fprobe: Rewrite fprobe on function-graph tracer

Rewrite fprobe implementation on function-graph tracer.
Major API changes are:
 -  'nr_maxactive' field is deprecated.
 -  This depends on CONFIG_DYNAMIC_FTRACE_WITH_ARGS or
    !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS, and
    CONFIG_HAVE_FUNCTION_GRAPH_FREGS. So currently works only
    on x86_64.
 -  Currently the entry size is limited in 15 * sizeof(long).
 -  If there is too many fprobe exit handler set on the same
    function, it will fail to probe.

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Heiko Carstens <hca@linux.ibm.com> # s390
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: Heiko Carstens <hca@linux.ibm.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: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@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>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/173519003970.391279.14406792285453830996.stgit@devnote2
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>

Author: mhiramat

arch/arm64/include/asm/ftrace.h

@@ -135,6 +135,12 @@ ftrace_regs_get_frame_pointer(const struct ftrace_regs *fregs)
 	return arch_ftrace_regs(fregs)->fp;
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->lr;
+}
+
 static __always_inline struct pt_regs *
 ftrace_partial_regs(const struct ftrace_regs *fregs, struct pt_regs *regs)
 {

arch/loongarch/include/asm/ftrace.h

@@ -61,6 +61,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs, unsigned long ip)
 #define ftrace_regs_get_frame_pointer(fregs) \
 	(arch_ftrace_regs(fregs)->regs.regs[22])
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return *(unsigned long *)(arch_ftrace_regs(fregs)->regs.regs[1]);
+}
+
 #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);

arch/powerpc/include/asm/ftrace.h

@@ -57,6 +57,12 @@ ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
 	regs_set_return_ip(&arch_ftrace_regs(fregs)->regs, ip);
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.link;
+}
+
 struct ftrace_ops;
 
 #define ftrace_graph_func ftrace_graph_func

arch/riscv/include/asm/ftrace.h

@@ -186,6 +186,11 @@ static __always_inline unsigned long ftrace_regs_get_return_value(const struct f
 	return arch_ftrace_regs(fregs)->a0;
 }
 
+static __always_inline unsigned long ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->ra;
+}
+
 static __always_inline void ftrace_regs_set_return_value(struct ftrace_regs *fregs,
 							 unsigned long ret)
 {

arch/s390/include/asm/ftrace.h

@@ -77,6 +77,12 @@ ftrace_regs_get_frame_pointer(struct ftrace_regs *fregs)
 	return ftrace_regs_get_stack_pointer(fregs);
 }
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(const struct ftrace_regs *fregs)
+{
+	return arch_ftrace_regs(fregs)->regs.gprs[14];
+}
+
 #define arch_ftrace_fill_perf_regs(fregs, _regs)	 do {		\
 		(_regs)->psw.mask = 0;					\
 		(_regs)->psw.addr = arch_ftrace_regs(fregs)->regs.psw.addr;		\

arch/x86/include/asm/ftrace.h

@@ -58,6 +58,12 @@ arch_ftrace_get_regs(struct ftrace_regs *fregs)
 	do { arch_ftrace_regs(fregs)->regs.ip = (_ip); } while (0)
 
 
+static __always_inline unsigned long
+ftrace_regs_get_return_address(struct ftrace_regs *fregs)
+{
+	return *(unsigned long *)ftrace_regs_get_stack_pointer(fregs);
+}
+
 struct ftrace_ops;
 #define ftrace_graph_func ftrace_graph_func
 void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,

include/linux/fprobe.h

@@ -5,10 +5,11 @@
 
 #include <linux/compiler.h>
 #include <linux/ftrace.h>
-#include <linux/rethook.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/slab.h>
 
 struct fprobe;
-
 typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip,
 			       unsigned long ret_ip, struct ftrace_regs *regs,
 			       void *entry_data);
@@ -17,35 +18,57 @@ typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip,
 			       unsigned long ret_ip, struct ftrace_regs *regs,
 			       void *entry_data);
 
+/**
+ * struct fprobe_hlist_node - address based hash list node for fprobe.
+ *
+ * @hlist: The hlist node for address search hash table.
+ * @addr: One of the probing address of @fp.
+ * @fp: The fprobe which owns this.
+ */
+struct fprobe_hlist_node {
+	struct hlist_node	hlist;
+	unsigned long		addr;
+	struct fprobe		*fp;
+};
+
+/**
+ * struct fprobe_hlist - hash list nodes for fprobe.
+ *
+ * @hlist: The hlist node for existence checking hash table.
+ * @rcu: rcu_head for RCU deferred release.
+ * @fp: The fprobe which owns this fprobe_hlist.
+ * @size: The size of @array.
+ * @array: The fprobe_hlist_node for each address to probe.
+ */
+struct fprobe_hlist {
+	struct hlist_node		hlist;
+	struct rcu_head			rcu;
+	struct fprobe			*fp;
+	int				size;
+	struct fprobe_hlist_node	array[] __counted_by(size);
+};
+
 /**
  * struct fprobe - ftrace based probe.
- * @ops: The ftrace_ops.
+ *
  * @nmissed: The counter for missing events.
  * @flags: The status flag.
- * @rethook: The rethook data structure. (internal data)
  * @entry_data_size: The private data storage size.
- * @nr_maxactive: The max number of active functions.
+ * @nr_maxactive: The max number of active functions. (*deprecated)
  * @entry_handler: The callback function for function entry.
  * @exit_handler: The callback function for function exit.
+ * @hlist_array: The fprobe_hlist for fprobe search from IP hash table.
  */
 struct fprobe {
-#ifdef CONFIG_FUNCTION_TRACER
-	/*
-	 * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too.
-	 * But user of fprobe may keep embedding the struct fprobe on their own
-	 * code. To avoid build error, this will keep the fprobe data structure
-	 * defined here, but remove ftrace_ops data structure.
-	 */
-	struct ftrace_ops	ops;
-#endif
 	unsigned long		nmissed;
 	unsigned int		flags;
-	struct rethook		*rethook;
 	size_t			entry_data_size;
 	int			nr_maxactive;
 
 	fprobe_entry_cb entry_handler;
 	fprobe_exit_cb  exit_handler;
+
+	struct fprobe_hlist	*hlist_array;
 };
 
 /* This fprobe is soft-disabled. */
@@ -121,4 +144,9 @@ static inline void enable_fprobe(struct fprobe *fp)
 		fp->flags &= ~FPROBE_FL_DISABLED;
 }
 
+/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */
+#define FPROBE_DATA_SIZE_BITS		4
+#define MAX_FPROBE_DATA_SIZE_WORD	((1L << FPROBE_DATA_SIZE_BITS) - 1)
+#define MAX_FPROBE_DATA_SIZE		(MAX_FPROBE_DATA_SIZE_WORD * sizeof(long))
+
 #endif

kernel/trace/Kconfig

@@ -307,11 +307,9 @@ config DYNAMIC_FTRACE_WITH_ARGS
 
 config FPROBE
 	bool "Kernel Function Probe (fprobe)"
-	depends on FUNCTION_TRACER
-	depends on DYNAMIC_FTRACE_WITH_REGS || DYNAMIC_FTRACE_WITH_ARGS
-	depends on HAVE_FTRACE_REGS_HAVING_PT_REGS || !HAVE_DYNAMIC_FTRACE_WITH_ARGS
-	depends on HAVE_RETHOOK
-	select RETHOOK
+	depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC
+	depends on DYNAMIC_FTRACE_WITH_ARGS
+	select FUNCTION_GRAPH_TRACER
 	default n
 	help
 	  This option enables kernel function probe (fprobe) based on ftrace.