[PATCH v8 25/35] fprobe: Use ftrace_regs in fprobe exit handler

From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: 2024-02-25 15:19:41
Also in: bpf, lkml
Subsystem: bpf [general] (safe dynamic programs and tools), bpf [security & lsm] (security audit and enforcement using bpf), bpf [tracing], function hooks (ftrace), library code, loongarch, s390 architecture, the rest, tracing, x86 architecture (32-bit and 64-bit) · Maintainers: Alexei Starovoitov, Daniel Borkmann, Andrii Nakryiko, Eduard Zingerman, Kumar Kartikeya Dwivedi, KP Singh, Matt Bobrowski, Song Liu, Steven Rostedt, Masami Hiramatsu, Andrew Morton, Huacai Chen, Heiko Carstens, Vasily Gorbik, Alexander Gordeev, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen

From: Masami Hiramatsu (Google) <mhiramat@kernel.org>

Change the fprobe exit handler to use ftrace_regs structure instead of
pt_regs. This also introduce HAVE_PT_REGS_TO_FTRACE_REGS_CAST which means
the ftrace_regs's memory layout is equal to the pt_regs so that those are
able to cast. Fprobe introduces a new dependency with that.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
  Changes in v3:
   - Use ftrace_regs_get_return_value()
  Changes from previous series: NOTHING, just forward ported.
---
 arch/loongarch/Kconfig          |    1 +
 arch/s390/Kconfig               |    1 +
 arch/x86/Kconfig                |    1 +
 include/linux/fprobe.h          |    2 +-
 include/linux/ftrace.h          |    6 ++++++
 kernel/trace/Kconfig            |    8 ++++++++
 kernel/trace/bpf_trace.c        |    6 +++++-
 kernel/trace/fprobe.c           |    3 ++-
 kernel/trace/trace_fprobe.c     |    6 +++++-
 lib/test_fprobe.c               |    6 +++---
 samples/fprobe/fprobe_example.c |    2 +-
 11 files changed, 34 insertions(+), 8 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index d0f17f81451a..b1c5e12d4e64 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig

@@ -112,6 +112,7 @@ config LOONGARCH
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_PT_REGS_TO_FTRACE_REGS_CAST
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EBPF_JIT

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index d78d047047cb..b6271753c31b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig

@@ -167,6 +167,7 @@ config S390
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS
+	select HAVE_PT_REGS_TO_FTRACE_REGS_CAST
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_EBPF_JIT if HAVE_MARCH_Z196_FEATURES

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e7eb605696bc..6d1566822a7b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig

@@ -213,6 +213,7 @@ config X86
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS	if X86_64
+	select HAVE_PT_REGS_TO_FTRACE_REGS_CAST	if X86_64
 	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_SAMPLE_FTRACE_DIRECT	if X86_64
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 36c0595f7b93..879a30956009 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h

@@ -38,7 +38,7 @@ struct fprobe {
 			     unsigned long ret_ip, struct ftrace_regs *regs,
 			     void *entry_data);
 	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
+			     unsigned long ret_ip, struct ftrace_regs *fregs,
 			     void *entry_data);
 };

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 96b42f994c2f..f6b729808ae2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h

@@ -163,6 +163,12 @@ struct ftrace_regs {
 #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
+#ifdef CONFIG_HAVE_PT_REGS_TO_FTRACE_REGS_CAST
+
+static_assert(sizeof(struct pt_regs) == sizeof(struct ftrace_regs));
+
+#endif /* CONFIG_HAVE_PT_REGS_TO_FTRACE_REGS_CAST */
+
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	if (!fregs)

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 0aba53b7b0be..d818ba3ff943 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig

@@ -57,6 +57,13 @@ config HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	 This allows for use of ftrace_regs_get_argument() and
 	 ftrace_regs_get_stack_pointer().
 
+config HAVE_PT_REGS_TO_FTRACE_REGS_CAST
+	bool
+	help
+	 If this is set, the memory layout of the ftrace_regs data structure
+	 is the same as the pt_regs. So the pt_regs is possible to be casted
+	 to ftrace_regs.
+
 config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	bool
 	help

@@ -288,6 +295,7 @@ config FPROBE
 	bool "Kernel Function Probe (fprobe)"
 	depends on FUNCTION_TRACER
 	depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
+	depends on HAVE_PT_REGS_TO_FTRACE_REGS_CAST || !HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	depends on HAVE_RETHOOK
 	select RETHOOK
 	default n

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 2f04777330e0..115c4166ac00 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c

@@ -2823,10 +2823,14 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long fentry_ip,
 
 static void
 kprobe_multi_link_exit_handler(struct fprobe *fp, unsigned long fentry_ip,
-			       unsigned long ret_ip, struct pt_regs *regs,
+			       unsigned long ret_ip, struct ftrace_regs *fregs,
 			       void *data)
 {
 	struct bpf_kprobe_multi_link *link;
+	struct pt_regs *regs = ftrace_get_regs(fregs);
+
+	if (!regs)
+		return;
 
 	link = container_of(fp, struct bpf_kprobe_multi_link, fp);
 	kprobe_multi_link_prog_run(link, get_entry_ip(fentry_ip), regs);

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index a932c3a79e8f..31210423efc3 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c

@@ -124,6 +124,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
 {
 	struct fprobe *fp = (struct fprobe *)data;
 	struct fprobe_rethook_node *fpr;
+	struct ftrace_regs *fregs = (struct ftrace_regs *)regs;
 	int bit;
 
 	if (!fp || fprobe_disabled(fp))

@@ -141,7 +142,7 @@ static void fprobe_exit_handler(struct rethook_node *rh, void *data,
 		return;
 	}
 
-	fp->exit_handler(fp, fpr->entry_ip, ret_ip, regs,
+	fp->exit_handler(fp, fpr->entry_ip, ret_ip, fregs,
 			 fp->entry_data_size ? (void *)fpr->data : NULL);
 	ftrace_test_recursion_unlock(bit);
 }

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index ef6b36fd05ae..3982626c82e6 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c

@@ -341,10 +341,14 @@ static int fentry_dispatcher(struct fprobe *fp, unsigned long entry_ip,
 NOKPROBE_SYMBOL(fentry_dispatcher);
 
 static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip,
-			     unsigned long ret_ip, struct pt_regs *regs,
+			     unsigned long ret_ip, struct ftrace_regs *fregs,
 			     void *entry_data)
 {
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+	struct pt_regs *regs = ftrace_get_regs(fregs);
+
+	if (!regs)
+		return;
 
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
 		fexit_trace_func(tf, entry_ip, ret_ip, regs);

diff --git a/lib/test_fprobe.c b/lib/test_fprobe.c
index ff607babba18..271ce0caeec0 100644
--- a/lib/test_fprobe.c
+++ b/lib/test_fprobe.c

@@ -59,9 +59,9 @@ static notrace int fp_entry_handler(struct fprobe *fp, unsigned long ip,
 
 static notrace void fp_exit_handler(struct fprobe *fp, unsigned long ip,
 				    unsigned long ret_ip,
-				    struct pt_regs *regs, void *data)
+				    struct ftrace_regs *fregs, void *data)
 {
-	unsigned long ret = regs_return_value(regs);
+	unsigned long ret = ftrace_regs_get_return_value(fregs);
 
 	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	if (ip != target_ip) {

@@ -89,7 +89,7 @@ static notrace int nest_entry_handler(struct fprobe *fp, unsigned long ip,
 
 static notrace void nest_exit_handler(struct fprobe *fp, unsigned long ip,
 				      unsigned long ret_ip,
-				      struct pt_regs *regs, void *data)
+				      struct ftrace_regs *fregs, void *data)
 {
 	KUNIT_EXPECT_FALSE(current_test, preemptible());
 	KUNIT_EXPECT_EQ(current_test, ip, target_nest_ip);

diff --git a/samples/fprobe/fprobe_example.c b/samples/fprobe/fprobe_example.c
index 1545a1aac616..d476d1f07538 100644
--- a/samples/fprobe/fprobe_example.c
+++ b/samples/fprobe/fprobe_example.c

@@ -67,7 +67,7 @@ static int sample_entry_handler(struct fprobe *fp, unsigned long ip,
 }
 
 static void sample_exit_handler(struct fprobe *fp, unsigned long ip,
-				unsigned long ret_ip, struct pt_regs *regs,
+				unsigned long ret_ip, struct ftrace_regs *regs,
 				void *data)
 {
 	unsigned long rip = ret_ip;

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help