Merge tag 'trace-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull tracing updates from Steven Rostedt:

 - Add new feature to have function graph tracer record the return
   value. Adds a new option: funcgraph-retval ; when set, will show the
   return value of a function in the function graph tracer.

 - Also add the option: funcgraph-retval-hex where if it is not set, and
   the return value is an error code, then it will return the decimal of
   the error code, otherwise it still reports the hex value.

 - Add the file /sys/kernel/tracing/osnoise/per_cpu/cpu<cpu>/timerlat_fd
   That when a application opens it, it becomes the task that the timer
   lat tracer traces. The application can also read this file to find
   out how it's being interrupted.

 - Add the file /sys/kernel/tracing/available_filter_functions_addrs
   that works just the same as available_filter_functions but also shows
   the addresses of the functions like kallsyms, except that it gives
   the address of where the fentry/mcount jump/nop is. This is used by
   BPF to make it easier to attach BPF programs to ftrace hooks.

 - Replace strlcpy with strscpy in the tracing boot code.

* tag 'trace-v6.5' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  tracing: Fix warnings when building htmldocs for function graph retval
  riscv: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
  tracing/boot: Replace strlcpy with strscpy
  tracing/timerlat: Add user-space interface
  tracing/osnoise: Skip running osnoise if all instances are off
  tracing/osnoise: Switch from PF_NO_SETAFFINITY to migrate_disable
  ftrace: Show all functions with addresses in available_filter_functions_addrs
  selftests/ftrace: Add funcgraph-retval test case
  LoongArch: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
  x86/ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
  arm64: ftrace: Enable HAVE_FUNCTION_GRAPH_RETVAL
  tracing: Add documentation for funcgraph-retval and funcgraph-retval-hex
  function_graph: Support recording and printing the return value of function
  fgraph: Add declaration of "struct fgraph_ret_regs"

29 files changed, 1079 insertions, 62 deletions

diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index 027437b745a0..f606c5bd1c0d 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -324,6 +324,12 @@ of ftrace. Here is a list of some of the key files:
 	"set_graph_function", or "set_graph_notrace".
 	(See the section "dynamic ftrace" below for more details.)
 
+  available_filter_functions_addrs:
+
+	Similar to available_filter_functions, but with address displayed
+	for each function. The displayed address is the patch-site address
+	and can differ from /proc/kallsyms address.
+
   dyn_ftrace_total_info:
 
 	This file is for debugging purposes. The number of functions that
@@ -1359,6 +1365,19 @@ Options for function_graph tracer:
 	only a closing curly bracket "}" is displayed for
 	the return of a function.
 
+  funcgraph-retval
+	When set, the return value of each traced function
+	will be printed after an equal sign "=". By default
+	this is off.
+
+  funcgraph-retval-hex
+	When set, the return value will always be printed
+	in hexadecimal format. If the option is not set and
+	the return value is an error code, it will be printed
+	in signed decimal format; otherwise it will also be
+	printed in hexadecimal format. By default, this option
+	is off.
+
   sleep-time
 	When running function graph tracer, to include
 	the time a task schedules out in its function.
@@ -2704,6 +2723,119 @@ It is default disabled.
     0)   1.757 us    |        } /* kmem_cache_free() */
     0)   2.861 us    |      } /* putname() */
 
+The return value of each traced function can be displayed after
+an equal sign "=". When encountering system call failures, it
+can be verfy helpful to quickly locate the function that first
+returns an error code.
+
+	- hide: echo nofuncgraph-retval > trace_options
+	- show: echo funcgraph-retval > trace_options
+
+  Example with funcgraph-retval::
+
+    1)               |    cgroup_migrate() {
+    1)   0.651 us    |      cgroup_migrate_add_task(); /* = 0xffff93fcfd346c00 */
+    1)               |      cgroup_migrate_execute() {
+    1)               |        cpu_cgroup_can_attach() {
+    1)               |          cgroup_taskset_first() {
+    1)   0.732 us    |            cgroup_taskset_next(); /* = 0xffff93fc8fb20000 */
+    1)   1.232 us    |          } /* cgroup_taskset_first = 0xffff93fc8fb20000 */
+    1)   0.380 us    |          sched_rt_can_attach(); /* = 0x0 */
+    1)   2.335 us    |        } /* cpu_cgroup_can_attach = -22 */
+    1)   4.369 us    |      } /* cgroup_migrate_execute = -22 */
+    1)   7.143 us    |    } /* cgroup_migrate = -22 */
+
+The above example shows that the function cpu_cgroup_can_attach
+returned the error code -22 firstly, then we can read the code
+of this function to get the root cause.
+
+When the option funcgraph-retval-hex is not set, the return value can
+be displayed in a smart way. Specifically, if it is an error code,
+it will be printed in signed decimal format, otherwise it will
+printed in hexadecimal format.
+
+	- smart: echo nofuncgraph-retval-hex > trace_options
+	- hexadecimal: echo funcgraph-retval-hex > trace_options
+
+  Example with funcgraph-retval-hex::
+
+    1)               |      cgroup_migrate() {
+    1)   0.651 us    |        cgroup_migrate_add_task(); /* = 0xffff93fcfd346c00 */
+    1)               |        cgroup_migrate_execute() {
+    1)               |          cpu_cgroup_can_attach() {
+    1)               |            cgroup_taskset_first() {
+    1)   0.732 us    |              cgroup_taskset_next(); /* = 0xffff93fc8fb20000 */
+    1)   1.232 us    |            } /* cgroup_taskset_first = 0xffff93fc8fb20000 */
+    1)   0.380 us    |            sched_rt_can_attach(); /* = 0x0 */
+    1)   2.335 us    |          } /* cpu_cgroup_can_attach = 0xffffffea */
+    1)   4.369 us    |        } /* cgroup_migrate_execute = 0xffffffea */
+    1)   7.143 us    |      } /* cgroup_migrate = 0xffffffea */
+
+At present, there are some limitations when using the funcgraph-retval
+option, and these limitations will be eliminated in the future:
+
+- Even if the function return type is void, a return value will still
+  be printed, and you can just ignore it.
+
+- Even if return values are stored in multiple registers, only the
+  value contained in the first register will be recorded and printed.
+  To illustrate, in the x86 architecture, eax and edx are used to store
+  a 64-bit return value, with the lower 32 bits saved in eax and the
+  upper 32 bits saved in edx. However, only the value stored in eax
+  will be recorded and printed.
+
+- In certain procedure call standards, such as arm64's AAPCS64, when a
+  type is smaller than a GPR, it is the responsibility of the consumer
+  to perform the narrowing, and the upper bits may contain UNKNOWN values.
+  Therefore, it is advisable to check the code for such cases. For instance,
+  when using a u8 in a 64-bit GPR, bits [63:8] may contain arbitrary values,
+  especially when larger types are truncated, whether explicitly or implicitly.
+  Here are some specific cases to illustrate this point:
+
+  **Case One**:
+
+  The function narrow_to_u8 is defined as follows::
+
+	u8 narrow_to_u8(u64 val)
+	{
+		// implicitly truncated
+		return val;
+	}
+
+  It may be compiled to::
+
+	narrow_to_u8:
+		< ... ftrace instrumentation ... >
+		RET
+
+  If you pass 0x123456789abcdef to this function and want to narrow it,
+  it may be recorded as 0x123456789abcdef instead of 0xef.
+
+  **Case Two**:
+
+  The function error_if_not_4g_aligned is defined as follows::
+
+	int error_if_not_4g_aligned(u64 val)
+	{
+		if (val & GENMASK(31, 0))
+			return -EINVAL;
+
+		return 0;
+	}
+
+  It could be compiled to::
+
+	error_if_not_4g_aligned:
+		CBNZ    w0, .Lnot_aligned
+		RET			// bits [31:0] are zero, bits
+					// [63:32] are UNKNOWN
+	.Lnot_aligned:
+		MOV    x0, #-EINVAL
+		RET
+
+  When passing 0x2_0000_0000 to it, the return value may be recorded as
+  0x2_0000_0000 instead of 0.
+
 You can put some comments on specific functions by using
 trace_printk() For example, if you want to put a comment inside
 the __might_sleep() function, you just have to include
diff --git a/Documentation/trace/timerlat-tracer.rst b/Documentation/trace/timerlat-tracer.rst
index db17df312bc8..53a56823e903 100644
--- a/Documentation/trace/timerlat-tracer.rst
+++ b/Documentation/trace/timerlat-tracer.rst
@@ -180,3 +180,81 @@ dummy_load_1ms_pd_init, which had the following code (on purpose)::
 		return 0;
 
 	}
+
+User-space interface
+---------------------------
+
+Timerlat allows user-space threads to use timerlat infra-structure to
+measure scheduling latency. This interface is accessible via a per-CPU
+file descriptor inside $tracing_dir/osnoise/per_cpu/cpu$ID/timerlat_fd.
+
+This interface is accessible under the following conditions:
+
+ - timerlat tracer is enable
+ - osnoise workload option is set to NO_OSNOISE_WORKLOAD
+ - The user-space thread is affined to a single processor
+ - The thread opens the file associated with its single processor
+ - Only one thread can access the file at a time
+
+The open() syscall will fail if any of these conditions are not met.
+After opening the file descriptor, the user space can read from it.
+
+The read() system call will run a timerlat code that will arm the
+timer in the future and wait for it as the regular kernel thread does.
+
+When the timer IRQ fires, the timerlat IRQ will execute, report the
+IRQ latency and wake up the thread waiting in the read. The thread will be
+scheduled and report the thread latency via tracer - as for the kernel
+thread.
+
+The difference from the in-kernel timerlat is that, instead of re-arming
+the timer, timerlat will return to the read() system call. At this point,
+the user can run any code.
+
+If the application rereads the file timerlat file descriptor, the tracer
+will report the return from user-space latency, which is the total
+latency. If this is the end of the work, it can be interpreted as the
+response time for the request.
+
+After reporting the total latency, timerlat will restart the cycle, arm
+a timer, and go to sleep for the following activation.
+
+If at any time one of the conditions is broken, e.g., the thread migrates
+while in user space, or the timerlat tracer is disabled, the SIG_KILL
+signal will be sent to the user-space thread.
+
+Here is an basic example of user-space code for timerlat::
+
+ int main(void)
+ {
+	char buffer[1024];
+	int timerlat_fd;
+	int retval;
+	long cpu = 0;   /* place in CPU 0 */
+	cpu_set_t set;
+
+	CPU_ZERO(&set);
+	CPU_SET(cpu, &set);
+
+	if (sched_setaffinity(gettid(), sizeof(set), &set) == -1)
+		return 1;
+
+	snprintf(buffer, sizeof(buffer),
+		"/sys/kernel/tracing/osnoise/per_cpu/cpu%ld/timerlat_fd",
+		cpu);
+
+	timerlat_fd = open(buffer, O_RDONLY);
+	if (timerlat_fd < 0) {
+		printf("error opening %s: %s\n", buffer, strerror(errno));
+		exit(1);
+	}
+
+	for (;;) {
+		retval = read(timerlat_fd, buffer, 1024);
+		if (retval < 0)
+			break;
+	}
+
+	close(timerlat_fd);
+	exit(0);
+ }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 595028bd9160..891ab530a665 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -202,6 +202,7 @@ config ARM64
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_GCC_PLUGINS
 	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && \
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index b87d70b693c6..21ac1c5c71d3 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -192,4 +192,26 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 }
 #endif /* ifndef __ASSEMBLY__ */
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+struct fgraph_ret_regs {
+	/* x0 - x7 */
+	unsigned long regs[8];
+
+	unsigned long fp;
+	unsigned long __unused;
+};
+
+static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->regs[0];
+}
+
+static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->fp;
+}
+#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER  */
+#endif
+
 #endif /* __ASM_FTRACE_H */
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 0996094b0d22..757d01a68ffd 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -200,6 +200,19 @@ int main(void)
 #endif
 #ifdef CONFIG_FUNCTION_TRACER
   DEFINE(FTRACE_OPS_FUNC,		offsetof(struct ftrace_ops, func));
+#endif
+  BLANK();
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+  DEFINE(FGRET_REGS_X0,			offsetof(struct fgraph_ret_regs, regs[0]));
+  DEFINE(FGRET_REGS_X1,			offsetof(struct fgraph_ret_regs, regs[1]));
+  DEFINE(FGRET_REGS_X2,			offsetof(struct fgraph_ret_regs, regs[2]));
+  DEFINE(FGRET_REGS_X3,			offsetof(struct fgraph_ret_regs, regs[3]));
+  DEFINE(FGRET_REGS_X4,			offsetof(struct fgraph_ret_regs, regs[4]));
+  DEFINE(FGRET_REGS_X5,			offsetof(struct fgraph_ret_regs, regs[5]));
+  DEFINE(FGRET_REGS_X6,			offsetof(struct fgraph_ret_regs, regs[6]));
+  DEFINE(FGRET_REGS_X7,			offsetof(struct fgraph_ret_regs, regs[7]));
+  DEFINE(FGRET_REGS_FP,			offsetof(struct fgraph_ret_regs, fp));
+  DEFINE(FGRET_REGS_SIZE,		sizeof(struct fgraph_ret_regs));
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
   DEFINE(FTRACE_OPS_DIRECT_CALL,	offsetof(struct ftrace_ops, direct_call));
 #endif
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 1c38a60575aa..f0c16640ef21 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -330,22 +330,23 @@ SYM_FUNC_END(ftrace_stub_graph)
  */
 SYM_CODE_START(return_to_handler)
 	/* save return value regs */
-	sub sp, sp, #64
-	stp x0, x1, [sp]
-	stp x2, x3, [sp, #16]
-	stp x4, x5, [sp, #32]
-	stp x6, x7, [sp, #48]
+	sub sp, sp, #FGRET_REGS_SIZE
+	stp x0, x1, [sp, #FGRET_REGS_X0]
+	stp x2, x3, [sp, #FGRET_REGS_X2]
+	stp x4, x5, [sp, #FGRET_REGS_X4]
+	stp x6, x7, [sp, #FGRET_REGS_X6]
+	str x29,    [sp, #FGRET_REGS_FP]	// parent's fp
 
-	mov	x0, x29			//     parent's fp
-	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
-	mov	x30, x0			// restore the original return address
+	mov	x0, sp
+	bl	ftrace_return_to_handler	// addr = ftrace_return_to_hander(regs);
+	mov	x30, x0				// restore the original return address
 
 	/* restore return value regs */
-	ldp x0, x1, [sp]
-	ldp x2, x3, [sp, #16]
-	ldp x4, x5, [sp, #32]
-	ldp x6, x7, [sp, #48]
-	add sp, sp, #64
+	ldp x0, x1, [sp, #FGRET_REGS_X0]
+	ldp x2, x3, [sp, #FGRET_REGS_X2]
+	ldp x4, x5, [sp, #FGRET_REGS_X4]
+	ldp x6, x7, [sp, #FGRET_REGS_X6]
+	add sp, sp, #FGRET_REGS_SIZE
 
 	ret
 SYM_CODE_END(return_to_handler)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 0c7fb52727ba..e55511af4c77 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -111,6 +111,7 @@ config LOONGARCH
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GENERIC_VDSO
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 23e2ba78dcb0..a11996eb5892 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -100,4 +100,26 @@ __arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
 
 #endif /* CONFIG_FUNCTION_TRACER */
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+struct fgraph_ret_regs {
+	/* a0 - a1 */
+	unsigned long regs[2];
+
+	unsigned long fp;
+	unsigned long __unused;
+};
+
+static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->regs[0];
+}
+
+static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->fp;
+}
+#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
+#endif
+
 #endif /* _ASM_LOONGARCH_FTRACE_H */
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 4bdb203fc66e..505e4bf59603 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -12,6 +12,7 @@
 #include <asm/cpu-info.h>
 #include <asm/ptrace.h>
 #include <asm/processor.h>
+#include <asm/ftrace.h>
 
 void output_ptreg_defines(void)
 {
@@ -264,7 +265,7 @@ void output_smpboot_defines(void)
 #ifdef CONFIG_HIBERNATION
 void output_pbe_defines(void)
 {
-	COMMENT(" Linux struct pbe offsets. ");
+	COMMENT("Linux struct pbe offsets.");
 	OFFSET(PBE_ADDRESS, pbe, address);
 	OFFSET(PBE_ORIG_ADDRESS, pbe, orig_address);
 	OFFSET(PBE_NEXT, pbe, next);
@@ -272,3 +273,15 @@ void output_pbe_defines(void)
 	BLANK();
 }
 #endif
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void output_fgraph_ret_regs_defines(void)
+{
+	COMMENT("LoongArch fgraph_ret_regs offsets.");
+	OFFSET(FGRET_REGS_A0, fgraph_ret_regs, regs[0]);
+	OFFSET(FGRET_REGS_A1, fgraph_ret_regs, regs[1]);
+	OFFSET(FGRET_REGS_FP, fgraph_ret_regs, fp);
+	DEFINE(FGRET_REGS_SIZE, sizeof(struct fgraph_ret_regs));
+	BLANK();
+}
+#endif
diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S
index 8cdc1563cd33..cb8e5803de4b 100644
--- a/arch/loongarch/kernel/mcount.S
+++ b/arch/loongarch/kernel/mcount.S
@@ -79,18 +79,20 @@ SYM_FUNC_START(ftrace_graph_caller)
 SYM_FUNC_END(ftrace_graph_caller)
 
 SYM_FUNC_START(return_to_handler)
-	PTR_ADDI	sp, sp, -2 * SZREG
-	PTR_S		a0, sp, 0
-	PTR_S		a1, sp, SZREG
+	PTR_ADDI	sp, sp, -FGRET_REGS_SIZE
+	PTR_S		a0, sp, FGRET_REGS_A0
+	PTR_S		a1, sp, FGRET_REGS_A1
+	PTR_S		zero, sp, FGRET_REGS_FP
 
+	move		a0, sp
 	bl		ftrace_return_to_handler
 
 	/* Restore the real parent address: a0 -> ra */
 	move		ra, a0
 
-	PTR_L		a0, sp, 0
-	PTR_L		a1, sp, SZREG
-	PTR_ADDI	sp, sp, 2 * SZREG
+	PTR_L		a0, sp, FGRET_REGS_A0
+	PTR_L		a1, sp, FGRET_REGS_A1
+	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
 	jr		ra
 SYM_FUNC_END(return_to_handler)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/loongarch/kernel/mcount_dyn.S b/arch/loongarch/kernel/mcount_dyn.S
index c7d961fc72c2..e16ab0b98e5a 100644
--- a/arch/loongarch/kernel/mcount_dyn.S
+++ b/arch/loongarch/kernel/mcount_dyn.S
@@ -136,18 +136,19 @@ SYM_CODE_END(ftrace_graph_caller)
 
 SYM_CODE_START(return_to_handler)
 	/* Save return value regs */
-	PTR_ADDI 	sp, sp, -2 * SZREG
-	PTR_S		a0, sp, 0
-	PTR_S		a1, sp, SZREG
+	PTR_ADDI	sp, sp, -FGRET_REGS_SIZE
+	PTR_S		a0, sp, FGRET_REGS_A0
+	PTR_S		a1, sp, FGRET_REGS_A1
+	PTR_S		zero, sp, FGRET_REGS_FP
 
-	move		a0, zero
+	move		a0, sp
 	bl		ftrace_return_to_handler
 	move		ra, a0
 
 	/* Restore return value regs */
-	PTR_L		a0, sp, 0
-	PTR_L		a1, sp, SZREG
-	PTR_ADDI 	sp, sp, 2 * SZREG
+	PTR_L		a0, sp, FGRET_REGS_A0
+	PTR_L		a1, sp, FGRET_REGS_A1
+	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
 
 	jr		ra
 SYM_CODE_END(return_to_handler)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 08f3a01fa1ea..b49793cf34eb 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -152,6 +152,7 @@ config RISCV
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_GRAPH_RETVAL if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 
 config CLANG_SUPPORTS_DYNAMIC_FTRACE
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index d47d87c2d7e3..740a979171e5 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -111,4 +111,25 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
 
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+struct fgraph_ret_regs {
+	unsigned long a1;
+	unsigned long a0;
+	unsigned long s0;
+	unsigned long ra;
+};
+
+static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->a0;
+}
+
+static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->s0;
+}
+#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
+#endif
+
 #endif /* _ASM_RISCV_FTRACE_H */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index 30102aadc4d7..8a6e5a9e842a 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -65,13 +65,8 @@ ENTRY(return_to_handler)
  * So alternatively we check the *old* frame pointer position, that is, the
  * value stored in -16(s0) on entry, and the s0 on return.
  */
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	t6, s0
-#endif
 	SAVE_RET_ABI_STATE
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a0, t6
-#endif
+	mv	a0, sp
 	call	ftrace_return_to_handler
 	mv	a2, a0
 	RESTORE_RET_ABI_STATE
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b3ebf58cf77e..7422db409770 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -217,6 +217,7 @@ config X86
 	select HAVE_FAST_GUP
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
 	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_RETVAL	if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER	if X86_32 || (X86_64 && DYNAMIC_FTRACE)
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index b8d4a07f9595..897cf02c20b1 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -150,4 +150,24 @@ static inline bool arch_trace_is_compat_syscall(struct pt_regs *regs)
 #endif /* !COMPILE_OFFSETS */
 #endif /* !__ASSEMBLY__ */
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+struct fgraph_ret_regs {
+	unsigned long ax;
+	unsigned long dx;
+	unsigned long bp;
+};
+
+static inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->ax;
+}
+
+static inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
+{
+	return ret_regs->bp;
+}
+#endif /* ifdef CONFIG_FUNCTION_GRAPH_TRACER */
+#endif
+
 #endif /* _ASM_X86_FTRACE_H */
diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 0d9a14528176..24c1175a47e2 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -187,12 +187,14 @@ SYM_CODE_END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:
-	pushl	%eax
+	pushl	$0
 	pushl	%edx
-	movl	$0, %eax
+	pushl	%eax
+	movl	%esp, %eax
 	call	ftrace_return_to_handler
 	movl	%eax, %ecx
-	popl	%edx
 	popl	%eax
+	popl	%edx
+	addl	$4, %esp		# skip ebp
 	JMP_NOSPEC ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index b8c720b5dab2..945cfa5f7239 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -348,12 +348,13 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__)
 SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
-	subq  $16, %rsp
+	subq  $24, %rsp
 
 	/* Save the return values */
 	movq %rax, (%rsp)
 	movq %rdx, 8(%rsp)
-	movq %rbp, %rdi
+	movq %rbp, 16(%rsp)
+	movq %rsp, %rdi
 
 	call ftrace_return_to_handler
 
@@ -361,7 +362,7 @@ SYM_CODE_START(return_to_handler)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
 
-	addq $16, %rsp
+	addq $24, %rsp
 	/*
 	 * Jump back to the old return address. This cannot be JMP_NOSPEC rdi
 	 * since IBT would demand that contain ENDBR, which simply isn't so for
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b23bdd414394..8e59bd954153 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -633,6 +633,7 @@ enum {
 	FTRACE_ITER_MOD		= (1 << 5),
 	FTRACE_ITER_ENABLED	= (1 << 6),
 	FTRACE_ITER_TOUCHED	= (1 << 7),
+	FTRACE_ITER_ADDRS	= (1 << 8),
 };
 
 void arch_ftrace_update_code(int command);
@@ -1018,6 +1019,9 @@ struct ftrace_graph_ent {
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	unsigned long retval;
+#endif
 	int depth;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned int overrun;
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8cf97fa4a4b3..abe5c583bd59 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,6 +31,9 @@ config HAVE_FUNCTION_GRAPH_TRACER
 	help
 	  See Documentation/trace/ftrace-design.rst
 
+config HAVE_FUNCTION_GRAPH_RETVAL
+	bool
+
 config HAVE_DYNAMIC_FTRACE
 	bool
 	help
@@ -227,6 +230,18 @@ config FUNCTION_GRAPH_TRACER
 	  the return value. This is done by setting the current return
 	  address on the current task structure into a stack of calls.
 
+config FUNCTION_GRAPH_RETVAL
+	bool "Kernel Function Graph Return Value"
+	depends on HAVE_FUNCTION_GRAPH_RETVAL
+	depends on FUNCTION_GRAPH_TRACER
+	default n
+	help
+	  Support recording and printing the function return value when
+	  using function graph tracer. It can be helpful to locate functions
+	  that return errors. This feature is off by default, and you can
+	  enable it via the trace option funcgraph-retval.
+	  See Documentation/trace/ftrace.rst
+
 config DYNAMIC_FTRACE
 	bool "enable/disable function tracing dynamically"
 	depends on FUNCTION_TRACER
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 218cd95bf8e4..cd2c35b1dd8f 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -236,16 +236,23 @@ static struct notifier_block ftrace_suspend_notifier = {
 	.notifier_call = ftrace_suspend_notifier_call,
 };
 
+/* fgraph_ret_regs is not defined without CONFIG_FUNCTION_GRAPH_RETVAL */
+struct fgraph_ret_regs;
+
 /*
  * Send the trace to the ring-buffer.
  * @return the original return address.
  */
-unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
+static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
+						unsigned long frame_pointer)
 {
 	struct ftrace_graph_ret trace;
 	unsigned long ret;
 
 	ftrace_pop_return_trace(&trace, &ret, frame_pointer);
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	trace.retval = fgraph_ret_regs_return_value(ret_regs);
+#endif
 	trace.rettime = trace_clock_local();
 	ftrace_graph_return(&trace);
 	/*
@@ -266,6 +273,23 @@ unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
 	return ret;
 }
 
+/*
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
+ * leave only ftrace_return_to_handler(ret_regs).
+ */
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
+unsigned long ftrace_return_to_ha