From cc252bb592638e0f7aea40d580186c36d89526b8 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 11 Dec 2024 13:53:35 -0500
Subject: fgraph: Still initialize idle shadow stacks when starting

A bug was discovered where the idle shadow stacks were not initialized
for offline CPUs when starting function graph tracer, and when they came
online they were not traced due to the missing shadow stack. To fix
this, the idle task shadow stack initialization was moved to using the
CPU hotplug callbacks. But it removed the initialization when the
function graph was enabled. The problem here is that the hotplug
callbacks are called when the CPUs come online, but the idle shadow
stack initialization only happens if function graph is currently
active. This caused the online CPUs to not get their shadow stack
initialized.

The idle shadow stack initialization still needs to be done when the
function graph is registered, as they will not be allocated if function
graph is not registered.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20241211135335.094ba282@batman.local.home
Fixes: 2c02f7375e65 ("fgraph: Use CPU hotplug mechanism to initialize idle shadow stacks")
Reported-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Closes: https://lore.kernel.org/all/CACRpkdaTBrHwRbbrphVy-=SeDz6MSsXhTKypOtLrTQ+DgGAOcQ@mail.gmail.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 0bf78517b5d4..ddedcb50917f 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -1215,7 +1215,7 @@ void fgraph_update_pid_func(void)
 static int start_graph_tracing(void)
 {
 	unsigned long **ret_stack_list;
-	int ret;
+	int ret, cpu;
 
 	ret_stack_list = kcalloc(FTRACE_RETSTACK_ALLOC_SIZE,
 				 sizeof(*ret_stack_list), GFP_KERNEL);
@@ -1223,6 +1223,12 @@ static int start_graph_tracing(void)
 	if (!ret_stack_list)
 		return -ENOMEM;
 
+	/* The cpu_boot init_task->ret_stack will never be freed */
+	for_each_online_cpu(cpu) {
+		if (!idle_task(cpu)->ret_stack)
+			ftrace_graph_init_idle_task(idle_task(cpu), cpu);
+	}
+
 	do {
 		ret = alloc_retstack_tasklist(ret_stack_list);
 	} while (ret == -EAGAIN);
-- 
cgit v1.2.3


From d576aec24df9f58ed0ebe2ff854daafe837f0225 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 10 Dec 2024 11:08:57 +0900
Subject: fgraph: Get ftrace recursion lock in function_graph_enter

Get the ftrace recursion lock in the generic function_graph_enter()
instead of each architecture code.
This changes all function_graph tracer callbacks running in
non-preemptive state. On x86 and powerpc, this is by default, but
on the other architecutres, this will be new.

Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Naveen N Rao <naveen@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/173379653720.973433.18438622234884980494.stgit@devnote2
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/powerpc/kernel/trace/ftrace.c       | 6 ------
 arch/powerpc/kernel/trace/ftrace_64_pg.c | 6 ------
 arch/x86/kernel/ftrace.c                 | 7 -------
 kernel/trace/fgraph.c                    | 8 +++++++-
 4 files changed, 7 insertions(+), 20 deletions(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 5ccd791761e8..e41daf2c4a31 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -658,7 +658,6 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long sp = arch_ftrace_regs(fregs)->regs.gpr[1];
-	int bit;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
@@ -666,14 +665,9 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	bit = ftrace_test_recursion_trylock(ip, parent_ip);
-	if (bit < 0)
-		goto out;
-
 	if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
 		parent_ip = ppc_function_entry(return_to_handler);
 
-	ftrace_test_recursion_unlock(bit);
 out:
 	arch_ftrace_regs(fregs)->regs.link = parent_ip;
 }
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 98787376eb87..8fb860b90ae1 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -790,7 +790,6 @@ static unsigned long
 __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
 {
 	unsigned long return_hooker;
-	int bit;
 
 	if (unlikely(ftrace_graph_is_dead()))
 		goto out;
@@ -798,16 +797,11 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	bit = ftrace_test_recursion_trylock(ip, parent);
-	if (bit < 0)
-		goto out;
-
 	return_hooker = ppc_function_entry(return_to_handler);
 
 	if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
 		parent = return_hooker;
 
-	ftrace_test_recursion_unlock(bit);
 out:
 	return parent;
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 4dd0ad6c94d6..33f50c80f481 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -615,7 +615,6 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 			   unsigned long frame_pointer)
 {
 	unsigned long return_hooker = (unsigned long)&return_to_handler;
-	int bit;
 
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
@@ -635,14 +634,8 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
-	bit = ftrace_test_recursion_trylock(ip, *parent);
-	if (bit < 0)
-		return;
-
 	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
 		*parent = return_hooker;
-
-	ftrace_test_recursion_unlock(bit);
 }
 
 #ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index ddedcb50917f..5c68d6109119 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -650,8 +650,13 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	struct ftrace_graph_ent trace;
 	unsigned long bitmap = 0;
 	int offset;
+	int bit;
 	int i;
 
+	bit = ftrace_test_recursion_trylock(func, ret);
+	if (bit < 0)
+		return -EBUSY;
+
 	trace.func = func;
 	trace.depth = ++current->curr_ret_depth;
 
@@ -697,12 +702,13 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	 * flag, set that bit always.
 	 */
 	set_bitmap(current, offset, bitmap | BIT(0));
-
+	ftrace_test_recursion_unlock(bit);
 	return 0;
  out_ret:
 	current->curr_ret_stack -= FGRAPH_FRAME_OFFSET + 1;
  out:
 	current->curr_ret_depth--;
+	ftrace_test_recursion_unlock(bit);
 	return -EBUSY;
 }
 
-- 
cgit v1.2.3


From 41705c4262aaca49b8d9fe9b24fe048dc6c2b301 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 26 Dec 2024 14:11:40 +0900
Subject: fgraph: Pass ftrace_regs to entryfunc

Pass ftrace_regs to the fgraph_ops::entryfunc(). If ftrace_regs is not
available, it passes a NULL instead. User callback function can access
some registers (including return address) via this ftrace_regs.

Note that the ftrace_regs can be NULL when the arch does NOT define:
HAVE_DYNAMIC_FTRACE_WITH_ARGS or HAVE_DYNAMIC_FTRACE_WITH_REGS.
More specifically, if HAVE_DYNAMIC_FTRACE_WITH_REGS is defined but
not the HAVE_DYNAMIC_FTRACE_WITH_ARGS, and the ftrace ops used to
register the function callback does not set FTRACE_OPS_FL_SAVE_REGS.
In this case, ftrace_regs can be NULL in user callback.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Naveen N Rao <naveen@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/173518990044.391279.17406984900626078579.stgit@devnote2
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/arm64/kernel/ftrace.c               | 15 +++++++++++-
 arch/loongarch/kernel/ftrace_dyn.c       | 10 +++++++-
 arch/powerpc/kernel/trace/ftrace.c       |  2 +-
 arch/powerpc/kernel/trace/ftrace_64_pg.c | 10 +++++---
 arch/riscv/kernel/ftrace.c               | 17 ++++++++++++-
 arch/x86/kernel/ftrace.c                 | 42 +++++++++++++++++++++-----------
 include/linux/ftrace.h                   | 17 ++++++++++---
 kernel/trace/fgraph.c                    | 20 +++++++++------
 kernel/trace/ftrace.c                    |  3 ++-
 kernel/trace/trace.h                     |  3 ++-
 kernel/trace/trace_functions_graph.c     |  3 ++-
 kernel/trace/trace_irqsoff.c             |  3 ++-
 kernel/trace/trace_sched_wakeup.c        |  3 ++-
 kernel/trace/trace_selftest.c            |  8 +++---
 14 files changed, 114 insertions(+), 42 deletions(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/arch/arm64/kernel/ftrace.c b/arch/arm64/kernel/ftrace.c
index 245cb419ca24..570c38be833c 100644
--- a/arch/arm64/kernel/ftrace.c
+++ b/arch/arm64/kernel/ftrace.c
@@ -481,7 +481,20 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	prepare_ftrace_return(ip, &arch_ftrace_regs(fregs)->lr, arch_ftrace_regs(fregs)->fp);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long frame_pointer = arch_ftrace_regs(fregs)->fp;
+	unsigned long *parent = &arch_ftrace_regs(fregs)->lr;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+
+	if (!function_graph_enter_regs(old, ip, frame_pointer,
+				       (void *)frame_pointer, fregs)) {
+		*parent = return_hooker;
+	}
 }
 #else
 /*
diff --git a/arch/loongarch/kernel/ftrace_dyn.c b/arch/loongarch/kernel/ftrace_dyn.c
index 18056229e22e..25c9a4cfd5fa 100644
--- a/arch/loongarch/kernel/ftrace_dyn.c
+++ b/arch/loongarch/kernel/ftrace_dyn.c
@@ -243,8 +243,16 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 {
 	struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
 	unsigned long *parent = (unsigned long *)&regs->regs[1];
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
 
-	prepare_ftrace_return(ip, (unsigned long *)parent);
+	if (!function_graph_enter_regs(old, ip, 0, parent, fregs))
+		*parent = return_hooker;
 }
 #else
 static int ftrace_modify_graph_caller(bool enable)
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index e41daf2c4a31..2f776f137a89 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -665,7 +665,7 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		goto out;
 
-	if (!function_graph_enter(parent_ip, ip, 0, (unsigned long *)sp))
+	if (!function_graph_enter_regs(parent_ip, ip, 0, (unsigned long *)sp, fregs))
 		parent_ip = ppc_function_entry(return_to_handler);
 
 out:
diff --git a/arch/powerpc/kernel/trace/ftrace_64_pg.c b/arch/powerpc/kernel/trace/ftrace_64_pg.c
index 8fb860b90ae1..ac35015f04c6 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_pg.c
+++ b/arch/powerpc/kernel/trace/ftrace_64_pg.c
@@ -787,7 +787,8 @@ int ftrace_disable_ftrace_graph_caller(void)
  * in current thread info. Return the address we want to divert to.
  */
 static unsigned long
-__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp)
+__prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp,
+			struct ftrace_regs *fregs)
 {
 	unsigned long return_hooker;
 
@@ -799,7 +800,7 @@ __prepare_ftrace_return(unsigned long parent, unsigned long ip, unsigned long sp
 
 	return_hooker = ppc_function_entry(return_to_handler);
 
-	if (!function_graph_enter(parent, ip, 0, (unsigned long *)sp))
+	if (!function_graph_enter_regs(parent, ip, 0, (unsigned long *)sp, fregs))
 		parent = return_hooker;
 
 out:
@@ -810,13 +811,14 @@ out:
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip, arch_ftrace_regs(fregs)->regs.gpr[1]);
+	arch_ftrace_regs(fregs)->regs.link = __prepare_ftrace_return(parent_ip, ip,
+						arch_ftrace_regs(fregs)->regs.gpr[1], fregs);
 }
 #else
 unsigned long prepare_ftrace_return(unsigned long parent, unsigned long ip,
 				    unsigned long sp)
 {
-	return __prepare_ftrace_return(parent, ip, sp);
+	return __prepare_ftrace_return(parent, ip, sp, NULL);
 }
 #endif
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 8cb9b211611d..3524db5e4fa0 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -214,7 +214,22 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
-	prepare_ftrace_return(&arch_ftrace_regs(fregs)->ra, ip, arch_ftrace_regs(fregs)->s0);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long frame_pointer = arch_ftrace_regs(fregs)->s0;
+	unsigned long *parent = &arch_ftrace_regs(fregs)->ra;
+	unsigned long old;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	/*
+	 * We don't suffer access faults, so no extra fault-recovery assembly
+	 * is needed here.
+	 */
+	old = *parent;
+
+	if (!function_graph_enter_regs(old, ip, frame_pointer, parent, fregs))
+		*parent = return_hooker;
 }
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_ARGS */
 extern void ftrace_graph_call(void);
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 33f50c80f481..166bc0ea3bdf 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -607,15 +607,8 @@ int ftrace_disable_ftrace_graph_caller(void)
 }
 #endif /* CONFIG_DYNAMIC_FTRACE && !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
-/*
- * Hook the return address and push it in the stack of return addrs
- * in current thread info.
- */
-void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
-			   unsigned long frame_pointer)
+static inline bool skip_ftrace_return(void)
 {
-	unsigned long return_hooker = (unsigned long)&return_to_handler;
-
 	/*
 	 * When resuming from suspend-to-ram, this function can be indirectly
 	 * called from early CPU startup code while the CPU is in real mode,
@@ -625,13 +618,27 @@ void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
 	 * This check isn't as accurate as virt_addr_valid(), but it should be
 	 * good enough for this purpose, and it's fast.
 	 */
-	if (unlikely((long)__builtin_frame_address(0) >= 0))
-		return;
+	if ((long)__builtin_frame_address(0) >= 0)
+		return true;
 
-	if (unlikely(ftrace_graph_is_dead()))
-		return;
+	if (ftrace_graph_is_dead())
+		return true;
+
+	if (atomic_read(&current->tracing_graph_pause))
+		return true;
+	return false;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long ip, unsigned long *parent,
+			   unsigned long frame_pointer)
+{
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
 
-	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+	if (unlikely(skip_ftrace_return()))
 		return;
 
 	if (!function_graph_enter(*parent, ip, frame_pointer, parent))
@@ -644,8 +651,15 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 {
 	struct pt_regs *regs = &arch_ftrace_regs(fregs)->regs;
 	unsigned long *stack = (unsigned long *)kernel_stack_pointer(regs);
+	unsigned long return_hooker = (unsigned long)&return_to_handler;
+	unsigned long *parent = (unsigned long *)stack;
+
+	if (unlikely(skip_ftrace_return()))
+		return;
+
 
-	prepare_ftrace_return(ip, (unsigned long *)stack, 0);
+	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+		*parent = return_hooker;
 }
 #endif
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index aa9ddd1e4bb6..c86ac786da3d 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1071,10 +1071,12 @@ struct fgraph_ops;
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
 				       struct fgraph_ops *); /* return */
 typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
-				      struct fgraph_ops *); /* entry */
+				      struct fgraph_ops *,
+				      struct ftrace_regs *); /* entry */
 
 extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-				   struct fgraph_ops *gops);
+				   struct fgraph_ops *gops,
+				   struct ftrace_regs *fregs);
 bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -1114,8 +1116,15 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-function_graph_enter(unsigned long ret, unsigned long func,
-		     unsigned long frame_pointer, unsigned long *retp);
+function_graph_enter_regs(unsigned long ret, unsigned long func,
+			  unsigned long frame_pointer, unsigned long *retp,
+			  struct ftrace_regs *fregs);
+
+static inline int function_graph_enter(unsigned long ret, unsigned long func,
+				       unsigned long fp, unsigned long *retp)
+{
+	return function_graph_enter_regs(ret, func, fp, retp, NULL);
+}
 
 struct ftrace_ret_stack *
 ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 5c68d6109119..4791fd704e28 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -292,7 +292,8 @@ static inline unsigned long make_data_type_val(int idx, int size, int offset)
 }
 
 /* ftrace_graph_entry set to this to tell some archs to run function graph */
-static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops)
+static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops,
+		     struct ftrace_regs *fregs)
 {
 	return 0;
 }
@@ -520,7 +521,8 @@ int __weak ftrace_disable_ftrace_graph_caller(void)
 #endif
 
 int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
-			    struct fgraph_ops *gops)
+			    struct fgraph_ops *gops,
+			    struct ftrace_regs *fregs)
 {
 	return 0;
 }
@@ -644,8 +646,9 @@ ftrace_push_return_trace(unsigned long ret, unsigned long func,
 #endif
 
 /* If the caller does not use ftrace, call this function. */
-int function_graph_enter(unsigned long ret, unsigned long func,
-			 unsigned long frame_pointer, unsigned long *retp)
+int function_graph_enter_regs(unsigned long ret, unsigned long func,
+			      unsigned long frame_pointer, unsigned long *retp,
+			      struct ftrace_regs *fregs)
 {
 	struct ftrace_graph_ent trace;
 	unsigned long bitmap = 0;
@@ -668,7 +671,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 	if (static_branch_likely(&fgraph_do_direct)) {
 		int save_curr_ret_stack = current->curr_ret_stack;
 
-		if (static_call(fgraph_func)(&trace, fgraph_direct_gops))
+		if (static_call(fgraph_func)(&trace, fgraph_direct_gops, fregs))
 			bitmap |= BIT(fgraph_direct_gops->idx);
 		else
 			/* Clear out any saved storage */
@@ -686,7 +689,7 @@ int function_graph_enter(unsigned long ret, unsigned long func,
 
 			save_curr_ret_stack = current->curr_ret_stack;
 			if (ftrace_ops_test(&gops->ops, func, NULL) &&
-			    gops->entryfunc(&trace, gops))
+			    gops->entryfunc(&trace, gops, fregs))
 				bitmap |= BIT(i);
 			else
 				/* Clear out any saved storage */
@@ -1180,7 +1183,8 @@ void ftrace_graph_exit_task(struct task_struct *t)
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 static int fgraph_pid_func(struct ftrace_graph_ent *trace,
-			   struct fgraph_ops *gops)
+			   struct fgraph_ops *gops,
+			   struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = gops->ops.private;
 	int pid;
@@ -1194,7 +1198,7 @@ static int fgraph_pid_func(struct ftrace_graph_ent *trace,
 			return 0;
 	}
 
-	return gops->saved_func(trace, gops);
+	return gops->saved_func(trace, gops, fregs);
 }
 
 void fgraph_update_pid_func(void)
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6ebc76bafd38..ae29e1c4177d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -819,7 +819,8 @@ struct profile_fgraph_data {
 };
 
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9691b47b5f3d..0f38f36a5a8a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -694,7 +694,8 @@ void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 
 void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
-int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops);
+int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
+		      struct ftrace_regs *fregs);
 
 void tracing_start_cmdline_record(void);
 void tracing_stop_cmdline_record(void);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index f513603d7df9..676cf3e38f51 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -175,7 +175,8 @@ struct fgraph_times {
 };
 
 int trace_graph_entry(struct ftrace_graph_ent *trace,
-		      struct fgraph_ops *gops)
+		      struct fgraph_ops *gops,
+		      struct ftrace_regs *fregs)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index fce064e20570..ad739d76fc86 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -176,7 +176,8 @@ static int irqsoff_display_graph(struct trace_array *tr, int set)
 }
 
 static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index d6c7f18daa15..0d9e1075d815 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -113,7 +113,8 @@ static int wakeup_display_graph(struct trace_array *tr, int set)
 }
 
 static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 38b5754790c9..f54493f8783d 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -774,7 +774,8 @@ struct fgraph_fixture {
 };
 
 static __init int store_entry(struct ftrace_graph_ent *trace,
-			      struct fgraph_ops *gops)
+			      struct fgraph_ops *gops,
+			      struct ftrace_regs *fregs)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
@@ -1025,7 +1026,8 @@ static unsigned int graph_hang_thresh;
 
 /* Wrap the real function entry probe to avoid possible hanging */
 static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
-				      struct fgraph_ops *gops)
+				      struct fgraph_ops *gops,
+				      struct ftrace_regs *fregs)
 {
 	/* This is harmlessly racy, we want to approximately detect a hang */
 	if (unlikely(++graph_hang_thresh > GRAPH_MAX_FUNC_TEST)) {
@@ -1039,7 +1041,7 @@ static int trace_graph_entry_watchdog(struct ftrace_graph_ent *trace,
 		return 0;
 	}
 
-	return trace_graph_entry(trace, gops);
+	return trace_graph_entry(trace, gops, fregs);
 }
 
 static struct fgraph_ops fgraph_ops __initdata  = {
-- 
cgit v1.2.3


From a3ed4157b7d89800a0008de0c9e46a438a5c3745 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 26 Dec 2024 14:11:55 +0900
Subject: fgraph: Replace fgraph_ret_regs with ftrace_regs

Use ftrace_regs instead of fgraph_ret_regs for tracing return value
on function_graph tracer because of simplifying the callback interface.

The CONFIG_HAVE_FUNCTION_GRAPH_RETVAL is also replaced by
CONFIG_HAVE_FUNCTION_GRAPH_FREGS.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: WANG Xuerui <kernel@xen0n.name>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: x86@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/173518991508.391279.16635322774382197642.stgit@devnote2
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 arch/arm64/Kconfig                  |  1 +
 arch/arm64/include/asm/ftrace.h     | 23 ++++++-----------------
 arch/arm64/kernel/asm-offsets.c     | 12 ------------
 arch/arm64/kernel/entry-ftrace.S    | 32 ++++++++++++++++++--------------
 arch/loongarch/Kconfig              |  2 +-
 arch/loongarch/include/asm/ftrace.h | 26 ++++----------------------
 arch/loongarch/kernel/asm-offsets.c | 12 ------------
 arch/loongarch/kernel/mcount.S      | 17 ++++++++++-------
 arch/loongarch/kernel/mcount_dyn.S  | 14 +++++++-------
 arch/riscv/Kconfig                  |  2 +-
 arch/riscv/include/asm/ftrace.h     | 26 +++++---------------------
 arch/riscv/kernel/mcount.S          | 24 +++++++++++++-----------
 arch/s390/Kconfig                   |  2 +-
 arch/s390/include/asm/ftrace.h      | 24 +++++++-----------------
 arch/s390/kernel/asm-offsets.c      |  6 ------
 arch/s390/kernel/mcount.S           | 12 ++++++------
 arch/x86/Kconfig                    |  2 +-
 arch/x86/include/asm/ftrace.h       | 20 --------------------
 arch/x86/kernel/ftrace_32.S         | 13 +++++++------
 arch/x86/kernel/ftrace_64.S         | 17 +++++++++--------
 include/linux/ftrace.h              | 12 +++++++++---
 include/linux/ftrace_regs.h         |  2 ++
 kernel/trace/Kconfig                |  4 ++--
 kernel/trace/fgraph.c               | 21 +++++++++------------
 24 files changed, 119 insertions(+), 207 deletions(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 100570a048c5..5f086777dad9 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -219,6 +219,7 @@ config ARM64
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_RETVAL
 	select HAVE_GCC_PLUGINS
diff --git a/arch/arm64/include/asm/ftrace.h b/arch/arm64/include/asm/ftrace.h
index 5ccff4de7f09..b5fa57b61378 100644
--- a/arch/arm64/include/asm/ftrace.h
+++ b/arch/arm64/include/asm/ftrace.h
@@ -129,6 +129,12 @@ ftrace_override_function_with_return(struct ftrace_regs *fregs)
 	arch_ftrace_regs(fregs)->pc = arch_ftrace_regs(fregs)->lr;
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->fp;
+}
+
 int ftrace_regs_query_register_offset(const char *name);
 
 int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec);
@@ -186,23 +192,6 @@ static inline bool arch_syscall_match_sym_name(const char *sym,
 
 #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;
-}
 
 void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 			   unsigned long frame_pointer);
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 29bf85dacffe..eb1a840e4110 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -179,18 +179,6 @@ int main(void)
   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));
-#endif
 #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 f0c16640ef21..169ccf600066 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -329,24 +329,28 @@ SYM_FUNC_END(ftrace_stub_graph)
  * @fp is checked against the value passed by ftrace_graph_caller().
  */
 SYM_CODE_START(return_to_handler)
-	/* save return value regs */
-	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
+	/* Make room for ftrace_regs */
+	sub	sp, sp, #FREGS_SIZE
+
+	/* Save return value regs */
+	stp	x0, x1, [sp, #FREGS_X0]
+	stp	x2, x3, [sp, #FREGS_X2]
+	stp	x4, x5, [sp, #FREGS_X4]
+	stp	x6, x7, [sp, #FREGS_X6]
+
+	/* Save the callsite's FP */
+	str	x29, [sp, #FREGS_FP]
 
 	mov	x0, sp
-	bl	ftrace_return_to_handler	// addr = ftrace_return_to_hander(regs);
+	bl	ftrace_return_to_handler	// addr = ftrace_return_to_hander(fregs);
 	mov	x30, x0				// restore the original return address
 
-	/* restore return value regs */
-	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
+	/* Restore return value regs */
+	ldp	x0, x1, [sp, #FREGS_X0]
+	ldp	x2, x3, [sp, #FREGS_X2]
+	ldp	x4, x5, [sp, #FREGS_X4]
+	ldp	x6, x7, [sp, #FREGS_X6]
+	add	sp, sp, #FREGS_SIZE
 
 	ret
 SYM_CODE_END(return_to_handler)
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index dae3a9104ca6..49f5bfc00e5a 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -137,7 +137,7 @@ 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_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/loongarch/include/asm/ftrace.h b/arch/loongarch/include/asm/ftrace.h
index 8f13eaeaa325..ceb3e3d9c0d3 100644
--- a/arch/loongarch/include/asm/ftrace.h
+++ b/arch/loongarch/include/asm/ftrace.h
@@ -57,6 +57,10 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 	instruction_pointer_set(&arch_ftrace_regs(fregs)->regs, ip);
 }
 
+#undef ftrace_regs_get_frame_pointer
+#define ftrace_regs_get_frame_pointer(fregs) \
+	(arch_ftrace_regs(fregs)->regs.regs[22])
+
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs);
@@ -78,26 +82,4 @@ __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 049c5c3e370c..8be1c38ad8eb 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -280,18 +280,6 @@ static void __used output_pbe_defines(void)
 }
 #endif
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-static void __used 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
-
 static void __used output_kvm_defines(void)
 {
 	COMMENT("KVM/LoongArch Specific offsets.");
diff --git a/arch/loongarch/kernel/mcount.S b/arch/loongarch/kernel/mcount.S
index 3015896016a0..b6850503e061 100644
--- a/arch/loongarch/kernel/mcount.S
+++ b/arch/loongarch/kernel/mcount.S
@@ -79,10 +79,11 @@ SYM_FUNC_START(ftrace_graph_caller)
 SYM_FUNC_END(ftrace_graph_caller)
 
 SYM_FUNC_START(return_to_handler)
-	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
+	/* Save return value regs */
+	PTR_ADDI	sp, sp, -PT_SIZE
+	PTR_S		a0, sp, PT_R4
+	PTR_S		a1, sp, PT_R5
+	PTR_S		zero, sp, PT_R22
 
 	move		a0, sp
 	bl		ftrace_return_to_handler
@@ -90,9 +91,11 @@ SYM_FUNC_START(return_to_handler)
 	/* Restore the real parent address: a0 -> ra */
 	move		ra, a0
 
-	PTR_L		a0, sp, FGRET_REGS_A0
-	PTR_L		a1, sp, FGRET_REGS_A1
-	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
+	/* Restore return value regs */
+	PTR_L		a0, sp, PT_R4
+	PTR_L		a1, sp, PT_R5
+	PTR_ADDI	sp, sp, PT_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 0c65cf09110c..d6b474ad1d5e 100644
--- a/arch/loongarch/kernel/mcount_dyn.S
+++ b/arch/loongarch/kernel/mcount_dyn.S
@@ -140,19 +140,19 @@ SYM_CODE_END(ftrace_graph_caller)
 SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	/* Save return value regs */
-	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
+	PTR_ADDI	sp, sp, -PT_SIZE
+	PTR_S		a0, sp, PT_R4
+	PTR_S		a1, sp, PT_R5
+	PTR_S		zero, sp, PT_R22
 
 	move		a0, sp
 	bl		ftrace_return_to_handler
 	move		ra, a0
 
 	/* Restore return value regs */
-	PTR_L		a0, sp, FGRET_REGS_A0
-	PTR_L		a1, sp, FGRET_REGS_A1
-	PTR_ADDI	sp, sp, FGRET_REGS_SIZE
+	PTR_L		a0, sp, PT_R4
+	PTR_L		a1, sp, PT_R5
+	PTR_ADDI	sp, sp, PT_SIZE
 
 	jr		ra
 SYM_CODE_END(return_to_handler)
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d4a7ca0388c0..1e807c61258f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -148,7 +148,7 @@ config RISCV
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS 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_GRAPH_FREGS
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !PREEMPTION
 	select HAVE_EBPF_JIT if MMU
 	select HAVE_GUP_FAST if MMU
diff --git a/arch/riscv/include/asm/ftrace.h b/arch/riscv/include/asm/ftrace.h
index 3d66437a1029..9372f8d7036f 100644
--- a/arch/riscv/include/asm/ftrace.h
+++ b/arch/riscv/include/asm/ftrace.h
@@ -168,6 +168,11 @@ static __always_inline unsigned long ftrace_regs_get_stack_pointer(const struct
 	return arch_ftrace_regs(fregs)->sp;
 }
 
+static __always_inline unsigned long ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->s0;
+}
+
 static __always_inline unsigned long ftrace_regs_get_argument(struct ftrace_regs *fregs,
 							      unsigned int n)
 {
@@ -208,25 +213,4 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs, unsi
 
 #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 3a42f6287909..068168046e0e 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -12,6 +12,8 @@
 #include <asm/asm-offsets.h>
 #include <asm/ftrace.h>
 
+#define ABI_SIZE_ON_STACK	80
+
 	.text
 
 	.macro SAVE_ABI_STATE
@@ -26,12 +28,12 @@
 	 * register if a0 was not saved.
 	 */
 	.macro SAVE_RET_ABI_STATE
-	addi	sp, sp, -4*SZREG
-	REG_S	s0, 2*SZREG(sp)
-	REG_S	ra, 3*SZREG(sp)
-	REG_S	a0, 1*SZREG(sp)
-	REG_S	a1, 0*SZREG(sp)
-	addi	s0, sp, 4*SZREG
+	addi	sp, sp, -ABI_SIZE_ON_STACK
+	REG_S	ra, 1*SZREG(sp)
+	REG_S	s0, 8*SZREG(sp)
+	REG_S	a0, 10*SZREG(sp)
+	REG_S	a1, 11*SZREG(sp)
+	addi	s0, sp, ABI_SIZE_ON_STACK
 	.endm
 
 	.macro RESTORE_ABI_STATE
@@ -41,11 +43,11 @@
 	.endm
 
 	.macro RESTORE_RET_ABI_STATE
-	REG_L	ra, 3*SZREG(sp)
-	REG_L	s0, 2*SZREG(sp)
-	REG_L	a0, 1*SZREG(sp)
-	REG_L	a1, 0*SZREG(sp)
-	addi	sp, sp, 4*SZREG
+	REG_L	ra, 1*SZREG(sp)
+	REG_L	s0, 8*SZREG(sp)
+	REG_L	a0, 10*SZREG(sp)
+	REG_L	a1, 11*SZREG(sp)
+	addi	sp, sp, ABI_SIZE_ON_STACK
 	.endm
 
 SYM_TYPED_FUNC_START(ftrace_stub)
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 0077969170e8..102029e56cf0 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -192,7 +192,7 @@ config S390
 	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
-	select HAVE_FUNCTION_GRAPH_RETVAL
+	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
index fc97d75dc752..5c94c1fc1bc1 100644
--- a/arch/s390/include/asm/ftrace.h
+++ b/arch/s390/include/asm/ftrace.h
@@ -62,23 +62,6 @@ static __always_inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *
 	return NULL;
 }
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-struct fgraph_ret_regs {
-	unsigned long gpr2;
-	unsigned long fp;
-};
-
-static __always_inline unsigned long fgraph_ret_regs_return_value(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->gpr2;
-}
-
-static __always_inline unsigned long fgraph_ret_regs_frame_pointer(struct fgraph_ret_regs *ret_regs)
-{
-	return ret_regs->fp;
-}
-#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-
 static __always_inline void
 ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 				    unsigned long ip)
@@ -86,6 +69,13 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 	arch_ftrace_regs(fregs)->regs.psw.addr = ip;
 }
 
+#undef ftrace_regs_get_frame_pointer
+static __always_inline unsigned long
+ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs)
+{
+	return ftrace_regs_get_stack_pointer(fregs);
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 /*
  * When an ftrace registered caller is tracing a function that is
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 862a9140528e..36709112ae7a 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -175,12 +175,6 @@ int main(void)
 	DEFINE(OLDMEM_SIZE, PARMAREA + offsetof(struct parmarea, oldmem_size));
 	DEFINE(COMMAND_LINE, PARMAREA + offsetof(struct parmarea, command_line));
 	DEFINE(MAX_COMMAND_LINE_SIZE, PARMAREA + offsetof(struct parmarea, max_command_line_size));
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	/* function graph return value tracing */
-	OFFSET(__FGRAPH_RET_GPR2, fgraph_ret_regs, gpr2);
-	OFFSET(__FGRAPH_RET_FP, fgraph_ret_regs, fp);
-	DEFINE(__FGRAPH_RET_SIZE, sizeof(struct fgraph_ret_regs));
-#endif
 	OFFSET(__FTRACE_REGS_PT_REGS, __arch_ftrace_regs, regs);
 	DEFINE(__FTRACE_REGS_SIZE, sizeof(struct __arch_ftrace_regs));
 
diff --git a/arch/s390/kernel/mcount.S b/arch/s390/kernel/mcount.S
index 7e267ef63a7f..2b628aa3d809 100644
--- a/arch/s390/kernel/mcount.S
+++ b/arch/s390/kernel/mcount.S
@@ -134,14 +134,14 @@ SYM_CODE_END(ftrace_common)
 SYM_FUNC_START(return_to_handler)
 	stmg	%r2,%r5,32(%r15)
 	lgr	%r1,%r15
-	aghi	%r15,-(STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE)
+	# allocate ftrace_regs and stack frame for ftrace_return_to_handler
+	aghi	%r15,-STACK_FRAME_SIZE_FREGS
 	stg	%r1,__SF_BACKCHAIN(%r15)
-	la	%r3,STACK_FRAME_OVERHEAD(%r15)
-	stg	%r1,__FGRAPH_RET_FP(%r3)
-	stg	%r2,__FGRAPH_RET_GPR2(%r3)
-	lgr	%r2,%r3
+	stg	%r2,(STACK_FREGS_PTREGS_GPRS+2*8)(%r15)
+	stg	%r1,(STACK_FREGS_PTREGS_GPRS+15*8)(%r15)
+	la	%r2,STACK_FRAME_OVERHEAD(%r15)
 	brasl	%r14,ftrace_return_to_handler
-	aghi	%r15,STACK_FRAME_OVERHEAD+__FGRAPH_RET_SIZE
+	aghi	%r15,STACK_FRAME_SIZE_FREGS
 	lgr	%r14,%r2
 	lmg	%r2,%r5,32(%r15)
 	BR_EX	%r14
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9d7bd0ae48c4..ff0d7e07c611 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -235,7 +235,7 @@ config X86
 	select HAVE_GUP_FAST
 	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_FREGS	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 6e8cf0fa48fc..d61407c680c2 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -134,24 +134,4 @@ 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 58d9ed50fe61..f4e0c3361234 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -187,14 +187,15 @@ SYM_CODE_END(ftrace_graph_caller)
 
 .globl return_to_handler
 return_to_handler:
-	pushl	$0
-	pushl	%edx
-	pushl	%eax
+	subl	$(PTREGS_SIZE), %esp
+	movl	$0, PT_EBP(%esp)
+	movl	%edx, PT_EDX(%esp)
+	movl	%eax, PT_EAX(%esp)
 	movl	%esp, %eax
 	call	ftrace_return_to_handler
 	movl	%eax, %ecx
-	popl	%eax
-	popl	%edx
-	addl	$4, %esp		# skip ebp
+	movl	PT_EAX(%esp), %eax
+	movl	PT_EDX(%esp), %edx
+	addl	$(PTREGS_SIZE), %esp
 	JMP_NOSPEC ecx
 #endif
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index 214f30e9f0c0..d51647228596 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -348,21 +348,22 @@ STACK_FRAME_NON_STANDARD_FP(__fentry__)
 SYM_CODE_START(return_to_handler)
 	UNWIND_HINT_UNDEFINED
 	ANNOTATE_NOENDBR
-	subq  $24, %rsp
 
-	/* Save the return values */
-	movq %rax, (%rsp)
-	movq %rdx, 8(%rsp)
-	movq %rbp, 16(%rsp)
+	/* Save ftrace_regs for function exit context  */
+	subq $(FRAME_SIZE), %rsp
+
+	movq %rax, RAX(%rsp)
+	movq %rdx, RDX(%rsp)
+	movq %rbp, RBP(%rsp)
 	movq %rsp, %rdi
 
 	call ftrace_return_to_handler
 
 	movq %rax, %rdi
-	movq 8(%rsp), %rdx
-	movq (%rsp), %rax
+	movq RDX(%rsp), %rdx
+	movq RAX(%rsp), %rax
 
-	addq $24, %rsp
+	addq $(FRAME_SIZE), %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 c86ac786da3d..069f270bd7ae 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -43,9 +43,8 @@ struct dyn_ftrace;
 
 char *arch_ftrace_match_adjust(char *str, const char *search);
 
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-struct fgraph_ret_regs;
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs);
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs);
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
 #endif
@@ -134,6 +133,13 @@ extern int ftrace_enabled;
  * Also, architecture dependent fields can be used for internal process.
  * (e.g. orig_ax on x86_64)
  *
+ * Basically, ftrace_regs stores the registers related to the context.
+ * On function entry, registers for function parameters and hooking the
+ * function call are stored, and on function exit, registers for function
+ * return value and frame pointers are stored.
+ *
+ * And also, it dpends on the context that which registers are restored
+ * from the ftrace_regs.
  * On the function entry, those registers will be restored except for
  * the stack pointer, so that user can change the function parameters
  * and instruction pointer (e.g. live patching.)
diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h
index be1ed0c891d0..bbc1873ca6b8 100644
--- a/include/linux/ftrace_regs.h
+++ b/include/linux/ftrace_regs.h
@@ -30,6 +30,8 @@ struct ftrace_regs;
 	override_function_with_return(&arch_ftrace_regs(fregs)->regs)
 #define ftrace_regs_query_register_offset(name) \
 	regs_query_register_offset(name)
+#define ftrace_regs_get_frame_pointer(fregs) \
+	frame_pointer(&arch_ftrace_regs(fregs)->regs)
 
 #endif /* HAVE_ARCH_FTRACE_REGS */
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 74c2b1d43bb9..c5ab2a561272 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -31,7 +31,7 @@ config HAVE_FUNCTION_GRAPH_TRACER
 	help
 	  See Documentation/trace/ftrace-design.rst
 
-config HAVE_FUNCTION_GRAPH_RETVAL
+config HAVE_FUNCTION_GRAPH_FREGS
 	bool
 
 config HAVE_DYNAMIC_FTRACE
@@ -232,7 +232,7 @@ config FUNCTION_GRAPH_TRACER
 
 config FUNCTION_GRAPH_RETVAL
 	bool "Kernel Function Graph Return Value"
-	depends on HAVE_FUNCTION_GRAPH_RETVAL
+	depends on HAVE_FUNCTION_GRAPH_FREGS
 	depends on FUNCTION_GRAPH_TRACER
 	default n
 	help
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 4791fd704e28..51196f10d96e 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -801,15 +801,12 @@ 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.
  */
-static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs,
-						unsigned long frame_pointer)
+static inline unsigned long
+__ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointer)
 {
 	struct ftrace_ret_stack *ret_stack;
 	struct ftrace_graph_ret trace;
@@ -829,7 +826,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 
 	trace.rettime = trace_clock_local();
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
-	trace.retval = fgraph_ret_regs_return_value(ret_regs);
+	trace.retval = ftrace_regs_get_return_value(fregs);
 #endif
 
 	bitmap = get_bitmap_bits(current, offset);
@@ -864,14 +861,14 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 }
 
 /*
- * After all architecures have selected HAVE_FUNCTION_GRAPH_RETVAL, we can
- * leave only ftrace_return_to_handler(ret_regs).
+ * After all architecures have selected HAVE_FUNCTION_GRAPH_FREGS, we can
+ * leave only ftrace_return_to_handler(fregs).
  */
-#ifdef CONFIG_HAVE_FUNCTION_GRAPH_RETVAL
-unsigned long ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs)
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs)
 {
-	return __ftrace_return_to_handler(ret_regs,
-				fgraph_ret_regs_frame_pointer(ret_regs));
+	return __ftrace_return_to_handler(fregs,
+				ftrace_regs_get_frame_pointer(fregs));
 }
 #else
 unsigned long ftrace_return_to_handler(unsigned long frame_pointer)
-- 
cgit v1.2.3


From 2ca8c112c9676e2394d76760db78ffddf21d93b5 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 26 Dec 2024 14:12:09 +0900
Subject: fgraph: Pass ftrace_regs to retfunc

Pass ftrace_regs to the fgraph_ops::retfunc(). If ftrace_regs is not
available, it passes a NULL instead. User callback function can access
some registers (including return address) via this ftrace_regs.

Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: bpf <bpf@vger.kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Alan Maguire <alan.maguire@oracle.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/173518992972.391279.14055405490327765506.stgit@devnote2
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h               |  3 ++-
 kernel/trace/fgraph.c                | 16 +++++++++++-----
 kernel/trace/ftrace.c                |  3 ++-
 kernel/trace/trace.h                 |  3 ++-
 kernel/trace/trace_functions_graph.c |  7 ++++---
 kernel/trace/trace_irqsoff.c         |  3 ++-
 kernel/trace/trace_sched_wakeup.c    |  3 ++-
 kernel/trace/trace_selftest.c        |  3 ++-
 8 files changed, 27 insertions(+), 14 deletions(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 069f270bd7ae..9a1e768e47da 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1075,7 +1075,8 @@ struct fgraph_ops;
 
 /* Type of the callback handlers for tracing function graph*/
 typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
-				       struct fgraph_ops *); /* return */
+				       struct fgraph_ops *,
+				       struct ftrace_regs *); /* return */
 typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
 				      struct fgraph_ops *,
 				      struct ftrace_regs *); /* entry */
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 51196f10d96e..c928527251e3 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -299,7 +299,8 @@ static int entry_run(struct ftrace_graph_ent *trace, struct fgraph_ops *ops,
 }
 
 /* ftrace_graph_return set to this to tell some archs to run function graph */
-static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops)
+static void return_run(struct ftrace_graph_ret *trace, struct fgraph_ops *ops,
+		       struct ftrace_regs *fregs)
 {
 }
 
@@ -528,7 +529,8 @@ int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
 }
 
 static void ftrace_graph_ret_stub(struct ftrace_graph_ret *trace,
-				  struct fgraph_ops *gops)
+				  struct fgraph_ops *gops,
+				  struct ftrace_regs *fregs)
 {
 }
 
@@ -825,6 +827,9 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 	}
 
 	trace.rettime = trace_clock_local();
+	if (fregs)
+		ftrace_regs_set_instruction_pointer(fregs, ret);
+
 #ifdef CONFIG_FUNCTION_GRAPH_RETVAL
 	trace.retval = ftrace_regs_get_return_value(fregs);
 #endif
@@ -834,7 +839,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 #ifdef CONFIG_HAVE_STATIC_CALL
 	if (static_branch_likely(&fgraph_do_direct)) {
 		if (test_bit(fgraph_direct_gops->idx, &bitmap))
-			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops);
+			static_call(fgraph_retfunc)(&trace, fgraph_direct_gops, fregs);
 	} else
 #endif
 	{
@@ -844,7 +849,7 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 			if (gops == &fgraph_stub)
 				continue;
 
-			gops->retfunc(&trace, gops);
+			gops->retfunc(&trace, gops, fregs);
 		}
 	}
 
@@ -1016,7 +1021,8 @@ void ftrace_graph_sleep_time_control(bool enable)
  * Simply points to ftrace_stub, but with the proper protocol.
  * Defined by the linker script in linux/vmlinux.lds.h
  */
-void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
+void ftrace_stub_graph(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,
+		       struct ftrace_regs *fregs);
 
 /* The callbacks that hook a function */
 trace_func_graph_ret_t ftrace_graph_return = ftrace_stub_graph;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index ae29e1c4177d..f054343be026 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -842,7 +842,8 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void profile_graph_return(struct ftrace_graph_ret *trace,
-				 struct fgraph_ops *gops)
+				 struct fgraph_ops *gops,
+				 struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 	struct ftrace_profile_stat *stat;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 0f38f36a5a8a..5f3e68a8d8a0 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -693,7 +693,8 @@ void trace_latency_header(struct seq_file *m);
 void trace_default_header(struct seq_file *m);
 void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
 
-void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops);
+void trace_graph_return(struct ftrace_graph_ret *trace, struct fgraph_ops *gops,
+			struct ftrace_regs *fregs);
 int trace_graph_entry(struct ftrace_graph_ent *trace, struct fgraph_ops *gops,
 		      struct ftrace_regs *fregs);
 
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 676cf3e38f51..dc62eb93837a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -310,7 +310,7 @@ static void handle_nosleeptime(struct ftrace_graph_ret *trace,
 }
 
 void trace_graph_return(struct ftrace_graph_ret *trace,
-			struct fgraph_ops *gops)
+			struct fgraph_ops *gops, struct ftrace_regs *fregs)
 {
 	unsigned long *task_var = fgraph_get_task_var(gops);
 	struct trace_array *tr = gops->private;
@@ -348,7 +348,8 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 }
 
 static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
-				      struct fgraph_ops *gops)
+				      struct fgraph_ops *gops,
+				      struct ftrace_regs *fregs)
 {
 	struct fgraph_times *ftimes;
 	int size;
@@ -372,7 +373,7 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 	    (trace->rettime - ftimes->calltime < tracing_thresh))
 		return;
 	else
-		trace_graph_return(trace, gops);
+		trace_graph_return(trace, gops, fregs);
 }
 
 static struct fgraph_ops funcgraph_ops = {
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index ad739d76fc86..504de7a05498 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -208,7 +208,8 @@ static int irqsoff_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
-				 struct fgraph_ops *gops)
+				 struct fgraph_ops *gops,
+				 struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = irqsoff_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index 0d9e1075d815..8165382a174a 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -144,7 +144,8 @@ static int wakeup_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void wakeup_graph_return(struct ftrace_graph_ret *trace,
-				struct fgraph_ops *gops)
+				struct fgraph_ops *gops,
+				struct ftrace_regs *fregs)
 {
 	struct trace_array *tr = wakeup_trace;
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index f54493f8783d..d88c44f1dfa5 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -808,7 +808,8 @@ static __init int store_entry(struct ftrace_graph_ent *trace,
 }
 
 static __init void store_return(struct ftrace_graph_ret *trace,
-				struct fgraph_ops *gops)
+				struct fgraph_ops *gops,
+				struct ftrace_regs *fregs)
 {
 	struct fgraph_fixture *fixture = container_of(gops, struct fgraph_fixture, gops);
 	const char *type = fixture->store_type_name;
-- 
cgit v1.2.3


From d65474033740ded0a4fe9a097fce72328655b41d Mon Sep 17 00:00:00 2001
From: Zilin Guan <zilin@seu.edu.cn>
Date: Tue, 31 Dec 2024 11:37:31 +0000
Subject: fgraph: Add READ_ONCE() when accessing fgraph_array[]

In __ftrace_return_to_handler(), a loop iterates over the fgraph_array[]
elements, which are fgraph_ops. The loop checks if an element is a
fgraph_stub to prevent using a fgraph_stub afterward.

However, if the compiler reloads fgraph_array[] after this check, it might
race with an update to fgraph_array[] that introduces a fgraph_stub. This
could result in the stub being processed, but the stub contains a null
"func_hash" field, leading to a NULL pointer dereference.

To ensure that the gops compared against the fgraph_stub matches the gops
processed later, add a READ_ONCE(). A similar patch appears in commit
63a8dfb ("function_graph: Add READ_ONCE() when accessing fgraph_array[]").

Cc: stable@vger.kernel.org
Fixes: 37238abe3cb47 ("ftrace/function_graph: Pass fgraph_ops to function graph callbacks")
Link: https://lore.kernel.org/20241231113731.277668-1-zilin@seu.edu.cn
Signed-off-by: Zilin Guan <zilin@seu.edu.cn>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fgraph.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index ddedcb50917f..30e3ddc8a8a8 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -833,7 +833,7 @@ static unsigned long __ftrace_return_to_handler(struct fgraph_ret_regs *ret_regs
 #endif
 	{
 		for_each_set_bit(i, &bitmap, sizeof(bitmap) * BITS_PER_BYTE) {
-			struct fgraph_ops *gops = fgraph_array[i];
+			struct fgraph_ops *gops = READ_ONCE(fgraph_array[i]);
 
 			if (gops == &fgraph_stub)
 				continue;
-- 
cgit v1.2.3


From 66611c0475709607f398e2a5d691b1fc72fe9dfc Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 21 Jan 2025 19:44:36 -0500
Subject: fgraph: Remove calltime and rettime from generic operations

The function graph infrastructure is now generic so that kretprobes,
fprobes and BPF can use it. But there is still some leftover logic that
only the function graph tracer itself uses. This is the calculation of the
calltime and return time of the functions. The calculation of the calltime
has been moved into the function graph tracer and those users that need it
so that it doesn't cause overhead to the other users. But the return
function timestamp was still called.

Instead of just moving the taking of the timestamp into the function graph
trace remove the calltime and rettime completely from the ftrace_graph_ret
structure. Instead, move it into the function graph return entry event
structure and this also moves all the calltime and rettime logic out of
the generic fgraph.c code and into the tracing code that uses it.

This has been reported to decrease the overhead by ~27%.

Link: https://lore.kernel.org/all/Z3aSuql3fnXMVMoM@krava/
Link: https://lore.kernel.org/all/173665959558.1629214.16724136597211810729.stgit@devnote2/

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250121194436.15bdf71a@gandalf.local.home
Reported-by: Jiri Olsa <olsajiri@gmail.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ftrace.h               |  2 --
 kernel/trace/fgraph.c                |  1 -
 kernel/trace/trace.h                 |  4 +++-
 kernel/trace/trace_entries.h         |  8 ++++----
 kernel/trace/trace_functions_graph.c | 33 +++++++++++++++++++--------------
 kernel/trace/trace_irqsoff.c         |  5 +++--
 kernel/trace/trace_sched_wakeup.c    |  6 ++++--
 7 files changed, 33 insertions(+), 26 deletions(-)

(limited to 'kernel/trace/fgraph.c')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 07092dfb21a4..fbabc3d848b3 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1151,8 +1151,6 @@ struct ftrace_graph_ret {
 	int depth;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned int overrun;
-	unsigned long long calltime;
-	unsigned long long rettime;
 } __packed;
 
 struct fgraph_ops;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 9e6b5a71555b..5dddfc2149f6 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -826,7 +826,6 @@ __ftrace_return_to_handler(struct ftrace_regs *fregs, unsigned long frame_pointe
 		return (unsigned long)panic;
 	}
 
-	trace.rettime = trace_clock_local();
 	if (fregs)
 		ftrace_regs_set_instruction_pointer(fregs, ret);
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 04058a9889b7..2742d14df383 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -912,7 +912,9 @@ extern int __trace_graph_retaddr_entry(struct trace_array *tr,
 				unsigned long retaddr);
 extern void __trace_graph_return(struct trace_array *tr,
 				 struct ftrace_graph_ret *trace,
-				 unsigned int trace_ctx);
+				 unsigned int trace_ctx,
+				 u64 calltime, u64 rettime);
+
 extern void init_array_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
 extern int allocate_fgraph_ops(struct trace_array *tr, struct ftrace_ops *ops);
 extern void free_fgraph_ops(struct trace_array *tr);
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index 82fd174ebbe0..fbfb396905a6 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -124,8 +124,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 		__field_packed(	unsigned long,	ret,		retval	)
 		__field_packed(	int,		ret,		depth	)
 		__field_packed(	unsigned int,	ret,		overrun	)
-		__field_packed(	unsigned long long, ret,	calltime)
-		__field_packed(	unsigned long long, ret,	rettime	)
+		__field(unsigned long long,	calltime		)
+		__field(unsigned long long,	rettime			)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d retval: %lx",
@@ -146,8 +146,8 @@ FTRACE_ENTRY_PACKED(funcgraph_exit, ftrace_graph_ret_entry,
 		__field_packed(	unsigned long,	ret,		func	)
 		__field_packed(	int,		ret,		depth	)
 		__field_packed(	unsigned int,	ret,		overrun	)
-		__field_packed(	unsigned long long, ret,	calltime)
-		__field_packed(	unsigned long long, ret,	rettime	)
+		__field(unsigned long long,	calltime		)
+		__field(unsigned long long,	rettime			)
 	),
 
 	F_printk("<-- %ps (%d) (start: %llx  end: %llx) over: %d",
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index dc62eb93837a..54d850997c0a 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -266,12 +266,10 @@ __trace_graph_function(struct trace_array *tr,
 	struct ftrace_graph_ret ret = {
 		.func     = ip,
 		.depth    = 0,
-		.calltime = time,
-		.rettime  = time,
 	};
 
 	__trace_graph_entry(tr, &ent, trace_ctx);
-	__trace_graph_return(tr, &ret, trace_ctx);
+	__trace_graph_return(tr, &ret, trace_ctx, time, time);
 }
 
 void
@@ -283,8 +281,9 @@ trace_graph_function(struct trace_array *tr,
 }
 
 void __trace_graph_return(struct trace_array *tr,
-				struct ftrace_graph_ret *trace,
-				unsigned int trace_ctx)
+			  struct ftrace_graph_ret *trace,
+			  unsigned int trace_ctx,
+			  u64 calltime, u64 rettime)
 {
 	struct ring_buffer_event *event;
 	struct trace_buffer *buffer = tr->array_buffer.buffer;
@@ -296,6 +295,8 @@ void __trace_graph_return(struct trace_array *tr,
 		return;
 	entry	= ring_buffer_event_data(event);
 	entry->ret				= *trace;
+	entry->calltime				= calltime;
+	entry->rettime				= rettime;
 	trace_buffer_unlock_commit_nostack(buffer, event);
 }
 
@@ -317,10 +318,13 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 	struct trace_array_cpu *data;
 	struct fgraph_times *ftimes;
 	unsigned int trace_ctx;
+	u64 calltime, rettime;
 	long disabled;
 	int size;
 	int cpu;
 
+	rettime = trace_clock_local();
+
 	ftrace_graph_addr_finish(gops, trace);
 
 	if (*task_var & TRACE_GRAPH_NOTRACE) {
@@ -334,7 +338,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 
 	handle_nosleeptime(trace, ftimes, size);
 
-	trace->calltime = ftimes->calltime;
+	calltime = ftimes->calltime;
 
 	preempt_disable_notrace();
 	cpu = raw_smp_processor_id();
@@ -342,7 +346,7 @@ void trace_graph_return(struct ftrace_graph_ret *trace,
 	disabled = atomic_read(&data->disabled);
 	if (likely(!disabled)) {
 		trace_ctx = tracing_gen_ctx();
-		__trace_graph_return(tr, trace, trace_ctx);
+		__trace_graph_return(tr, trace, trace_ctx, calltime, rettime);
 	}
 	preempt_enable_notrace();
 }
@@ -367,10 +371,8 @@ static void trace_graph_thresh_return(struct ftrace_graph_ret *trace,
 
 	handle_nosleeptime(trace, ftimes, size);
 
-	trace->calltime = ftimes->calltime;
-
 	if (tracing_thresh &&
-	    (trace->rettime - ftimes->calltime < tracing_thresh))
+	    (trace_clock_local() - ftimes->calltime < tracing_thresh))
 		return;
 	else
 		trace_graph_return(trace, gops, fregs);
@@ -856,7 +858,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
 
 	graph_ret = &ret_entry->ret;
 	call = &entry->graph_ent;
-	duration = graph_ret->rettime - graph_ret->calltime;
+	duration = ret_entry->rettime - ret_entry->calltime;
 
 	func = call->func + iter->tr->text_delta;
 
@@ -1137,11 +1139,14 @@ print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
 }
 
 static enum print_line_t
-print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
+print_graph_return(struct ftrace_graph_ret_entry *retentry, struct trace_seq *s,
 		   struct trace_entry *ent, struct trace_iterator *iter,
 		   u32 flags)
 {
-	unsigned long long duration = trace->rettime - trace->calltime;
+	struct ftrace_graph_ret *trace = &retentry->ret;
+	u64 calltime = retentry->calltime;
+	u64 rettime = retentry->rettime;
+	unsigned long long duration = rettime - calltime;
 	struct fgraph_data *data = iter->private;
 	struct trace_array *tr = iter->tr;
 	unsigned long func;
@@ -1342,7 +1347,7 @@ print_graph_function_flags(struct trace_iterator *iter, u32 flags)
 	case TRACE_GRAPH_RET: {
 		struct ftrace_graph_ret_entry *field;
 		trace_assign_type(field, entry);
-		return print_graph_return(&field->ret, s, entry, iter, flags);
+		return print_graph_return(field, s, entry, iter, flags);
 	}
 	case TRACE_STACK:
 	case TRACE_FN:
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 08786c59d397..7294ad676379 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -223,6 +223,7 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 	unsigned long flags;
 	unsigned int trace_ctx;
 	u64 *calltime;
+	u64 rettime;
 	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
@@ -230,13 +231,13 @@ static void irqsoff_graph_return(struct ftrace_graph_ret *trace,
 	if (!func_prolog_dec(tr, &data, &flags))
 		return;
 
+	rettime = trace_clock_local();
 	calltime = fgraph_retrieve_data(gops->idx, &size);
 	if (!calltime)
 		return;
-	trace->calltime = *calltime;
 
 	trace_ctx = tracing_gen_ctx_flags(flags);
-	__trace_graph_return(tr, trace, trace_ctx);
+	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
 	atomic_dec(&data->disabled);
 }
 
diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c
index f372252dc8bb..af30586f1aea 100644
--- a/kernel/trace/trace_sched_wakeup.c
+++ b/kernel/trace/trace_sched_wakeup.c
@@ -158,6 +158,7 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
 	u64 *calltime;
+	u64 rettime;
 	int size;
 
 	ftrace_graph_addr_finish(gops, trace);
@@ -165,12 +166,13 @@ static void wakeup_graph_return(struct ftrace_graph_ret *trace,
 	if (!func_prolog_preempt_disable(tr, &data, &trace_ctx))
 		return;
 
+	rettime = trace_clock_local();
+
 	calltime = fgraph_retrieve_data(gops->idx, &size);
 	if (!calltime)
 		return;
-	trace->calltime = *calltime;
 
-	__trace_graph_return(tr, trace, trace_ctx);
+	__trace_graph_return(tr, trace, trace_ctx, *calltime, rettime);
 	atomic_dec(&data->disabled);
 
 	preempt_enable_notrace();
-- 
cgit v1.2.3