diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3ec338169981..6f12fc40b682 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -443,6 +443,8 @@ enum {
 
 	INSN_F_DST_REG_STACK = BIT(1), /* dst_reg is PTR_TO_STACK */
 	INSN_F_SRC_REG_STACK = BIT(2), /* src_reg is PTR_TO_STACK */
+
+	INSN_F_STACK_ARG_ACCESS = BIT(3),
 };
 
 struct bpf_jmp_history_entry {
@@ -858,6 +860,7 @@ struct backtrack_state {
 	u32 frame;
 	u32 reg_masks[MAX_CALL_FRAMES];
 	u64 stack_masks[MAX_CALL_FRAMES];
+	u8 stack_arg_masks[MAX_CALL_FRAMES];
 };
 
 struct bpf_id_pair {
@@ -1256,6 +1259,11 @@ static inline void bpf_bt_set_frame_slot(struct backtrack_state *bt, u32 frame,
 	bt->stack_masks[frame] |= 1ull << slot;
 }
 
+static inline void bt_set_frame_stack_arg_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	bt->stack_arg_masks[frame] |= 1 << slot;
+}
+
 static inline bool bt_is_frame_reg_set(struct backtrack_state *bt, u32 frame, u32 reg)
 {
 	return bt->reg_masks[frame] & (1 << reg);
diff --git a/kernel/bpf/backtrack.c b/kernel/bpf/backtrack.c
index 5e93e57fb7ae..2e4ae0ef0860 100644
--- a/kernel/bpf/backtrack.c
+++ b/kernel/bpf/backtrack.c
@@ -129,11 +129,21 @@ static inline u32 bt_empty(struct backtrack_state *bt)
 	int i;
 
 	for (i = 0; i <= bt->frame; i++)
-		mask |= bt->reg_masks[i] | bt->stack_masks[i];
+		mask |= bt->reg_masks[i] | bt->stack_masks[i] | bt->stack_arg_masks[i];
 
 	return mask == 0;
 }
 
+static inline void bt_clear_frame_stack_arg_slot(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	bt->stack_arg_masks[frame] &= ~(1 << slot);
+}
+
+static inline bool bt_is_frame_stack_arg_slot_set(struct backtrack_state *bt, u32 frame, u32 slot)
+{
+	return bt->stack_arg_masks[frame] & (1 << slot);
+}
+
 static inline int bt_subprog_enter(struct backtrack_state *bt)
 {
 	if (bt->frame == MAX_CALL_FRAMES - 1) {
@@ -194,6 +204,11 @@ static inline u64 bt_stack_mask(struct backtrack_state *bt)
 	return bt->stack_masks[bt->frame];
 }
 
+static inline u8 bt_stack_arg_mask(struct backtrack_state *bt)
+{
+	return bt->stack_arg_masks[bt->frame];
+}
+
 static inline bool bt_is_reg_set(struct backtrack_state *bt, u32 reg)
 {
 	return bt->reg_masks[bt->frame] & (1 << reg);
@@ -335,6 +350,19 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			return 0;
 		bt_clear_reg(bt, load_reg);
 
+		if (hist && hist->flags & INSN_F_STACK_ARG_ACCESS) {
+			spi = hist->spi;
+			/*
+			 * Stack arg read: callee reads from r11+off, but
+			 * the data lives in the caller's stack_arg_regs.
+			 * Set the mask in the caller frame so precision
+			 * is marked in the caller's slot at the callee
+			 * entry checkpoint.
+			 */
+			bt_set_frame_stack_arg_slot(bt, bt->frame - 1, spi);
+			return 0;
+		}
+
 		/* scalars can only be spilled into stack w/o losing precision.
 		 * Load from any other memory can be zero extended.
 		 * The desire to keep that precision is already indicated
@@ -357,6 +385,17 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 			 * encountered a case of pointer subtraction.
 			 */
 			return -ENOTSUPP;
+
+		if (hist && hist->flags & INSN_F_STACK_ARG_ACCESS) {
+			spi = hist->spi;
+			if (!bt_is_frame_stack_arg_slot_set(bt, bt->frame, spi))
+				return 0;
+			bt_clear_frame_stack_arg_slot(bt, bt->frame, spi);
+			if (class == BPF_STX)
+				bt_set_reg(bt, sreg);
+			return 0;
+		}
+
 		/* scalars can only be spilled into stack */
 		if (!hist || !(hist->flags & INSN_F_STACK_ACCESS))
 			return 0;
@@ -425,6 +464,12 @@ static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
 						bpf_bt_set_frame_reg(bt, bt->frame - 1, i);
 					}
 				}
+				if (bt_stack_arg_mask(bt)) {
+					verifier_bug(env,
+						     "static subprog leftover stack arg slots %x",
+						     bt_stack_arg_mask(bt));
+					return -EFAULT;
+				}
 				if (bt_subprog_exit(bt))
 					return -EFAULT;
 				return 0;
@@ -895,6 +940,17 @@ int bpf_mark_chain_precision(struct bpf_verifier_env *env,
 					*changed = true;
 				}
 			}
+			for (i = 0; i < func->out_stack_arg_cnt; i++) {
+				if (!bt_is_frame_stack_arg_slot_set(bt, fr, i))
+					continue;
+				reg = &func->stack_arg_regs[i];
+				if (reg->type != SCALAR_VALUE || reg->precise) {
+					bt_clear_frame_stack_arg_slot(bt, fr, i);
+				} else {
+					reg->precise = true;
+					*changed = true;
+				}
+			}
 			if (env->log.level & BPF_LOG_LEVEL2) {
 				fmt_reg_mask(env->tmp_str_buf, TMP_STR_BUF_LEN,
 					     bt_frame_reg_mask(bt, fr));
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d15aef2fe4a1..ebd13661933e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -292,6 +292,11 @@ static int arg_from_argno(argno_t a)
 	return -1;
 }
 
+static int arg_idx_from_argno(argno_t a)
+{
+	return arg_from_argno(a) - 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);
@@ -4115,7 +4120,8 @@ static int check_stack_arg_write(struct bpf_verifier_env *env, struct bpf_func_s
 		__mark_reg_known(arg, env->prog->insnsi[env->insn_idx].imm);
 	}
 	state->no_stack_arg_load = true;
-	return 0;
+	return bpf_push_jmp_history(env, env->cur_state,
+				    INSN_F_STACK_ARG_ACCESS, spi, 0, 0);
 }
 
 /*
@@ -4146,7 +4152,17 @@ static int check_stack_arg_read(struct bpf_verifier_env *env, struct bpf_func_st
 	arg = &caller->stack_arg_regs[spi];
 	cur = vstate->frame[vstate->curframe];
 	cur->regs[dst_regno] = *arg;
-	return 0;
+	return bpf_push_jmp_history(env, env->cur_state,
+				    INSN_F_STACK_ARG_ACCESS, spi, 0, 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 check_outgoing_stack_args(struct bpf_verifier_env *env, struct bpf_func_state *caller,
@@ -6875,8 +6891,14 @@ static int check_mem_size_reg(struct bpf_verifier_env *env,
 	}
 	err = check_helper_mem_access(env, mem_reg, mem_argno, reg_umax(size_reg),
 				      access_type, zero_size_allowed, meta);
-	if (!err)
-		err = mark_chain_precision(env, reg_from_argno(size_argno));
+	if (!err) {
+		int regno = reg_from_argno(size_argno);
+
+		if (regno >= 0)
+			err = mark_chain_precision(env, regno);
+		else
+			err = mark_stack_arg_precision(env, arg_idx_from_argno(size_argno));
+	}
 	return err;
 }
 
@@ -7325,7 +7347,7 @@ static int process_iter_arg(struct bpf_verifier_env *env, struct bpf_reg_state *
 			    struct bpf_kfunc_call_arg_meta *meta)
 {
 	const struct btf_type *t;
-	u32 arg_idx = arg_from_argno(argno) - 1;
+	u32 arg_idx = arg_idx_from_argno(argno);
 	int spi, err, i, nr_slots, btf_id;
 
 	if (reg->type != PTR_TO_STACK) {