diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 41ddba63082d7cb8afa2362161b419292c98b93e..5b7004b580353f23a2e064dc1975792961fc1d15 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -1477,6 +1477,12 @@ int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level,
 		ret = 1;
 	} else if (ctx.optlen > max_optlen || ctx.optlen < -1) {
 		/* optlen is out of bounds */
+		if (*optlen > PAGE_SIZE && ctx.optlen >= 0) {
+			pr_info_once("bpf setsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
+				     ctx.optlen, max_optlen);
+			ret = 0;
+			goto out;
+		}
 		ret = -EFAULT;
 	} else {
 		/* optlen within bounds, run kernel handler */
@@ -1532,6 +1538,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 		.optname = optname,
 		.retval = retval,
 	};
+	int orig_optlen;
 	int ret;
 
 	/* Opportunistic check to see whether we have any BPF program
@@ -1541,6 +1548,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	if (__cgroup_bpf_prog_array_is_empty(cgrp, CGROUP_GETSOCKOPT))
 		return retval;
 
+	orig_optlen = max_optlen;
 	ctx.optlen = max_optlen;
 
 	max_optlen = sockopt_alloc_buf(&ctx, max_optlen, &buf);
@@ -1564,6 +1572,7 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 			ret = -EFAULT;
 			goto out;
 		}
+		orig_optlen = ctx.optlen;
 
 		if (copy_from_user(ctx.optval, optval,
 				   min(ctx.optlen, max_optlen)) != 0) {
@@ -1583,6 +1592,12 @@ int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
 	}
 
 	if (optval && (ctx.optlen > max_optlen || ctx.optlen < 0)) {
+		if (orig_optlen > PAGE_SIZE && ctx.optlen >= 0) {
+			pr_info_once("bpf getsockopt: ignoring program buffer with optlen=%d (max_optlen=%d)\n",
+				     ctx.optlen, max_optlen);
+			ret = retval;
+			goto out;
+		}
 		ret = -EFAULT;
 		goto out;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4f60168ce1758fc93d1643319b6940396f049b60..386b5d6b564c65aa5f9dfca4ba86e44447e7f20f 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1281,9 +1281,9 @@ static void __reg_bound_offset(struct bpf_reg_state *reg)
 	struct tnum var64_off = tnum_intersect(reg->var_off,
 					       tnum_range(reg->umin_value,
 							  reg->umax_value));
-	struct tnum var32_off = tnum_intersect(tnum_subreg(reg->var_off),
-						tnum_range(reg->u32_min_value,
-							   reg->u32_max_value));
+	struct tnum var32_off = tnum_intersect(tnum_subreg(var64_off),
+					       tnum_range(reg->u32_min_value,
+							  reg->u32_max_value));
 
 	reg->var_off = tnum_or(tnum_clear_subreg(var64_off), var32_off);
 }
@@ -4333,10 +4333,6 @@ static int check_stack_range_initialized(
 			goto mark;
 		}
 
-		if (is_spilled_reg(&state->stack[spi]) &&
-		    state->stack[spi].spilled_ptr.type == PTR_TO_BTF_ID)
-			goto mark;
-
 		if (is_spilled_reg(&state->stack[spi]) &&
 		    (state->stack[spi].spilled_ptr.type == SCALAR_VALUE ||
 		     env->allow_ptr_leaks)) {
@@ -4366,6 +4362,11 @@ static int check_stack_range_initialized(
 		mark_reg_read(env, &state->stack[spi].spilled_ptr,
 			      state->stack[spi].spilled_ptr.parent,
 			      REG_LIVE_READ64);
+		/* We do not set REG_LIVE_WRITTEN for stack slot, as we can not
+		 * be sure that whether stack slot is written to or not. Hence,
+		 * we must still conservatively propagate reads upwards even if
+		 * helper may write to the entire memory range.
+		 */
 	}
 	return 0;
 }
@@ -5430,7 +5431,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 	/* Transfer references to the callee */
 	err = copy_reference_state(callee, caller);
 	if (err)
-		return err;
+		goto err_out;
 
 	/* copy r1 - r5 args that callee can access.  The copy includes parent
 	 * pointers, which connects us up to the liveness chain
@@ -5453,6 +5454,10 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		print_verifier_state(env, callee);
 	}
 	return 0;
+err_out:
+	free_func_state(callee);
+	state->frame[state->curframe + 1] = NULL;
+	return err;
 }
 
 static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
@@ -5475,8 +5480,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 		return -EINVAL;
 	}
 
-	state->curframe--;
-	caller = state->frame[state->curframe];
+	caller = state->frame[state->curframe - 1];
 	/* return to the caller whatever r0 had in the callee */
 	caller->regs[BPF_REG_0] = *r0;
 
@@ -5494,7 +5498,7 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
 	}
 	/* clear everything in the callee */
 	free_func_state(callee);
-	state->frame[state->curframe + 1] = NULL;
+	state->frame[state->curframe--] = NULL;
 	return 0;
 }
 
@@ -11539,9 +11543,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 	}
 
 	/* finally lock prog and jit images for all functions and
-	 * populate kallsysm
+	 * populate kallsysm. Begin at the first subprogram, since
+	 * bpf_prog_load will add the kallsyms for the main program.
 	 */
-	for (i = 0; i < env->subprog_cnt; i++) {
+	for (i = 1; i < env->subprog_cnt; i++) {
 		bpf_prog_lock_ro(func[i]);
 		bpf_prog_kallsyms_add(func[i]);
 	}
@@ -11561,6 +11566,8 @@ static int jit_subprogs(struct bpf_verifier_env *env)
 
 	prog->jited = 1;
 	prog->bpf_func = func[0]->bpf_func;
+	prog->aux->extable = func[0]->aux->extable;
+	prog->aux->num_exentries = func[0]->aux->num_exentries;
 	prog->aux->func = func;
 	prog->aux->func_cnt = env->subprog_cnt;
 	bpf_prog_free_unused_jited_linfo(prog);
diff --git a/tools/testing/selftests/bpf/prog_tests/align.c b/tools/testing/selftests/bpf/prog_tests/align.c
index 7996ec07e0bdb0cb6153f2d6bf619bc5a51d72c7..1d4b4f9b06eddece84383bdac019b6256e1f2897 100644
--- a/tools/testing/selftests/bpf/prog_tests/align.c
+++ b/tools/testing/selftests/bpf/prog_tests/align.c
@@ -575,14 +575,14 @@ static struct bpf_align_test tests[] = {
 			/* New unknown value in R7 is (4n), >= 76 */
 			{15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"},
 			/* Adding it to packet pointer gives nice bounds again */
-			{16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
+			{16, "R5_w=pkt(id=3,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc)"},
 			/* At the time the word size load is performed from R5,
 			 * its total fixed offset is NET_IP_ALIGN + reg->off (0)
 			 * which is 2.  Then the variable offset is (4n+2), so
 			 * the total offset is 4-byte aligned and meets the
 			 * load's requirements.
 			 */
-			{20, "R5=pkt(id=3,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0xfffffffc)"},
+			{20, "R5=pkt(id=3,off=0,r=4,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc)"},
 		},
 	},
 };