diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index d6349e930b06..b1fd000feb89 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -1362,7 +1362,7 @@ static void restore_regs(const struct btf_func_model *m, u8 **prog, int nr_args,
 }
 
 static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
-			   struct bpf_prog *p, int stack_size)
+			   struct bpf_prog *p, int stack_size, bool mod_ret)
 {
 	u8 *prog = *pprog;
 	int cnt = 0;
@@ -1383,6 +1383,13 @@ static int invoke_bpf_prog(const struct btf_func_model *m, u8 **pprog,
 	if (emit_call(&prog, p->bpf_func, prog))
 		return -EINVAL;
 
+	/* BPF_TRAMP_MODIFY_RETURN trampolines can modify the return
+	 * of the previous call which is then passed on the stack to
+	 * the next BPF program.
+	 */
+	if (mod_ret)
+		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+
 	/* arg1: mov rdi, progs[i] */
 	emit_mov_imm64(&prog, BPF_REG_1, (long) p >> 32,
 		       (u32) (long) p);
@@ -1442,6 +1449,23 @@ static int emit_cond_near_jump(u8 **pprog, void *func, void *ip, u8 jmp_cond)
 	return 0;
 }
 
+static int emit_mod_ret_check_imm8(u8 **pprog, int value)
+{
+	u8 *prog = *pprog;
+	int cnt = 0;
+
+	if (!is_imm8(value))
+		return -EINVAL;
+
+	if (value == 0)
+		EMIT2(0x85, add_2reg(0xC0, BPF_REG_0, BPF_REG_0));
+	else
+		EMIT3(0x83, add_1reg(0xF8, BPF_REG_0), value);
+
+	*pprog = prog;
+	return 0;
+}
+
 static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 		      struct bpf_tramp_progs *tp, int stack_size)
 {
@@ -1449,13 +1473,53 @@ static int invoke_bpf(const struct btf_func_model *m, u8 **pprog,
 	u8 *prog = *pprog;
 
 	for (i = 0; i < tp->nr_progs; i++) {
-		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size))
+		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, false))
 			return -EINVAL;
 	}
 	*pprog = prog;
 	return 0;
 }
 
+static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
+			      struct bpf_tramp_progs *tp, int stack_size,
+			      u8 **branches)
+{
+	u8 *prog = *pprog;
+	int i;
+
+	/* The first fmod_ret program will receive a garbage return value.
+	 * Set this to 0 to avoid confusing the program.
+	 */
+	emit_mov_imm32(&prog, false, BPF_REG_0, 0);
+	emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+	for (i = 0; i < tp->nr_progs; i++) {
+		if (invoke_bpf_prog(m, &prog, tp->progs[i], stack_size, true))
+			return -EINVAL;
+
+		/* Generate a branch:
+		 *
+		 * if (ret !=  0)
+		 *	goto do_fexit;
+		 *
+		 * If needed this can be extended to any integer value which can
+		 * be passed by user-space when the program is loaded.
+		 */
+		if (emit_mod_ret_check_imm8(&prog, 0))
+			return -EINVAL;
+
+		/* Save the location of the branch and Generate 6 nops
+		 * (4 bytes for an offset and 2 bytes for the jump) These nops
+		 * are replaced with a conditional jump once do_fexit (i.e. the
+		 * start of the fexit invocation) is finalized.
+		 */
+		branches[i] = prog;
+		emit_nops(&prog, 4 + 2);
+	}
+
+	*pprog = prog;
+	return 0;
+}
+
 /* Example:
  * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
  * its 'struct btf_func_model' will be nr_args=2
@@ -1521,10 +1585,12 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 				struct bpf_tramp_progs *tprogs,
 				void *orig_call)
 {
-	int cnt = 0, nr_args = m->nr_args;
+	int ret, i, cnt = 0, nr_args = m->nr_args;
 	int stack_size = nr_args * 8;
 	struct bpf_tramp_progs *fentry = &tprogs[BPF_TRAMP_FENTRY];
 	struct bpf_tramp_progs *fexit = &tprogs[BPF_TRAMP_FEXIT];
+	struct bpf_tramp_progs *fmod_ret = &tprogs[BPF_TRAMP_MODIFY_RETURN];
+	u8 **branches = NULL;
 	u8 *prog;
 
 	/* x86-64 supports up to 6 arguments. 7+ can be added in the future */
@@ -1557,24 +1623,60 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 		if (invoke_bpf(m, &prog, fentry, stack_size))
 			return -EINVAL;
 
+	if (fmod_ret->nr_progs) {
+		branches = kcalloc(fmod_ret->nr_progs, sizeof(u8 *),
+				   GFP_KERNEL);
+		if (!branches)
+			return -ENOMEM;
+
+		if (invoke_bpf_mod_ret(m, &prog, fmod_ret, stack_size,
+				       branches)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+	}
+
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		if (fentry->nr_progs)
+		if (fentry->nr_progs || fmod_ret->nr_progs)
 			restore_regs(m, &prog, nr_args, stack_size);
 
 		/* call original function */
-		if (emit_call(&prog, orig_call, prog))
-			return -EINVAL;
+		if (emit_call(&prog, orig_call, prog)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
 	}
 
+	if (fmod_ret->nr_progs) {
+		/* From Intel 64 and IA-32 Architectures Optimization
+		 * Reference Manual, 3.4.1.4 Code Alignment, Assembly/Compiler
+		 * Coding Rule 11: All branch targets should be 16-byte
+		 * aligned.
+		 */
+		emit_align(&prog, 16);
+		/* Update the branches saved in invoke_bpf_mod_ret with the
+		 * aligned address of do_fexit.
+		 */
+		for (i = 0; i < fmod_ret->nr_progs; i++)
+			emit_cond_near_jump(&branches[i], prog, branches[i],
+					    X86_JNE);
+	}
+
 	if (fexit->nr_progs)
-		if (invoke_bpf(m, &prog, fexit, stack_size))
-			return -EINVAL;
+		if (invoke_bpf(m, &prog, fexit, stack_size)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
 
 	if (flags & BPF_TRAMP_F_RESTORE_REGS)
 		restore_regs(m, &prog, nr_args, stack_size);
 
+	/* This needs to be done regardless. If there were fmod_ret programs,
+	 * the return value is only updated on the stack and still needs to be
+	 * restored to R0.
+	 */
 	if (flags & BPF_TRAMP_F_CALL_ORIG)
 		/* restore original return value back into RAX */
 		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
@@ -1586,9 +1688,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 		EMIT4(0x48, 0x83, 0xC4, 8); /* add rsp, 8 */
 	EMIT1(0xC3); /* ret */
 	/* Make sure the trampoline generation logic doesn't overflow */
-	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY))
-		return -EFAULT;
-	return prog - (u8 *)image;
+	if (WARN_ON_ONCE(prog > (u8 *)image_end - BPF_INSN_SAFETY)) {
+		ret = -EFAULT;
+		goto cleanup;
+	}
+	ret = prog - (u8 *)image;
+
+cleanup:
+	kfree(branches);
+	return ret;
 }
 
 static int emit_fallback_jump(u8 **pprog)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 98ec10b23dbb..f748b31e5888 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -474,6 +474,7 @@ void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
 enum bpf_tramp_prog_type {
 	BPF_TRAMP_FENTRY,
 	BPF_TRAMP_FEXIT,
+	BPF_TRAMP_MODIFY_RETURN,
 	BPF_TRAMP_MAX,
 	BPF_TRAMP_REPLACE, /* more than MAX */
 };
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d6b33ea27bcc..40b2d9476268 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -210,6 +210,7 @@ enum bpf_attach_type {
 	BPF_TRACE_RAW_TP,
 	BPF_TRACE_FENTRY,
 	BPF_TRACE_FEXIT,
+	BPF_MODIFY_RETURN,
 	__MAX_BPF_ATTACH_TYPE
 };
 
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 787140095e58..30841fb8b3c0 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -3710,7 +3710,8 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
 		nr_args--;
 	}
 
-	if (prog->expected_attach_type == BPF_TRACE_FEXIT &&
+	if ((prog->expected_attach_type == BPF_TRACE_FEXIT ||
+	     prog->expected_attach_type == BPF_MODIFY_RETURN) &&
 	    arg == nr_args) {
 		if (!t)
 			/* Default prog with 5 args. 6th arg is retval. */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 13de65363ba2..7ce0815793dd 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2324,6 +2324,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog)
 
 	if (prog->expected_attach_type != BPF_TRACE_FENTRY &&
 	    prog->expected_attach_type != BPF_TRACE_FEXIT &&
+	    prog->expected_attach_type != BPF_MODIFY_RETURN &&
 	    prog->type != BPF_PROG_TYPE_EXT) {
 		err = -EINVAL;
 		goto out_put_prog;
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index 546198f6f307..221a17af1f81 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -232,7 +232,8 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 		goto out;
 	}
 
-	if (tprogs[BPF_TRAMP_FEXIT].nr_progs)
+	if (tprogs[BPF_TRAMP_FEXIT].nr_progs ||
+	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
 	/* Though the second half of trampoline page is unused a task could be
@@ -269,6 +270,8 @@ static enum bpf_tramp_prog_type bpf_attach_type_to_tramp(enum bpf_attach_type t)
 	switch (t) {
 	case BPF_TRACE_FENTRY:
 		return BPF_TRAMP_FENTRY;
+	case BPF_MODIFY_RETURN:
+		return BPF_TRAMP_MODIFY_RETURN;
 	case BPF_TRACE_FEXIT:
 		return BPF_TRAMP_FEXIT;
 	default:
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 289383edfc8c..2460c8e6b5be 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -9950,6 +9950,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env)
 		if (!prog_extension)
 			return -EINVAL;
 		/* fallthrough */
+	case BPF_MODIFY_RETURN:
 	case BPF_TRACE_FENTRY:
 	case BPF_TRACE_FEXIT:
 		if (!btf_type_is_func(t)) {
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d6b33ea27bcc..40b2d9476268 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -210,6 +210,7 @@ enum bpf_attach_type {
 	BPF_TRACE_RAW_TP,
 	BPF_TRACE_FENTRY,
 	BPF_TRACE_FEXIT,
+	BPF_MODIFY_RETURN,
 	__MAX_BPF_ATTACH_TYPE
 };