ftrace: Introduce FTRACE_OPS_FL_JMP

For now, the "nop" will be replaced with a "call" instruction when a
function is hooked by the ftrace. However, sometimes the "call" can break
the RSB and introduce extra overhead. Therefore, introduce the flag
FTRACE_OPS_FL_JMP, which indicate that the ftrace_ops should be called
with a "jmp" instead of "call". For now, it is only used by the direct
call case.

When a direct ftrace_ops is marked with FTRACE_OPS_FL_JMP, the last bit of
the ops->direct_call will be set to 1. Therefore, we can tell if we should
use "jmp" for the callback in ftrace_call_replace().

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Link: https://lore.kernel.org/r/20251118123639.688444-2-dongml2@chinatelecom.cn
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/ftrace.h

@@ -359,6 +359,7 @@ enum {
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
 	FTRACE_OPS_FL_SUBOP			= BIT(18),
 	FTRACE_OPS_FL_GRAPH			= BIT(19),
+	FTRACE_OPS_FL_JMP			= BIT(20),
 };
 
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -577,6 +578,38 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 						 unsigned long addr) { }
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return addr & 1;
+}
+
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr | 1UL;
+}
+
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr & ~1UL;
+}
+#else
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return false;
+}
+
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr;
+}
+
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_JMP */
+
 #ifdef CONFIG_STACK_TRACER
 
 int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,

kernel/trace/Kconfig

@@ -80,6 +80,12 @@ config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	  If the architecture generates __patchable_function_entries sections
 	  but does not want them included in the ftrace locations.
 
+config HAVE_DYNAMIC_FTRACE_WITH_JMP
+	bool
+	help
+	  If the architecture supports to replace the __fentry__ with a
+	  "jmp" instruction.
+
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -330,6 +336,12 @@ config DYNAMIC_FTRACE_WITH_ARGS
 	depends on DYNAMIC_FTRACE
 	depends on HAVE_DYNAMIC_FTRACE_WITH_ARGS
 
+config DYNAMIC_FTRACE_WITH_JMP
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+	depends on HAVE_DYNAMIC_FTRACE_WITH_JMP
+
 config FPROBE
 	bool "Kernel Function Probe (fprobe)"
 	depends on HAVE_FUNCTION_GRAPH_FREGS && HAVE_FTRACE_GRAPH_FUNC

kernel/trace/ftrace.c

@@ -5951,7 +5951,8 @@ static void remove_direct_functions_hash(struct ftrace_hash *hash, unsigned long
 	for (i = 0; i < size; i++) {
 		hlist_for_each_entry(entry, &hash->buckets[i], hlist) {
 			del = __ftrace_lookup_ip(direct_functions, entry->ip);
-			if (del && del->direct == addr) {
+			if (del && ftrace_jmp_get(del->direct) ==
+				   ftrace_jmp_get(addr)) {
 				remove_hash_entry(direct_functions, del);
 				kfree(del);
 			}
@@ -6016,8 +6017,15 @@ int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 	if (ftrace_hash_empty(hash))
 		return -EINVAL;
 
+	/* This is a "raw" address, and this should never happen. */
+	if (WARN_ON_ONCE(ftrace_is_jmp(addr)))
+		return -EINVAL;
+
 	mutex_lock(&direct_mutex);
 
+	if (ops->flags & FTRACE_OPS_FL_JMP)
+		addr = ftrace_jmp_set(addr);
+
 	/* Make sure requested entries are not already registered.. */
 	size = 1 << hash->size_bits;
 	for (i = 0; i < size; i++) {
@@ -6138,6 +6146,13 @@ __modify_ftrace_direct(struct ftrace_ops *ops, unsigned long addr)
 
 	lockdep_assert_held_once(&direct_mutex);
 
+	/* This is a "raw" address, and this should never happen. */
+	if (WARN_ON_ONCE(ftrace_is_jmp(addr)))
+		return -EINVAL;
+
+	if (ops->flags & FTRACE_OPS_FL_JMP)
+		addr = ftrace_jmp_set(addr);
+
 	/* Enable the tmp_ops to have the same functions as the direct ops */
 	ftrace_ops_init(&tmp_ops);
 	tmp_ops.func_hash = ops->func_hash;