, src_reg,
					       src_reg->type, false);
			mark_pkt_end(this_branch, insn->src_reg, true);
		} else {
			return false;
		}
		break;
	case BPF_JLE:
		if ((dst_reg->type == PTR_TO_PACKET &&
		     src_reg->type == PTR_TO_PACKET_END) ||
		    (dst_reg->type == PTR_TO_PACKET_META &&
		     reg_is_init_pkt_pointer(src_reg, PTR_TO_PACKET))) {
			/* pkt_data' <= pkt_end, pkt_meta' <= pkt_data */
			find_good_pkt_pointers(other_branch, dst_reg,
					       dst_reg->type, false);
			mark_pkt_end(this_branch, insn->dst_reg, true);
		} else if ((dst_reg->type == PTR_TO_PACKET_END &&
			    src_reg->type == PTR_TO_PACKET) ||
			   (reg_is_init_pkt_pointer(dst_reg, PTR_TO_PACKET) &&
			    src_reg->type == PTR_TO_PACKET_META)) {
			/* pkt_end <= pkt_data', pkt_data <= pkt_meta' */
			find_good_pkt_pointers(this_branch, src_reg,
					       src_reg->type, true);
			mark_pkt_end(other_branch, insn->src_reg, false);
		} else {
			return false;
		}
		break;
	default:
		return false;
	}

	return true;
}

static void __collect_linked_regs(struct linked_regs *reg_set, struct bpf_reg_state *reg,
				  u32 id, u32 frameno, u32 spi_or_reg, bool is_reg)
{
	struct linked_reg *e;

	if (reg->type != SCALAR_VALUE || (reg->id & ~BPF_ADD_CONST) != id)
		return;

	e = linked_regs_push(reg_set);
	if (e) {
		e->frameno = frameno;
		e->is_reg = is_reg;
		e->regno = spi_or_reg;
	} else {
		clear_scalar_id(reg);
	}
}

/* For all R being scalar registers or spilled scalar registers
 * in verifier state, save R in linked_regs if R->id == id.
 * If there are too many Rs sharing same id, reset id for leftover Rs.
 */
static void collect_linked_regs(struct bpf_verifier_env *env,
				struct bpf_verifier_state *vstate,
				u32 id,
				struct linked_regs *linked_regs)
{
	struct bpf_insn_aux_data *aux = env->insn_aux_data;
	struct bpf_func_state *func;
	struct bpf_reg_state *reg;
	u16 live_regs;
	int i, j;

	id = id & ~BPF_ADD_CONST;
	for (i = vstate->curframe; i >= 0; i--) {
		live_regs = aux[bpf_frame_insn_idx(vstate, i)].live_regs_before;
		func = vstate->frame[i];
		for (j = 0; j < BPF_REG_FP; j++) {
			if (!(live_regs & BIT(j)))
				continue;
			reg = &func->regs[j];
			__collect_linked_regs(linked_regs, reg, id, i, j, true);
		}
		for (j = 0; j < bpf_stack_nr_slots(func); j++) {
			struct bpf_stack_state *ss = bpf_stack_slot(func, j);

			if (!bpf_is_spilled_reg(ss))
				continue;
			reg = &ss->spilled_ptr;
			__collect_linked_regs(linked_regs, reg, id, i, j, false);
		}
	}
}

/* For all R in linked_regs, copy known_reg range into R
 * if R->id == known_reg->id.
 */
static void sync_linked_regs(struct bpf_verifier_env *env, struct bpf_verifier_state *vstate,
			     struct bpf_reg_state *known_reg, struct linked_regs *linked_regs)
{
	struct bpf_reg_state fake_reg;
	struct bpf_reg_state *reg;
	struct linked_reg *e;
	int i;

	for (i = 0; i < linked_regs->cnt; ++i) {
		e = &linked_regs->entries[i];
		reg = e->is_reg ? &vstate->frame[e->frameno]->regs[e->regno]
				: &bpf_stack_slot(vstate->frame[e->frameno], e->spi)->spilled_ptr;
		if (reg->type != SCALAR_VALUE || reg == known_reg)
			continue;
		if ((reg->id & ~BPF_ADD_CONST) != (known_reg->id & ~BPF_ADD_CONST))
			continue;
		/*
		 * Skip mixed 32/64-bit links: the delta relationship doesn't
		 * hold across different ALU widths.
		 */
		if (((reg->id ^ known_reg->id) & BPF_ADD_CONST) == BPF_ADD_CONST)
			continue;
		if ((!(reg->id & BPF_ADD_CONST) && !(known_reg->id & BPF_ADD_CONST)) ||
		    reg->delta == known_reg->delta) {
			*reg = *known_reg;
		} else {
			s32 saved_off = reg->delta;
			u32 saved_id = reg->id;

			fake_reg.type = SCALAR_VALUE;
			__mark_reg_known(&fake_reg, (s64)reg->delta - (s64)known_reg->delta);

			/* reg = known_reg; reg += delta */
			*reg = *known_reg;
			/*
			 * Must preserve off and id, otherwise another sync_linked_regs()
			 * will be incorrect.
			 */
			reg->delta = saved_off;
			reg->id = saved_id;

			scalar_step_add(reg, reg, &fake_reg);
			scalar32_min_max_add(reg, &fake_reg);
			scalar_min_max_add(reg, &fake_reg);
			reg->var_off = tnum_add(reg->var_off, fake_reg.var_off);
			if ((reg->id | known_reg->id) & BPF_ADD_CONST32)
				zext_32_to_64(reg);
			reg_bounds_sync(reg);
		}
		if (e->is_reg)
			mark_reg_scratched(env, e->regno);
		else
			mark_stack_slot_scratched(env, e->spi);
	}
}

static int check_cond_jmp_op(struct bpf_verifier_env *env,
			     struct bpf_insn *insn, int *insn_idx)
{
	struct bpf_verifier_state *this_branch = env->cur_state;
	struct bpf_verifier_state *other_branch;
	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
	struct bpf_reg_state *dst_reg, *other_branch_regs, *src_reg = NULL;
	struct bpf_reg_state *eq_branch_regs;
	struct linked_regs linked_regs = {};
	u8 opcode = BPF_OP(insn->code);
	int insn_flags = 0;
	bool is_jmp32;
	int pred = -1;
	int err;

	/* Only conditional jumps are expected to reach here. */
	if (opcode == BPF_JA || opcode > BPF_JCOND) {
		verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode);
		return -EINVAL;
	}

	if (bpf_is_unwind_goto(insn)) {
		if (!env->cur_state->unwound)
			return 0;
		env->cur_state->unwound = false;
		/*
		 * unwind_exit changed its return address, so the return is
		 * mispredicted and what follows unwind_goto runs speculatively.
		 */
		if (!env->bypass_spec_v1) {
			err = sanitize_speculative_path(env, NULL, *insn_idx + 1, *insn_idx);
			if (err)
				return err;
		}
		*insn_idx += insn->off;
		return 0;
	}

	if (opcode == BPF_JCOND) {
		struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st;
		int idx = *insn_idx;

		prev_st = find_prev_entry(env, cur_st->parent, idx);

		/* branch out 'fallthrough' insn as a new state to explore */
		queued_st = push_stack(env, idx + 1, idx, false);
		if (IS_ERR(queued_st))
			return PTR_ERR(queued_st);

		queued_st->may_goto_depth++;
		if (prev_st)
			widen_imprecise_scalars(env, prev_st, queued_st);
		*insn_idx += insn->off;
		return 0;
	}

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

	dst_reg = &regs[insn->dst_reg];
	if (BPF_SRC(insn->code) == BPF_X) {
		/* check src1 operand */
		err = check_reg_arg(env, insn->src_reg, SRC_OP);
		if (err)
			return err;

		src_reg = &regs[insn->src_reg];
		if (!(reg_is_pkt_pointer_any(dst_reg) && reg_is_pkt_pointer_any(src_reg)) &&
		    is_pointer_value(env, insn->src_reg)) {
			verbose(env, "R%d pointer comparison prohibited\n",
				insn->src_reg);
			return -EACCES;
		}

		if (src_reg->type == PTR_TO_STACK)
			insn_flags |= INSN_F_SRC_REG_STACK;
		if (dst_reg->type == PTR_TO_STACK)
			insn_flags |= INSN_F_DST_REG_STACK;
	} else {
		src_reg = &env->fake_reg[0];
		memset(src_reg, 0, sizeof(*src_reg));
		src_reg->type = SCALAR_VALUE;
		__mark_reg_known(src_reg, insn->imm);

		if (dst_reg->type == PTR_TO_STACK)
			insn_flags |= INSN_F_DST_REG_STACK;
	}

	if (insn_flags) {
		err = bpf_push_jmp_history(env, this_branch, insn_flags, 0, 0, NULL, 0);
		if (err)
			return err;
	}

	/*
	 * Collect the linked registers before env->{true,false}_reg{1,2} setup,
	 * otherwise ids dropped by collect_linked_regs() would be resurrected
	 * when env->{true,false}_reg{1,2} are copied back.
	 */
	if (BPF_SRC(insn->code) == BPF_X && src_reg->type == SCALAR_VALUE && src_reg->id)
		collect_linked_regs(env, this_branch, src_reg->id, &linked_regs);
	if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
		collect_linked_regs(env, this_branch, dst_reg->id, &linked_regs);

	is_jmp32 = BPF_CLASS(insn->code) == BPF_JMP32;
	env->false_reg1 = *dst_reg;
	env->false_reg2 = *src_reg;
	env->true_reg1 = *dst_reg;
	env->true_reg2 = *src_reg;
	pred = is_branch_taken(env, dst_reg, src_reg, opcode, is_jmp32);
	if (pred >= 0) {
		/* If we get here with a dst_reg pointer type it is because
		 * above is_branch_taken() special cased the 0 comparison.
		 */
		if (!__is_pointer_value(false, dst_reg))
			err = mark_chain_precision(env, insn->dst_reg);
		if (BPF_SRC(insn->code) == BPF_X && !err &&
		    !__is_pointer_value(false, src_reg))
			err = mark_chain_precision(env, insn->src_reg);
		if (err)
			return err;
	}

	if (pred == 1) {
		/* Only follow the goto, ignore fall-through. If needed, push
		 * the fall-through branch for simulation under speculative
		 * execution.
		 */
		if (!env->bypass_spec_v1) {
			err = sanitize_speculative_path(env, insn, *insn_idx + 1, *insn_idx);
			if (err < 0)
				return err;
		}
		if (env->log.level & BPF_LOG_LEVEL)
			print_insn_state(env, this_branch, this_branch->curframe);
		*insn_idx += insn->off;
		return 0;
	} else if (pred == 0) {
		/* Only follow the fall-through branch, since that's where the
		 * program will go. If needed, push the goto branch for
		 * simulation under speculative execution.
		 */
		if (!env->bypass_spec_v1) {
			err = sanitize_speculative_path(env, insn, *insn_idx + insn->off + 1,
							*insn_idx);
			if (err < 0)
				return err;
		}
		if (env->log.level & BPF_LOG_LEVEL)
			print_insn_state(env, this_branch, this_branch->curframe);
		return 0;
	}

	/* Push scalar registers sharing same ID to jump history,
	 * do this before creating 'other_branch', so that both
	 * 'this_branch' and 'other_branch' share this history
	 * if parent state is created.
	 */
	if (linked_regs.cnt > 1) {
		u16 packed[LINKED_REGS_MAX];

		linked_regs_pack(&linked_regs, packed);
		err = bpf_push_jmp_history(env, this_branch, 0, 0, 0, packed, linked_regs.cnt);
		if (err)
			return err;
	}

	other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx, false);
	if (IS_ERR(other_branch))
		return PTR_ERR(other_branch);
	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;

	err = regs_bounds_sanity_check_branches(env);
	if (err)
		return err;

	*dst_reg = env->false_reg1;
	*src_reg = env->false_reg2;
	other_branch_regs[insn->dst_reg] = env->true_reg1;
	if (BPF_SRC(insn->code) == BPF_X)
		other_branch_regs[insn->src_reg] = env->true_reg2;

	if (BPF_SRC(insn->code) == BPF_X &&
	    src_reg->type == SCALAR_VALUE && src_reg->id &&
	    !WARN_ON_ONCE(src_reg->id != other_branch_regs[insn->src_reg].id)) {
		sync_linked_regs(env, this_branch, src_reg, &linked_regs);
		sync_linked_regs(env, other_branch, &other_branch_regs[insn->src_reg],
				 &linked_regs);
	}
	if (dst_reg->type == SCALAR_VALUE && dst_reg->id &&
	    !WARN_ON_ONCE(dst_reg->id != other_branch_regs[insn->dst_reg].id)) {
		sync_linked_regs(env, this_branch, dst_reg, &linked_regs);
		sync_linked_regs(env, other_branch, &other_branch_regs[insn->dst_reg],
				 &linked_regs);
	}

	/* if one pointer register is compared to another pointer
	 * register check if PTR_MAYBE_NULL could be lifted.
	 * E.g. register A - maybe null
	 *      register B - not null
	 * for JNE A, B, ... - A is not null in the false branch;
	 * for JEQ A, B, ... - A is not null in the true branch.
	 *
	 * Since PTR_TO_BTF_ID points to a kernel struct that does
	 * not need to be null checked by the BPF program, i.e.,
	 * could be null even without PTR_MAYBE_NULL marking, so
	 * only propagate nullness when neither reg is that type.
	 */
	if (!is_jmp32 && BPF_SRC(insn->code) == BPF_X &&
	    __is_pointer_value(false, src_reg) && __is_pointer_value(false, dst_reg) &&
	    base_type(src_reg->type) != PTR_TO_BTF_ID &&
	    base_type(dst_reg->type) != PTR_TO_BTF_ID) {
		eq_branch_regs = NULL;
		switch (opcode) {
		case BPF_JEQ:
			eq_branch_regs = other_branch_regs;
			break;
		case BPF_JNE:
			eq_branch_regs = regs;
			break;
		default:
			/* do nothing */
			break;
		}
		if (eq_branch_regs) {
			/* src == dst && dst != NULL => src != NULL */
			if (reg_not_null(env, dst_reg) && type_may_be_null(src_reg->type))
				mark_ptr_not_null_reg(&eq_branch_regs[insn->src_reg]);
			/* src == dst && src != NULL => dst != NULL */
			if (reg_not_null(env, src_reg) && type_may_be_null(dst_reg->type))
				mark_ptr_not_null_reg(&eq_branch_regs[insn->dst_reg]);
		}
	}

	/* detect if R == 0 where R is returned from bpf_map_lookup_elem().
	 * Also does the same detection for a register whose the value is
	 * known to be 0.
	 * NOTE: these optimizations below are related with pointer comparison
	 *       which will never be JMP32.
	 */
	if (!is_jmp32 && (opcode == BPF_JEQ || opcode == BPF_JNE) &&
	    type_may_be_null(dst_reg->type) &&
	    ((BPF_SRC(insn->code) == BPF_K && insn->imm == 0) ||
	     (BPF_SRC(insn->code) == BPF_X && bpf_register_is_null(src_reg)))) {
		/*
		 * For BPF_X the zero is a property of this execution path,
		 * hence src_reg has to be precise.
		 */
		if (BPF_SRC(insn->code) == BPF_X) {
			err = mark_chain_precision(env, insn->src_reg);
			if (err)
				return err;
		}
		/* Mark all identical registers in each branch as either
		 * safe or unknown depending R == 0 or R != 0 conditional.
		 */
		mark_ptr_or_null_regs(this_branch, insn->dst_reg,
				      opcode == BPF_JNE);
		mark_ptr_or_null_regs(other_branch, insn->dst_reg,
				      opcode == BPF_JEQ);
	} else if (!try_match_pkt_pointers(insn, dst_reg, &regs[insn->src_reg],
					   this_branch, other_branch) &&
		   is_pointer_value(env, insn->dst_reg)) {
		verbose(env, "R%d pointer comparison prohibited\n",
			insn->dst_reg);
		return -EACCES;
	}
	if (env->log.level & BPF_LOG_LEVEL)
		print_insn_state(env, this_branch, this_branch->curframe);
	return 0;
}

/* verify BPF_LD_IMM64 instruction */
static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_insn_aux_data *aux = cur_aux(env);
	struct bpf_reg_state *regs = cur_regs(env);
	struct bpf_reg_state *dst_reg;
	struct bpf_map *map;
	int err;

	if (BPF_SIZE(insn->code) != BPF_DW) {
		verbose(env, "invalid BPF_LD_IMM insn\n");
		return -EINVAL;
	}

	err = check_reg_arg(env, insn->dst_reg, DST_OP);
	if (err)
		return err;

	dst_reg = &regs[insn->dst_reg];
	bpf_diag_mod_begin(env, dst_reg, NULL, BPF_DIAG_MOD_WRITE);
	if (insn->src_reg == 0) {
		u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm;

		dst_reg->type = SCALAR_VALUE;
		__mark_reg_known(&regs[insn->dst_reg], imm);
		bpf_diag_mod_end(env);
		return 0;
	}

	/* All special src_reg cases are listed below. From this point onwards
	 * we either succeed and assign a corresponding dst_reg->type after
	 * zeroing the offset, or fail and reject the program.
	 */
	mark_reg_known_zero(env, regs, insn->dst_reg);

	if (insn->src_reg == BPF_PSEUDO_BTF_ID) {
		dst_reg->type = aux->btf_var.reg_type;
		switch (base_type(dst_reg->type)) {
		case PTR_TO_MEM:
			dst_reg->mem_size = aux->btf_var.mem_size;
			break;
		case PTR_TO_BTF_ID:
			dst_reg->btf = aux->btf_var.btf;
			dst_reg->btf_id = aux->btf_var.btf_id;
			break;
		default:
			verifier_bug(env, "pseudo btf id: unexpected dst reg type");
			return -EFAULT;
		}
		bpf_diag_mod_end(env);
		return 0;
	}

	if (insn->src_reg == BPF_PSEUDO_FUNC) {
		struct bpf_prog_aux *aux = env->prog->aux;
		u32 subprogno = bpf_find_subprog(env,
						 env->insn_idx + insn->imm + 1);

		if (!aux->func_info) {
			verbose(env, "missing btf func_info\n");
			return -EINVAL;
		}
		if (aux->func_info_aux[subprogno].linkage != BTF_FUNC_STATIC) {
			verbose(env, "callback function not static\n");
			return -EINVAL;
		}
		/*
		 * When env->subprog_cnt == 1 this instruction won't be rewritten
		 * to hold a real function address. Assume that no usable program
		 * combines e.g. main and timer callback and just reject here.
		 */
		if (subprogno == 0) {
			verbose(env, "callback function cannot be the main program\n");
			return -EINVAL;
		}

		dst_reg->type = PTR_TO_FUNC;
		dst_reg->subprogno = subprogno;
		bpf_diag_mod_end(env);
		return 0;
	}

	map = env->used_maps[aux->map_index];

	if (insn->src_reg == BPF_PSEUDO_MAP_VALUE ||
	    insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) {
		if (map->map_type == BPF_MAP_TYPE_ARENA) {
			__mark_reg_unknown(env, dst_reg);
			dst_reg->map_ptr = map;
			bpf_diag_mod_end(env);
			return 0;
		}
		__mark_reg_known(dst_reg, aux->map_off);
		dst_reg->type = PTR_TO_MAP_VALUE;
		dst_reg->map_ptr = map;
		WARN_ON_ONCE(map->map_type != BPF_MAP_TYPE_INSN_ARRAY &&
			     map->max_entries != 1);
		/* We want reg->id to be same (0) as map_value is not distinct */
	} else if (insn->src_reg == BPF_PSEUDO_MAP_FD ||
		   insn->src_reg == BPF_PSEUDO_MAP_IDX) {
		dst_reg->type = CONST_PTR_TO_MAP;
		dst_reg->map_ptr = map;
	} else {
		verifier_bug(env, "unexpected src reg value for ldimm64");
		return -EFAULT;
	}

	bpf_diag_mod_end(env);
	return 0;
}

static bool may_access_skb(enum bpf_prog_type type)
{
	switch (type) {
	case BPF_PROG_TYPE_SOCKET_FILTER:
	case BPF_PROG_TYPE_SCHED_CLS:
	case BPF_PROG_TYPE_SCHED_ACT:
		return true;
	default:
		return false;
	}
}

/* verify safety of LD_ABS|LD_IND instructions:
 * - they can only appear in the programs where ctx == skb
 * - since they are wrappers of function calls, they scratch R1-R5 registers,
 *   preserve R6-R9, and store return value into R0
 *
 * Implicit input:
 *   ctx == skb == R6 == CTX
 *
 * Explicit input:
 *   SRC == any register
 *   IMM == 32-bit immediate
 *
 * Output:
 *   R0 - 8/16/32-bit skb data converted to cpu endianness
 */
static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_reg_state *regs = cur_regs(env);
	static const int ctx_reg = BPF_REG_6;
	u8 mode = BPF_MODE(insn->code);
	int i, err;

	if (!may_access_skb(resolve_prog_type(env->prog))) {
		verbose(env, "BPF_LD_[ABS|IND] instructions not allowed for this program type\n");
		return -EINVAL;
	}

	for (i = state->curframe; i; i--) {
		if (state->frame[i]->in_callback_fn) {
			verbose(env, "cannot use BPF_LD_[ABS|IND] within callback\n");
			return -EINVAL;
		}
	}

	if (!env->ops->gen_ld_abs) {
		verifier_bug(env, "gen_ld_abs is null");
		return -EFAULT;
	}

	/* check whether implicit source operand (register R6) is readable */
	err = check_reg_arg(env, ctx_reg, SRC_OP);
	if (err)
		return err;

	/* Disallow usage of BPF_LD_[ABS|IND] with reference tracking, as
	 * gen_ld_abs() may terminate the program at runtime, leading to
	 * reference leak.
	 */
	err = check_resource_leak(env, false, true, "BPF_LD_[ABS|IND]");
	if (err)
		return err;

	if (regs[ctx_reg].type != PTR_TO_CTX) {
		verbose(env,
			"at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
		return -EINVAL;
	}

	if (mode == BPF_IND) {
		/* check explicit source operand */
		err = check_reg_arg(env, insn->src_reg, SRC_OP);
		if (err)
			return err;
	}

	err = check_ptr_off_reg(env, &regs[ctx_reg], ctx_reg);
	if (err < 0)
		return err;

	/* reset caller saved regs to unreadable */
	bpf_diag_record_caller_saved(env, regs);
	bpf_diag_mod_begin(env, &regs[BPF_REG_0], NULL, BPF_DIAG_MOD_WRITE);
	for (i = 0; i < CALLER_SAVED_REGS; i++) {
		bpf_mark_reg_not_init(env, &regs[caller_saved[i]]);
		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
	}

	/* mark destination R0 register as readable, since it contains
	 * the value fetched from the packet.
	 * Already marked as written above.
	 */
	mark_reg_unknown(env, regs, BPF_REG_0);
	bpf_diag_mod_end(env);
	/*
	 * See bpf_gen_ld_abs() which emits a hidden BPF_EXIT with r0=0
	 * which must be explored by the verifier when in a subprog.
	 */
	if (env->cur_state->curframe) {
		struct bpf_verifier_state *branch;

		mark_reg_scratched(env, BPF_REG_0);
		branch = push_stack(env, env->insn_idx + 1, env->insn_idx, false);
		if (IS_ERR(branch))
			return PTR_ERR(branch);
		mark_reg_known_zero(env, regs, BPF_REG_0);
		err = prepare_func_exit(env, &env->insn_idx);
		if (err)
			return err;
		env->insn_idx--;
	}
	return 0;
}

static bool return_retval_range(struct bpf_verifier_env *env, struct bpf_retval_range *range)
{
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);

	/* Default return value range. */
	*range = retval_range(0, 1);

	switch (prog_type) {
	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
		switch (env->prog->expected_attach_type) {
		case BPF_CGROUP_UDP4_RECVMSG:
		case BPF_CGROUP_UDP6_RECVMSG:
		case BPF_CGROUP_UNIX_RECVMSG:
		case BPF_CGROUP_INET4_GETPEERNAME:
		case BPF_CGROUP_INET6_GETPEERNAME:
		case BPF_CGROUP_UNIX_GETPEERNAME:
		case BPF_CGROUP_INET4_GETSOCKNAME:
		case BPF_CGROUP_INET6_GETSOCKNAME:
		case BPF_CGROUP_UNIX_GETSOCKNAME:
			*range = retval_range(1, 1);
			break;
		case BPF_CGROUP_INET4_BIND:
		case BPF_CGROUP_INET6_BIND:
			*range = retval_range(0, 3);
			break;
		default:
			break;
		}
		break;
	case BPF_PROG_TYPE_CGROUP_SKB:
		if (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS)
			*range = retval_range(0, 3);
		break;
	case BPF_PROG_TYPE_CGROUP_SOCK:
	case BPF_PROG_TYPE_SOCK_OPS:
	case BPF_PROG_TYPE_CGROUP_DEVICE:
	case BPF_PROG_TYPE_CGROUP_SYSCTL:
	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
		break;
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
		if (!env->prog->aux->attach_btf_id)
			return false;
		*range = retval_range(0, 0);
		break;
	case BPF_PROG_TYPE_TRACING:
		switch (env->prog->expected_attach_type) {
		case BPF_TRACE_FENTRY:
		case BPF_TRACE_FEXIT:
		case BPF_TRACE_FSESSION:
		case BPF_TRACE_FENTRY_MULTI:
		case BPF_TRACE_FEXIT_MULTI:
		case BPF_TRACE_FSESSION_MULTI:
			*range = retval_range(0, 0);
			break;
		case BPF_TRACE_RAW_TP:
		case BPF_MODIFY_RETURN:
			return false;
		case BPF_TRACE_ITER:
		default:
			break;
		}
		break;
	case BPF_PROG_TYPE_KPROBE:
		switch (env->prog->expected_attach_type) {
		case BPF_TRACE_KPROBE_SESSION:
		case BPF_TRACE_UPROBE_SESSION:
			break;
		default:
			return false;
		}
		break;
	case BPF_PROG_TYPE_SK_LOOKUP:
		*range = retval_range(SK_DROP, SK_PASS);
		break;

	case BPF_PROG_TYPE_LSM:
		if (env->prog->expected_attach_type != BPF_LSM_CGROUP) {
			/* no range found, any return value is allowed */
			if (!get_func_retval_range(env->prog, range))
				return false;
			/* no restricted range, any return value is allowed */
			if (range->minval == S32_MIN && range->maxval == S32_MAX)
				return false;
			range->return_32bit = true;
		} else if (!env->prog->aux->attach_func_proto->type) {
			/* Make sure programs that attach to void
			 * hooks don't try to modify return value.
			 */
			*range = retval_range(1, 1);
		}
		break;

	case BPF_PROG_TYPE_NETFILTER:
		*range = retval_range(NF_DROP, NF_ACCEPT);
		break;
	case BPF_PROG_TYPE_STRUCT_OPS:
		*range = retval_range(0, 0);
		break;
	case BPF_PROG_TYPE_EXT:
		/* freplace program can return anything as its return value
		 * depends on the to-be-replaced kernel func or bpf program.
		 */
	default:
		return false;
	}

	/* Continue calculating. */

	return true;
}

static bool program_returns_void(struct bpf_verifier_env *env)
{
	const struct bpf_prog *prog = env->prog;
	enum bpf_prog_type prog_type = prog->type;

	switch (prog_type) {
	case BPF_PROG_TYPE_LSM:
		/* See return_retval_range, for BPF_LSM_CGROUP can be 0 or 0-1 depending on hook. */
		if (prog->expected_attach_type != BPF_LSM_CGROUP &&
		    !prog->aux->attach_func_proto->type)
			return true;
		break;
	case BPF_PROG_TYPE_STRUCT_OPS:
		if (!prog->aux->attach_func_proto->type)
			return true;
		break;
	case BPF_PROG_TYPE_EXT:
		/*
		 * If the actual program is an extension, let it
		 * return void - attaching will succeed only if the
		 * program being replaced also returns void, and since
		 * it has passed verification its actual type doesn't matter.
		 */
		if (subprog_returns_void(env, 0))
			return true;
		break;
	default:
		break;
	}
	return false;
}

static int check_return_code(struct bpf_verifier_env *env, int regno, const char *reg_name)
{
	const char *exit_ctx = "At program exit";
	struct tnum enforce_attach_type_range = tnum_unknown;
	const struct bpf_prog *prog = env->prog;
	struct bpf_reg_state *reg = reg_state(env, regno);
	struct bpf_retval_range range = retval_range(0, 1);
	enum bpf_prog_type prog_type = resolve_prog_type(env->prog);
	struct bpf_func_state *frame = env->cur_state->frame[0];
	const struct btf_type *reg_type, *ret_type = NULL;
	int err;

	/* LSM and struct_ops func-ptr's return type could be "void" */
	if (!frame->in_async_callback_fn && program_returns_void(env))
		return 0;

	if (prog_type == BPF_PROG_TYPE_STRUCT_OPS) {
		/* Allow a struct_ops program to return a referenced kptr if it
		 * matches the operator's return type and is in its unmodified
		 * form. A scalar zero (i.e., a null pointer) is also allowed.
		 */
		reg_type = reg->btf ? btf_type_by_id(reg->btf, reg->btf_id) : NULL;
		ret_type = btf_type_resolve_ptr(prog->aux->attach_btf,
						prog->aux->attach_func_proto->type,
						NULL);
		if (ret_type && ret_type == reg_type && reg_is_referenced(env, reg))
			return __check_ptr_off_reg(env, reg, argno_from_reg(regno), false);
	}

	/* eBPF calling convention is such that R0 is used
	 * to return the value from eBPF program.
	 * Make sure that it's readable at this time
	 * of bpf_exit, which means that program wrote
	 * something into it earlier
	 */
	err = check_reg_arg(env, regno, SRC_OP);
	if (err)
		return err;

	if (is_pointer_value(env, regno)) {
		verbose(env, "R%d leaks addr as return value\n", regno);
		return -EACCES;
	}

	if (frame->in_async_callback_fn) {
		exit_ctx = "At async callback return";
		range = frame->callback_ret_range;
		goto enforce_retval;
	}

	if (prog_type == BPF_PROG_TYPE_STRUCT_OPS && !ret_type)
		return 0;

	if (prog_type == BPF_PROG_TYPE_CGROUP_SKB && (env->prog->expected_attach_type == BPF_CGROUP_INET_EGRESS))
		enforce_attach_type_range = tnum_range(2, 3);

	if (!return_retval_range(env, &range))
		return 0;

enforce_retval:
	if (reg->type != SCALAR_VALUE) {
		verbose(env, "%s the register R%d is not a known value (%s)\n",
			exit_ctx, regno, reg_type_str(env, reg->type));
		return -EINVAL;
	}

	err = mark_chain_precision(env, regno);
	if (err)
		return err;

	if (!retval_range_within(range, reg)) {
		verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name);
		if (prog->expected_attach_type == BPF_LSM_CGROUP &&
		    prog_type == BPF_PROG_TYPE_LSM &&
		    !prog->aux->attach_func_proto->type)
			verbose(env, "Note, BPF_LSM_CGROUP that attach to void LSM hooks can't modify return value!\n");
		return -EINVAL;
	}

	if (!tnum_is_unknown(enforce_attach_type_range) &&
	    tnum_in(enforce_attach_type_range, reg->var_off))
		env->prog->enforce_expected_attach_type = 1;
	return 0;
}

static int check_global_ret_scalar_reg(struct bpf_verifier_env *env, u32 regno)
{
	struct bpf_reg_state *reg;
	int err;

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

	/* Pointers to arena are safe to pass between subprograms. */
	if (is_arena_reg(env, regno))
		return 0;

	if (is_pointer_value(env, regno)) {
		verbose(env, "R%d leaks addr as return value\n", regno);
		return -EACCES;
	}

	reg = reg_state(env, regno);
	if (reg->type != SCALAR_VALUE) {
		verbose(env, "At subprogram exit the register R%d is not a scalar value (%s)\n",
			regno, reg_type_str(env, reg->type));
		return -EINVAL;
	}

	return 0;
}

static int check_global_subprog_return_code(struct bpf_verifier_env *env)
{
	struct bpf_func_state *cur_frame = cur_func(env);
	u32 subprog = cur_frame->subprogno;
	u32 i, nregs;
	int err;

	if (subprog_returns_void(env, subprog))
		return 0;

	nregs = bpf_ret_reg_pair(env, subprog) ? 2 : 1;
	for (i = 0; i < nregs; i++) {
		err = check_global_ret_scalar_reg(env, ret_regs[i]);
		if (err)
			return err;
	}

	return 0;
}

/* Bitmask with 1s for all caller saved registers */
#define ALL_CALLER_SAVED_REGS ((1u << CALLER_SAVED_REGS) - 1)

/* True if do_misc_fixups() replaces calls to helper number 'imm',
 * replacement patch is presumed to follow bpf_fastcall contract
 * (see mark_fastcall_pattern_for_call() below).
 */
bool bpf_verifier_inlines_helper_call(struct bpf_verifier_env *env, s32 imm)
{
	switch (imm) {
#ifdef CONFIG_X86_64
	case BPF_FUNC_get_smp_processor_id:
#ifdef CONFIG_SMP
	case BPF_FUNC_get_current_task_btf:
	case BPF_FUNC_get_current_task:
#endif
		return env->prog->jit_requested && bpf_jit_supports_percpu_insn();
#endif
	default:
		return false;
	}
}

/* If @call is a kfunc or helper call, fills @cs and returns true,
 * otherwise returns false.
 */
bool bpf_get_call_summary(struct bpf_verifier_env *env, struct bpf_insn *call,
			  struct bpf_call_summary *cs)
{
	struct bpf_call_arg_meta meta;
	const struct bpf_func_proto *fn;
	int i;

	if (bpf_helper_call(call)) {
		if (bpf_get_helper_proto(env, call->imm, &fn) < 0)
			/* error would be reported later */
			return false;
		cs->fastcall = fn->allow_fastcall &&
			       (bpf_verifier_inlines_helper_call(env, call->imm) ||
				bpf_jit_inlines_helper_call(call->imm));
		cs->is_void = fn->ret_type == RET_VOID;
		cs->arg_slot_cnt = 0;
		for (i = 0; i < ARRAY_SIZE(fn->arg_type); ++i) {
			if (fn->arg_type[i] == ARG_UNUSED)
				break;
			cs->arg_slot_cnt++;
		}
		return true;
	}

	if (bpf_pseudo_kfunc_call(call)) {
		int err;

		err = bpf_fetch_kfunc_arg_meta(env, call->imm, call->off, &meta);
		if (err < 0)
			/* error would be reported later */
			return false;
		cs->arg_slot_cnt = btf_proto_slots(meta.btf, meta.func_proto);
		cs->fastcall = meta.kfunc_flags & KF_FASTCALL;
		cs->is_void = btf_type_is_void(btf_type_by_id(meta.btf, meta.func_proto->type));
		return true;
	}

	return false;
}

/* LLVM define a bpf_fastcall function attribute.
 * This attribute means that function scratches only some of
 * the caller saved registers defined by ABI.
 * For BPF the set of such registers could be defined as follows:
 * - R0 is scratched only if function is non-void;
 * - R1-R5 are scratched only if corresponding parameter type is defined
 *   in the function prototype.
 *
 * The contract between kernel and clang allows to simultaneously use
 * such functions and maintain backwards compatibility with old
 * kernels that don't understand bpf_fastcall calls:
 *
 * - for bpf_fastcall calls clang allocates registers as-if relevant r0-r5
 *   registers are not scratched by the call;
 *
 * - as a post-processing step, clang visits each bpf_fastcall call and adds
 *   spill/fill for every live r0-r5;
 *
 * - stack offsets used for the spill/fill are allocated as lowest
 *   stack offsets in whole function and are not used for any other
 *   purposes;
 *
 * - when kernel loads a program, it looks for such patterns
 *   (bpf_fastcall function surrounded by spills/fills) and checks if
 *   spill/fill stack offsets are used exclusively in fastcall patterns;
 *
 * - if so, and if verifier or current JIT inlines the call to the
 *   bpf_fastcall function (e.g. a helper call), kernel removes unnecessary
 *   spill/fill pairs;
 *
 * - when old kernel loads a program, presence of spill/fill pairs
 *   keeps BPF program valid, albeit slightly less efficient.
 *
 * For example:
 *
 *   r1 = 1;
 *   r2 = 2;
 *   *(u64 *)(r10 - 8)  = r1;            r1 = 1;
 *   *(u64 *)(r10 - 16) = r2;            r2 = 2;
 *   call %[to_be_inlined]         -->   call %[to_be_inlined]
 *   r2 = *(u64 *)(r10 - 16);            r0 = r1;
 *   r1 = *(u64 *)(r10 - 8);             r0 += r2;
 *   r0 = r1;                            exit;
 *   r0 += r2;
 *   exit;
 *
 * The purpose of mark_fastcall_pattern_for_call is to:
 * - look for such patterns;
 * - mark spill and fill instructions in env->insn_aux_data[*].fastcall_pattern;
 * - mark set env->insn_aux_data[*].fastcall_spills_num for call instruction;
 * - update env->subprog_info[*]->fastcall_stack_off to find an offset
 *   at which bpf_fastcall spill/fill stack slots start;
 * - update env->subprog_info[*]->keep_fastcall_stack.
 *
 * The .fastcall_pattern and .fastcall_stack_off are used by
 * check_fastcall_stack_contract() to check if every stack access to
 * fastcall spill/fill stack slot originates from spill/fill
 * instructions, members of fastcall patterns.
 *
 * If such condition holds true for a subprogram, fastcall patterns could
 * be rewritten by remove_fastcall_spills_fills().
 * Otherwise bpf_fastcall patterns are not changed in the subprogram
 * (code, presumably, generated by an older clang version).
 *
 * For example, it is *not* safe to remove spill/fill below:
 *
 *   r1 = 1;
 *   *(u64 *)(r10 - 8)  = r1;            r1 = 1;
 *   call %[to_be_inlined]         -->   call %[to_be_inlined]
 *   r1 = *(u64 *)(r10 - 8);             r0 = *(u64 *)(r10 - 8);  <---- wrong !!!
 *   r0 = *(u64 *)(r10 - 8);             r0 += r1;
 *   r0 += r1;                           exit;
 *   exit;
 *
 * Both uses of the marks assume that a pattern is entered at its first
 * spill and thus executes as a unit, hence a pattern is not grown past
 * an instruction targeted by a jump.
 */
static void mark_fastcall_pattern_for_call(struct bpf_verifier_env *env,
					   struct bpf_subprog_info *subprog,
					   int insn_idx, s16 lowest_off)
{
	struct bpf_insn *insns = env->prog->insnsi, *stx, *ldx;
	struct bpf_insn *call = &env->prog->insnsi[insn_idx];
	u32 clobbered_regs_mask;
	struct bpf_call_summary cs;
	u32 expected_regs_mask;
	s16 off;
	int i;

	if (!bpf_get_call_summary(env, call, &cs))
		return;

	/* A bitmask specifying which caller saved registers are clobbered
	 * by a call to a helper/kfunc *as if* this helper/kfunc follows
	 * bpf_fastcall contract:
	 * - includes R0 if function is non-void;
	 * - includes R1-R5 if corresponding parameter has is described
	 *   in the function prototype.
	 */
	clobbered_regs_mask = GENMASK(cs.arg_slot_cnt, cs.is_void ? 1 : 0);
	/* e.g. if helper call clobbers r{0,1}, expect r{2,3,4,5} in the pattern */
	expected_regs_mask = ~clobbered_regs_mask & ALL_CALLER_SAVED_REGS;

	/* match pairs of form:
	 *
	 * *(u64 *)(r10 - Y) = rX   (where Y % 8 == 0)
	 * ...
	 * call %[to_be_inlined]
	 * ...
	 * rX = *(u64 *)(r10 - Y)
	 */
	for (i = 1, off = lowest_off; i <= ARRAY_SIZE(caller_saved); ++i, off += BPF_REG_SIZE) {
		if (insn_idx - i < 0 || insn_idx + i >= env->prog->len)
			break;
		/* stx/ldx/call must not be a jump targets, a jump to the first stx is fine */
		if (bpf_is_jump_target(env, insn_idx - i + 1) ||
		    bpf_is_jump_target(env, insn_idx + i))
			break;
		stx = &insns[insn_idx - i];
		ldx = &insns[insn_idx + i];
		/* must be a stack spill/fill pair */
		if (stx->code != (BPF_STX | BPF_MEM | BPF_DW) ||
		    ldx->code != (BPF_LDX | BPF_MEM | BPF_DW) ||
		    stx->dst_reg != BPF_REG_10 ||
		    ldx->src_reg != BPF_REG_10)
			break;
		/* must be a spill/fill for the same reg */
		if (stx->src_reg != ldx->dst_reg)
			break;
		/* must be one of the previously unseen registers */
		if ((BIT(stx->src_reg) & expected_regs_mask) == 0)
			break;
		/* must be a spill/fill for the same expected offset,
		 * no need to check offset alignment, BPF_DW stack access
		 * is always 8-byte aligned.
		 */
		if (stx->off != off || ldx->off != off)
			break;
		expected_regs_mask &= ~BIT(stx->src_reg);
		env->insn_aux_data[insn_idx - i].fastcall_pattern = 1;
		env->insn_aux_data[insn_idx + i].fastcall_pattern = 1;
	}
	if (i == 1)
		return;

	/* Conditionally set 'fastcall_spills_num' to allow forward
	 * compatibility when more helper functions are marked as
	 * bpf_fastcall at compile time than current kernel supports, e.g:
	 *
	 *   1: *(u64 *)(r10 - 8) = r1
	 *   2: call A                  ;; assume A is bpf_fastcall for current kernel
	 *   3: r1 = *(u64 *)(r10 - 8)
	 *   4: *(u64 *)(r10 - 8) = r1
	 *   5: call B                  ;; assume B is not bpf_fastcall for current kernel
	 *   6: r1 = *(u64 *)(r10 - 8)
	 *
	 * There is no need to block bpf_fastcall rewrite for such program.
	 * Set 'fastcall_pattern' for both calls to keep check_fastcall_stack_contract() happy,
	 * don't set 'fastcall_spills_num' for call B so that remove_fastcall_spills_fills()
	 * does not remove spill/fill pair {4,6}.
	 */
	if (cs.fastcall)
		env->insn_aux_data[insn_idx].fastcall_spills_num = i - 1;
	else
		subprog->keep_fastcall_stack = 1;
	subprog->fastcall_stack_off = min(subprog->fastcall_stack_off, off);
}

static int mark_fastcall_patterns(struct bpf_verifier_env *env)
{
	struct bpf_subprog_info *subprog = env->subprog_info;
	struct bpf_insn *insn;
	s16 lowest_off;
	int s, i;

	for (s = 0; s < env->subprog_cnt; ++s, ++subprog) {
		/* find lowest stack spill offset used in this subprog */
		lowest_off = 0;
		for (i = subprog->start; i < (subprog + 1)->start; ++i) {
			insn = env->prog->insnsi + i;
			if (insn->code != (BPF_STX | BPF_MEM | BPF_DW) ||
			    insn->dst_reg != BPF_REG_10)
				continue;
			lowest_off = min(lowest_off, insn->off);
		}
		/* use this offset to find fastcall patterns */
		for (i = subprog->start; i < (subprog + 1)->start; ++i) {
			insn = env->prog->insnsi + i;
			if (insn->code != (BPF_JMP | BPF_CALL))
				continue;
			mark_fastcall_pattern_for_call(env, subprog, i, lowest_off);
		}
	}
	return 0;
}

static void adjust_btf_func(struct bpf_verifier_env *env)
{
	struct bpf_prog_aux *aux = env->prog->aux;
	int i;

	if (!aux->func_info)
		return;

	/* func_info is not available for hidden subprogs */
	for (i = 0; i < env->subprog_cnt - env->hidden_subprog_cnt; i++)
		aux->func_info[i].insn_off = env->subprog_info[i].start;
}

/* Find id in idset and increment its count, or add new entry */
static void idset_cnt_inc(struct bpf_idset *idset, u32 id)
{
	u32 i;

	for (i = 0; i < idset->num_ids; i++) {
		if (idset->entries[i].id == id) {
			idset->entries[i].cnt++;
			return;
		}
	}
	/* New id */
	if (idset->num_ids < BPF_ID_MAP_SIZE) {
		idset->entries[idset->num_ids].id = id;
		idset->entries[idset->num_ids].cnt = 1;
		idset->num_ids++;
	}
}

/* Find id in idset and return its count, or 0 if not found */
static u32 idset_cnt_get(struct bpf_idset *idset, u32 id)
{
	u32 i;

	for (i = 0; i < idset->num_ids; i++) {
		if (idset->entries[i].id == id)
			return idset->entries[i].cnt;
	}
	return 0;
}

/*
 * Clear singular scalar ids in a state.
 * A register with a non-zero id is called singular if no other register shares
 * the same base id. Such registers can be treated as independent (id=0).
 */
void bpf_clear_singular_ids(struct bpf_verifier_env *env,
			    struct bpf_verifier_state *st)
{
	struct bpf_idset *idset = &env->idset_scratch;
	struct bpf_func_state *func;
	struct bpf_reg_state *reg;

	idset->num_ids = 0;

	bpf_for_each_reg_in_vstate(st, func, reg, ({
		if (reg->type != SCALAR_VALUE)
			continue;
		if (!reg->id)
			continue;
		idset_cnt_inc(idset, reg->id & ~BPF_ADD_CONST);
	}));

	bpf_for_each_reg_in_vstate(st, func, reg, ({
		if (reg->type != SCALAR_VALUE)
			continue;
		if (!reg->id)
			continue;
		if (idset_cnt_get(idset, reg->id & ~BPF_ADD_CONST) == 1)
			clear_scalar_id(reg);
	}));
}

/* Return true if it's OK to have the same insn return a different type. */
static bool reg_type_mismatch_ok(enum bpf_reg_type type)
{
	switch (base_type(type)) {
	case PTR_TO_CTX:
	case PTR_TO_SOCKET:
	case PTR_TO_SOCK_COMMON:
	case PTR_TO_TCP_SOCK:
	case PTR_TO_XDP_SOCK:
	case PTR_TO_BTF_ID:
	case PTR_TO_ARENA:
		return false;
	case PTR_TO_MEM:
		return !bpf_may_fault_on_deref(type);
	default:
		return true;
	}
}

/* If an instruction was previously used with particular pointer types, then we
 * need to be careful to avoid cases such as the below, where it may be ok
 * for one branch accessing the pointer, but not ok for the other branch:
 *
 * R1 = sock_ptr
 * goto X;
 * ...
 * R1 = some_other_valid_ptr;
 * goto X;
 * ...
 * R2 = *(u32 *)(R1 + 0);
 */
static bool reg_type_mismatch(enum bpf_reg_type src, enum bpf_reg_type prev)
{
	return src != prev && (!reg_type_mismatch_ok(src) ||
			       !reg_type_mismatch_ok(prev));
}

static bool is_ptr_to_mem(enum bpf_reg_type type)
{
	return base_type(type) == PTR_TO_MEM;
}

static enum bpf_reg_type merge_ptr_types(enum bpf_reg_type type_a,
					 enum bpf_reg_type type_b)
{
	bool to_mem = is_ptr_to_mem(type_a) || is_ptr_to_mem(type_b);
	enum bpf_reg_type type_merged = to_mem ? PTR_TO_MEM : PTR_TO_BTF_ID;

	if (bpf_may_fault_on_deref(type_a) || bpf_may_fault_on_deref(type_b))
		type_merged |= to_mem ? MEM_RDONLY | PTR_UNTRUSTED :
					PTR_UNTRUSTED;
	else
		type_merged |= ((type_a | type_b) & MEM_RDONLY);
	return type_merged;
}

static int save_aux_ptr_type(struct bpf_verifier_env *env, enum bpf_reg_type type,
			     bool allow_trust_mismatch)
{
	enum bpf_reg_type *prev_type = &env->insn_aux_data[env->insn_idx].ptr_type;

	if (*prev_type == NOT_INIT) {
		/* Saw a valid insn
		 * dst_reg = *(u32 *)(src_reg + off)
		 * save type to validate intersecting paths
		 */
		*prev_type = type;
	} else if (reg_type_mismatch(type, *prev_type)) {
		/* Abuser program is trying to use the same insn
		 * dst_reg = *(u32*) (src_reg + off)
		 * with different pointer types:
		 * src_reg == ctx in one branch and
		 * src_reg == stack|map in some other branch.
		 * Reject it.
		 */
		if (allow_trust_mismatch &&
		    bpf_is_ptr_to_mem_or_btf_id(type) &&
		    bpf_is_ptr_to_mem_or_btf_id(*prev_type)) {
			/*
			 * Have to support a use case when one path through
			 * the program yields a TRUSTED pointer while another
			 * is UNTRUSTED. Merge them into a type which keeps
			 * the BPF_PROBE_MEM/BPF_PROBE_MEMSX rewrite when
			 * either side needs it.
			 */
			*prev_type = merge_ptr_types(type, *prev_type);
		} else {
			verbose(env, "same insn cannot be used with different pointers\n");
			return -EINVAL;
		}
	}

	return 0;
}

enum {
	PROCESS_BPF_EXIT = 1,
	INSN_IDX_UPDATED = 2,
};

static int process_bpf_exit_full(struct bpf_verifier_env *env,
				 bool *do_print_state,
				 bool exception_exit)
{
	struct bpf_func_state *cur_frame = cur_func(env);

	/* We must do check_reference_leak here before
	 * prepare_func_exit to handle the case when
	 * state->curframe > 0, it may be a callback function,
	 * for which reference_state must match caller reference
	 * state when it exits.
	 */
	int err = check_resource_leak(env, exception_exit,
				      exception_exit || !env->cur_state->curframe,
				      exception_exit ? "bpf_throw" :
				      "BPF_EXIT instruction in main prog");
	if (err)
		return err;

	/* The side effect of the prepare_func_exit which is
	 * being skipped is that it frees bpf_func_state.
	 * Typically, process_bpf_exit will only be hit with
	 * outermost exit. copy_verifier_state in pop_stack will
	 * handle freeing of any extra bpf_func_state left over
	 * from not processing all nested function exits. We
	 * also skip return code checks as they are not needed
	 * for exceptional exits.
	 */
	if (exception_exit)
		return PROCESS_BPF_EXIT;

	if (env->cur_state->curframe) {
		/* exit from nested function */
		err = prepare_func_exit(env, &env->insn_idx);
		if (err)
			return err;
		*do_print_state = true;
		return INSN_IDX_UPDATED;
	}

	/*
	 * Return from a regular global subprogram differs from return
	 * from the main program or async/exception callback.
	 * Main program exit implies return code restrictions
	 * that depend on program type.
	 * Exit from exception callback is equivalent to main program exit.
	 * Exit from async callback implies return code restrictions
	 * that depend on async scheduling mechanism.
	 */
	if (cur_frame->subprogno &&
	    !cur_frame->in_async_callback_fn &&
	    !cur_frame->in_exception_callback_fn)
		err = check_global_subprog_return_code(env);
	else
		err = check_return_code(env, BPF_REG_0, "R0");
	if (err)
		return err;
	return PROCESS_BPF_EXIT;
}

static int indirect_jump_min_max_index(struct bpf_verifier_env *env,
				       int regno,
				       struct bpf_map *map,
				       u32 *pmin_index, u32 *pmax_index)
{
	struct bpf_reg_state *reg = reg_state(env, regno);
	u64 min_index = reg_umin(reg);
	u64 max_index = reg_umax(reg);
	const u32 size = 8;

	if (min_index > (u64) U32_MAX * size) {
		verbose(env, "the sum of R%u umin_value %llu is too big\n", regno, reg_umin(reg));
		return -ERANGE;
	}
	if (max_index > (u64) U32_MAX * size) {
		verbose(env, "the sum of R%u umax_value %llu is too big\n", regno, reg_umax(reg));
		return -ERANGE;
	}

	min_index /= size;
	max_index /= size;

	if (max_index >= map->max_entries) {
		verbose(env, "R%u points to outside of jump table: [%llu,%llu] max_entries %u\n",
			     regno, min_index, max_index, map->max_entries);
		return -EINVAL;
	}

	*pmin_index = min_index;
	*pmax_index = max_index;
	return 0;
}

static int reject_gotox_out_of_subprog(struct bpf_verifier_env *env, u32 target,
				       u32 subprog_start, u32 subprog_end)
{
	verbose(env, "indirect jump from insn %d to %u leaves the subprog [%u,%u)\n",
		env->insn_idx, target, subprog_start, subprog_end);
	bpf_diag_program_structure(
		env, env->insn_idx, "indirect jump leaves subprogram",
		"Keep every reachable jump-table target inside the subprogram of the indirect jump.",
		"Instruction %d can jump indirectly to instruction %u, which is outside its own subprogram [%u,%u).",
		env->insn_idx, target, subprog_start, subprog_end);
	return -EINVAL;
}

/* gotox *dst_reg */
static int check_indirect_jump(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	struct bpf_verifier_state *other_branch;
	struct bpf_subprog_info *subprog;
	u32 subprog_start, subprog_end;
	struct bpf_reg_state *dst_reg;
	struct bpf_map *map;
	u32 min_index, max_index;
	int err = 0;
	int n;
	int i;

	dst_reg = reg_state(env, insn->dst_reg);
	if (dst_reg->type != PTR_TO_INSN) {
		verbose(env, "R%d has type %s, expected PTR_TO_INSN\n",
			     insn->dst_reg, reg_type_str(env, dst_reg->type));
		return -EINVAL;
	}

	map = dst_reg->map_ptr;
	if (verifier_bug_if(!map, env, "R%d has an empty map pointer", insn->dst_reg))
		return -EFAULT;

	if (verifier_bug_if(map->map_type != BPF_MAP_TYPE_INSN_ARRAY, env,
			    "R%d has incorrect map type %d", insn->dst_reg, map->map_type))
		return -EFAULT;

	err = indirect_jump_min_max_index(env, insn->dst_reg, map, &min_index, &max_index);
	if (err)
		return err;

	/* Ensure that the buffer is large enough */
	if (!env->gotox_tmp_buf || env->gotox_tmp_buf->cnt < max_index - min_index + 1) {
		env->gotox_tmp_buf = bpf_iarray_realloc(env->gotox_tmp_buf,
						        max_index - min_index + 1);
		if (!env->gotox_tmp_buf)
			return -ENOMEM;
	}

	n = bpf_copy_insn_array_uniq(map, min_index, max_index, env->gotox_tmp_buf->items);
	if (n < 0)
		return n;
	if (n == 0) {
		verbose(env, "register R%d doesn't point to any offset in map id=%d\n",
			     insn->dst_reg, map->id);
		return -EINVAL;
	}

	subprog = bpf_find_containing_subprog(env, env->insn_idx);
	if (verifier_bug_if(!subprog, env, "no subprog contains insn %d", env->insn_idx))
		return -EFAULT;
	subprog_start = subprog->start;
	subprog_end = (subprog + 1)->start;

	/*
	 * Maps are confined to a subprog, see compute_subprog_jts(), and the
	 * targets are sorted and free of duplicates, see sort_insn_array_uniq(),
	 * so either all of them belong to this subprog or none of them does.
	 */
	if (env->gotox_tmp_buf->items[0] < subprog_start)
		return reject_gotox_out_of_subprog(env, env->gotox_tmp_buf->items[0],
						   subprog_start, subprog_end);
	if (env->gotox_tmp_buf->items[n - 1] >= subprog_end)
		return reject_gotox_out_of_subprog(env, env->gotox_tmp_buf->items[n - 1],
						   subprog_start, subprog_end);

	for (i = 0; i < n - 1; i++) {
		mark_indirect_target(env, env->gotox_tmp_buf->items[i]);
		other_branch = push_stack(env, env->gotox_tmp_buf->items[i],
					  env->insn_idx, env->cur_state->speculative);
		if (IS_ERR(other_branch))
			return PTR_ERR(other_branch);
	}
	env->insn_idx = env->gotox_tmp_buf->items[n-1];
	mark_indirect_target(env, env->insn_idx);
	return INSN_IDX_UPDATED;
}

static int do_check_insn(struct bpf_verifier_env *env, bool *do_print_state)
{
	int err;
	struct bpf_insn *insn = &env->prog->insnsi[env->insn_idx];
	u8 class = BPF_CLASS(insn->code);

	switch (class) {
	case BPF_ALU:
	case BPF_ALU64:
		return check_alu_op(env, insn);

	case BPF_LDX:
		return check_load_mem(env, insn, false,
				      BPF_MODE(insn->code) == BPF_MEMSX,
				      true, "ldx");

	case BPF_STX:
		if (BPF_MODE(insn->code) == BPF_ATOMIC)
			return check_atomic(env, insn);
		return check_store_reg(env, insn, false);

	case BPF_ST: {
		/* Handle stack arg write (store immediate) */
		if (is_stack_arg_st(insn)) {
			struct bpf_verifier_state *vstate = env->cur_state;
			struct bpf_func_state *state = vstate->frame[vstate->curframe];

			return check_stack_arg_write(env, state, insn->off, NULL);
		}

		struct bpf_reg_state arena, *dst_reg;
		enum bpf_reg_type dst_reg_type;

		err = check_reg_arg(env, insn->dst_reg, SRC_OP);
		if (err)
			return err;

		dst_reg = mem_access_reg(env, insn->dst_reg, &arena);
		dst_reg_type = dst_reg->type;

		err = check_mem_access(env, env->insn_idx, dst_reg, argno_from_reg(insn->dst_reg),
				       insn->off, BPF_SIZE(insn->code),
				       BPF_WRITE, -1, false, false);
		if (err)
			return err;

		return save_aux_ptr_type(env, dst_reg_type, false);
	}
	case BPF_JMP:
	case BPF_JMP32: {
		u8 opcode = BPF_OP(insn->code);

		env->jmps_processed++;
		if (opcode == BPF_CALL) {
			if (env->cur_state->active_locks) {
				/* similar to static subprog calls callx is allowed under a lock */
				if (!bpf_is_callx(insn) &&
				    ((insn->src_reg == BPF_REG_0 &&
				      insn->imm != BPF_FUNC_spin_unlock &&
				      insn->imm != BPF_FUNC_kptr_xchg) ||
				     (insn->src_reg == BPF_PSEUDO_KFUNC_CALL &&
				      !kfunc_spin_allowed(env, insn->imm, insn->off)))) {
					verbose(env,
						"function calls are not allowed while holding a lock\n");
					bpf_diag_ctx_active(
						env, env->insn_idx,
						"function call", BPF_DIAG_CONTEXT_LOCK,
						"Release the BPF spin lock before making this call, or move the call outside the locked region.");
					return -EINVAL;
				}
			}
			mark_reg_scratched(env, BPF_REG_0);
			if (bpf_in_stack_arg_cnt(&env->subprog_info[cur_func(env)->subprogno]))
				cur_func(env)->no_stack_arg_load = true;
			if (bpf_is_callx(insn))
				return check_func_callx(env, insn, &env->insn_idx);
			if (insn->src_reg == BPF_PSEUDO_CALL)
				return check_func_call(env, insn, &env->insn_idx);
			if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL)
				return check_kfunc_call(env, insn, &env->insn_idx);
			return check_helper_call(env, insn, &env->insn_idx);
		} else if (opcode == BPF_JA) {
			if (BPF_SRC(insn->code) == BPF_X)
				return check_indirect_jump(env, insn);

			if (class == BPF_JMP)
				env->insn_idx += insn->off + 1;
			else
				env->insn_idx += insn->imm + 1;
			return INSN_IDX_UPDATED;
		} else if (opcode == BPF_EXIT) {
			return process_bpf_exit_full(env, do_print_state, false);
		}
		return check_cond_jmp_op(env, insn, &env->insn_idx);
	}
	case BPF_LD: {
		u8 mode = BPF_MODE(insn->code);

		if (mode == BPF_ABS || mode == BPF_IND)
			return check_ld_abs(env, insn);

		if (mode == BPF_IMM) {
			err = check_ld_imm(env, insn);
			if (err)
				return err;

			env->insn_idx++;
			sanitize_mark_insn_seen(env);
		}
		return 0;
	}
	}
	/* all class values are handled above. silence compiler warning */
	return -EFAULT;
}

/*
 * Push the loop entered at insn_idx onto the stack. Usually this adds a single
 * entry on top of its enclosing loop. However, an edge may enter an inner loop
 * directly, bypassing the header(s) of its enclosing loop(s), e.g.:
 *
 *   1: for (...):       // enclosing loop, header at 1
 *   2:   for (...):     // inner loop, header at 2
 *        ...
 *   3: if ...:
 *        goto 2b;       // enters loop 2 without going through header 1
 *
 * Such a bypass makes the enclosing loop irreducible, so its header is missing
 * from the stack and both headers (1) and (2) need to be pushed onto stack.
 * Only the innermost loop (the one actually entered at insn_idx) carries SCEV bounds;
 * the bypassed ancestors are irreducible and pushed as non-terminating.
 *
 * Assumes loop_stack_pop() has already truncated the stack to the common ancestor
 * of the bpf_loop_at_index(env->insn_idx) and whatever was at the top of the loop stack.
 */
static int loop_stack_push(struct bpf_verifier_env *env, bool *pushed)
{
	struct bpf_insn_aux_data *aux = env->insn_aux_data;
	struct bpf_func_state *frame = cur_func(env);
	struct loop_stack_entry *loop_stack = frame->loop_stack;
	u32 missing_headers[LOOP_STACK_SIZE];
	u32 cnt = frame->loop_stack_cnt;
	u32 num_missing = 0;
	int h;

	*pushed = false;

	for (h = bpf_loop_at_index(env, env->insn_idx); h >= 0; h = aux[h].loop_header, num_missing++) {
		if (cnt && loop_stack[cnt - 1].loop_id == h)
			break;
		if (num_missing == LOOP_STACK_SIZE)
			goto e2big;
		missing_headers[num_missing] = h;
	}

	if (num_missing == 0)
		return 0;
	if (cnt + num_missing > LOOP_STACK_SIZE)
		goto e2big;
	frame->loop_stack = realloc_array(frame->loop_stack, cnt, cnt + num_missing,
					 sizeof(*frame->loop_stack));
	if (!frame->loop_stack)
		return -ENOMEM;
	loop_stack = frame->loop_stack;

	for (; num_missing; num_missing--, cnt++) {
		h = missing_headers[num_missing - 1];
		loop_stack[cnt] = (struct loop_stack_entry){ .loop_id = h };
		if (env->log.level & BPF_LOG_LEVEL2)
			verbose(env, "entering loop %d\n", h);
		*pushed = true;
	}
	frame->loop_stack_cnt = cnt;
	return 0;

e2big:
	verbose(env, "Too many nested loops (%d/%d) at %d\n", cnt, num_missing, env->insn_idx);
	return -E2BIG;
}

/*
 * An exit from a loop can cross several nested loops, e.g.:
 *
 *   1: for (...):
 *   2:   for (...):
 *   3:     for (...):
 *            if ...:    // before goto the loop stack is [1, 2, 3 <top>]
 *              goto 1b; // after goto it should become [1]
 */
static int loop_stack_pop(struct bpf_verifier_env *env)
{
	struct bpf_insn_aux_data *aux = env->insn_aux_data;
	struct bpf_func_state *frame = cur_func(env);
	int new_cnt = 0;
	int h, i;

	/*
	 * Walk the loop nest of insn_idx outwards (innermost first) and stop at
	 * the first loop that is present on the stack - that loop is the common
	 * ancestor and becomes the new top. If no enclosing loop is on the
	 * stack, drop all loops.
	 */
	for (h = bpf_loop_at_index(env, env->insn_idx); h >= 0; h = aux[h].loop_header) {
		for (i = frame->loop_stack_cnt - 1; i >= 0; i--) {
			if (frame->loop_stack[i].loop_id == h) {
				new_cnt = i + 1;
				goto pop;
			}
		}
	}

pop:
	if (env->log.level & BPF_LOG_LEVEL2)
		for (i = frame->loop_stack_cnt - 1; i >= new_cnt; i--)
			verbose(env, "exiting loop %d\n", frame->loop_stack[i].loop_id);
	frame->loop_stack_cnt = new_cnt;
	return 0;
}

static int maybe_clamp_scev_regs(struct bpf_verifier_env *env)
{
	struct bpf_func_state *frame = cur_func(env);
	struct loop_stack_entry *entry;

	if (frame->loop_stack_cnt == 0) {
		verifier_bug(env, "%s: loop stack empty at %d", __FUNCTION__, env->insn_idx);
		return -EFAULT;
	}

	entry = &frame->loop_stack[frame->loop_stack_cnt - 1];
	if (!entry->terminates)
		return 0;

	return bpf_clamp_scev_regs(env, frame, env->insn_idx, entry->entry_state,
				   entry->max_header_count);
}

static int handle_loop_entry_exit(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state *cur = env->cur_state;
	struct bpf_func_state *frame = cur_func(env);
	struct loop_stack_entry *entry;
	struct bpf_loop_iters iters;
	bool pushed, terminates;
	int err;

	err = loop_stack_pop(env);
	if (err)
		return err;

	err = loop_stack_push(env, &pushed);
	if (err)
		return err;

	if (frame->loop_stack_cnt == 0)
		return 0;

	entry = &frame->loop_stack[frame->loop_stack_cnt - 1];
	if (env->insn_idx != entry->loop_id)
		return 0;

	/* If nothing was pushed and env->insn_idx is a loop header, we've taken a backedge. */
	if (!pushed)
		return maybe_clamp_scev_regs(env);

	err = bpf_compute_loop_iters(env, env->cur_state, &iters);
	if (err < 0)
		return err;

	terminates = err == 1;
	if (!terminates)
		return 0;

	/* Create a loop_entry checkpoint before widening */
	err = bpf_split_cur_state(env);
	if (err)
		return err;

	entry->min_header_count = iters.min_header_count;
	entry->max_header_count = iters.max_header_count;
	entry->entry_state = cur->parent;
	entry->terminates = true;
	err = bpf_widen_scev_regs(env, cur, cur->parent, &iters);
	if (err < 0)
		return err;
	return 0;
}

static int do_check(struct bpf_verifier_env *env)
{
	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
	struct bpf_verifier_state *state = env->cur_state;
	struct bpf_insn *insns = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	bool do_print_state = false;
	int prev_insn_idx = -1;

	for (;;) {
		struct bpf_insn *insn;
		struct bpf_insn_aux_data *insn_aux;
		int err;

		if (signal_pending(current))
			return -EAGAIN;

		if (need_resched())
			cond_resched();

		/* reset current history entry on each new instruction */
		env->cur_hist_ent = NULL;

		env->prev_insn_idx = prev_insn_idx;
		if (env->insn_idx >= insn_cnt) {
			verbose(env, "invalid insn idx %d insn_cnt %d\n",
				env->insn_idx, insn_cnt);
			return -EFAULT;
		}

		insn = &insns[env->insn_idx];
		insn_aux = &env->insn_aux_data[env->insn_idx];

		account_processed_insn(env);

		if (env->insn_processed > BPF_COMPLEXITY_LIMIT_INSNS) {
			verbose(env,
				"BPF program is too large. Processed %d insn\n",
				env->insn_processed);
			return -E2BIG;
		}

		state->last_insn_idx = env->prev_insn_idx;
		state->insn_idx = env->insn_idx;
		/*
		 * Record the incoming edge so active and queued paths use the same
		 * branch-recording path. A zero-offset conditional has identical
		 * successors, so its outcome cannot be reconstructed from the edge.
		 */
		if (!state->speculative && prev_insn_idx >= 0 && prev_insn_idx < insn_cnt) {
			struct bpf_insn *prev_insn = &insns[prev_insn_idx];
			int fallthrough_idx = prev_insn_idx + 1;
			int branch_idx = prev_insn_idx + bpf_jmp_offset(prev_insn) + 1;
			u8 class = BPF_CLASS(prev_insn->code);
			u8 opcode = BPF_OP(prev_insn->code);

			if ((class == BPF_JMP || class == BPF_JMP32) &&
			    opcode != BPF_JA && opcode != BPF_CALL && opcode != BPF_EXIT &&
			    opcode <= BPF_JCOND && branch_idx != fallthrough_idx) {
				if (env->insn_idx == branch_idx)
					bpf_diag_record_branch(env, prev_insn_idx, true);
				else if (env->insn_idx == fallthrough_idx)
					bpf_diag_record_branch(env, prev_insn_idx, false);
			}
		}

		/*
		 * Possibly widen the registers before creating a checkpoint
		 * in bpf_is_state_visited(). The next loop iteration will
		 * have a chance to hit this checkpoint and converge.
		 */
		err = handle_loop_entry_exit(env);
		if (err)
			return err;

		if (bpf_is_prune_point(env, env->insn_idx)) {
			err = bpf_is_state_visited(env, env->insn_idx);
			if (err < 0)
				return err;
			if (err == 1) {
				/* found equivalent state, can prune the search */
				if (env->log.level & BPF_LOG_LEVEL) {
					if (do_print_state)
						verbose(env, "\nfrom %d to %d%s: safe\n",
							env->prev_insn_idx, env->insn_idx,
							env->cur_state->speculative ?
							" (speculative execution)" : "");
					else
						verbose(env, "%d: safe\n", env->insn_idx);
				}
				goto process_bpf_exit;
			}
		}

		if (bpf_is_jmp_point(env, env->insn_idx)) {
			err = bpf_push_jmp_history(env, state, 0, 0, 0, NULL, 0);
			if (err)
				return err;
		}

		if (env->log.level & BPF_LOG_LEVEL2 && do_print_state) {
			verbose(env, "\nfrom %d to %d%s:",
				env->prev_insn_idx, env->insn_idx,
				env->cur_state->speculative ?
				" (speculative execution)" : "");
			print_verifier_state(env, state, state->curframe, true);
			do_print_state = false;
		}

		if (bpf_loop_at_index(env, env->insn_idx) >= 0 &&
		    cur_func(env)->loop_stack_cnt == 0) {
			verifier_bug(env, "loop stack empty at %d, while inside the loop %d\n",
				     env->insn_idx, bpf_loop_at_index(env, env->insn_idx));
			return -EFAULT;
		}

		if (env->log.level & BPF_LOG_LEVEL) {
			if (verifier_state_scratched(env))
				print_insn_state(env, state, state->curframe);

			verbose_linfo(env, env->insn_idx, "; ");
			env->prev_log_pos = env->log.end_pos;
			verbose(env, "%d: ", env->insn_idx);
			bpf_verbose_insn(env, insn);
			verbose(env, "\n");
			env->prev_insn_print_pos = env->log.end_pos - env->prev_log_pos;
			env->prev_log_pos = env->log.end_pos;
		}

		if (bpf_prog_is_offloaded(env->prog->aux)) {
			err = bpf_prog_offload_verify_insn(env, env->insn_idx,
							   env->prev_insn_idx);
			if (err)
				return err;
		}

		sanitize_mark_insn_seen(env);
		prev_insn_idx = env->insn_idx;

		/* Sanity check: precomputed constants must match verifier state */
		if (!state->speculative && insn_aux->const_reg_mask) {
			struct bpf_reg_state *regs = cur_regs(env);
			u16 mask = insn_aux->const_reg_mask;

			for (int r = 0; r < ARRAY_SIZE(insn_aux->const_reg_vals); r++) {
				u32 cval = insn_aux->const_reg_vals[r];

				if (!(mask & BIT(r)))
					continue;
				if (regs[r].type != SCALAR_VALUE)
					continue;
				if (!tnum_is_const(regs[r].var_off))
					continue;
				if (verifier_bug_if((u32)regs[r].var_off.value != cval,
						    env, "const R%d: %u != %llu",
						    r, cval, regs[r].var_off.value))
					return -EFAULT;
			}
		}

		/* Reduce verification complexity by stopping speculative path
		 * verification when a nospec is encountered.
		 */
		if (state->speculative && insn_aux->nospec)
			goto process_bpf_exit;

		err = do_check_insn(env, &do_print_state);
		if (error_recoverable_with_nospec(err) && state->speculative) {
			/* Prevent this speculative path from ever reaching the
			 * insn that would have been unsafe to execute.
			 */
			insn_aux->nospec = true;
			/* If it was an ADD/SUB insn, potentially remove any
			 * markings for alu sanitization.
			 */
			insn_aux->alu_state = 0;
			goto process_bpf_exit;
		} else if (err < 0) {
			return err;
		} else if (err == PROCESS_BPF_EXIT) {
			goto process_bpf_exit;
		} else if (err == INSN_IDX_UPDATED) {
		} else if (err == 0) {
			env->insn_idx++;
		}

		if (state->speculative && insn_aux->nospec_result) {
			/* If we are on a path that performed a jump-op, this
			 * may skip a nospec patched-in after the jump. This can
			 * currently never happen because nospec_result is only
			 * used for the write-ops
			 * `*(size*)(dst_reg+off)=src_reg|imm32` and helper
			 * calls. These must never skip the following insn
			 * (i.e., bpf_insn_successors()'s opcode_info.can_jump
			 * is false). Still, add a warning to document this in
			 * case nospec_result is used elsewhere in the future.
			 *
			 * All non-branch instructions have a single
			 * fall-through edge. For these, nospec_result should
			 * already work.
			 */
			if (verifier_bug_if((BPF_CLASS(insn->code) == BPF_JMP ||
					     BPF_CLASS(insn->code) == BPF_JMP32) &&
					    BPF_OP(insn->code) != BPF_CALL, env,
					    "speculation barrier after jump instruction may not have the desired effect"))
				return -EFAULT;
process_bpf_exit:
			account_current_path(env);
			mark_verifier_state_scratched(env);
			err = bpf_update_branch_counts(env, env->cur_state);
			if (err)
				return err;
			err = pop_stack(env, &prev_insn_idx, &env->insn_idx,
					pop_log);
			if (err < 0) {
				if (err != -ENOENT)
					return err;
				break;
			} else {
				do_print_state = true;
				continue;
			}
		}
	}

	return 0;
}

static int find_btf_percpu_datasec(struct btf *btf)
{
	const struct btf_type *t;
	const char *tname;
	int i, n;

	/*
	 * Both vmlinux and module each have their own ".data..percpu"
	 * DATASECs in BTF. So for module's case, we need to skip vmlinux BTF
	 * types to look at only module's own BTF types.
	 */
	n = btf_nr_types(btf);
	for (i = btf_named_start_id(btf, true); i < n; i++) {
		t = btf_type_by_id(btf, i);
		if (BTF_INFO_KIND(t->info) != BTF_KIND_DATASEC)
			continue;

		tname = btf_name_by_offset(btf, t->name_off);
		if (!strcmp(tname, ".data..percpu"))
			return i;
	}

	return -ENOENT;
}

/*
 * Add btf to the env->used_btfs array. If needed, refcount the
 * corresponding kernel module. To simplify caller's logic
 * in case of error or if btf was added before the function
 * decreases the btf refcount.
 */
static int __add_used_btf(struct bpf_verifier_env *env, struct btf *btf)
{
	struct btf_mod_pair *btf_mod;
	int ret = 0;
	int i;

	/* check whether we recorded this BTF (and maybe module) already */
	for (i = 0; i < env->used_btf_cnt; i++)
		if (env->used_btfs[i].btf == btf)
			goto ret_put;

	if (env->signature) {
		verbose(env, "signed program cannot bind any BTF\n");
		ret = -EACCES;
		goto ret_put;
	}
	if (env->used_btf_cnt >= MAX_USED_BTFS) {
		verbose(env, "The total number of btfs per program has reached the limit of %u\n",
			MAX_USED_BTFS);
		ret = -E2BIG;
		goto ret_put;
	}

	btf_mod = &env->used_btfs[env->used_btf_cnt];
	btf_mod->btf = btf;
	btf_mod->module = NULL;

	/* if we reference variables from kernel module, bump its refcount */
	if (btf_is_module(btf)) {
		btf_mod->module = btf_try_get_module(btf);
		if (!btf_mod->module) {
			ret = -ENXIO;
			goto ret_put;
		}
	}

	env->used_btf_cnt++;
	return 0;

ret_put:
	/* Either error or this BTF was already added */
	btf_put(btf);
	return ret;
}

/* replace pseudo btf_id with kernel symbol address */
static int __check_pseudo_btf_id(struct bpf_verifier_env *env,
				 struct bpf_insn *insn,
				 struct bpf_insn_aux_data *aux,
				 struct btf *btf)
{
	const struct btf_var_secinfo *vsi;
	const struct btf_type *datasec;
	const struct btf_type *t;
	const char *sym_name;
	bool percpu = false;
	u32 type, id = insn->imm;
	s32 datasec_id;
	u64 addr;
	int i;

	t = btf_type_by_id(btf, id);
	if (!t) {
		verbose(env, "ldimm64 insn specifies invalid btf_id %d.\n", id);
		return -ENOENT;
	}

	if (!btf_type_is_var(t) && !btf_type_is_func(t)) {
		verbose(env, "pseudo btf_id %d in ldimm64 isn't KIND_VAR or KIND_FUNC\n", id);
		return -EINVAL;
	}

	sym_name = btf_name_by_offset(btf, t->name_off);
	addr = kallsyms_lookup_name(sym_name);
	if (!addr) {
		verbose(env, "ldimm64 failed to find the address for kernel symbol '%s'.\n",
			sym_name);
		return -ENOENT;
	}
	insn[0].imm = (u32)addr;
	insn[1].imm = addr >> 32;

	if (btf_type_is_func(t)) {
		aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
		aux->btf_var.mem_size = 0;
		return 0;
	}

	datasec_id = find_btf_percpu_datasec(btf);
	if (datasec_id > 0) {
		datasec = btf_type_by_id(btf, datasec_id);
		for_each_vsi(i, datasec, vsi) {
			if (vsi->type == id) {
				percpu = true;
				break;
			}
		}
	}

	type = t->type;
	t = btf_type_skip_modifiers(btf, type, NULL);
	if (percpu) {
		aux->btf_var.reg_type = PTR_TO_BTF_ID | MEM_PERCPU;
		aux->btf_var.btf = btf;
		aux->btf_var.btf_id = type;
	} else if (!btf_type_is_struct(t)) {
		const struct btf_type *ret;
		const char *tname;
		u32 tsize;

		/* resolve the type size of ksym. */
		ret = btf_resolve_size(btf, t, &tsize);
		if (IS_ERR(ret)) {
			tname = btf_name_by_offset(btf, t->name_off);
			verbose(env, "ldimm64 unable to resolve the size of type '%s': %ld\n",
				tname, PTR_ERR(ret));
			return -EINVAL;
		}
		aux->btf_var.reg_type = PTR_TO_MEM | MEM_RDONLY;
		aux->btf_var.mem_size = tsize;
	} else {
		aux->btf_var.reg_type = PTR_TO_BTF_ID;
		aux->btf_var.btf = btf;
		aux->btf_var.btf_id = type;
	}

	return 0;
}

static int check_pseudo_btf_id(struct bpf_verifier_env *env,
			       struct bpf_insn *insn,
			       struct bpf_insn_aux_data *aux)
{
	struct btf *btf;
	int btf_fd;
	int err;

	btf_fd = insn[1].imm;
	if (btf_fd) {
		btf = btf_get_by_fd(btf_fd);
		if (IS_ERR(btf)) {
			verbose(env, "invalid module BTF object FD specified.\n");
			return -EINVAL;
		}
	} else {
		if (!btf_vmlinux) {
			verbose(env, "kernel is missing BTF, make sure CONFIG_DEBUG_INFO_BTF=y is specified in Kconfig.\n");
			return -EINVAL;
		}
		btf_get(btf_vmlinux);
		btf = btf_vmlinux;
	}

	err = __check_pseudo_btf_id(env, insn, aux, btf);
	if (err) {
		btf_put(btf);
		return err;
	}

	return __add_used_btf(env, btf);
}

static bool is_tracing_prog_type(enum bpf_prog_type type)
{
	switch (type) {
	case BPF_PROG_TYPE_KPROBE:
	case BPF_PROG_TYPE_TRACEPOINT:
	case BPF_PROG_TYPE_PERF_EVENT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT:
	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
		return true;
	default:
		return false;
	}
}

static bool bpf_map_is_cgroup_storage(struct bpf_map *map)
{
	return (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE ||
		map->map_type == BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE);
}

static int check_map_prog_compatibility(struct bpf_verifier_env *env,
					struct bpf_map *map,
					struct bpf_prog *prog)

{
	enum bpf_prog_type prog_type = resolve_prog_type(prog);

	if (btf_record_has_field(map->record, BPF_LIST_HEAD) ||
	    btf_record_has_field(map->record, BPF_RB_ROOT)) {
		if (is_tracing_prog_type(prog_type)) {
			verbose(env, "tracing progs cannot use bpf_{list_head,rb_root} yet\n");
			return -EINVAL;
		}
	}

	if (btf_record_has_field(map->record, BPF_SPIN_LOCK | BPF_RES_SPIN_LOCK)) {
		if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) {
			verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n");
			return -EINVAL;
		}
	}

	if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) {
		if (is_tracing_prog_type(prog_type)) {
			verbose(env, "tracing progs cannot use bpf_spin_lock yet\n");
			return -EINVAL;
		}
	}

	if ((bpf_prog_is_offloaded(prog->aux) || bpf_map_is_offloaded(map)) &&
	    !bpf_offload_prog_map_match(prog, map)) {
		verbose(env, "offload device mismatch between prog and map\n");
		return -EINVAL;
	}

	if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
		verbose(env, "bpf_struct_ops map cannot be used in prog\n");
		return -EINVAL;
	}

	if (prog->sleepable && !map_needs_no_rcu(map)) {
		verbose(env,
			"Sleepable programs can only use array, hash, ringbuf and local storage maps\n");
		return -EINVAL;
	}

	if (bpf_map_is_cgroup_storage(map) &&
	    bpf_cgroup_storage_assign(env->prog->aux, map)) {
		verbose(env, "only one cgroup storage of each type is allowed\n");
		return -EBUSY;
	}

	if (map->map_type == BPF_MAP_TYPE_ARENA) {
		if (env->prog->aux->arena) {
			verbose(env, "Only one arena per program\n");
			return -EBUSY;
		}
		if (!env->allow_ptr_leaks || !env->bpf_capable) {
			verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n");
			return -EPERM;
		}
		if (!env->prog->jit_requested) {
			verbose(env, "JIT is required to use arena\n");
			return -EOPNOTSUPP;
		}
		if (!bpf_jit_supports_arena()) {
			verbose(env, "JIT doesn't support arena\n");
			return -EOPNOTSUPP;
		}
		env->prog->aux->arena = (void *)map;
		env->prog->jit_required = true;
		if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) {
			verbose(env, "arena's user address must be set via map_extra or mmap()\n");
			return -EINVAL;
		}
	}

	return 0;
}

/*
 * Keep track of whether the map is used by one program only. Such program may
 * store the addresses of its functions into the map when it's frozen, see
 * resolve_func_ptrs(), since nothing else relies on what the map has. After
 * that the map is not available to other programs.
 */
static int bpf_map_claim(struct bpf_verifier_env *env, struct bpf_map *map)
{
	unsigned long me = (unsigned long)env->prog->aux, old;

	for (;;) {
		old = READ_ONCE(map->user);
		if (old == me || old == BPF_MAP_USER_MANY)
			return 0;
		if (old & BPF_MAP_USER_PATCHED) {
			verbose(env, "map '%s' has addresses of functions of another program\n",
				map->name);
			return -EBUSY;
		}
		if (cmpxchg(&map->user, old, old ? BPF_MAP_USER_MANY : me) == old)
			return 0;
	}
}

/*
 * An exclusive map is bound to the digest of its program. The digest covers
 * the insns as they are verified, after the CO-RE relocations the kernel
 * applies, so it exists only once check_and_resolve_insns() has computed it,
 * and the maps are checked against it there, whether an insn referred to
 * them or a continuous fd_array bound them before.
 */
static int check_excl_maps(struct bpf_verifier_env *env)
{
	int i;

	for (i = 0; i < env->used_map_cnt; i++) {
		struct bpf_map *map = env->used_maps[i];

		if (map->excl_prog_sha &&
		    memcmp(map->excl_prog_sha, env->prog->digest, SHA256_DIGEST_SIZE)) {
			verbose(env, "program's hash doesn't match map's excl_prog_hash\n");
			return -EACCES;
		}
	}
	return 0;
}

/*
 * The program may use every map it referred to, see check_excl_maps(). Only now
 * does it leave a trace on them: it claims each as its user, see
 * bpf_map_claim(), and takes over its insn arrays. A program rejected before
 * this point, one that is not the owner of an exclusive map in particular,
 * leaves the maps as it found them. Nothing consults a claim before
 * resolve_func_ptrs() and the fixup passes, which run later.
 */
static int claim_used_maps(struct bpf_verifier_env *env)
{
	int i, err;

	for (i = 0; i < env->used_map_cnt; i++) {
		struct bpf_map *map = env->used_maps[i];

		err = bpf_map_claim(env, map);
		if (err)
			return err;

		if (map->map_type != BPF_MAP_TYPE_INSN_ARRAY)
			continue;
		err = bpf_insn_array_init(map, env->prog);
		if (err) {
			verbose(env, "Failed to properly initialize insn array\n");
			return err;
		}
		env->insn_array_maps[env->insn_array_map_cnt++] = map;
		env->prog->jit_required = true;
	}
	return 0;
}

static int __add_used_map(struct bpf_verifier_env *env, struct bpf_map *map)
{
	int i, err;

	/* check whether we recorded this map already */
	for (i = 0; i < env->used_map_cnt; i++)
		if (env->used_maps[i] == map)
			return i;

	if (env->signature &&
	    env->prog->aux->sig.verdict == BPF_SIG_VERIFIED) {
		verbose(env, "signed program cannot bind map '%s' not covered by the signature\n",
			map->name);
		return -EACCES;
	}
	if (env->used_map_cnt >= MAX_USED_MAPS) {
		verbose(env, "The total number of maps per program has reached the limit of %u\n",
			MAX_USED_MAPS);
		return -E2BIG;
	}

	err = check_map_prog_compatibility(env, map, env->prog);
	if (err)
		return err;

	if (bpf_prog_runs_sleepable(env->prog))
		atomic64_inc(&map->sleepable_refcnt);

	/* hold the map. If the program is rejected by verifier,
	 * the map will be released by release_maps() or it
	 * will be used by the valid program until it's unloaded
	 * and all maps are released in bpf_free_used_maps()
	 */
	bpf_map_inc(map);

	env->used_maps[env->used_map_cnt++] = map;

	return env->used_map_cnt - 1;
}

/* Add map behind fd to used maps list, if it's not already there, and return
 * its index.
 * Returns <0 on error, or >= 0 index, on success.
 */
static int add_used_map(struct bpf_verifier_env *env, int fd)
{
	struct bpf_map *map;
	CLASS(fd, f)(fd);

	map = __bpf_map_get(f);
	if (IS_ERR(map)) {
		verbose(env, "fd %d is not pointing to valid bpf_map\n", fd);
		return PTR_ERR(map);
	}

	return __add_used_map(env, map);
}

static int fd_array_get_map_idx_continuous(struct bpf_verifier_env *env, u32 idx)
{
	struct bpf_map *map;

	if (idx >= env->fd_array_cnt) {
		verbose(env, "fd_idx %u out of bounds, fd_array_cnt %u\n",
			idx, env->fd_array_cnt);
		return -EINVAL;
	}
	map = fd_slot_map(env->fd_array[idx]);
	if (!map) {
		verbose(env, "fd_idx %u is not a map\n", idx);
		return -EINVAL;
	}
	return __add_used_map(env, map);
}

static int fd_array_get_map_idx_sparse(struct bpf_verifier_env *env, u32 idx)
{
	int fd;

	if (copy_from_bpfptr_offset(&fd, env->fd_array_raw,
				    (size_t)idx * sizeof(fd), sizeof(fd)))
		return -EFAULT;
	return add_used_map(env, fd);
}

static int fd_array_get_map_idx(struct bpf_verifier_env *env, u32 idx)
{
	if (env->fd_array)
		return fd_array_get_map_idx_continuous(env, idx);
	if (env->signature) {
		verbose(env, "signed program must bind maps via a continuous fd_array (fd_array_cnt)\n");
		return -EACCES;
	}
	if (!bpfptr_is_null(env->fd_array_raw))
		return fd_array_get_map_idx_sparse(env, idx);

	verbose(env, "fd_idx without fd_array is invalid\n");
	return -EPROTO;
}

static int check_alu_fields(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	u8 class = BPF_CLASS(insn->code);
	u8 opcode = BPF_OP(insn->code);

	switch (opcode) {
	case BPF_NEG:
		if (BPF_SRC(insn->code) != BPF_K || insn->src_reg != BPF_REG_0 ||
		    insn->off != 0 || insn->imm != 0) {
			verbose(env, "BPF_NEG uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_END:
		if (insn->src_reg != BPF_REG_0 || insn->off != 0 ||
		    (insn->imm != 16 && insn->imm != 32 && insn->imm != 64) ||
		    (class == BPF_ALU64 && BPF_SRC(insn->code) != BPF_TO_LE)) {
			verbose(env, "BPF_END uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_MOV:
		if (BPF_SRC(insn->code) == BPF_X) {
			if (class == BPF_ALU) {
				if ((insn->off != 0 && insn->off != 8 && insn->off != 16) ||
				    insn->imm) {
					verbose(env, "BPF_MOV uses reserved fields\n");
					return -EINVAL;
				}
			} else if (insn->off == BPF_ADDR_SPACE_CAST) {
				if (insn->imm != 1 && insn->imm != 1u << 16) {
					verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n");
					return -EINVAL;
				}
			} else if ((insn->off != 0 && insn->off != 8 &&
				    insn->off != 16 && insn->off != 32) || insn->imm) {
				verbose(env, "BPF_MOV uses reserved fields\n");
				return -EINVAL;
			}
		} else if (insn->src_reg != BPF_REG_0 || insn->off != 0) {
			verbose(env, "BPF_MOV uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_ADD:
	case BPF_SUB:
	case BPF_AND:
	case BPF_OR:
	case BPF_XOR:
	case BPF_LSH:
	case BPF_RSH:
	case BPF_ARSH:
	case BPF_MUL:
	case BPF_DIV:
	case BPF_MOD:
		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0 || (insn->off != 0 && insn->off != 1) ||
			    (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
				verbose(env, "BPF_ALU uses reserved fields\n");
				return -EINVAL;
			}
		} else if (insn->src_reg != BPF_REG_0 ||
			   (insn->off != 0 && insn->off != 1) ||
			   (insn->off == 1 && opcode != BPF_MOD && opcode != BPF_DIV)) {
			verbose(env, "BPF_ALU uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	default:
		verbose(env, "invalid BPF_ALU opcode %x\n", opcode);
		return -EINVAL;
	}
}

static int check_jmp_fields(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	u8 class = BPF_CLASS(insn->code);
	u8 opcode = BPF_OP(insn->code);

	switch (opcode) {
	case BPF_CALL:
		if (bpf_is_callx(insn)) {
			/* callx dst_reg */
			if (insn->src_reg != BPF_REG_0 || insn->imm != 0 || insn->off != 0) {
				verbose(env, "BPF_CALL|BPF_X uses reserved fields\n");
				return -EINVAL;
			}
			return 0;
		}
		if (BPF_SRC(insn->code) != BPF_K ||
		    (insn->src_reg != BPF_PSEUDO_KFUNC_CALL && insn->off != 0) ||
		    (insn->src_reg != BPF_REG_0 && insn->src_reg != BPF_PSEUDO_CALL &&
		     insn->src_reg != BPF_PSEUDO_KFUNC_CALL) ||
		    insn->dst_reg != BPF_REG_0 || class == BPF_JMP32) {
			verbose(env, "BPF_CALL uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_JA:
		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->src_reg != BPF_REG_0 || insn->imm != 0 || insn->off != 0) {
				verbose(env, "BPF_JA|BPF_X uses reserved fields\n");
				return -EINVAL;
			}
		} else if (insn->src_reg != BPF_REG_0 || insn->dst_reg != BPF_REG_0 ||
			   (class == BPF_JMP && insn->imm != 0) ||
			   (class == BPF_JMP32 && insn->off != 0)) {
			verbose(env, "BPF_JA uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_EXIT:
		if (BPF_SRC(insn->code) != BPF_K || insn->imm != 0 ||
		    insn->src_reg > BPF_UNWIND_EXIT || insn->dst_reg != BPF_REG_0 ||
		    class == BPF_JMP32) {
			verbose(env, "BPF_EXIT uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_JCOND:
		if (insn->code != (BPF_JMP | BPF_JCOND) || insn->src_reg > BPF_UNWIND_GOTO ||
		    insn->dst_reg || insn->imm) {
			verbose(env, "invalid may_goto imm %d\n", insn->imm);
			return -EINVAL;
		}
		return 0;
	default:
		if (BPF_SRC(insn->code) == BPF_X) {
			if (insn->imm != 0) {
				verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
				return -EINVAL;
			}
		} else if (insn->src_reg != BPF_REG_0) {
			verbose(env, "BPF_JMP/JMP32 uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	}
}

static int check_insn_fields(struct bpf_verifier_env *env, struct bpf_insn *insn)
{
	switch (BPF_CLASS(insn->code)) {
	case BPF_ALU:
	case BPF_ALU64:
		return check_alu_fields(env, insn);
	case BPF_LDX:
		if ((BPF_MODE(insn->code) != BPF_MEM && BPF_MODE(insn->code) != BPF_MEMSX) ||
		    insn->imm != 0) {
			verbose(env, "BPF_LDX uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_STX:
		if (BPF_MODE(insn->code) == BPF_ATOMIC)
			return 0;
		if (BPF_MODE(insn->code) != BPF_MEM || insn->imm != 0) {
			verbose(env, "BPF_STX uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_ST:
		if (BPF_MODE(insn->code) != BPF_MEM || insn->src_reg != BPF_REG_0) {
			verbose(env, "BPF_ST uses reserved fields\n");
			return -EINVAL;
		}
		return 0;
	case BPF_JMP:
	case BPF_JMP32:
		return check_jmp_fields(env, insn);
	case BPF_LD: {
		u8 mode = BPF_MODE(insn->code);

		if (mode == BPF_ABS || mode == BPF_IND) {
			if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
			    BPF_SIZE(insn->code) == BPF_DW ||
			    (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
				verbose(env, "BPF_LD_[ABS|IND] uses reserved fields\n");
				return -EINVAL;
			}
		} else if (mode != BPF_IMM) {
			verbose(env, "invalid BPF_LD mode\n");
			return -EINVAL;
		}
		return 0;
	}
	default:
		verbose(env, "unknown insn class %d\n", BPF_CLASS(insn->code));
		return -EINVAL;
	}
}

/*
 * Check that insns are sane and rewrite pseudo imm in ld_imm64 instructions:
 *
 * 1. if it accesses map FD, replace it with actual map pointer.
 * 2. if it accesses btf_id of a VAR, replace it with pointer to the var.
 *
 * NOTE: btf_vmlinux is required for converting pseudo btf_id.
 */
static int check_and_resolve_insns(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i, err;

	err = bpf_prog_calc_tag(env->prog);
	if (err)
		return err;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn->dst_reg >= MAX_BPF_REG &&
		    !is_stack_arg_st(insn) && !is_stack_arg_stx(insn)) {
			verbose(env, "R%d is invalid\n", insn->dst_reg);
			return -EINVAL;
		}
		if (insn->src_reg >= MAX_BPF_REG && !is_stack_arg_ldx(insn)) {
			verbose(env, "R%d is invalid\n", insn->src_reg);
			return -EINVAL;
		}
		if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) {
			struct bpf_insn_aux_data *aux;
			struct bpf_map *map;
			int map_idx;
			u64 addr;

			if (i == insn_cnt - 1 || insn[1].code != 0 ||
			    insn[1].dst_reg != 0 || insn[1].src_reg != 0 ||
			    insn[1].off != 0) {
				verbose(env, "invalid bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			if (insn[0].off != 0) {
				verbose(env, "BPF_LD_IMM64 uses reserved fields\n");
				return -EINVAL;
			}

			if (insn[0].src_reg == 0)
				/* valid generic load 64-bit imm */
				goto next_insn;

			if (insn[0].src_reg == BPF_PSEUDO_BTF_ID) {
				aux = &env->insn_aux_data[i];
				err = check_pseudo_btf_id(env, insn, aux);
				if (err)
					return err;
				goto next_insn;
			}

			if (insn[0].src_reg == BPF_PSEUDO_FUNC) {
				aux = &env->insn_aux_data[i];
				aux->ptr_type = PTR_TO_FUNC;
				goto next_insn;
			}

			/* In final convert_pseudo_ld_imm64() step, this is
			 * converted into regular 64-bit imm load insn.
			 */
			switch (insn[0].src_reg) {
			case BPF_PSEUDO_MAP_VALUE:
			case BPF_PSEUDO_MAP_IDX_VALUE:
				break;
			case BPF_PSEUDO_MAP_FD:
			case BPF_PSEUDO_MAP_IDX:
				if (insn[1].imm == 0)
					break;
				fallthrough;
			default:
				verbose(env, "unrecognized bpf_ld_imm64 insn\n");
				return -EINVAL;
			}

			switch (insn[0].src_reg) {
			case BPF_PSEUDO_MAP_IDX_VALUE:
			case BPF_PSEUDO_MAP_IDX:
				map_idx = fd_array_get_map_idx(env, insn[0].imm);
				break;
			default:
				if (env->signature) {
					verbose(env, "signed program cannot reference a map by fd, only via fd_array index\n");
					return -EINVAL;
				}
				map_idx = add_used_map(env, insn[0].imm);
				break;
			}

			if (map_idx < 0)
				return map_idx;
			map = env->used_maps[map_idx];

			aux = &env->insn_aux_data[i];
			aux->map_index = map_idx;

			if (insn[0].src_reg == BPF_PSEUDO_MAP_FD ||
			    insn[0].src_reg == BPF_PSEUDO_MAP_IDX) {
				addr = (unsigned long)map;
			} else {
				u32 off = insn[1].imm;

				if (!map->ops->map_direct_value_addr) {
					verbose(env, "no direct value access support for this map type\n");
					return -EINVAL;
				}

				err = map->ops->map_direct_value_addr(map, &addr, off);
				if (err) {
					verbose(env, "invalid access to map value pointer, value_size=%u off=%u\n",
						map->value_size, off);
					return err;
				}

				aux->map_off = off;
				addr += off;
			}

			insn[0].imm = (u32)addr;
			insn[1].imm = addr >> 32;

next_insn:
			insn++;
			i++;
			continue;
		}

		/* Basic sanity check before we invest more work here. */
		if (!bpf_opcode_in_insntable(insn->code)) {
			verbose(env, "unknown opcode %02x\n", insn->code);
			return -EINVAL;
		}

		err = check_insn_fields(env, insn);
		if (err)
			return err;
	}

	/* now all pseudo BPF_LD_IMM64 instructions load valid
	 * 'struct bpf_map *' into a register instead of user map_fd.
	 * These pointers will be used later by verifier to validate map access.
	 */
	err = check_excl_maps(env);
	if (err)
		return err;
	return claim_used_maps(env);
}

/* that many pointers to functions are recognized in the maps of a program at most */
#define BPF_MAX_FUNC_PTRS (1 << 20)

static int add_func_ptr(struct bpf_verifier_env *env, struct bpf_map *map, u32 map_off,
			u32 xlated_off)
{
	struct bpf_func_ptr *ptrs;

	if (env->func_ptr_cnt == BPF_MAX_FUNC_PTRS) {
		verbose(env, "too many pointers to functions in maps, the limit is %d\n",
			BPF_MAX_FUNC_PTRS);
		return -E2BIG;
	}

	/* grow by doubling, the array is sorted and searched later */
	if (!(env->func_ptr_cnt & (env->func_ptr_cnt - 1))) {
		ptrs = kvrealloc(env->func_ptrs,
				 array_size(max(2 * env->func_ptr_cnt, 16U), sizeof(*ptrs)),
				 GFP_KERNEL_ACCOUNT);
		if (!ptrs)
			return -ENOMEM;
		env->func_ptrs = ptrs;
	}
	env->func_ptrs[env->func_ptr_cnt++] = (struct bpf_func_ptr){
		.map = map,
		.map_off = map_off,
		.orig_off = xlated_off,
		.xlated_off = xlated_off,
	};
	return 0;
}

/*
 * Compilers put pointers to functions into read-only data: tables of functions,
 * structures of operations, vtables, where they are mixed with other data.
 * The loader stores such data in a frozen read-only array map and resolves
 * a pointer to a static function to the offset in bytes of its first
 * instruction in the program: the address of the function in the program.
 *
 * Find 64-bit values that look like that in the maps of a program that uses
 * callx. It's a guess. When the value is not a pointer, the program either
 * fails to load, because it does with a pointer what can be done with
 * a number only, or it sees the address of a function instead of the number.
 * It's known before the control flow graph of the program is built and the main
 * verification pass begins which functions may be called via callx.
 *
 * When the program is jitted the offsets are replaced with the addresses of
 * the functions in the map itself, see jit_subprogs(). Hence the program has to
 * be the only user of the map, see bpf_map_claim(): nothing else may rely on
 * what the map had.
 *
 * The program reads the addresses of its functions from there like any other
 * data, so it has to be allowed to leak pointers.
 */
static int resolve_func_ptrs(struct bpf_verifier_env *env)
{
	int insn_cnt = env->prog->len;
	int i, err, subprog;
	struct bpf_map *map;
	u64 addr, val;
	u32 off;

	if (!env->has_callx || !env->allow_ptr_leaks)
		return 0;

	for (i = 0; i < env->used_map_cnt; i++) {
		map = env->used_maps[i];
		/* coincidences in maps that are shared with other programs don't matter */
		if (READ_ONCE(map->user) != (unsigned long)env->prog->aux)
			continue;
		if (map->map_type != BPF_MAP_TYPE_ARRAY || map->max_entries != 1 ||
		    !bpf_map_is_rdonly(map) || !map->ops->map_direct_value_addr ||
		    !IS_ERR_OR_NULL(map->record))
			continue;
		if (map->ops->map_direct_value_addr(map, &addr, 0))
			continue;

		for (off = 0; off + sizeof(u64) <= map->value_size; off += sizeof(u64)) {
			if (!(off % SZ_64K))
				cond_resched();
			val = *(u64 *)(unsigned long)(addr + off);
			if (!val || val % sizeof(struct bpf_insn) ||
			    val / sizeof(struct bpf_insn) >= insn_cnt)
				continue;
			subprog = bpf_find_subprog(env, val / sizeof(struct bpf_insn));
			if (subprog <= 0 || bpf_subprog_is_global(env, subprog))
				continue;
			err = add_func_ptr(env, map, off, val / sizeof(struct bpf_insn));
			if (err)
				return err;
		}
	}
	if (env->func_ptr_cnt)
		sort(env->func_ptrs, env->func_ptr_cnt, sizeof(*env->func_ptrs),
		     cmp_func_ptrs, NULL);
	return 0;
}

/* drop refcnt of maps used by the rejected program */
static void release_maps(struct bpf_verifier_env *env)
{
	__bpf_free_used_maps(env->prog->aux, env->used_maps,
			     env->used_map_cnt);
}

/* drop refcnt of maps used by the rejected program */
static void release_btfs(struct bpf_verifier_env *env)
{
	__bpf_free_used_btfs(env->used_btfs, env->used_btf_cnt);
}

/* convert pseudo BPF_LD_IMM64 into generic BPF_LD_IMM64 */
static void convert_pseudo_ld_imm64(struct bpf_verifier_env *env)
{
	struct bpf_insn *insn = env->prog->insnsi;
	int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++, insn++) {
		if (insn->code != (BPF_LD | BPF_IMM | BPF_DW))
			continue;
		if (insn->src_reg == BPF_PSEUDO_FUNC)
			continue;
		insn->src_reg = 0;
	}
}

static void release_insn_arrays(struct bpf_verifier_env *env)
{
	int i;

	for (i = 0; i < env->insn_array_map_cnt; i++)
		bpf_insn_array_release(env->insn_array_maps[i]);
}

/* The verifier does more data flow analysis than llvm and will not
 * explore branches that are dead at run time. Malicious programs can
 * have dead code too. Therefore replace all dead at-run-time code
 * with 'ja -1'.
 *
 * Just nops are not optimal, e.g. if they would sit at the end of the
 * program and through another bug we would manage to jump there, then
 * we'd execute beyond program memory otherwise. Returning exception
 * code also wouldn't work since we can have subprogs where the dead
 * code could be located.
 */
static void sanitize_dead_code(struct bpf_verifier_env *env)
{
	struct bpf_insn_aux_data *aux_data = env->insn_aux_data;
	struct bpf_insn trap = BPF_JMP_IMM(BPF_JA, 0, 0, -1);
	struct bpf_insn *insn = env->prog->insnsi;
	const int insn_cnt = env->prog->len;
	int i;

	for (i = 0; i < insn_cnt; i++) {
		if (aux_data[i].seen)
			continue;
		memcpy(insn + i, &trap, sizeof(trap));
		aux_data[i].zext_dst = false;
	}
}

static void free_states(struct bpf_verifier_env *env)
{
	struct bpf_verifier_state_list *sl;
	struct list_head *head, *pos, *tmp;
	struct bpf_scc_info *info;
	int i, j;

	bpf_free_verifier_state(env->cur_state, true);
	env->cur_state = NULL;
	while (!pop_stack(env, NULL, NULL, false));

	list_for_each_safe(pos, tmp, &env->free_list) {
		sl = container_of(pos, struct bpf_verifier_state_list, node);
		bpf_free_verifier_state(&sl->state, false);
		kfree(sl);
	}
	INIT_LIST_HEAD(&env->free_list);

	for (i = 0; i < env->scc_cnt; ++i) {
		info = env->scc_info[i];
		if (!info)
			continue;
		for (j = 0; j < info->num_visits; j++)
			bpf_free_backedges(&info->visits[j]);
		kvfree(info);
		env->scc_info[i] = NULL;
	}

	if (!env->explored_states)
		return;

	for (i = 0; i < state_htab_size(env); i++) {
		head = &env->explored_states[i];

		list_for_each_safe(pos, tmp, head) {
			sl = container_of(pos, struct bpf_verifier_state_list, node);
			bpf_free_verifier_state(&sl->state, false);
			kfree(sl);
		}
		INIT_LIST_HEAD(&env->explored_states[i]);
	}
}

static int do_check_common(struct bpf_verifier_env *env, int subprog,
			   enum bpf_func_context context)
{
	bool pop_log = !(env->log.level & BPF_LOG_LEVEL2);
	struct bpf_subprog_info *sub = subprog_info(env, subprog);
	struct bpf_prog_aux *aux = env->prog->aux;
	struct bpf_verifier_state *state;
	struct bpf_reg_state *regs;
	u32 old_insns_total = sub->insns_total;
	u32 insn_processed = env->insn_processed;
	int ret, i;

	env->prev_linfo = NULL;
	env->pass_cnt++;

	state = kzalloc_obj(struct bpf_verifier_state, GFP_KERNEL_ACCOUNT);
	if (!state)
		return -ENOMEM;
	state->curframe = 0;
	state->speculative = false;
	state->branches = 1;
	state->in_sleepable = context == BPF_FUNC_CTX_SLEEPABLE;
	env->no_rcu_read_lock = context == BPF_FUNC_CTX_NO_RCU_LOCK;
	state->frame[0] = kzalloc_obj(struct bpf_func_state, GFP_KERNEL_ACCOUNT);
	if (!state->frame[0]) {
		kfree(state);
		return -ENOMEM;
	}
	env->cur_state = state;
	init_func_state(env, state->frame[0],
			BPF_MAIN_FUNC /* callsite */,
			0 /* frameno */,
			subprog);
	state->first_insn_idx = env->subprog_info[subprog].start;
	state->last_insn_idx = -1;

	regs = state->frame[state->curframe]->regs;
	if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) {
		const char *sub_name = bpf_subprog_name(env, subprog);
		struct bpf_subprog_arg_info *arg;
		struct bpf_reg_state *reg;

		if (env->log.level & BPF_LOG_LEVEL)
			verbose(env, "Validating %s() func#%d...\n", sub_name, subprog);
		ret = btf_prepare_func_args(env, subprog);
		if (ret)
			goto out;

		if (subprog_is_exc_cb(env, subprog)) {
			state->frame[0]->in_exception_callback_fn = true;

			/*
			 * Global functions are scalar or void, make sure
			 * we return a scalar.
			 */
			if (subprog_returns_void(env, subprog)) {
				verbose(env, "exception cb cannot return void\n");
				ret = -EINVAL;
				goto out;
			}

			/* Also ensure the callback only has a single scalar argument. */
			if (sub->arg_slot_cnt != 1 || sub->args[0].arg_type != ARG_SCALAR) {
				verbose(env, "exception cb only supports single integer argument\n");
				ret = -EINVAL;
				goto out;
			}
		}
		for (i = BPF_REG_1;
		     i <= min_t(u32, sub->arg_slot_cnt, MAX_BPF_FUNC_REG_ARGS); i++) {
			arg = &sub->args[i - BPF_REG_1];
			reg = &regs[i];

			if (arg->arg_type == ARG_PTR_TO_CTX) {
				reg->type = PTR_TO_CTX;
				mark_reg_known_zero(env, regs, i);
			} else if (arg->arg_type == ARG_SCALAR) {
				reg->type = SCALAR_VALUE;
				mark_reg_unknown(env, regs, i);
			} else if (arg->arg_type == ARG_PTR_TO_DYNPTR) {
				/*
				 * The callers may hand in a dynptr of any type.
				 * Take it for that of an skb, so that a write
				 * through it and its slices are treated with care.
				 */
				__mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_SKB, true, ++env->id_gen, 0);
			} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
				reg->type = PTR_TO_MEM;
				reg->type |= arg->arg_type &
					     (PTR_MAYBE_NULL | PTR_UNTRUSTED | MEM_RDONLY);
				mark_reg_known_zero(env, regs, i);
				reg->mem_size = arg->mem_size;
				if (arg->arg_type & PTR_MAYBE_NULL)
					reg->id = ++env->id_gen;
			} else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) {
				reg->type = PTR_TO_BTF_ID;
				if (arg->arg_type & PTR_MAYBE_NULL)
					reg->type |= PTR_MAYBE_NULL;
				if (arg->arg_type & PTR_UNTRUSTED)
					reg->type |= PTR_UNTRUSTED;
				if (arg->arg_type & PTR_TRUSTED)
					reg->type |= PTR_TRUSTED;
				mark_reg_known_zero(env, regs, i);
				reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */
				reg->btf_id = arg->btf_id;
				reg->id = ++env->id_gen;
			} else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) {
				/* caller can pass either PTR_TO_ARENA or SCALAR */
				mark_reg_unknown(env, regs, i);
			} else {
				verifier_bug(env, "unhandled arg#%d type %d",
					     i - BPF_REG_1 + 1, arg->arg_type);
				ret = -EFAULT;
				goto out;
			}
		}
		if (env->prog->type == BPF_PROG_TYPE_EXT &&
		    sub->arg_slot_cnt > MAX_BPF_FUNC_REG_ARGS) {
			verbose(env, "freplace programs with >%d args not supported yet\n",
				MAX_BPF_FUNC_REG_ARGS);
			ret = -EINVAL;
			goto out;
		}
	} else {
		/* if main BPF program has associated BTF info, validate that
		 * it's matching expected signature, and otherwise mark BTF
		 * info for main program as unreliable
		 */
		if (env->prog->aux->func_info_aux) {
			ret = btf_prepare_func_args(env, 0);
			if (ret || sub->arg_slot_cnt != 1 ||
			    sub->args[0].arg_type != ARG_PTR_TO_CTX) {
				env->prog->aux->func_info_aux[0].unreliable = true;
				sub->arg_slot_cnt = 1;
				sub->stack_arg_cnt = 0;
			}
		}

		/* 1st arg to a function */
		regs[BPF_REG_1].type = PTR_TO_CTX;
		mark_reg_known_zero(env, regs, BPF_REG_1);
	}

	/* Acquire references for struct_ops program arguments tagged with "__ref" */
	if (!subprog && env->prog->type == BPF_PROG_TYPE_STRUCT_OPS) {
		for (i = 0; i < aux->ctx_arg_info_size; i++) {
			ret = aux->ctx_arg_info[i].refcounted ? acquire_reference(env, 0, 0) : 0;
			if (ret < 0)
				goto out;

			aux->ctx_arg_info[i].ref_id = ret;
		}
	}

	ret = do_check(env);
out:
	account_current_path(env);
	if (!ret) {
		if (pop_log)
			bpf_vlog_reset(&env->log, 0);
		bpf_diag_event_log_restore(env, 0);
	}
	free_states(env);

	/*
	 * The override is needed to account for async subprograms, which
	 * are verified with their own set of stack frames and thus are
	 * not accounted as callees by account_current_path().
	 * Accumulate their total counts as total counts of the main or
	 * global subprog hosting the async call.
	 * Start from the saved total of earlier contexts: adding to the current
	 * total would count this pass's synchronous paths twice.
	 */
	sub->insns_total = old_insns_total + (env->insn_processed - insn_processed);
	return ret;
}

/* Lazily verify all global functions based on their BTF, if they are called
 * from main BPF program or any of subprograms transitively.
 * BPF global subprogs called from dead code are not validated.
 * All callable global functions must pass verification.
 * Otherwise the whole program is rejected.
 * Consider:
 * int bar(int);
 * int foo(int f)
 * {
 *    return bar(f);
 * }
 * int bar(int b)
 * {
 *    ...
 * }
 * foo() will be verified first for R1=any_scalar_value. During verification it
 * will be assumed that bar() already verified successfully and call to bar()
 * from foo() will be checked for type match only. Later bar() will be verified
 * independently to check that it's safe for R1=any_scalar_value.
 */
static int do_check_subprogs(struct bpf_verifier_env *env)
{
	struct bpf_prog_aux *aux = env->prog->aux;
	struct bpf_func_info_aux *sub_aux;
	int context, i, ret, new_cnt;

	if (!aux->func_info)
		return 0;

	/*
	 * Callbacks cannot throw, so the exception callback always runs in the
	 * main program's context. It is presumed to be always called.
	 */
	if (env->exception_callback_subprog) {
		sub_aux = subprog_aux(env, env->exception_callback_subprog);
		sub_aux->called[env->prog->sleepable] = true;
	}

again:
	new_cnt = 0;
	for (i = 1; i < env->subprog_cnt; i++) {
		if (!bpf_subprog_is_global(env, i))
			continue;

		sub_aux = subprog_aux(env, i);
		for (context = 0; context < ARRAY_SIZE(sub_aux->called); context++) {
			if (!sub_aux->called[context] || sub_aux->verified[context])
				continue;

			env->insn_idx = env->subprog_info[i].start;
			WARN_ON_ONCE(env->insn_idx == 0);
			ret = do_check_common(env, i, context);
			if (ret)
				return ret;
			if (env->log.level & BPF_LOG_LEVEL)
				verbose(env, "Func#%d ('%s') is safe for any args "
					"that match its prototype\n",
					i, bpf_subprog_name(env, i));

			sub_aux->verified[context] = true;
			new_cnt++;
		}
	}

	/*
	 * We can't loop forever as each pass verifies at least one new context,
	 * and there are only three contexts per global subprog.
	 */
	if (new_cnt)
		goto again;

	return 0;
}

static int do_check_main(struct bpf_verifier_env *env)
{
	int ret;

	env->insn_idx = 0;
	ret = do_check_common(env, 0, env->prog->sleepable);
	if (!ret)
		env->prog->aux->stack_depth = env->subprog_info[0].stack_depth;
	return ret;
}

static void print_verification_stats(struct bpf_verifier_env *env)
{
	/* Skip over hidden subprogs which are not verified. */
	int i, subprog_cnt = env->subprog_cnt - env->hidden_subprog_cnt;

	if (env->log.level & BPF_LOG_STATS) {
		verbose(env, "verification time %lld usec\n",
			div_u64(env->verification_time, 1000));
		verbose(env, "stack depth max %d\n", env->max_stack_depth);
		for (i = 0; i < subprog_cnt; i++) {
			const char *name = env->subprog_info[i].name;
			const char *kind;

			if (!name || !name[0])
				name = "<unknown>";
			kind = i == 0 ? "main" :
			       bpf_subprog_is_global(env, i) ? "global" : "static";
			verbose(env, "subprog %d (%s) %s insns_self %d insns_total %d stack %d\n",
				i, name, kind, env->subprog_info[i].insns_self,
				env->subprog_info[i].insns_total,
				env->subprog_info[i].stack_depth);
		}
	}
	verbose(env, "processed %d insns (limit %d) max_states_per_insn %d "
		"total_states %d peak_states %d mark_read %d\n",
		env->insn_processed, BPF_COMPLEXITY_LIMIT_INSNS,
		env->max_states_per_insn, env->total_states,
		env->peak_states, env->longest_mark_read_walk);
}

int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
			       const struct bpf_ctx_arg_aux *info, u32 cnt)
{
	prog->aux->ctx_arg_info = kmemdup_array(info, cnt, sizeof(*info), GFP_KERNEL_ACCOUNT);
	prog->aux->ctx_arg_info_size = cnt;

	return prog->aux->ctx_arg_info ? 0 : -ENOMEM;
}

static int check_struct_ops_btf_id(struct bpf_verifier_env *env)
{
	const struct btf_type *t, *func_proto;
	const struct bpf_struct_ops_desc *st_ops_desc;
	const struct bpf_struct_ops_arg_info *arg_info;
	const struct bpf_struct_ops *st_ops;
	const struct btf_member *member;
	struct bpf_prog *prog = env->prog;
	bool has_refcounted_arg = false;
	u32 btf_id, member_idx, member_off;
	struct btf *btf;
	const char *mname;
	int i, err;

	if (!prog->gpl_compatible) {
		verbose(env, "struct ops programs must have a GPL compatible license\n");
		return -EINVAL;
	}

	if (!prog->aux->attach_btf_id)
		return -ENOTSUPP;

	btf = prog->aux->attach_btf;
	if (btf_is_module(btf)) {
		/* Make sure st_ops is valid through the lifetime of env */
		env->attach_btf_mod = btf_try_get_module(btf);
		if (!env->attach_btf_mod) {
			verbose(env, "struct_ops module %s is not found\n",
				btf_get_name(btf));
			return -ENOTSUPP;
		}
	}

	btf_id = prog->aux->attach_btf_id;
	st_ops_desc = bpf_struct_ops_find(btf, btf_id);
	if (!st_ops_desc) {
		verbose(env, "attach_btf_id %u is not a supported struct\n",
			btf_id);
		return -ENOTSUPP;
	}
	st_ops = st_ops_desc->st_ops;

	t = st_ops_desc->type;
	member_idx = prog->expected_attach_type;
	if (member_idx >= btf_type_vlen(t)) {
		verbose(env, "attach to invalid member idx %u of struct %s\n",
			member_idx, st_ops->name);
		return -EINVAL;
	}

	member = &btf_type_member(t)[member_idx];
	mname = btf_name_by_offset(btf, member->name_off);
	func_proto = btf_type_resolve_func_ptr(btf, member->type,
					       NULL);
	if (!func_proto) {
		verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n",
			mname, member_idx, st_ops->name);
		return -EINVAL;
	}

	member_off = __btf_member_bit_offset(t, member) / 8;
	err = bpf_struct_ops_supported(st_ops, member_off);
	if (err) {
		verbose(env, "attach to unsupported member %s of struct %s\n",
			mname, st_ops->name);
		return err;
	}

	if (st_ops->check_member) {
		err = st_ops->check_member(t, member, prog);

		if (err) {
			verbose(env, "attach to unsupported member %s of struct %s\n",
				mname, st_ops->name);
			return err;
		}
	}

	if (prog->aux->priv_stack_requested && !bpf_jit_supports_private_stack()) {
		verbose(env, "Private stack not supported by jit\n");
		return -EACCES;
	}

	arg_info = &st_ops_desc->arg_info[member_idx];
	for (i = 0; i < arg_info->cnt; i++) {
		const struct bpf_ctx_arg_aux *info = &arg_info->info[i];

		if (info->refcounted)
			has_refcounted_arg = true;
		if (base_type(info->reg_type) == PTR_TO_ARENA) {
			if (!bpf_jit_supports_arena_args()) {
				verbose(env, "JIT does not support arena arguments\n");
				return -ENOTSUPP;
			}
			if (!prog->aux->arena) {
				verbose(env,
					"arena argument of %s requires a program with an associated arena\n",
					mname);
				return -EINVAL;
			}
		}
	}

	/* Tail call is not allowed for programs with refcounted arguments since we
	 * cannot guarantee that valid refcounted kptrs will be passed to the callee.
	 */
	for (i = 0; i < env->subprog_cnt; i++) {
		if (has_refcounted_arg && env->subprog_info[i].has_tail_call) {
			verbose(env, "program with __ref argument cannot tail call\n");
			return -EINVAL;
		}
	}

	prog->aux->st_ops = st_ops;
	prog->aux->attach_st_ops_member_off = member_off;

	prog->aux->attach_func_proto = func_proto;
	prog->aux->attach_func_name = mname;
	env->ops = st_ops->verifier_ops;

	return bpf_prog_ctx_arg_info_init(prog, arg_info->info, arg_info->cnt);
}
#define SECURITY_PREFIX "security_"

#ifdef CONFIG_FUNCTION_ERROR_INJECTION

/* list of non-sleepable functions that are otherwise on
 * ALLOW_ERROR_INJECTION list
 */
BTF_SET_START(btf_non_sleepable_error_inject)
/* Three functions below can be called from sleepable and non-sleepable context.
 * Assume non-sleepable from bpf safety point of view.
 */
BTF_ID(func, __filemap_add_folio)
#ifdef CONFIG_FAIL_PAGE_ALLOC
BTF_ID(func, should_fail_alloc_page)
#endif
#ifdef CONFIG_FAILSLAB
BTF_ID(func, should_failslab)
#endif
BTF_SET_END(btf_non_sleepable_error_inject)

static int check_non_sleepable_error_inject(u32 btf_id)
{
	return btf_id_set_contains(&btf_non_sleepable_error_inject, btf_id);
}

static int check_attach_sleepable(u32 btf_id, unsigned long addr, const char *func_name)
{
	/* fentry/fexit/fmod_ret progs can be sleepable if they are
	 * attached to ALLOW_ERROR_INJECTION and are not in denylist.
	 */
	if (!check_non_sleepable_error_inject(btf_id) &&
	    within_error_injection_list(addr))
		return 0;

	return -EINVAL;
}

static int check_attach_modify_return(unsigned long addr, const char *func_name)
{
	if (within_error_injection_list(addr) ||
	    !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
		return 0;

	return -EINVAL;
}

#else

/* Unfortunately, the arch-specific prefixes are hard-coded in arch syscall code
 * so we need to hard-code them, too. Ftrace has arch_syscall_match_sym_name()
 * but that just compares two concrete function names.
 */
static bool has_arch_syscall_prefix(const char *func_name)
{
#if defined(__x86_64__)
	return !strncmp(func_name, "__x64_", 6);
#elif defined(__i386__)
	return !strncmp(func_name, "__ia32_", 7);
#elif defined(__s390x__)
	return !strncmp(func_name, "__s390x_", 8);
#elif defined(__aarch64__)
	return !strncmp(func_name, "__arm64_", 8);
#elif defined(__riscv)
	return !strncmp(func_name, "__riscv_", 8);
#elif defined(__powerpc__) || defined(__powerpc64__)
	return !strncmp(func_name, "sys_", 4);
#elif defined(__loongarch__)
	return !strncmp(func_name, "sys_", 4);
#else
	return false;
#endif
}

/* Without error injection, allow sleepable and fmod_ret progs on syscalls. */

static int check_attach_sleepable(u32 btf_id, unsigned long addr, const char *func_name)
{
	if (has_arch_syscall_prefix(func_name))
		return 0;

	return -EINVAL;
}

static int check_attach_modify_return(unsigned long addr, const char *func_name)
{
	if (has_arch_syscall_prefix(func_name) ||
	    !strncmp(SECURITY_PREFIX, func_name, sizeof(SECURITY_PREFIX) - 1))
		return 0;

	return -EINVAL;
}

#endif /* CONFIG_FUNCTION_ERROR_INJECTION */

static bool is_tracing_multi_id(const struct bpf_prog *prog, u32 btf_id)
{
	return is_tracing_multi(prog->expected_attach_type) && bpf_multi_func_btf_id[0] == btf_id;
}

static int btf_id_allow_sleepable(u32 btf_id, unsigned long addr, const struct bpf_prog *prog,
				  const struct btf *btf)
{
	const struct btf_type *t;
	const char *tname;

	if (!btf_is_kernel(btf))
		return -EINVAL;

	switch (prog->type) {
	case BPF_PROG_TYPE_TRACING:
		t = btf_type_by_id(btf, btf_id);
		if (!t)
			return -EINVAL;
		tname = btf_name_by_offset(btf, t->name_off);
		if (!tname)
			return -EINVAL;

		/*
		 * *.multi sleepable programs will pass initial sleepable check,
		 * the actual attached btf ids are checked later during the link
		 * attachment.
		 */
		if (is_tracing_multi_id(prog, btf_id))
			return 0;
		if (!check_attach_sleepable(btf_id, addr, tname))
			return 0;
		/*
		 * fentry/fexit/fmod_ret progs can also be sleepable if they are
		 * in the fmodret id set with the KF_SLEEPABLE flag.
		 */
		else {
			u32 *flags = btf_kfunc_is_modify_return(btf, btf_id, prog);

			if (flags && (*flags & KF_SLEEPABLE))
				return 0;
		}
		break;
	case BPF_PROG_TYPE_LSM:
		/*
		 * LSM progs check that they are attached to bpf_lsm_*() funcs.
		 * Only some of them are sleepable.
		 */
		if (bpf_lsm_is_sleepable_hook(btf_id))
			return 0;
		break;
	default:
		break;
	}
	return -EINVAL;
}

/*
 * Resolve the prototype describing a trace target's real ABI. A
 * KF_IMPLICIT_ARGS kfunc has its injected args stripped from the public
 * prototype, so use the _impl prototype; other targets use their own.
 */
static const struct btf_type *
btf_attach_func_proto(struct bpf_verifier_log *log, struct btf *btf, u32 func_id)
{
	const struct btf_type *func;
	struct module *mod = NULL;
	const char *name;
	int implicit;

	func = btf_type_by_id(btf, func_id);
	if (!func || !btf_type_is_func(func))
		return NULL;
	name = btf_name_by_offset(btf, func->name_off);

	/*
	 * btf_kfunc_check_flag() reads kfunc_set_tab, which for a module is
	 * stable only once it is live; hold a module ref across the read to
	 * exclude a concurrent module load.
	 */
	if (btf_is_module(btf)) {
		mod = btf_try_get_module(btf);
		if (!mod)
			return NULL;
	}
	implicit = btf_kfunc_check_flag(btf, func_id, KF_IMPLICIT_ARGS);
	module_put(mod);

	if (implicit == -EINVAL) {
		bpf_log(log, "kfunc %s has inconsistent KF_IMPLICIT_ARGS\n", name);
		return NULL;
	}
	if (implicit > 0)
		return find_kfunc_impl_proto(log, btf, name);

	return btf_type_by_id(btf, func->type);
}

static bool attach_uses_trampoline_retval(enum bpf_attach_type type)
{
	switch (type) {
	case BPF_MODIFY_RETURN:
	case BPF_TRACE_FEXIT:
	case BPF_TRACE_FEXIT_MULTI:
	case BPF_TRACE_FSESSION:
	case BPF_TRACE_FSESSION_MULTI:
		return true;
	default:
		return false;
	}
}

/*
 * BPF code passes argument slot N where the kernel convention passes its Nth
 * u64 argument, so describe a BPF function to its trampoline as one u64 per
 * slot, and every arch places its arguments right.
 */
static int flatten_bpf_func_model(struct bpf_verifier_log *log, const char *tname,
				  struct btf_func_model *m)
{
	u32 i, nslots = 0;

	for (i = 0; i < m->nr_args; i++)
		nslots += btf_func_model_arg_slots(m, i);
	if (nslots > MAX_BPF_FUNC_ARGS) {
		bpf_log(log, "The function %s has %u argument slots. Too many.\n",
			tname, nslots);
		return -EINVAL;
	}

	for (i = 0; i < nslots; i++) {
		m->arg_size[i] = sizeof(u64);
		m->arg_flags[i] = 0;
	}
	m->nr_args = nslots;
	return 0;
}

/*
 * The verifier lets a static function use stack arguments counted from its
 * BTF, even if that BTF turns out unreliable. A trampoline on the function is
 * then given only MAX_BPF_FUNC_REG_ARGS u64 arguments and would lose the
 * stack arguments, so such a function cannot be attached to.
 */
static int check_unreliable_func_args(struct bpf_verifier_log *log, struct btf *btf,
				      const struct btf_type *func_proto, const char *tname)
{
	struct btf_func_model m;
	u32 i, nslots = 0;

	if (btf_distill_func_proto(NULL, btf, func_proto, tname, &m)) {
		/* at least a slot for each argument */
		nslots = btf_type_vlen(func_proto);
	} else {
		for (i = 0; i < m.nr_args; i++)
			nslots += btf_func_model_arg_slots(&m, i);
	}
	if (nslots <= MAX_BPF_FUNC_REG_ARGS)
		return 0;

	bpf_log(log, "Cannot attach to static function %s: unreliable BTF and stack arguments\n",
		tname);
	return -EINVAL;
}

/* Functions may share a type id. The first of them is attached to. */
static int find_tgt_subprog(const struct bpf_prog *tgt_prog, u32 btf_id)
{
	const struct bpf_prog_aux *aux = tgt_prog->aux;
	int i;

	for (i = 0; i < aux->func_info_cnt; i++)
		if (aux->func_info[i].type_id == btf_id)
			return i;

	return -1;
}

/*
 * The prologue of an extension gives a cloned skb a new head, unless the
 * prologue of the target program has done that. The callers of the function
 * that it replaces must not hold on to the old head.
 */
int bpf_check_ext_prologue(struct bpf_verifier_log *log,
			   const struct bpf_prog *tgt_prog, u32 btf_id)
{
	const struct bpf_prog_aux *aux = tgt_prog->aux;
	int subprog = find_tgt_subprog(tgt_prog, btf_id);

	if (aux->has_prologue)
		return 0;

	if (subprog >= 0 && !aux->func_info_aux[subprog].called_with_pkt_ptrs)
		return 0;

	bpf_log(log,
		"Extension writing packet data cannot replace a function whose callers keep packet pointers\n");
	return -EINVAL;
}

/*
 * An extension is verified as a program that runs under the RCU read lock. Does
 * the function that it is to replace?
 */
static bool func_has_rcu_read_lock(const struct bpf_prog *prog, int subprog)
{
	const struct bpf_func_info_aux *sub_aux = &prog->aux->func_info_aux[subprog];

	if (!subprog)
		return !prog->sleepable;

	return !sub_aux->called[BPF_FUNC_CTX_SLEEPABLE] &&
	       !sub_aux->called[BPF_FUNC_CTX_NO_RCU_LOCK];
}

int bpf_check_attach_target(struct bpf_verifier_log *log,
			    const struct bpf_prog *prog,
			    const struct bpf_prog *tgt_prog,
			    u32 btf_id,
			    struct bpf_attach_target_info *tgt_info)
{
	bool prog_extension = prog->type == BPF_PROG_TYPE_EXT;
	bool prog_tracing = prog->type == BPF_PROG_TYPE_TRACING;
	char trace_symbol[KSYM_SYMBOL_LEN];
	const char prefix[] = "btf_trace_";
	struct bpf_raw_event_map *btp;
	int ret = 0, subprog = -1;
	const struct btf_type *t;
	bool conservative = true;
	const char *tname, *fname;
	struct btf *btf;
	long addr = 0;
	struct module *mod = NULL;

	if (!btf_id) {
		bpf_log(log, "Tracing programs must provide btf_id\n");
		return -EINVAL;
	}
	btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf;
	if (!btf) {
		bpf_log(log,
			"Tracing program can only be attached to another program annotated with BTF\n");
		return -EINVAL;
	}
	t = btf_type_by_id(btf, btf_id);
	if (!t) {
		bpf_log(log, "attach_btf_id %u is invalid\n", btf_id);
		return -EINVAL;
	}
	tname = btf_name_by_offset(btf, t->name_off);
	if (!tname) {
		bpf_log(log, "attach_btf_id %u doesn't have a name\n", btf_id);
		return -EINVAL;
	}
	if (tgt_prog) {
		struct bpf_prog_aux *aux = tgt_prog->aux;
		bool tgt_changes_pkt_data;
		bool tgt_might_sleep;
		bool tgt_can_unwind;

		if (bpf_prog_is_dev_bound(prog->aux) &&
		    !bpf_prog_dev_bound_match(prog, tgt_prog)) {
			bpf_log(log, "Target program bound device mismatch");
			return -EINVAL;
		}

		subprog = find_tgt_subprog(tgt_prog, btf_id);
		if (subprog == -1) {
			bpf_log(log, "Subprog %s doesn't exist\n", tname);
			return -EINVAL;
		}
		/*
		 * A struct_ops indirect trampoline converts arena arguments
		 * before invoking its program. A tracing or extension program
		 * attached to the main program would see the converted offset as a
		 * regular BTF pointer.
		 */
		if (subprog == 0 && bpf_prog_has_arena_ctx_arg(tgt_prog)) {
			bpf_log(log, "Cannot attach to a target with arena context arguments\n");
			return -EOPNOTSUPP;
		}
		if (aux->func && aux->func[subprog]->aux->exception_cb) {
			bpf_log(log,
				"%s programs cannot attach to exception callback\n",
				prog_extension ? "Extension" : "Tracing");
			return -EINVAL;
		}
		/* unwind_exit of the main prog is exit, unless it's an extension */
		tgt_can_unwind = (subprog || tgt_prog->type == BPF_PROG_TYPE_EXT) &&
				 (aux->func ? aux->func[subprog]->aux->can_unwind
					    : aux->can_unwind);
		/* unwind_exit would return to the trampoline that called the target */
		if (tgt_can_unwind && !prog_extension &&
		    prog->expected_attach_type != BPF_TRACE_FENTRY) {
			bpf_log(log, "Only fentry can attach to %s, which can unwind\n", tname);
			return -EINVAL;
		}
		conservative = aux->func_info_aux[subprog].unreliable;
		if (prog_extension) {
			if (aux->func_info_aux[subprog].linkage != BTF_FUNC_GLOBAL ||
			    conservative) {
				bpf_log(log,
					"Cannot replace static functions\n");
				return -EINVAL;
			}
			if (!prog->jit_requested) {
				bpf_log(log,
					"Extension programs should be JITed\n");
				return -EINVAL;
			}
			/*
			 * How much of the buffer of the tracepoint is used
			 * is checked for the program that is attached to it.
			 */
			if (tgt_prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE) {
				bpf_log(log,
					"Cannot extend a writable raw tracepoint program\n");
				return -EINVAL;
			}
			if (!func_has_rcu_read_lock(tgt_prog, subprog)) {
				bpf_log(log,
					"Cannot extend a function that runs without RCU read lock\n");
				return -EINVAL;
			}
			tgt_changes_pkt_data = aux->func
					       ? aux->func[subprog]->aux->changes_pkt_data
					       : aux->changes_pkt_data;
			if (prog->aux->changes_pkt_data && !tgt_changes_pkt_data) {
				bpf_log(log,
					"Extension program changes packet data, while original does not\n");
				return -EINVAL;
			}
			if (prog->aux->has_prologue &&
			    bpf_check_ext_prologue(log, tgt_prog, btf_id))
				return -EINVAL;

			tgt_might_sleep = aux->func
					  ? aux->func[subprog]->aux->might_sleep
					  : aux->might_sleep;
			if (prog->aux->might_sleep && !tgt_might_sleep) {
				bpf_log(log,
					"Extension program may sleep, while original does not\n");
				return -EINVAL;
			}
			/* There is no unwind_goto after the calls of the original */
			if (prog->aux->can_unwind && !tgt_can_unwind) {
				bpf_log(log,
					"Extension program can unwind, while original does not\n");
				return -EINVAL;
			}
		}
		if (!tgt_prog->jited) {
			bpf_log(log, "Can attach to only JITed progs\n");
			return -EINVAL;
		}
		if (prog_tracing) {
			if (aux->attach_tracing_prog) {
				/*
				 * Target program is an fentry/fexit which is already attached
				 * to another tracing program. More levels of nesting
				 * attachment are not allowed.
				 */
				bpf_log(log, "Cannot nest tracing program attach more than once\n");
				return -EINVAL;
			}
		} else if (tgt_prog->type == prog->type) {
			/*
			 * To avoid potential call chain cycles, prevent attaching of a
			 * program extension to another extension. It's ok to attach
			 * fentry/fexit to extension program.
			 */
			bpf_log(log, "Cannot recursively attach\n");
			return -EINVAL;
		}
		if (tgt_prog->type == BPF_PROG_TYPE_TRACING &&
		    prog_extension &&
		    (tgt_prog->expected_attach_type == BPF_TRACE_FENTRY ||
		     tgt_prog->expected_attach_type == BPF_TRACE_FEXIT ||
		     tgt_prog->expected_attach_type == BPF_TRACE_FENTRY_MULTI ||
		     tgt_prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
		     tgt_prog->expected_attach_type == BPF_TRACE_FSESSION ||
		     tgt_prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {
			/* Program extensions can extend all program types
			 * except fentry/fexit. The reason is the following.
			 * The fentry/fexit programs are used for performance
			 * analysis, stats and can be attached to any program
			 * type. When extension program is replacing XDP function
			 * it is necessary to allow performance analysis of all
			 * functions. Both original XDP program and its program
			 * extension. Hence attaching fentry/fexit to
			 * BPF_PROG_TYPE_EXT is allowed. If extending of
			 * fentry/fexit was allowed it would be possible to create
			 * long call chain fentry->extension->fentry->extension
			 * beyond reasonable stack size. Hence extending fentry
			 * is not allowed.
			 */
			bpf_log(log, "Cannot extend fentry/fexit/fsession\n");
			return -EINVAL;
		}
	} else {
		if (prog_extension) {
			bpf_log(log, "Cannot replace kernel functions\n");
			return -EINVAL;
		}
	}

	switch (prog->expected_attach_type) {
	case BPF_TRACE_RAW_TP:
		if (tgt_prog) {
			bpf_log(log,
				"Only FENTRY/FEXIT/FSESSION progs are attachable to another BPF prog\n");
			return -EINVAL;
		}
		if (!btf_type_is_typedef(t)) {
			bpf_log(log, "attach_btf_id %u is not a typedef\n",
				btf_id);
			return -EINVAL;
		}
		if (strncmp(prefix, tname, sizeof(prefix) - 1)) {
			bpf_log(log, "attach_btf_id %u points to wrong type name %s\n",
				btf_id, tname);
			return -EINVAL;
		}
		tname += sizeof(prefix) - 1;

		/* The func_proto of "btf_trace_##tname" is generated from typedef without argument
		 * names. Thus using bpf_raw_event_map to get argument names.
		 */
		btp = bpf_get_raw_tracepoint(tname);
		if (!btp)
			return -EINVAL;
		if (prog->sleepable && !tracepoint_is_faultable(btp->tp)) {
			bpf_log(log, "Sleepable program cannot attach to non-faultable tracepoint %s\n",
				tname);
			bpf_put_raw_tracepoint(btp);
			return -EINVAL;
		}
		fname = kallsyms_lookup((unsigned long)btp->bpf_func, NULL, NULL, NULL,
					trace_symbol);
		bpf_put_raw_tracepoint(btp);

		if (fname)
			ret = btf_find_by_name_kind(btf, fname, BTF_KIND_FUNC);

		if (!fname || ret < 0) {
			bpf_log(log, "Cannot find btf of tracepoint template, fall back to %s%s.\n",
				prefix, tname);
			t = btf_type_by_id(btf, t->type);
			if (!btf_type_is_ptr(t))
				/* should never happen in valid vmlinux build */
				return -EINVAL;
		} else {
			t = btf_type_by_id(btf, ret);
			if (!btf_type_is_func(t))
				/* should never happen in valid vmlinux build */
				return -EINVAL;
		}

		t = btf_type_by_id(btf, t->type);
		if (!btf_type_is_func_proto(t))
			/* should never happen in valid vmlinux build */
			return -EINVAL;

		break;
	case BPF_TRACE_ITER:
		if (!btf_type_is_func(t)) {
			bpf_log(log, "attach_btf_id %u is not a function\n",
				btf_id);
			return -EINVAL;
		}
		t = btf_type_by_id(btf, t->type);
		if (!btf_type_is_func_proto(t))
			return -EINVAL;
		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
		if (ret)
			return ret;
		break;
	default:
		if (!prog_extension)
			return -EINVAL;
		fallthrough;
	case BPF_MODIFY_RETURN:
	case BPF_LSM_MAC:
	case BPF_LSM_CGROUP:
	case BPF_TRACE_FENTRY:
	case BPF_TRACE_FEXIT:
	case BPF_TRACE_FSESSION:
	case BPF_TRACE_FSESSION_MULTI:
	case BPF_TRACE_FENTRY_MULTI:
	case BPF_TRACE_FEXIT_MULTI:
		if ((prog->expected_attach_type == BPF_TRACE_FSESSION ||
		    prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) &&
		    !bpf_jit_supports_fsession()) {
			bpf_log(log, "JIT does not support fsession\n");
			return -EOPNOTSUPP;
		}
		if (!btf_type_is_func(t)) {
			bpf_log(log, "attach_btf_id %u is not a function\n",
				btf_id);
			return -EINVAL;
		}
		if (prog_extension &&
		    btf_check_type_match(log, prog, btf, t))
			return -EINVAL;
		t = btf_attach_func_proto(log, btf, btf_id);
		if (!t || !btf_type_is_func_proto(t))
			return -EINVAL;

		if ((prog->aux->saved_dst_prog_type || prog->aux->saved_dst_attach_type) &&
		    (!tgt_prog || prog->aux->saved_dst_prog_type != tgt_prog->type ||
		     prog->aux->saved_dst_attach_type != tgt_prog->expected_attach_type))
			return -EINVAL;

		if (tgt_prog && conservative) {
			if (subprog > 0) {
				ret = check_unreliable_func_args(log, btf, t, tname);
				if (ret)
					return ret;
			}
			t = NULL;
		}

		ret = btf_distill_func_proto(log, btf, t, tname, &tgt_info->fmodel);
		if (ret < 0)
			return ret;
		if (tgt_prog) {
			ret = flatten_bpf_func_model(log, tname, &tgt_info->fmodel);
			if (ret < 0)
				return ret;
		}

		if (tgt_info->fmodel.ret_size > 8 &&
		    attach_uses_trampoline_retval(prog->expected_attach_type)) {
			bpf_log(log,
				"Attach to function %s with a >8 byte return value is not supported for this attach type\n",
				tname);
			return -EOPNOTSUPP;
		}

		/*
		 * *.multi programs don't need an address during program
		 * verification, we just take the module ref if needed.
		 */
		if (is_tracing_multi_id(prog, btf_id)) {
			if (btf_is_module(btf)) {
				mod = btf_try_get_module(btf);
				if (!mod)
					return -ENOENT;
			}
			addr = 0;
		} else if (tgt_prog) {
			if (subprog == 0)
				addr = (long) tgt_prog->bpf_func;
			else
				addr = (long) tgt_prog->aux->func[subprog]->bpf_func;
		} else {
			if (btf_is_module(btf)) {
				mod = btf_try_get_module(btf);
				if (mod)
					addr = find_kallsyms_symbol_value(mod, tname);
				else
					addr = 0;
			} else {
				addr = kallsyms_lookup_name(tname);
			}
			if (!addr) {
				module_put(mod);
				bpf_log(log,
					"The address of function %s cannot be found\n",
					tname);
				return -ENOENT;
			}
		}

		if (prog->sleepable) {
			ret = btf_id_allow_sleepable(btf_id, addr, prog, btf);
			if (ret) {
				module_put(mod);
				bpf_log(log, "%s is not sleepable\n", tname);
				return ret;
			}
		} else if (prog->expected_attach_type == BPF_MODIFY_RETURN) {
			if (tgt_prog) {
				module_put(mod);
				bpf_log(log, "can't modify return codes of BPF programs\n");
				return -EINVAL;
			}
			ret = -EINVAL;
			if (btf_kfunc_is_modify_return(btf, btf_id, prog) ||
			    !check_attach_modify_return(addr, tname))
				ret = 0;
			if (ret) {
				module_put(mod);
				bpf_log(log, "%s() is not modifiable\n", tname);
				return ret;
			}
		}

		break;
	}
	tgt_info->tgt_addr = addr;
	tgt_info->tgt_name = tname;
	tgt_info->tgt_type = t;
	tgt_info->tgt_mod = mod;
	return 0;
}

BTF_SET_START(btf_id_deny)
BTF_ID_UNUSED
#ifdef CONFIG_SMP
BTF_ID(func, ___migrate_enable)
BTF_ID(func, migrate_disable)
BTF_ID(func, migrate_enable)
#endif
#if !defined CONFIG_PREEMPT_RCU && !defined CONFIG_TINY_RCU
BTF_ID(func, rcu_read_unlock_strict)
#endif
#if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_TRACE_PREEMPT_TOGGLE)
BTF_ID(func, preempt_count_add)
BTF_ID(func, preempt_count_sub)
#endif
#ifdef CONFIG_PREEMPT_RCU
BTF_ID(func, __rcu_read_lock)
BTF_ID(func, __rcu_read_unlock)
#endif
BTF_SET_END(btf_id_deny)

/* fexit and fmod_ret can't be used to attach to __noreturn functions.
 * Currently, we must manually list all __noreturn functions here. Once a more
 * robust solution is implemented, this workaround can be removed.
 */
BTF_SET_START(noreturn_deny)
#ifdef CONFIG_IA32_EMULATION
BTF_ID(func, __ia32_sys_exit)
BTF_ID(func, __ia32_sys_exit_group)
#endif
#ifdef CONFIG_KUNIT
BTF_ID(func, __kunit_abort)
BTF_ID(func, kunit_try_catch_throw)
#endif
#ifdef CONFIG_MODULES
BTF_ID(func, __module_put_and_kthread_exit)
#endif
#ifdef CONFIG_X86_64
BTF_ID(func, __x64_sys_exit)
BTF_ID(func, __x64_sys_exit_group)
#endif
BTF_ID(func, do_exit)
BTF_ID(func, do_group_exit)
BTF_ID(func, kthread_complete_and_exit)
BTF_ID(func, make_task_dead)
BTF_SET_END(noreturn_deny)

static bool can_be_sleepable(struct bpf_prog *prog)
{
	if (prog->type == BPF_PROG_TYPE_TRACING) {
		switch (prog->expected_attach_type) {
		case BPF_TRACE_FENTRY:
		case BPF_TRACE_FEXIT:
		case BPF_MODIFY_RETURN:
		case BPF_TRACE_ITER:
		case BPF_TRACE_FSESSION:
		case BPF_TRACE_RAW_TP:
		case BPF_TRACE_FENTRY_MULTI:
		case BPF_TRACE_FEXIT_MULTI:
		case BPF_TRACE_FSESSION_MULTI:
			return true;
		default:
			return false;
		}
	}
	if (prog->type == BPF_PROG_TYPE_LSM)
		return prog->expected_attach_type != BPF_LSM_CGROUP;

	return prog->type == BPF_PROG_TYPE_KPROBE /* only for uprobes */ ||
	       prog->type == BPF_PROG_TYPE_STRUCT_OPS ||
	       prog->type == BPF_PROG_TYPE_RAW_TRACEPOINT ||
	       prog->type == BPF_PROG_TYPE_TRACEPOINT;
}

static int check_attach_btf_id(struct bpf_verifier_env *env)
{
	struct bpf_prog *prog = env->prog;
	struct bpf_prog *tgt_prog = prog->aux->dst_prog;
	struct bpf_attach_target_info tgt_info = {};
	u32 btf_id = prog->aux->attach_btf_id;
	struct bpf_trampoline *tr;
	int ret;
	u64 key;

	if (prog->type == BPF_PROG_TYPE_SYSCALL) {
		if (prog->sleepable)
			/* attach_btf_id checked to be zero already */
			return 0;
		verbose(env, "Syscall programs can only be sleepable\n");
		return -EINVAL;
	}

	if (prog->sleepable && !can_be_sleepable(prog)) {
		verbose(env, "Program of this type cannot be sleepable\n");
		return -EINVAL;
	}

	if (prog->type == BPF_PROG_TYPE_STRUCT_OPS)
		return check_struct_ops_btf_id(env);

	if (prog->type != BPF_PROG_TYPE_TRACING &&
	    prog->type != BPF_PROG_TYPE_LSM &&
	    prog->type != BPF_PROG_TYPE_EXT)
		return 0;

	ret = bpf_check_attach_target(&env->log, prog, tgt_prog, btf_id, &tgt_info);
	if (ret)
		return ret;

	if (tgt_prog && prog->type == BPF_PROG_TYPE_EXT) {
		/* to make freplace equivalent to their targets, they need to
		 * inherit env->ops and expected_attach_type for the rest of the
		 * verification
		 */
		env->ops = bpf_verifier_ops[tgt_prog->type];
		prog->expected_attach_type = tgt_prog->expected_attach_type;
	}

	/* store info about the attachment target that will be used later */
	prog->aux->attach_func_proto = tgt_info.tgt_type;
	prog->aux->attach_func_name = tgt_info.tgt_name;
	prog->aux->mod = tgt_info.tgt_mod;

	if (tgt_prog) {
		prog->aux->saved_dst_prog_type = tgt_prog->type;
		prog->aux->saved_dst_attach_type = tgt_prog->expected_attach_type;
	}

	if (prog->expected_attach_type == BPF_TRACE_RAW_TP) {
		prog->aux->attach_btf_trace = true;
		return 0;
	} else if (prog->expected_attach_type == BPF_TRACE_ITER) {
		return bpf_iter_prog_supported(prog);
	}

	if (prog->type == BPF_PROG_TYPE_LSM) {
		ret = bpf_lsm_verify_prog(&env->log, prog);
		if (ret < 0)
			return ret;
	} else if (prog->type == BPF_PROG_TYPE_TRACING &&
		   btf_id_set_contains(&btf_id_deny, btf_id)) {
		verbose(env, "Attaching tracing programs to function '%s' is rejected.\n",
			tgt_info.tgt_name);
		return -EINVAL;
	} else if ((prog->expected_attach_type == BPF_TRACE_FEXIT ||
		   prog->expected_attach_type == BPF_TRACE_FSESSION ||
		   prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI ||
		   prog->expected_attach_type == BPF_MODIFY_RETURN) &&
		   btf_id_set_contains(&noreturn_deny, btf_id)) {
		verbose(env, "Attaching fexit/fsession/fmod_ret to __noreturn function '%s' is rejected.\n",
			tgt_info.tgt_name);
		return -EINVAL;
	}

	/*
	 * We don't get trampoline for tracing_multi programs at this point,
	 * it's done when tracing_multi link is created.
	 */
	if (prog->type == BPF_PROG_TYPE_TRACING &&
	    is_tracing_multi(prog->expected_attach_type))
		return 0;

	key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id);
	tr = bpf_trampoline_get(key, &tgt_info);
	if (!tr)
		return -ENOMEM;

	if (tgt_prog && tgt_prog->aux->tail_call_reachable)
		bpf_trampoline_set_flags(tr, BPF_TRAMP_F_TAIL_CALL_CTX);

	prog->aux->dst_trampoline = tr;
	return 0;
}

int bpf_check_attach_btf_id_multi(struct btf *btf, struct bpf_prog *prog, u32 btf_id,
				  struct bpf_attach_target_info *tgt_info)
{
	const struct btf_type *t;
	unsigned long addr;
	const char *tname;
	int err;

	if (!btf_id || !btf)
		return -EINVAL;

	/* Check noreturn attachment. */
	if ((prog->expected_attach_type == BPF_TRACE_FEXIT_MULTI ||
	     prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI) &&
	     btf_id_set_contains(&noreturn_deny, btf_id))
		return -EINVAL;
	/* Check denied attachment. */
	if (btf_id_set_contains(&btf_id_deny, btf_id))
		return -EINVAL;

	/* Check and get function target data. */
	t = btf_type_by_id(btf, btf_id);
	if (!t)
		return -EINVAL;
	tname = btf_name_by_offset(btf, t->name_off);
	if (!tname)
		return -EINVAL;
	t = btf_attach_func_proto(NULL, btf, btf_id);
	if (!t || !btf_type_is_func_proto(t))
		return -EINVAL;
	err = btf_distill_func_proto(NULL, btf, t, tname, &tgt_info->fmodel);
	if (err < 0)
		return err;
	if (tgt_info->fmodel.ret_size > 8 &&
	    attach_uses_trampoline_retval(prog->expected_attach_type))
		return -EOPNOTSUPP;
	if (btf_is_module(btf)) {
		/* The bpf program already holds reference to module. */
		if (WARN_ON_ONCE(!prog->aux->mod))
			return -EINVAL;
		addr = find_kallsyms_symbol_value(prog->aux->mod, tname);
	} else {
		addr = kallsyms_lookup_name(tname);
	}
	if (!addr || !ftrace_location(addr))
		return -ENOENT;

	/* Check sleepable program attachment. */
	if (prog->sleepable) {
		err = btf_id_allow_sleepable(btf_id, addr, prog, btf);
		if (err)
			return err;
	}
	tgt_info->tgt_addr = addr;
	return 0;
}

struct btf *bpf_get_btf_vmlinux(void)
{
	/* Pairs with the smp_store_release() on the parse path below. */
	struct btf *btf = smp_load_acquire(&btf_vmlinux);

	if (!btf && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) {
		mutex_lock(&btf_vmlinux_lock);
		btf = btf_vmlinux;
		if (!btf) {
			btf = btf_parse_vmlinux();
			/*
			 * Order the parsed BTF contents and the globals the
			 * parse populated (e.g. bpf_ctx_convert.t) before
			 * the pointer publication. Pairs with the acquire
			 * on the lockless fast path above.
			 */
			smp_store_release(&btf_vmlinux, btf);
		}
		mutex_unlock(&btf_vmlinux_lock);
	}
	return btf;
}

/*
 * The add_fd_from_fd_array() is executed only if fd_array_cnt is non-zero. In
 * this case expect that every file descriptor in the array is either a map or
 * a BTF. Everything else is considered to be trash.
 */
static int add_fd_from_fd_array(struct bpf_verifier_env *env, u32 idx, int fd)
{
	struct bpf_map *map;
	struct btf *btf;
	CLASS(fd, f)(fd);
	int err;

	map = __bpf_map_get(f);
	if (!IS_ERR(map)) {
		err = __add_used_map(env, map);
		if (err < 0)
			return err;
		fd_slot_set_map(&env->fd_array[idx], map);
		return 0;
	}

	btf = __btf_get_by_fd(f);
	if (!IS_ERR(btf)) {
		btf_get(btf);
		err = __add_used_btf(env, btf);
		if (err < 0)
			return err;
		fd_slot_set_btf(&env->fd_array[idx], btf);
		return 0;
	}

	verbose(env, "fd %d is not pointing to valid bpf_map or btf\n", fd);
	return PTR_ERR(map);
}

/*
 * A continuous fd_array is resolved into an in-memory cache with one slot
 * per entry. The bound here is deliberately generous and not derived from
 * the per-program object limits: Duplicate entries /are/ permitted, and
 * the number of distinct maps and BTFs a program can bind is enforced when
 * each entry is resolved by __add_used_map() and __add_used_btf().
 */
#define MAX_FD_ARRAY_CNT 4096

static int process_fd_array_continuous(struct bpf_verifier_env *env,
				       bpfptr_t fd_array, u32 cnt)
{
	int fd, ret;
	u32 i;

	if (cnt > MAX_FD_ARRAY_CNT) {
		verbose(env, "fd_array has too many entries (%u, max %u)\n",
			cnt, MAX_FD_ARRAY_CNT);
		return -E2BIG;
	}

	env->fd_array = kvzalloc_objs(*env->fd_array, cnt, GFP_KERNEL_ACCOUNT);
	if (!env->fd_array)
		return -ENOMEM;
	env->fd_array_cnt = cnt;
	for (i = 0; i < cnt; i++) {
		if (copy_from_bpfptr_offset(&fd, fd_array,
					    (size_t)i * sizeof(fd), sizeof(fd)))
			return -EFAULT;
		ret = add_fd_from_fd_array(env, i, fd);
		if (ret)
			return ret;
	}
	return 0;
}

static int process_fd_array(struct bpf_verifier_env *env,
			    union bpf_attr *attr, bpfptr_t uattr)
{
	bpfptr_t fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel);

	if (bpfptr_is_null(fd_array)) {
		if (attr->fd_array_cnt) {
			verbose(env, "fd_array_cnt %u without fd_array is invalid\n",
				attr->fd_array_cnt);
			return -EINVAL;
		}
		return 0;
	}
	/*
	 * New API: the caller passes fd_array_cnt and a continuous array that
	 * is resolved and bound up front. Legacy API (no fd_array_cnt): keep
	 * the caller's array and resolve entries on the spot at each reference.
	 */
	if (attr->fd_array_cnt)
		return process_fd_array_continuous(env, fd_array,
						   attr->fd_array_cnt);
	env->fd_array_raw = fd_array;
	return 0;
}

/* replace a generic kfunc with a specialized version if necessary */
static int specialize_kfunc(struct bpf_verifier_env *env, struct bpf_kfunc_desc *desc, int insn_idx)
{
	struct bpf_prog *prog = env->prog;
	bool seen_direct_write;
	void *xdp_kfunc;
	bool is_rdonly;
	u32 func_id = desc->func_id;
	u16 offset = desc->offset;
	unsigned long addr = desc->addr;

	if (offset) /* return if module BTF is used */
		return 0;

	if (bpf_dev_bound_kfunc_id(func_id)) {
		xdp_kfunc = bpf_dev_bound_resolve_kfunc(prog, func_id);
		if (xdp_kfunc)
			addr = (unsigned long)xdp_kfunc;
		/* fallback to default kfunc when not supported by netdev */
	} else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
		seen_direct_write = env->seen_direct_write;
		is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE);

		if (is_rdonly)
			addr = (unsigned long)bpf_dynptr_from_skb_rdonly;

		/* restore env->seen_direct_write to its original value, since
		 * may_access_direct_pkt_data mutates it
		 */
		env->seen_direct_write = seen_direct_write;
	} else if (func_id == special_kfunc_list[KF_bpf_set_dentry_xattr]) {
		if (bpf_lsm_has_d_inode_locked(prog))
			addr = (unsigned long)bpf_set_dentry_xattr_locked;
	} else if (func_id == special_kfunc_list[KF_bpf_remove_dentry_xattr]) {
		if (bpf_lsm_has_d_inode_locked(prog))
			addr = (unsigned long)bpf_remove_dentry_xattr_locked;
	} else if (func_id == special_kfunc_list[KF_bpf_dynptr_from_file]) {
		if (!env->insn_aux_data[insn_idx].non_sleepable)
			addr = (unsigned long)bpf_dynptr_from_file_sleepable;
	} else if (func_id == special_kfunc_list[KF_bpf_arena_alloc_pages]) {
		if (env->insn_aux_data[insn_idx].non_sleepable)
			addr = (unsigned long)bpf_arena_alloc_pages_non_sleepable;
	} else if (func_id == special_kfunc_list[KF_bpf_arena_free_pages]) {
		if (env->insn_aux_data[insn_idx].non_sleepable)
			addr = (unsigned long)bpf_arena_free_pages_non_sleepable;
	}
	desc->addr = addr;
	return 0;
}

static int add_kfunc_desc_target(struct bpf_verifier_env *env,
				 const struct bpf_kfunc_desc *target_desc,
				 u16 base_desc_idx, u16 *desc_idx)
{
	struct bpf_kfunc_desc desc = *target_desc;
	struct bpf_kfunc_desc_tab *new_tab;
	struct bpf_kfunc_desc_tab *tab;
	struct bpf_prog_aux *prog_aux;
	u32 i;

	prog_aux = env->prog->aux;
	tab = prog_aux->kfunc_tab;

	if (base_desc_idx >= tab->nr_base_descs) {
		verifier_bug(env, "kfunc desc_idx %d out of bounds (%d descriptors)",
				base_desc_idx, tab->nr_base_descs);
		return -EFAULT;
	}
	if (tab->descs[base_desc_idx].func_id != desc.func_id) {
		verifier_bug(env, "kfunc desc %d has invalid id (expected %d, got %d)",
				base_desc_idx, tab->descs[base_desc_idx].func_id, desc.func_id);
		return -EFAULT;
	}
	if (tab->descs[base_desc_idx].offset != desc.offset) {
		verifier_bug(env, "kfunc desc %d has invalid offset (expected %d, got %d)",
				base_desc_idx, tab->descs[base_desc_idx].offset, desc.offset);
		return -EFAULT;
	}

	if (tab->descs[base_desc_idx].addr == desc.addr) {
		*desc_idx = base_desc_idx;
		return 0;
	}

	for (i = tab->nr_base_descs; i < tab->nr_descs; i++) {
		if (tab->descs[i].func_id == desc.func_id &&
		    tab->descs[i].offset == desc.offset &&
		    tab->descs[i].addr == desc.addr) {
			*desc_idx = i;
			return 0;
		}
	}

	if (tab->nr_descs == MAX_KFUNC_CALL_DESCS) {
		verbose(env, "too many different kernel function call targets\n");
		return -E2BIG;
	}

	new_tab = krealloc(tab, struct_size(tab, descs, tab->nr_descs + 1),
			   GFP_KERNEL_ACCOUNT);
	if (!new_tab)
		return -ENOMEM;
	tab = new_tab;
	prog_aux->kfunc_tab = tab;

	*desc_idx = tab->nr_descs;
	tab->descs[tab->nr_descs++] = desc;
	return 0;
}

static void __fixup_collection_insert_kfunc(struct bpf_insn_aux_data *insn_aux,
					    u16 struct_meta_reg,
					    u16 node_offset_reg,
					    struct bpf_insn *insn,
					    struct bpf_insn *insn_buf,
					    int *cnt)
{
	struct btf_struct_meta *kptr_struct_meta = insn_aux->kptr_struct_meta;
	struct bpf_insn addr[2] = { BPF_LD_IMM64(struct_meta_reg, (long)kptr_struct_meta) };

	insn_buf[0] = addr[0];
	insn_buf[1] = addr[1];
	insn_buf[2] = BPF_MOV64_IMM(node_offset_reg, insn_aux->insert_off);
	insn_buf[3] = *insn;
	*cnt = 4;
}

int bpf_fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
		     struct bpf_insn *insn_buf, int insn_idx, int *cnt)
{
	struct bpf_kfunc_desc desc_copy;
	struct bpf_kfunc_desc *desc;
	unsigned long call_imm;
	u16 base_desc_idx, desc_idx;
	bool near_call;
	int err;

	if (!insn->imm) {
		verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
		return -EINVAL;
	}

	*cnt = 0;

	/* insn->imm has the btf func_id. Replace it with an offset relative to
	 * __bpf_call_base, unless the JIT needs to call functions that are
	 * further than 32 bits away (bpf_jit_supports_far_kfunc_call()).
	 */
	desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
	if (!desc) {
		verifier_bug(env, "kernel function descriptor not found for func_id %u",
			     insn->imm);
		return -EFAULT;
	}
	base_desc_idx = desc - env->prog->aux->kfunc_tab->descs;

	near_call = !bpf_jit_supports_far_kfunc_call();
	desc_copy = *desc;
	desc = &desc_copy;

	err = specialize_kfunc(env, desc, insn_idx);
	if (err)
		return err;

	if (near_call) {
		call_imm = BPF_CALL_IMM(desc->addr);
		if ((unsigned long)(s32)call_imm != call_imm) {
			verbose(env, "address of kernel func_id %u is out of range\n",
				desc->func_id);
			return -EINVAL;
		}
		insn->imm = call_imm;
	}

	err = add_kfunc_desc_target(env, desc, base_desc_idx, &desc_idx);
	if (err)
		return err;
	insn->off = desc_idx;

	if (is_bpf_obj_new_kfunc(desc->func_id) || is_bpf_percpu_obj_new_kfunc(desc->func_id)) {
		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
		struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };
		u64 obj_new_size = env->insn_aux_data[insn_idx].obj_new_size;

		if (is_bpf_percpu_obj_new_kfunc(desc->func_id) && kptr_struct_meta) {
			verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d",
				     insn_idx);
			return -EFAULT;
		}

		insn_buf[0] = BPF_MOV64_IMM(BPF_REG_1, obj_new_size);
		insn_buf[1] = addr[0];
		insn_buf[2] = addr[1];
		insn_buf[3] = *insn;
		*cnt = 4;
	} else if (is_bpf_obj_drop_kfunc(desc->func_id) ||
		   is_bpf_percpu_obj_drop_kfunc(desc->func_id) ||
		   is_bpf_refcount_acquire_kfunc(desc->func_id)) {
		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
		struct bpf_insn addr[2] = { BPF_LD_IMM64(BPF_REG_2, (long)kptr_struct_meta) };

		if (is_bpf_percpu_obj_drop_kfunc(desc->func_id) && kptr_struct_meta) {
			verifier_bug(env, "NULL kptr_struct_meta expected at insn_idx %d",
				     insn_idx);
			return -EFAULT;
		}

		if (is_bpf_refcount_acquire_kfunc(desc->func_id) && !kptr_struct_meta) {
			verifier_bug(env, "kptr_struct_meta expected at insn_idx %d",
				     insn_idx);
			return -EFAULT;
		}

		insn_buf[0] = addr[0];
		insn_buf[1] = addr[1];
		insn_buf[2] = *insn;
		*cnt = 3;
	} else if (is_bpf_list_push_kfunc(desc->func_id) ||
		   is_bpf_rbtree_add_kfunc(desc->func_id)) {
		struct btf_struct_meta *kptr_struct_meta = env->insn_aux_data[insn_idx].kptr_struct_meta;
		int struct_meta_reg = BPF_REG_3;
		int node_offset_reg = BPF_REG_4;

		/* list_add/rbtree_add have an extra arg (prev/less),
		 * so args-to-fixup are in diff regs.
		 */
		if (desc->func_id == special_kfunc_list[KF_bpf_list_add] ||
		    is_bpf_rbtree_add_kfunc(desc->func_id)) {
			struct_meta_reg = BPF_REG_4;
			node_offset_reg = BPF_REG_5;
		}

		if (!kptr_struct_meta) {
			verifier_bug(env, "kptr_struct_meta expected at insn_idx %d",
				     insn_idx);
			return -EFAULT;
		}

		__fixup_collection_insert_kfunc(&env->insn_aux_data[insn_idx], struct_meta_reg,
						node_offset_reg, insn, insn_buf, cnt);
	} else if (desc->func_id == special_kfunc_list[KF_bpf_cast_to_kern_ctx] ||
		   desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
		insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
		*cnt = 1;
	} else if (desc->func_id == special_kfunc_list[KF_bpf_session_is_return] &&
		   (env->prog->expected_attach_type == BPF_TRACE_FSESSION ||
		    env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {

		/*
		 * inline the bpf_session_is_return() for fsession:
		 *   bool bpf_session_is_return(void *ctx)
		 *   {
		 *       return (((u64 *)ctx)[-1] >> BPF_TRAMP_IS_RETURN_SHIFT) & 1;
		 *   }
		 */
		insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
		insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_IS_RETURN_SHIFT);
		insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1);
		*cnt = 3;
	} else if (desc->func_id == special_kfunc_list[KF_bpf_session_cookie] &&
		   (env->prog->expected_attach_type == BPF_TRACE_FSESSION ||
		    env->prog->expected_attach_type == BPF_TRACE_FSESSION_MULTI)) {
		/*
		 * inline bpf_session_cookie() for fsession:
		 *   __u64 *bpf_session_cookie(void *ctx)
		 *   {
		 *       u64 off = (((u64 *)ctx)[-1] >> BPF_TRAMP_COOKIE_INDEX_SHIFT) & 0xFF;
		 *       return &((u64 *)ctx)[-off];
		 *   }
		 */
		insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
		insn_buf[1] = BPF_ALU64_IMM(BPF_RSH, BPF_REG_0, BPF_TRAMP_COOKIE_INDEX_SHIFT);
		insn_buf[2] = BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 0xFF);
		insn_buf[3] = BPF_ALU64_IMM(BPF_LSH, BPF_REG_0, 3);
		insn_buf[4] = BPF_ALU64_REG(BPF_SUB, BPF_REG_0, BPF_REG_1);
		insn_buf[5] = BPF_ALU64_IMM(BPF_NEG, BPF_REG_0, 0);
		*cnt = 6;
	} else if (desc->func_id == special_kfunc_list[KF_bpf_iter_num_new]) {
		/* inline bpf_iter_num_new(&it, start, end); R1=&it, R2=start, R3=end */
		int i = 0;

		/* if (start > end) goto einval; */
		insn_buf[i++] = BPF_JMP32_REG(BPF_JSGT, BPF_REG_2, BPF_REG_3, 8);
		/* r0 = (u32)end - (u32)start; if (r0 > BPF_MAX_LOOPS) goto e2big; */
		insn_buf[i++] = BPF_MOV32_REG(BPF_REG_0, BPF_REG_3);
		insn_buf[i++] = BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_2);
		insn_buf[i++] = BPF_JMP_IMM(BPF_JGT, BPF_REG_0, BPF_MAX_LOOPS, 8);
		/* s->cur = start - 1; s->end = end; return 0; */
		insn_buf[i++] = BPF_ALU32_IMM(BPF_ADD, BPF_REG_2, -1);
		insn_buf[i++] = BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_2, 0);
		insn_buf[i++] = BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_3, 4);
		insn_buf[i++] = BPF_MOV64_IMM(BPF_REG_0, 0);
		insn_buf[i++] = BPF_JMP_A(5);
		/* einval: s->cur = s->end = 0; return -EINVAL; */
		insn_buf[i++] = BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0);
		insn_buf[i++] = BPF_MOV64_IMM(BPF_REG_0, -EINVAL);
		insn_buf[i++] = BPF_JMP_A(2);
		/* e2big: s->cur = s->end = 0; return -E2BIG; */
		insn_buf[i++] = BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0);
		insn_buf[i++] = BPF_MOV64_IMM(BPF_REG_0, -E2BIG);
		*cnt = i;
	} else if (desc->func_id == special_kfunc_list[KF_bpf_iter_num_next]) {
		/* inline bpf_iter_num_next(&it); R1=&it, returns &s->cur or NULL */
		int i = 0;

		/* r0 = s->cur + 1; if ((s32)r0 >= s->end) goto done; */
		insn_buf[i++] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0);
		insn_buf[i++] = BPF_ALU32_IMM(BPF_ADD, BPF_REG_0, 1);
		insn_buf[i++] = BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1, 4);
		insn_buf[i++] = BPF_JMP32_REG(BPF_JSGE, BPF_REG_0, BPF_REG_2, 3);
		/* s->cur = r0; return &s->cur; */
		insn_buf[i++] = BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0);
		insn_buf[i++] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
		insn_buf[i++] = BPF_JMP_A(2);
		/* done: s->cur = s->end = 0; return NULL; */
		insn_buf[i++] = BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0);
		insn_buf[i++] = BPF_MOV64_IMM(BPF_REG_0, 0);
		*cnt = i;
	} else if (desc->func_id == special_kfunc_list[KF_bpf_iter_num_destroy]) {
		/* bpf_iter_num_destroy() is a no-op; emit a nop to drop the call */
		insn_buf[0] = BPF_JMP_A(0);
		*cnt = 1;
	}

	if (env->insn_aux_data[insn_idx].arg_prog) {
		u32 regno = env->insn_aux_data[insn_idx].arg_prog;
		struct bpf_insn ld_addrs[2] = { BPF_LD_IMM64(regno, (long)env->prog->aux) };
		int idx = *cnt;

		insn_buf[idx++] = ld_addrs[0];
		insn_buf[idx++] = ld_addrs[1];
		insn_buf[idx++] = *insn;
		*cnt = idx;
	}
	return 0;
}

/*
 * Upper bound on the PKCS#7 signature blob passed with a program. Comfortably
 * above the largest signature the kernel can verify, and far below anything
 * that would make rejecting a load expensive. Deliberately a fixed number so
 * that what the syscall accepts does not depend on PAGE_SIZE.
 */
#define BPF_PROG_MAX_SIGNATURE_SIZE	(64 * 1024)

static enum bpf_sig_keyring bpf_classify_keyring(s32 keyring_id)
{
	switch (keyring_id) {
	case 0:
		return BPF_SIG_KEYRING_BUILTIN;
	case (s32)(unsigned long)VERIFY_USE_SECONDARY_KEYRING:
		return BPF_SIG_KEYRING_SECONDARY;
	case (s32)(unsigned long)VERIFY_USE_PLATFORM_KEYRING:
		return BPF_SIG_KEYRING_PLATFORM;
	case KEY_SPEC_BPF_KEYRING:
		return BPF_SIG_KEYRING_BPF;
	default:
		return BPF_SIG_KEYRING_USER;
	}
}

/*
 * Verify the PKCS#7 signature of a loaded program. Called from bpf_check()
 * once the program's metadata maps have been resolved into used_maps, so
 * the exact maps folded into the signature are the ones the program binds.
 *
 * The signature covers the instructions followed by the frozen contents of
 * each map, in @maps order: insns || map_0 || map_1 || [...]. On success the
 * verdict and keyring info are recorded on prog->aux.
 */
static int bpf_prog_verify_signature(struct bpf_verifier_env *env,
				     union bpf_attr *attr, bool is_kernel)
{
	bpfptr_t usig = make_bpfptr(attr->signature, is_kernel);
	struct bpf_dynptr_kern sig_ptr, data_ptr;
	struct bpf_prog *prog = env->prog;
	struct bpf_map **maps = env->used_maps;
	struct bpf_key *key = NULL;
	void *sig, *data = NULL;
	u32 map_cnt = env->used_map_cnt;
	u32 i, off, insns_sz;
	u64 data_sz;
	int err = 0;

	/*
	 * The signature covers the insns as submitted. CO-RE relocations would
	 * have the kernel rewrite them afterwards, with values the loader picks
	 * through the BTF it supplies, see bpf_check_core_relo().
	 */
	if (attr->core_relo_cnt) {
		verbose(env, "signed program cannot carry CO-RE relocations\n");
		return -EACCES;
	}
	if (!attr->signature_size ||
	    attr->signature_size > BPF_PROG_MAX_SIGNATURE_SIZE)
		return -EINVAL;

	if (system_keyring_id_check(attr->keyring_id) == 0) {
		key = bpf_lookup_system_key(attr->keyring_id);
	} else if (attr->keyring_id == KEY_SPEC_BPF_KEYRING) {
		key = bpf_lookup_keyring();
	} else if (bpf_keyring_enforced()) {
		verbose(env, "caller-supplied keyring refused, use bpf keyring\n");
		return -EPERM;
	} else {
		key = bpf_lookup_user_key(attr->keyring_id, 0);
	}
	if (!key) {
		if (attr->keyring_id == KEY_SPEC_BPF_KEYRING) {
			verbose(env, "the bpf keyring is empty or has not been restricted\n");
			return -ENOKEY;
		}
		verbose(env, "cannot resolve signing keyring with keyring_id %d\n",
			attr->keyring_id);
		return -EINVAL;
	}

	sig = kvmemdup_bpfptr(usig, attr->signature_size);
	if (IS_ERR(sig)) {
		bpf_key_put(key);
		return PTR_ERR(sig);
	}

	insns_sz = prog->len * sizeof(struct bpf_insn);
	data_sz = insns_sz;
	for (i = 0; i < map_cnt; i++) {
		struct bpf_map *map = maps[i];

		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
		    !map->ops->map_direct_value_addr) {
			verbose(env, "signed program metadata map '%s' must be an array\n",
				map->name);
			err = -EINVAL;
			goto out;
		}
		if (!READ_ONCE(map->frozen)) {
			verbose(env, "signed program metadata map '%s' must be frozen\n",
				map->name);
			err = -EPERM;
			goto out;
		}
		if (bpf_map_write_active(map)) {
			verbose(env, "signed program metadata map '%s' has active writers\n",
				map->name);
			err = -EBUSY;
			goto out;
		}
		if (!map->excl_prog_sha) {
			verbose(env, "signed program metadata map '%s' must be exclusive\n",
				map->name);
			err = -EPERM;
			goto out;
		}
		data_sz += map->value_size;
	}
	if (bpf_dynptr_check_size(data_sz)) {
		verbose(env, "signed payload too large: %llu bytes\n", data_sz);
		err = -E2BIG;
		goto out;
	}
	data = kvmalloc(data_sz, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
	if (!data) {
		err = -ENOMEM;
		goto out;
	}
	memcpy(data, prog->insnsi, insns_sz);
	off = insns_sz;
	for (i = 0; i < map_cnt; i++) {
		struct bpf_map *map = maps[i];
		u64 addr;

		err = map->ops->map_direct_value_addr(map, &addr, 0);
		if (err) {
			verbose(env, "failed to read signed metadata map '%s': %d\n",
				map->name, err);
			goto out;
		}
		memcpy(data + off, (void *)(unsigned long)addr,
		       map->value_size);
		off += map->value_size;
	}

	bpf_dynptr_init(&data_ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, data_sz);
	bpf_dynptr_init(&sig_ptr, sig, BPF_DYNPTR_TYPE_LOCAL, 0,
			attr->signature_size);

	err = bpf_verify_pkcs7_signature((struct bpf_dynptr *)&data_ptr,
					 (struct bpf_dynptr *)&sig_ptr, key);
	if (err) {
		verbose(env, "signature verification failed: %d\n", err);
	} else {
		verbose(env, "signature verification passed\n");
		prog->aux->sig.keyring_serial = bpf_key_serial(key);
		prog->aux->sig.keyring_type = bpf_classify_keyring(attr->keyring_id);
		prog->aux->sig.verdict = BPF_SIG_VERIFIED;
	}
out:
	kvfree(data);
	bpf_key_put(key);
	kvfree(sig);
	return err;
}

/*
 * bpf_clone_redirect() transmits from inside the program, so a tc egress or
 * lwt_xmit program that redirects to its own device runs again on top of its
 * own frame, and again from there, until the datapath's recursion limit drops
 * the packet: ten frames deep. Ten MAX_BPF_STACK frames fit the kernel stack
 * as they always did; ten MAX_BPF_STACK_JIT frames would not, so a program
 * calling it keeps the smaller budget. The redirect helpers that transmit
 * after the program has returned leave no frame behind.
 */
static bool bpf_prog_reenters_datapath(const struct bpf_prog *prog)
{
	const struct bpf_insn *insn = prog->insnsi;
	int i;

	for (i = 0; i < prog->len; i++, insn++)
		if (bpf_helper_call(insn) && insn->imm == BPF_FUNC_clone_redirect)
			return true;
	return false;
}

/* Various log level 2 information about the program */
static void log_program(struct bpf_verifier_env *env)
{
	struct bpf_insn_aux_data *insn_aux = env->insn_aux_data;
	struct bpf_insn *insns = env->prog->insnsi;
	u32 insn_cnt = env->prog->len;
	u64 pos, insn_pos;
	u32 i, j;

	verbose(env, "Program dump (scc? loop_header? idom insn#: live_regs_before):\n");
	for (i = 0; i < insn_cnt; ++i) {
		verbose_linfo(env, i, "    ; ");
		if (env->insn_aux_data[i].scc)
			verbose(env, "%3d ", env->insn_aux_data[i].scc);
		else
			verbose(env, "    ");
		if (env->insn_aux_data[i].loop_header >= 0)
			verbose(env, "%3d ", env->insn_aux_data[i].loop_header);
		else
			verbose(env, "    ");
		verbose(env, "%3d ", env->idoms[i]);
		verbose(env, "%3d: ", i);
		for (j = BPF_REG_0; j < BPF_REG_10; ++j)
			if (insn_aux[i].live_regs_before & BIT(j))
				verbose(env, "%d", j);
			else
				verbose(env, ".");
		verbose(env, " ");
		pos = env->log.end_pos;
		bpf_verbose_insn(env, &insns[i]);
		insn_pos = env->log.end_pos;
		if (insn_aux[i].zext_dst)
			verbose(env, "%*c; zext", bpf_vlog_alignment(insn_pos - pos), ' ');
		verbose(env, "\n");
		if (bpf_is_ldimm64(&insns[i]))
			i++;
	}
}

int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr,
	      struct bpf_log_attr *attr_log)
{
	u64 start_time = ktime_get_ns();
	struct bpf_verifier_env *env;
	int i, len, ret = -EINVAL, err;
	bool is_priv;

	BTF_TYPE_EMIT(enum bpf_features);

	/* no program is valid */
	if (ARRAY_SIZE(bpf_verifier_ops) == 0)
		return -EINVAL;

	/* 'struct bpf_verifier_env' can be global, but since it's not small,
	 * allocate/free it every time bpf_check() is called
	 */
	env = kvzalloc_obj(struct bpf_verifier_env, GFP_KERNEL_ACCOUNT);
	if (!env)
		return -ENOMEM;

	env->bt.env = env;
	env->prog = *prog;
	env->ops = bpf_verifier_ops[env->prog->type];
	env->stack_limit = bpf_prog_stack_limit(env->prog);
	if (bpf_prog_reenters_datapath(env->prog))
		env->stack_limit = MAX_BPF_STACK;

	env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token);
	env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token);
	env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token);
	env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token);
	env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF);
	env->signature = attr->signature;

	/* user could have requested verbose verifier output
	 * and supplied buffer to store the verification trace
	 */
	ret = bpf_vlog_init(&env->log, attr_log->level, attr_log->ubuf, attr_log->size);
	if (ret)
		goto err_free_env;
	ret = bpf_diag_init(env);
	if (ret)
		goto err_prep;
	if (env->prog->insnsi[env->prog->len - 1].code == (BPF_LD | BPF_IMM | BPF_DW)) {
		verbose(env, "invalid bpf_ld_imm64 insn\n");
		ret = -EINVAL;
		goto err_prep;
	}

	ret = process_fd_array(env, attr, uattr);
	if (ret)
		goto err_prep;

	if (env->signature) {
		ret = bpf_prog_verify_signature(env, attr, uattr.is_kernel);
		if (ret)
			goto err_prep;
	}

	ret = security_bpf_prog_load(env->prog, attr, env->prog->aux->token,
				     uattr.is_kernel);
	if (ret)
		goto err_prep;

	bpf_get_btf_vmlinux();

	/* Serialize verification of unprivileged programs. */
	if (!is_priv)
		mutex_lock(&bpf_verifier_lock);

	len = env->insn_aux_data_len = env->prog->len;
	env->insn_aux_data =
		__vmalloc(array_size(sizeof(struct bpf_insn_aux_data), len),
			  GFP_KERNEL_ACCOUNT | __GFP_ZERO);
	ret = -ENOMEM;
	if (!env->insn_aux_data)
		goto skip_full_check;
	for (i = 0; i < len; i++)
		env->insn_aux_data[i].orig_idx = i;
	env->succ = bpf_iarray_realloc(NULL, 2);
	if (!env->succ)
		goto skip_full_check;

	mark_verifier_state_clean(env);

	if (IS_ERR(btf_vmlinux)) {
		/* Either gcc or pahole or kernel are broken. */
		verbose(env, "in-kernel BTF is malformed\n");
		ret = PTR_ERR(btf_vmlinux);
		goto skip_full_check;
	}

	env->strict_alignment = !!(attr->prog_flags & BPF_F_STRICT_ALIGNMENT);
	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
		env->strict_alignment = true;
	if (attr->prog_flags & BPF_F_ANY_ALIGNMENT)
		env->strict_alignment = false;

	if (is_priv)
		env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ;
	env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS;
	env->arena_scalar = attr->prog_flags & BPF_F_ARENA_SCALAR;

	env->explored_states = kvzalloc_objs(struct list_head,
					     state_htab_size(env),
					     GFP_KERNEL_ACCOUNT);
	ret = -ENOMEM;
	if (!env->explored_states)
		goto skip_full_check;

	for (i = 0; i < state_htab_size(env); i++)
		INIT_LIST_HEAD(&env->explored_states[i]);
	INIT_LIST_HEAD(&env->free_list);

	/* Prepare BTF and func_info needed to discover all subprograms. */
	ret = bpf_prepare_btf_info(env, attr, uattr);
	if (ret < 0)
		goto skip_full_check;

	/* Apply CO-RE before validating the program's instruction layout. */
	ret = bpf_check_core_relo(env, attr, uattr);
	if (ret < 0)
		goto skip_full_check;

	/* Discover all subprograms and collect the properties needed by BTF validation. */
	ret = add_subprogs(env);
	if (ret < 0)
		goto skip_full_check;

	find_subprog_properties(env);

	/* Validate BTF before reporting subprogram layout errors. */
	ret = bpf_check_btf_info(env, attr, uattr);
	if (ret < 0)
		goto skip_full_check;

	ret = check_subprogs(env);
	if (ret < 0)
		goto skip_full_check;

	/* Validate instructions and resolve the program's referenced resources. */
	ret = check_and_resolve_insns(env);
	if (ret < 0)
		goto skip_full_check;

	/* Find pointers to functions in the read-only maps of the program. */
	ret = resolve_func_ptrs(env);
	if (ret < 0)
		goto skip_full_check;

	/* Build kfunc prototypes after resolving program resources. */
	ret = add_kfuncs(env);
	if (ret < 0)
		goto skip_full_check;

	if (bpf_prog_is_offloaded(env->prog->aux)) {
		ret = bpf_prog_offload_verifier_prep(env->prog);
		if (ret)
			goto skip_full_check;
	}

	ret = bpf_check_cfg(env);
	if (ret < 0)
		goto skip_full_check;

	ret = check_unwind_insns(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_compute_postorder(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_stack_liveness_init(env);
	if (ret)
		goto skip_full_check;

	ret = check_attach_btf_id(env);
	if (ret)
		goto skip_full_check;

	ret = bpf_compute_const_regs(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_prune_dead_branches(env);
	if (ret < 0)
		goto skip_full_check;

	ret = sort_subprogs_topo(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_compute_scc(env);
	if (ret < 0)
		goto skip_full_check;

	/* must precede the first bpf_ret_reg_pair() user below */
	ret = bpf_compute_subprog_ret_regs(env);
	if (ret < 0)
		goto skip_full_check;

	prepare_subprog_args(env);

	ret = bpf_compute_idoms(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_compute_loops(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_compute_live_registers(env);
	if (ret < 0)
		goto skip_full_check;

	if (env->log.level & BPF_LOG_LEVEL2)
		log_program(env);

	ret = bpf_init_scev(env);
	if (ret < 0)
		goto skip_full_check;

	ret = bpf_compute_scev(env);
	if (ret < 0)
		goto skip_full_check;

	bpf_free_subprog_jts(env);

	ret = mark_fastcall_patterns(env);
	if (ret < 0)
		goto skip_full_check;

	ret = do_check_main(env);
	ret = ret ?: do_check_subprogs(env);

	/* reject recursion through the callx edges found by the main pass */
	if (ret == 0 && env->callx_edges)
		ret = sort_subprogs_topo(env);

	if (ret == 0 && bpf_prog_is_offloaded(env->prog->aux))
		ret = bpf_prog_offload_finalize(env);

skip_full_check:
	kvfree(env->explored_states);

	/* might decrease stack depth, keep it before passes that
	 * allocate additional slots.
	 */
	if (ret == 0)
		ret = bpf_remove_fastcall_spills_fills(env);

	if (ret == 0)
		ret = check_max_stack_depth(env);

	/* instruction rewrites happen after this point */
	if (ret == 0)
		ret = bpf_optimize_bpf_loop(env);

	if (is_priv) {
		if (ret == 0)
			bpf_opt_hard_wire_dead_code_branches(env);
		if (ret == 0)
			ret = bpf_opt_remove_dead_code(env);
		if (ret == 0)
			ret = bpf_opt_remove_nops(env);
	} else {
		if (ret == 0)
			sanitize_dead_code(env);
	}

	if (ret == 0)
		/* program is valid, convert *(u32*)(ctx + off) accesses */
		ret = bpf_convert_ctx_accesses(env);

	if (ret == 0)
		ret = bpf_do_misc_fixups(env);

	/* do 32-bit optimization after insn patching has done so those patched
	 * insns could be handled correctly.
	 */
	if (ret == 0 && !bpf_prog_is_offloaded(env->prog->aux)) {
		ret = bpf_opt_subreg_zext_lo32_rnd_hi32(env, attr);
		env->prog->aux->verifier_zext = bpf_jit_needs_zext() ? !ret
								     : false;
	}

	if (ret == 0)
		ret = bpf_fixup_call_args(env);

	env->verification_time = ktime_get_ns() - start_time;
	print_verification_stats(env);
	env->prog->aux->verified_insns = env->insn_processed;

	/* preserve original error even if log finalization is successful */
	err = bpf_log_attr_finalize(attr_log, &env->log);
	if (err)
		ret = err;

	if (ret)
		goto err_release_maps;

	if (env->used_map_cnt) {
		/* if program passed verifier, update used_maps in bpf_prog_info */
		env->prog->aux->used_maps = kmalloc_objs(env->used_maps[0],
							 env->used_map_cnt,
							 GFP_KERNEL_ACCOUNT);

		if (!env->prog->aux->used_maps) {
			ret = -ENOMEM;
			goto err_release_maps;
		}

		memcpy(env->prog->aux->used_maps, env->used_maps,
		       sizeof(env->used_maps[0]) * env->used_map_cnt);
		env->prog->aux->used_map_cnt = env->used_map_cnt;
	}
	if (env->used_btf_cnt) {
		/* if program passed verifier, update used_btfs in bpf_prog_aux */
		env->prog->aux->used_btfs = kmalloc_objs(env->used_btfs[0],
							 env->used_btf_cnt,
							 GFP_KERNEL_ACCOUNT);
		if (!env->prog->aux->used_btfs) {
			ret = -ENOMEM;
			goto err_release_maps;
		}

		memcpy(env->prog->aux->used_btfs, env->used_btfs,
		       sizeof(env->used_btfs[0]) * env->used_btf_cnt);
		env->prog->aux->used_btf_cnt = env->used_btf_cnt;
	}
	if (env->used_map_cnt || env->used_btf_cnt) {
		/* program is valid. Convert pseudo bpf_ld_imm64 into generic
		 * bpf_ld_imm64 instructions
		 */
		convert_pseudo_ld_imm64(env);
	}

	adjust_btf_func(env);

	/* extension progs temporarily inherit the attach_type of their targets
	   for verification purposes, so set it back to zero before returning
	 */
	if (env->prog->type == BPF_PROG_TYPE_EXT)
		env->prog->expected_attach_type = 0;

	env->prog = __bpf_prog_select_runtime(env, env->prog, &ret);

err_release_maps:
	if (ret)
		release_insn_arrays(env);
	if (!env->prog->aux->used_maps)
		/* if we didn't copy map pointers into bpf_prog_info, release
		 * them now. Otherwise free_used_maps() will release them.
		 */
		release_maps(env);
	if (!env->prog->aux->used_btfs)
		release_btfs(env);

	*prog = env->prog;

	module_put(env->attach_btf_mod);
	if (!is_priv)
		mutex_unlock(&bpf_verifier_lock);
	goto err_free_env;
err_prep:
	err = bpf_log_attr_finalize(attr_log, &env->log);
	if (err)
		ret = err;
	release_insn_arrays(env);
	release_maps(env);
	release_btfs(env);
err_free_env:
	bpf_free_subprog_jts(env);
	if (env->insn_aux_data)
		bpf_clear_insn_aux_data(env, 0, env->insn_aux_data_len);
	vfree(env->insn_aux_data);
	kvfree(env->fd_array);
	bpf_free_scev(env);
	bpf_stack_liveness_free(env);
	kvfree(env->cfg.postorder_nums);
	kvfree(env->cfg.insn_postorder);
	kvfree(env->scc_info);
	kvfree(env->succ);
	kvfree(env->gotox_tmp_buf);
	kvfree(env->callx_edges);
	kvfree(env->func_ptrs);
	bpf_diag_free(env);
	kvfree(env->idoms);
	kvfree(env);
	return ret;
}