1 files changed, 297 insertions, 76 deletions

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index de006552be8a..f0dca726ebfd 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -612,6 +612,20 @@ static const char *kernel_type_name(const struct btf* btf, u32 id)
 	return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off);
 }
 
+/* The reg state of a pointer or a bounded scalar was saved when
+ * it was spilled to the stack.
+ */
+static bool is_spilled_reg(const struct bpf_stack_state *stack)
+{
+	return stack->slot_type[BPF_REG_SIZE - 1] == STACK_SPILL;
+}
+
+static void scrub_spilled_slot(u8 *stype)
+{
+	if (*stype != STACK_INVALID)
+		*stype = STACK_MISC;
+}
+
 static void print_verifier_state(struct bpf_verifier_env *env,
 				 const struct bpf_func_state *state)
 {
@@ -717,7 +731,7 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 			continue;
 		verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
 		print_liveness(env, state->stack[i].spilled_ptr.live);
-		if (state->stack[i].slot_type[0] == STACK_SPILL) {
+		if (is_spilled_reg(&state->stack[i])) {
 			reg = &state->stack[i].spilled_ptr;
 			t = reg->type;
 			verbose(env, "=%s", reg_type_str[t]);
@@ -1406,12 +1420,12 @@ static void __reg_combine_32_into_64(struct bpf_reg_state *reg)
 
 static bool __reg64_bound_s32(s64 a)
 {
-	return a > S32_MIN && a < S32_MAX;
+	return a >= S32_MIN && a <= S32_MAX;
 }
 
 static bool __reg64_bound_u32(u64 a)
 {
-	return a > U32_MIN && a < U32_MAX;
+	return a >= U32_MIN && a <= U32_MAX;
 }
 
 static void __reg_combine_64_into_32(struct bpf_reg_state *reg)
@@ -1626,52 +1640,168 @@ static int add_subprog(struct bpf_verifier_env *env, int off)
 	return env->subprog_cnt - 1;
 }
 
+#define MAX_KFUNC_DESCS 256
+#define MAX_KFUNC_BTFS	256
+
 struct bpf_kfunc_desc {
 	struct btf_func_model func_model;
 	u32 func_id;
 	s32 imm;
+	u16 offset;
+};
+
+struct bpf_kfunc_btf {
+	struct btf *btf;
+	struct module *module;
+	u16 offset;
 };
 
-#define MAX_KFUNC_DESCS 256
 struct bpf_kfunc_desc_tab {
 	struct bpf_kfunc_desc descs[MAX_KFUNC_DESCS];
 	u32 nr_descs;
 };
 
-static int kfunc_desc_cmp_by_id(const void *a, const void *b)
+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;
+	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 const struct bpf_kfunc_desc *
-find_kfunc_desc(const struct bpf_prog *prog, u32 func_id)
+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_descs,
-		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id);
+		       sizeof(tab->descs[0]), kfunc_desc_cmp_by_id_off);
+}
+
+static struct btf *__find_kfunc_desc_btf(struct bpf_verifier_env *env,
+					 s16 offset, struct module **btf_modp)
+{
+	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;
+	int btf_fd;
+
+	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);
+		}
+
+		if (bpfptr_is_null(env->fd_array)) {
+			verbose(env, "kfunc offset > 0 without fd_array is invalid\n");
+			return ERR_PTR(-EPROTO);
+		}
+
+		if (copy_from_bpfptr_offset(&btf_fd, env->fd_array,
+					    offset * 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;
+		}
+
+		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(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
+		     kfunc_btf_cmp_by_off, NULL);
+	}
+	if (btf_modp)
+		*btf_modp = b->module;
+	return b->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,
+				       u32 func_id, s16 offset,
+				       struct module **btf_modp)
+{
+	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, btf_modp);
+	}
+	return btf_vmlinux ?: ERR_PTR(-ENOENT);
 }
 
-static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
+static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id, s16 offset)
 {
 	const struct btf_type *func, *func_proto;
+	struct bpf_kfunc_btf_tab *btf_tab;
 	struct bpf_kfunc_desc_tab *tab;
 	struct bpf_prog_aux *prog_aux;
 	struct bpf_kfunc_desc *desc;
 	const char *func_name;
+	struct btf *desc_btf;
 	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");
@@ -1699,7 +1829,29 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 		prog_aux->kfunc_tab = tab;
 	}
 
-	if (find_kfunc_desc(env->prog, func_id))
+	/* 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(sizeof(*btf_tab), GFP_KERNEL);
+		if (!btf_tab)
+			return -ENOMEM;
+		prog_aux->kfunc_btf_tab = btf_tab;
+	}
+
+	desc_btf = find_kfunc_desc_btf(env, func_id, offset, NULL);
+	if (IS_ERR(desc_btf)) {
+		verbose(env, "failed to find BTF for kernel function\n");
+		return PTR_ERR(desc_btf);
+	}
+
+	if (find_kfunc_desc(env->prog, func_id, offset))
 		return 0;
 
 	if (tab->nr_descs == MAX_KFUNC_DESCS) {
@@ -1707,20 +1859,20 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 		return -E2BIG;
 	}
 
-	func = btf_type_by_id(btf_vmlinux, func_id);
+	func = btf_type_by_id(desc_btf, func_id);
 	if (!func || !btf_type_is_func(func)) {
 		verbose(env, "kernel btf_id %u is not a function\n",
 			func_id);
 		return -EINVAL;
 	}
-	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+	func_proto = btf_type_by_id(desc_btf, func->type);
 	if (!func_proto || !btf_type_is_func_proto(func_proto)) {
 		verbose(env, "kernel function btf_id %u does not have a valid func_proto\n",
 			func_id);
 		return -EINVAL;
 	}
 
-	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
+	func_name = btf_name_by_offset(desc_btf, func->name_off);
 	addr = kallsyms_lookup_name(func_name);
 	if (!addr) {
 		verbose(env, "cannot find address for kernel function %s\n",
@@ -1730,13 +1882,14 @@ static int add_kfunc_call(struct bpf_verifier_env *env, u32 func_id)
 
 	desc = &tab->descs[tab->nr_descs++];
 	desc->func_id = func_id;
-	desc->imm = BPF_CAST_CALL(addr) - __bpf_call_base;
-	err = btf_distill_func_proto(&env->log, btf_vmlinux,
+	desc->imm = BPF_CALL_IMM(addr);
+	desc->offset = offset;
+	err = btf_distill_func_proto(&env->log, desc_btf,
 				     func_proto, func_name,
 				     &desc->func_model);
 	if (!err)
 		sort(tab->descs, tab->nr_descs, sizeof(tab->descs[0]),
-		     kfunc_desc_cmp_by_id, NULL);
+		     kfunc_desc_cmp_by_id_off, NULL);
 	return err;
 }
 
@@ -1815,7 +1968,7 @@ static int add_subprog_and_kfunc(struct bpf_verifier_env *env)
 		} else if (bpf_pseudo_call(insn)) {
 			ret = add_subprog(env, i + insn->imm + 1);
 		} else {
-			ret = add_kfunc_call(env, insn->imm);
+			ret = add_kfunc_call(env, insn->imm, insn->off);
 		}
 
 		if (ret < 0)
@@ -2152,12 +2305,17 @@ static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
 static const char *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;
 
-	func = btf_type_by_id(btf_vmlinux, insn->imm);
-	return btf_name_by_offset(btf_vmlinux, func->name_off);
+	desc_btf = find_kfunc_desc_btf(data, insn->imm, insn->off, NULL);
+	if (IS_ERR(desc_btf))
+		return "<error>";
+
+	func = btf_type_by_id(desc_btf, insn->imm);
+	return btf_name_by_offset(desc_btf, func->name_off);
 }
 
 /* For given verifier state backtrack_insn() is called from the last insn to
@@ -2373,7 +2531,7 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env,
 				reg->precise = true;
 			}
 			for (j = 0; j < func->allocated_stack / BPF_REG_SIZE; j++) {
-				if (func->stack[j].slot_type[0] != STACK_SPILL)
+				if (!is_spilled_reg(&func->stack[j]))
 					continue;
 				reg = &func->stack[j].spilled_ptr;
 				if (reg->type != SCALAR_VALUE)
@@ -2415,7 +2573,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 	}
 
 	while (spi >= 0) {
-		if (func->stack[spi].slot_type[0] != STACK_SPILL) {
+		if (!is_spilled_reg(&func->stack[spi])) {
 			stack_mask = 0;
 			break;
 		}
@@ -2514,7 +2672,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno,
 				return 0;
 			}
 
-			if (func->stack[i].slot_type[0] != STACK_SPILL) {
+			if (!is_spilled_reg(&func->stack[i])) {
 				stack_mask &= ~(1ull << i);
 				continue;
 			}
@@ -2626,15 +2784,21 @@ static bool __is_pointer_value(bool allow_ptr_leaks,
 }
 
 static void save_register_state(struct bpf_func_state *state,
-				int spi, struct bpf_reg_state *reg)
+				int spi, struct bpf_reg_state *reg,
+				int size)
 {
 	int i;
 
 	state->stack[spi].spilled_ptr = *reg;
-	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+	if (size == BPF_REG_SIZE)
+		state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+
+	for (i = BPF_REG_SIZE; i > BPF_REG_SIZE - size; i--)
+		state->stack[spi].slot_type[i - 1] = STACK_SPILL;
 
-	for (i = 0; i < BPF_REG_SIZE; i++)
-		state->stack[spi].slot_type[i] = STACK_SPILL;
+	/* size < 8 bytes spill */
+	for (; i; i--)
+		scrub_spilled_slot(&state->stack[spi].slot_type[i - 1]);
 }
 
 /* check_stack_{read,write}_fixed_off functions track spill/fill of registers,
@@ -2681,7 +2845,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
 	}
 
-	if (reg && size == BPF_REG_SIZE && register_is_bounded(reg) &&
+	if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) &&
 	    !register_is_null(reg) && env->bpf_capable) {
 		if (dst_reg != BPF_REG_FP) {
 			/* The backtracking logic can only recognize explicit
@@ -2694,7 +2858,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			if (err)
 				return err;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else if (reg && is_spillable_regtype(reg->type)) {
 		/* register containing pointer is being spilled into stack */
 		if (size != BPF_REG_SIZE) {
@@ -2706,16 +2870,16 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
 			return -EINVAL;
 		}
-		save_register_state(state, spi, reg);
+		save_register_state(state, spi, reg, size);
 	} else {
 		u8 type = STACK_MISC;
 
 		/* regular write of data into stack destroys any spilled ptr */
 		state->stack[spi].spilled_ptr.type = NOT_INIT;
 		/* Mark slots as STACK_MISC if they belonged to spilled ptr. */
-		if (state->stack[spi].slot_type[0] == STACK_SPILL)
+		if (is_spilled_reg(&state->stack[spi]))
 			for (i = 0; i < BPF_REG_SIZE; i++)
-				state->stack[spi].slot_type[i] = STACK_MISC;
+				scrub_spilled_slot(&state->stack[spi].slot_type[i]);
 
 		/* only mark the slot as written if all 8 bytes were written
 		 * otherwise read propagation may incorrectly stop too soon
@@ -2918,23 +3082,50 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
 	int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
 	struct bpf_reg_state *reg;
-	u8 *stype;
+	u8 *stype, type;
 
 	stype = reg_state->stack[spi].slot_type;
 	reg = &reg_state->stack[spi].spilled_ptr;
 
-	if (stype[0] == STACK_SPILL) {
+	if (is_spilled_reg(&reg_state->stack[spi])) {
 		if (size != BPF_REG_SIZE) {
+			u8 scalar_size = 0;
+
 			if (reg->type != SCALAR_VALUE) {
 				verbose_linfo(env, env->insn_idx, "; ");
 				verbose(env, "invalid size of register fill\n");
 				return -EACCES;
 			}
-			if (dst_regno >= 0) {
+
+			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			if (dst_regno < 0)
+				return 0;
+
+			for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--)
+				scalar_size++;
+
+			if (!(off % BPF_REG_SIZE) && size == scalar_size) {
+				/* The earlier check_reg_arg() has decided the
+				 * subreg_def for this insn.  Save it first.
+				 */
+				s32 subreg_def = state->regs[dst_regno].subreg_def;
+
+				state->regs[dst_regno] = *reg;
+				state->regs[dst_regno].subreg_def = subreg_def;
+			} else {
+				for (i = 0; i < size; i++) {
+					type = stype[(slot - i) % BPF_REG_SIZE];
+					if (type == STACK_SPILL)
+						continue;
+					if (type == STACK_MISC)
+						continue;
+					verbose(env, "invalid read from stack off %d+%d size %d\n",
+						off, i, size);
+					return -EACCES;
+				}
 				mark_reg_unknown(env, state->regs, dst_regno);
-				state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			}
-			mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
+			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			return 0;
 		}
 		for (i = 1; i < BPF_REG_SIZE; i++) {
@@ -2965,8 +3156,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		}
 		mark_reg_read(env, reg, reg->parent, REG_LIVE_READ64);
 	} else {
-		u8 type;
-
 		for (i = 0; i < size; i++) {
 			type = stype[(slot - i) % BPF_REG_SIZE];
 			if (type == STACK_MISC)
@@ -4514,17 +4703,17 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
 			goto mark;
 
-		if (state->stack[spi].slot_type[0] == STACK_SPILL &&
+		if (is_spilled_reg(&state->stack[spi]) &&
 		    (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
 		     env->allow_ptr_leaks)) {
 			if (clobber) {
 				__mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
 				for (j = 0; j < BPF_REG_SIZE; j++)
-					state->stack[spi].slot_type[j] = STACK_MISC;
+					scrub_spilled_slot(&state->stack[spi].slot_type[j]);
 			}
 			goto mark;
 		}
@@ -4813,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env,
 			return -EINVAL;
 		}
 		break;
-
+	case BPF_MAP_TYPE_BLOOM_FILTER:
+		if (meta->func_id == BPF_FUNC_map_peek_elem)
+			*arg_type = ARG_PTR_TO_MAP_VALUE;
+		break;
 	default:
 		break;
 	}
@@ -5388,6 +5580,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_task_storage_delete)
 			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;
 	default:
 		break;
 	}
@@ -5455,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
-	case BPF_FUNC_map_peek_elem:
 	case BPF_FUNC_map_pop_elem:
-	case BPF_FUNC_map_push_elem:
 		if (map->map_type != BPF_MAP_TYPE_QUEUE &&
 		    map->map_type != BPF_MAP_TYPE_STACK)
 			goto error;
 		break;
+	case BPF_FUNC_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_sk_storage_get:
 	case BPF_FUNC_sk_storage_delete:
 		if (map->map_type != BPF_MAP_TYPE_SK_STORAGE)
@@ -6485,23 +6687,33 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	struct bpf_reg_state *regs = cur_regs(env);
 	const char *func_name, *ptr_type_name;
 	u32 i, nargs, func_id, ptr_type_id;
+	struct module *btf_mod = NULL;
 	const struct btf_param *args;
+	struct btf *desc_btf;
 	int err;
 
+	/* skip for now, but return error when we find this in fixup_kfunc_call */
+	if (!insn->imm)
+		return 0;
+
+	desc_btf = find_kfunc_desc_btf(env, insn->imm, insn->off, &btf_mod);
+	if (IS_ERR(desc_btf))
+		return PTR_ERR(desc_btf);
+
 	func_id = insn->imm;
-	func = btf_type_by_id(btf_vmlinux, func_id);
-	func_name = btf_name_by_offset(btf_vmlinux, func->name_off);
-	func_proto = btf_type_by_id(btf_vmlinux, func->type);
+	func = btf_type_by_id(desc_btf, func_id);
+	func_name = btf_name_by_offset(desc_btf, func->name_off);
+	func_proto = btf_type_by_id(desc_btf, func->type);
 
 	if (!env->ops->check_kfunc_call ||
-	    !env->ops->check_kfunc_call(func_id)) {
+	    !env->ops->check_kfunc_call(func_id, btf_mod)) {
 		verbose(env, "calling kernel function %s is not allowed\n",
 			func_name);
 		return -EACCES;
 	}
 
 	/* Check the arguments */
-	err = btf_check_kfunc_arg_match(env, btf_vmlinux, func_id, regs);
+	err = btf_check_kfunc_arg_match(env, desc_btf, func_id, regs);
 	if (err)
 		return err;
 
@@ -6509,15 +6721,15 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		mark_reg_not_init(env, regs, caller_saved[i]);
 
 	/* Check return type */
-	t = btf_type_skip_modifiers(btf_vmlinux, func_proto->type, NULL);
+	t = btf_type_skip_modifiers(desc_btf, func_proto->type, NULL);
 	if (btf_type_is_scalar(t)) {
 		mark_reg_unknown(env, regs, BPF_REG_0);
 		mark_btf_func_reg_size(env, BPF_REG_0, t->size);
 	} else if (btf_type_is_ptr(t)) {
-		ptr_type = btf_type_skip_modifiers(btf_vmlinux, t->type,
+		ptr_type = btf_type_skip_modifiers(desc_btf, t->type,
 						   &ptr_type_id);
 		if (!btf_type_is_struct(ptr_type)) {
-			ptr_type_name = btf_name_by_offset(btf_vmlinux,
+			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),
@@ -6525,7 +6737,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			return -EINVAL;
 		}
 		mark_reg_known_zero(env, regs, BPF_REG_0);
-		regs[BPF_REG_0].btf = btf_vmlinux;
+		regs[BPF_REG_0].btf = desc_btf;
 		regs[BPF_REG_0].type = PTR_TO_BTF_ID;
 		regs[BPF_REG_0].btf_id = ptr_type_id;
 		mark_btf_func_reg_size(env, BPF_REG_0, sizeof(void *));
@@ -6536,7 +6748,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn)
 	for (i = 0; i < nargs; i++) {
 		u32 regno = i + 1;
 
-		t = btf_type_skip_modifiers(btf_vmlinux, args[i].type, NULL);
+		t = btf_type_skip_modifiers(desc_btf, args[i].type, NULL);
 		if (btf_type_is_ptr(t))
 			mark_btf_func_reg_size(env, regno, sizeof(void *));
 		else
@@ -10356,9 +10568,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
 			 * return false to continue verification of this path
 			 */
 			return false;
-		if (i % BPF_REG_SIZE)
+		if (i % BPF_REG_SIZE != BPF_REG_SIZE - 1)
 			continue;
-		if (old->stack[spi].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&old->stack[spi]))
 			continue;
 		if (!regsafe(env, &old->stack[spi].spilled_ptr,
 			     &cur->stack[spi].spilled_ptr, idmap))
@@ -10565,7 +10777,7 @@ static int propagate_precision(struct bpf_verifier_env *env,
 	}
 
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		if (state->stack[i].slot_type[0] != STACK_SPILL)
+		if (!is_spilled_reg(&state->stack[i]))
 			continue;
 		state_reg = &state->stack[i].spilled_ptr;
 		if (state_reg->type != SCALAR_VALUE ||
@@ -11076,7 +11288,8 @@ static int do_check(struct bpf_verifier_env *env)
 			env->jmps_processed++;
 			if (opcode == BPF_CALL) {
 				if (BPF_SRC(insn->code) != BPF_K ||
-				    insn->off != 0 ||
+				    (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) ||
@@ -12432,6 +12645,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 		func[i]->aux->stack_depth = env->subprog_info[i].stack_depth;
 		func[i]->jit_requested = 1;
 		func[i]->aux->kfunc_tab = prog->aux->kfunc_tab;
+		func[i]->aux->kfunc_btf_tab = prog->aux->kfunc_btf_tab;
 		func[i]->aux->linfo = prog->aux->linfo;
 		func[i]->aux->nr_linfo = prog->aux->nr_linfo;
 		func[i]->aux->jited_linfo = prog->aux->jited_linfo;
@@ -12469,8 +12683,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 			if (!bpf_pseudo_call(insn))
 				continue;
 			subprog = insn->off;
-			insn->imm = BPF_CAST_CALL(func[subprog]->bpf_func) -
-				    __bpf_call_base;
+			insn->imm = BPF_CALL_IMM(func[subprog]->bpf_func);
 		}
 
 		/* we use the aux data to keep a list of the start addresses
@@ -12618,10 +12831,15 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env,
 {
 	const struct bpf_kfunc_desc *desc;
 
+	if (!insn->imm) {
+		verbose(env, "invalid kernel function call not eliminated in verifier pass\n");
+		return -EINVAL;
+	}
+
 	/* insn->imm has the btf func_id. Replace it with
 	 * an address (relative to __bpf_base_call).
 	 */
-	desc = find_kfunc_desc(env->prog, insn->imm);
+	desc = find_kfunc_desc(env->prog, insn->imm, insn->off);
 	if (!desc) {
 		verbose(env, "verifier internal error: kernel function descriptor not found for func_id %u\n",
 			insn->imm);
@@ -12902,7 +13120,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 		     insn->imm == BPF_FUNC_map_push_elem   ||
 		     insn->imm == BPF_FUNC_map_pop_elem    ||
 		     insn->imm == BPF_FUNC_map_peek_elem   ||
-		     insn->imm == BPF_FUNC_redirect_map)) {
+		     insn->imm == BPF_FUNC_redirect_map    ||
+		     insn->imm == BPF_FUNC_for_each_map_elem)) {
 			aux = &env->insn_aux_data[i + delta];
 			if (bpf_map_ptr_poisoned(aux))
 				goto patch_call_imm;
@@ -12946,36 +13165,37 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 				     (int (*)(struct bpf_map *map, void *value))NULL));
 			BUILD_BUG_ON(!__same_type(ops->map_redirect,
 				     (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL));
+			BUILD_BUG_ON(!__same_type(ops->map_for_each_callback,
+				     (int (*)(struct bpf_map *map,
+					      bpf_callback_t callback_fn,
+					      void *callback_ctx,
+					      u64 flags))NULL));
 
 patch_map_ops_generic:
 			switch (insn->imm) {
 			case BPF_FUNC_map_lookup_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_lookup_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_lookup_elem);
 				continue;
 			case BPF_FUNC_map_update_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_update_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_update_elem);
 				continue;
 			case BPF_FUNC_map_delete_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_delete_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_delete_elem);
 				continue;
 			case BPF_FUNC_map_push_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_push_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_push_elem);
 				continue;
 			case BPF_FUNC_map_pop_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_pop_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_pop_elem);
 				continue;
 			case BPF_FUNC_map_peek_elem:
-				insn->imm = BPF_CAST_CALL(ops->map_peek_elem) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_peek_elem);
 				continue;
 			case BPF_FUNC_redirect_map:
-				insn->imm = BPF_CAST_CALL(ops->map_redirect) -
-					    __bpf_call_base;
+				insn->imm = BPF_CALL_IMM(ops->map_redirect);
+				continue;
+			case BPF_FUNC_for_each_map_elem:
+				insn->imm = BPF_CALL_IMM(ops->map_for_each_callback);
 				continue;
 			}
 
@@ -13826,6 +14046,7 @@ skip_full_check:
 
 	env->verification_time = ktime_get_ns() - start_time;
 	print_verification_stats(env);
+	env->prog->aux->verified_insns = env->insn_processed;
 
 	if (log->level && bpf_verifier_log_full(log))
 		ret = -ENOSPC;